WO2004054246A1 - 情報処理装置および情報処理方法、記録媒体、並びにプログラム - Google Patents
情報処理装置および情報処理方法、記録媒体、並びにプログラム Download PDFInfo
- Publication number
- WO2004054246A1 WO2004054246A1 PCT/JP2003/015926 JP0315926W WO2004054246A1 WO 2004054246 A1 WO2004054246 A1 WO 2004054246A1 JP 0315926 W JP0315926 W JP 0315926W WO 2004054246 A1 WO2004054246 A1 WO 2004054246A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- vector
- program
- user
- preference
- Prior art date
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/08—Systems for the simultaneous or sequential transmission of more than one television signal, e.g. additional information signals, the signals occupying wholly or partially the same frequency band, e.g. by time division
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/235—Processing of additional data, e.g. scrambling of additional data or processing content descriptors
- H04N21/2353—Processing of additional data, e.g. scrambling of additional data or processing content descriptors specifically adapted to content descriptors, e.g. coding, compressing or processing of metadata
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
- H04N21/4334—Recording operations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/44—Receiver circuitry for the reception of television signals according to analogue transmission standards
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
- H04N5/78—Television signal recording using magnetic recording
- H04N5/782—Television signal recording using magnetic recording on tape
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/41—Structure of client; Structure of client peripherals
- H04N21/426—Internal components of the client ; Characteristics thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
- H04N5/765—Interface circuits between an apparatus for recording and another apparatus
- H04N5/775—Interface circuits between an apparatus for recording and another apparatus between a recording apparatus and a television receiver
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
- H04N5/78—Television signal recording using magnetic recording
- H04N5/781—Television signal recording using magnetic recording on disks or drums
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
- H04N5/84—Television signal recording using optical recording
- H04N5/85—Television signal recording using optical recording on discs or drums
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
- H04N5/907—Television signal recording using static stores, e.g. storage tubes or semiconductor memories
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S707/00—Data processing: database and file management or data structures
- Y10S707/99931—Database or file accessing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
- Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y10S707/00—Data processing: database and file management or data structures
- Y10S707/99931—Database or file accessing
- Y10S707/99933—Query processing, i.e. searching
- Y10S707/99934—Query formulation, input preparation, or translation
Definitions
- the present invention relates to an information processing apparatus, an information processing method, a recording medium, and a program, and particularly to a user who watches a program such as a television broadcast or a radio broadcast, streaming data, and the like.
- the present invention relates to an information processing apparatus and an information processing method, a recording medium, and a program that are suitable for use in recommending programs and programs.
- program information program metadata
- EPG electronic program guide
- the method of recommending a program to a user differs depending on the method of acquiring user preference data. For example, an initial interest registration method in which information on a user's interest is initially registered, and a program is recommended based on the information, There is a viewing history usage method that recommends programs using the history of programs viewed in the past, or a collaborative filtering method that recommends programs using the viewing histories of other users. Was.
- the user can enter, for example, a favorite program category (eg, drama, variety, etc.), a favorite genre (inference, comedy, etc.), or a favorite talent name.
- a favorite program category eg, drama, variety, etc.
- a favorite genre inference, comedy, etc.
- a favorite talent name is obtained by matching with the program metadata using these information as keywords.
- the watched program metadata is stored every time the user views the program.
- the data is analyzed to obtain information such as, for example, favorite program categories, favorite genres, or favorite talent names.
- the program name to be recommended can be obtained.
- HDD hard disk drive
- user operations such as recording reservation or recording are accumulated as history information, which may be used to acquire preference information.
- history information which may be used to acquire preference information.
- the user was not watching the program with particular interest, but was watching the program because he had a television receiver or radio. It is possible to distinguish some of the programs that are interested and consciously watched, and acquire information that reflects the user's preferences.
- the viewing history of the first user is matched with the viewing histories of other users, so that the viewing history is similar to that of the first user.
- searching for the second user and acquiring the history data of the viewing or operation the programs that the second user has watched and the programs that the first user has not watched are extracted and recommended. Is what you do.
- an n-dimensional attribute vector is added to the broadcast program in advance as program attribute information, and the initial registration contents of the user, the attribute of the program that the user has reproduced or recorded for recording, and the attribute items of each attribute of the vector are set.
- There is a technology that can select a program to be recorded or a program to be played back by comparing a selection vector generated based on an average value with an attribute vector for example, And Japanese Patent Application Laid-Open No. 2001-16955).
- a program when a program is selected by simply using the total or average of metadata collected based on the user's viewing history, such as a history utilization method, if the history is not accumulated to some extent, It is not possible to recommend programs that match the user's preferences correctly. Furthermore, in the history use method, the relationship between metadata was lost, and sufficient personalization was not possible. Also, by accumulating the history, items that tend to overlap as a history (such as genres) (items that are likely to be detected as being preferred by the user), and items such as performers whose elements tend to spread as a history (such as those that the user prefers) The weighting may be biased.
- a broadcast program is added with a program attribute vector in advance, so that the initial registration contents of the user and the reproduction and reproduction of the user can be performed.
- the program to be recorded or played back by comparing the selected vector generated based on the average value of each attribute item of the attribute vector of the program reserved for recording with the attribute vector.
- performer B who frequently appears in dramas though he is not a favorite actor, overlaps history as comedian A who rarely appears in dramas. Therefore, the documentary starring performer B who frequently appears in the drama will be recommended over the variety starring Comedy A.
- the present invention has been made in view of such a situation, and it is an object of the present invention to be able to select a program that matches a user's preference.
- An information processing apparatus includes: an attribute information acquisition unit that acquires attribute information of a content; an operation history acquisition unit that acquires an operation history of a user; and an operation history acquired by the operation history acquisition unit.
- First preference information indicating a positive factor of preference preference information generating means for generating second preference information indicating a negative factor of user preference, similarity between the first preference information and attribute information
- a recommendation information generating means for independently calculating the similarity between the second preference information and the attribute information to generate recommendation information indicating content recommended for viewing by the user.
- the first preference information and the second preference information generated by the preference information generating means, and the attribute information obtained by the attribute information obtaining means are each composed of a plurality of items.
- the first preference information and the second preference information can be generated for each element of the focused item by focusing on one of the items of the operation history acquired by the means. Can extract the first preference information and the second preference information corresponding to the element of the attribute information, and calculate the degree of similarity with the attribute information.
- the recommendation information generating means may generate the content having a low similarity in any of the contents. Can be generated.
- the first preference information and the second preference information generated by the preference information generating means, and the attribute information obtained by the attribute information obtaining means, are assumed to be solid for each predetermined item. Can be.
- Normalization processing means for normalizing at least a part of the content attribute information and at least one of the first preference information and the second preference information for each item may be further provided.
- the means include: calculating the similarity between the attribute information of the content, which is at least partially normalized by the normalization processing means, and the first preference information and the second preference information; Can be generated.
- the recommendation information generating means includes the recommendation information based on the inner product operation of the first preference information and the second preference information generated by the preference information generation means and the attribute information acquired by the attribute information acquisition means. Can be generated.
- the predetermined item may be composed of a large item and a small item that classifies the large item in more detail.
- the recommended information generating means includes a first preference generated by the preference information generating means.
- the second preference information and the attribute information obtained by the attribute information obtaining means are calculated for inner items for each major item, and recommendation information is generated based on the sum of the inner product calculation results.
- the operation history acquisition means classifies the acquired operation history into a first operation history indicating content that the user prefers and a second operation history indicating content that the user does not like.
- the preference information generating means can generate the first preference information based on the first operation history, and can generate the second preference information based on the second operation history. Is generated.
- the recommendation information generating means includes a second preference generated by the preference information generating means based on a similarity between the first preference information generated by the preference information generating means and the attribute information obtained by the attribute information obtaining means.
- Recommendation information can be generated based on a value obtained by subtracting the degree of similarity between the information and the attribute information obtained by the attribute information obtaining means.
- a display means for displaying the recommendation information generated by the recommendation information generating means can be further provided.
- the information processing apparatus may further include a receiving unit that receives the content, and a selection control unit that controls selection of content received by the receiving unit based on the recommendation information generated by the recommendation information generating unit.
- Recording means for recording the content selected to be received by the selection control means can be further provided.
- An information processing method includes: an operation history acquisition step of acquiring a user operation history; and a first operation history indicating a positive factor of a user preference based on the operation history acquired by the operation history acquisition step.
- a preference information, a preference information generating step of generating second preference information indicating a negative factor of the user's preference, a similarity between the first preference information and the attribute information, and a second preference information and the attribute A recommendation information generating step of calculating recommendation information indicating content matching the user's preference by independently calculating the similarity with the information.
- the program recorded on the recording medium of the present invention comprises: an operation history acquisition step of acquiring a user operation history; and a positive factor of the user's preference based on the operation history acquired by the operation history acquisition step.
- a first preference information indicating a negative factor of the user's preference; a preference information generating step of generating second preference information; a similarity between the first preference information and the attribute information; The similarity between preference information and attribute information 3 015926
- the program according to the present invention includes: an operation history acquisition step for acquiring a user operation history; and first preference information indicating a positive factor of the user's preference based on the operation history acquired by the operation history acquisition step.
- first preference information indicating a positive factor of the user's preference, and a negative factor of the user's preference. Is generated, and the similarity between the first preference information and the attribute information and the similarity between the second preference information and the attribute information are calculated independently. Recommendation information indicating content recommended for viewing by the user is generated.
- FIG. 1 is a diagram illustrating television program broadcasting and distribution of stream data.
- FIG. 2 is a block diagram showing the configuration of the distribution server of FIG.
- FIG. 3 is a flowchart illustrating the program vector generation processing 1.
- FIG. 4 is a diagram illustrating EPG data.
- FIG. 5 is a diagram for explaining a program vector.
- FIG. 6 is a flowchart illustrating the program vector generation processing 2.
- FIG. 7 is a flowchart illustrating the grouping process 1.
- FIG. 8 is a flowchart illustrating the grouping process 2.
- FIG. 9 is a flowchart illustrating the title grouping process 1.
- FIG. 10 is a flowchart for explaining the title grouping process 2.
- FIG. 11 is a flowchart illustrating title grouping process 3.
- FIG. 12 is a flowchart illustrating title grouping processing 4.
- FIG. 13 is a block diagram showing a configuration of the program recommendation processing device of FIG.
- FIG. 14 is a flowchart illustrating the positive history vector and negative history vector generation processing 1.
- FIG. 15 is a diagram for explaining the normal history vector.
- FIG. 16 is a flowchart illustrating the positive history vector and negative history vector generation processing 2.
- FIG. 17 is a flowchart illustrating the matching process 1.
- FIG. 18 is a flowchart illustrating the matching process 2.
- FIG. 19 is a flowchart illustrating the matching process 3.
- FIG. 20 is a flowchart illustrating the matching process 4.
- FIG. 21 is a flowchart illustrating the matching process 5.
- FIG. 22 is a flowchart illustrating the user-side effect vector generation processing 1.
- FIG. 23 is a flowchart illustrating the user-side effect vector generation processing 2.
- FIG. 24 is a flowchart illustrating the user-side effect vector generation processing 3.
- FIG. 25 is a flowchart illustrating the user-side effect vector generation processing 4.
- FIG. 26 is a flowchart for explaining the first reaction vector generation process on the user side.
- FIG. 27 is a flowchart illustrating the user-side reaction vector generation process 2.
- FIG. 28 is a flowchart illustrating a matching process including group recommendation.
- FIG. 29 is a flowchart illustrating a matching process using a user model.
- FIG. 30 is a flowchart illustrating the exception recommendation process.
- FIG. 31 is a block diagram illustrating a configuration of the television receiver in FIG. 1.
- FIG. 32 is a block diagram illustrating a configuration of the television display device in FIG. 1.
- FIG. 33 is a flowchart illustrating the recommendation information display process.
- FIG. 34 is a flowchart for explaining the automatic channel setting process.
- FIG. 35 is a block diagram showing a configuration of the recording / reproducing apparatus of FIG.
- FIG. 36 is a flowchart illustrating the automatic recording process.
- FIG. 37 is a block diagram illustrating a different configuration example of the distribution server.
- FIG. 38 is a block diagram showing a different configuration example of the program recommendation processing device.
- FIG. 39 is a view for explaining different examples of networks for television program broadcasting and stream data distribution.
- FIG. 40 is a block diagram illustrating a different configuration example of the distribution server. BEST MODE FOR CARRYING OUT THE INVENTION
- the broadcast station 1 transmits a terrestrial program broadcast or a satellite wave program broadcast via the satellite 2.
- the antenna 3 of the television receiver 4 receives a terrestrial or satellite program broadcast.
- the broadcast signal includes an EPG (Electronic Program Guide) as necessary.
- EPG Electronic Program Guide
- the distribution server 5 reads the streaming data from the streaming data database 6 and distributes the streaming data to the television receiver 4 via a network 8 including the Internet and other networks.
- Reads the EPG which is information about the program broadcasted from 1, or metadata containing more detailed information than the EPG, generates a program vector PP for each program, and creates a network along with the EPG data. 8 to the EPG receiving device 9.
- the processing uses the same information as the EPG superimposed on the general broadcast signal. You may do it. If the amount of information of the EPG superimposed on the general broadcast signal is not sufficient information for the processing described below, the processing includes the EPG superimposed on the general broadcast signal. In addition, metadata may be used alone or independently.
- information including metadata is used, and this information is referred to as EPG data. Shall be collectively referred to as
- the EPG receiving device 9 supplies the distributed EPG data to the television receiving device 4. Further, the EPG receiving device 9 supplies the program recommendation processing device 10 with the program vector PP distributed together with the EPG data.
- the television receiving device 4 having a tuner is connected to the television display device 11 having an operation unit or the control signal indicating the selection of a channel supplied from the recording / reproducing device 12 via the antenna 3 based on a control signal. It selects and receives terrestrial or satellite broadcast signals, and receives streaming data from a distribution server 5 via a network 8.
- the television receiver 4 receives the supply of the EPG data from the EPG receiver 9 and supplies the EPG data to the television display device 11 or the recording / reproducing device 12. If the received broadcast wave contains an EPG, the television receiver 4 separates it from the program signal and supplies it to the television display device 11 or the recording / reproducing device 12, respectively. .
- the program recommendation processing device 10 obtains the program vector PP from the EPG receiving device 9 and obtains the operation port from the television display device 11 and the recording / reproducing device 12. It generates recommendation information for recommending a program that matches the user's preference based on the information or the user's operation input, and supplies it to the television display device 11 and the recording / reproducing device 12.
- the television display device 11 displays a broadcast signal supplied from the television receiving device 4 or a reproduced signal supplied from the recording / reproducing device 12 based on a user's operation input, and recommends a program. Based on the recommendation information supplied from the processing device 10, a channel is automatically set or recommended program information is displayed.
- the television display device 11 supplies an operation log, which is an operation history of the user, to the program recommendation processing device 10.
- the recording / reproducing device 12 records the broadcast signal supplied from the television receiver 4 on a mounted recording medium or a built-in recording medium (for example, a hard disk) based on a user's operation input. On the basis of the recommendation information supplied from the program recommendation processing device 10, the broadcast signal supplied from the television receiving device 4 is automatically recorded on a mounted recording medium or a built-in recording medium. Further, the recording / reproducing device 12 reproduces a program recorded on a mounted recording medium or a built-in recording medium, and outputs the program to the television display device 11 for display. Further, the recording / reproducing apparatus 12 supplies an operation log, which is a user's operation history, to the program recommendation processing apparatus 10.
