CN109545232A - Information-pushing method, information push-delivery apparatus and interactive voice equipment - Google Patents
Information-pushing method, information push-delivery apparatus and interactive voice equipment Download PDFInfo
- Publication number
- CN109545232A CN109545232A CN201910054466.2A CN201910054466A CN109545232A CN 109545232 A CN109545232 A CN 109545232A CN 201910054466 A CN201910054466 A CN 201910054466A CN 109545232 A CN109545232 A CN 109545232A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- target
- voice messaging
- voice
- 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.)
- Pending
Links
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000001755 vocal effect Effects 0.000 claims abstract description 38
- 230000006870 function Effects 0.000 claims description 61
- 238000012216 screening Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 19
- 238000003058 natural language processing Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 abstract description 11
- 238000004378 air conditioning Methods 0.000 description 16
- 238000004458 analytical method Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 8
- 238000000605 extraction Methods 0.000 description 8
- 230000008901 benefit Effects 0.000 description 5
- 241001269238 Data Species 0.000 description 4
- 230000003796 beauty Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
- H04L51/10—Multimedia information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/21—Monitoring or handling of messages
- H04L51/214—Monitoring or handling of messages using selective forwarding
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Information Transfer Between Computers (AREA)
- User Interface Of Digital Computer (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of information-pushing method, information push-delivery apparatus and interactive voice equipment, wherein, information-pushing method includes: to determine the attribute information of user according to the recognition result to collected first voice messaging, with determining and at least one matched Adapted information of attribute information；According to the recognition result to collected second voice messaging, it determines corresponding semantic information, to filter out the target information at least one Adapted information according to semantic information, and is pushed to user, wherein, the second voice messaging is matched with the vocal print feature of the first voice messaging.According to the technical solution of the present invention, for the equipment with voice interactive function, it is able to ascend specific aim, validity and the reliability to user demand feedback, and it can be based on the training of different application scenarios and the different types of information of storage, to meet the needs of different application scene, to promote the versatility of the equipment.
Description
Technical field
The present invention relates to multimedia equipment technical fields, push in particular to a kind of information of interactive voice equipment
Method, a kind of information push-delivery apparatus of interactive voice equipment and a kind of interactive voice equipment.
Background technique
In the related technology, speech robot people can be fed back accordingly after certain language of identification user, but be deposited
In following defect:
Actual operation is poor, can not make effective Feedback for the specific requirements of user, lead to speech robot people not
Its function can be given full play to.
In addition, any discussion of the whole instruction to background technique, not representing the background technique must be fields
The prior art that technical staff is known, not representing in the whole instruction to any discussion of the prior art think that this is existing
Technology must be widely known or certain common knowledge for constituting this field.
Summary of the invention
The present invention is directed to solve at least one of the technical problems existing in the prior art or related technologies.
For this purpose, it is an object of the present invention to provide a kind of information-pushing methods of interactive voice equipment.
It is another object of the present invention to provide a kind of information push-delivery apparatus of interactive voice equipment.
It is another object of the present invention to provide a kind of interactive voice equipment.
To achieve the goals above, according to the embodiment of the first aspect of the invention, a kind of interactive voice equipment is provided
Information-pushing method, comprising: according to the recognition result to collected first voice messaging, determine the attribute information of user,
With determining and at least one matched Adapted information of attribute information；According to the recognition result to collected second voice messaging,
Corresponding semantic information is determined, to filter out the target information at least one Adapted information according to semantic information, and by target
Information is pushed to user, wherein the second voice messaging is matched with the vocal print feature of the first voice messaging.
In the technical scheme, by receiving at least two sections of languages including above-mentioned first voice messaging and the second voice messaging
Message breath, and the first voice messaging is identified and parsed with the second voice messaging, to be identified by the first voice messaging
Out after the attribute information of user, generation and at least one matched Adapted information of attribute information, to meet to different attribute
User recommends the demand of different information, further, in conjunction with the recognition result to the second voice messaging, can to it is above-mentioned at least
One Adapted information further progress screening, to obtain the target information for meeting the individual subscriber, and target information is pushed to
User, on the one hand, for the equipment with voice interactive function, be able to ascend the specific aim to user demand feedback, validity
It on the other hand can be answered with reliability based on the training of different application scenarios and the different types of information of storage with meeting difference
With the demand of scene, to promote the versatility of the equipment.
Specifically, by taking shopping guide's scene as an example, the speech robot people with voice interactive function can be by receiving user's
First voice messaging identifies that the attribute information of user obtains matched Adapted information and (use after determining the attribute of user
Family can be interested be in the product of which type), the intention of user is further identified according to the second voice messaging received, with
Specifically intended according to user screens Adapted information, with target information needed for obtaining user, and then realizes phonetic machine
Shopping guide's function of device people.
In the above-mentioned technical solutions, according to the recognition result to collected first voice messaging, the attribute of user is determined
Information specifically includes: generating guidance voice broadcast message, and receives and believed according to the first voice of guidance voice broadcast message feedback
Breath；According to the parsing result of the vocal print feature to the first voice messaging, user gender information is determined；According to the first voice messaging
In digital information recognition result, determine age of user information；It is determined and is used according to age of user information and user gender information
The attribute information at family.
In the technical scheme, before acquiring the first voice messaging, guidance voice broadcast message can be played, first to draw
It leads user and describes the information such as the Sex, Age of oneself, user's gender directly can be determined by the first voice messaging of analysis in this way
With the age etc., further, if user answers not according to guidance voice broadcast message, it can directly pass through analysis the
Vocal print feature in one voice messaging determines gender information and the age information of user, or by the first voice messaging of identification
Digital information determine the age information of user, then determine age bracket described in age of user, in conjunction with the gender of user, make
For user property, can search and the matched Adapted information of user property.
Specifically, age of user can be divided into multiple age brackets, such as 18 years old to 28 years old, 29 years old to 40 years old, 41 years old
To 50 years old, with first-class, in conjunction with gender information, as the attribute information of definition, for example when executing shopping guide's function, 18 years old extremely within 50 years old
28 years old male users are interested in electronic product, and 29 years old to 40 years old female user is interested in beauty class product
Deng using as match information to be recommended.
In any of the above-described technical solution, interactive voice equipment is additionally provided with image collecting device, is generating leading question
Sound broadcast message, and receive according to before the first voice messaging for guiding voice broadcast message feedback, further includes: response is collected
User images information generates guidance voice broadcast message.
