CN110136701A - Interactive voice service processing method, device and equipment - Google Patents
Interactive voice service processing method, device and equipment Download PDFInfo
- Publication number
- CN110136701A CN110136701A CN201810134247.0A CN201810134247A CN110136701A CN 110136701 A CN110136701 A CN 110136701A CN 201810134247 A CN201810134247 A CN 201810134247A CN 110136701 A CN110136701 A CN 110136701A
- Authority
- CN
- China
- Prior art keywords
- service subsystem
- user
- interactive voice
- collection
- subsystem
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/16—Speech classification or search using artificial neural networks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
- G10L2015/227—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of the speaker; Human-factor methodology
Abstract
The embodiment of the present invention provides a kind of interactive voice service processing method, device and equipment, this method comprises: in response to the interactive voice of user's triggering, according to the interactive voice matching degree between multiple service subsystems respectively, candidate service subsystem collection corresponding with interactive voice is determined from multiple service subsystems；According to the user's characteristic information of user, processing is modified to candidate service subsystem collection；If it only includes a service subsystem that revised candidate service subsystem, which is concentrated, interactive voice is responded with a service subsystem.By being modified processing to service subsystem collection according to user's characteristic information, can obtain for users has specific aim, rational candidate service subsystem more to provide more preferably interactive voice service for user.
Description
Technical field
The present invention relates to Internet technical field more particularly to a kind of interactive voice service processing methods, device and equipment.
Background technique
With the continuous development of Internet technology, artificial intelligence technology, intelligent speech interactive system has been configured in respectively
In kind intelligent electronic device, to provide various interactive voice services for user.
For example when user's shopping, the information such as itself height, weight, the required type of merchandise can be inputted, with voice to purchase
Object platform can recommend the items list for meeting user demand for user.For another example, in intelligent vehicle-carried platform, user can also be with
Mode by voice input carries out weather lookup, song search etc..
When some system or platform support multi-field interactive voice service to provide multiple voice interactive service subsystem
When, it is current for user when can provide the service subsystems such as weather lookup, song search than vehicular platform as stated above
Voice input, how to match reasonable service subsystem respond the voice of the user input, be a problem to be solved.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of interactive voice service processing method, device and equipment, more to close
Reason, more targetedly service subsystem for user provides interactive voice service.
In a first aspect, the embodiment of the present invention provides a kind of interactive voice service processing method, comprising:
In response to the interactive voice of user's triggering, according to the interactive voice matching between multiple service subsystems respectively
Degree determines candidate service subsystem collection corresponding with the interactive voice from the multiple service subsystem；
According to the user's characteristic information of the user, processing is modified to the candidate service subsystem collection；
If it includes a service subsystem that the revised candidate service subsystem, which is concentrated only, with one service
Interactive voice described in subsystem responses.
Second aspect, the embodiment of the present invention provide a kind of interactive voice service processing device, comprising:
Determining module, the interactive voice for being triggered in response to user, according to the interactive voice respectively with multiple services
Matching degree between subsystem determines candidate service subsystem corresponding with the interactive voice from the multiple service subsystem
Collection；
Correction module repairs the candidate service subsystem collection for the user's characteristic information according to the user
Positive processing；
Response processing module, if concentrating for the revised candidate service subsystem only includes a service subsystem
System then responds the interactive voice with one service subsystem.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, including processor and memory, and the memory is used
In storing one or more computer instruction, wherein real when one or more computer instruction is executed by the processor
Interactive voice service processing method in existing above-mentioned first aspect.The electronic equipment can also include communication interface, be used for and other
Equipment or communication.
The embodiment of the invention provides a kind of computer storage mediums, for storing storage computer program, the calculating
Machine program realizes interactive voice service processing method in above-mentioned first aspect when executing computer.
Interactive voice service processing method, device and equipment provided in an embodiment of the present invention, support multiple service subsystems
Interactive voice service system receive user triggering interactive voice after, can first according to the interactive voice respectively with it is more
Matching degree between a service subsystem determines candidate service subsystem collection from multiple service subsystems.In turn, in conjunction with user
User's characteristic information processing is modified to candidate service subsystem collection so that candidate service subsystem concentrate service son
System can be more in line with the use preference of user.Finally, if it only includes one that revised candidate service subsystem, which is concentrated,
Service subsystem, then directly with the interactive voice of service subsystem response user.By being modified to service subsystem collection
Processing, can obtain for users has specific aim, rational candidate service subsystem more to provide more preferably for user
Interactive voice service.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the flow chart of interactive voice service processing method embodiment one provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic diagram of execution scene when embodiment illustrated in fig. 1 executes；
Fig. 3 is another schematic diagram for executing scene when embodiment illustrated in fig. 1 executes；
Fig. 4 is the schematic diagram of another execution scene when embodiment illustrated in fig. 1 executes；
Fig. 5 is the flow chart of interactive voice service processing method embodiment two provided in an embodiment of the present invention；
Fig. 6 is the structural schematic diagram of interactive voice service processing device provided in an embodiment of the present invention；
Fig. 7 is that the structure of electronic equipment corresponding with the interactive voice service processing device that embodiment illustrated in fig. 6 provides is shown
It is intended to.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
The term used in embodiments of the present invention is only to be not intended to be limiting merely for for the purpose of describing particular embodiments
The present invention.In the embodiment of the present invention and the "an" of singular used in the attached claims, " described " and "the"
It is also intended to including most forms, unless the context clearly indicates other meaning, " a variety of " generally comprise at least two, but not
It excludes to include at least one situation.
It should be appreciated that term "and/or" used herein is only a kind of incidence relation for describing affiliated partner, indicate
There may be three kinds of relationships, for example, A and/or B, can indicate: individualism A, exist simultaneously A and B, individualism B these three
Situation.In addition, character "/" herein, typicallys represent the relationship that forward-backward correlation object is a kind of "or".
