CN108777804B - Media playing method and device - Google Patents
Media playing method and device Download PDFInfo
- Publication number
- CN108777804B CN108777804B CN201810538301.8A CN201810538301A CN108777804B CN 108777804 B CN108777804 B CN 108777804B CN 201810538301 A CN201810538301 A CN 201810538301A CN 108777804 B CN108777804 B CN 108777804B
- Authority
- CN
- China
- Prior art keywords
- playing
- characteristic information
- media
- media file
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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]
- H04N21/20—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
-
- 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
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/252—Processing of multiple end-users' preferences to derive collaborative data
-
- 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
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
-
- 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
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user 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
- H04N21/43—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
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
-
- 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
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Computing Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a media playing method and a device, wherein the method comprises the following steps: receiving a media playing instruction, wherein the media playing instruction comprises a playing object identifier and playing indication content; analyzing the playing indication content to obtain the characteristic information of the playing object corresponding to the playing object identification, wherein the characteristic information comprises personality characteristic information and/or emotion characteristic information; searching a first media file identifier matched with the characteristic information of the playing object in a music database; and playing the first media file identified by the first media file identification. By adopting the embodiment of the invention, the corresponding media file can be played based on the characteristic information, and the accuracy of recommending the media file is improved.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a media playing method and apparatus.
Background
With the development of network technology, more and more users listen to or download media files online through the internet or the mobile internet. Taking the media file as music as an example, when a user requests a song, the user needs to provide related information of the music, such as the name and author of the music, and then the server returns a music list meeting the search condition for the user to select. In addition, the user may like a certain kind of music, and thus the music needs to be actively recommended to the user. The conventional music playing method only recommends music related information (e.g., album name, author, genre, etc.), for example, if a user listens to music a, and music a and music B belong to the same album, the user is considered to like music B, so music B is recommended to the user to play music B.
However, in the conventional music playing method, only the music related information is referred to for recommendation, but in practical applications, habits of some users are very different, and two pieces of music with the same related information are often not preferred by the users, so that the accuracy of recommendation by the conventional music playing method is not high.
Disclosure of Invention
The technical problem to be solved by the embodiments of the present invention is to provide a media playing method and apparatus, which can play a corresponding media file based on feature information, and improve the accuracy of media file recommendation.
In order to solve the foregoing technical problem, in a first aspect, an embodiment of the present invention provides a media playing method, where the method includes:
receiving a media playing instruction, wherein the media playing instruction comprises a playing object identifier and playing indication content;
analyzing the playing indication content to obtain the characteristic information of the playing object corresponding to the playing object identification, wherein the characteristic information comprises personality characteristic information and/or emotion characteristic information;
searching a first media file identifier matched with the characteristic information of the playing object in a music database;
and playing the first media file identified by the first media file identification.
In a second aspect, an embodiment of the present invention provides a media playing apparatus, which includes means for executing the method of the first aspect.
In a third aspect, the present invention provides a computer-readable storage medium storing a computer program, where the computer program includes program instructions, and when the program instructions are executed by a network device, the network device executes the method according to the first aspect.
In a fourth aspect, an embodiment of the present invention provides a network device, where the network device includes: a processor, a memory having stored therein program instructions, and a communication interface, the processor calling the program instructions stored in the memory for performing the method according to the first aspect.
By implementing the embodiment of the invention, the media playing instruction is received, the playing instruction content contained in the media playing instruction is analyzed, the characteristic information of the playing object corresponding to the playing object identifier contained in the media playing instruction is obtained, the first media file identifier matched with the characteristic information of the playing object is searched in the music database, the first media file identified by the first media file identifier is played, the characteristic information of the playing object can be obtained in real time based on the media playing instruction, the media file identified by the media file identifier matched with the characteristic information is played, the played media file is more in line with the will of a user, and the recommendation accuracy is higher.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts;
fig. 1 is a schematic flowchart of a media playing method provided in an embodiment of the present invention;
fig. 2 is a flowchart illustrating a media playing method according to another embodiment of the present invention;
fig. 3 is a schematic structural diagram of a media playing apparatus provided in an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a network device provided in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Compared with the traditional media playing method, the method refers to the media related information (such as album name, author, type and the like) to recommend the media files to the user, so that the recommended media files have low degree of engagement with the user's will, and the recommendation accuracy is reduced. The media playing method provided by the embodiment of the application obtains the characteristic information of the playing object corresponding to the playing object identifier contained in the media playing instruction by receiving the media playing instruction and analyzing the playing instruction content contained in the media playing instruction, searches the first media file identifier matched with the characteristic information of the playing object in the music database, plays the first media file identified by the first media file identifier, can obtain the characteristic information of the playing object in real time based on the media playing instruction, plays the media file identified by the media file identifier matched with the characteristic information, and the played media file is more in accordance with the user's will and has higher recommendation accuracy.
The media playing method in the embodiment of the present application may be executed in a terminal or a network device such as a server. The terminal can be operated with a media playing client, such as a Tencent video player, a QQ music player or a WeChat reading client. The terminal can be a personal computer, a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, a palm computer, or a wearable device, etc. The server can be a Tencent video server, a QQ music server or a WeChat reading server and other media playing servers. For example, the client may receive a media playing instruction input by a user, parse the playing instruction content to obtain the feature information of the playing object corresponding to the playing object identifier, search the first media file identifier matching with the feature information of the playing object in the music database, and play the first media file identified by the first media file identifier. For another example, the user inputs a media playing request to the client, the client sends a media playing instruction to the server in response to the media playing request, and the server may analyze the playing instruction content to obtain the feature information of the playing object corresponding to the playing object identifier, search for the first media file identifier matching with the feature information of the playing object in the music database, and play the first media file identified by the first media file identifier. For another example, when the user inputs a media playing instruction to the server, the server may parse the playing instruction content to obtain the feature information of the playing object corresponding to the playing object identifier, search for the first media file identifier matching with the feature information of the playing object in the music database, and play the first media file identified by the first media file identifier.