In the technical scheme, by detecting whether to collect the image information of user, in the image for collecting user
When information, show then to can be generated at this time with the user for needing to carry out interactive voice and broadcast them guidance voice broadcast service is believed
Breath, so that the triggering of interactive voice is realized, to prevent from collecting useless voice messaging.
Furthermore it is also possible to by setting trigger module, such as key, touch device etc., it is current whether in need to detect
Carry out the user of interactive voice.
In any of the above-described technical solution, determining and at least one matched Adapted information of attribute information is specifically included:
It determines in the information bank prestored and recommends target with the matched at least one kind of attribute information, and at least one kind is recommended to the information of target
It is determined as Adapted information.
In the technical scheme, Adapted information is specifically as follows recommendation target, is directed to user to realize by interactive voice
The recommendation function of attribute and user demand, to promote the applicability and practicability of interactive voice equipment.
In any of the above-described technical solution, analogize in determining the information bank prestored with attribute information matched at least one
Before recommending target, further includes: determine the corresponding satisfaction concern threshold value of each user property according to the user's history record being collected into
It is at least a kind of to recommend target；According to user property and target is recommended to generate the information bank prestored.
In the technical scheme, big data analysis is carried out by a large number of users historical record being collected into, it is every to determine
One or more of recommendation targets that user under a user property is most interested in, and establish user property and recommend between target
Association matching, to will be associated with matched a kind of or several after parsing user property according to the first voice messaging received
Kind recommends Objective extraction to come out, and target can be recommended these to make further to screen, these directly can also be recommended target
It is pushed to user.
In any of the above-described technical solution, further includes: by target information in the form of audio-frequency information and/or video information
It is pushed to user.
In the technical scheme, as most directly to the mode of user's pushed information, passing through and play audio and/or video
Information understands above-mentioned recommendation target, to promote user to the convenience for recommending target to understand.
In any of the above-described technical solution, in the attribute for determining user according to age of user information and user gender information
After information, further includes: the vocal print feature of the first voice messaging of storage and saves preset duration, in preset duration according to sound
Line feature determines collected second voice messaging
In the technical scheme, by being saved in short-term to the vocal print feature parsed in the first voice messaging, with
After receiving new voice messaging, by vocal print feature verify whether verify the voice of letter for the second above-mentioned voice messaging
Whether information with the first voice messaging comes from same user, on the one hand, can guarantee the specific aim and unicity of interactive voice, prevent
It only generates semanteme to obscure, on the other hand, by being also prevented from user speech to a large amount of of memory space for vocal print feature short time treatment
It occupies.
In any of the above-described technical solution, according to the recognition result to collected second voice messaging, determines and correspond to
Semantic information specifically included: with filtering out the target information at least one Adapted information according to semantic information according to first
Natural Language Processing Models identify type keyword in the second voice messaging and function keyword, by type keyword with
Function keyword is determined as semantic information；According to type keyword at least a kind of type matching for recommending target as a result, determining
At least a kind of specified class recommended in target recommends target；Recommend the matching result of target according to function keyword and specified class,
It determines that specified class recommends the specific object in target, the parsing information of specific object is determined as target information.
In the technical scheme, recommend to include type information and functional information, the preset first natural language in target information
Speech processing model mainly for detection of whether have in the second voice messaging received with the consistent type keyword of type information,
And with the consistent function keyword of functional information, by the parsing to type keyword and function keyword, to obtain user
The recommendation information specifically needed, as target information, to promote the accuracy of interactive voice result.
Specifically, as a kind of simple embodiment, type keyword is " air-conditioning ", and function keyword is " mute ",
Then targeted target information can be obtained by above-mentioned key word information and be pushed to user, to realize guidance function.
In any of the above-described technical solution, according to the recognition result to collected second voice messaging, determines and correspond to
Semantic information specifically included: with filtering out the target information at least one Adapted information according to semantic information according to second
Natural Language Processing Models identify the intention keyword in the second voice messaging, will be intended to keyword and be determined as semantic letter
Breath；Recommend to meet the specific object for being intended to keyword in target according to the screening of preset screening model is at least a kind of, it will be specific
The parsing information of object is determined as target information.
In the technical scheme, preset the second nature Language Processing model is mainly used for recommending target to not yet explicitly specific
Second speech data analyzed, to determine user demand based on the analysis results, to meet not directly containing matched
The extraction and parsing that the user of the voice messaging of key word information is intended to, with according to parsing as a result, in conjunction with preset screening mould
Type executes screening operation, and then obtains target information.
Wherein, the second nature Language Processing model can be by way of machine learning by carrying out to a large amount of related datas
Training obtains.
Specifically, for example the second voice messaging includes " fresh-keeping ", then directly can inquire fresh-keeping function from refrigerator class product
Can preferable brand and model, for another example, the second voice messaging includes " I does not like the wind of air-conditioning against my blow-through with air-conditioning ",
It then can determine that being intended to keyword is " calm sense ", then subsequent robot will mainly introduce the air-conditioning of calm sense to user's recommendation.
In any of the above-described technical solution, further includes: the third voice messaging that acquisition is fed back according to target information；According to
To the recognition result of third voice messaging, the Target Acquisition routing information in target information is generated.
In the technical scheme, further, target information can be specially that item of hardware or software article illustrate letter
Breath can also continue to the third voice messaging of acquisition user after getting target information, to determine that third voice messaging is
When destination path acquisition request, generate Target Acquisition routing information, further promoted interactive voice it is successional simultaneously, mention
It rises the resolution of different information and is timely feedbacked.
Technical solution according to the second aspect of the invention provides a kind of information push-delivery apparatus, comprising: memory and place
Manage device；Memory, for storing memory for storing program code；Processor is executed for caller code: according to right
The recognition result of collected first voice messaging, determines the attribute information of user, with determining matched at least with attribute information
One Adapted information；According to the recognition result to collected second voice messaging, corresponding semantic information is determined, according to language
Adopted information
The target information at least one Adapted information is filtered out, and target information is pushed to user, wherein the second language
Message breath is matched with the vocal print feature of the first voice messaging.
