CN109710799A - Voice interactive method, medium, device and calculating equipment - Google Patents
Voice interactive method, medium, device and calculating equipment Download PDFInfo
- Publication number
- CN109710799A CN109710799A CN201910005993.4A CN201910005993A CN109710799A CN 109710799 A CN109710799 A CN 109710799A CN 201910005993 A CN201910005993 A CN 201910005993A CN 109710799 A CN109710799 A CN 109710799A
- Authority
- CN
- China
- Prior art keywords
- information
- music
- comment information
- comment
- focus
- 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.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Embodiments of the present invention provide a kind of voice interactive method, comprising: the voice messaging is converted to statement text by the voice messaging for receiving user's input；The comment information to match with the statement text is obtained from preset music commentary library；And the output comment information is as the response for the voice messaging.The embodiment of the present disclosure makes full use of existing music commentary information as response, and a large amount of reductions write upper input manpower in response content, and can cause the emotional resonance of the user of current input voice information, meets user feeling demand.Embodiments of the present invention additionally provide a kind of voice interaction device, medium and calculate equipment.
Description
Technical field
Embodiments of the present invention are related to field of computer technology, more specifically, embodiments of the present invention are related to voice
Exchange method, medium, device and calculating equipment.
Background technique
Background that this section is intended to provide an explanation of the embodiments of the present invention set forth in the claims or context.Herein
Description recognizes it is the prior art not because not being included in this section.
The essence of interactive voice is human-computer interaction, refers to that user is interacted using voice as carrier with machine, linked up, information
Exchange, generation is a series of to be output and input, and is finally completed corresponding task or is reached corresponding purpose.
Existing interactive voice scheme needs developer to write machine response content in advance, when user's input voice information
When, voice messaging is converted into text, selects the response content to match with the text as output.On the one hand, response content
Write and need to put into a large amount of manpower, inefficiency, on the other hand, the response content write in advance is mechanical stiff, Wu Faman
Sufficient user feeling demand.
Summary of the invention
For the above reasons, existing interactive voice scheme needs to put into a large amount of manpowers and writes response content, and in response
It is mechanical stiff to hold, and is unable to satisfy user feeling demand.
For this reason, it may be necessary to a kind of improved voice interactive method, to realize the human-computer interaction of more efficient more emotional resonance.
In the present context, embodiments of the present invention are intended to provide a kind of voice interactive method and device.
In the first aspect of embodiment of the present invention, a kind of voice interactive method is provided, comprising: receive user's input
Voice messaging, the voice messaging is converted into statement text；It is obtained and the statement text from preset music commentary library
The comment information to match；And the comment information is exported as the response for the voice messaging.
In one embodiment of the invention, in the above-mentioned output comment information as answering for the voice messaging
After answering, the above method further include: play music corresponding with the comment information.
In another embodiment of the invention, it is obtained and the statement text phase from preset music commentary library above-mentioned
Before the comment information matched, the above method further include: a plurality of comment information about music for meeting preset condition is obtained, by institute
The a plurality of comment information obtained constructs preset music commentary library；Identify the focus information of each comment information in preset music commentary library
And intent information.The above-mentioned comment information to match with the statement text that obtains from preset music commentary library includes: to be based on
The focus information and intent information of each comment information in the preset music commentary library, what acquisition matched with the statement text
Comment information.
In another embodiment of the present invention, above-mentioned acquisition meets a plurality of comment information packet about music of preset condition
It includes: according to the history music interaction behavioral data of the user, obtaining the corresponding comment information of individualized music of the user,
Wherein, the individualized music of the user includes following at least one: the sound that the music of user's collection, the user create
The music that the music or the user that happy, the described user likes play；And/or it obtains and current promotes that music is corresponding to be commented
By information；And/or obtain the comment information for thumbing up that number is more than first threshold.
In one more embodiment of the present invention, the above-mentioned focus letter based on each comment information in the preset music commentary library
Breath and intent information, obtaining the comment information to match with the statement text includes: to identify that the focus of the statement text is believed
Breath and intent information；The focus of each comment information in the focus information of the statement text and the preset music commentary library is believed
Breath is matched, and the matched comment information of focus is filtered out；And by the intent information of the statement text and the focus
The intent information for the comment information matched is matched, and is filtered out focus matching and is intended to matched comment information.
In one more embodiment of the present invention, in the above-mentioned preset music commentary library of identification the focus information of each comment information and
Intent information includes: the label extracted from each comment information based on tag library for characterizing corresponding focus information, base
The intention clause for characterizing corresponding intent information is extracted from each comment information in intent classifier library.Above-mentioned identification institute
The focus information and intent information for stating statement text include: to be extracted from the statement text for characterizing based on the tag library
The label of corresponding focus information, is extracted from the statement text for characterizing corresponding intent information based on intent classifier library
Intention clause.The focus information of each comment information in the above-mentioned focus information by the statement text and music commentary library
Carrying out matching includes: to match the label of the statement text with the label of each comment information, when matching degree is more than
It is determined as focus matched comment information when second threshold.And the above-mentioned intent information by the statement text and the coke
It includes: to match the intention clause of the statement text with the focus that the intent information of the matched comment information of point, which carries out matching,
The intention clause of comment information matched, be determined as focus matching when matching degree is more than third threshold value and be intended to matched
Comment information.
In one more embodiment of the present invention, above-mentioned obtain from music commentary library is commented with what the statement text matched
By information further include: when filtering out a plurality of focus matching and being intended to matched comment information, it is corresponding to obtain each comment information
The priority of music；Priority based on the music is ranked up the comment, chooses a comment based on ranking results
Information.
In one more embodiment of the present invention, the priority of the corresponding music of above-mentioned each comment information of acquisition includes: basis
The history music interaction behavioral data of the user, determines the comprehensive score of the corresponding music of each comment information, the use
The history music interaction behavioral data at family includes following at least one: the user collects the behavioral data of music, the user
Thumb up the behavioral data of music, the user plays the behavioral data of music, the behavioral data of the user comment music, described
User shares the behavioral data of music or the behavioral data of user creation music.
In the second aspect of embodiment of the present invention, provide a kind of voice interaction device, comprising: receiving module,
With module and output module.Receiving module is used to receive the voice messaging of user's input, and the voice messaging is converted to sentence
Text.Matching module from preset music commentary library for obtaining the comment information to match with the statement text.Export mould
Block is for exporting the comment information as the response for the voice messaging.
In one embodiment of the invention, above-mentioned apparatus further includes playing module, described in exporting in output module
After comment information is as the response for the voice messaging, music corresponding with the comment information is played.
In another embodiment of the invention, above-mentioned apparatus further include: the first preprocessing module and the second preprocessing module.