It will be appreciated that though XXX may be described in embodiments of the present invention using term first, second, third, etc., but
These XXX should not necessarily be limited by these terms.These terms are only used to distinguish XXX.For example, not departing from model of the embodiment of the present invention
In the case where enclosing, the first XXX can also be referred to as the 2nd XXX, and similarly, the 2nd XXX can also be referred to as the first XXX.
Depending on context, word as used in this " if ", " if " can be construed to " ... when " or
" when ... " or " in response to determination " or " in response to detection ".Similarly, context is depended on, phrase " if it is determined that " or " such as
Fruit detection (condition or event of statement) " can be construed to " when determining " or " in response to determination " or " when detection (statement
Condition or event) when " or " in response to detection (condition or event of statement) ".
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
Include, so that commodity or system including a series of elements not only include those elements, but also including not clear
The other element listed, or further include for this commodity or the intrinsic element of system.In the feelings not limited more
Under condition, the element that is limited by sentence "including a ...", it is not excluded that in the commodity or system for including the element also
There are other identical elements.
In addition, the step timing in following each method embodiments is only a kind of citing, rather than considered critical.
Fig. 1 is the flow chart of interactive voice service processing method embodiment one provided in an embodiment of the present invention, the present embodiment
The interactive voice service processing method provided can be executed by an interactive voice service processing device, the interactive voice service
Processing unit can be implemented as software, or be embodied as the combination of software and hardware.The interactive voice service processing device can be with
It is integrally disposed in the subscriber terminal equipment or server for supporting voice interactive system.As shown in Figure 1, this method includes as follows
Step:
101, in response to the interactive voice of user's triggering, according to the interactive voice matching between multiple service subsystems respectively
Degree determines candidate service subsystem collection corresponding with interactive voice from multiple service subsystems.
In certain occasions, such as when the both hands inconvenience of user carries out man-machine interactive operation, interactive voice mode is user
Biggish convenience is provided, therefore, more and more products for supporting interactive voice service are constantly presented.
In the embodiment of the present invention, it is assumed that certain application system or certain electronic equipment for providing interactive voice service can be user
Multi-field interactive voice service is provided, that is, supports multiple service subsystems, wherein can be understood as each service subsystem pair
A certain specific interactive voice service should be completed in a kind of service field, each service subsystem.For example, weather service subsystem
It is responsible for answering inquiry of the user about weather condition；Music service subsystem can provide for user plays song, inquiry singer
The service such as information；Carryout service subsystem can carry out voice for user and make a reservation；KFC service subsystem can for user into
Row KFC express delivery company makes a reservation；Ambient services subsystem can carry out the inquiry, etc. of peripheral information for user.
In practical application, the fuzzy voice of Mr. Yu user is inputted, there may be more than one service subsystem can satisfy
The demand of user.For example, user expresses the wish of " I wants to drink cola ", then he may be intended to whether inquiry following peripheral has convenience
Shop can buy cola so as to him, it is also possible to be intended to order a take out and cola is delivered to one's home, at this point, with the several of the example above
For service subsystem, the service subsystem that can satisfy user demand may include: carryout service subsystem, KFC service
Subsystem, ambient services subsystem.
Therefore, the interactive voice currently triggered in face of user, it is necessary first to which filtering out from multiple service subsystems can be with
It is sub for responding the candidate service subsystem collection of the interactive voice, such as including above-mentioned carryout service subsystem, KFC service
The candidate service subsystem collection of system, ambient services subsystem；In turn, by certain treatment process therefrom select eventually for
Respond a service subsystem of the interactive voice.
Specifically, when receive user triggering interactive voice after, can according to the interactive voice respectively with multiple services
Matching degree between subsystem determines candidate service subsystem collection corresponding with interactive voice from multiple service subsystems.
Candidate service subsystem collection is that the service subsystem to be met certain requirements by the matching degree between interactive voice is constituted
Set, generally, service subsystem wherein included all should be to meet user demand to match with the intention of user
Service subsystem, therefore, the acquisition process of above-mentioned candidate service subsystem is it can be appreciated that be the process of user's intention assessment.
Intention assessment understands the intention of user, user wants what does, for example, user say " today, how is weather " be intended that inquiry
Weather, then candidate service subsystem concentration should include weather service subsystem；What user said " I will listen song " is intended that music
It plays, then candidate service subsystem concentration should include music service subsystem.
The acquisition of the intention assessment of user above-mentioned candidate service subsystem collection in other words, it is alternatively possible to pass through following mistake
Cheng Shixian:
By interactive voice input preset service subsystem disaggregated model with obtain interactive voice respectively with multiple service subsystems
Similarity score between system, so that it is determined that constituting candidate service subsystem by the service subsystem that similarity score is greater than default score value
System collection.
Optionally, before obtaining above-mentioned similarity score, speech recognition technology can be first passed through and convert the interactive voice
For text, and then the text is input to above-mentioned disaggregated model.
Above-mentioned preset service subsystem disaggregated model, which can be, pre- to be first passed through a large amount of training samples and divides neural network
Class training obtains, which is such as convolutional neural networks, deep neural network etc..Wherein, training sample can lead to
It crosses and collects or construct the corresponding common alternate statement acquisition of each service subsystem.
In an alternative embodiment, interactive voice or the corresponding text of interactive voice are input to above-mentioned preset service
After system classification model, the output form of the disaggregated model may is that the interactive voice belongs to some service with great probability
Subsystem, for example carryout service subsystem is belonged to 80% probability, at this point, the probability is above-mentioned similarity score.It can be with
Certain default score value is set, to constitute candidate service subsystem by the service subsystem that similarity score is greater than default score value
Collection.