The media playing instruction in the embodiment of the present application may be text information, image information, or voice information. When the media playing instruction is text information or image information, the network device may use text description content included in the text information as playing instruction content, or perform character recognition on an image indicated by the image information, use the recognized text description content as playing instruction content, and analyze the playing instruction content to obtain personality characteristic information of a playing object. When the media playing instruction is voice information, the network device may use text description content and audio parameters contained in the voice information as playing instruction content, analyze the text description content to obtain personality characteristic information of the playing object, and analyze the audio parameters to obtain emotion characteristic information of the playing object. The media file in the embodiment of the present application may be an audio file or a video file.
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a media playing method according to an embodiment of the present invention. As shown in fig. 1, the media playing method may include at least the following steps:
s101, receiving a media playing instruction, wherein the media playing instruction comprises a playing object identifier and playing instruction content.
The network device may receive a media playing instruction, where the media playing instruction may include a playing object identifier and playing indication content, the playing object identifier may be used to indicate a playing object of the network device, and the playing indication content may be used to indicate a playing requirement. For example, the network device is a media playing client, when a first user has a playing requirement, a media playing account and a password of the first user may be input in a media playing application operated by the terminal to log in the media playing client, the first user may input a media playing instruction in a manner of inputting text information, image information, or voice information in a search area of the media playing client, and the media playing client may receive the media playing instruction input by the user. For another example, the network device is a server, when the first user has a play requirement, the terminal may be controlled to operate the media playing client, the first user may input a media playing request in a manner of inputting text information, image information, or voice information in a search area of the media playing client, and the media playing client responds to the media playing request and sends a media playing instruction to the server.
For example, the media playing instruction is text information "play a song to listen to", the network device may determine that the playing object identifier is a user identifier of the first user, and the user identifier of the first user may be a media playing account input by the first user or a terminal identifier of a permitted media client. The network device may also determine that the play indication content is "play song".
And S102, analyzing the playing indication content to obtain the characteristic information of the playing object corresponding to the playing object identifier, wherein the characteristic information comprises personality characteristic information and/or emotion characteristic information.
After receiving the media playing instruction, the network device may analyze the playing instruction content to obtain the feature information of the playing object corresponding to the playing object identifier. The characteristic information may include personality characteristic information and/or emotion characteristic information. The personality characteristic information is used for indicating the personality characteristics of the playing object, such as an outward type, a conscientious type, a neural type, an associative type, an open type, and the like. The emotional characteristic information is used for indicating the current emotion or mood of the playing object, such as low, excited, tense, dysphoric or sweet, etc.
In a possible implementation manner, the playing instruction content may include text description content, and the network device may search the personality characteristic information matched with the description text content in the personality characteristic information database, and use the searched personality characteristic information as personality characteristic information of the playing object.
For example, the network device may collect sample data (e.g., 10 ten thousand media playing instructions), label personality characteristic information of a provider of the media playing instructions, and generate a personality characteristic identification system. The network device can input the text description content into the personality characteristic identification system, and the personality characteristic information of the playing object is obtained through identification. For example, the network device may train the sample data and personality characteristic information of a provider of a media playing instruction labeled to obtain a personality characteristic identification system, use text description content included in a media playing instruction of a media playing instruction received recently as input of the personality characteristic identification system, and use output of the personality characteristic identification system as personality characteristic information of a playing object. For example, the text description is "play a piece of music to listen to a bar", the network device inputs the text description into the personality characteristic identification system, and the personality characteristic information of the playing object may be identified and obtained in an open manner.
In a possible implementation manner, the playing indication content may include text description content, the network device may perform word segmentation processing on the description text content to obtain at least one first keyword, when the at least one first keyword is found in the keyword database, obtain personality characteristic information corresponding to the at least one keyword, where the keyword database includes the first keyword and personality characteristic information corresponding to the first keyword, and use the personality characteristic information corresponding to the at least one keyword as personality characteristic information of a playing object.
Optionally, the network device establishes a keyword database including the first keyword and personality characteristic information corresponding to the first keyword in advance, where the keyword database may include personality characteristic information corresponding to one keyword or personality characteristic information corresponding to multiple keywords, where personality characteristic information corresponding to a word-oriented assistant such as "bar", "a", or "woolen" is an inclusive type, and the personality characteristic information corresponding to a word-oriented assistant such as "listen to" or "parent" and a word-oriented assistant such as "bar", "a", or "woolen" is an open type. The network device may perform word segmentation processing on the description text content to obtain at least one first keyword, obtain personality characteristic information corresponding to all keywords in the at least one keyword when the at least one first keyword is found in the keyword database, and use the personality characteristic information corresponding to all keywords in the at least one keyword as personality characteristic information of a playing object.
Optionally, the network device may pre-establish a feature value of each first keyword, where the feature value of a word-oriented word such as "bar", "o", or "wool" is 1, the feature value of a superimposed word such as "listen to" or "parent" is 2, the feature value of an adjective such as "romantic" or "cheerful" is 3, and the network device may further establish a corresponding relationship between a feature value sum and personality feature information, where for example, when the feature value sum is 5, the corresponding personality feature information is an arbitrary type, and when the feature value sum is 10, the corresponding personality feature information is an open type. The network device can perform word segmentation processing on the description text content to obtain at least one first keyword, obtain a feature value of each first keyword, add the feature values of each first keyword to obtain a feature value sum, obtain personality feature information corresponding to the feature value sum according to a corresponding relation between the feature value sum and the personality feature information, and use the personality feature information corresponding to the feature value sum as personality feature information of a playing object.