- a mounted recording medium or a built-in recording medium for example, a hard disk
- the EPG receiving device 9, the television receiving device 4, the program recommendation processing device 10, the television display device 11, and the recording / reproducing device 12 have been described as different devices, respectively. It does not have to be configured separately.
- the EPG receiving device 9, the television receiving device 4, and the television display device 11 may be integrally configured as a television receiver 15-1 having a built-in tuner function.
- the recording / reproducing apparatus 12 may be integrally configured to be configured as a television receiver 15-2 having a recording function. It can be said that the recording / reproducing apparatus 12 may be a so-called hard disk recorder having a large-capacity hard disk as a recording medium. Not even.
- the program recommendation processing device 10 is built in a television receiver 15-1 having a built-in tuner function, and can be used as a television receiver 15-3 or a television receiver 1 having a recording function.
- the television receiver 15-5-4 may be built in the 5-2.
- FIG. 2 is a block diagram showing the configuration of the distribution server 5.
- the data acquisition unit 21 acquires data from the metadata database 7 and the streaming data database 6, supplies the data to the data transmission unit 25, and supplies the EPG data to the metadata extraction unit 22. Further, the data acquisition unit 21 executes a process of grouping the EPG data registered in the metadata database 7 according to the contents.
- the metadata extraction unit 22 extracts data necessary to generate the program vector PP from the EPG data supplied from the data acquisition unit 21 and supplies the data to the program vector generation unit 23.
- the program vector generation unit 23 generates a program vector PP based on the metadata, and if necessary, associates the program side effect vector EfPP stored in the data storage unit 24 with The data is supplied to the data transmission unit 25.
- the data storage unit 24 stores the program side effect vector EfPP, which is information necessary for generating the program vector PP, as necessary.
- the characteristics of genres and contents are strong, and in variety programs, the cast elements are strong. Characteristics and dramas are characterized by strong performers and scriptwriters. These characteristics must be used to correctly extract program features. In other words, of the elements that make up the program vector PP, which elements are important in the matching process that is performed to recommend a program that matches the user's preference depends on the genre of the program.
- the program genre of the program is “education 'documentation'”, the important items are not the performers but the contents and titles.
- the program genre is “drama”, the important items are the performer and the writer.
- the data transmission unit 25 includes the EPG data and streaming data supplied from the data acquisition unit 21, the program vector PP supplied from the program vector generation unit 23, and the program side effect vector.
- the EfPP is transmitted to the EPG receiving device 9 or the television receiving device 4 via the network 8.
- a drive 26 is connected to the program vector generation unit 23 as necessary.
- the magnetic disk 31, the optical disk 32, the magneto-optical disk 33, and the semiconductor memory 34 are mounted on the drive 26 as necessary, and data is transferred.
- step S1 the data acquisition unit 21 receives the supply of the EPG data composed of the metadata from the metadata database 7.
- step S2 the metadata extraction unit 22 receives the supply of the EPG data from the data acquisition unit 21 and extracts the metadata required to generate the program vector PP. Output to
- Figure 4 shows an example of metadata. Metadata, for example, as a genre
- Metadata includes the director's name, scriptwriter's name, photographer (photographer), music staff, performers, etc., and the content of this program, such as movie commentary.
- step S3 the program vector generation unit 23 performs a morphological analysis on the title, contents, and the like included in the metadata as necessary, and decomposes the words into words.
- the program vector generation unit 23 uses the title of the movie included in the metadata as a title and breaks it down into three words, “Tokaido”, “Mitani”, and “Kaidan”.
- the program vector generation unit 23, as shown in FIG. 4 in the metadata describes the movie “'59 Shinseiho Style, depicting the world of Mitani Kaidan, famous for its beautiful beauty.
- step S4 the program vector generation section 23 converts each item included in the metadata into a vector, generates a program vector PP, and ends the processing.
- the generated program vector PP is output to the data transmission unit 25 and transmitted to the EPG reception device 9 via the network 8.
- all the detailed elements may be arranged in one column, or they may be separated into large items and then vectorized for each large item.
- Sm ⁇ NNK General, NNK Education, Asia Television, TT S, Buji, TV Japan, Toto, NNK Satellite 1, NNK Satellite 2, WOWO ⁇ , Performers
- the genre Gm ⁇ drama, variety, sports, film, music, children / education, culture / documentation, news / reporting, etc. ⁇
- the genre of the corresponding program is culture / documentation.
- Item values words
- weights numeric values
- Tm (1 Tokaido 1, 1 Mitani 1, 1 Kaidan 1)
- “1 Tokaido 1” means that the frequency of the word “Tokaido” is “1”.
- the program vector PP is generated and transmitted to the EPG receiving device 9.
- the program vector PP generated in this way for example, among the components of the performer Pm, the main star is weighted, and the director is weighted among the components of the script Z original Z production Z production Am, and the program vector is weighted.
- a PP may be generated.
- the program side effect vector EfPP indicating what elements are important for each genre is stored in the data storage unit 24 as the program side effect vector information
- the program side effect vector EfPP is used. Alternatively, it may be transmitted in association with the program vector PP.
- the program side effect EfPP is set corresponding to the major items of the program vector PP.
- steps S11 to S14 processing similar to the processing in steps S1 to S4 described using FIG. 3 is performed.
- the EPG data is supplied from the metadata database 7, and the metadata necessary to generate the program vector PP is extracted from the EPG data, and the title, content, etc. included in the metadata are extracted. Is morphologically analyzed as necessary and decomposed into words. Then, each item included in the metadata is vectorized to generate a program vector PP.
- step S16 the program vector generation unit 23 associates the effect vector EfPP extracted in step S15 with the program vector PP generated in step S14, and ends the processing. Is done.
- a program vector PP is generated, and a program-side effect vector EfPP for weighting important items based on the genre of the program is associated with the program vector PP.
- a program vector PP is generated.For example, by grouping programs according to their attributes, the program vector PP can be accurately created with a small amount of computation. be able to.
- Program grouping can be generated, for example, by serial drama, programs of the same genre in weekly units, and program groups of performers in programming units (13 weeks).
- the grouping process 1 for grouping serial drama will be described below with reference to the flowchart of FIG.
- step S31 the data acquisition unit 21 retrieves the EPG data registered in the metadata database 7 from, for example, the same title, the same broadcasting station, and the broadcast time is the same on weekdays or the same on the same day of the week. Extract programs that meet predetermined conditions (conditions for grouping) such as time.
- step S32 the data acquisition unit 21 groups the extracted programs and attaches a group ID to the EPG data of the corresponding program.
- step S33 the metadata extraction unit 22 has the same group ID, that is, the metadata necessary for generating the program vector of the first broadcast of the program recognized as a serial drama. Is extracted.
- step S34 the program vector generation processing described with reference to FIG. 3 or FIG. 6 is executed.
- step S35 the program vector generation unit 33 fixes the program vector FP of the corresponding group ID to the program vector of the first broadcast, and the process ends. .
- the serial drama is grouped, and the program vector is unified. Further, the group ID and the program vector PP may be stored in the data storage unit 24 in association with each other.
- the content of the first time is the commentary of the whole program, but the content other than the first time is often the commentary of the episode.
- the program vector PP is generated by using the first EPG data to reduce the number of times the program vector generation process is performed. Not only can it be reduced, but it is also possible to more accurately generate a program vector PP that matches the program characteristics.
- FIG. 7 the process of adding the same ID to the EPG data of the serial drama has been described.However, if the EPG data includes information for distinguishing the serial drama in advance, the process of step S31 is performed. By omitting it, the same ID may be added to the EPG of the serial drama with reference to the information for identifying the serial drama included in the EPG data.
- step S51 the data acquisition unit 21 refers to the EPG data registered in the metadata database 7 and adds a cluster code corresponding to the content of the metadata to the EPG data of the program.
- a program that matches the condition of a serial drama, such as the same title, the same broadcasting station, and the broadcast time is the same time on weekdays or the same time on the same day 3 is extracted and the Among the programs that are recognized as dramas, for example, depending on the broadcast time of the serial drama, code 1 for the same time in flat 3, code 2 for the same time on the same day, biweekly, alternate day, etc. If the broadcast time is other than code 1 and code 2, the first cluster code of the smallest digit, such as code 3, is determined. If it is not a serial drama, the first cluster code of the least significant digit is 0.
- the data relating to the genre of the metadata registered in the metadata database 7 is referred to, and for each genre, for example, the second digit (1 0 A second cluster code having a numerical value in the () position is determined.
- the data acquisition unit 21 determines whether or not the corresponding EPG is a serial drama based on whether or not the first digit of the cluster code is 0.
- step S52 If it is determined in step S52 that the drama is a serial drama, in steps S53 and S54, the same processing as in steps S33 and S34 in FIG. 7 is performed. That is, the EPG of the first broadcast is extracted, and the program vector generation processing described with reference to FIG. 3 or FIG. 6 is executed.
- step S55 the program vector generation unit 33 fixes the program vector PP of the serial drama to the program vector PP for the first broadcast, and sets the program vector PP in the program vector PP.
- the generated cluster codes are set in association with each other, and the process ends. If it is determined in step S52 that it is not a serial drama, in step S56, the program vector generation processing described with reference to FIG. 3 or FIG. 6 is executed.
- step S57 the program vector generation unit 33 associates the generated cluster code with the program vector PP and ends the processing.
- the program vector PP is generated as described with reference to FIGS. 3 to 8, so that the program vector PP corresponding to a new term or genre is always generated. Can be generated.
- the generated program vector PP is received by the EPG receiving device 9 via the network 8 together with the EPG data and supplied to the program recommendation processing device 10.
- the grouping process may be performed by morphologically analyzing the title, decomposing the title into words, and attaching a group ID to each word.
- step S61 the data acquisition unit 21 refers to the EPG data registered in the metadata database 7, extracts a title from the registered metadata, and generates a program vector generation unit. 2 to 3
- step S62 the program vector generation unit 23 performs a morphological analysis on the title and breaks it down into words. Specifically, if the title of the movie included in the metadata is “Tokaido Mitani Kaidan”, this will be morphologically analyzed as the title, so the three titles “Tokaido”, “Miya”, and “Kaidan” A word is obtained.
- step S63 the program vector generation unit 23 extracts one of the analyzed word or a group of words composed of a plurality of words, and extracts the word from the data storage unit 24. Then, a group ID corresponding to the extracted word or word group is extracted from.
- the word group composed of a plurality of words is a word group generated by a combination of words obtained by morphological analysis.
- words obtained by morphological analysis include “Tokaido”, “ In the case of "Mitani” and “Kaidan”, the words are “Tokaido ⁇ Mitani”, “Tokaido 'Kaidan” and "Mitani'Kaidan”
- step S64 the program vector generation unit 23 determines whether the corresponding group ID has been extracted from the data storage unit 24.
- step S64 If it is determined in step S64 that the corresponding group ID has not been extracted, the extracted word or a group of words composed of a plurality of words has not yet been assigned a group ID.
- step S65 the program vector generation unit 23 associates a new group ID with the extracted word or a word group including a plurality of words.
- the program vector generation unit 23 stores the word or a word group including a plurality of words and the corresponding group ID in the data storage unit 24.
- step S66 the program The vector generation unit 23 determines whether or not a group ID has been extracted for all the words constituting the title or a word group composed of a plurality of words.
- step S66 If it is determined in step S66 that the group ID has not been extracted for all words constituting the title or for a word group including a plurality of words, the process returns to step S63. Subsequent processing is repeated.
- step S66 if it is determined that the group ID has been extracted for all the words constituting the title or for a group of words composed of a plurality of words, in step S67, the program vector generation unit 2 In step 3, the extracted group ID is associated with the program vector, and the processing ends.
- the words constituting the title or the group ID corresponding to the group of words are associated with the program vector, and the data transmitting unit 25 transmits the television receiving device via the network 8 via the network 8. 4 or transmitted to EPG receiver 9.
- programs with similar titles may be grouped together.
- the title drama “Two Years A Gumi Ginpachi-sensei” and the special program “Two years A Gumi Ginpachi-sensei Special” can be grouped into the same group.
- the word match rate is calculated on a round-robin basis for a program title for a predetermined period, such as two weeks, one month, and six months, and the word match rate is If the value is equal to or greater than the value, they may be in the same group.
- step S401 and step S402 the same processing as step S61 and step S62 described with reference to FIG. 9 is executed. That is, the data acquisition unit 21 refers to the EPG data registered in the metadata database 7, extracts the title information from the registered metadata, and generates a program vector program. The program vector is supplied to the component unit 23, and the program vector generation unit 23 performs morphological analysis on the title and decomposes the title into words.
- step S403 the program vector generation unit 23 calculates the degree of word matching between titles, that is, the matching rate indicating the rate of matching of words, based on the analyzed words.
- step S404 the program vector generation unit 23 determines whether the words match at least a predetermined value such as 70%, for example.
- a predetermined value such as 70%
- the threshold value of the coincidence rate may be any numerical value other than 70%.
- step S404 If it is determined in step S404 that the words match at least a predetermined value such as 70%, in step S405, the program vector generation unit 23 sets the Assign the same group ID to the program.
- the program vector generating unit 2 3, matching words or a word group, the group ID corresponding thereto is stored in the data storage unit 2 4.
- step S404 If it is determined in step S404 that the matching rate is equal to or less than a predetermined value such as 70%, or if the processing in step S405 ends, the program The vector generator 23 determines whether or not the brute force of the title has been completed.
- step S 406 If it is determined in step S 406 that the brute force of the title has not been completed, the process returns to step S 403, and the subsequent processes are repeated.
- step S406 If it is determined in step S406 that the brute force of the title has been completed, the process is terminated.
- the program vector is associated with the group ID based on the matching rate of words constituting the title, and the data transmission unit 25 transmits the television reception device via the network 8 to the television receiver. 4 or the program is transmitted to the EPG receiving device 9, so that programs having similar titles such as a serial drama and a special program can be processed as the same group.
- a broadcast station for example, a broadcast station, a program genre, or a broadcast start time may be added to the grouping condition.
- the title is composed of a small number of words including "news". Therefore, the processing described with reference to FIG.
- the same group since the same group may be detected, the same group may be used if the broadcast stations also match in addition to the word match rate.
- steps S421 to S424 the same processing as steps S401 to S404 described using FIG. 10 is performed. That is, the data acquisition unit 21 refers to the EPG data registered in the metadata database 7, extracts the title from the registered metadata, and supplies the title to the program vector generation unit 23.
- the program vector generation unit 23 morphologically analyzes the title and decomposes the title into words. Then, the program vector generation unit 23, based on the analyzed words, T JP2003 / 015926
- the degree of matching of words between the titles is calculated, and it is determined whether or not the words match at least a predetermined value such as 70%.
- step S424 If it is determined in step S424 that the words match at least a predetermined value such as 70%, in step S425, the program vector generation unit 23 executes the program It is determined whether or not the broadcasting stations are the same.
- step S425 If it is determined in step S425 that the broadcasting stations of these programs match, in step S425, the program vector generation unit 23 assigns the same group ID to those programs. Is associated. Further, the program vector generation unit 23 causes the data storage unit 24 to store the matched word or word group and the corresponding broadcasting station and group ID.
- step S424 If it is determined in step S424 that the match rate is equal to or less than a predetermined value such as 70%, if it is determined in step S425 that the broadcast stations of these programs do not match, Alternatively, after the processing in step S 426 is completed, in step S 427, the program vector generation unit 23 determines whether or not the round robin of the title has been completed.