In the technical scheme, by receiving at least two sections of languages including above-mentioned first voice messaging and the second voice messaging
Message breath, and the first voice messaging is identified and parsed with the second voice messaging, to be identified by the first voice messaging
Out after the attribute information of user, generation and at least one matched Adapted information of attribute information, to meet to different attribute
User recommends the demand of different information, further, in conjunction with the recognition result to the second voice messaging, can to it is above-mentioned at least
One Adapted information further progress screening, to obtain the target information for meeting the individual subscriber, and target information is pushed to
User, on the one hand, for the equipment with voice interactive function, be able to ascend the specific aim to user demand feedback, validity
It on the other hand can be answered with reliability based on the training of different application scenarios and the different types of information of storage with meeting difference
With the demand of scene, to promote the versatility of the equipment.
Specifically, by taking shopping guide's scene as an example, the speech robot people with voice interactive function can be by receiving user's
First voice messaging identifies that the attribute information of user obtains matched Adapted information and (use after determining the attribute of user
Family can be interested be in the product of which type), the intention of user is further identified according to the second voice messaging received, with
Specifically intended according to user screens Adapted information, with target information needed for obtaining user, and then realizes phonetic machine
Shopping guide's function of device people.
In the above-mentioned technical solutions, further includes: audio transceiver for generating guidance voice broadcast message, and receives root
According to the first voice messaging of guidance voice broadcast message feedback；Processor is specifically used for: according to the vocal print to the first voice messaging
The parsing result of feature determines user gender information；According to the recognition result to the digital information in the first voice messaging, determine
Age of user information；The attribute information of user is determined according to age of user information and user gender information.
In the technical scheme, before acquiring the first voice messaging, guidance voice broadcast message can be played, first to draw
It leads user and describes the information such as the Sex, Age of oneself, user's gender directly can be determined by the first voice messaging of analysis in this way
With the age etc., further, if user answers not according to guidance voice broadcast message, it can directly pass through analysis the
Vocal print feature in one voice messaging determines gender information and the age information of user, or by the first voice messaging of identification
Digital information determine the age information of user, then determine age bracket described in age of user, in conjunction with the gender of user, make
For user property, can search and the matched Adapted information of user property.
Specifically, age of user can be divided into multiple age brackets, such as 18 years old to 28 years old, 29 years old to 40 years old, 41 years old
To 50 years old, with first-class, in conjunction with gender information, as the attribute information of definition, for example when executing shopping guide's function, 18 years old extremely within 50 years old
28 years old male users are interested in electronic product, and 29 years old to 40 years old female user is interested in beauty class product
Deng using as match information to be recommended.
In any of the above-described technical solution, further includes: image acquisition device, for acquiring user images information；Processor,
It is specifically used for: responds collected user images information, generates guidance voice broadcast message.
In the technical scheme, by detecting whether to collect the image information of user, in the image for collecting user
When information, show then to can be generated at this time with the user for needing to carry out interactive voice and broadcast them guidance voice broadcast service is believed
Breath, so that the triggering of interactive voice is realized, to prevent from collecting useless voice messaging.
Furthermore it is also possible to by setting trigger module, such as key, touch device etc., it is current whether in need to detect
Carry out the user of interactive voice.
In any of the above-described technical solution, processor is specifically used for: determine in the information bank that prestores with attribute information
At least a kind of recommendation target matched, and at least a kind of information for recommending target is determined as Adapted information.
In the technical scheme, Adapted information is specifically as follows recommendation target, is directed to user to realize by interactive voice
The recommendation function of attribute and user demand, to promote the applicability and practicability of information push-delivery apparatus.
In any of the above-described technical solution, processor is specifically used for: being determined according to the user's history record being collected into every
The corresponding at least a kind of recommendation target for meeting concern threshold value of a user property；It is prestored according to user property with target generation is recommended
Information bank.
In the technical scheme, big data analysis is carried out by a large number of users historical record being collected into, it is every to determine
One or more of recommendation targets that user under a user property is most interested in, and establish user property and recommend between target
Association matching, to will be associated with matched a kind of or several after parsing user property according to the first voice messaging received
Kind recommends Objective extraction to come out, and target can be recommended these to make further to screen, these directly can also be recommended target
It is pushed to user.
In any of the above-described technical solution, processor is specifically used for: by target information with audio-frequency information and/or video
The form of information is pushed to user；Audio transceiver is specifically used for: broadcasting audio information；And/or information push-delivery apparatus also wraps
It includes: display, for showing video information.
In the technical scheme, as most directly to the mode of user's pushed information, passing through and play audio and/or video
Information understands above-mentioned recommendation target, to promote user to the convenience for recommending target to understand.
In any of the above-described technical solution, memory is specifically used for: the vocal print feature of the first voice messaging of storage, and
Save preset duration；Processor is specifically used for: determining that collected second voice is believed according to vocal print feature in preset duration
Breath.
In the technical scheme, by being saved in short-term to the vocal print feature parsed in the first voice messaging, with
After receiving new voice messaging, by vocal print feature verify whether verify the voice of letter for the second above-mentioned voice messaging
Whether information with the first voice messaging comes from same user, on the one hand, can guarantee the specific aim and unicity of interactive voice, prevent
It only generates semanteme to obscure, on the other hand, by being also prevented from user speech to a large amount of of memory space for vocal print feature short time treatment
It occupies.
In any of the above-described technical solution, processor is specifically used for: being identified according to the first Natural Language Processing Models
Type keyword and function keyword are determined as semantic letter by type keyword and function keyword in the second voice messaging
Breath；According to type keyword at least a kind of type matching for recommending target as a result, determining at least a kind of finger recommended in target
Determine class and recommends target；The matching result for recommending target according to function keyword and specified class determines that specified class is recommended in target
The parsing information of specific object is determined as target information by specific object.
In the technical scheme, recommend to include type information and functional information, the preset first natural language in target information
Speech processing model mainly for detection of whether have in the second voice messaging received with the consistent type keyword of type information,
And with the consistent function keyword of functional information, by the parsing to type keyword and function keyword, to obtain user
The recommendation information specifically needed, as target information, to promote the accuracy of interactive voice result.
Specifically, as a kind of simple embodiment, type keyword is " air-conditioning ", and function keyword is " mute ",
Then targeted target information can be obtained by above-mentioned key word information and be pushed to user, to realize guidance function.
In any of the above-described technical solution, processor is specifically used for: being identified according to the second nature Language Processing model
Intention keyword in second voice messaging will be intended to keyword and be determined as semantic information；It is sieved according to preset screening model
Choosing is at least a kind of to be recommended to meet the specific object for being intended to keyword in target, and the parsing information of specific object is determined as target
Information.