In a possible implementation manner, the playing instruction content may include an audio parameter describing text content of the playing instruction, and when the audio parameter is found in the personality characteristic information database, personality characteristic information corresponding to the audio parameter is obtained, where the personality characteristic information database includes the audio parameter and personality characteristic information corresponding to the audio parameter, and the personality characteristic information corresponding to the audio parameter is used as the personality characteristic information of the playing object. The audio parameters may include a speech rate, a tone, a frequency, a volume, or the like.
For example, the audio parameters of different users are different, and after the network device analyzes the playing indication content to obtain the personality characteristic information of the playing object, the audio parameters of the playing indication content and the personality characteristic information corresponding to the audio parameters may be stored in advance. After the network device receives the media playing instruction latest, whether the provider of the media playing instruction is the existing user can be identified based on the audio parameter of the playing instruction content, and when the provider is the existing user, the network device can acquire the personality characteristic information corresponding to the audio parameter and take the personality characteristic information corresponding to the audio parameter as the personality characteristic information of the playing object. When the user is a new user, the network device may analyze the playing indication content to obtain the personality characteristic information of the playing object corresponding to the playing object identifier, and store the audio parameter of the playing indication content and the personality characteristic information corresponding to the audio parameter.
In a possible implementation manner, the playing instruction content includes an audio parameter of the playing instruction describing the text content, the emotion feature information matched with the audio parameter is searched in the emotion feature information database, and the searched emotion feature information is used as the emotion feature information of the playing object.
For example, the network device may collect sample data (e.g., audio parameters of 200 users), label current emotional feature information of the provider of the audio parameters, and train the emotion recognition model according to the supervised model training method. The network device can identify and obtain the emotion characteristic information of the playing object by taking the audio parameters describing the text content as the input of the emotion identification model.
Optionally, when the speed of speech describing the text content is greater than a first preset threshold, or the tone of speech is greater than a second preset threshold, or the volume is greater than a preset threshold, the network device may determine that the emotional characteristic information of the playing object is excited. When the speed of speech describing the text content is less than or equal to a first preset threshold, the intonation is greater than a second preset threshold, and the volume is greater than the preset threshold, the network device can determine that the emotional characteristic information of the playing object is dysphoria.
Optionally, the network device may pre-establish a feature value of each audio parameter, for example, the feature value of the speech rate in the first speech rate interval is 1, the feature value of the speech rate in the second speech rate interval is 2, the feature value of the intonation in the first intonation interval is 3, the feature value of the intonation in the second intonation interval is 4, the feature value of the volume in the first volume interval is 5, the feature value of the volume in the second volume interval is 6, and the network device may further establish a corresponding relationship between a sum of the feature values and the emotion feature information, for example, when the sum of the feature values is 5, the corresponding emotion feature information is excited, and when the sum of the feature values is 10, the corresponding emotion feature information is dysphoria. The network equipment can obtain at least one audio parameter for describing text content, obtain the characteristic value of each audio parameter, add the characteristic values of each audio parameter to obtain the sum of the characteristic values, obtain the emotional characteristic information corresponding to the sum of the characteristic values according to the corresponding relation between the sum of the characteristic values and the emotional characteristic information, and use the emotional characteristic information corresponding to the sum of the characteristic values as the emotional characteristic information of the playing object.
It should be noted that, if the feature information includes personality feature information and emotional feature information of the playing object, the embodiment of the present invention does not limit the sequence in which the network device acquires the personality feature information and emotional feature information of the playing object, for example, after the network device can acquire the personality feature information of the playing object, the emotional feature information of the playing object is acquired, and if the network device can acquire the emotional feature information of the playing object, the personality feature information of the playing object is acquired, and if the network device can acquire the personality feature information and emotional feature information of the playing object at the same time.
S103, searching a first media file identifier matched with the characteristic information of the playing object in the music database.
In a possible implementation manner, the network device may search the first media file identifier corresponding to the feature information in the music database according to the corresponding relationship between the feature information and the first media file identifier.
In a possible implementation manner, the feature information is personality feature information of the playing object, and the network device may search the first media file identifier corresponding to the personality feature information of the playing object in the music database according to a corresponding relationship between the personality feature information and the first media file identifier. For example, the network device parses the play instruction content to obtain the personality characteristic information of the play object as an outward type, and the first media file identifier corresponding to the outward type is a music identifier with a bright tempo, so that the network device may search for the music identifier with the bright tempo in the music database, for example, "i am today to be married to you". For another example, the network device analyzes the playing instruction content to obtain personality characteristic information of the playing object, the personality characteristic information is a neural type, and the first media file identifier corresponding to the neural type is a music identifier of a deep emotion, so that the network device may search for the music identifier of the deep emotion in the music database, for example, "love like tidal water".
In a possible implementation manner, the feature information is emotion feature information of the playing object, and the network device may search, in the music database, the first media file identifier corresponding to the emotion feature information of the playing object according to a correspondence between the emotion feature information and the first media file identifier. For example, if the network device parses the playing indication content to obtain the emotional characteristic information of the playing object as the sweet, the network device may search the music database for a music identifier corresponding to the sweet, such as "sweet". For another example, if the network device parses the playing indication content to obtain the emotional characteristic information of the playing object as a low level, the network device may search a music identifier corresponding to the low level in the music database, for example, "love like tidal water".