It is optional other than it can obtain candidate service subsystem collection corresponding with interactive voice by above-mentioned disaggregated model
Ground can also realize the acquisition of candidate service subsystem collection by following process:
The similarity score between interactive voice and the corresponding corpus sample of multiple service subsystems is calculated, thus really
The fixed service subsystem for being greater than default score value by similarity score constitutes candidate service subsystem collection.
The corresponding common alternate statement of any service subsystem can be collected or construct in advance, to obtained common interactive language
Sentence carries out de-redundancy processing, it is thus possible to simply directly using obtained common alternate statement as any service subsystem
Corpus sample.The corresponding corpus sample of one service subsystem may be one, it is also possible to a plurality of.To for any
For service subsystem, similarity score between interactive voice corpus sample corresponding with any service subsystem can be with
Peak or flat between each corpus sample corresponding with any service subsystem that be the interactive voice in similarity score
Mean value, the peak or average value are used to evaluate the matching degree between the interactive voice and any service subsystem, it is thus possible to
The service subsystem that corresponding peak or average value are greater than default score value is added to candidate service subsystem to concentrate.Wherein,
The calculating of above-mentioned similarity can be realized using the algorithm for calculating the semantic similarity between two sentences.
As an example it is assumed that it includes weather, music, periphery, Taobao, take-away, KFC six that voice interactive system, which has altogether,
A service subsystem, it is assumed that when the interactive voice of user's input is the content in such as following table, each service subsystem and user are inputted
Between similarity score it is as follows:
At this point, the service subsystem of user's input can be responded to carry out screening by presetting this threshold value of score value, to constitute
Corresponding candidate service subsystem collection.For example, default score value is set to 0.90, then score is greater than the service subsystem of the default score value
(overstriking italic indicates in table) can be added to user and input corresponding candidate service subsystem concentration.
Optionally, the acquisition of above-mentioned candidate service subsystem collection can also be realized by following process:
It determines in the corresponding description rule template of multiple service subsystems and is retouched with the presence or absence of corresponding with interactive voice
State rule template, and if it exists, then determine that candidate service subsystem collection is corresponding with interactive voice by existing in multiple service subsystems
Description rule template service subsystem constitute.
The corresponding description rule template of certain service subsystem reflects the corresponding common interactive voice of the service subsystem
Communicative habits, accordingly it is also possible to be known as the similar title methods such as expression form template.For example, carryout service subsystem is corresponding
Certain description rule template are as follows: I wants to eat * * *.To if the interactive voice of user's input meets me and wants to eat the expression of * * *
Form, then it is assumed that the interactive voice has hit carryout service subsystem, and carryout service subsystem is added to candidate service subsystem
In system.For example, if the interactive voice of user is today, I wants to eat Sichuan cuisine, I wants to eat steamed stuffed bun, etc. all thinking to have hit take-away clothes
Business subsystem.
It is worth noting that a service subsystem can be corresponding with multiple and different description rule templates, same description
Rule template is also possibly corresponding to different service subsystems.
102, according to the user's characteristic information of user, processing is modified to candidate service subsystem collection.
In the embodiment of the present invention, after initially obtaining above-mentioned candidate service subsystem collection, it is not meant as responding
The service subsystem of the interactive voice of user is necessarily from candidate service subsystem collection at this time, because, in a possible feelings
In shape, though it is multiple, such as 2,3 that current candidate service subsystem, which concentrates the service subsystem quantity for including, and this
The similarity score of a little service subsystems and interactive voice is higher than certain predetermined score value, and still, this is not meant to these services
Subsystem is all reasonable, i.e., is had targetedly to the user.Therefore, above-mentioned candidate service subsystem is initially being obtained
It, can be in order to guarantee to obtain more reasonable, the candidate service subsystem for responding interactive voice on the basis of collection
In conjunction with the user's characteristic information of user, processing is modified to the above-mentioned candidate service subsystem collection initially obtained.
The necessity of processing is modified to candidate service subsystem collection, in addition to the above-mentioned time initially obtained can be embodied in
It selects service subsystem to concentrate in the situation comprising multiple service subsystems, the candidate service initially obtained can also be embodied in
System integrate there is no as empty set in the situation of the matched service subsystem of interactive voice.Because working as candidate service subsystem
System is when integrate as empty set, if to user without any response therefore it, can be user's recommendation that it is bad to will lead to user experience at this time
Some service subsystem responds the interactive voice of user as revealing all the details, and the service subsystem as bottom-line plan is added to
The scheme that candidate service subsystem is concentrated and a kind of pair of candidate service subsystem collection is modified.
In order to distinguish conveniently, the candidate service subsystem collection obtained by step 101 is known as initial candidate service below
Subsystem collection.In the embodiment of the present invention, processing is modified to initial candidate service subsystem collection, can be presented as two layers
Face:
First, if initial candidate service subsystem concentrates the service subsystem quantity for including to be less than or equal to default value,
Then according to the user's characteristic information of user, processing is extended to initial candidate service subsystem collection, as shown in Figures 2 and 3.
Second, if initial candidate service subsystem concentrates the service subsystem quantity for including to be greater than default value, basis
The user's characteristic information of user is filtered processing to initial candidate service subsystem collection, as shown in Figure 4.
The purpose of above-mentioned two level are as follows: obtain the candidate service subsystem being made of more reasonable candidate service subsystem
System collection is directed to sexual intercourse to user to realize therefrom to obtain the service subsystem of the final interactive voice for responding user
Mutually response.
Above-mentioned default value can be set to reasonable numerical value, should not be too large, for example be set as 1, thus, work as initial candidate
Service subsystem integrate as empty set or wherein only comprising a service subsystem when, can be to the initial candidate service subsystem collection
It is extended processing；And when service subsystem quantity wherein included is greater than 1, for example when being 2,3, initial candidate can be taken
Business subsystem collection is filtered processing.