First preprocessing module is used to obtain the comment to match with the statement text from preset music commentary library in matching module
Before information, a plurality of comment information about music for meeting preset condition is obtained, is constructed by acquired a plurality of comment information
Preset music commentary library.Second preprocessing module for identification in preset music commentary library each comment information focus information and meaning
Figure information.Then matching module is used for focus information and intent information based on each comment information in the preset music commentary library,
The comment information to match with the statement text is obtained from preset music commentary library.
In another embodiment of the present invention, the first preprocessing module is specifically used for being handed over according to the history music of the user
Mutual behavioral data obtains the corresponding comment information of individualized music of the user, wherein the individualized music packet of the user
Include following at least one: the music or described that the music of user's collection, the music of user creation, the user like
The music that user plays；And/or obtain the corresponding comment information of current popularization music；And/or acquisition thumbs up number
More than the comment information of first threshold.
In one more embodiment of the present invention, matching module includes: identification submodule, the first matched sub-block and second
Sub-module.Identify the focus information and intent information of the submodule statement text for identification.First matched sub-block is used
In the focus information of the statement text is matched with the focus information of each comment information in the preset music commentary library,
Filter out the matched comment information of focus.Second matched sub-block is used for the intent information of the statement text and the focus
The intent information of matched comment information is matched, and is filtered out focus matching and is intended to matched comment information.
In one more embodiment of the present invention, the second preprocessing module is specifically used for believing based on tag library from each comment
The label for characterizing corresponding focus information is extracted in breath, is extracted and is used for from each comment information based on intent classifier library
Characterize the intention clause of corresponding intent information.Identify that submodule is specifically used for based on the tag library from the statement text
The label for characterizing corresponding focus information is extracted, is extracted from the statement text for characterizing phase based on intent classifier library
The intention clause for the intent information answered.First matched sub-block is specifically used for the label of the statement text and each comment
The label of information is matched, and is determined as the matched comment information of focus when matching degree is more than second threshold.And second
Sub-module be specifically used for by the intention clause of the intentions clause of the statement text and the matched comment information of the focus into
Row matching is determined as focus matching when matching degree is more than third threshold value and is intended to matched comment information.
In one more embodiment of the present invention, matching module further includes acquisition submodule and sorting sub-module.Obtain submodule
Block is used to obtain belonging to the corresponding music of each comment information when filtering out a plurality of focus matching and being intended to matched comment information
The priority of classification.Sorting sub-module is ranked up the comment for the priority based on the music, based on sequence knot
Fruit chooses a comment information.
In one more embodiment of the present invention, acquisition submodule is specifically used for the history music interaction row according to the user
For data, the comprehensive score of the corresponding music of each comment information is determined, wherein the history music interaction behavior of the user
Data include following at least one: the user collects the behavioral data of music, the user thumbs up the behavioral data of music, institute
State user play the behavioral data of music, the behavioral data of the user comment music, the user share music behavior number
According to or the user create music behavioral data.
In the third aspect of embodiment of the present invention, a kind of medium is provided, is stored with computer executable instructions, institute
Instruction is stated when being executed by processor for realizing voice interactive method described in any one of above-described embodiment.
In the fourth aspect of embodiment of the present invention, provide a kind of calculating equipment, comprising: memory, processor and
Store the executable instruction that can be run on a memory and on a processor, realization when processor executes instruction: above-described embodiment
Any one of described in voice interactive method.
The voice interactive method and device of embodiment according to the present invention, from numerous existing comment informations about music
The comment information that the voice messaging of middle selection and active user's input matches is write in advance without developer and is answered as response
Content is answered, a large amount of reductions write upper input manpower in response content.And due to comment information by real user be based on to phase
It answers expressed by the true emotional of music, using the comment information to match as the response of voice messaging, can cause currently to input
The emotional resonance of the user of voice messaging meets user feeling demand.
Detailed description of the invention
The following detailed description is read with reference to the accompanying drawings, above-mentioned and other mesh of exemplary embodiment of the invention
, feature and advantage will become prone to understand.In the accompanying drawings, if showing by way of example rather than limitation of the invention
Dry embodiment, in which:
Fig. 1 schematically shows the application scenarios of the voice interactive method and its device of embodiment according to the present invention；
Fig. 2 schematically shows the flow charts of voice interactive method according to an embodiment of the invention；
Fig. 3 schematically shows the flow chart of voice interactive method in accordance with another embodiment of the present invention；
Fig. 4 A schematically shows the schematic diagram in preset music commentary library according to an embodiment of the invention；
Fig. 4 B schematically shows the schematic diagram of interactive voice process according to an embodiment of the invention；
Fig. 5 A schematically shows the block diagram of voice interaction device according to an embodiment of the invention；
Fig. 5 B schematically shows the block diagram of voice interaction device in accordance with another embodiment of the present invention；
Fig. 6 schematically shows the block diagram of matching module according to an embodiment of the invention；
Fig. 7 schematically shows the schematic diagram of the computer readable storage medium product of embodiment according to the present invention；
And
Fig. 8 schematically shows the block diagram of the calculating equipment of embodiment according to the present invention.
In the accompanying drawings, identical or corresponding label indicates identical or corresponding part.
Specific embodiment
The principle and spirit of the invention are described below with reference to several illustrative embodiments.It should be appreciated that providing this
A little embodiments are used for the purpose of making those skilled in the art can better understand that realizing the present invention in turn, and be not with any
Mode limits the scope of the invention.On the contrary, these embodiments are provided so that this disclosure will be more thorough and complete, and energy
It is enough that the scope of the present disclosure is completely communicated to those skilled in the art.
One skilled in the art will appreciate that embodiments of the present invention can be implemented as a kind of system, device, equipment, method
Or computer program product.Therefore, the present disclosure may be embodied in the following forms, it may be assumed that complete hardware, complete software
The form that (including firmware, resident software, microcode etc.) or hardware and software combine.
Embodiment according to the present invention proposes a kind of voice interactive method, medium, device and calculates equipment.
Herein, it is to be understood that related term includes: voice messaging, statement text, preset music commentary
Library, comment information etc..Wherein, voice messaging is the audio data based on SoundRec, is phase by the Content Transformation of voice messaging
The text answered to get arrive statement text.Comment information refers to music commentary information, and any user can comment any music
By obtaining the comment information accordingly about music.Preset music commentary library is constructed by multiple comment informations about music.This
Outside, any number of elements in attached drawing be used to example rather than limit and it is any name be only used for distinguishing, without appoint
What limitation.
Below with reference to several representative embodiments of the invention, the principle and spirit of the present invention are explained in detail.
Summary of the invention
During realizing disclosure design, inventor's discovery: existing interactive voice scheme needs developer pre-
Machine response content is first write, when user's input voice information, voice messaging is converted into text, selection and text phase
The response content matched is as output.There are the following problems for the program: on the one hand, writing for response content needs to put into a large amount of people
Power, inefficiency, on the other hand, the response content write in advance is mechanical stiff, is unable to satisfy user feeling demand.
For this purpose, the embodiment of the invention provides a kind of voice interactive method and device, this method comprises: receiving user's input
Voice messaging, the voice messaging is converted into statement text；It is obtained and the statement text from preset music commentary library
The comment information to match；And the comment information is exported as the response for the voice messaging.The embodiment of the present disclosure
The comment to match with the voice messaging of active user's input is selected from numerous existing comment informations about music to believe
Breath is used as response, writes response content in advance without developer, and a large amount of reductions write upper input manpower in response content.
And as comment information as real user based on expressed by the true emotional to corresponding music, using the comment information to match as
The response of voice messaging can cause the emotional resonance of the user of current input voice information, meet user feeling demand.
After introduced the basic principles of the present invention, lower mask body introduces various non-limiting embodiment party of the invention
Formula.
Application scenarios overview
The voice interactive method of the embodiment of the present invention and its application scenarios of device are elaborated referring initially to Fig. 1.
Fig. 1 schematically shows the application scenarios of the voice interactive method and its device of embodiment according to the present invention.
As shown in Figure 1, including electronic equipment 110 and user 120 in the application scenarios, electronic equipment 110 has voice interactive function, with
User 120 carries out interactive voice.Electronic equipment 110 is intelligent sound box, in other embodiments, electronic equipment in the present embodiment
110 can be the arbitrary equipment with voice interactive function, such as smart phone, computer, smartwatch, various intelligent appliances
Deng herein with no restrictions.
Electronic equipment 110 acquires the voice messaging that user 120 inputs by microphone, and makes phase according to the voice messaging
The response answered executes corresponding task.For example, 120 input voice information of user " today, how is weather ", electronic equipment 110
Inquiry weather simultaneously responds " -4 degrees Celsius of minimum temperature, 6 degrees Celsius of maximum temperature, clear to cloudy " according to query result, or
Person, 120 input voice information of user " several points now ", electronic equipment 110 are inquired current time and are made according to query result
Response " 9 points 05 minute ".In the two examples, the voice messaging that user 120 inputs all is to have clear answer, electronic equipment 110
Clear answer can directly be inquired in response, however in daily life, the voice that in most cases user 120 inputs
Information is not clear answer, such as 120 input voice information of user " today is good sad ", and electronic equipment 110 is answered at this time
When using the content that is best suitable for the current psychological needs of user 120 as response.
Illustrative methods
Below with reference to the application scenarios of Fig. 1, the language of illustrative embodiments according to the present invention is described with reference to Fig. 2~Fig. 4 B
Sound exchange method.It should be noted which is shown only for the purpose of facilitating an understanding of the spirit and principles of the present invention for above-mentioned application scenarios,
Embodiments of the present invention are not limited in this respect.On the contrary, embodiments of the present invention can be applied to applicable appoint
What scene.
Fig. 2 schematically shows the flow charts of voice interactive method according to an embodiment of the invention.Such as Fig. 2 institute
Show, this method includes following operation:
S201 is operated, the voice messaging of user's input is received, the voice messaging is converted into statement text.
S202 is operated, the comment information to match with the statement text is obtained from preset music commentary library.
S203 is operated, exports the comment information as the response for the voice messaging.
As it can be seen that the voice messaging that method shown in Fig. 2 inputs user, believes from numerous existing comments about music
The comment information to match with the voice messaging of active user's input is selected in breath as response, is write in advance without developer
Response content is write, a large amount of reductions write upper input manpower in response content.And since comment information is based on by real user
Expressed by true emotional to corresponding music, using the comment information to match as the response of voice messaging, it can cause current
The emotional resonance of the user of input voice information meets user feeling demand.
Fig. 3 schematically shows the flow chart of voice interactive method in accordance with another embodiment of the present invention.Such as Fig. 3 institute
Show, this method includes operation S201~S204, wherein operation S201~S203 is identical as each operation correspondence shown in Fig. 2, herein
It repeats no more.
S204 is operated, music corresponding with the comment information is played.
In specific example, it is corresponding can directly to play the comment information after output comment information is as response
Music, can also be in output comment information as in the predetermined time after response, the broadcasting when meeting preset trigger condition
The corresponding music of the comment information.It is each that the corresponding music of comment information can be song, absolute music, cross-talk, speech, broadcast etc.
Kind audio file, herein with no restrictions.
In the embodiment of the present disclosure, for any music, user can evaluate the music, obtain comment information,
Therefore any music corresponds to comment information of one or more users about the music, includes one in preset music commentary library
Or the comment information of multiple music.After the voice messaging for receiving user's input, which is converted into statement text,
The comment information to match with the statement text is obtained from preset music commentary library, the comment information got can be expressed
The mood similar with the voice messaging of input exports the comment information as response, can cause currently to input voice letter naturally
The emotional resonance of the user of breath.Further, the corresponding music of the comment information is also played after exporting the comment information, due to
Mood expressed by the comment information is caused by the corresponding music of the comment information, illustrates that the music adapts to the feelings
Thread, the user of Xiang Dangqian input voice information play the music, can build the atmosphere for adapting to the user emotion, so that voice
Interactive process is more natural, rich in emotion, is no longer stiff mechanical human-computer interaction in the prior art.
In embodiment of the disclosure, it is obtained and the statement text phase from preset music commentary library in operation S202
Before the comment information matched, method shown in Fig. 2 or Fig. 3 can also include some preprocessing process: acquisition meets preset condition
The a plurality of comment information about music constructs preset music commentary library by acquired a plurality of comment information；Identify preset music
Comment on the focus information and intent information of each comment information in library.Above-mentioned preprocessing process constructs preset music commentary library, this is pre-
Setting music commentary library includes a plurality of comment information about music for meeting preset condition, and it also requires to preset music commentary
Comment information in library carries out identifying processing, identifies the focus information and intent information of each comment information.Wherein, comment information
Focus information refers to most important information expressed by comment information, is that the promoter of comment information wishes the viewing of comment information
The part that person pays attention to when seeing the comment information, each comment information may include one or more focus informations, the focus
Information can be characterized by one or more labels.The intent information of comment information refers to the promoter of comment information by being somebody's turn to do
The operation or purpose for the desired realization that comment information gives expression to.
On this basis, operation S202 obtains the comment to match with the statement text from preset music commentary library and believes
Breath includes: focus information and intent information based on each comment information in the preset music commentary library, is obtained and the sentence
The comment information that text matches.Scheme according to the present embodiment, be based on focus information and intent information, to comment information with it is defeated
The statement text for entering voice messaging is matched, since focus information and intent information be able to reflect the mood of real user, thinks
The subjective factors such as method, viewpoint can effectively get mood similar with input voice information expression based on these two types of information, think
Method, the comment information of viewpoint, the user of current input voice information is farthest adapted to from psychological levels.
Specifically, as an optional embodiment, above-mentioned acquisition meets a plurality of comment about music of preset condition
Information includes: the history music interaction behavioral data according to the user, and the individualized music for obtaining the user corresponding is commented
By information, wherein the individualized music of the user includes following at least one: the music of user's collection, the user
The music that the music or the user that the music of creation, the user like play.And/or obtain current popularization music
Corresponding comment information.And/or obtain the comment information for thumbing up that number is more than first threshold.
Scheme according to the present embodiment, preset music commentary library may include the individual character of the current user for carrying out interactive voice
Change the comment information of music, the individualized music of user reflects the music preferences of user, from the comment of the music of user preference
The comment information to match with the voice messaging of user input is obtained in information as response, and further plays corresponding sound
It is happy, it is easier to cause the sympathetic response of the user.Preset music commentary library also may include the corresponding comment information of current popularization music,
The comment information to match with the voice messaging of user's input is obtained from the current comment information for promoting music as response, and
Corresponding popularization music is further played, not only can satisfy the interactive voice demand of user, moreover it is possible to recommend corresponding promote to user
Music.Preset music commentary library also may include thumbing up the comment information that number is more than first threshold, i.e., popular comment information, popular
Comment information is comment information that is representative, can causing most people sympathetic response, from popular comment information obtain with
The comment information that the voice messaging of user's input matches further plays corresponding music as response, it is easier to cause this
The sympathetic response of user.
In one embodiment of the present disclosure, the above-mentioned focus letter based on each comment information in the preset music commentary library
Breath and intent information, obtaining the comment information to match with the statement text includes: to identify that the focus of the statement text is believed
Breath and intent information；By the focus information of each comment information in the focus information of the statement text and preset music commentary library into
Row matching, filters out the matched comment information of focus；And it is the intent information of the statement text and the focus is matched
The intent information of comment information is matched, and is filtered out focus matching and is intended to matched comment information.
Wherein, the focus information of statement text refers to most important information expressed by the statement text, is sentence text
The promoter of this corresponding voice messaging wishes the part that recipient pays attention to, each statement text may include one or more burnt
Point information, the focus information can be characterized by one or more labels.The intent information of statement text refers to sentence text
The operation or purpose for the desired realization that the promoter of this corresponding voice messaging gives expression to.The above process first carries out focus matching,
It filters out with the matched comment information of statement text focus, screens out a large amount of unrelated comment informations, then carry out intention matching, screen
Matched comment information is matched and be intended to statement text focus out, improves matching efficiency.
Specifically, as an optional embodiment, the focus of each comment information in the above-mentioned preset music commentary library of identification
Information and intent information include: the mark extracted from each comment information based on tag library for characterizing corresponding focus information
Label, the intention clause for characterizing corresponding intent information is extracted based on intent classifier library from each comment information.It is above-mentioned
It identifies the focus information of the statement text and intent information includes: to extract use from the statement text based on the tag library
In the label for characterizing corresponding focus information, extracted from the statement text for characterizing corresponding meaning based on intent classifier library
The intention clause of figure information.The coke of each comment information in the above-mentioned focus information by the statement text and music commentary library
It includes: to match the label of the statement text with the label of each comment information that point information, which carries out matching, works as matching
Degree is determined as the matched comment information of focus when being more than second threshold.And the above-mentioned intent information by the statement text with
It includes: by the intention clause of the statement text and the coke that the intent information of the matched comment information of focus, which carries out matching,
The intention clause of the matched comment information of point is matched, and is determined as focus matching when matching degree is more than third threshold value and is intended to
Matched comment information.
Wherein it is possible to tag library and intent classifier library used in identification focus information and intent information are preset, and
It constantly updates and expands in use.The process of the focus information of above-mentioned identification comment information and the focus of identification statement text
The process of information uses identical tag library, so that the extraction standard of focus information is consistent, guarantees the matched standard of subsequent focus
True property.And it is identical to identify that the process of the intent information of comment information and the process of the intent information of identification statement text use
Intent classifier library guarantees the subsequent matched accuracy of intention so that the extraction standard of intent information is consistent.
In another embodiment of the disclosure, can in advance in the preset music commentary library of nonrecognition comment information focus
Information and intent information operate S202 from preset music commentary after the voice messaging for inputting user is converted to statement text
It may include: the focus information and meaning for identifying the statement text that the comment information to match with the statement text is obtained in library
Figure information；The focus information of the statement text is matched with each comment information in preset music commentary library, screening is discharged of the coke
The matched comment information of point；And by the intention of the intent information of the statement text and the matched comment information of the focus
Information is matched, and is filtered out focus matching and is intended to matched comment information.
When filtering out a focus matching and being intended to matched comment information, directly exports comment information conduct and answer
Answer, when filtering out the matching of a plurality of focus and being intended to matched comment information, as an optional embodiment, operate S202 from
The comment information to match with the statement text is obtained in preset music commentary library further include: match when filtering out a plurality of focus
And when being intended to matched comment information, the priority of the corresponding music of each comment information is obtained；Priority based on the music
The comment is ranked up, chooses a comment information based on ranking results.
Wherein optionally, the priority for obtaining the corresponding music of each comment information includes: going through according to the user
History music interaction behavioral data determines the comprehensive score of the corresponding music of each comment information, the history music of the user
Interbehavior data include following at least one: the behavioral data of user's collection music, the user thumb up the row of music
The behavioral data of music, the behavioral data of the user comment music, user sharing music are played for data, the user
Behavioral data or the user create music behavioral data.
Below with reference to Fig. 4 A~Fig. 4 B, Fig. 2~method shown in Fig. 3 is illustrated in conjunction with specific embodiments:
In the present embodiment, user A and intelligent sound box carry out interactive voice, and preset sound is first constructed before interactive voice starts
Music comment opinion library.
Fig. 4 A schematically shows the schematic diagram in preset music commentary library according to an embodiment of the invention.
It as shown in Figure 4 A, include: the corresponding comment information of individualized music of user A in preset music commentary library, currently
The comment information of popularization music in predetermined time, and popular comment information.Wherein, the individualized music of user A refers to use
Family A such as is collected, is created, being liked, being shared, being played at the music of positive music interaction behavior, the popularization in the current predetermined time
Music includes that hot music in the current predetermined time, the music for needing to promote with partner agreement etc. are one or more, popular
Comment information, which refers to, thumbs up the comment information that number is more than or equal to 500.
According to the history interactive voice content of user A, preliminary basic label is filtered out, such as basic label includes: " lonely
Solely ", " insomnia ", " sad ", " memory ", " sorrow ", " anxiety " etc. construct basic label library by these basic labels.Based on this
Basic label in basic label library forms clause, carries out semantic clause to the standby comment information in preset music commentary library and takes out
It takes, so that each comment information is carried out basic label classification, and concludes into intent classifier clause, form intent classifier library, root
According to the clause expandtabs library extracted.The extraction of sentence clause is carried out to each comment information again based on the tag library after expansion, it will
Each comment information is updated labeling, concludes into intent classifier library, and again according to the clause expandtabs extracted
Library.And so on, continuous cyclic extension is reached final tag library and intent classifier library, and is obtained based on final tag library
For characterizing one or more labels of the focus information of each comment information, obtained based on final intent classifier library for characterizing
The intention clause of the intent information of each comment information.
Fig. 4 B schematically shows the schematic diagram of interactive voice process according to an embodiment of the invention.
When intelligent sound box receives the voice messaging of user A input, pass through speech recognition technology (ASR, Automatic
Speech Recognition) voice messaging is converted into statement text, in this example, the voice messaging of user A input is corresponding
Statement text be " I can't fall asleep ".It is right based on natural language understanding (NLU, Natural Language Understanding)
The statement text carries out semantic analysis, obtains the intention clause for characterizing the intent information of the statement text: { I, chats, comfort },
Obtain the multiple labels for characterizing the focus information of the statement text: { insomnia, lonely }.
Comment in preset music commentary library shown in focus information and Fig. 4 A based on preset algorithm computing statement text
The similarity of information filters out the comment information that similarity is higher than second threshold.In this example, calculated using recommender system item_cf
The similarity of the corresponding label of method computing statement text " I can't fall asleep " { insomnia, lonely } label corresponding with each comment information,
Filter out 5 comment informations in preset music commentary library shown in Fig. 4 B: comment 1, comment 2, comment 3, comment 4, comment 5.
Wherein, 1 corresponding intention clause of comment is { chat }, and 2 corresponding intention clause of comment are { chat, comfort }, and comment 3 is corresponding
Being intended to clause is { treatment }, and 4 corresponding intention clause of comment are { video display }, and 5 corresponding intention clause of comment are { chat, peace
Console }.
The intent information of statement text intention clause corresponding with the comment information filtered out is matched, is further sieved
Select the comment information that matching degree is more than third threshold value.In this example, by the corresponding intention clause of statement text " I can't fall asleep "
{ I, chats, comfort } intention clause corresponding with 5 comment informations filtered out above is matched, and intention clause is filtered out
Comment information including { chat, comfort }, that is, comment on 2 and comment 5.
According to the history music interaction behavioral data of user A, the comprehensive of the corresponding music of each comment information filtered out is determined
Scoring is closed, the corresponding comment information of the highest music of comprehensive score is chosen.Further, it is also contemplated that each comment information selected
Other speciality of corresponding music in addition to user preference, as liked according to popularization music > user in the current predetermined time
Music > user plays more than each comment of the priority orders of music > user's collection music of the 4th threshold value to screening
Information is ranked up, and chooses a comment of highest priority.In this example, to the comment 2 and comment 5 filtered out according to user A
Music preferences sequence, 5 corresponding music of comment are the music liked of user A, have higher priority, finishing screen, which is selected, to be commented
By 5, corresponding music are as follows: song " late into the night dining room ".
Intelligent sound box by speech synthesis technique (TTS, Text to speech) by comment 5 be converted to voice messaging " according to
Say, at night restless people, be because waking up in others' dream " and export, " I can't fall asleep " as user A input is answered
It answers.And it is possible to 5 corresponding music " late into the night dining room " of comment directly be played, alternatively, playing 5 pairs of comment after user A confirmation
The music " late into the night dining room " answered.Since the music is the favorite song of user A, and comment on 5 be other real users be based on with
What the similar mood of " I can't fall asleep " of family A write, when intelligent sound box output comment 5 is used as response and plays corresponding song,
User A emotion and sympathetic response will be brought, is the human-computer interaction process for more having temperature.
The embodiment of the present disclosure can reduce human input cost needed for interactive voice, make full use of existing true use
Write the comment information of generation in family；By choosing the comment information to match with the statement text of input as response, Neng Gouti
The emotional interaction in interactive voice is risen, the question-response formula dialogue of machine is different from, the content not only answered meets user's heart
Reason demand, the music for matching broadcasting also help to build atmosphere, and user is allowed to feel emotional resonance.
Exemplary means
After describing the method for exemplary embodiment of the invention, next, showing with reference to Fig. 5 A~Fig. 6 the present invention
The voice interaction device of example property embodiment is described in detail.
Fig. 5 A schematically shows the block diagram of voice interaction device according to an embodiment of the invention.Such as Fig. 5 A institute
Show, which includes:
Receiving module 510 is used to receive the voice messaging of user's input, and the voice messaging is converted to statement text.
Matching module 520 from preset music commentary library for obtaining the comment information to match with the statement text.
Output module 530 is for exporting the comment information as the response for the voice messaging.
As it can be seen that the voice messaging that device shown in Fig. 5 A inputs user, from numerous existing comments about music
The comment information to match with the voice messaging of active user's input is selected in information as response, and it is preparatory to be not necessarily to developer
Response content is write, a large amount of reductions write upper input manpower in response content.And since comment information is by real user base
Expressed by the true emotional to corresponding music, using the comment information to match as the response of voice messaging, it can cause to work as
The emotional resonance of the user of preceding input voice information meets user feeling demand.
Fig. 5 B schematically shows the block diagram of voice interaction device in accordance with another embodiment of the present invention.Such as Fig. 5 B institute
Show, which includes: receiving module 510, matching module 520, output module 530, playing module 540,
One preprocessing module 550 and the second preprocessing module 560.Wherein, receiving module 510, matching module 520 and output module 530
Hereinbefore it is stated that, duplicate part repeats no more.
Playing module 540 is used to export the comment information as answering for the voice messaging in the output module
After answering, music corresponding with the comment information is played.
In one embodiment of the present disclosure, it is obtained from preset music commentary library in matching module 520 and the sentence
Before the comment information that text matches, the first preprocessing module 550 meets a plurality of about music of preset condition for obtaining
Comment information, preset music commentary library is constructed by acquired a plurality of comment information.Second preprocessing module 560 is for identification
The focus information and intent information of each comment information in preset music commentary library.
On this basis, matching module 520 is obtained from preset music commentary library and is commented with what the statement text matched
By information specifically: focus information and intent information based on each comment information in the preset music commentary library, from preset sound
The comment information to match with the statement text is obtained in music comment opinion library.
Wherein specifically, as an optional embodiment, the first preprocessing module 550 is used for going through according to the user
History music interaction behavioral data obtains the corresponding comment information of individualized music of the user, wherein the individual character of the user
It includes following at least one for changing music: the sound that the music of user's collection, the music of user creation, the user like
The music that the happy or described user plays；And/or obtain the corresponding comment information of current popularization music；And/or it obtains
Take the comment information for thumbing up that number is more than first threshold.
Fig. 6 schematically shows the block diagram of matching module according to an embodiment of the invention.As shown in fig. 6, this
It include: identification submodule 521, the first matched sub-block 522, the second matched sub-block 523, acquisition submodule 524 with module 520
With sorting sub-module 525.
In one embodiment of the present disclosure, identification submodule 521 for identification the focus information of the statement text and
Intent information.First matched sub-block 522 in the focus information of the statement text and preset music commentary library for will respectively comment
It is matched by the focus information of information, filters out the matched comment information of focus.And second matched sub-block 523 be used for
The intent information of the statement text is matched with the intent information of the matched comment information of the focus, filters out focus
It matches and is intended to matched comment information.
Wherein, as an optional embodiment, the second preprocessing module 560 is specifically used for based on tag library from described each
The label for characterizing corresponding focus information is extracted in comment information, is mentioned from each comment information based on intent classifier library
It takes in the intention clause for characterizing corresponding intent information.Identify that submodule 521 is specifically used for based on the tag library from described
The label for characterizing corresponding focus information is extracted in statement text, is extracted from the statement text based on intent classifier library
For characterizing the intention clause of corresponding intent information.First matched sub-block 522 is specifically used for the mark of the statement text
Label are matched with the label of each comment information, are determined as the matched comment letter of focus when matching degree is more than second threshold
Breath.And second matched sub-block 523 be specifically used for the intention clause of the statement text and the matched comment of the focus
The intention clause of information is matched, and is determined as focus matching when matching degree is more than third threshold value and is intended to matched comment letter
Breath.
In one embodiment of the present disclosure, acquisition submodule 524, which is used to work as, filters out a plurality of focus matching and intention
When the comment information matched, the priority of the corresponding music generic of each comment information is obtained.Sorting sub-module 525 is for being based on
The priority of the music is ranked up the comment, chooses a comment information based on ranking results.
Wherein optionally, acquisition submodule 524 is specifically used for the history music interaction behavioral data according to the user, really
The comprehensive score of the corresponding music of fixed each comment information, wherein the history music interaction behavioral data of the user includes
Following at least one: the behavioral data of user's collection music, the user thumbs up the behavioral data of music, the user broadcasts
The behavioral data of the behavioral data, the user comment music put the music on, the user share the behavioral data or described of music
The behavioral data of user's creation music.
It should be noted that in device section Example each module/unit/subelement etc. embodiment, the skill of solution
Art problem, the function of realization and the technical effect reached respectively with the implementation of corresponding step each in method section Example
Mode, the technical issues of solving, the function of realization and the technical effect that reaches are same or like, and details are not described herein.
Exemplary media
After describing the method and apparatus of exemplary embodiment of the invention, next, to the exemplary reality of the present invention
The medium for applying the realization voice interactive method of mode is introduced.
The embodiment of the invention provides a kind of media, are stored with computer executable instructions, above-metioned instruction is by processor
For realizing voice interactive method described in any one of above method embodiment when execution.
In some possible embodiments, various aspects of the invention are also implemented as a kind of shape of program product
Formula comprising program code, when described program product is run on the computing device, said program code is for making the calculating
Equipment executes described in above-mentioned " illustrative methods " part of this specification the language of various illustrative embodiments according to the present invention
Step in sound exchange method can also execute for example, the calculating equipment can execute operating procedure as shown in Figure 2
Operating procedure as shown in Figure 3.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example may be-but not limited to-electricity, magnetic, optical, electromagnetic, red
The system of outside line or semiconductor, device or device, or any above combination.The more specific example of readable storage medium storing program for executing
(non exhaustive list) includes: the electrical connection with one or more conducting wires, portable disc, hard disk, random access memory
(RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc
Read memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Fig. 7 schematically shows the schematic diagram of the computer readable storage medium product of embodiment according to the present invention,
As shown in fig. 7, describing the program product 70 of the realization voice interactive method of embodiment according to the present invention, can use
Portable compact disc read only memory (CD-ROM) and including program code, and can be on calculating equipment, such as PC
Operation.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing, which can be, any to be included or deposits
The tangible medium of program is stored up, which can be commanded execution system, device or device use or in connection.
Readable signal medium may include in a base band or as the data-signal that carrier wave a part is propagated, wherein carrying
Readable program code.The data-signal of this propagation can take various forms, including --- but being not limited to --- electromagnetism letter
Number, optical signal or above-mentioned any appropriate combination.Readable signal medium can also be other than readable storage medium storing program for executing it is any can
Read medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Program in connection.
The program code for including on readable medium can transmit with any suitable medium, including --- but being not limited to ---
Wirelessly, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language --- and such as Java, C++ etc. further include routine
Procedural programming language --- such as " C ", language or similar programming language.Program code can fully exist
It executes in user calculating equipment, partly execute on a user device, executing, as an independent software package partially in user
Upper side point is calculated to execute or execute in remote computing device or server completely on a remote computing.It is relating to
And in the situation of remote computing device, remote computing device can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN) one is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize internet
Service provider is connected by internet).
Exemplary computer device
After method, medium and the device for describing exemplary embodiment of the invention, next, introducing according to this hair
The calculating equipment of the realization voice interactive method of bright another exemplary embodiment.
The embodiment of the invention also provides a kind of calculating equipment, comprising: memory, processor and storage are on a memory simultaneously
The executable instruction that can be run on a processor, the processor are realized any in above method embodiment when executing described instruction
Voice interactive method described in.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
In some possible embodiments, the calculating equipment according to the present invention for realizing voice interactive method can be at least
Including at least one processing unit and at least one storage unit.Wherein, the storage unit is stored with program code, when
When said program code is executed by the processing unit, so as to execute this specification above-mentioned " illustrative methods " for the processing unit
Operating procedure in the data processing method of various illustrative embodiments according to the present invention described in part.For example, described
Processing unit can execute operating procedure as shown in Figure 2, can also execute operating procedure as shown in Figure 3.
The calculating equipment of the realization voice interactive method of this embodiment according to the present invention is described referring to Fig. 8
80.Calculating equipment 80 as shown in Figure 8 is only an example, should not function to the embodiment of the present invention and use scope bring
Any restrictions.
It is showed in the form of universal computing device as shown in figure 8, calculating equipment 80.Calculate equipment 80 component may include
But it is not limited to: at least one above-mentioned processing unit 801, at least one above-mentioned storage unit 802, connection different system components (packet
Include storage unit 802 and processing unit 801) bus 803.
Bus 803 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.
Storage unit 802 may include the readable medium of form of volatile memory, such as random access memory (RAM)
8021 and/or cache memory 8022, it can further include read-only memory (ROM) 8023.
Storage unit 802 can also include program/utility with one group of (at least one) program module 8024
8025, such program module 8024 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Calculating equipment 80 can also be with one or more external equipment 804 (such as keyboard, sensing equipment, bluetooth equipment etc.)
Communication can also be enabled a user to communicate with the equipment that calculating equipment 80 interacts with one or more, and/or be set with to calculate
The standby 80 any equipment (such as router, modem etc.) that can be communicated with one or more of the other calculating equipment are led to
Letter.This communication can be carried out by input/output (I/0) interface 805.Also, calculating equipment 80 can also be suitable by network
Orchestration 806 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as because of spy
Net) communication.As shown, network adapter 806 is communicated by bus 803 with the other modules for calculating equipment 80.It should be understood that
Although not shown in the drawings, other hardware and/or software module can be used in conjunction with equipment 80 is calculated, including but not limited to: micro- generation
Code, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup are deposited
Storage system etc..
It should be noted that although being referred to several units/modules or son list of data processing equipment in the above detailed description
Member/module, but it is this division be only exemplary it is not enforceable.In fact, embodiment according to the present invention, on
The feature and function of two or more units/modules of text description can embody in a units/modules.Conversely, above
The feature and function of one units/modules of description can be to be embodied by multiple units/modules with further division.
In addition, although describing the operation of the method for the present invention in the accompanying drawings with particular order, this do not require that or
Hint must execute these operations in this particular order, or have to carry out shown in whole operation be just able to achieve it is desired
As a result.Additionally or alternatively, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/or by one
Step is decomposed into execution of multiple steps.
Although detailed description of the preferred embodimentsthe spirit and principles of the present invention are described by reference to several, it should be appreciated that, this
It is not limited to the specific embodiments disclosed for invention, does not also mean that the feature in these aspects cannot to the division of various aspects
Combination is benefited to carry out, this to divide the convenience merely to statement.The present invention is directed to cover appended claims spirit and
Included various modifications and equivalent arrangements in range.
Claims (10)
1. a kind of voice interactive method, comprising:
The voice messaging for receiving user's input, is converted to statement text for the voice messaging；
The comment information to match with the statement text is obtained from preset music commentary library；And
The comment information is exported as the response for the voice messaging.
2. according to the method described in claim 1, wherein, being used as in the output comment information for the voice messaging
Response after, the method also includes: play corresponding with comment information music.
3. according to the method described in claim 1, wherein:
Described before the comment information that acquisition matches with the statement text in preset music commentary library, the method is also
Include:
The a plurality of comment information about music for meeting preset condition is obtained, preset sound is constructed by acquired a plurality of comment information
Music comment opinion library；And
Identify the focus information and intent information of each comment information in preset music commentary library；
Described obtain from preset music commentary library with the comment information that the statement text matches includes: based on described preset
The focus information and intent information of each comment information in music commentary library obtain the comment to match with the statement text and believe
Breath.
4. according to the method described in claim 3, wherein, a plurality of comment about music that the acquisition meets preset condition is believed
Breath includes:
According to the history music interaction behavioral data of the user, the corresponding comment letter of individualized music of the user is obtained
Breath, wherein the individualized music of the user includes following at least one: the music of user's collection, user creation
The music that plays of music, the music liked of the user or the user；And/or
Obtain the corresponding comment information of current popularization music；And/or
Obtain the comment information for thumbing up that number is more than first threshold.
5. according to the method described in claim 3, wherein, the coke based on each comment information in the preset music commentary library
Point information and intent information, obtaining the comment information to match with the statement text includes:
Identify the focus information and intent information of the statement text；
By the focus information progress of each comment information in the focus information of the statement text and the preset music commentary library
Match, filters out the matched comment information of focus；And
The intent information of the statement text is matched with the intent information of the matched comment information of the focus, is filtered out
Focus matches and is intended to matched comment information.
6. according to the method described in claim 5, wherein:
The focus information of each comment information and intent information include: based on tag library from institute in the preset music commentary library of the identification
The label extracted in each comment information for characterizing corresponding focus information is stated, is based on intent classifier library from each comment information
The middle intention clause extracted for characterizing corresponding intent information；
The focus information and intent information of the identification statement text include: based on the tag library from the statement text
The middle label extracted for characterizing corresponding focus information is extracted from the statement text for characterizing based on intent classifier library
The intention clause of corresponding intent information；
The focus information progress of each comment information in the focus information by the statement text and music commentary library
With including: to match the label of the statement text with the label of each comment information, when matching degree is more than the second threshold
It is determined as focus matched comment information when value；And
The intent information of the intent information by the statement text and the matched comment information of focus carries out matching packet
It includes: the intention clause of the statement text being matched with the intention clause of the matched comment information of the focus, works as matching
Degree is determined as focus matching and is intended to matched comment information when being more than third threshold value.
7. according to the method described in claim 5, wherein, described obtain from music commentary library matches with the statement text
Comment information further include:
When filtering out a plurality of focus matching and being intended to matched comment information, the preferential of the corresponding music of each comment information is obtained
Grade；And
Priority based on the music is ranked up the comment, chooses a comment information based on ranking results.
8. a kind of voice interaction device, comprising:
The voice messaging is converted to statement text for receiving the voice messaging of user's input by receiving module；
Matching module, for obtaining the comment information to match with the statement text from preset music commentary library；And
Output module, for exporting the comment information as the response for the voice messaging.
9. a kind of medium, be stored with computer executable instructions, described instruction when being executed by processor for realizing:
Voice interactive method as described in any one of claims 1 to 7.
10. a kind of calculating equipment, comprising: memory, processor and storage on a memory and can run on a processor can
It executes instruction, the processor is realized when executing described instruction:
Voice interactive method as described in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910005993.4A CN109710799B (en) | 2019-01-03 | 2019-01-03 | Voice interaction method, medium, device and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910005993.4A CN109710799B (en) | 2019-01-03 | 2019-01-03 | Voice interaction method, medium, device and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109710799A true CN109710799A (en) | 2019-05-03 |
| CN109710799B CN109710799B (en) | 2021-08-27 |
Family
ID=66260703
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910005993.4A Active CN109710799B (en) | 2019-01-03 | 2019-01-03 | Voice interaction method, medium, device and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109710799B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110413834A (en) * | 2019-06-14 | 2019-11-05 | 北京字节跳动网络技术有限公司 | Voice remark method of modifying, system, medium and electronic equipment |
| CN112749260A (en) * | 2019-10-31 | 2021-05-04 | 阿里巴巴集团控股有限公司 | Information interaction method, device, equipment and medium |
| WO2021147710A1 (en) * | 2020-01-20 | 2021-07-29 | 北京大米未来科技有限公司 | Data processing method and apparatus, storage medium, and electronic device |
| CN113744071A (en) * | 2021-08-03 | 2021-12-03 | 北京搜狗科技发展有限公司 | Comment information processing method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559619A (en) * | 2013-11-12 | 2014-02-05 | 北京京东尚科信息技术有限公司 | Response method and system for garment size information |
| CN103970791A (en) * | 2013-02-01 | 2014-08-06 | 华为技术有限公司 | Method and device for recommending video from video database |
| CN107153641A (en) * | 2017-05-08 | 2017-09-12 | 北京百度网讯科技有限公司 | Comment information determines method, device, server and storage medium |
| CN107688608A (en) * | 2017-07-28 | 2018-02-13 | 合肥美的智能科技有限公司 | Intelligent sound answering method, device, computer equipment and readable storage medium storing program for executing |
| CN108227932A (en) * | 2018-01-26 | 2018-06-29 | 上海智臻智能网络科技股份有限公司 | Interaction is intended to determine method and device, computer equipment and storage medium |
| CN108804456A (en) * | 2017-04-28 | 2018-11-13 | 微软技术许可有限责任公司 | Chat sessions based on the knowledge base specific to object |
| WO2018214163A1 (en) * | 2017-05-26 | 2018-11-29 | Microsoft Technology Licensing, Llc | Providing product recommendation in automated chatting |
| WO2018232622A1 (en) * | 2017-06-21 | 2018-12-27 | Microsoft Technology Licensing, Llc | Media content recommendation through chatbots |
-
2019
- 2019-01-03 CN CN201910005993.4A patent/CN109710799B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970791A (en) * | 2013-02-01 | 2014-08-06 | 华为技术有限公司 | Method and device for recommending video from video database |
| CN103559619A (en) * | 2013-11-12 | 2014-02-05 | 北京京东尚科信息技术有限公司 | Response method and system for garment size information |
| CN108804456A (en) * | 2017-04-28 | 2018-11-13 | 微软技术许可有限责任公司 | Chat sessions based on the knowledge base specific to object |
| CN107153641A (en) * | 2017-05-08 | 2017-09-12 | 北京百度网讯科技有限公司 | Comment information determines method, device, server and storage medium |
| WO2018214163A1 (en) * | 2017-05-26 | 2018-11-29 | Microsoft Technology Licensing, Llc | Providing product recommendation in automated chatting |
| WO2018232622A1 (en) * | 2017-06-21 | 2018-12-27 | Microsoft Technology Licensing, Llc | Media content recommendation through chatbots |
| CN107688608A (en) * | 2017-07-28 | 2018-02-13 | 合肥美的智能科技有限公司 | Intelligent sound answering method, device, computer equipment and readable storage medium storing program for executing |
| CN108227932A (en) * | 2018-01-26 | 2018-06-29 | 上海智臻智能网络科技股份有限公司 | Interaction is intended to determine method and device, computer equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110413834A (en) * | 2019-06-14 | 2019-11-05 | 北京字节跳动网络技术有限公司 | Voice remark method of modifying, system, medium and electronic equipment |
| CN110413834B (en) * | 2019-06-14 | 2022-07-05 | 北京字节跳动网络技术有限公司 | Voice comment modification method, system, medium and electronic device |
| CN112749260A (en) * | 2019-10-31 | 2021-05-04 | 阿里巴巴集团控股有限公司 | Information interaction method, device, equipment and medium |
| WO2021147710A1 (en) * | 2020-01-20 | 2021-07-29 | 北京大米未来科技有限公司 | Data processing method and apparatus, storage medium, and electronic device |
| CN113744071A (en) * | 2021-08-03 | 2021-12-03 | 北京搜狗科技发展有限公司 | Comment information processing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109710799B (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109710799A (en) | Voice interactive method, medium, device and calculating equipment | |
| JP6876752B2 (en) | Response method and equipment | |
| US8285654B2 (en) | Method and system of providing a personalized performance | |
| CN109165302B (en) | Multimedia file recommendation method and device | |
| CN111737444B (en) | Dialog generation method and device and electronic equipment | |
| US10679626B2 (en) | Generating interactive audio-visual representations of individuals | |
| CN108737872A (en) | Method and apparatus for output information | |
| CN106250553A (en) | A kind of service recommendation method and terminal | |
| CN107092664A (en) | A kind of content means of interpretation and device | |
| CN111372109A (en) | Intelligent television and information interaction method | |
| CN108140030A (en) | Conversational system, terminal, the method for control dialogue and the program for making computer performance conversational system function | |
| US11188605B2 (en) | Systems and methods for recommending collaborative content | |
| CN109671435A (en) | Method and apparatus for waking up smart machine | |
| US20210034661A1 (en) | Systems and methods for recommending collaborative content | |
| CN111383669A (en) | Multimedia file uploading method, device, equipment and computer readable storage medium | |
| CN112883209A (en) | Recommendation method and processing method, device, equipment and readable medium for multimedia data | |
| CN108920649A (en) | A kind of information recommendation method, device, equipment and medium | |
| CN110148393B (en) | Music generation method, device and system and data processing method | |
| CN103488669A (en) | Information processing apparatus, information processing method and program | |
| CN110111611A (en) | Information processing method, device, medium and electronic equipment | |
| CN109829075A (en) | The method and apparatus that intelligence plays music | |
| CN114297354B (en) | Bullet screen generation method and device, storage medium and electronic device | |
| CN110263346A (en) | Lexical analysis method, electronic equipment and storage medium based on small-sample learning | |
| CN109918502A (en) | Document explains method, apparatus, computer installation and computer readable storage medium | |
| CN111522914B (en) | Labeling data acquisition method and device, electronic equipment and storage medium |
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 |