In a possible implementation manner, the feature information is personality feature information and emotion feature information of the playing object, and the network device may search the first media file identifier corresponding to the feature information of the playing object in the music database according to the corresponding relationship between the feature information and the first media file identifier.
Illustratively, the feature information may be a combination of personality feature information and emotional feature information, as shown in the following table:
| outward type | Type of responsibility | Nervous type | Random type | Open type | |
| Low drop | Low falling outward type | Low-grade type of responsibility | Low falling nerve pattern | Low-fall random type | Low drop open type |
| Excitement | Excited outward type | Type of excitation and responsibility | Excitatory nervous type | Type of excitation following harmony | Excited open type |
| Tension | Tense outward type | Type of tension leading to blame | Nervous tension type | Type of tension following | Open type of tension |
| Restlessness | Restlessness and outward syndrome | Restlessness and liability type | Dysphoria with nerve pattern | Restlessness and restlessness type | Dysphoria open type |
| Sweet taste | Sweet outward type | Sweet type of responsibility | Sweet nerve type | Sweet random type | Sweet open type |
For example, the music identifier "sweet" in the music database is marked as a sweet open type, the music identifier "love like tidewater" is marked as a low open type, and the network device determines that the feature information of the playing object is the low open type, so that the first media file identifier corresponding to the found feature information of the playing object may be "love like tidewater".
It should be noted that, the manner of determining, by the network device, the first media file identifier corresponding to the feature information includes, but is not limited to, the manner described above, for example, the personality feature information and the emotion feature information of the playing object may be used as coefficient factors to obtain the first media file identifier matching with the feature information of the playing object, for example, based on the weight of the emotion feature information and the weight of the personality feature information, performing weighted summation, and obtaining the first media file identifier matching with the feature information of the playing object according to the result of the weighted summation.
S104, playing the first media file identified by the first media file identification.
For example, if the network device is a server, after the network device searches for a first media file identifier matching with the feature information of the playing object in the music database, the network device may send the first media file identifier to the media playing client, the terminal running the media playing client may display the first media file identifier in a display screen of the terminal, and when the terminal detects a selection operation of the first media file identifier by the user, the terminal plays the media file identified by the target media file identifier selected by the user.
For another example, if the network device is a server, after the network device searches for the first media file identifier matching the feature information of the playing object in the music database, the first media file identifier is displayed in a display screen of the network device, and when the network device detects a selection operation of the first media file identifier by the user, the network device plays the media file identified by the target media file identifier selected by the user.
For another example, if the network device is a media playing client, after the network device searches for a first media file identifier matching with the feature information of the playing object in the music database, a terminal running the media playing client displays the first media file identifier in a display screen of the terminal, and when the terminal detects a selection operation of the first media file identifier by a user, the terminal plays a media file identified by a target media file identifier selected by the user.
In the embodiment of the invention, a media playing instruction is received, playing instruction content contained in the media playing instruction is analyzed, characteristic information of a playing object corresponding to a playing object identifier contained in the media playing instruction is obtained, a first media file identifier matched with the characteristic information of the playing object is searched in a music database, a first media file identified by the first media file identifier is played, the characteristic information of the playing object can be obtained in real time based on the media playing instruction, the media file identified by the media file identifier matched with the characteristic information is played, the played media file is more in accordance with the will of a user, and the recommendation accuracy is higher.
In a possible media playing method, after receiving the media playing instruction, the network device may detect whether the playing indication content includes a third media file identifier, and when the playing indication content includes the third media file identifier, the network device may play a third media file identified by the third media file identifier. When the playing instruction content does not include the third media file identifier, the network device may analyze the playing instruction content included in the media playing instruction, obtain the feature information of the playing object corresponding to the playing object identifier included in the media playing instruction, search the first media file identifier matched with the feature information of the playing object in the music database, play the first media file identified by the first media file identifier, obtain the feature information of the playing object in real time based on the media playing instruction, play the media file identified by the media file identifier matched with the feature information, the played media file is more in accordance with the user's will, and the recommendation accuracy is higher.
For example, in a language intelligent product such as a smart speaker, a user requests to play music through a media playing instruction, and if the playing instruction content is "forget to play liu deli water", the network device may determine that the playing instruction content includes a third media file identifier, for example, the third media file identifier is "forget water", and the singer is liu deli ", so as to play the forget water" that the singer sings liu deli. If the playing indication content is ' playing romantic music ', the network device may determine that the playing indication content does not include the third media file identifier, and further determine the will and interest of the user, and play music matching the user's will and interest.
In one possible media playing method, after receiving a media playing instruction, the network device may detect whether the playing instruction content includes a second keyword, where the second keyword may be a parent name of a wife, a girl friend, a baby, or the like, or a person name of a millet, a xiaoming, or the like. When the playing indication content does not contain the second keyword, the network device may determine that the playing object is a provider of the media playing instruction. Furthermore, the network device may analyze the playing instruction content included in the media playing instruction, obtain the feature information of the playing object corresponding to the playing object identifier included in the media playing instruction, search the first media file identifier matched with the feature information of the playing object in the music database, play the first media file identified by the first media file identifier, obtain the feature information of the playing object in real time based on the media playing instruction, play the media file identified by the media file identifier matched with the feature information, the played media file more conforms to the will of the provider of the media playing instruction, and the recommendation accuracy is high.
In one possible media playing method, after receiving a media playing instruction, the network device may detect whether the playing instruction content includes a second keyword, where the second keyword may be a parent name of a wife, a girl friend, a baby, or the like, or a person name of a millet, a xiaoming, or the like. When the play instruction content includes the second keyword, the network device may determine that the play object is the second user indicated by the second keyword. Further, the network device may search the music database for a second media file identifier matching the second user, and play the second media file identified by the second media file identifier.