In the technical scheme, preset the second nature Language Processing model is mainly used for recommending target to not yet explicitly specific
Second speech data analyzed, to determine user demand based on the analysis results, to meet not directly containing matched
The extraction and parsing that the user of the voice messaging of key word information is intended to, with according to parsing as a result, in conjunction with preset screening mould
Type executes screening operation, and then obtains target information.
Wherein, the second nature Language Processing model can be by way of machine learning by carrying out to a large amount of related datas
Training obtains.
Specifically, for example the second voice messaging includes " fresh-keeping ", then directly can inquire fresh-keeping function from refrigerator class product
Can preferable brand and model, for another example, the second voice messaging includes " I does not like the wind of air-conditioning against my blow-through with air-conditioning ",
It then can determine that being intended to keyword is " calm sense ", then subsequent robot will mainly introduce the air-conditioning of calm sense to user's recommendation.
In any of the above-described technical solution, audio transceiver is specifically used for: the third that acquisition is fed back according to target information
Voice messaging；Processor is specifically used for: according to the recognition result to third voice messaging, the target generated in target information is obtained
Take routing information.
In the technical scheme, further, target information can be specially that item of hardware or software article illustrate letter
Breath can also continue to the third voice messaging of acquisition user after getting target information, to determine that third voice messaging is
When destination path acquisition request, generate Target Acquisition routing information, further promoted interactive voice it is successional simultaneously, mention
It rises the resolution of different information and is timely feedbacked.
Technical solution according to the third aspect of the invention we additionally provides a kind of interactive voice equipment, comprising: above-mentioned second
Information push-delivery apparatus described in any technical solution of aspect.
Interactive voice equipment is specifically as follows speech robot people.
Additional aspect and advantage of the invention will provide in following description section, will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 shows the schematic flow diagram of information-pushing method according to an embodiment of the invention；
Fig. 2 shows the schematic flow diagrams of information-pushing method according to another embodiment of the invention；
Fig. 3 shows the schematic block diagram of information push-delivery apparatus according to an embodiment of the invention；
Fig. 4 shows the schematic block diagram of interactive voice equipment according to an embodiment of the invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention is further described in detail.It should be noted that in the absence of conflict, the implementation of the application
Feature in example and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
To be implemented using other than the one described here other modes, therefore, protection scope of the present invention is not by described below
Specific embodiment limitation.
Embodiment one
As shown in Figure 1, information-pushing method according to an embodiment of the invention, is suitable for interactive voice equipment, packet
It includes: step 102, according to the recognition result to collected first voice messaging, determining the attribute information of user, to determine and belong to
At least one Adapted information of property information matches；Step 104, according to the recognition result to collected second voice messaging, really
Fixed corresponding semantic information, to filter out the target information at least one Adapted information according to semantic information, and target is believed
Breath is pushed to user, wherein the second voice messaging is matched with the vocal print feature of the first voice messaging.
In this embodiment, by receiving at least two sections of voices including above-mentioned first voice messaging and the second voice messaging
Information, and the first voice messaging is identified and parsed with the second voice messaging, to be identified by the first voice messaging
After the attribute information of user, generation and at least one matched Adapted information of attribute information, to meet the use to different attribute
The demand of different information is recommended at family, further, can be to above-mentioned at least one in conjunction with the recognition result to the second voice messaging
A Adapted information further progress screening, to obtain the target information for meeting the individual subscriber, and is pushed to use for target information
Family, on the one hand, for the equipment with voice interactive function, be able to ascend to user demand feedback specific aim, validity with
Reliability on the other hand can be based on the training of different application scenarios and the different types of information of storage, to meet different application
The demand of scene, to promote the versatility of the equipment.
Specifically, by taking shopping guide's scene as an example, the speech robot people with voice interactive function can be by receiving user's
First voice messaging identifies that the attribute information of user obtains matched Adapted information and (use after determining the attribute of user
Family can be interested be in the product of which type), the intention of user is further identified according to the second voice messaging received, with
Specifically intended according to user screens Adapted information, with target information needed for obtaining user, and then realizes phonetic machine
Shopping guide's function of device people.
Embodiment two
As shown in Fig. 2, information-pushing method according to another embodiment of the invention, comprising: step 202, response is adopted
The user images information collected generates guidance voice broadcast message；Step 204, it receives according to guidance voice broadcast message feedback
The first voice messaging；Step 206, according to the parsing result of the vocal print feature to the first voice messaging, determine that user's gender is believed
Breath；Step 208, according to the recognition result to the digital information in the first voice messaging, age of user information is determined；Step 210,
The attribute information of user is determined according to age of user information and user gender information；Step 212, determine in the information bank that prestores with
The matched at least a kind of recommendation target of attribute information, and at least a kind of information for recommending target is determined as Adapted information.
In this embodiment, by detecting whether to collect the image information of user, in the image letter for collecting user
When breath, show then to can be generated at this time with the user for needing to carry out interactive voice and broadcast them guides voice broadcast message,
To realize the triggering of interactive voice, to prevent from collecting useless voice messaging.
Furthermore it is also possible to by setting trigger module, such as key, touch device etc., it is current whether in need to detect
Carry out the user of interactive voice.
Further, before acquiring the first voice messaging, guidance voice broadcast message can be played, first to guide user
The information such as the Sex, Age of oneself are described, user's gender and age directly can be determined by the first voice messaging of analysis in this way
Deng further, if user not according to guiding voice broadcast message to answer, can directly pass through the first voice of analysis
Vocal print feature in information determines gender information and the age information of user, or passes through the number in the first voice messaging of identification
Information determines the age information of user, then determines age bracket described in age of user, in conjunction with the gender of user, as user
Attribute, can search and the matched Adapted information of user property.
Specifically, age of user can be divided into multiple age brackets, such as 18 years old to 28 years old, 29 years old to 40 years old, 41 years old
To 50 years old, with first-class, in conjunction with gender information, as the attribute information of definition, for example when executing shopping guide's function, 18 years old extremely within 50 years old
28 years old male users are interested in electronic product, and 29 years old to 40 years old female user is interested in beauty class product
Deng using as match information to be recommended.
Wherein, Adapted information is specifically as follows recommendation target, is directed to user property and user to realize by interactive voice
The recommendation function of demand, to promote the applicability and practicability of information push-delivery apparatus.
In any of the above-described embodiment, recommend in determining the information bank prestored with the matched at least one kind of attribute information
Before target, further includes: determine the corresponding satisfaction concern threshold value of each user property extremely according to the user's history record being collected into
Few a kind of recommendation target；According to user property and target is recommended to generate the information bank prestored.
In this embodiment, big data analysis is carried out by a large number of users historical record being collected into, it is each to determine
One or more of recommendation targets that user under user property is most interested in, and establish user property and recommend the pass between target
Lump is matched, to will be associated with matched one or more after parsing user property according to the first voice messaging received
Recommend Objective extraction to come out, target can be recommended these to make further screening, can also directly push away these recommendation targets
Give user.
In any of the above-described embodiment, further includes: push away target information in the form of audio-frequency information and/or video information
Give user.
In this embodiment, audio and/or video letter are played as most directly to the mode of user's pushed information, passing through
Breath, understands above-mentioned recommendation target, to promote user to the convenience for recommending target to understand.
In any of the above-described embodiment, believe in the attribute for determining user according to age of user information and user gender information
After breath, further includes: the vocal print feature of the first voice messaging of storage and saves preset duration, in preset duration according to vocal print
Feature determines collected second voice messaging
In this embodiment, by being saved in short-term to the vocal print feature parsed in the first voice messaging, to connect
After receiving new voice messaging, verify whether that for the second above-mentioned voice messaging, that is, the voice for verifying letter is believed by vocal print feature
Whether breath with the first voice messaging comes from same user, on the one hand, the specific aim and unicity that can guarantee interactive voice prevent
It generates semanteme to obscure, on the other hand, by being also prevented from user speech largely accounting for memory space for vocal print feature short time treatment
With.
Embodiment three
As shown in figure 3, the information-pushing method of still another embodiment in accordance with the present invention, comprising: step 302, receive the
Two voice messagings；Step 304, according to the first Natural Language Processing Models identify type keyword in the second voice messaging with
Type keyword and function keyword are determined as semantic information by function keyword；Step 306, according to type keyword with
At least a kind of type matching for recommending target is as a result, determine that at least a kind of specified class recommended in target recommends target；Step
308, recommend the matching result of target according to function keyword and specified class, determines that specified class recommends the specific object in target,
The parsing information of specific object is determined as target information；Step 310；Is identified according to the second nature Language Processing model
Intention keyword in two voice messagings will be intended to keyword and be determined as semantic information；Step 312, according to preset screening
Model discrimination is at least a kind of to be recommended to meet the specific object for being intended to keyword in target, and the parsing information of specific object is determined
For target information.
In this embodiment, on the one hand, include type information and in the case where functional information in recommending target information, in advance
If the first Natural Language Processing Models mainly for detection of whether having and type information one in the second voice messaging received
The type keyword of cause, and with the consistent function keyword of functional information, by type keyword and function keyword
Parsing, to obtain the recommendation information that user specifically needs, as target information, to promote the accuracy of interactive voice result.
Specifically, as a kind of simple embodiment, type keyword is " air-conditioning ", and function keyword is " mute ",
Then targeted target information can be obtained by above-mentioned key word information and be pushed to user, to realize guidance function.
In this embodiment, on the other hand, preset the second nature Language Processing model is mainly used for specific to being not known
Recommend the second speech data of target to be analyzed, to determine user demand based on the analysis results, does not contain directly to meet
The extraction and parsing for thering is the user of the voice messaging of matched key word information to be intended to, with presetting as a result, combining according to parsing
Screening model execute screening operation, and then obtain target information.
Wherein, the second nature Language Processing model can be by way of machine learning by carrying out to a large amount of related datas
Training obtains.
Specifically, for example the second voice messaging includes " fresh-keeping ", then directly can inquire fresh-keeping function from refrigerator class product
Can preferable brand and model, for another example, the second voice messaging includes " I does not like the wind of air-conditioning against my blow-through with air-conditioning ",
It then can determine that being intended to keyword is " calm sense ", then subsequent robot will mainly introduce the air-conditioning of calm sense to user's recommendation.
In any of the above-described embodiment, further includes: the third voice messaging that acquisition is fed back according to target information；According to right
The recognition result of third voice messaging generates the Target Acquisition routing information in target information.
In this embodiment, further, target information can be specially that item of hardware or software article illustrate information,
After getting target information, the third voice messaging of acquisition user can also continue to, to determine third voice messaging as mesh
Mark path acquisition request when, generate Target Acquisition routing information, further promoted interactive voice it is successional simultaneously, promoted
The resolution of different information is simultaneously timely feedbacked.
Example IV
As shown in figure 4, the information push-delivery apparatus 40 of embodiment according to the present invention, comprising: memory 402 and processor
404；Memory 402, for storing program code；Processor 404 is executed for caller code: according to collected
The recognition result of first voice messaging determines the attribute information of user, with it is determining it is matched with attribute information at least one be adapted to
Information；According to the recognition result to collected second voice messaging, corresponding semantic information is determined, to sieve according to semantic information
The target information at least one Adapted information is selected, and target information is pushed to user, wherein the second voice messaging and
The vocal print feature of one voice messaging matches.
In this embodiment, by receiving at least two sections of voices including above-mentioned first voice messaging and the second voice messaging
Information, and the first voice messaging is identified and parsed with the second voice messaging, to be identified by the first voice messaging
After the attribute information of user, generation and at least one matched Adapted information of attribute information, to meet the use to different attribute
The demand of different information is recommended at family, further, can be to above-mentioned at least one in conjunction with the recognition result to the second voice messaging
A Adapted information further progress screening, to obtain the target information for meeting the individual subscriber, and is pushed to use for target information
Family, on the one hand, for the equipment with voice interactive function, be able to ascend to user demand feedback specific aim, validity with
Reliability on the other hand can be based on the training of different application scenarios and the different types of information of storage, to meet different application
The demand of scene, to promote the versatility of the equipment.
Specifically, by taking shopping guide's scene as an example, the speech robot people with voice interactive function can be by receiving user's
First voice messaging identifies that the attribute information of user obtains matched Adapted information and (use after determining the attribute of user
Family can be interested be in the product of which type), the intention of user is further identified according to the second voice messaging received, with
Specifically intended according to user screens Adapted information, with target information needed for obtaining user, and then realizes phonetic machine
Shopping guide's function of device people.
In the above-described embodiments, further includes: audio transceiver 406 for generating guidance voice broadcast message, and receives root
According to the first voice messaging of guidance voice broadcast message feedback；Processor 404, is specifically used for: according to the first voice messaging
The parsing result of vocal print feature determines user gender information；According to the recognition result to the digital information in the first voice messaging,
Determine age of user information；The attribute information of user is determined according to age of user information and user gender information.
In this embodiment, before acquiring the first voice messaging, guidance voice broadcast message can be played, first with guidance
User describes the information such as the Sex, Age of oneself, in this way can directly by analysis the first voice messaging come determine user's gender with
Age etc. further if user answers not according to guidance voice broadcast message, can directly pass through analysis first
Vocal print feature in voice messaging determines gender information and the age information of user, or by the first voice messaging of identification
Digital information determines the age information of user, then determines age bracket described in age of user, in conjunction with the gender of user, as
User property, can search and the matched Adapted information of user property.
Specifically, age of user can be divided into multiple age brackets, such as 18 years old to 28 years old, 29 years old to 40 years old, 41 years old
To 50 years old, with first-class, in conjunction with gender information, as the attribute information of definition, for example when executing shopping guide's function, 18 years old extremely within 50 years old
28 years old male users are interested in electronic product, and 29 years old to 40 years old female user is interested in beauty class product
Deng using as match information to be recommended.
In any of the above-described embodiment, further includes: image acquisition device 408, for acquiring user images information；Processor
404, it is specifically used for: responds collected user images information, generates guidance voice broadcast message.
In this embodiment, by detecting whether to collect the image information of user, in the image letter for collecting user
When breath, show then to can be generated at this time with the user for needing to carry out interactive voice and broadcast them guides voice broadcast message,
To realize the triggering of interactive voice, to prevent from collecting useless voice messaging.
Furthermore it is also possible to by setting trigger module, such as key, touch device etc., it is current whether in need to detect
Carry out the user of interactive voice.
In any of the above-described embodiment, processor 404 is specifically used for: determine in the information bank that prestores with attribute information
Matched at least a kind of recommendation target, and at least a kind of information for recommending target is determined as Adapted information.
In this embodiment, Adapted information is specifically as follows recommendation target, is belonged to being realized by interactive voice for user
The recommendation function of property and user demand, to promote the applicability and practicability of information push-delivery apparatus 40.
In any of the above-described embodiment, processor 404 is specifically used for: being determined according to the user's history record being collected into
The corresponding at least a kind of recommendation target for meeting concern threshold value of each user property；According to user property and target is recommended to generate in advance
The information bank deposited.
In this embodiment, big data analysis is carried out by a large number of users historical record being collected into, it is each to determine
One or more of recommendation targets that user under user property is most interested in, and establish user property and recommend the pass between target
Lump is matched, to will be associated with matched one or more after parsing user property according to the first voice messaging received
Recommend Objective extraction to come out, target can be recommended these to make further screening, can also directly push away these recommendation targets
Give user.
In any of the above-described embodiment, processor 404 is specifically used for: by target information with audio-frequency information and/or video
The form of information is pushed to user；Audio transceiver 406, is specifically used for: broadcasting audio information；And/or information push-delivery apparatus 40
Further include: display 410, for showing video information.
In this embodiment, audio and/or video letter are played as most directly to the mode of user's pushed information, passing through
Breath, understands above-mentioned recommendation target, to promote user to the convenience for recommending target to understand.
In any of the above-described embodiment, memory 402 is specifically used for: the vocal print feature of the first voice messaging of storage, and
Save preset duration；Processor 404, is specifically used for: determining collected second voice according to vocal print feature in preset duration
Information.
In this embodiment, by being saved in short-term to the vocal print feature parsed in the first voice messaging, to connect
After receiving new voice messaging, verify whether that for the second above-mentioned voice messaging, that is, the voice for verifying letter is believed by vocal print feature
Whether breath with the first voice messaging comes from same user, on the one hand, the specific aim and unicity that can guarantee interactive voice prevent
It generates semanteme to obscure, on the other hand, by being also prevented from user speech largely accounting for memory space for vocal print feature short time treatment
With.
In any of the above-described embodiment, processor 404 is specifically used for: being identified according to the first Natural Language Processing Models
Type keyword and function keyword are determined as semanteme by the type keyword in the second voice messaging and function keyword out
Information；According to type keyword at least a kind of type matching for recommending target as a result, determining at least a kind of recommend in target
Specified class recommends target；The matching result for recommending target according to function keyword and specified class determines that specified class is recommended in target
Specific object, the parsing information of specific object is determined as target information.
In this embodiment, recommend to include type information and functional information, preset first natural language in target information
Processing model mainly for detection of whether have in the second voice messaging received with the consistent type keyword of type information, with
And have with the consistent function keyword of functional information by the parsing to type keyword and function keyword to obtain user
The recommendation information that body needs, as target information, to promote the accuracy of interactive voice result.
Specifically, as a kind of simple embodiment, type keyword is " air-conditioning ", and function keyword is " mute ",
Then targeted target information can be obtained by above-mentioned key word information and be pushed to user, to realize guidance function.
In any of the above-described embodiment, processor 404 is specifically used for: being identified according to the second nature Language Processing model
Intention keyword in second voice messaging out will be intended to keyword and be determined as semantic information；According to preset screening model
Screening is at least a kind of to be recommended to meet the specific object for being intended to keyword in target, and the parsing information of specific object is determined as mesh
Mark information.
In this embodiment, preset the second nature Language Processing model is mainly used for not yet explicitly specific recommendation target
Second speech data is analyzed, and to determine user demand based on the analysis results, does not contain matched pass directly to meet
The extraction and parsing that the user of the voice messaging of keyword information is intended to, with according to parsing as a result, in conjunction with preset screening model
Screening operation is executed, and then obtains target information.
Wherein, the second nature Language Processing model can be by way of machine learning by carrying out to a large amount of related datas
Training obtains.
Specifically, for example the second voice messaging includes " fresh-keeping ", then directly can inquire fresh-keeping function from refrigerator class product
Can preferable brand and model, for another example, the second voice messaging includes " I does not like the wind of air-conditioning against my blow-through with air-conditioning ",
It then can determine that being intended to keyword is " calm sense ", then subsequent robot will mainly introduce the air-conditioning of calm sense to user's recommendation.
In any of the above-described embodiment, audio transceiver 406 is specifically used for: acquisition fed back according to target information the
Three voice messagings；Processor 404, is specifically used for: according to the recognition result to third voice messaging, generating the mesh in target information
Mark to acquisite approachs information.
In this embodiment, further, target information can be specially that item of hardware or software article illustrate information,
After getting target information, the third voice messaging of acquisition user can also continue to, to determine third voice messaging as mesh
Mark path acquisition request when, generate Target Acquisition routing information, further promoted interactive voice it is successional simultaneously, promoted
The resolution of different information is simultaneously timely feedbacked.
The interactive voice equipment of embodiment according to the present invention, comprising: any of the above-described information push as described in the examples
Device.
Interactive voice equipment is specifically as follows speech robot people.
Computer readable storage medium according to an embodiment of the invention is stored thereon with computer program, calculates
The step of machine program is performed, and realizes the information-pushing method such as the restriction of any of the above-described embodiment.
Compared with prior art, embodiment disclosed in technical scheme at least have it is following the utility model has the advantages that
(1) for the equipment with voice interactive function, be able to ascend to user demand feedback specific aim, validity with
Reliability.
It (2) can be based on the training of different application scenarios and the different types of information of storage, to meet different application scene
Demand, to promote the versatility of the equipment.
(3) specific aim and unicity that can guarantee interactive voice, prevent that semanteme is obscured, and by the way that vocal print is special
Short time treatment is levied, is also prevented from user speech to a large amount of occupancy of memory space
The technical scheme of the present invention has been explained in detail above with reference to the attached drawings, according to the technical solution of the present invention, can satisfy
Recommend the user of different attribute the demand of different information, it further, can in conjunction with the recognition result to the second voice messaging
Above-mentioned at least one Adapted information further progress is screened, to obtain the target information for meeting the individual subscriber, and by mesh
Mark information is pushed to user, on the one hand, for the equipment with voice interactive function, is able to ascend the needle to user demand feedback
To property, validity and reliability, on the other hand, based on the training of different application scenarios and different types of information can be stored,
To meet the needs of different application scene, to promote the versatility of the equipment.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
It should be noted that in the claims, any reference symbol between parentheses should not be configured to power
The limitation that benefit requires.Word "comprising" does not exclude the presence of component or step not listed in the claims.Before component
Word "a" or "an" does not exclude the presence of multiple such components.The present invention can be by means of including several different components
It hardware and is realized by means of properly programmed computer.In the unit claims listing several devices, these are filled
Several in setting, which can be, to be embodied by the same item of hardware.The use of word first, second, and third is not
Indicate any sequence.These words can be construed to title.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from right of the present invention by those skilled in the art
It is required that and its within the scope of equivalent technologies, then the present invention is also intended to include these modifications and variations.
Claims (12)
1. a kind of information-pushing method of interactive voice equipment characterized by comprising
According to the recognition result to collected first voice messaging, the attribute information of user is determined, with the determining and attribute
At least one Adapted information of information matches；
According to the recognition result to collected second voice messaging, corresponding semantic information is determined, according to the semantic letter
Breath filters out the target information at least one described Adapted information, and the target information is pushed to user, wherein described
Second voice messaging is matched with the vocal print feature of first voice messaging.
2. information-pushing method according to claim 1, which is characterized in that the basis believes collected first voice
The recognition result of breath determines the attribute information of user, specifically includes:
Guidance voice broadcast message is generated, and receives and is believed according to first voice of the guidance voice broadcast message feedback
Breath；
According to the parsing result of the vocal print feature to first voice messaging, user gender information is determined；
According to the recognition result to the digital information in first voice messaging, age of user information is determined；
The attribute information of the user is determined according to the age of user information and the user gender information.
3. information-pushing method according to claim 2, which is characterized in that the interactive voice equipment is additionally provided with image
Acquisition device, it is described to generate guidance voice broadcast message, and receive according to guidance voice broadcast message feedback
Before first voice messaging, further includes:
Collected user images information is responded, to generate the guidance voice broadcast message.
4. information-pushing method according to claim 2, which is characterized in that the determination and the attribute information are matched
At least one Adapted information, specifically includes:
It determines in the information bank prestored and recommends target with the matched at least one kind of the attribute information, and described at least one is analogized
The information for recommending target is determined as the Adapted information.
5. information-pushing method according to claim 4, which is characterized in that it is described in determining the information bank that prestores with institute
Before stating the matched at least a kind of recommendation target of attribute information, further includes:
Determine that the corresponding satisfaction of each user property is paid close attention to described in threshold value at least according to the user's history record being collected into
One kind recommends target；
The information bank prestored according to the user property and the recommendation target generation.
6. information-pushing method according to claim 1, which is characterized in that further include:
The target information is pushed to user in the form of audio-frequency information and/or video information.
7. information-pushing method according to claim 2, which is characterized in that according to the age of user information with it is described
After user gender information determines the attribute information of the user, further includes:
Store the vocal print feature of first voice messaging, and save preset duration, in the preset duration according to
Vocal print feature determines collected second voice messaging.
8. information-pushing method according to claim 4, which is characterized in that the basis believes collected second voice
The recognition result of breath determines corresponding semantic information, to filter out at least one described Adapted information according to institute's semantic information
In target information, specifically include:
Type keyword and function keyword in second voice messaging are identified according to the first Natural Language Processing Models,
The type keyword and the function keyword are determined as institute's semantic information；
According to the type keyword at least a kind of type matching for recommending target as a result, determining that described at least one analogizes
The specified class recommended in target recommends target；
The matching result for recommending target according to the function keyword and the specified class determines that the specified class is recommended in target
Specific object, the parsing information of the specific object is determined as the target information.
9. information-pushing method according to claim 4, which is characterized in that the basis believes collected second voice
The recognition result of breath determines corresponding semantic information, to filter out at least one described Adapted information according to institute's semantic information
In target information, specifically include:
The intention keyword in second voice messaging is identified according to the second nature Language Processing model, by the intention
Keyword is determined as institute's semantic information；
Meet the specific object for being intended to keyword according in preset screening model screening at least a kind of recommendation target,
The parsing information of the specific object is determined as the target information.
10. information-pushing method according to any one of claim 1 to 9, which is characterized in that further include:
Acquire the third voice messaging fed back according to the target information；
According to the recognition result to the third voice messaging, the Target Acquisition routing information in the target information is generated.
11. a kind of information push-delivery apparatus of interactive voice equipment characterized by comprising memory and processor；
The memory, for storing the memory for storing program code；
The processor, for calling said program code to execute:
According to the recognition result to collected first voice messaging, the attribute information of user is determined, with the determining and attribute
At least one Adapted information of information matches；
According to the recognition result to collected second voice messaging, corresponding semantic information is determined, according to the semantic letter
Breath filters out the target information at least one described Adapted information, and the target information is pushed to user, wherein described
Second voice messaging is matched with the vocal print feature of first voice messaging.