- a predetermined value such as 70%
- step S 427 If it is determined in step S 427 that the brute force of the title has not been completed, the process returns to step S 423, and the subsequent processes are repeated. If it is determined in step S 427 that the brute force of the title has been completed, the processing is terminated.
- the program vector is associated with the group ID based on the matching rate of the broadcast station and the matching rate of the words constituting the title, and the data transmitting unit 25 transmits the program ID via the network 8. Since it is transmitted to the television receiver 4 or the EPG receiver 9, for example, when programs having similar titles are in the same group, news programs of other stations may be in the same group. Can be prevented.
- the grouping may be executed by using a condition other than the station, for example, a broadcasting time zone or a genre, as a condition other than the matching rate of the words constituting the title.
- the broadcast start time of a serial drama or a band program is shifted due to a sports broadcast or a special program, etc.
- the condition may be determined based on whether or not the broadcast time matches within a predetermined time range such as one hour, for example.
- the grouping is performed based on the matching rate of the words constituting the title, with the condition that the broadcast times match within a predetermined time range or not.
- the title grouping process 4 will be described.
- steps S444 to S444 the same processing as in steps S401 to S404 described with reference to FIG. 10 is executed. That is, the data acquisition unit 21 refers to the EPG data registered in the metadata database 7, extracts a title from the registered metadata, and supplies the title to the program vector generation unit 23.
- the program vector generation unit 23 morphologically analyzes the title and decomposes the title into words. Then, the program vector generation unit 23 calculates the degree of matching between the words based on the analyzed words, and determines whether the words match at least a predetermined value such as 70%, for example. Judge.
- step S444 If it is determined in step S444 that the words match at least a predetermined value such as 70%, in step S445, the program vector generation unit 23 executes It is determined whether or not the broadcast start time of the program is coincident with a shift within a predetermined range such as one hour, for example.
- step S446 determines The same group ID is associated with the program. Also, the program The vector generation unit 23 causes the data storage unit 24 to store the matched word or word group, the corresponding broadcast start time range, and the group ID. If it is determined in step S444 that the matching rate is equal to or less than a predetermined value such as 70%, in step S444, the broadcast start times of those programs are shifted beyond a predetermined range. Is determined, or after the processing in step S446 is completed, in step S444, the program vector generation unit 23 determines whether or not the gross winning of the title has been completed. I do.
- step S444 If it is determined in step S444 that the brute force of the title has not been completed, the process returns to step S444, and the subsequent processes are repeated. If it is determined in step S447 that the brute force of the title has been completed, the processing is terminated.
- the program vector is associated with a match including a deviation within a predetermined range of the broadcast start time and a group ID based on the match rate of words constituting the title, and the data transmission unit 25, the broadcast is transmitted to the television receiver 4 or the EPG receiver 9 via the network 8 so that, for example, when programs having similar titles are in the same group, the broadcast time of a special program or the like As a result, it is possible to prevent programs that should be detected as being in the same group from being detected as being in the same group.
- FIG. 13 is a block diagram showing the configuration of the program recommendation processing device 10.
- the data acquisition unit 41 acquires the program vector PP transmitted from the distribution server 5 and the program-side effect vector EfPP corresponding to the program vector PP.
- the program vector extraction unit 42 converts the program vector PP acquired by the data acquisition unit 41 from the program vector PP required for matching processing or the program vector PP required for user model generation. Is extracted, and if necessary, supplied to the matching processing unit 43 together with the program side effect vector EfPP corresponding to the program vector PP.
- the operation input unit 44 includes input devices such as a keyboard, a touch pad, and a mouse, and is used for initial registration information input by a user and for generating a user model. , And output it to the initial registration storage unit 45.
- the initial registration storage unit 45 registers the initial registration contents supplied from the operation input unit 44 and topics for generating a user model, and, if necessary, the operation log acquisition unit 46 or a matching process. Supply to part 43. Further, the contents stored in the initial registration storage unit 45 are sequentially updated based on a user operation input from the operation input unit 44.
- the information that is initially registered includes, for example, information indicating programs that the user does not like, such as disliked genres, disliked keywords, disliked performers, favorite genres, favorite keywords, favorite performers, etc. There is information indicating programs that the user prefers.
- the operation port acquisition unit 46 acquires operation logs from the television display device 11 or the recording / reproducing device 12, classifies the information into positive history and negative history, and performs initial registration as necessary.
- the program vector PP corresponding to the positive history and the negative history is read out of the program vector PP obtained by the data obtaining unit 41, and is stored in the positive history. It is supplied to section 47 and negative history storage section 48 for storage.
- the correct history storage unit 47 stores the supplied correct history and generates a correct history vector UP.
- the negative history storage unit 48 stores the supplied negative history and generates a negative history vector MUP.
- the generated positive history vector UP and negative history vector MUP are supplied to the matching processing unit 43.
- the correct history is information used to extract program candidates that the user intends to actively watch, in other words, a program that he or she likes, and for example, the user can watch one user program, If the program is recorded, or if a program proposed as a recommended program list to the user by the processing described later is accepted and viewed or recorded by the user, the metadata of the program is recorded as good impression metadata as positive history metadata.
- the main history storage unit 47 calculates the total of the main history for each detailed item or for each major item, and generates the main history vector UP.
- the matching processing unit 43 includes the program vector extracted from the program vector extraction unit 42 and the positive history vector UP supplied from the positive history storage unit 47 or the negative history storage unit 48, or Verify matching with the negative history vector MUP.
- the vector calculation unit 62 performs a matching process between the program vector PP and the positive history vector UP or the negative history vector MUP.
- the vector calculation unit 62 is a program vector PP, positive history vector UP, negative history vector MUP, and a positive history vector when all elements of detailed items are expressed in a single row.
- the program vector PP and the positive history vector are calculated as shown in the following equation (1).
- the degree of similarity Sim UP with the torque UP is calculated, and is expressed by equation (2).
- the similarity SimMUP between the program vector PP and the negative history vector MUP is calculated.
- the cosine distance is a value obtained by dividing the inner product of two vectors by the product of the absolute values of the vectors, as shown in equations (1) and (2).
- PP indicates the program vector PP
- UP indicates the positive history vector UP
- MUP indicates the negative history vector MUP.
- a positive history vector UP ⁇ title Tup, Jan Gup, performer Pup, script / original / production Aup, content (keyword) Kup ⁇ and negative history vector MUP
- Negative history vector MUP ⁇ Ty Tonore Tmup, Giannore G mup, Performer Pmup, Screenplay / Original / Direction Amu P , Content (Keyword) Kttmp ⁇
- the similarity can be obtained for each major item by the same operation as in equation (3), and the similarity SimUP and similarity SimMUP can be calculated using the similarity of the following equation (4). Calculated as Sim.
- c OS 0 t is the cosine distance between the program vector PP and the regular history vector UP or the negative history vector MUP in the major item “Title”
- cos 0 g is The cosine distance between the program vector PP in the item “Genre” and the positive history vector UP or the negative history vector recommendation P
- cos 0 p is the program vector PP in the major item “Performers”.
- cosine distance between the positive history base-vector UP or the negative history base vector MUP is a cosine distance between the positive history base-vector UP or the negative history base vector MUP
- co s 0 a is, in large item "screenwriter / original Z demonstration”
- the cosine distance between the UP or the negative history vector MUP, and cos 0 k is the cosine distance between the program vector PP and the positive history vector UP or the negative history vector MUP in the major item “content”.
- the similarity SimUP and the similarity SimMUP are calculated as the sum of the operation results for each major item, there is no bias in the weight between items, so it is moral to perform normalization. Therefore, unlike the vector in which all elements are arranged in one column, the normalization processing by the normalization processing unit 61 need not be performed.
- the normalization power ⁇ or the sum of the operation results for each major item is calculated as the similarity SimUP and the similarity SiraMUP, so that it is not affected by the magnitude of the history frequency, Commenter A can recommend the variety program on which the performer is performing, and can more accurately reflect the user's preferences.
- the vector calculation unit 62 stores the user's initial registration information stored in the initial registration storage unit 45, the program side effect vector EfPP transmitted in association with the program vector PP, or Weighting is performed by the user side effect vector Ef UP (described later) or the user side effect vector EfMUP (described later) generated and registered in the user information registration unit 63, and the similarity SimUP and the similarity are calculated. It is also possible to calculate SimMUP.
- the vector calculation unit 62 Based on the similarity score SimUP calculated by the above-described method, the vector calculation unit 62 generates, for example, a set of a predetermined number of higher ranks (eg, 10) having a higher similarity score with the positive history vector. On the other hand, the similarity SimMUP with the history vector MUP is further calculated, and SimUP-SimMUP is calculated, and a predetermined number (for example, 3) of programs having higher calculation results are output to the recommended information output unit 49 as recommended programs.
- a predetermined number of higher ranks eg, 10
- the vector calculation unit 62 registers the recommendation priority group in the user information registration unit 63 based on the information of the recommended program, and The program corresponding to the priority group is recommended with priority.
- the vector operation unit 62 generates a user model vector by filtering the program vector PP using the topics stored in the initial registration storage unit 45, and generates the user information registration unit 63 Can be registered to perform the matching process. Details of the user model will be described later.
- the user information registration unit 63 stores the initial registration content of the user supplied from the initial registration storage unit 45 or the positive history vector UP supplied from the positive history storage unit 47 or the negative history storage unit 48. Or user-effect vector based on negative history vector MUP 3 015926
- EfUP is a vector that indicates to the user which of the major items is important for program selection and which is the item that is weighted for program selection. Or a vector indicating the user's preference for each item.
- the reaction vector EfMUP is a vector that indicates which of the large items is an insignificant factor for program selection for the user and is an item that is not weighted for program selection. , Or, for each item, a vector indicating the item that the user does not like.
- the user-side effect vector EfUP and the counter-effect vector EfMUP are all significant factors in matching the program vector PP with the positive history vector UP or the negative history vector MUP. It is specified.
- the user side effect vector EfUP and the counter effect vector EfMUP may be set by the user or may be set to a predetermined value, but are registered in the initial registration storage unit 45. It may be generated based on the initial registration contents of the user.
- the program vector PP (Title T m, genre G m, time zone Hm, broadcast station S m, performer P m, screenplay original / directed Am, content K m ⁇ , if the genre is important to the user, for example, the effect vector EfUP2 (1 , 5, 1, 1, 1, 1, 1, 1, 1). On the other hand, when the performer and the genre are important for the user, for example, the effect vector EfUP is set to (1, 3, 1, 1, 5, 1, 1).
- the user side effect vector EfUP is a vector indicating the user's preference in each item
- the user-side effect vector EfUP and the counter-effect vector EUP are generated based on the positive history vector UP or the negative history vector MUP, or by counting programs watched by the user during a certain period. You may make it. Further, the user-side effect vector EfUP and the counter-effect vector EfMUP can be generated for each genre. A method of generating the user-side effect vector EfUP or the counter-effect vector EfMUP will be described later with reference to FIGS. 22 to 27. Further, the user information registration unit 63 registers the information of the recommended priority group, the user model vector, and the like generated by the processing of the vector calculation unit 62 as necessary.
- programs that are highly similar to the positive history vector UP are used to select programs that the user does not like using the negative history. Even without performing the process of removing (programs that the user is reluctant to view), for example, it is possible to determine a recommended program using only the correct history.
- the recommended information output unit 49 registers the information on the recommended programs supplied from the matching processing unit 43 in the recommended program list 50 and supplies the information to the television display device 11 or the recording / reproducing device 12. I do.
- the recommended program list 50 is configured to be detachable from the program recommendation processing device 10 and registers the recommended program information output from the recommended program output unit 49. By storing recommended program information in the recommended program list 50, for example, even when different television receivers 4, television display devices 11 or recording / reproducing devices 12 are used, Using the accumulated history information, it is possible to recommend programs and perform automatic recording. Further, the matching processing section 43 is connected to the drive 51 as necessary.
- a magnetic disk 71, an optical disk 72, a magneto-optical disk 73, and a semiconductor memory 74 are mounted on the drive 51 as needed to exchange data.
- the positive history vector and negative history vector generation processing 1 executed by the program recommendation processing device 10 will be described.
- step S71 the operation log acquisition unit 46 supplies the initial registration content read from the initial registration storage unit 45 to the negative history storage unit 48.
- the negative history storage unit 48 generates a negative history vector MUP by referring to the supplied initial registration contents.
- step S72 the operation port acquisition unit 46 determines whether the initial registration contents have been changed based on the registration contents stored in the initial registration storage unit 45. If it is determined in step S72 that the initial registration content has been changed, the process returns to step S71, and the subsequent processes are repeated.
- step S73 the operation log acquisition unit 46 transmits the information from the television display device 11 or the recording / reproducing device 12 It is determined whether an operation log has been supplied. If it is determined in step S73 that the operation log has not been supplied, the process returns to step S72, and the subsequent processes are repeated.
- step S74 the operation log acquisition unit 46 determines whether the supplied operation log is a normal history. For example, if the operation log is a recording operation, the program vector PP of the program corresponding to the operation is the normal history, and if the operation log is the deletion of unplayed recorded data, The program vector PP of the corresponding program has a negative history.
- step S74 if the supplied operation log is determined to be the correct history, in step S75, the operation log acquisition unit 46 responds to the operation log determined to be the correct history Pp from the data acquisition unit 41 Supply to the history storage unit 47.
- the main history storage unit 47 additionally stores the supplied program vector PP as a main history.
- step S76 the main history storage unit 47 obtains the sum of the vectors of the main history program vector PP for each detailed item or for each major item, and generates the main history vector UP. After the processing in step S76 ends, the processing returns to step S72, and the subsequent processing is repeated.
- step S77 the operation port
- the program vector PP corresponding to the operation port determined to be the history is extracted from the data acquisition unit 41 and supplied to the negative history storage unit 48.
- the negative history storage unit 48 additionally stores the supplied program vector PP as a negative history.
- step S78 the negative history storage unit 48 obtains the sum of the vectors of the negative history program vector PP for each detailed item or for each major item, and generates a negative history vector .MUP. After the process in step S78 ends, the process returns to step S72, and the subsequent processes are repeated.
- the major items of the positive history vector UP are the title, genre, cast, script Z original / directed, and content (keyword).
- the number of items is described as being smaller than the program vector PP described above, it is needless to say that it may be a large item similar to the program vector PP.
- the negative history vector MUP is generated before the operation log is input based on the contents of the initial registration.
- the registration of the information for selection may be received, and the normal history vector UP may be generated before the operation log is input.
- the positive history vector UP or the negative history vector MUP is not generated, and only the operation log is used to increase the positive history vector or the negative history vector MUP. May be generated.
- the positive history and the negative history may be determined more precisely.
- the positive history vector UP and the negative history vector MUP are calculated using the sum of the program vectors PP corresponding to the positive history and the negative history for all items.
- the total of the program vectors PP corresponding to the positive history and the negative history is accumulated, for example, by genre, and the positive history vector UP and the negative history vector MUP are generated for each genre. Is also good.
- the positive history and the negative history may be accumulated for each performer, and based on this, the positive history vector UP and the negative history vector MUP may be generated for each performer. . In this way, by accumulating histories for specific elements, it is possible to reflect user preferences more precisely without dulling user preferences.
- the matching processing unit 43 verifies the matching between the positive history vector UP and the negative history vector MUP generated in this way and the supplied program vector PP, so that the user's preference is obtained. It is possible to generate recommended program information that correctly reflects the information.