Illustratively, the play indication content is "put a song to a girlfriend", the network device may determine that the play object is "girlfriend". Further, the network device may look up the music identifier preferred by women, such as "honey", in the music database and play the song "honey".
In a possible media playing method, after receiving the media playing instruction, the network device may detect whether the playing instruction content includes a second keyword, and when the playing instruction content includes the second keyword, the network device may determine that the playing object is a second user indicated by the second keyword. Further, the network device may obtain historical behavior data associated with the second user from the instant messaging information of the first user sending the media playing instruction, analyze the historical behavior data to obtain feature information of the second user, search a second media file identifier matched with the feature information of the second user in the music database, and play the second media file identified by the second media file identifier.
Illustratively, the play indication content is "put a song to a girlfriend", the network device may determine that the play object is "girlfriend". Further, the network device may obtain historical behavior data associated with the "girlfriend" in an interface such as a friend circle, a QQ space, or an instant messaging session window related to the "girlfriend" of the provider of the media playing instruction, parse the historical behavior data to obtain feature information of the "girlfriend" as a low-fall open type, and the network device may search a music database for a music identifier of the low-fall open type, for example, "love like tidal water", and play a song, "love like tidal water". For example, the manner in which the network device parses the historical behavior data to obtain the feature information of the second user may be the same as the manner in which the network device parses the play instruction content to obtain the feature information of the play object corresponding to the play object identifier. The characteristic information of the second user may include personality characteristic information and/or emotional characteristic information of the second user.
In a possible media playing method, a network device receives a media playing instruction, analyzes playing instruction content contained in the media playing instruction, obtains personality characteristic information of a playing object corresponding to the playing object identifier contained in the media playing instruction, searches a first media file identifier matched with the personality characteristic information of the playing object in a music database, further analyzes the playing instruction content contained in the media playing instruction, obtains emotion characteristic information of the playing object, searches a target media file identifier matched with the emotion characteristic information of the playing object in the first media file identifier, and plays a target media file identified by the target media file identifier.
In a possible media playing method, a network device receives a media playing instruction, analyzes playing instruction content contained in the media playing instruction, obtains emotion feature information of a playing object corresponding to the playing object identifier contained in the media playing instruction, searches a first media file identifier matched with the emotion feature information of the playing object in a music database, further analyzes the playing instruction content contained in the media playing instruction, obtains personality feature information of the playing object, searches a target media file identifier matched with the personality feature information of the playing object in the first media file identifier, and plays a target media file identified by the target media file identifier.
Taking the media playing method shown in fig. 2 as an example, after receiving a voice instruction (for example, a user voice instruction collected by a smart speaker), the network device may perform text feature extraction, specifically, extract text content from the voice instruction. The network device can also generate a personality characteristic identification system by collecting sample data (for example, 10 ten thousand text instructions) and performing labeling (labeling the personality characteristics to which the provider of the text instructions belongs). And inputting the text feature extraction result into a personality feature recognition system, recognizing the personality feature classification of the user, and acquiring the personality feature description of the user according to the recognized personality feature classification.
After the network device receives the voice instruction, audio feature extraction may also be performed, specifically, the acoustic feature may be extracted from the voice instruction. After the network device extracts the acoustic features, it may use a voiceprint technology to identify whether the user sending the voice command is an existing user, and the manner of identifying whether the user sending the voice command is an existing user by using the voiceprint technology may specifically be: the method comprises the steps of obtaining a historical voice instruction obtained before receiving a current voice instruction, storing audio features of the historical voice instruction to obtain a user identification model, inputting the result of audio feature extraction to the user identification model after the current voice instruction is subjected to audio feature extraction, identifying whether a user is an existing user or a new user, and storing voiceprint records and personality feature descriptions of the new user in a user feature database if the user is the new user. If the user is an existing user, the personality characteristic description corresponding to the voiceprint record of the user can be directly searched in the user characteristic database without carrying out text characteristic extraction operation.
After the network device performs audio feature extraction, emotion recognition may also be performed, for example, audio files of 200 persons are collected, and emotion labeling is performed on the 200 persons when audio is collected. And training the emotion recognition model according to a supervised model training method. The emotion of the user when the voice command is sent is recognized through the emotion recognition model, and the emotion is low, excited, tense, irritated, sweet and the like. Further, the music database may store a plurality of audio files and their audio file identifications, and the music feature library may include music feature information of each audio file labeled manually or by machine, such as singer, album, genre, rhythm or used musical instrument. The music recommendation system can be used as a recommendation coefficient factor by combining the personality characteristics and the emotion characteristics, for example, the music recommendation system can select a music list to be randomly recommended according to the personality characteristics and the emotion characteristics of the user and the response labels according to the recognition result of the voice instruction. Examples are: the mark is sweet openness, the mark is love like tidal water, and the mark is excitement openness. Suppose a personality trait that an open user says "play a piece of music to listen to a bar," this piece of audio is recognized and the mood is recognized as sweet. The music player plays the sweet honey to the user. Assuming that the piece of audio is recognized and the emotion of the voice is recognized as "excited", the music player plays "I want to be married to you today".
Referring to fig. 3, fig. 3 is a schematic structural diagram of a media playing device provided in an embodiment of the present invention, and as shown in the diagram, the media playing device in the embodiment of the present invention at least may include a receiving unit 301, a processing unit 302, and an output unit 303, where:
a receiving unit 301, configured to receive a media playing instruction, where the media playing instruction includes a playing object identifier and a playing instruction content;
a processing unit 302, configured to analyze the playing indication content to obtain feature information of the playing object corresponding to the playing object identifier, where the feature information includes personality feature information and/or emotion feature information;
the processing unit 302 is further configured to search a music database for a first media file identifier matching the feature information of the playing object;
an output unit 303, configured to play the first media file identified by the first media file identifier.