12. a kind of interactive voice equipment characterized by comprising
Information push-delivery apparatus as claimed in claim 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910054466.2A CN109545232A (en) | 2019-01-21 | 2019-01-21 | Information-pushing method, information push-delivery apparatus and interactive voice equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910054466.2A CN109545232A (en) | 2019-01-21 | 2019-01-21 | Information-pushing method, information push-delivery apparatus and interactive voice equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109545232A true CN109545232A (en) | 2019-03-29 |
Family
ID=65838142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910054466.2A Pending CN109545232A (en) | 2019-01-21 | 2019-01-21 | Information-pushing method, information push-delivery apparatus and interactive voice equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109545232A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110569806A (en) * | 2019-09-11 | 2019-12-13 | 上海软中信息系统咨询有限公司 | Man-machine interaction system |
| CN112116367A (en) * | 2019-06-19 | 2020-12-22 | 百度在线网络技术（北京）有限公司 | Method and apparatus for recommending advertisements, machine-readable storage medium, and processor |
| CN112116368A (en) * | 2019-06-19 | 2020-12-22 | 百度在线网络技术（北京）有限公司 | Method and device for labeling equipment recommending contents to crowd and processor |
| CN113837819A (en) * | 2020-06-08 | 2021-12-24 | 阿里巴巴集团控股有限公司 | Information processing device, method, apparatus and electronic device |
| CN113870861A (en) * | 2021-09-10 | 2021-12-31 | Oppo广东移动通信有限公司 | Voice interaction method and device, storage medium and terminal |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105959806A (en) * | 2016-05-25 | 2016-09-21 | 乐视控股（北京）有限公司 | Program recommendation method and device |
| CN106128467A (en) * | 2016-06-06 | 2016-11-16 | 北京云知声信息技术有限公司 | Method of speech processing and device |
| CN106570020A (en) * | 2015-10-09 | 2017-04-19 | 百度在线网络技术（北京）有限公司 | Method and apparatus used for providing recommended information |
| CN107886949A (en) * | 2017-11-24 | 2018-04-06 | 科大讯飞股份有限公司 | A kind of content recommendation method and device |
| CN107993133A (en) * | 2018-01-23 | 2018-05-04 | 北京知行信科技有限公司 | A kind of intellectual analysis based on natural language recommends method and system |
| US20180189857A1 (en) * | 2017-01-05 | 2018-07-05 | Microsoft Technology Licensing, Llc | Recommendation through conversational ai |
-
2019
- 2019-01-21 CN CN201910054466.2A patent/CN109545232A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570020A (en) * | 2015-10-09 | 2017-04-19 | 百度在线网络技术（北京）有限公司 | Method and apparatus used for providing recommended information |
| CN105959806A (en) * | 2016-05-25 | 2016-09-21 | 乐视控股（北京）有限公司 | Program recommendation method and device |
| CN106128467A (en) * | 2016-06-06 | 2016-11-16 | 北京云知声信息技术有限公司 | Method of speech processing and device |
| US20180189857A1 (en) * | 2017-01-05 | 2018-07-05 | Microsoft Technology Licensing, Llc | Recommendation through conversational ai |
| CN107886949A (en) * | 2017-11-24 | 2018-04-06 | 科大讯飞股份有限公司 | A kind of content recommendation method and device |
| CN107993133A (en) * | 2018-01-23 | 2018-05-04 | 北京知行信科技有限公司 | A kind of intellectual analysis based on natural language recommends method and system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112116367A (en) * | 2019-06-19 | 2020-12-22 | 百度在线网络技术（北京）有限公司 | Method and apparatus for recommending advertisements, machine-readable storage medium, and processor |
| CN112116368A (en) * | 2019-06-19 | 2020-12-22 | 百度在线网络技术（北京）有限公司 | Method and device for labeling equipment recommending contents to crowd and processor |
| CN110569806A (en) * | 2019-09-11 | 2019-12-13 | 上海软中信息系统咨询有限公司 | Man-machine interaction system |
| CN113837819A (en) * | 2020-06-08 | 2021-12-24 | 阿里巴巴集团控股有限公司 | Information processing device, method, apparatus and electronic device |
| CN113870861A (en) * | 2021-09-10 | 2021-12-31 | Oppo广东移动通信有限公司 | Voice interaction method and device, storage medium and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109545232A (en) | Information-pushing method, information push-delivery apparatus and interactive voice equipment | |
| US10824874B2 (en) | Method and apparatus for processing video | |
| CN108566565B (en) | Bullet screen display method and device | |
| CN111541910B (en) | Video barrage comment automatic generation method and system based on deep learning | |
| CN108075892B (en) | Voice processing method, device and equipment | |
| US10446150B2 (en) | In-vehicle voice command recognition method and apparatus, and storage medium | |
| CN109348275B (en) | Video processing method and device | |
| CN108347646B (en) | Multimedia content playing method and device | |
| Hong et al. | Dynamic captioning: video accessibility enhancement for hearing impairment | |
| US20160308802A1 (en) | Coordinated deep tagging of media content with community chat postings | |
| CN110147726A (en) | Business quality detecting method and device, storage medium and electronic device | |
| WO2019021088A1 (en) | Navigating video scenes using cognitive insights | |
| CN106021496A (en) | Video search method and video search device | |
| CN114465737B (en) | Data processing method and device, computer equipment and storage medium | |
| CN110121116A (en) | Video generation method and device | |
| CN106250553A (en) | A kind of service recommendation method and terminal | |
| CN107430858A (en) | The metadata of transmission mark current speaker | |
| KR20120038000A (en) | Method and system for determining the topic of a conversation and obtaining and presenting related content | |
| CN106789543A (en) | The method and apparatus that facial expression image sends are realized in session | |
| CN103559880B (en) | Voice entry system and method | |
| CN110148400A (en) | The pronunciation recognition methods of type, the training method of model, device and equipment | |
| CN110557659A (en) | Video recommendation method and device, server and storage medium | |
| CN107943914A (en) | Voice information processing method and device | |
| CN110166818A (en) | Wait match generation method, computer equipment and the storage medium of audio-video | |
| WO2019137391A1 (en) | Method and apparatus for performing categorised matching of videos, and selection engine |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |
|
| RJ01 | Rejection of invention patent application after publication |