Assuming that above-mentioned default value is 1, introduced separately below according to user's characteristic information, to initial candidate service subsystem
Collection be extended, the optional implementation of filtration treatment:
Optionally, if it is empty set that initial candidate service subsystem centralized services subsystem quantity, which is 0, user is preparatory
Setting reveal all the details service subsystem or the highest service subsystem of user's frequency of use expands to initial candidate service subsystem
It concentrates.Wherein, user can preset service subsystem corresponding if there is the interactive voice that can not be matched to it is inputted
Which when system, responded using service subsystem as bottom-line plan；Alternatively, can also be right whithin a period of time according to user
The frequency of use for numerous service subsystems that user uses is supplied to determine which current service subsystem should be used to respond
The interactive voice of user.Such as, it is assumed that in nearest week age, user has been used A service subsystem 10 times, has used B service
Subsystem 7 times, then A service subsystem is selected to expand to initial candidate service subsystem collection, to complete to initial candidate service
The amendment of subsystem collection, as shown in Figure 2.
Optionally, if initial candidate service subsystem centralized services subsystem quantity is 1, son will be serviced with initial candidate
The service subsystem that the service subsystem that system is concentrated belongs in same grouping expands to initial candidate service subsystem concentration, or
The service subsystem concentrated with initial candidate service subsystem is belonged in same grouping and meets frequency of use requirement by person
Service subsystem expands to initial candidate service subsystem concentration.It can understand in conjunction with the situation being likely encountered in practice as follows
The extension purpose of which: for the service of calling a taxi, it is assumed that A service subsystem, B service are provided in the service subsystem provided at present
Subsystem and C service subsystem can provide the service of calling a taxi for user, can be by this in the service of initial configuration interactive voice
Three service subsystems for providing service of calling a taxi are divided into one group.Assuming that the interactive voice current for user, with foregoing description
The initial candidate service subsystem that obtains of certain mode concentrate only comprising A service subsystem, at this point, in order to provide the user with more
More optional spaces can extend the B service subsystem and C service subsystem that belong in same grouping with A service subsystem
It is concentrated to initial candidate service subsystem, as shown in Figure 3；Alternatively, further considering that user services son to B within a certain period of time
System and the frequency of use of C service subsystem determine the need for expanding to B service subsystem and C service subsystem initially
Service subsystem is concentrated.Such as, it is assumed that in nearest one month, user has been used B service subsystem 5 times, and C has been used to service subsystem
System 1 time, preset access times threshold value are 2 times, then are based on this, B service subsystem is expanded to initial service subsystem
It concentrates, thus, it includes A service subsystem and B service subsystem that revised service subsystem, which is concentrated,.
In the above two optional implementation being extended to initial candidate service subsystem collection, user's characteristic information packet
It includes: the pre-set service subsystem of revealing all the details of user, frequency of use of the user to numerous service subsystems.
To first when quantity relative to initial candidate service subsystem centralized services subsystem is less than or equal to default value
Beginning candidate service subsystem collection is extended correcting process, when the quantity of initial candidate service subsystem centralized services subsystem is big
When default value, correcting process can be filtered to initial candidate service subsystem collection, wherein may less be closed with filtering out
The service subsystem of reason.
It optionally, can be using such as if initial candidate service subsystem concentrates the service subsystem quantity for including to be greater than 1
The combination of any mode or various ways in lower three kinds is filtered processing to initial candidate service subsystem collection:
The service subsystem that initial candidate service subsystem concentration does not support user location is filtered out according to the position of user.Than
Such as, it includes KFC service subsystem that initial candidate service subsystem, which is concentrated, but current user position does not have KFC nearby
StoreFront then should therefrom filter out KFC service subsystem at this time.
The clothes that initial candidate service subsystem concentrates user not customized are filtered out according to the service subsystem customized information of user
Business subsystem.For example, user only has subscribed the A service subsystem of interactive voice service system offer, B service subsystem, if
It includes C service subsystem that initial candidate service subsystem, which is concentrated, then therefrom filters out C service subsystem.
History service subsystem collection corresponding with initial candidate service subsystem collection if it exists, then according to right in user's history
The selection operation of history service subsystem collection determines that user preference corresponding with initial candidate service subsystem collection services subsystem
System filters out initial candidate service subsystem and concentrates the service subsystem in addition to user preference service subsystem, wherein history service
Subsystem collection is the service subsystem collection identical with initial candidate service subsystem collection occurred in history.
For example, initial candidate service subsystem collection is made of A service subsystem and B service subsystem, then corresponding history
Service subsystem collection is also the set being made of A service subsystem and B service subsystem, and the history service subsystem collection is in history
On be likely to occur it is primary, it is also possible to occurred repeatedly, and user at each occurrence can be counted, which has therefrom been selected service
Subsystem is such as selected the preference selection when this kind occur and selecting situation for user of the highest service subsystem of number to obtain
Service subsystem, that is, user preference service subsystem, it is assumed that the number that A service subsystem is selected be higher than B service subsystem quilt
The number of selection, then A service subsystem is as user preference service subsystem, it is thus possible to filter out initial candidate service subsystem
The B service subsystem for concentration of uniting, as shown in Figure 4.
The above-mentioned historical time section that can be setting in history.It is above-mentioned only to be selected number highest inclined as user
The evaluation index of good service subsystem, but be not limited thereto, for example certain threshold value can be set, being more than by selection number should
Threshold value all can serve as user preference service subsystem.
Initial candidate service subsystem is filtered in modified treatment process above-mentioned, user's characteristic information includes:
User location, user are to the customized situation of service subsystem, user to the history housing choice behavior of service subsystem.
If it includes a service subsystem that 103, revised candidate service subsystem, which is concentrated only, with one service
Subsystem responses interactive voice.
If 104, revised candidate service subsystem concentration contains at least two service subsystem, exports and select to user
Select instruction, and in response to the selection operation that user triggers revised candidate service subsystem collection according to selection instruction, with
The service subsystem response interactive voice selected.
The candidate service subsystem collection initially obtained extend or filtered according to the user's characteristic information of user
After correcting process, revised candidate service subsystem concentration may only include a service subsystem, it is also possible to comprising more than
One service subsystem.When it includes a service subsystem that revised candidate service subsystem, which is concentrated only, directly with the clothes
Subsystem be engaged in respond interactive voice；When it includes a service subsystem that revised candidate service subsystem, which is concentrated incessantly,
To avoid multiple service subsystems from repeating to respond interactive voice, it can be exported to user and select to indicate such as to ask to user's output
Ask voice, thus, according to the selection operation that user triggers revised candidate service subsystem collection, the clothes selected with user
Business subsystem responses interactive voice.It is serviced for example, being concentrated when revised candidate service subsystem comprising A service subsystem and B
It when subsystem, inquires user: may I ask you and select A service subsystem or B service subsystem, if that user's reply is selection A
Service subsystem, then with the interactive voice of A service subsystem response user.
Above-mentioned selection prompt can be the form output of showing interface, be also possible to voice mode output.
The processing logic of service subsystem itself is followed the response process of interactive voice.For example, if interactive voice is
Inquire weather today how, then respond the interactive voice weather service subsystem can reply the weather of user's today, temperature,
The relevant informations such as air quality.For another example, it if interactive voice is that I wants to call a taxi, responds calling a taxi for the interactive voice and services son
System can reply the reply voice of user's " may I ask you now at which, need where ", as shown in Figure 3.
To sum up, supporting the interactive voice service system of multiple service subsystems in the interactive voice for receiving user's triggering
It afterwards, can be first according to the interactive voice matching degree between multiple service subsystems respectively, from multiple service subsystems really
Make candidate service subsystem collection.In turn, place is modified to candidate service subsystem collection in conjunction with the user's characteristic information of user
Reason obtains more preferably so that the service subsystem that candidate service subsystem is concentrated can be more in line with the use preference of user
Alternate item, thus, can guarantee that it obtains and more there is specific aim, rational service subsystem to come for it for users
The more preferably interactive voice service of offer.
Fig. 5 is the flow chart of interactive voice service processing method embodiment two provided in an embodiment of the present invention, such as Fig. 5 institute
Show, may include steps of:
201, in response to the interactive voice of user's triggering, the corresponding description rule template of multiple service subsystems is determined
In whether there is description rule template corresponding with interactive voice, and if it exists, then follow the steps 202, if it does not exist, then execute step
Rapid 203.
202, the service subsystem by there is description rule template corresponding with interactive voice in multiple service subsystems is determined
System constitutes candidate service subsystem collection.
203, by interactive voice input preset service subsystem disaggregated model with obtain interactive voice respectively with multiple services
Similarity score between subsystem, alternatively, calculating between interactive voice and the corresponding corpus sample of multiple service subsystems
Similarity score；Determine that the service subsystem for being greater than default score value by similarity score constitutes candidate service subsystem collection.
In the present embodiment, three kinds introduced in embodiment illustrated in fig. 1 are obtained with the side of initial candidate service subsystem collection
Formula provides a kind of combined operational version, i.e., carries out the acquisition of candidate service subsystem collection according to description rule template first,
If there is no the candidate service subsystem collection comprising at least one service subsystem at this time, i.e., multiple service subsystems are respectively
Description rule template corresponding with interactive voice is not present in corresponding description rule template, and then further according to preset service subsystem
System disaggregated model or the mode for calculating similarity carry out the acquisition of candidate service subsystem collection.This is because description rule template
There is directive property definitely compared to preset service subsystem disaggregated model or the mode for calculating similarity, in other words to
The accuracy of the intention assessment of family interactive voice is higher.
If 204, candidate service subsystem concentrates the service subsystem quantity for including to be less than or equal to default value, basis
The user's characteristic information of user is extended processing to candidate service subsystem collection.
If 205, candidate service subsystem concentrates the service subsystem quantity for including to be greater than default value, according to user's
User's characteristic information is filtered processing to candidate service subsystem collection.
If it includes a service subsystem that 206, current candidate service subsystem, which is concentrated only, with a service subsystem
Respond interactive voice.
If 207, current candidate service subsystem concentration contains at least two service subsystem, selection is exported to user and is referred to
Show；In response to user according to the selection operation of selection instruction triggering, interactive voice is responded with the service subsystem selected.
208, the corresponding relationship of record current candidate service subsystem collection and the service subsystem selected.
If containing at least two service subsystem by extension or filtered correction treated candidate service subsystem concentration,
After then therefrom selecting required service subsystem in user, the revised candidate service subsystem collection at this time can recorde down
With the corresponding relationship for the service subsystem selected, occur and the revised candidate service subsystem again for use in subsequent
It, can be based on the corresponding relationship to the subsequent initial candidate service subsystem when collecting identical initial candidate service subsystem collection
Collection be filtered processing, referring specifically in previous embodiment about to candidate service subsystem collection be filtered processing the third
The description of processing mode, at this point, the revised service subsystem collection will service son as history described in previous embodiment
One of system concentration.
The interactive voice service processing device of one or more embodiments of the invention described in detail below.This field skill
Art personnel are appreciated that commercially available hardware component can be used to be instructed by this programme for these interactive voice service processing devices
The step of configured to constitute.
Fig. 6 is the structural schematic diagram of interactive voice service processing device provided in an embodiment of the present invention, as shown in fig. 6, should
Device comprises determining that module 11, correction module 12, response processing module 13.
Determining module 11, the interactive voice for being triggered in response to user, according to the interactive voice respectively with multiple clothes
Matching degree between business subsystem, determines candidate service subsystem corresponding with the interactive voice from the multiple service subsystem
System collection.
Correction module 12 carries out the candidate service subsystem collection for the user's characteristic information according to the user
Correcting process.
Response processing module 13, if concentrating for the revised candidate service subsystem only includes a service subsystem
System then responds the interactive voice with one service subsystem.
Optionally, the response processing module 13 is also used to: if the revised candidate service subsystem concentration includes
At least two service subsystems then export selection instruction to the user；In response to the user according to selection instruction pair
The selection operation of the revised candidate service subsystem collection triggering, responds the interactive language with the service subsystem selected
Sound.
Optionally, described device further include: logging modle 14.
Logging modle 14 records the revised candidate service subsystem collection and selected service subsystem
Corresponding relationship.
Optionally, the correction module 12 is used for: if the candidate service subsystem concentrates the service subsystem number for including
Amount is less than or equal to default value, then according to the user's characteristic information of the user, carries out to the candidate service subsystem collection
Extension process.
Optionally, the correction module 12 is used for: if the service subsystem quantity is zero, the user being set in advance
It is fixed to reveal all the details service subsystem or the highest service subsystem of user's frequency of use expands to the candidate service subsystem
System is concentrated；
It, will be with the candidate clothes if the service subsystem quantity is less than or equal to the default value and greater than zero
The service subsystem that the service subsystem that business subsystem is concentrated belongs in same grouping expands to the candidate service subsystem collection
In, alternatively, the service subsystem concentrated with the candidate service subsystem is belonged in same grouping and meets frequency of use
It is required that service subsystem expand to the candidate service subsystem and concentrate, the default value is greater than or equal to 1.
Optionally, the correction module 12 is used for: if the candidate service subsystem concentrates the service subsystem number for including
Amount is greater than default value and is filtered place to the candidate service subsystem collection then according to the user's characteristic information of the user
Reason.
Optionally, the correction module 12 is used for: according to the position of the user, filtering out the candidate service subsystem collection
In do not support the service subsystem of the position.
Optionally, the correction module 12 is used for: according to the service subsystem customized information of the user, filtering out the time
The service subsystem for selecting user described in service subsystem collection not customized.
Optionally, the correction module 12 is used for: determining whether there is go through corresponding with the candidate service subsystem collection
History service subsystem collection, the history service subsystem collection be occurred in history it is identical as the candidate service subsystem collection
Service subsystem collection；If it exists, then according in the user's history to the selection operation of the history service subsystem collection, really
Fixed user preference service subsystem corresponding with the candidate service subsystem collection；The candidate service subsystem concentration is filtered out to remove
Service subsystem outside the user preference service subsystem.
Optionally, the determining module 11 is used for: by the interactive voice input preset service subsystem disaggregated model with
Obtain similarity score of the interactive voice respectively between the multiple service subsystem；Alternatively, calculating the interactive voice
With the similarity score between the corresponding corpus sample of the multiple service subsystem；It determines and is greater than in advance by similarity score
If the service subsystem of score value constitutes the candidate service subsystem collection.
Optionally, the determining module 11 is used for: determining the corresponding description rule mould of the multiple service subsystem
It whether there is description rule template corresponding with the interactive voice in plate；Description rule corresponding with the interactive voice if it exists
Then template, it is determined that the candidate service subsystem collection is corresponding with the interactive voice by existing in the multiple service subsystem
Description rule template service subsystem constitute；Description rule template corresponding with the interactive voice if it does not exist then will
The interactive voice input preset service subsystem disaggregated model is sub with the multiple service respectively to obtain the interactive voice
Similarity score between system；Alternatively, calculating the interactive voice and the corresponding corpus sample of the multiple service subsystem
Similarity score between this；Determine that the service subsystem for being greater than default score value by similarity score constitutes candidate service
System collection.
The method that Fig. 6 shown device can execute Fig. 1, embodiment illustrated in fig. 5, the part that the present embodiment is not described in detail,
It can refer to the related description to Fig. 1, embodiment illustrated in fig. 5.The implementation procedure and technical effect of the technical solution are referring to Fig. 1, Fig. 5
Description in illustrated embodiment, details are not described herein.
The foregoing describe the built-in function of interactive voice service processing device and structures, in a possible design, language
The structure of sound interactive service processing unit can realize that for an electronic equipment, which is such as terminal device, such as Fig. 7 institute
Show, which may include: processor 21 and memory 22.Wherein, the memory 22 supports voice to hand over for storing
Mutual service processing device executes the program of above-mentioned Fig. 1, the interactive voice service processing method provided in embodiment illustrated in fig. 5, institute
Processor 21 is stated to be configurable for executing the program stored in the memory 22.
Described program includes one or more computer instruction, wherein one or more computer instruction is described
Processor 21 can be realized following steps when executing:
In response to the interactive voice of user's triggering, according to the interactive voice matching between multiple service subsystems respectively
Degree determines candidate service subsystem collection corresponding with the interactive voice from the multiple service subsystem；
According to the user's characteristic information of the user, processing is modified to the candidate service subsystem collection；
If it includes a service subsystem that the revised candidate service subsystem, which is concentrated only, with one service
Interactive voice described in subsystem responses.
Optionally, the processor 21 is also used to execute all or part of step in earlier figures 1 and embodiment illustrated in fig. 3
Suddenly.
Wherein, it can also include communication interface 23 in the structure of the interactive voice service processing device, be handed over for voice
Mutual service processing device and other equipment or communication.
In addition, the embodiment of the invention provides a kind of computer storage medium, for store voice interactive service processing dress
Computer software instructions used are set, it includes for executing interactive voice service in embodiment of the method shown in above-mentioned Fig. 1 and Fig. 3
Program involved in processing method.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of required general hardware platform is added, naturally it is also possible to which reality is come in conjunction with by way of hardware and software
It is existing.Based on this understanding, substantially the part that contributes to existing technology can be to calculate in other words for above-mentioned technical proposal
The form of machine product embodies, and it wherein includes the meter of computer usable program code that the present invention, which can be used in one or more,
The computer journey implemented in calculation machine usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of sequence 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.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (15)
1. a kind of interactive voice service processing method characterized by comprising
In response to the interactive voice of user's triggering, according to the interactive voice matching degree between multiple service subsystems respectively,
Candidate service subsystem collection corresponding with the interactive voice is determined from the multiple service subsystem；
According to the user's characteristic information of the user, processing is modified to the candidate service subsystem collection；
If it includes a service subsystem that the revised candidate service subsystem, which is concentrated only, with one service subsystem
System responds the interactive voice.
2. the method according to claim 1, wherein the method also includes:
If the revised candidate service subsystem concentration contains at least two service subsystem, exports and select to the user
Select instruction；
It is grasped in response to the user according to selection of the selection instruction to the revised candidate service subsystem collection triggering
Make, the interactive voice is responded with the service subsystem selected.
3. according to the method described in claim 2, it is characterized in that, the method also includes:
Record the corresponding relationship of revised the candidate service subsystem collection and selected service subsystem.
4. the method according to claim 1, wherein the user's characteristic information according to the user, to institute
It states candidate service subsystem collection and is modified processing, comprising:
If the candidate service subsystem concentrates the service subsystem quantity for including to be less than or equal to default value, according to
The user's characteristic information of user is extended processing to the candidate service subsystem collection.
5. if according to the method described in claim 4, it is characterized in that, the candidate service subsystem concentrates the clothes for including
Subsystem quantity of being engaged in is less than or equal to default value, then according to the user's characteristic information of the user, to candidate service
System collection is extended processing, comprising:
If the service subsystem quantity is zero, by the user preset reveal all the details service subsystem or the user
The highest service subsystem of frequency of use expands to the candidate service subsystem and concentrates；
It, will be with candidate service if the service subsystem quantity is less than or equal to the default value and greater than zero
The service subsystem that the service subsystem that system is concentrated belongs in same grouping expands to the candidate service subsystem and concentrates, or
The service subsystem concentrated with the candidate service subsystem is belonged in same grouping and meets frequency of use requirement by person
Service subsystem expands to the candidate service subsystem and concentrates, and the default value is greater than or equal to 1.
6. the method according to claim 1, wherein the user's characteristic information according to the user, to institute
It states candidate service subsystem collection and is modified processing, comprising:
If the candidate service subsystem concentrates the service subsystem quantity for including to be greater than default value, according to the user's
User's characteristic information is filtered processing to the candidate service subsystem collection.
7. according to the method described in claim 6, it is characterized in that, the user's characteristic information according to the user, to institute
It states candidate service subsystem collection and is filtered processing, comprising:
According to the position of the user, filters out the candidate service subsystem and concentrate the service subsystem for not supporting the position.
8. according to the method described in claim 6, it is characterized in that, the user's characteristic information according to the user, to institute
It states candidate service subsystem collection and is filtered processing, comprising:
According to the service subsystem customized information of the user, it is not customized to filter out user described in the candidate service subsystem collection
Service subsystem.
9. according to the method described in claim 6, it is characterized in that, the user's characteristic information according to the user, to institute
It states candidate service subsystem collection and is filtered processing, comprising:
History service subsystem collection corresponding with the candidate service subsystem collection is determined whether there is, the history services subsystem
System collection is the service subsystem collection identical with the candidate service subsystem collection occurred in history；
If it exists, then according in the user's history to the selection operation of the history service subsystem collection, it is determining with the time
Select the corresponding user preference service subsystem of service subsystem collection；
It filters out the candidate service subsystem and concentrates the service subsystem in addition to the user preference service subsystem.
10. method according to any one of claim 1 to 9, which is characterized in that described to be distinguished according to the interactive voice
With the matching degree between multiple service subsystems, candidate corresponding with the interactive voice is determined from the multiple service subsystem
Service subsystem collection, comprising:
By the interactive voice input preset service subsystem disaggregated model with obtain the interactive voice respectively with it is the multiple
Similarity score between service subsystem；Alternatively, calculating the interactive voice and the multiple service subsystem is corresponding
Similarity score between corpus sample；
Determine that the service subsystem for being greater than default score value by similarity score constitutes the candidate service subsystem collection.
11. method according to any one of claim 1 to 9, which is characterized in that described to be distinguished according to the interactive voice
With the matching degree between multiple service subsystems, candidate corresponding with the interactive voice is determined from the multiple service subsystem
Service subsystem collection, comprising:
It determines in the corresponding description rule template of the multiple service subsystem with the presence or absence of corresponding with the interactive voice
Description rule template；
Description rule template corresponding with the interactive voice if it exists, it is determined that the candidate service subsystem collection is by described more
It is constituted in a service subsystem in the presence of the service subsystem of description rule template corresponding with the interactive voice.
12. according to the method for claim 11, which is characterized in that the method also includes:
The interactive voice is then inputted preset service subsystem by description rule template corresponding with the interactive voice if it does not exist
Disaggregated model unite to obtain similarity score of the interactive voice respectively between the multiple service subsystem；Alternatively, calculating
Similarity score between the interactive voice and the corresponding corpus sample of the multiple service subsystem；
Determine that the service subsystem for being greater than default score value by similarity score constitutes the candidate service subsystem collection.
13. a kind of interactive voice service processing device characterized by comprising
Determining module, the interactive voice for being triggered in response to user, according to the interactive voice respectively with multiple service subsystems
Matching degree between system determines candidate service subsystem collection corresponding with the interactive voice from the multiple service subsystem；
Correction module is modified place to the candidate service subsystem collection for the user's characteristic information according to the user
Reason；
Response processing module, if concentrating for the revised candidate service subsystem only includes a service subsystem,
The interactive voice is responded with one service subsystem.
14. a kind of electronic equipment, which is characterized in that including memory and processor；Wherein,
The memory is for storing one or more computer instruction, wherein one or more computer instruction is by institute
State the interactive voice service processing method realized as described in any one of claims 1 to 12 when processor executes.
15. a kind of computer readable storage medium for being stored with computer program, which is characterized in that the computer program makes to count
The interactive voice service processing method as described in any one of claims 1 to 12 is realized when calculation machine executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810134247.0A CN110136701B (en) | 2018-02-09 | 2018-02-09 | Voice interaction service processing method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810134247.0A CN110136701B (en) | 2018-02-09 | 2018-02-09 | Voice interaction service processing method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110136701A true CN110136701A (en) | 2019-08-16 |
| CN110136701B CN110136701B (en) | 2023-03-31 |
Family
ID=67567956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810134247.0A Active CN110136701B (en) | 2018-02-09 | 2018-02-09 | Voice interaction service processing method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110136701B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737577A (en) * | 2020-06-22 | 2020-10-02 | 平安医疗健康管理股份有限公司 | Data query method, device, equipment and medium based on service platform |
| CN115079882A (en) * | 2022-06-16 | 2022-09-20 | 广州国威文化科技有限公司 | Human-computer interaction processing method and system based on virtual reality |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060143007A1 (en) * | 2000-07-24 | 2006-06-29 | Koh V E | User interaction with voice information services |
| CN103645876A (en) * | 2013-12-06 | 2014-03-19 | 百度在线网络技术（北京）有限公司 | Voice inputting method and device |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN105224278A (en) * | 2015-08-21 | 2016-01-06 | 百度在线网络技术（北京）有限公司 | Interactive voice service processing method and device |
| CN106486120A (en) * | 2016-10-21 | 2017-03-08 | 上海智臻智能网络科技股份有限公司 | Interactive voice response method and answering system |
| CN107092609A (en) * | 2016-05-10 | 2017-08-25 | 口碑控股有限公司 | A kind of information-pushing method and device |
| CN107316643A (en) * | 2017-07-04 | 2017-11-03 | 科大讯飞股份有限公司 | Voice interactive method and device |
| US20170351532A1 (en) * | 2016-06-07 | 2017-12-07 | Google Inc. | Nondeterministic task initiation by a personal assistant module |
-
2018
- 2018-02-09 CN CN201810134247.0A patent/CN110136701B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060143007A1 (en) * | 2000-07-24 | 2006-06-29 | Koh V E | User interaction with voice information services |
| CN103645876A (en) * | 2013-12-06 | 2014-03-19 | 百度在线网络技术（北京）有限公司 | Voice inputting method and device |
| CN105224278A (en) * | 2015-08-21 | 2016-01-06 | 百度在线网络技术（北京）有限公司 | Interactive voice service processing method and device |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN107092609A (en) * | 2016-05-10 | 2017-08-25 | 口碑控股有限公司 | A kind of information-pushing method and device |
| US20170351532A1 (en) * | 2016-06-07 | 2017-12-07 | Google Inc. | Nondeterministic task initiation by a personal assistant module |
| CN106486120A (en) * | 2016-10-21 | 2017-03-08 | 上海智臻智能网络科技股份有限公司 | Interactive voice response method and answering system |
| CN107316643A (en) * | 2017-07-04 | 2017-11-03 | 科大讯飞股份有限公司 | Voice interactive method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737577A (en) * | 2020-06-22 | 2020-10-02 | 平安医疗健康管理股份有限公司 | Data query method, device, equipment and medium based on service platform |
| CN115079882A (en) * | 2022-06-16 | 2022-09-20 | 广州国威文化科技有限公司 | Human-computer interaction processing method and system based on virtual reality |
| CN115079882B (en) * | 2022-06-16 | 2024-04-05 | 广州国威文化科技有限公司 | Human-computer interaction processing method and system based on virtual reality |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110136701B (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110532479A (en) | A kind of information recommendation method, device and equipment | |
| CN107835231B (en) | Feedback information processing method and terminal equipment | |
| WO2019037202A1 (en) | Method and apparatus for recognising target customer, electronic device and medium | |
| CN110060090A (en) | Method, apparatus, electronic equipment and the readable storage medium storing program for executing of Recommendations combination | |
| CN110196904B (en) | Method and device for acquiring recommendation information and computer readable storage medium | |
| CN109492180A (en) | Resource recommendation method, device, computer equipment and computer readable storage medium | |
| CN109829108B (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
| CN108230085A (en) | A kind of commodity evaluation system and method based on user comment | |
| CN109241451B (en) | Content combination recommendation method and device and readable storage medium | |
| CN105095179B (en) | The method and device that user's evaluation is handled | |
| CN104102819B (en) | A kind of determination method and apparatus of user's natural quality | |
| CN108038730A (en) | Product similarity determination methods, device and server cluster | |
| CN103778225B (en) | Processing method, identification device and the system of advertisement marketing speech like sound information | |
| CN108230007A (en) | A kind of recognition methods of user view, device, electronic equipment and storage medium | |
| CN110197404B (en) | Personalized long-tail commodity recommendation method and system capable of reducing popularity deviation | |
| CN107247728B (en) | Text processing method and device and computer storage medium | |
| CN106708871A (en) | Method and device for identifying social service characteristics user | |
| CN107092609A (en) | A kind of information-pushing method and device | |
| CN110111167A (en) | A kind of method and apparatus of determining recommended | |
| CN110599307A (en) | Commodity recommendation method and device | |
| CN104933204A (en) | Intelligent network response method and device | |
| TW201642195A (en) | System and method for automatically summarizing images and comments within commodity-related WEB articles | |
| CN110136701A (en) | Interactive voice service processing method, device and equipment | |
| CN108694171B (en) | Information pushing method and device | |
| CN116843376A (en) | Marketing effect prejudging method, marketing effect prejudging device, storage medium and marketing effect prejudging equipment |
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 |