Optionally, the playing instruction content includes: playing the indicated description text content;
the analyzing, by the processing unit 302, the playing indication content to obtain the feature information of the playing object corresponding to the playing object identifier includes:
searching the personality characteristic information matched with the description text content in a personality characteristic information database;
and taking the searched personality characteristic information as the personality characteristic information of the playing object.
Optionally, the playing instruction content includes: playing the indicated description text content;
the analyzing, by the processing unit 302, the playing indication content to obtain the feature information of the playing object corresponding to the playing object identifier includes:
performing word segmentation processing on the description text content to obtain at least one first keyword;
when the at least one first keyword is found in the keyword database, acquiring personality characteristic information corresponding to the at least one keyword, wherein the keyword database comprises the first keyword and the personality characteristic information corresponding to the first keyword;
and taking the personality characteristic information corresponding to the at least one keyword as the personality characteristic information of the playing object.
Optionally, the playing instruction content includes: playing the indicated audio parameters describing the text content;
the analyzing, by the processing unit 302, the playing indication content to obtain the feature information of the playing object corresponding to the playing object identifier includes:
when the audio parameters are found in a personality characteristic information database, acquiring personality characteristic information corresponding to the audio parameters, wherein the personality characteristic information database comprises the audio parameters and the personality characteristic information corresponding to the audio parameters;
and taking the personality characteristic information corresponding to the audio parameters as the personality characteristic information of the playing object.
Optionally, the playing instruction content includes: playing the indicated audio parameters describing the text content;
the analyzing, by the processing unit 302, the playing indication content to obtain the feature information of the playing object corresponding to the playing object identifier includes:
searching emotion characteristic information matched with the audio parameters in an emotion characteristic information database;
and taking the searched emotional characteristic information as the emotional characteristic information of the playing object.
Optionally, the searching, by the processing unit 302, a first media file identifier matching with the feature information of the playing object in a music database includes:
and searching the first media file identifier corresponding to the characteristic information in the music database according to the corresponding relation between the characteristic information and the first media file identifier.
Optionally, after the receiving unit 301 receives the media playing instruction, the method further includes:
when the playing object is the first user who sends the media playing instruction, the trigger processing unit 302 analyzes the playing instruction content to obtain the characteristic information of the playing object corresponding to the playing object identifier.
Optionally, the processing unit 302 is further configured to, after the receiving unit 301 receives a media playing instruction, search, in the music database, a second media file identifier matched with a second user when the playing object is the second user indicated by the playing instruction content;
the output unit 303 is further configured to play a second media file corresponding to the second media file identifier.
Optionally, the searching, by the processing unit 302, for a second media file identifier matching the second user in the music database includes:
acquiring historical behavior data associated with the second user from instant messaging information of the first user sending the media playing instruction;
analyzing the historical behavior data to obtain the characteristic information of the second user;
and searching a second media file identifier matched with the characteristic information of the second user in the music database.
Optionally, the processing unit 302 is further configured to determine that the playing object is the first user when the playing instruction content does not include the second keyword after the receiving unit 301 receives the media playing instruction; and when the playing indication content contains the second keyword, determining that the playing object is a second user indicated by the second keyword.
In the embodiment of the present invention, the receiving unit 301 receives a media playing instruction, where the media playing instruction includes a playing object identifier and a playing indication content, the processing unit 302 parses the playing indication content to obtain feature information of a playing object corresponding to the playing object identifier, the processing unit 302 searches a music database for a first media file identifier matching with the feature information of the playing object, and the output unit 303 plays a first media file identified by the first media file identifier, so as to improve accuracy of media file recommendation.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a network device according to an embodiment of the present invention, where the network device according to the embodiment of the present invention may be used to implement the method implemented by the embodiment of the present invention shown in fig. 1 and 2, for convenience of description, only the part related to the embodiment of the present invention is shown, and details of the specific technology are not disclosed, please refer to the embodiment of the present invention shown in fig. 1 and 2.
As shown in fig. 4, the network device includes: at least one processor 401, such as a CPU, at least one input device 403, at least one output device 404, memory 405, at least one communication bus 402. Wherein a communication bus 402 is used to enable connective communication between these components. The input device 403 may be a network interface, a control panel, or a microphone, and is used for interacting with the client. The output device 404 may be a speaker or a display screen, and is used for playing media files. Memory 405 may include a high speed RAM memory and may also include non-volatile memory. The memory 405 may optionally include at least one memory device located remotely from the processor 401 as previously described. The processor 401 may be incorporated in the media playing device shown in fig. 3. A set of program codes is stored in the memory 405, and the processor 401, the input device 403, and the output device 404 call the program codes stored in the memory 405 for performing the following operations:
the input device 403 receives a media playing instruction, where the media playing instruction includes a playing object identifier and playing instruction content;
the processor 401 analyzes the playing indication content to obtain feature information of the playing object corresponding to the playing object identifier, where the feature information includes personality feature information and/or emotion feature information;
the processor 401 searches a music database for a first media file identifier matched with the characteristic information of the playing object;
Optionally, the playing instruction content includes: playing the indicated description text content;
the analyzing, by the processor 401, the play instruction content to obtain the feature information of the play object corresponding to the play object identifier includes:
searching the personality characteristic information matched with the description text content in a personality characteristic information database;
and taking the searched personality characteristic information as the personality characteristic information of the playing object.