- steps S81 to S84 the same processing as in steps S71 to S74 in FIG. 14 is performed. That is, the initial registration is referred to A history vector MUP is generated and it is determined whether or not the initial registration contents have been changed. If not, it is determined whether or not the supplied operation log is the correct history.
- step S85 the operation log acquisition unit 46 responds to the operation log determined to be the correct history
- the program vector PP is extracted from the data acquisition unit 41 and supplied to the normal history storage unit 47.
- the main history storage unit 47 extracts the genre of the supplied program vector PP.
- step S86 the main history storage unit 47 additionally stores the program vector PP extracted from the data acquisition unit 41 as a main history for each genre.
- step S87 the main history storage unit 47 stores, for each detailed item or for each major item, the total of the vectors of the main history program vector PP in the genre in which the program vector is additionally stored. Then, a positive history vector UP of the corresponding genre is generated. After the processing in step S87 is completed, the processing returns to step S82, and the subsequent processing is repeated.
- step S84 If it is determined in step S84 that the supplied operation log is not a positive history, the supplied operation log is a negative history. Then, the program vector PP corresponding to the operation log determined to be as is extracted from the data acquisition unit 41 and supplied to the negative history storage unit 48. The negative history storage unit 48 extracts the genre of the supplied program vector PP.
- step S89 the negative history storage unit 48 additionally stores the program vector PP extracted from the data acquisition unit 41 as a negative history for each genre.
- step S90 the negative history storage unit 48 stores the program vector of the negative history PP in the genre in which the program vector is additionally stored for each detailed item or for each major item. The sum is calculated, and a negative history vector MUP of the corresponding genre is generated.
- step S90 ends, the processing returns to step S82, and the subsequent processing is repeated.
- a positive history vector UP and a negative history vector MUP are generated for each genre, so that it is possible to more accurately reflect user preferences without dulling user preferences. It is possible to generate recommended program information that accurately reflects the user's preferences.
- the program vector is represented by PP, the positive history vector UP, and the negative history vector MUP.
- the matching process 1 will be described.
- step S101 the program vector extraction unit 42 extracts a program vector PP of a plurality of programs (for example, a program broadcasted in a predetermined time zone) from the data acquisition unit 41, and performs a matching process. This is supplied to the normalization processing section 61 of the section 43.
- the normalization processing unit 61 converts the supplied program vector PP and the regular history beta UP read out from the regular history storage unit 47 into the regularity of the title and content composed of words. Then, the normalized result is supplied to the beta operation unit 62.
- step S102 the vector operation unit 62 of the matching processing unit 43 calculates the cosine distance between the program vector PP of a plurality of programs and the positive history vector UP using the above-described equation (1). Calculate the similarity SiraUP.
- step S103 the vector operation unit 62 compares the similarity SimUP indicating the similarity between the program vector PP and the positive history vector UP calculated in step S102, For example, a predetermined number of program vectors PP such as 10 is extracted from the highest similarity.
- step S104 the vector operation unit 62 includes the program vector PP extracted in step S103 and the negative history vector read from the negative history storage unit 48.
- the similarity SimMUP which is the cosine distance from the torque MUP, is calculated by using the above-described equation (2).
- step S105 the vector calculation unit 62 determines the similarity to the positive history vector UP (that is, the cosine distance) SimMUP—the similarity to the negative history vector (that is, the cosine distance) SimMUP , And a program vector or EPG data of a predetermined number (for example, one) of higher-ranked programs is extracted as recommendation information, output to the recommendation information output unit 49, and a recommended program list 50 Are output to the television display device 11 and the recording / reproducing device 12, and the processing is terminated.
- a program vector or EPG data of a predetermined number (for example, one) of higher-ranked programs is extracted as recommendation information, output to the recommendation information output unit 49, and a recommended program list 50 Are output to the television display device 11 and the recording / reproducing device 12, and the processing is terminated.
- the program vector PP, the positive history vector UP, and the negative history vector MUP power
- the program vector in the case where all the elements of the detailed items are represented by a vector arranged in one line
- the similarity between the Tonore PP and the positive history vector UP and the similarity between the program vector PP and the negative history vector it becomes possible to determine a recommended program that matches the user's preference. .
- step S111 the program vector extraction unit 42 extracts a program vector PP of a plurality of programs (for example, a program broadcasted in a predetermined time zone) from the data acquisition unit 41 and performs matching. This is supplied to the vector operation unit 62 of the processing unit 43.
- the vector calculation unit 62 includes a program vector PP and a main history vector for each of the major items of the supplied program vector PP and the main history vector UP read from the main history storage unit 47. Calculate the cosine distance of UP.
- step S112 the vector computing unit 62 sums up the cosine distance values calculated for each item in step S111 using the above-described equation (4), and calculates the similarity SiraUP. calculate.
- step S113 the vector operation unit 62 compares the similarity SitnUP between the program vector PP and the positive history vector UP calculated in step S112, and For example, a predetermined number of program vectors PP such as 10, for example, is extracted.
- step S114 the vector operation unit 62 receives the program vector PP extracted by the processing in step S113 and the negative history vector MUP read from the negative history storage unit 48. For the items, calculate the cosine distance between the program vector PP and the negative history vector MUP.
- step S115 the vector operation unit 62 sums the values of the cosine distances calculated for each item in step S114 using the above equation (4), and calculates the similarity SimMUP. calculate.
- step S116 the vector calculation unit 62 determines that ⁇ similarity S imUP, which is the cosine distance between the program vector PP and the positive history vector UP ⁇ — ⁇ the similarity between the program vector PP and the negative history vector
- the similarity SimMUP ⁇ which is the cosine distance, is calculated, and the program vectors PP or EPG data of a predetermined number (for example, three) of the higher-order programs are extracted as recommendation information, and output to the recommendation information output unit 49.
- the program is registered in the recommended program list 50, and is output to the television display device 11 and the recording / reproducing device 12, and the process is terminated.
- the sum of the calculation results is calculated as the similarity S imUP and the similarity S imMUP for each of the large items without normalizing the items indicated by the words.
- the similarity between the program vector PP and the positive history vector UP, and the similarity between the program vector PP and the negative history beta request P thus, it becomes possible to determine a recommended program that matches the user's preference.
- the matching process may be performed using the above-described program effect vector EfPP, user effect vector EfUP, or user effect vector EfMUP. Whether or not to use the program side effect vector EfPP, the user side effect vector EfUP, or the user side effect vector EfMUP may be settable by a user.
- step S121 the vector operation unit 62 receives the program effect vector EfPP and the user effect input by the user using the operation input unit 44 and registered in the initial registration storage unit 45. Acquires the usage setting contents of the vector EfUP or the user side reaction vector EfMUP.
- the effect vector usage settings indicate whether or not weighting should be performed using the program side effect vector EfPP, user side effect vector EfUP, or user side effect vector EfMUP in the matching process. Information.
- step S122 the vector calculation unit 62 reads the user-side effect vector EfUP from the user information registration unit 63 as necessary, and calculates the following equation (5). 6
- the user side effect vector EfUP may be set by the user, may be set based on the user's initial settings, or may be generated by the user information registration unit 63. May be. The details of the generation of the user-side effect vector EfUP will be described later with reference to FIGS.
- step S123 the vector calculation unit 62 compares the similarity SimUP between the program vector PP and the positive history vector UP calculated in step S122, and from the highest similarity, For example, a predetermined number of program vectors PP such as 10 are extracted.
- step S124 the vector operation unit 62 reads the user side reaction vector EfMUP, if necessary, from the user information registration unit 63, and
- Equation (6) describes that both the program side effect vector EfPP and the user side effect vector EfMUP are used. However, depending on the setting, the program side effect vector EfMUP is used. If any of EfPP and the user side effect vector EfMUP are not used, the value "1" is substituted for the unused vector and calculated.
- the user side reaction vector EfMUP may be set by the user, may be set based on the user's initial settings, or may be generated by the user information registration unit 63. There may be. Details of generation of the user side reaction vector EfMUP will be described later with reference to FIG. 26 or FIG.
- step S125 the vector calculation unit 62 calculates the similarity SimUP between the program vector PP and the positive history vector SimUP—the similarity SimMUP between the program vector PP and the negative history vector. Then, program vector PP or EPG data of a predetermined number (for example, three) of higher-ranked programs is extracted as recommendation information, output to the recommendation information output unit 49, and registered in the recommended program list 50. Then, the data is output to the television display device 11 and the recording / reproducing device 12, and the process is terminated.
- the recommendation information is extracted by using the program side effect vector EfPP, the user side effect vector EfUP, or the user side effect vector EUP according to the setting, so that the user's preference can be correctly determined. It is possible to recommend the program that reflects it.
- step S131 the same processing as step S121 in FIG. 19 is performed, and the usage setting contents of the effect vector are obtained.
- step S 1 32 the vector calculation unit 62 determines the program vector PP for each of the supplied program vector PP and the main history vector UP read from the main history storage unit 47. Calculate the cosine distance of the positive history vector UP.
- the effect vector is not used in the calculation.
- step S133 the betattle calculation unit 62 multiplies the cosine distance calculated for each item by the effect vector as necessary using the following equation (7), and calculates the obtained value. Sum up to calculate the similarity SimUP.
- both the program side effect vector Ef PP and the user side effect vector EfUP are described as being used, but depending on the setting, the program side effect vector may be used. If either EfPP or the user-side effect vector EfUP is not used, the value "1" is substituted for the unused vector and calculated.
- step S134 the vector operation unit 62 compares the similarity SimUP between the program vector PP and the positive history vector UP calculated in step S133. Then, a predetermined number of program vectors PP such as 10 are extracted from the top of the similarity.
- Step S 1 3 Betatoru calculator 6 2, the program base vector PP extracted by the processing in step S 1 3 4, for each of the major items of negative history Betatoru MUP read out from the negative history storing unit 4 8 Calculate the cosine distance between the program vector and the negative history vector MUP.
- the effect vector is not used for the calculation.
- step S136 the vector calculation unit 62 uses the following equation (8) to multiply the cosine distance calculated for each item by the effect vector as necessary, and obtain the obtained value. And calculate the similarity SiraMUP.
- step S 1 37 the vector calculation unit 62 sets ⁇ similarity SimUP, which is the cosine distance between the program vector PP and the positive history vector UP ⁇ — ⁇ the program vector PP and the negative history vector , And extract the program vector PP or EPG data of a predetermined number (for example, 3) of the higher rank programs as recommendation information, and output it to the recommendation information output unit 49. And register it in the recommended program list 50 6
- the data is output to the television display device 11 and the recording / reproducing device 12, and the process is terminated.
- the weighting is performed using the effect vector for each large item, so that it is possible to generate recommendation information that matches the user's preference in detail.
- the positive history vector for each genre generated by the processing of the positive history vector generation processing 2 described with reference to FIG.
- the following describes a matching process 5 in which a matching process is performed using the torque UP and the negative history vector MUP, and the user-side effect vector EfUP and the user-side countereffect vector EfMUP for each genre.
- step S141 the same processing as in step S121 of FIG. 19 is executed, and the usage setting contents of the effect vector are obtained.
- step S142 the vector calculation unit 62 extracts the genre of the supplied program vector PP.
- the genre of the supplied program vector PP is “drama”.
- step S143 the vector calculation unit 62 determines the supplied program vector PP and the regular history vector UP read from the normal history storage unit 47 and corresponding to the genre "drama". Calculate the cosine distance between the program vector PP and the positive history vector UP for the major items in (1). Here, the effect vector is not used for the calculation.
- step S144 the vector operation unit 62 adds the cosine distance calculated for each item to the user-side effect corresponding to the genre “drama” as necessary using the following equation (9). The vectors are multiplied, and the obtained values are summed to calculate the similarity S imUP.
- step S145 the vector operation unit 62 compares the similarity SimUP between the program vector PP and the normal history vector UP calculated in step S143, and for example, from the highest similarity, for example, 10 Extract a predetermined number of program vectors, such as PP.
- step S146 the vector operation unit 62 includes the program vector PP extracted by the processing in step S145 and the negative history vector MUP corresponding to the Jan-Nore “drama” read from the negative history storage unit 48. Calculate the cosine distance between the program vector PP and the negative history vector MUP for each of the major items. Here, the effect vector is not used in the calculation.
- step S147 the vector operation unit 62 uses the following equation (10) to add an effect vector corresponding to the genre “drama” to the cosine distance calculated for each item, if necessary. Multiply and sum the obtained values to calculate the similarity SimMUP.
- both the program side effect vector EfPP and the user side effect vector EfMUP are described as being used, but the program side effect vector EfPP and user If any of the side reaction vectors EfMUP are not used, they are calculated by substituting the value "1" for the unused vector.
- step S148 the vector calculation unit 62 sets the similarity SimUP, which is the cosine distance between the program vector PP and the positive history vector UP, —— ⁇ the program vector PP and the negative history vector
- the similarity SimMUP ⁇ which is the cosine distance, is calculated, and the program vector PP or EPG data of a predetermined number (for example, three) of the higher rank programs is extracted as recommendation information, and output to the recommendation information output unit 49.
- the program is registered in the recommended program list 50, and is output to the television display device 11 and the recording / reproducing device 12, thereby completing the process.
- the cosine distance between the positive history vector UP and negative history vector MUP and program vector PP for each genre is obtained for each major item, and the effect vector corresponding to the genre is obtained. Since the similarity is calculated by using and weighting, it is possible to generate recommendation information that matches the user's preference in detail.
- the user side effect vector EfUP and the counter effect vector EfMUP may be generated based on the user's initial registration contents registered in the initial registration storage unit 45 as described above, By counting the positive history vector UP or negative history vector MUP, or the programs that the user has watched in a certain period of time, the user-specific effect vector EfUP and countereffect vector EfMUP are generated. You may do it. With reference to the flowchart of FIG. 22, the user-side effect vector generation processing 1 for generating the user-side effect vector EfUP by counting the programs watched by the user during a certain period will be described.
- step S151 the user information registration unit 63 of the matching processing unit 43 selects one of the unprocessed large items.
- the user information registration unit 63 refers to the main history stored in the main history storage unit 47, and, for example, during a certain period such as one week, one month, or three months.
- the program vector extraction unit 42 causes the program vector extraction unit 42 to extract from the data acquisition unit 41 the program vector PP corresponding to the program watched by the user during a certain period. The number of programs is counted for each detailed item included in the large item selected in 1.
- step S153 the user information registration unit 63 causes the program vector extraction unit 42 to extract, from the data acquisition unit 41, program vectors PP corresponding to all programs in the same period. The number of programs is counted for each detailed item included in the large item selected in S151.
- the programming is considered to reflect the tastes of the public due to the influence of audience rating competition.
- the calculation of the count of the user's viewing performance / the count of all programs is, in other words, synonymous with normalizing the count of the user's viewing performance by the number of counts of all programs as a standard model. is there.
- the normalization vector calculated in step S154 is referred to as a normalization vector D.
- the component of the normalized vector D is 1.0, the user has watched all the programs of the corresponding item during the set period, and the component of the normalized vector D is 0. In some cases, this means that during the set period, no relevant program was viewed.
- step S155 the user information registration unit 63 generates an effect vector of the corresponding large item based on the calculation result of step S155.
- the standard value may be set to 0.2. Since the effect vector of the large item is calculated as a relative value, the set value may be any value from 0 to 1.
- the user-side effect vector is a relative value between the normalization vector D calculated in step S154 and the set value.
- step S156 the user information registration unit 63 determines whether the effect vector of all the major items has been generated. If it is determined in step S156 that the effect vectors of all large items have not been generated, the process returns to step S151, and the subsequent processes are repeated.
- step S157 the user information registration unit 63 stores the effect vectors of all large items. Then, the process is terminated.
- the user side effect vector EfUP is obtained based on a program watched by the user during a certain period such as one week, one month, or three months.
- the user-side effect vector EfUP corresponding to the short-term, medium-term, and long-term may be calculated, and the recommendation information may be determined using the plurality of effect vectors.
- the user-specific preference is used as the user-side effect vector EfUP.
- the user-specific preference may be used as the normal history vector UP for the matching process.
- all programs broadcast in a predetermined time zone for example, so-called golden time between 18 o'clock and 22 o'clock
- golden time for example, so-called golden time between 18 o'clock and 22 o'clock
- the user-specific preference and the public preference are calculated by calculating the positive history vector UP and the cosine distance indicating the similarity to the public preference.
- the user-side effect vector calculation process 2 for obtaining the user-side effect vector EfUP for using the gap for matching will be described.
- step S 161 the user information registration unit 63 of the matching processing unit 43 acquires the main history vector UP stored in the main history storage unit 47.
- step S162 the user information registration unit 63 acquires a standard preference title APP indicating a general preference.
- the standard preference vector APP may be supplied from the distribution server 5, or the program composition is considered to reflect the public's preference due to the influence of audience rating competition. In the same way as the user-side effect vector calculation process 1 described using 2, the contents of all programs broadcast during a certain period are counted, and if necessary, normalized, so that the standard preference vector APP is obtained. May be.
- the distribution server 5 may generate a standard preference vector APP indicating general preferences, for example, using a general audience rating survey or another method.
- the user information registration unit 63 calculates the cosine distance between the standard preference vector APP and the normal history vector UP for each large item. The larger the cosine distance, the higher the similarity between the standard preference vector APP and the normal history vector UP. 2003/015926
- step S164 the user information registration unit 63 generates an effect vector EfUP for each major item by reversing the cosine distance based on the cosine distance calculated in step S166. Then, the process is terminated.
- the user-side effect vector EfUP that reflects the difference between the general preference and the corresponding user-specific preference can be obtained.
- the program recommendation process is performed using the user side effect vector EfUP, the difference between the user's preference and the general preference is emphasized, and the recommended program is determined.
- program vector PP and the normal history vector UP have been described as being represented by vectors for each major item.
- program vector PP and the normal history vector UP It is needless to say that the same processing can be executed even when all the elements of the item are represented by a single row of vector.
- the similarity between the standard preference vector APP and the positive history vector UP is calculated not only by calculating the effect vector, but also by using it directly as an index indicating the user's uniqueness in recommending programs. May be. For example, when the similarity between the standard preference vector APP and the positive history vector UP is high, a new program that matches the trend of the general public may be preferentially recommended.
- the user-side effect vector EfUP be obtained in a learning manner based on the user's operation history, but the user-side effect vector is Alternatively, the value may be registered in advance as an initial registration, or a preset value obtained by experience or the like may be used.
- the user-side effect vector EfUP may be generated not only by generating the user-side effect vector EfUP by focusing on the large items, but also by focusing on the constituent elements constituting the large item.
- the leading role and the supporting role can be distinguished, and in a drama or movie, a user who gives priority to the supporting role over the leading role will be assigned to the leading role.
- the user-side effect vector EfUP can be set so as to increase the weight of supporting roles, or a configuration that configures large items In the element "Screenplay / Original / Direction Ara", directors, directors, original authors, photographers, etc. should be distinguishable, and users who value photographers more than directors and directors should increase the weight of photographers.
- the user side effect vector EfUP may be settable.
- the user-side effect vector EfUP is generated for each genre, and as shown in the matching process 5 described with reference to FIG. 21, the matching between the positive history vector UP of the corresponding genre and the program vector PP is performed. May be made to act.
- step S171 the user information registration unit 63 of the matching processing unit 43 selects one of the genres in order to count the programs watched by the user during a certain period by genre.
- step S172 the user information registration unit 63 selects one of the unprocessed large items.
- the user information registration unit 63 refers to the main history stored in the main history storage unit 47 and, for example, during a certain period such as one week, one month, or three months. Among the programs watched by the user in the selected genre, the program genre that is selected is detected. The vector PP is extracted from the data acquisition unit 41, and the number of programs is counted for each detailed item included in the large item selected in step S172.
- step S174 the user information registration unit 63 sends the program vector PP corresponding to the selected genre among all programs in the same period to the program vector extraction unit 42 from the data acquisition unit 41. Then, the number of programs is counted for each detailed item included in the large item selected in step S172. In step S175, the user information registration unit 63 determines, based on the count results of step S177 and step S174, the number of user viewing performance points Z in the selected genre. Calculate the number of power points for all programs.
- the programming is considered to reflect the tastes of the public due to the influence of audience competition. That is, in the selected genre, the count of the user's viewing performance z
- the calculation of the count of all programs is, in other words, the count of the user's viewing performance in the corresponding genre is converted to the corresponding jan This is equivalent to normalizing with the count number of all programs in the program.
- the normalized vector calculated in step S175 is referred to as a normalized vector D '.
- the count of all programs in a week is (10, 35, 7, 53, 17)
- the count number of the program watched is (5, 0, 0, 8, 4)
- the normalized vector D ' is as follows.
- the component of the normalized vector D ' is 1.0, it means that all programs of the corresponding item have been watched during the set period, and the component of the normalized vector D' If is 0, it means that no relevant program was watched during the set period.
- step S176 the user information registration unit 63 generates an effect vector of the corresponding large item in the selected genre based on the calculation result of step S175.
- time zone In a week of the “Golden” program, it is assumed that general users watch about 20% of dramas, and the standard value may be set to 0.2.
- the effect vector of the large item is calculated as a relative value, so the set value may be any value from 0 to 1.
- the user-side effect vector is a relative value between the normalization vector D ′ calculated in step S175 and the set value.
- step S177 the user information registration unit 63 determines whether or not the effect vectors of all large items have been generated in the selected genre. In step S177, If it is determined that the effect vectors of all the large items have not been generated, the process returns to step S172 and the subsequent processes are repeated. When it is determined that the effect vector of the item has been generated, in step S178, the user information registration unit 63 determines whether or not processing of all genres has been completed. If it is determined in step 8 that all the genres have not been completed, the process returns to step S171, and the subsequent processes are repeated.
- step S179 the user information registration unit 63 stores the effect vectors of all the large items and performs processing. Is terminated.
- the difference between general preferences and user-specific preferences can be determined for each genre.
- the user-side effect vector EfUP is recalculated every predetermined period, for example, three months, six months, etc.
- a program that reflects preferences in real time can be recommended.
- the user side effect vector EfUP is obtained based on the program watched by the user during a certain period such as one week, one month, or three months.
- the user-side effect vector EfUP corresponding to, for example, the short-term, medium-term, and long-term is calculated for a plurality of periods, and the plurality of effect vectors are calculated.
- the recommendation information may be determined.
- a predetermined time period in which the viewer views the program most (for example, the so-called “golden time” from 18 o'clock to 22 o'clock) ) May be counted for all programs broadcasted on the same day.
- the user-specific preference is obtained by executing the UP of the positive history vector and the cosine distance calculation indicating the degree of similarity with the public preference for each genre.
- the user-side effect vector generation processing 4 for finding the user-side effect vector EfUP for using the difference between the user and the preference of the public for matching will be described.
- step S191 the user information registration unit 63 of the matching processing unit 43 selects one of the genres in order to specify the genre in which the processing is performed.
- step S192 the user information registration unit 63 acquires the correct history vector UP of the selected genre from the correct history vectors UP stored in the correct history storage unit 47.
- step S193 the user information registration unit 63 acquires the standard preference vector APP of the selected genre from the standard preference vector APP indicating the general preference.
- the standard preference vector APP may be supplied from the distribution server 5 as described above, or the programming is considered to reflect the preference of the public due to the influence of the audience rating competition. Therefore, in the same way as in the user-side effect vector calculation process 3 described with reference to FIG. 24, the contents of all programs broadcast during a certain period are classified by genre. May be normalized, if necessary, and used as a genre standard preference vector APP.
- the distribution server 5 may generate a standard preference vector APP indicating a general preference for each genre using, for example, a general audience rating survey or other methods.
- step S194 the user information registration unit 63 uses the normal history vector UP of the selected genre and the standard preference vector APP of the selected genre to set the standard preference for each major item. Calculate the cosine distance between the vector APP and the normal history vector UP. The larger the cosine distance, the higher the similarity between the standard preference vector APP and the normal history vector UP.
- step S 195 the user information registration unit 63 sets the reciprocal of the cosine distance for each major item based on the cosine distance calculated in step S 194 to determine the effect of the selected genre. Generates vector EfUP. The larger the reciprocal of the cosine distance, the lower the similarity between the standard preference vector APP and the normal history vector UP.
- step S196 the user information registration unit 63 determines whether or not processing for all genres has been completed. If it is determined in step S178 that all genres have not been completed, the process returns to step S191, and the subsequent processes are repeated. If it is determined in step S196 that all genres have been completed, the processing is terminated.
- step S201 the user information registration unit 63 of the matching processing unit 43 acquires the negative history vector MUP stored in the negative history storage unit 48.
- step S202 the user information registration unit 63 acquires a standard preference vector APP indicating a general preference.
- the standard preference vector APP may be supplied from the distribution server 5.
- the programming is considered to reflect the tastes of the general public due to the influence of the audience rating competition. Therefore, the user-side effect vector calculation process 1 described with reference to FIG.
- the content of all programs broadcasted on the Internet may be counted, and the content may be normalized as necessary to make the standard preference vector APP.
- step S203 the user information registration unit 63 calculates a cosine distance between the standard preference vector APP and the negative history vector MUP for each large item.
- step S204 the user information registration unit 63 generates a reaction vector EfMUP based on the cosine distance calculated in step S203, for each large item, by reciprocal the cosine distance. Then, the process is terminated.
- reaction vector EfMUP can be generated, so that programs that the user does not like can be effectively omitted from recommended programs.
- step S 211 the user information registration unit 63 of the matching processing unit 43 selects one of the genres in order to specify the genre in which the processing is performed.
- step S212 the user information registration unit 63 acquires the negative history vector MUP of the selected genre from the negative history vectors MUP stored in the negative history storage unit 48. I do.
- step S213 the user information registration unit 63 acquires the standard preference vector APP of the selected genre from the standard preference vector APP indicating the general preference.
- step S214 the user information registration unit 63 determines the standard preference for each major item based on the negative history vector MUP of the selected genre and the standard preference vector APP of the selected genre. Calculate the cosine distance between the vector APP and the negative history vector MUP. The larger the cosine distance, the higher the similarity between the standard preference vector APP and the negative history vector MUP.
- step S215 the user information registration unit 63 sets the reaction vector EfMUP based on the cosine distance calculated in step S214, reversing the cosine distance for each major item. Generate. The larger the reciprocal of the cosine distance, the lower the similarity between the standard preference vector APP and the negative history vector MUP.
- step S216 the user information registration unit 63 determines whether or not processing of all genres has been completed. If it is determined in step S216 that all genres have not been completed, the process returns to step S211 and the subsequent processes are repeated. If it is determined in step S216 that all genres have been completed, the processing is terminated.
- the counter-effect vector EfMUP can be generated for each genre, so that programs that the user does not like can be effectively excluded from recommended programs.
- the user-side effect vector EfUP and the counter-effect vector EfMUP are n times the reciprocal of the cosine distance for each of the large items described with reference to FIG. 23 and FIGS. 25 to 27.
- a value rounded to a predetermined digit may be used, a value obtained by subtracting the reciprocal of the cosine distance from 1 or a value obtained by multiplying the value by n may be used.
- the program vector PP and the negative history vector MUP power are described in terms of vectors for each major item, but the program vector PP and the negative history It is needless to say that the same processing can be executed even when the vector MUP is represented by a vector in which all the elements of the detailed items are arranged in one column.
- the program vector extracted by the program vector extraction unit 42 includes information indicating a group such as a group ID or a cluster code generated by the processing described with reference to FIG. 7 or FIG. May be added.
- the program that the user prefers to watch is a serial drama
- the corresponding serial drama is recommended in all episodes
- the number of calculation processes for recommendation can be reduced.
- by preferentially recommending a program in the same group as a program that is highly liked by the user it is possible to reduce the calculation processing for the recommendation.
- step S221 the vector operation unit 62 of the matching processing unit 43 adds a group such as a group ID or a cluster code to the program vector PP supplied from the program vector extraction unit 42. It is determined whether or not the corresponding programs are grouped based on whether or not the information indicating “.” Is added.
- a group such as a group ID or a cluster code
- step S222 the vector calculation unit 62 determines whether the group indicated by the group ID or the cluster code is Then, it is determined whether the user information registration unit 63 is registered as a recommendation priority group.
- step S223 the vector operation unit 62 uses the information of the corresponding program as recommendation information as recommendation information.
- the recommended information output unit 49 registers the recommended program in the recommended program list 5 °, and outputs the information of the recommended program to the television display device 11 or the recording / reproducing device 12 for processing. Goes to step S 227 described later. 5926
- step S221 If it is determined in step S221 that the corresponding program is not grouped, or if it is determined in step S222 that it is not registered as a recommendation priority group, In 24, any one of the matching processing 1 to the matching processing 5 described with reference to FIGS. 17 to 21 is executed.
- step S225 the vector operation unit 62 adds, to the program vector of the program recommended in any one of the matching processes 1 to 3 executed in step S224, a group ID or Based on whether or not information indicating a group, such as a cluster code, is added, it is determined whether or not the recommended programs are grouped. If it is determined in step S225 that the recommended programs are not grouped, the processing is terminated.
- step S226 the vector operation unit 62 determines the group ID added to the program vector, Alternatively, the cluster code is registered and stored in the user information registration unit 63 as a recommendation priority group.
- step S2 27 the vector operation section 62 operates the negative history stored in the negative history storage section 48.
- the programs recommended by the processing of step S 223 or the programs recommended by the processing of step S 224 are grouped. For a program registered as a recommendation priority group in processing, for example, an operation input to command viewing or recording of other programs without accepting the recommended program, or before playing back an automatically recorded program Judgment is made as to whether or not an operation input that has a negative history, such as an operation input for instructing the deletion of an operation, is received. If it is determined in step S 227 that an operation input having a negative history has not been received, the processing is terminated.
- the corresponding group is removed from the registration of the recommendation priority group of, and the process is terminated.
- a plurality of groups ID may be associated with one program vector PP by the title grouping process 1 described with reference to FIG.
- step S 2208 all the group IDs are removed from the recommendation priority group registration of the user information registration unit 63 by an operation input that results in a negative history. It is also possible to accumulate the number of negative history operation inputs, and to register a recommendation priority group of the user information registration unit 63 when a predetermined number of negative history operation inputs are performed. , The corresponding group ID may be removed. The same applies to the case where one group ID is associated with one program vector PP.
- Negative history vector MUP may be generated for each corresponding group.
- the number of viewing or recording reservations in the same serial drama is counted based on the correct history of the user's operation history acquired from the television display device 11 or the recording / reproducing device 12, and the predetermined number or more is counted.
- the recommendation may be given priority without performing the matching process.
- a user model may be set based on a topic specified by the user in advance, and program recommendation processing may be performed based on the user model.
- the user model is obtained by extracting a program corresponding to a topic from a predetermined program group by performing filtering using a topic specified in advance by the user.
- the initial registration storage unit 45 stores the topic input by the user. More than one topic may be registered, and will be updated as appropriate according to the user's operation input.
- the vector calculation unit 62 includes a program vector including a topic stored in the initial registration storage unit 45 in the program vector of the program for which the user model is to be created, which is supplied from the program vector extraction unit 42.
- the user model vector is generated by normalizing the sum of the extracted program vectors as necessary, and is registered in the user information registration unit 63.
- the user model “Midnight Variety” includes as a component a comedian who appeared in a variety program that is broadcast in the midnight frame after 23 o'clock, so for example, in a drama or other program of a genre different from the variety, Since the program in which the corresponding comedian appears is extracted and recommended in the matching process, it is possible to apply the user's preferences beyond the genre, as compared to the case where the matching process is performed for each item. .
- the program for which the user model is to be created may be, for example, all programs in a predetermined period, or a group of programs broadcast in a predetermined time period (for example, so-called golden time).
- user model vectors that correspond to different program schedules in detail for example, at different times or at different time periods, etc. Can be generated.
- the vector computing unit 62 calculates the similarity between the program vector PP of the program supplied from the program vector extracting unit 42 and the user model vector registered in the user information registering unit 63. The calculation is performed, and recommendation information is generated based on the result, and is supplied to the recommendation information output unit 49.
- the recommended information output unit 49 registers the recommended information in the recommended program list 50 and supplies the recommended information to the television display device 11 or the recording / reproducing device 12.
- step S231 the vector operation unit 62 of the matching processing unit 43 acquires the program vector of the program for which the user model is to be created, which is extracted by the program vector extraction unit 42.
- a program for which a user model is to be created is, for example, a program broadcast during a predetermined period such as one month or three months, and broadcast during a predetermined time period (for example, golden time) during the predetermined period.
- the program may be a broadcasted program, or a program broadcast during a predetermined period in the past, such as 10 years ago, 20 years ago, or the like.
- step S232 the initial registration storage unit 45 acquires the topic input by the user from the operation input unit 44 and stores it.
- the vector calculation unit 62 reads the topics from the initial registration storage unit 45 and sets them as filtering conditions. You.
- the filtering condition may be described as, for example, a hash table.
- step S2 33 the vector computing unit 62 filters the program vector PP acquired in step S2 31 based on the filtering conditions set in step S2 32, Extract the program vector PP that matches the topic. For example, if the programs for which the user model is to be created are all programs in the past three months, the vector operation unit 62
- step S235 the vector calculation unit 62 determines the user model vector generated in step S234 and the recommendation information extracted in the program vector extraction unit 42. Calculate the cosine distance between the program candidate PP and the program vector PP that will be broadcast later.
- step S 236 the vector computing unit 62, based on the cosine distance calculated in step S 235, calculates the program model of the candidate program for obtaining the user model vector and the recommendation information. Based on the result of the comparison, a predetermined number of programs with the highest similarity are extracted from the top as recommended information and supplied to the recommended information output unit 49.
- the recommended information output unit 49 registers the recommended information in the recommended program list 50 and supplies the recommended information to the television display device 11 or the recording / reproducing device 12, and the process is terminated.
- the similarity is obtained by calculating the cosine distance between the user model vector and the program vector.However, the cosine distance is calculated individually for each major item, and the cosine distance is calculated. The similarity may be obtained using the sum.
- the generation process of the user model vector may be executed in the distribution server 5. In this case, for example, the processing of steps S231 to S234 in FIG. 29 is executed using the program vector generated by the program vector generation unit 23 described with reference to FIG. What should I do?
- step S 2 41 the vector calculation section 62 of the matching processing section 43 is stored in the program vector PP supplied from the program vector extraction section 42 and the main history storage section 47.
- the positive history vector UP and the negative history vector MUP stored in the negative history storage unit 48 the cosine distance between the positive history vector UP and the program beta PP for each major item , And Calculate the cosine distance between the negative history vector MUP and the program vector PP.
- step S224 the vector operation unit 62 sums the values of the cosine distance calculated for each item on the positive history side and the negative history side. That is, by the processing of step S241 and step S224, the similarity S iraUP between the positive history vector UP and the program vector PP and the negative history vector MUP and the program vector described above are obtained. The similarity SimMUP with the PP is calculated.
- step S243 the vector calculation unit 62 calculates an exceptional recommendation value indicating a low degree of similarity with the positive history vector UP and the negative history vector MUP.
- the exception recommendation value can be obtained from (1-SimUP) X (1-SimMUP) or (1 / SimUP) X (1 / SimMUP).
- step S224 the vector operation unit 62 obtains a program with a high exception recommendation value based on the calculation result in step S243, extracts it as recommendation information, and ends the process.
- a program having a feature that the user has never watched can be extracted and recommended, so that unexpectedness is given to the selection of a recommended program to the user, and the interest of the user is expanded. Not only will it be possible to connect to the Internet, but it will also be possible to acquire very important history information in order to recommend programs that match the user's preferences.
- recommendation information is generated in the program recommendation processing device 10 and supplied to the television display device 11 or the recording / reproducing device 12.
- the television display device 11 or the recording / reproducing device 12 is supplied with a satellite or terrestrial broadcast signal received and decoded by the television receiving device 4.
- the television display device 11 displays a broadcast signal supplied from the television receiving device 4 or reproduction data supplied from the recording / reproducing device 12 based on a user's operation input, or displays a program. Based on the recommendation information supplied from the recommendation processing device 10, it displays recommended program information and executes automatic channel setting. Further, the television display device 11 supplies the operation log to the program recommendation processing device 10.
- the recording / reproducing apparatus 12 records or reserves a broadcast signal supplied from the television receiving apparatus 4 based on a user's operation input, or based on recommendation information supplied from the program recommendation processing apparatus 10. Then, automatically record the program. Further, the recording / reproducing device 12 reproduces a program recorded on the attached recording medium or the built-in recording medium, and outputs the program to the television display device 11 for display. Further, the recording / reproducing device 12 supplies the operation log to the program recommendation processing device 10.
- FIG. 31 is a block diagram showing a configuration of the television receiver 4.
- the television receiver 4 will be described as a general receiver conforming to the standard for digital broadcast receivers.
- the satellite wave detector 91 converts a satellite wave transmitted via the satellite 2 and received by the antenna 3 into a signal for selecting a channel supplied from the television display device 11 or the recording / reproducing device 12. Based on this, the channel is detected and detected, and the control relating to the transmission mode is supplied to a TMCC (Transmission and Multiplexing Configuration Control) decoding unit 92, and the broadcast signal is demodulated and supplied to a decoding processing unit 93.
- TMCC Transmission and Multiplexing Configuration Control
- the decoding unit 92 receives input of information such as a transmission mode (modulation method, coding rate, etc.) and a slot in the transmission multiplex control signal, decodes the information, and demodulates and decodes the information. Supply 9 to 3.
- information such as a transmission mode (modulation method, coding rate, etc.) and a slot in the transmission multiplex control signal, decodes the information, and demodulates and decodes the information.
- the decoding processing unit 93 converts the supplied broadcast signal into, for example, QPSK (quadri-code) based on the information on the transmission mode supplied from the TMCC decoding unit 92.
- phase shift keying demodulated and decoded using a method such as a four-phase modulation method or a four-phase PSK method, or an eight-phase PSK method, and supplies the resulting signal to the din talever 94.
- Dinter liver 94 dinterleaves the supplied signal and supplies it to error correction processing section 95.
- the din taller 94 may further perform frame separation and descrambling processing on the supplied signal.
- the error correction processing section 95 performs error correction processing using, for example, a Reed-Solomon code or the like, and supplies the result to a CA (Conditional Access: limited reception) descrambling section 101.
- the terrestrial wave detector 96 selects and detects the terrestrial wave received by the antenna 3 based on a control signal for selecting a channel supplied from the television display device 11 or the recording / reproducing device 12. Then, the control signal for the transmission mode is supplied to the TMCC decoding section 97, and the broadcast signal is supplied to the demodulation and decoding processing section 98.
- the TMC C decoder 97 receives input of information such as the transmission mode (modulation method, coding rate, etc.), slot, and TS in the transmission multiplex control signal, decodes the information, and demodulates and decodes the information.
- Information such as the transmission mode (modulation method, coding rate, etc.), slot, and TS in the transmission multiplex control signal, decodes the information, and demodulates and decodes the information.
- the demodulation / decoding processing section 98 converts the supplied broadcast signal based on the information on the transmission mode supplied from the TMCC decoding section 97 into, for example, a QAM (quadrature amplitude modulation) system.
- the signal is demodulated and decoded by using the method, and supplied to the Dinta Riva 99.
- Transport Stream This is supplied to the playback unit 100.
- the din taller 99 may further perform a process of frame separation or descrambling on the supplied signal.
- the TS reproduction unit 100 reproduces a transport stream based on the supplied signal, and supplies the transport stream to the CA descramble unit 101.
- the CA descramble unit 101 descrambles the limited reception signal based on the signal supplied from the error correction processing unit 95 or the TS reproduction unit 100, and supplies the descrambled signal to the demultiplexer 102.
- the data input unit 103 receives the input of the EPG data from the EPG receiving device 9, receives the streaming data from the distribution server 5 via the network 8, and supplies the streaming data to the demultiplexer 102.
- the demultiplexer 102 demultiplexes the signal supplied from the CA descramble section 101 or the data input section 103, the audio signal is output to the audio signal decoding section 104, and the video signal is output to the audio signal decoding section 104.
- the video signal decoder 105 supplies the data such as the control signal and the EPG to the data decoder 106.
- the audio signal decoding unit 104 decodes the supplied audio signal and supplies it to the television display device 11 or the recording / reproducing device 12.
- the video signal decoding unit 105 decodes the supplied video signal and supplies it to the television display device 11 or the recording / reproducing device 12.
- the data decoding unit 106 decodes the supplied control signal and data such as EPG and supplies the data to the television display device 11 or the recording / reproducing device 12.
- the received satellite wave or terrestrial wave or the distributed streaming data is demodulated and decoded by a predetermined method, and the television display device 11 or It is supplied to the recording and playback device 12.
- FIG. 32 is a block diagram illustrating a configuration of the television display device 11.
- the operation input unit 12 1 receives an operation input from the user, supplies a control signal corresponding to the user's operation input to each unit of the television display device 11, and stores the operation contents of the user in an operation log list 1 2 2 To be stored.
- the user operation logs stored in the operation log list 122 are acquired by the operation log acquisition unit 46 of the program recommendation processing device 10 described with reference to FIG.
- the operation input unit 121 supplies the input user operation to the channel setting unit 123.
- the channel setting unit 123 generates a control signal indicating channel selection based on the signal indicating the user's operation input supplied from the operation input unit 122, and supplies the control signal to the television receiver 4.
- the channel setting unit 123 sets a control signal indicating a channel selection in order to automatically set a channel based on recommendation information registered in a recommended number list 128 described later. Generated and supplied to the television receiver 4.
- the television receiver 4 receives a broadcast signal of a specified channel based on the control signal.
- the data input section 124 receives an input of a broadcast signal from the television receiver 4 and supplies the broadcast signal to the image processing section 125.
- the image processing unit 125 performs image processing on the supplied broadcast signal based on the image display method of the output unit 126 and supplies the broadcast signal to the output unit 126.
- the output unit 126 includes, for example, a display device such as a CRT (Cathode Ray Tube) or an LCD (Liquid Crystal Display), and a sound output device such as a speaker.
- the image signal of the broadcast signal is displayed on the display device, and the audio signal is output from the audio output device.
- the recommended program list obtaining section 127 obtains recommendation information from the program recommendation processing device 10 and supplies the recommended information to the recommended program list 128.
- the recommended program list 128 registers the supplied recommended information.
- the recommendation information registered in the recommended program list 128 is read out to the channel setting unit 123 or to the recommended program information display control unit 129.
- the recommended program information display control unit 129 outputs the recommended information read from the recommended program list 128 to the image processing unit 125 in order to present the recommended information of the program to the user.
- the image processing unit 125 outputs the recommendation information supplied from the recommended program information display control unit 129 alone or superimposed on the image of the broadcast signal supplied from the data input unit 124. Output it to the unit 1 26 and display it on the display device.
- the ability to display the recommendation information on the output unit 126 and whether to automatically set the channel depends on the setting of the user. It may be determined.
- a recommendation information display process for presenting program recommendation information to a user based on the recommendation information supplied from the program recommendation processing device 10 will be described.
- step S ⁇ b> 251 the recommended program list acquisition section 127 acquires the recommendation information output from the recommendation information output section 49 of the program recommendation processing device 10.
- step S252 the recommended program list acquisition section 127 registers the acquired recommended information in the recommended program list 128.
- step S 253 the recommended program information display control unit 1 229 selects a program to be broadcast from the recommended program list 1 288 within a predetermined time from the current time, for example, 3 hours or 1 day.
- the recommended information is read, and data for recommendation information display for displaying the title, content, broadcast time, and broadcast channel of the recommended program is generated and supplied to the image processing unit 125.
- step S254 the image processing unit 125 executes image processing for displaying the supplied recommendation information display data on the output unit 126, and supplies the data to the output unit 126.
- the recommendation information is subjected to image processing alone or by being superimposed on the image of the broadcast signal supplied from the data input unit 124.
- step S255 the output unit 126 displays the recommendation information supplied from the image processing unit 125, and the process ends.
- the recommendation information is displayed on the output unit 126, so that the user can select a program to view by referring to the displayed recommendation information.
- a channel for automatically setting a channel based on the recommendation information supplied from the program recommendation processing device 10 and displaying a program matching the user's preference is displayed. The automatic channel setting process will be described.
- step S271 and step S272 the same processing as in step S251 and step S252 described with reference to FIG. 33 is executed. That is, the recommendation information output from the recommendation information output unit 49 of the program recommendation processing device 10 is acquired, and the acquired recommendation information is registered in the recommended program list 128.
- the channel setting unit 1 2 3 acquires the information of the recommended program corresponding to the current time from the program recommendation list 98 in step S 2 73, and in step S 2 74, based on the information of the recommended program, It generates channel setting information and outputs it to the television receiver 4.
- the television receiver 4 receives the broadcast signal of the designated channel based on the control signal.
- step S275 the data input unit 124 acquires the broadcast signal of the specified channel from the television receiver 4 and supplies the broadcast signal to the image processing unit 125.
- step S 276 the image processing unit 125 performs image processing for displaying the supplied broadcast signal on the output unit 126, and supplies the broadcast signal to the output unit 126.
- step S277 the output unit 126 displays the video of the recommended program supplied from the image processing unit 125, outputs the sound, and ends the processing.
- a channel is automatically set to a channel on which a program matching the user's preference is being broadcast.
- the automatic channel setting process described with reference to FIG. 34 may be executed, for example, when the user issues a command. This makes it possible to automatically set the channel to a program on which an appropriate program is being broadcast when the user is concerned about which program to watch.
- the automatic channel setting process described with reference to FIG. 34 is performed, for example, every two hours, such as at a predetermined time when it is determined that the user has just left the channel without setting the channel with particular consideration.
- the process may be executed when there is no operation input from the user for a predetermined time when it can be determined that the user has been left unattended.
- FIG. 35 is a block diagram showing a configuration of the recording / reproducing device 12.
- the operation input unit 14 1 receives an operation input from the user, supplies a control signal corresponding to the user's operation input to each unit of the recording / reproducing device 12, and displays the operation contents of the user through the operation port grease 14. Supply to 2 and save. Saved in operation log list 1 4 2
- the operation log of the user is acquired by the operation port acquisition unit 46 of the program recommendation processing device 10 described with reference to FIG.
- the recording setting section 144 is based on the signal indicating the user's operation input supplied from the operation input section 141 or based on recommendation information registered in a recommended program list 149 described later. For example, information necessary for performing a recording process, such as a broadcast start time and a broadcast end time of a program to be recorded and a broadcast channel, is extracted.
- the recording setting unit 144 registers the information necessary for performing the recording process in the recording reservation list 144
- the user's operation input supplied from the input unit 141 is a recording process of a currently broadcasted program, or automatic recording is performed using recommendation information registered in a recommended program list 149 described later.
- the information necessary for performing the recording processing is supplied to the recording control unit 145.
- the recording control section 144 is based on the information necessary for performing the recording process supplied from the recording setting section 144, or of the recording reservation information registered in the recording reservation list 144. By extracting the recording reservation information corresponding to the current time, a control signal indicating the broadcast channel of the program to be recorded is generated and supplied to the television receiver 4, and the control signal for executing the recording process is generated. It is generated and supplied to the recording / playback processing section 147.
- the television receiver 4 receives a broadcast signal of a specified channel based on the control signal.
- the data input unit 146 receives an input of a broadcast signal from the television receiver 4 and supplies the broadcast signal to the recording / playback processing unit 147.
- the recording / reproducing processing unit 147 is configured so that a recording medium such as a magnetic tape, an optical disk, a magnetic disk, a magneto-optical disk, or a semiconductor memory can be mounted therein, or includes, for example, a hard disk. Or a recording medium such as a semiconductor memory so that information can be recorded on the recording medium or the information can be reproduced from the recording medium.
- the recording medium attachable to the recording / playback processing unit 147 is a magnetic tape
- the recording / playback processing unit 147 has a magnetic head
- It records (ie, records) the broadcast signal supplied thereto, reproduces information recorded on a magnetic tape, and supplies the information to a television display device 11 or the like for reproduction and output.
- the recommended program list obtaining unit 148 obtains the recommended information from the program recommendation processing device 10 and supplies it to the recommended program list 149.
- the recommended program list 149 registers the supplied recommended information.
- the recommendation information registered in the recommended program list 149 is read out to the recording setting unit 143, and the recording process is automatically executed.
- step S291 the recommended program list acquisition unit 148 acquires the recommendation information output from the recommendation information output unit 49 of the program recommendation processing device 10.
- step S292 the recommended program list obtaining unit 148 registers the obtained recommended information in the recommended program list 149.
- step S293 the recording setting unit 144 extracts the information of the recommended program corresponding to the current time from the program recommendation list 109, and sets the broadcast start time and the broadcast end time, and the broadcast channel and the like. The information necessary for the recording process is obtained and supplied to the recording control unit 145.
- step S294 the recording control unit 145 generates channel setting information for receiving the supply of the broadcast signal of the program to be recorded, and outputs it to the television receiver 4 .
- the television receiver 4 receives the broadcast signal of the specified channel based on the control signal.
- step S295 the data input unit 146 acquires the broadcast signal of the specified channel from the television receiver 4 , and supplies the broadcast signal to the recording / playback processing unit 147.
- step S296 the recording / playback processing section 147 records the supplied broadcast signal on the attached or built-in recording medium, and the process ends. By such processing, it becomes possible to automatically record a program that matches the user's preference.
- the automatic recording process described with reference to FIG. 36 is not executed while a recording operation is already being performed, such as during a recording process instructed by a user or during a recording operation by a recording reservation process.
- the program vector PP has been described as being generated in the distribution server 5, but the distribution server does not generate the program vector PP, but via the network 8.
- the EPG data may be supplied to a program recommendation processing device, and the program recommendation processing device may generate a program vector PP.
- the distribution server does not generate the program vector PP, but supplies the EPG data to the program recommendation processing device via the network 8 and distributes it when the program recommendation processing device generates the program vector PP.
- the configuration of the server 171 is shown in FIG. 37, and the configuration of the program recommendation processing device 191 is shown in FIG.
- the distribution server 17 1 is composed of the data acquisition unit 21 and the data transmission unit 25 of the distribution server 5 described with reference to FIG. 2, and is streamed from the streaming data database 6 or the metadata database 7.
- EPG data composed of reaming data or meta data is acquired and transmitted to the EPG receiving device 8 or the television receiving device 4 via the network 8.
- a metadata acquisition unit 22 and a program vector generation unit 23 similar to those provided in the distribution server 5 of FIG. 2 are newly provided.
- the configuration is the same as that of the program recommendation processing device 10 described with reference to FIG.
- the grouping process 1 described with reference to FIG. 7 and the grouping process described with reference to FIG. 8 are executed.
- the EPG receiving device 9 collects the user's operation history and setting information from the television display device 11 and the recording / reproducing device 12, and transmits the distribution server via the network 8.
- the distribution server may not only generate the program vector PP but also execute the matching process and supply the matching result to the EPG receiving device 9 via the network 8.
- the network configuration in this case is shown in FIG. 39, and a block diagram showing the configuration of the distribution server 201 is shown in FIG.
- the distribution server 201 is obtained by adding the function of the program recommendation processing device 191 described with reference to FIG. 38 to the distribution server 171 described with reference to FIG. 37. Users do not need to own a program recommendation processor.
- the program vector PP In the configurations shown in Fig. 39 and Fig. 40, the program vector PP, program side effect vector EfPP, positive history vector UP, negative history vector MUP, or standard preference vector APP All of the processing described with reference to FIGS. 3 to 12 and FIGS. 14 to 30, such as generation processing, program vector grouping processing, matching processing, and exceptional recommended program selection processing.
- the EPG receiving device 9 collects the data from the television display device 11 and the recording / reproducing device 12 and transmits the collected data via the network 8.
- a user ID is attached to the operation history and setting information so that each user can be distinguished.
- the initial registration storage unit 45, the positive history storage unit 47, the negative history storage unit 48, etc. are based on the user ID of the supplied information. Then, each information is saved for each user.
- the series of processes described above can be executed by software.
- the software is capable of executing various functions by installing a computer in which the program constituting the software is built into dedicated hardware or installing various programs. Installed from a recording medium to a personal computer.
- this recording medium is a magnetic disk 31 or a magnetic disk 31 on which the program is recorded, which is distributed to provide the program to the user separately from the computer.
- 7 1 including flexible disk
- optical disk 32 or 7 2 including CD-ROM (Compact Disk-Read Only Memory), DVD (Digital Versatile Disk)
- magneto-optical disk 33 or 73 including MD (Mini-Disk) (trademark)
- a packaged media consisting of semiconductor memory 34 or 74.
- steps for describing a program recorded on a recording medium are not limited to processing performed in chronological order in the order described, but are not necessarily performed in chronological order. Alternatively, it also includes processing that is executed individually.
- system refers to an entire device including a plurality of devices.
- the present invention it is possible to select content that matches the user's preference.
- the recommendation information indicating the content recommended to the user for viewing is generated, it is possible to select the content that properly matches the user's preference.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP03778859.3A EP1571836B1 (en) | 2002-12-12 | 2003-12-12 | Information processing device and information processing method, recording medium, and computer program |
US10/538,181 US7577645B2 (en) | 2002-12-12 | 2003-12-12 | Information processing device and information processing method, recording medium, and computer program |
US11/514,255 US7587382B2 (en) | 2002-12-12 | 2006-09-01 | Information processing apparatus and information processing method, recording medium, and program |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2002361277A JP2004194108A (ja) | 2002-12-12 | 2002-12-12 | 情報処理装置および情報処理方法、記録媒体、並びにプログラム |
JP2002-361277 | 2002-12-12 |
Related Child Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/538,181 A-371-Of-International US7577645B2 (en) | 2002-12-12 | 2003-12-12 | Information processing device and information processing method, recording medium, and computer program |
US11/514,255 Division US7587382B2 (en) | 2002-12-12 | 2006-09-01 | Information processing apparatus and information processing method, recording medium, and program |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2004054246A1 true WO2004054246A1 (ja) | 2004-06-24 |
Family
ID=32501035
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2003/015926 WO2004054246A1 (ja) | 2002-12-12 | 2003-12-12 | 情報処理装置および情報処理方法、記録媒体、並びにプログラム |
Country Status (6)
Country | Link |
---|---|
US (2) | US7577645B2 (ja) |
EP (2) | EP1571836B1 (ja) |
JP (1) | JP2004194108A (ja) |
KR (2) | KR101007839B1 (ja) |
CN (2) | CN1750610A (ja) |
WO (1) | WO2004054246A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108369814A (zh) * | 2015-12-02 | 2018-08-03 | 索尼公司 | 信息处理设备、光盘、信息处理方法与程序 |
CN114443967A (zh) * | 2022-04-08 | 2022-05-06 | 北京并行科技股份有限公司 | 一种相似应用推荐方法、计算设备及存储介质 |
Families Citing this family (76)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030135539A1 (en) * | 2001-01-23 | 2003-07-17 | Tetsujiro Kondo | Communication apparatus, communication method, eletronic device, control method of the electronic device, and recording medium |
WO2004054245A1 (ja) * | 2002-12-12 | 2004-06-24 | Sony Corporation | 情報処理装置および情報処理方法、情報処理システム、記録媒体、並びにプログラム |
JP2004194108A (ja) * | 2002-12-12 | 2004-07-08 | Sony Corp | 情報処理装置および情報処理方法、記録媒体、並びにプログラム |
EP1743287A4 (en) * | 2004-02-27 | 2009-02-25 | Daniel Abrahamsohn | METHOD AND SYSTEM FOR OBTAINING DATA FROM MULTIPLE SOURCES AND CLASSIFYING DOCUMENTS BASED ON METADATA OBTAINED THROUGH COLLABORATIVE FILTERING AND OTHER MATCHING TECHNIQUES |
US20050210501A1 (en) * | 2004-03-19 | 2005-09-22 | Microsoft Corporation | Method and apparatus for handling metadata |
JP2006040085A (ja) * | 2004-07-29 | 2006-02-09 | Sony Corp | 情報処理装置および方法、記録媒体、並びにプログラム |
JP2006094018A (ja) * | 2004-09-22 | 2006-04-06 | Sharp Corp | 番組推薦装置、番組推薦方法、プログラムおよびそのプログラムを記録した記録媒体 |
JP4676441B2 (ja) * | 2004-10-01 | 2011-04-27 | パナソニック株式会社 | チャンネル契約提案装置、方法、プログラム及び集積回路 |
WO2006043498A1 (ja) * | 2004-10-18 | 2006-04-27 | Pioneer Corporation | 情報処理装置、統計情報データベースのデータ構造、情報生成装置、情報処理方法、情報生成方法、情報処理プログラム、およびそのプログラムを記録した記録媒体 |
JP2006148853A (ja) * | 2004-10-18 | 2006-06-08 | Sharp Corp | 情報作成装置、番組推薦装置、情報作成方法、番組推薦プログラムおよびそのプログラムを記録した記録媒体 |
JP2006129122A (ja) * | 2004-10-29 | 2006-05-18 | Sharp Corp | 放送受信装置、放送受信方法、放送受信プログラム及びプログラム記録媒体 |
JP2006129265A (ja) * | 2004-10-29 | 2006-05-18 | Sharp Corp | 番組情報抽出装置、番組情報表示装置、放送番組録画システム、番組情報抽出方法、プログラム、および、プログラムを記録したコンピュータ読み取り可能な記録媒体 |
JP2006134383A (ja) * | 2004-11-02 | 2006-05-25 | Canon Inc | 再生装置、再生方法及びそのプログラム |
JP4430002B2 (ja) * | 2004-11-03 | 2010-03-10 | 三星電子株式会社 | デジタル放送プログラム情報の表示装置及び方法 |
KR20050044844A (ko) | 2004-11-03 | 2005-05-13 | 삼성전자주식회사 | 디지털 방송 채널정보 표시 장치 및 방법 |
JP2006157715A (ja) * | 2004-11-30 | 2006-06-15 | Sharp Corp | 番組情報抽出装置、番組情報抽出方法、そのプログラムおよび記録媒体 |
JP4534748B2 (ja) * | 2004-12-20 | 2010-09-01 | ソニー株式会社 | 情報処理装置および方法、記録媒体、並びにプログラム |
DE102005039507A1 (de) * | 2005-01-18 | 2006-08-17 | Hirschmann Electronics Gmbh | Programmdiversity |
US7912806B2 (en) * | 2005-02-21 | 2011-03-22 | Brother Kogyo Kabushiki Kaisha | System and device for providing contents |
WO2006126537A1 (ja) * | 2005-05-23 | 2006-11-30 | Matsushita Electric Industrial Co., Ltd. | 通信装置、通信方法、通信プログラム、その記録媒体及び集積回路 |
JP4378646B2 (ja) | 2005-09-28 | 2009-12-09 | ソニー株式会社 | 情報処理装置、情報処理方法、およびプログラム |
JP2007110388A (ja) * | 2005-10-13 | 2007-04-26 | Funai Electric Co Ltd | 連係動作プログラム及び接続機器 |
CA3175867A1 (en) * | 2005-12-29 | 2007-07-12 | Rovi Guides, Inc. | Systems and methods for managing content |
JP2007272451A (ja) * | 2006-03-30 | 2007-10-18 | Toshiba Corp | 推薦番組情報提供装置、推薦番組情報提供方法及びプログラム |
US20070250378A1 (en) * | 2006-04-24 | 2007-10-25 | Hughes John M | Systems and methods for conducting production competitions |
JP4179341B2 (ja) * | 2006-06-01 | 2008-11-12 | ソニー株式会社 | 情報処理装置および方法、プログラム、並びに記録媒体 |
JP5027483B2 (ja) * | 2006-11-10 | 2012-09-19 | 富士通株式会社 | 情報検索装置及び情報検索方法 |
JP4909033B2 (ja) * | 2006-11-30 | 2012-04-04 | 富士通株式会社 | 番組検索装置 |
JP4423568B2 (ja) * | 2006-12-08 | 2010-03-03 | ソニー株式会社 | 表示制御処理装置および方法並びにプログラム |
US8473525B2 (en) * | 2006-12-29 | 2013-06-25 | Apple Inc. | Metadata generation for image files |
JP2008187576A (ja) * | 2007-01-31 | 2008-08-14 | Sony Corp | 情報処理装置および方法、並びにプログラム |
JP2008187575A (ja) | 2007-01-31 | 2008-08-14 | Sony Corp | 情報処理装置および方法、並びにプログラム |
JP5075423B2 (ja) * | 2007-02-16 | 2012-11-21 | 株式会社東芝 | 推薦番組提示装置、および推薦番組提示方法 |
JP4389973B2 (ja) * | 2007-06-26 | 2009-12-24 | ソニー株式会社 | 情報処理装置および方法、並びにプログラム |
JP5173287B2 (ja) * | 2007-07-06 | 2013-04-03 | キヤノン株式会社 | 番組記録装置及びその制御方法 |
JP4403432B2 (ja) * | 2007-07-19 | 2010-01-27 | ソニー株式会社 | 録画再生装置及び録画再生方法 |
US8949877B2 (en) * | 2007-08-31 | 2015-02-03 | At&T Intellectual Property I, L.P. | Method and system for determining subscriber demand for multimedia content |
KR100964013B1 (ko) * | 2007-11-09 | 2010-06-15 | 광주과학기술원 | 사용자 선호도 기반의 데이터 변환 서비스 시스템 및 그방법 |
KR101060487B1 (ko) * | 2007-11-19 | 2011-08-30 | 서울대학교산학협력단 | 태그 클라우드를 이용한 콘텐츠 추천 장치 및 방법 |
US20090170586A1 (en) * | 2007-12-26 | 2009-07-02 | Springtime Productions, Llc | Springtime productions special charity fund raising process |
JP5166949B2 (ja) * | 2008-04-10 | 2013-03-21 | 株式会社エヌ・ティ・ティ・ドコモ | レコメンド情報生成装置およびレコメンド情報生成方法 |
JP4645676B2 (ja) * | 2008-04-28 | 2011-03-09 | ソニー株式会社 | 情報処理装置、関連アイテムの提供方法、及びプログラム |
JP4636343B2 (ja) * | 2008-09-02 | 2011-02-23 | ソニー株式会社 | 情報処理装置、情報処理方法、情報処理プログラム及び情報処理システム |
JP4650552B2 (ja) * | 2008-10-14 | 2011-03-16 | ソニー株式会社 | 電子機器、コンテンツ推薦方法及びプログラム |
CN101819570B (zh) * | 2009-02-27 | 2012-08-15 | 国际商业机器公司 | 网络环境中的用户信息处理和资源推荐的方法和系统 |
JP5182178B2 (ja) * | 2009-03-18 | 2013-04-10 | ソニー株式会社 | 情報処理装置及び情報処理方法 |
JP5338450B2 (ja) * | 2009-04-22 | 2013-11-13 | 富士通株式会社 | 再生装置及びプログラム |
JP5409103B2 (ja) * | 2009-04-30 | 2014-02-05 | 株式会社Nttドコモ | レコメンド情報配信装置およびレコメンド情報配信方法 |
JP2011145742A (ja) * | 2010-01-12 | 2011-07-28 | Sony Corp | 情報処理装置、情報処理方法、およびプログラム |
JP5479134B2 (ja) * | 2010-01-29 | 2014-04-23 | 株式会社東芝 | デジタル放送受信機及び録画番組の制御方法 |
KR20110091382A (ko) * | 2010-02-05 | 2011-08-11 | 삼성전자주식회사 | 방송 수신 장치, 방송 프로그램 선택 방법 및 그 저장 매체 |
KR20110108776A (ko) * | 2010-03-29 | 2011-10-06 | 삼성전자주식회사 | 휴대단말기의 사용방법을 제공하는 방법 |
KR101829339B1 (ko) * | 2010-08-19 | 2018-02-19 | 톰슨 라이센싱 | 네트워크 트래픽을 모니터링함으로써 정보 컨텐츠를 개인화 |
KR20130100269A (ko) | 2010-08-19 | 2013-09-10 | 톰슨 라이센싱 | 네트워크 트래픽의 모니터링에 의한 정보 콘텐츠의 개인화 |
JP5578040B2 (ja) * | 2010-11-15 | 2014-08-27 | ソニー株式会社 | 情報処理装置および方法、情報処理システム、並びに、プログラム |
EP2518992A1 (en) * | 2011-04-28 | 2012-10-31 | Axel Springer Digital TV Guide GmbH | Apparatus and method for managing a personal channel |
US8577876B2 (en) * | 2011-06-06 | 2013-11-05 | Met Element, Inc. | System and method for determining art preferences of people |
JP5859771B2 (ja) * | 2011-08-22 | 2016-02-16 | ソニー株式会社 | 情報処理装置、情報処理システム情報処理方法及びプログラム |
CN103699551B (zh) * | 2012-09-27 | 2016-05-04 | 腾讯科技(深圳)有限公司 | 一种信息的推荐方法、服务器及系统 |
US20160065160A1 (en) * | 2013-03-21 | 2016-03-03 | Intellectual Discovery Co., Ltd. | Terminal device and audio signal output method thereof |
US9210461B2 (en) * | 2013-03-27 | 2015-12-08 | Verizon and Redbox Digital Entertainment Services, LLC | Theme-based media program discovery systems and methods |
US10459902B2 (en) * | 2014-06-19 | 2019-10-29 | Nec Corporation | Information processing device, vector data processing method, and recording medium |
US9986299B2 (en) * | 2014-09-22 | 2018-05-29 | DISH Technologies L.L.C. | Scheduled programming recommendation system |
KR20160051983A (ko) * | 2014-10-30 | 2016-05-12 | 현대자동차주식회사 | 차량의 음악 추천 시스템 및 그 방법 |
US9467733B2 (en) | 2014-11-14 | 2016-10-11 | Echostar Technologies L.L.C. | Intuitive timer |
US9503791B2 (en) | 2015-01-15 | 2016-11-22 | Echostar Technologies L.L.C. | Home screen intelligent viewing |
JP6986061B2 (ja) * | 2016-03-17 | 2021-12-22 | Kddi株式会社 | 番組推薦装置、番組推薦方法及び番組推薦プログラム |
JP6641204B2 (ja) * | 2016-03-17 | 2020-02-05 | Kddi株式会社 | 番組推薦装置、番組推薦方法及び番組推薦プログラム |
US9924217B1 (en) | 2016-11-22 | 2018-03-20 | Echostar Technologies L.L.C. | Home screen recommendations determination |
US10231020B2 (en) | 2017-05-16 | 2019-03-12 | The Directv Group, Inc | Sports recommender system utilizing content based filtering |
CN112740721A (zh) * | 2018-09-28 | 2021-04-30 | 索尼公司 | 信息处理装置、方法和程序 |
JP6866466B2 (ja) * | 2019-12-27 | 2021-04-28 | Kddi株式会社 | 番組推薦装置、番組推薦方法及び番組推薦プログラム |
JP6998933B2 (ja) * | 2019-12-27 | 2022-01-18 | Kddi株式会社 | 番組推薦装置、番組推薦方法及び番組推薦プログラム |
CN111563201A (zh) * | 2020-04-29 | 2020-08-21 | 北京三快在线科技有限公司 | 内容推送方法、装置、服务器及存储介质 |
JP2023521565A (ja) * | 2020-09-16 | 2023-05-25 | グーグル エルエルシー | デジタルビデオ分析 |
CN117641004B (zh) * | 2023-11-22 | 2024-05-14 | 北京风平智能科技有限公司 | 一种短视频推荐方法、装置、电子设备及存储介质 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09288683A (ja) * | 1995-09-04 | 1997-11-04 | Matsushita Electric Ind Co Ltd | 情報フィルタ装置及び情報フィルタリング方法 |
US6076082A (en) | 1995-09-04 | 2000-06-13 | Matsushita Electric Industrial Co., Ltd. | Information filtering method and apparatus for preferentially taking out information having a high necessity |
JP2001086420A (ja) * | 1999-09-16 | 2001-03-30 | Matsushita Electric Ind Co Ltd | 放送端末装置 |
JP2001160955A (ja) * | 1999-12-01 | 2001-06-12 | Sony Corp | 放送システム及び受信装置 |
WO2001069921A1 (en) | 2000-03-17 | 2001-09-20 | Koninklijke Philips Electronics N.V. | Method and apparatus for rating database objects |
JP2001282285A (ja) * | 2000-03-31 | 2001-10-12 | Matsushita Electric Ind Co Ltd | 音声認識方法及び音声認識装置、並びにそれを用いた番組指定装置 |
WO2002047381A2 (en) | 2000-12-05 | 2002-06-13 | Koninklijke Philips Electronics N.V. | Method and apparatus for selective updating of a user profile |
WO2002049357A2 (en) | 2000-12-14 | 2002-06-20 | Koninklijke Philips Electronics N.V. | Method and apparatus for generating recommendations based on consistency of selection |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6018738A (en) * | 1998-01-22 | 2000-01-25 | Microsft Corporation | Methods and apparatus for matching entities and for predicting an attribute of an entity based on an attribute frequency value |
US6742003B2 (en) * | 2001-04-30 | 2004-05-25 | Microsoft Corporation | Apparatus and accompanying methods for visualizing clusters of data and hierarchical cluster classifications |
AU2001241604A1 (en) * | 2000-02-18 | 2001-08-27 | Homeportfolio, Inc. | Attribute tagging and matching system and method for database management |
EP1156424A2 (en) * | 2000-05-17 | 2001-11-21 | Matsushita Electric Industrial Co., Ltd. | Information recommendation apparatus and information recommendation system |
US7454775B1 (en) * | 2000-07-27 | 2008-11-18 | Koninklijke Philips Electronics N.V. | Method and apparatus for generating television program recommendations based on similarity metric |
US20040032393A1 (en) * | 2001-04-04 | 2004-02-19 | Brandenberg Carl Brock | Method and apparatus for scheduling presentation of digital content on a personal communication device |
US7149804B2 (en) * | 2001-04-30 | 2006-12-12 | Sony Computer Entertainment America Inc. | Method and system for providing evaluation of text-based products |
JP4098539B2 (ja) * | 2002-03-15 | 2008-06-11 | 富士通株式会社 | プロファイル情報の推薦方法、プログラム及び装置 |
US20030220858A1 (en) * | 2002-05-24 | 2003-11-27 | Duc Lam | Method and system for collaborative vendor reconciliation |
US7171620B2 (en) * | 2002-07-24 | 2007-01-30 | Xerox Corporation | System and method for managing document retention of shared documents |
US6999962B2 (en) * | 2002-08-13 | 2006-02-14 | Xerox Corporation | Shared document repository with coupled recommender system |
JP2004194108A (ja) * | 2002-12-12 | 2004-07-08 | Sony Corp | 情報処理装置および情報処理方法、記録媒体、並びにプログラム |
-
2002
- 2002-12-12 JP JP2002361277A patent/JP2004194108A/ja active Pending
-
2003
- 2003-12-12 EP EP03778859.3A patent/EP1571836B1/en not_active Expired - Lifetime
- 2003-12-12 KR KR1020057010452A patent/KR101007839B1/ko not_active IP Right Cessation
- 2003-12-12 CN CNA2005100965689A patent/CN1750610A/zh active Pending
- 2003-12-12 KR KR1020057011879A patent/KR101029740B1/ko not_active IP Right Cessation
- 2003-12-12 WO PCT/JP2003/015926 patent/WO2004054246A1/ja active Application Filing
- 2003-12-12 EP EP07023836.5A patent/EP1942664A3/en not_active Withdrawn
- 2003-12-12 CN CNB2003801087695A patent/CN100566387C/zh not_active Expired - Fee Related
- 2003-12-12 US US10/538,181 patent/US7577645B2/en not_active Expired - Fee Related
-
2006
- 2006-09-01 US US11/514,255 patent/US7587382B2/en not_active Expired - Fee Related
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09288683A (ja) * | 1995-09-04 | 1997-11-04 | Matsushita Electric Ind Co Ltd | 情報フィルタ装置及び情報フィルタリング方法 |
US6076082A (en) | 1995-09-04 | 2000-06-13 | Matsushita Electric Industrial Co., Ltd. | Information filtering method and apparatus for preferentially taking out information having a high necessity |
JP2001086420A (ja) * | 1999-09-16 | 2001-03-30 | Matsushita Electric Ind Co Ltd | 放送端末装置 |
JP2001160955A (ja) * | 1999-12-01 | 2001-06-12 | Sony Corp | 放送システム及び受信装置 |
US20010049822A1 (en) | 1999-12-01 | 2001-12-06 | Tadao Yoshida | Broadcasting system and reception apparatus |
WO2001069921A1 (en) | 2000-03-17 | 2001-09-20 | Koninklijke Philips Electronics N.V. | Method and apparatus for rating database objects |
JP2001282285A (ja) * | 2000-03-31 | 2001-10-12 | Matsushita Electric Ind Co Ltd | 音声認識方法及び音声認識装置、並びにそれを用いた番組指定装置 |
WO2002047381A2 (en) | 2000-12-05 | 2002-06-13 | Koninklijke Philips Electronics N.V. | Method and apparatus for selective updating of a user profile |
WO2002049357A2 (en) | 2000-12-14 | 2002-06-20 | Koninklijke Philips Electronics N.V. | Method and apparatus for generating recommendations based on consistency of selection |
Non-Patent Citations (1)
Title |
---|
See also references of EP1571836A4 |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108369814A (zh) * | 2015-12-02 | 2018-08-03 | 索尼公司 | 信息处理设备、光盘、信息处理方法与程序 |
CN108369814B (zh) * | 2015-12-02 | 2020-07-17 | 索尼公司 | 信息处理设备、光盘与信息处理方法 |
CN114443967A (zh) * | 2022-04-08 | 2022-05-06 | 北京并行科技股份有限公司 | 一种相似应用推荐方法、计算设备及存储介质 |
Also Published As
Publication number | Publication date |
---|---|
CN100566387C (zh) | 2009-12-02 |
US20060294093A1 (en) | 2006-12-28 |
EP1571836A1 (en) | 2005-09-07 |
KR20050085479A (ko) | 2005-08-29 |
US7587382B2 (en) | 2009-09-08 |
KR101029740B1 (ko) | 2011-04-19 |
EP1571836B1 (en) | 2014-07-16 |
EP1942664A3 (en) | 2016-06-08 |
KR20050074655A (ko) | 2005-07-18 |
US20060129547A1 (en) | 2006-06-15 |
CN1739289A (zh) | 2006-02-22 |
EP1942664A2 (en) | 2008-07-09 |
JP2004194108A (ja) | 2004-07-08 |
US7577645B2 (en) | 2009-08-18 |
CN1750610A (zh) | 2006-03-22 |
EP1571836A4 (en) | 2010-09-08 |
KR101007839B1 (ko) | 2011-01-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2004054246A1 (ja) | 情報処理装置および情報処理方法、記録媒体、並びにプログラム | |
JP4003127B2 (ja) | 情報処理装置および情報処理方法、情報処理システム、記録媒体、並びにプログラム | |
KR101019976B1 (ko) | 정보 처리 장치 및 정보 처리 방법, 정보 처리 시스템, 기록 매체 | |
US8613023B2 (en) | Information processor, information processing method and computer program | |
JP4491746B2 (ja) | 情報処理装置および情報処理方法、記録媒体、並びにプログラム | |
US20170075994A1 (en) | Profile Based Content Retrieval for Recommender Systems | |
JP4182743B2 (ja) | 画像処理装置および方法、記録媒体、並びにプログラム | |
JP4161701B2 (ja) | 情報処理装置および情報処理方法、記録媒体、並びにプログラム | |
JP4501948B2 (ja) | 情報処理装置および情報処理方法、記録媒体、並びにプログラム | |
JP4547596B2 (ja) | 情報処理装置および情報処理方法、並びにプログラム | |
JP4577562B2 (ja) | 情報処理装置および情報処理方法、並びにプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): CN KR US |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PT RO SE SI SK TR |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 1020057010452 Country of ref document: KR |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2003778859 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 20038A87695 Country of ref document: CN |
|
WWP | Wipo information: published in national office |
Ref document number: 1020057010452 Country of ref document: KR |
|
WWP | Wipo information: published in national office |
Ref document number: 2003778859 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2006129547 Country of ref document: US Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 10538181 Country of ref document: US |
|
WWP | Wipo information: published in national office |
Ref document number: 10538181 Country of ref document: US |