Optionally, the playing instruction content includes: playing the indicated description text content;
the analyzing, by the processor 401, the play instruction content to obtain the feature information of the play object corresponding to the play object identifier includes:
performing word segmentation processing on the description text content to obtain at least one first keyword;
when the at least one first keyword is found in the keyword database, acquiring personality characteristic information corresponding to the at least one keyword, wherein the keyword database comprises the first keyword and the personality characteristic information corresponding to the first keyword;
and taking the personality characteristic information corresponding to the at least one keyword as the personality characteristic information of the playing object.
Optionally, the playing instruction content includes: playing the indicated audio parameters describing the text content;
the analyzing, by the processor 401, the play instruction content to obtain the feature information of the play object corresponding to the play object identifier includes:
when the audio parameters are found in a personality characteristic information database, acquiring personality characteristic information corresponding to the audio parameters, wherein the personality characteristic information database comprises the audio parameters and the personality characteristic information corresponding to the audio parameters;
and taking the personality characteristic information corresponding to the audio parameters as the personality characteristic information of the playing object.
Optionally, the playing instruction content includes: playing the indicated audio parameters describing the text content;
the analyzing, by the processor 401, the play instruction content to obtain the feature information of the play object corresponding to the play object identifier includes:
searching emotion characteristic information matched with the audio parameters in an emotion characteristic information database;
and taking the searched emotional characteristic information as the emotional characteristic information of the playing object.
Optionally, the searching, by the processor 401, the first media file identifier matched with the feature information of the playing object in the music database includes:
and searching the first media file identifier corresponding to the characteristic information in the music database according to the corresponding relation between the characteristic information and the first media file identifier.
Optionally, after the input device 403 receives the media playing instruction, the method further includes:
when the playing object is the first user who sends the media playing instruction, the trigger processor 401 analyzes the playing instruction content to obtain the characteristic information of the playing object corresponding to the playing object identifier.
Optionally, after the input device 403 receives the media playing instruction, the method further includes:
when the playing object is a second user indicated by the playing instruction content, the processor 401 searches the music database for a second media file identifier matched with the second user;
the output device 404 plays the second media file corresponding to the second media file identifier.
Optionally, the processor 401 searches the music database for a second media file identifier matching the second user, including:
acquiring historical behavior data associated with the second user from instant messaging information of the first user sending the media playing instruction;
analyzing the historical behavior data to obtain the characteristic information of the second user;
and searching a second media file identifier matched with the characteristic information of the second user in the music database.
Optionally, after the input device 403 receives the media playing instruction, the method further includes:
when the playing indication content does not contain the second keyword, the processor 401 determines that the playing object is the first user;
when the playing instruction content includes the second keyword, the processor 401 determines that the playing object is the second user indicated by the second keyword.
Specifically, the server described in the embodiment of the present invention may be used to implement part or all of the processes in the embodiment of the method described in conjunction with fig. 1 and 2.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (9)
1. A media playing method, comprising:
receiving a media playing instruction, wherein the media playing instruction comprises a playing object identifier and playing indication content;
when the playing object is a second user indicated by the playing indication content, obtaining historical behavior data associated with the second user in instant messaging information of a first user sending the media playing instruction, wherein the second user is not the same user as the first user;
analyzing the historical behavior data to obtain the characteristic information of the second user;
searching a second media file identifier matched with the characteristic information of the second user in a music database;
playing a second media file corresponding to the second media file identifier;
when the playing object is the first user sending the media playing instruction, analyzing the playing instruction content to obtain the characteristic information of the playing object corresponding to the playing object identification, wherein the characteristic information comprises personality characteristic information and/or emotion characteristic information;
searching a first media file identifier matched with the characteristic information of the playing object in a music database;
and playing the first media file identified by the first media file identification.
2. The method of claim 1, wherein the playing the instructional content comprises: playing the indicated description text content;
the analyzing the playing indication content to obtain the characteristic information of the playing object corresponding to the playing object identifier includes:
searching the personality characteristic information matched with the description text content in a personality characteristic information database;
and taking the searched personality characteristic information as the personality characteristic information of the playing object.
3. The method of claim 1, wherein the playing the instructional content comprises: playing the indicated description text content;
the analyzing the playing indication content to obtain the characteristic information of the playing object corresponding to the playing object identifier includes:
performing word segmentation processing on the description text content to obtain at least one first keyword;
when the at least one first keyword is found in the keyword database, acquiring personality characteristic information corresponding to the at least one keyword, wherein the keyword database comprises the first keyword and the personality characteristic information corresponding to the first keyword;
and taking the personality characteristic information corresponding to the at least one keyword as the personality characteristic information of the playing object.
4. The method of claim 1, wherein the playing the instructional content comprises: playing the indicated audio parameters describing the text content;
the analyzing the playing indication content to obtain the characteristic information of the playing object corresponding to the playing object identifier includes:
when the audio parameters are found in a personality characteristic information database, acquiring personality characteristic information corresponding to the audio parameters, wherein the personality characteristic information database comprises the audio parameters and the personality characteristic information corresponding to the audio parameters;
and taking the personality characteristic information corresponding to the audio parameters as the personality characteristic information of the playing object.
5. The method of claim 1, wherein the playing the instructional content comprises: playing the indicated audio parameters describing the text content;
the analyzing the playing indication content to obtain the characteristic information of the playing object corresponding to the playing object identifier includes:
searching emotion characteristic information matched with the audio parameters in an emotion characteristic information database;
and taking the searched emotional characteristic information as the emotional characteristic information of the playing object.
6. The method of claim 1, wherein the searching for the first media file identifier in the music database that matches the characterizing information of the playing object comprises:
and searching the first media file identifier corresponding to the characteristic information in the music database according to the corresponding relation between the characteristic information and the first media file identifier.
7. The method of claim 1, wherein after receiving the media play instruction, further comprising:
when the playing indication content does not contain a second keyword, determining that the playing object is the first user;
and when the playing indication content contains the second keyword, determining that the playing object is a second user indicated by the second keyword.
8. A media playback apparatus, characterized in that the apparatus comprises means for performing the method according to any of claims 1-7.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program comprising program instructions that, when executed by a network device, cause the network device to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810538301.8A CN108777804B (en) | 2018-05-30 | 2018-05-30 | Media playing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810538301.8A CN108777804B (en) | 2018-05-30 | 2018-05-30 | Media playing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108777804A CN108777804A (en) | 2018-11-09 |
| CN108777804B true CN108777804B (en) | 2021-07-27 |
Family
ID=64028219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810538301.8A Active CN108777804B (en) | 2018-05-30 | 2018-05-30 | Media playing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108777804B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109712646A (en) * | 2019-02-20 | 2019-05-03 | 百度在线网络技术（北京）有限公司 | Voice broadcast method, device and terminal |
| CN113139079B (en) * | 2021-04-15 | 2022-10-04 | 合肥中聚源智能科技有限公司 | Music recommendation method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598644A (en) * | 2015-02-12 | 2015-05-06 | 腾讯科技（深圳）有限公司 | User fond label mining method and device |
| CN105095406A (en) * | 2015-07-09 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for voice search based on user feature |
| CN105530521A (en) * | 2015-12-16 | 2016-04-27 | 广东欧珀移动通信有限公司 | Streaming media searching method, device and system |
| CN105956059A (en) * | 2016-04-27 | 2016-09-21 | 乐视控股（北京）有限公司 | Emotion recognition-based information recommendation method and apparatus |
| CN106202103A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | Music recommends method and apparatus |
| CN106407287A (en) * | 2016-08-29 | 2017-02-15 | 宇龙计算机通信科技(深圳)有限公司 | Multimedia resource pushing method and system |
| CN106528859A (en) * | 2016-11-30 | 2017-03-22 | 英华达（南京）科技有限公司 | Data pushing system and method |
| CN107943894A (en) * | 2017-11-16 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushing content of multimedia |
| CN108038243A (en) * | 2017-12-28 | 2018-05-15 | 广东欧珀移动通信有限公司 | Music recommends method, apparatus, storage medium and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8909637B2 (en) * | 2011-06-03 | 2014-12-09 | Facebook, Inc. | Context-based ranking of search results |
-
2018
- 2018-05-30 CN CN201810538301.8A patent/CN108777804B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598644A (en) * | 2015-02-12 | 2015-05-06 | 腾讯科技（深圳）有限公司 | User fond label mining method and device |
| CN106202103A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | Music recommends method and apparatus |
| CN105095406A (en) * | 2015-07-09 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for voice search based on user feature |
| CN105530521A (en) * | 2015-12-16 | 2016-04-27 | 广东欧珀移动通信有限公司 | Streaming media searching method, device and system |
| CN105956059A (en) * | 2016-04-27 | 2016-09-21 | 乐视控股（北京）有限公司 | Emotion recognition-based information recommendation method and apparatus |
| CN106407287A (en) * | 2016-08-29 | 2017-02-15 | 宇龙计算机通信科技(深圳)有限公司 | Multimedia resource pushing method and system |
| CN106528859A (en) * | 2016-11-30 | 2017-03-22 | 英华达（南京）科技有限公司 | Data pushing system and method |
| CN107943894A (en) * | 2017-11-16 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushing content of multimedia |
| CN108038243A (en) * | 2017-12-28 | 2018-05-15 | 广东欧珀移动通信有限公司 | Music recommends method, apparatus, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108777804A (en) | 2018-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9582757B1 (en) | Scalable curation system | |
| CN108153800B (en) | Information processing method, information processing apparatus, and recording medium | |
| CN104598644B (en) | Favorite label mining method and device | |
| US20100125539A1 (en) | Hybrid audio-visual categorization system and method | |
| CN109451147B (en) | Information display method and device | |
| CN110188356B (en) | Information processing method and device | |
| CN104281622A (en) | Information recommending method and information recommending device in social media | |
| US11842721B2 (en) | Systems and methods for generating synthesized speech responses to voice inputs by training a neural network model based on the voice input prosodic metrics and training voice inputs | |
| US11354754B2 (en) | Generating self-support metrics based on paralinguistic information | |
| CN111475714A (en) | Information recommendation method, device, equipment and medium | |
| CN111737414B (en) | Song recommendation method and device, server and storage medium | |
| CN106250400A (en) | A kind of audio data processing method, device and system | |
| CN109165336B (en) | Information output control method and family education equipment | |
| EP3087505A1 (en) | System and methods for vocal commenting on selected web pages | |
| CN109615009B (en) | Learning content recommendation method and electronic equipment | |
| CN107679196A (en) | A kind of multimedia recognition methods, electronic equipment and storage medium | |
| US20190083886A1 (en) | Dynamic Modification of Audio Playback in Games | |
| CN108777804B (en) | Media playing method and device | |
| CN114817582A (en) | Resource information pushing method and electronic device | |
| CN105895079A (en) | Voice data processing method and device | |
| CN111460215B (en) | Audio data processing method and device, computer equipment and storage medium | |
| CN109657049B (en) | Composition training method based on big data analysis and learning equipment | |
| CN113920996A (en) | Voice interaction processing method and device, electronic equipment and storage medium | |
| CN110830595B (en) | Personalized music pushing method and system | |
| JP2021012660A (en) | Information processing device, information processing method, and information processing program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |