CN109616108A - More wheel dialogue interaction processing methods, device, electronic equipment and storage medium - Google Patents
More wheel dialogue interaction processing methods, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109616108A CN109616108A CN201811446940.8A CN201811446940A CN109616108A CN 109616108 A CN109616108 A CN 109616108A CN 201811446940 A CN201811446940 A CN 201811446940A CN 109616108 A CN109616108 A CN 109616108A
- Authority
- CN
- China
- Prior art keywords
- dialogue
- knowledge
- module
- interaction
- knowledge mapping
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0631—Creating reference templates; Clustering
- G10L2015/0633—Creating reference templates; Clustering using lexical or orthographic knowledge sources
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0635—Training updating or merging of old and new templates; Mean values; Weighting
-
- 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
- G10L2015/225—Feedback of the input speech
Abstract
The embodiment of the invention discloses one kind to take turns dialogue interaction processing method, device, electronic equipment and storage medium more.This method comprises: obtaining the target interworking entity determined by current session round when terminating current session round；According to the renewal of knowledge corresponding with target interworking entity interaction knowledge mapping；Wherein, interaction knowledge mapping with by take turns more talk in terminated the corresponding knowledge connection of at least one interworking entity that dialog turns determine；According to the dictionary and/or model that at least one processing module uses in updated interactive knowledge mapping adjustment dialogue interactive system；When receiving dialog information corresponding with Next dialog round, response corresponding with dialog information is made using dialogue interactive system adjusted.It can enable to talk with through the above technical solution between each module of interactive system and the context of dialogue shares identical semantics information and knowledge each other, and then can permit conversation tasks and arbitrarily convert, reach seamless and integrate with.
Description
Technical field
The present embodiments relate to the information processing technology, taken turns more particularly to one kind more dialogue interaction processing method, device,
Electronic equipment and storage medium.
Background technique
Human-computer dialogue, is a sub- direction of artificial intelligence field, and popular saying is exactly to allow people can be by the language of the mankind
Speech (i.e. natural language) is interacted with computer.
Dialogue interactive system from user session input reply output to the end, it usually needs process a series of processing modules into
Row processing, including speech recognition-intent classifier-semanteme slot sequence labelling-dialogue management-candidate answer acquisition-language generation, it is whole
Link is very long and complicated.
In the specific implementation process, that there may be information is inconsistent for information transmitting in discovery dialogue interactive system by inventor
Situation especially is more likely to will appear, bad experience thus can be brought to user in more wheel dialogues.It is ideal right with one
Words interaction carries out example:
I want to listen song -> (system dials song of singing) of Zheng Jun -> his lover whom is -> (the correlation of system answer singer Zheng Jun
Knowledge problem) -> have drilled TV play -> (the relevant knowledge problem of system answer Zheng Jun/Liu Yun) -> to return to Lhasa-
> (system dial put Zheng Jun return to Lhasa)
Above-mentioned dialogue interaction is perfect condition, and practical situation may be really not so.For example, for the second wheel of user
Talk with " whom his lover is ", although dialogue management module can determine that " he " refers to " Zheng Jun " by reference resolution, such as
Fruit only removes inquiry knowledge mapping according to entity " Zheng Jun ", it is found that there are singer " Zheng Jun " and physicists in knowledge mapping
" Zheng Jun ", and then talk with that interactive system is different surely chooses correct entity " Zheng Jun " and make answer.For another example for using
The fourth round at family is talked with, and dialogue interactive system is also possible to that the intent classifier of " returning to Lhasa " navigation task can be mistakenly considered.
Summary of the invention
In view of this, taking turns dialogue interaction processing method, device, electronic equipment the embodiment of the invention provides one kind more and depositing
Storage media, with solve the problems, such as dialogue interactive system in information transmitting lose or it is inconsistent.
To solve the above-mentioned problems, the embodiment of the present invention mainly provides the following technical solutions:
In a first aspect, the embodiment of the invention provides one kind to take turns dialogue interaction processing method more, this method comprises:
When terminating current session round, the target interworking entity determined by the current session round is obtained；
According to the renewal of knowledge corresponding with target interworking entity interaction knowledge mapping；Wherein, the interactive knowledge graph
Spectrum with by take turns more talk in terminated the corresponding knowledge connection of at least one interworking entity that dialog turns determine；
It is used according at least one processing module in the updated interactive knowledge mapping adjustment dialogue interactive system
Dictionary and/or model；
When receiving dialog information corresponding with Next dialog round, done using the dialogue interactive system adjusted
Response corresponding with the dialog information out.
Second aspect, the embodiment of the present invention also provide one kind and take turns dialogue interaction process device more, which includes:
Interworking entity obtains module, for when terminating current session round, acquisition to be determined by the current session round
Target interworking entity；
Interaction knowledge mapping update module, for according to the renewal of knowledge corresponding with target interworking entity interaction knowledge
Map；Wherein, the interactive knowledge mapping interacts in fact at least one that dialog turns determine that terminated by more taking turns in dialogue
The corresponding knowledge connection of body；
Talk with interactive system and adjust module, for according to the updated interactive knowledge mapping adjustment dialogue interactive system
In at least one processing module dictionary and/or model that use；
Talk with interactive system processing module, for using when receiving dialog information corresponding with Next dialog round
The dialogue interactive system adjusted makes response corresponding with the dialog information.
The third aspect, the embodiment of the present invention also provide a kind of electronic equipment, comprising: at least one processor；And with institute
State at least one processor, the bus of processor connection；Wherein, the processor, memory are completed mutual by the bus
Between communication；The processor is used to call the program instruction in the memory, to execute described in any embodiment of that present invention
More wheels talk with interaction processing method.
Fourth aspect, the embodiment of the present invention also provide a kind of non-transient computer readable storage medium, the non-transient meter
Calculation machine readable storage medium storing program for executing stores computer instruction, and the computer instruction makes the computer execute any embodiment of that present invention
More wheels talk with interaction processing method.
By above-mentioned technical proposal, technical solution provided in an embodiment of the present invention is at least had the advantage that
The embodiment of the present invention obtains the target interaction determined by current session round when terminating current session round every time
Entity, according to the renewal of knowledge corresponding with target interworking entity interaction knowledge mapping, and then according to updated interactive knowledge graph
The dictionary and/or model that at least one processing module uses in spectrum adjustment dialogue interactive system, thus, it is possible to receiving under
When the corresponding dialog information of one dialog turns, corresponding answer is made using dialogue interactive system adjusted.Pass through above-mentioned skill
Art scheme can enable to talk between each module of interactive system and the context of dialogue is shared identical semantics information each other and known
Know, and then can permit conversation tasks and arbitrarily convert, reach seamless and integrate with, avoids semantics information in dialogue each mould of interactive system
Transmitting generates mistake between block, in turn results in cross-module semantics information loss or inconsistent problem.
Above description is only the general introduction of technical solution of the embodiment of the present invention, in order to better understand the embodiment of the present invention
Technological means, and can be implemented in accordance with the contents of the specification, and in order to allow above and other mesh of the embodiment of the present invention
, feature and advantage can be more clearly understood, the special specific embodiment for lifting the embodiment of the present invention below.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
The limitation of embodiment.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows the flow chart of the more wheel dialogue interaction processing methods of one kind of the offer of the embodiment of the present invention one；
Fig. 2 shows a kind of flow charts of more wheel dialogue interaction processing methods provided by Embodiment 2 of the present invention；
Fig. 3 shows the flow chart of the more wheel dialogue interaction processing methods of one kind of the offer of the embodiment of the present invention three；
Fig. 4 shows the structural schematic diagram of the more wheel dialogue interaction process devices of one kind of the offer of the embodiment of the present invention four；
Fig. 5 shows the structural schematic diagram of a kind of electronic equipment of the offer of the embodiment of the present invention five.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
Embodiment one
Fig. 1 is the flow charts for the more wheel dialogue interaction processing methods of one kind that the embodiment of the present invention one provides, and is applicable to pair
Semantics information transmits inconsistent situation when the more wheels of words interactive system processing are talked with, and this method can be provided by the embodiment of the present invention
More wheels dialogue interaction process device execute, the mode which can be used software and/or hardware is realized, and can generally integrate
In the processor.As shown in Figure 1, the method for the embodiment of the present invention specifically includes:
S110, when terminating current session round, obtain the target interworking entity that is determined by current session round.
The case where talking with for human-computer interaction dialogue for more wheels keeps one to make to take turns the semantics information between dialogue more
It causes, so the content that can talk with to user's each round is analyzed, and using the interaction content of current session round as to user
The dialog information of Next dialog round, the basis that the dialog information of even subsequent multiple dialog turns is analyzed.
So can be in each round end-of-dialogue, namely when terminating current session round, that is, dialogue interaction system
System, when corresponding response is made in wheel dialogue, determines the target interworking entity in the dialogue of this wheel for active user.Wherein,
Target interworking entity is specifically to determine that entity can be such as name, place name, mechanism by the conversation content of current session round
The information of name, number, date or the like.
For example, the dialog information of user is " I wants to listen the song of Zheng Jun " in current session round, then can be according to " Zheng
An ancient unit of weight " and " song " determine that the target interworking entity in current session round is " Zheng Jun " or " singer Zheng Jun ".
S120, the basis renewal of knowledge corresponding with target interworking entity interaction knowledge mapping；Wherein, interaction knowledge mapping with
By taking turns the corresponding knowledge connection of at least one interworking entity for having terminated dialog turns and having determined in dialogue more.
Associated interaction knowledge mapping is knowledge corresponding with interworking entity, it is specific it is associated be with by taking turns in dialogue more
The corresponding knowledge of interworking entity that the dialog turns being over determine, in turn, at the end of current session round, according to by working as
The target interworking entity that preceding dialog turns determine is updated to interaction knowledge mapping namely updated interactive knowledge mapping can
To be associated with knowledge corresponding with target interworking entity.
By taking following dialogues interaction as an example, " I wants to listen song -> (system dials song of singing) -> whom his lover is -> of Zheng Jun (be
System answers the relevant knowledge problem of singer Zheng Jun) ", after the first dialog turns, interaction knowledge mapping is associated to be and " song
The corresponding knowledge of hand Zheng Jun ", after the second wheel dialog turns, interaction knowledge mapping is updated, and updated interaction is known
It is knowledge corresponding with " singer Zheng Jun " and " lover of singer Zheng Jun " that it is associated, which to know map,.
It is worth noting that interaction knowledge mapping is that dynamic updates, interaction knowledge mapping can before mostly wheel beginning of conversation
Not to be associated with any knowledge, with the increase of conversation content, dynamic updates.Specifically, interaction knowledge mapping can be and take turns more
Be emptied, be also possible to after current session round after end-of-dialogue, be more than setting duration after do not receive with it is next
In the case where the corresponding dialog information of dialog turns, interaction knowledge mapping is carried out emptying processing.
S130, talk with what at least one processing module in interactive system used according to updated interactive knowledge mapping adjustment
Dictionary and/or model.
Modules usually require to define dictionary in dialogue interactive system, and derive model based on dictionary to complete spy
Determine task, such as speech recognition module carries out voice knowledge to the voice that user inputs based on speech recognition modeling and language model
Not, then such as intent classifier module speech recognition module is exported based on general field dictionary and tasks in areas dictionary text into
Row intent classifier, etc..
According to the dictionary and/or model that processing module uses in updated interactive knowledge mapping adjustment dialogue interactive system
After progress, each processing module talked in interactive system can share identical semantics information and knowledge.
For example, obtaining related expansion vocabulary and language mould according to updated interactive knowledge mapping in speech recognition module
Type statistical information is merged with basic dictionary and general language model.
For another example obtaining phase according to updated interactive knowledge mapping in modules such as intent classifier/semanteme slot sequence labellings
It closes and expands entity, dynamic importing field correlation dictionary, for making Chinese word separating/statistical model feature extraction/feature weight modification,
To improve intent classifier and semantic slot recognition sequence rate.
S140, when receiving dialog information corresponding with Next dialog round, use dialogue interactive system adjusted
Make response corresponding with dialog information.
When receiving dialog information corresponding with Next dialog round, at dialogue interactive system adjusted
Reason can share identical semantics information and knowledge between more wheel dialogues, and then provide corresponding with dialog information, meet user
The response of original idea.
By taking following dialogues interaction as an example, " 1. I want to listen his lover of song -> (system dials song of singing) of Zheng Jun -> 2. whom is-
> (the relevant knowledge problem of system answer singer Zheng Jun) -> 3. have drilled TV play -> (the correlation of system answer Zheng Jun/Liu Yun
Knowledge problem) -> 4. to return to Lhasa -> (system dial put Zheng Jun return to Lhasa) ", in 4. dialog turns, due to
Associated in interaction knowledge mapping is with " singer Zheng Jun " with corresponding knowledge such as " lovers of singer Zheng Jun ", and then adjusted
Conversational system, can be " returning to Lhasa " preferentially as " singer Zheng Jun when to the 4. user session information processing of dialog turns
The song of performance " is handled, and without handling " Lhasa " as place name, and then " returning to Lhasa " will not be mistakenly classified as leading
Boat task.
A kind of more wheel dialogue interaction processing methods provided in an embodiment of the present invention, when terminating current session round every time,
The target interworking entity determined by current session round is obtained, according to the renewal of knowledge corresponding with target interworking entity interaction knowledge
Map, and then according to the dictionary that at least one processing module uses in updated interactive knowledge mapping adjustment dialogue interactive system
And/or model, make that identical semantics information and knowledge can be shared between each processing module, and then receiving and lower a pair
When talking about the corresponding dialog information of round, corresponding answer is made using dialogue interactive system adjusted, dialogue can be made upper and lower
Identical semantics information and knowledge can be shared between text each other, allows conversation tasks arbitrarily to convert, reaches seamless and integrate with, avoid
Semantics information transmitting between dialogue each module of interactive system generates mistake, in turn results in cross-module semantics information loss or different
The problem of cause.
Embodiment two
Fig. 2 is a kind of flow chart of more wheel dialogue interaction processing methods provided by Embodiment 2 of the present invention.In above-mentioned technology
On the basis of scheme, the embodiment of the present invention will be according to the renewal of knowledge corresponding with target interworking entity interaction knowledge mapping, specifically
Are as follows:
World knowledge map is inquired according to target interworking entity, obtains knowledge corresponding with target interworking entity；According to
Target interworking entity corresponding renewal of knowledge interaction knowledge mapping.
As shown in Fig. 2, method provided in an embodiment of the present invention specifically includes:
S210, when terminating current session round, obtain the target interworking entity that is determined by current session round.
S220, world knowledge map is inquired according to target interworking entity, obtains knowledge corresponding with target interworking entity.
After determining target interworking entity according to current session round, inquiry interacts real with target in world knowledge map
The relevant knowledge of body, and then the dictionary and/or model that these knowledge are used as processing module in adjustment dialogue interactive system
Reference frame.
S230, according to the renewal of knowledge corresponding with target interworking entity interaction knowledge mapping, wherein interaction knowledge mapping with
By taking turns the corresponding knowledge connection of at least one interworking entity for having terminated dialog turns and having determined in dialogue more.
The knowledge connection relevant to target interworking entity that will acquire to interaction knowledge mapping, and then will interaction knowledge mapping
Reference frame as dictionary and/or model that processing module in adjustment dialogue interactive system uses.
Specifically, the association of interaction knowledge mapping is handed over at least one that dialog turns determine that terminated by more taking turns in dialogue
The mode of the mutual corresponding knowledge of entity can be interactive knowledge mapping include with by take turns more talk in have terminated dialog turns true
The fixed corresponding knowledge of at least one interworking entity, that is, building one interactive knowledge mapping, and by with by take turns more talk in
Terminate the corresponding knowledge of at least one interworking entity that dialog turns determine to be added in interactive knowledge mapping, and then can root
The dictionary and/or model used according at least one processing module in the knowledge adjustment dialogue interactive system in interaction knowledge mapping.
It is also possible that interaction knowledge mapping includes being directed toward to determine at least with by taking turns the dialog turns that terminated in dialogue more
The link of the corresponding knowledge of one interworking entity that is, being in interaction knowledge mapping does not include directly knowledge, but passes through friendship
Link in mutual knowledge mapping is available to be interacted more to by taking turns at least one that dialog turns determine that terminated in dialogue
The corresponding knowledge of entity, and then corresponding knowledge can be got according to the link in interaction knowledge mapping, and then adjust dialogue
The dictionary and/or model that at least one processing module uses in interactive system.
S240, talk with what at least one processing module in interactive system used according to updated interactive knowledge mapping adjustment
Dictionary and/or model.
For example, the target interworking entity determined is " singer Zheng Jun ", and then " sung all in world knowledge map with entity
Which the corresponding knowledge connection of hand Zheng Jun " to interaction knowledge mapping, such as the singer Zheng Jun song sung have, whom lover is, recently
What activity, etc. participated in.
It in turn, can be according to the dictionary that at least one processing module uses in interaction knowledge mapping adjustment dialogue interactive system
And/or model, wherein the processing module in dialogue interactive system includes: speech recognition module, semantic understanding module, dialogue pipe
Module and language generation module are managed, semantic understanding module can also specifically be divided into intent classifier submodule and semantic slot sequence mark
Infuse submodule.
Each processing module respectively corresponds respective dictionary and/or model in dialogue interactive system, to complete respective spy
Task is determined, for example, speech recognition module completes voice recognition tasks based on speech recognition dictionary and speech model, it is intended that classification
Submodule completes intent classifier task, semantic slot sequence labelling submodule base based on general field dictionary and tasks in areas dictionary
Complete semantic slot in task semantic slot dictionary and name entity dictionary and mark task, dialogue management module be based on semantic slot transfer after
It holds dictionary, task semantic slot dictionary and name entity dictionary and determines that computer is directed to the response operation of user session information, language
Say that generation module is based on language generation dictionary and tasks in areas dictionary generates question response corresponding with user session information.
The pronunciation of all words is stored by taking speech recognition module as an example, in speech recognition dictionary, effect is to connect acoustics
Model and language model, identifying that the phoneme in user session information, logical speech recognition dictionary can find word,
And the core of language model is exactly to predict the probability an of sentence or the appearance of one group of word sequence, and then generate and believe with user session
Cease corresponding text information.
Further, made according at least one processing module in updated interactive knowledge mapping adjustment dialogue interactive system
Dictionary and/or model, including one at least following:
According to the related dictionary and language model weight in updated interactive knowledge mapping adjustment speech recognition module；
According to the related dictionary and intent classifier model in updated interactive knowledge mapping adjustment semantic understanding module
Weight；And
It is related in the language very generation module according to updated interactive knowledge mapping adjustment dialogue management module
Dictionary.
For example, acquiring knowledge triple " Zheng in world knowledge map according to target interworking entity " singer Zheng Jun "
An ancient unit of weight-lover-Liu Yun ", and then updated interactive knowledge mapping can be associated with to the knowledge triple, according to interaction knowledge mapping
Adjust the speech recognition dictionary and language model weight in speech recognition module.If not including in speech recognition dictionary
" liuyun- Liu Yun ", then be added in speech recognition dictionary, while adjusting language model, make it to list by " liuyun- Liu Yun "
The prediction probability of word " Liu Yun " increases.
For another example can be with association knowledge triple according to the interaction knowledge mapping that target interworking entity " singer Wang Fei " updates
" Wang Fei-song-red bean ", according to the general field dictionary and tasks in areas in interaction knowledge mapping adjustment intent classifier submodule
Dictionary improves intent classifier submodule by the weight that " red bean " is identified as song field word, " red bean " is identified as food
The weight of field word reduces.
S250, when receiving dialog information corresponding with Next dialog round, use dialogue interactive system adjusted
Make response corresponding with dialog information.
When receiving dialog information corresponding with Next dialog round, at dialogue interactive system adjusted
Reason can share identical semantics information and knowledge between more wheel dialogues, and then provide corresponding with dialog information, meet user
The response of original idea.
Such as dialogue interaction is " 1. I wants to listen song -> (system dials song of singing) -> 2. red bean -> (system response) of Wang Fei "
When, when being responded using 2. user session information " red bean " that dialogue interactive system adjusted interacts round for the, meeting
Song red bean is played, rather than some knowledge in relation to food red bean are provided.
It is worth noting that interaction knowledge mapping is associated with and interworking entity " song due at the end of 1. interactive round
The corresponding knowledge of hand Wang Fei ", though when n-th interaction round when user change the topic of conversation, it is unrelated with interworking entity " singer Wang Fei ",
Later, when user proposes such as " red bean " etc with interworking entity " singer Wang Fei " corresponding dialogue in the n-th+m interaction round,
Dialogue interactive system adjusted can still provide correct response.
In the above-mentioned technical solutions, identical semantics information and knowledge can be shared between the context of dialogue each other, is allowed pair
Words task is arbitrarily converted, and is reached seamless and is integrated with, and is avoided semantics information transmitting between dialogue each module of interactive system and is generated mistake
Accidentally, cross-module semantics information loss or inconsistent problem are in turn resulted in.
Embodiment three
Fig. 3 is the flow chart for more than the one wheel dialogue interaction processing methods that the embodiment of the present invention three provides.In above-mentioned technical side
On the basis of case, the embodiment of the present invention will use dialogue interactive system adjusted to make answer corresponding with the dialog information
It answers, specifically:
Related dictionary and voice mould adjusted are based on using the speech recognition module in dialogue interactive system adjusted
Type carries out speech recognition to dialog information；
Related dictionary adjusted and intention point are based on using the semantic understanding module in dialogue interactive system adjusted
Class model carries out semantic analysis to the recognition result that speech recognition exports；
Related dictionary adjusted and interaction are based on using the dialogue management module in dialogue interactive system adjusted
Knowledge mapping carries out reference resolution to the analysis result that semantic understanding module exports, semantic slot position is inherited and task parameters parsing behaviour
Make, generates candidate answer corresponding with dialog information, and then make final response corresponding with dialog information；
Using the language generation module in dialogue interactive system adjusted based on related dictionary generation adjusted and most
The corresponding natural language text of whole response.
As shown in figure 3, method provided in an embodiment of the present invention specifically includes:
S310, when terminating current session round, obtain the target interworking entity that is determined by current session round.
S320, world knowledge map is inquired according to target interworking entity, obtains knowledge corresponding with target interworking entity.
S330, according to the renewal of knowledge corresponding with target interworking entity interaction knowledge mapping, wherein interaction knowledge mapping with
By taking turns the corresponding knowledge connection of at least one interworking entity for having terminated dialog turns and having determined in dialogue more.
S340, talk with what at least one processing module in interactive system used according to updated interactive knowledge mapping adjustment
Dictionary and/or model.
Explanation about S310-S340 please be detailed in previous embodiment, and details are not described herein.
S350, when receiving dialog information corresponding with Next dialog round, use dialogue interactive system adjusted
In speech recognition module be based on related dictionary and speech model adjusted speech recognition carried out to dialog information.
Speech recognition module is by acoustic model and language model, is text by the speech recognition of user, according to more
After interaction knowledge mapping pair dictionary corresponding with speech recognition module and language model after new are adjusted, speech recognition module
Meet the original idea of user in the dialog information Shi Huigeng of identification Next dialog round, substantially increases the accuracy rate of speech recognition.
S360, related dictionary adjusted and meaning are based on using the semantic understanding module in dialogue interactive system adjusted
Figure disaggregated model carries out semantic analysis to the recognition result that speech recognition exports.
Intent classifier submodule is completed intent classifier based on general field dictionary adjusted and tasks in areas dictionary and appointed
Business, and then semantic slot sequence labelling submodule task based access control semanteme slot dictionary and name entity dictionary, according to intent classifier result
Complete semantic slot sequence labelling task.Wherein, name entity dictionary in store be for example name, place name, mechanism name, number,
The entities such as date.
In turn, it can be deduced that the semantic analysis result of semantic understanding module, for example, from " Beijing weather tomorrow is how
In sample " the words, the available following semantic results of semantic understanding module:
Field (Domain): weather
It is intended to (Intent): inquiry weather
Word slot (Slot): city (city)=Beijing
Time (date)=tomorrow
When the interaction associated knowledge of knowledge mapping is mostly music class knowledge namely user takes turns involved in dialogue more
When topic is mostly music, if user has said in one " Chengdu ", " Chengdu " can be then classified as song class by semantic understanding module, and
It is not " Chengdu " to be returned to location category, and then be intended to be determined as playing song.
S370, be based on using the dialogue management module in dialogue interactive system adjusted related dictionary adjusted and
Interaction knowledge mapping carries out reference resolution to the analysis result that semantic understanding module exports, semantic slot position is inherited and across task parameters
Parsing operation, generates candidate answer corresponding with dialog information, and then make final response corresponding with dialog information.
Wherein, the conversation type of candidate answer may include Task, chat type and question and answer type.
By taking following dialogues interaction as an example, " 1. I want to listen his lover of song -> (system dials song of singing) of Zheng Jun -> 2. whom is-
> (the relevant knowledge problem of system answer singer Zheng Jun) -> 3. have drilled TV play -> (the correlation of system answer Zheng Jun/Liu Yun
Knowledge problem) -> 4. to return to Lhasa -> (system dial put Zheng Jun return to Lhasa) ", for the dialogue of the 2. dialog turns
" whom his lover is ", dialogue management module can not only pass through reference resolution and determine " he " in dialogue interactive system adjusted
It refers to " Zheng Jun ", but also can determine that " Zheng Jun " is referred to " singer Zheng Jun " by interaction knowledge mapping, rather than " physics
Scholar Zheng Jun " thus, it is possible to be based on " singer Zheng Jun " in world knowledge map to go inquiry answer, and then is generated and is correctly answered
It answers.
Reference resolution, semantic slot position inherit and task parameters parsing be all it is highly relevant with particular task scene, for example, leading
Purposefully (to) related entities are needed in boat task, and looks into hotel and needs place (location) entity, although the two are appointed
The semantic slot name of business claims (to/location) different, but dialogue management module passes through the interaction associated knowledge of knowledge mapping, can be with
Know that this two semantic slots referred to is all the entity of geography information, is thus easier processing ambiguity problem.
For example, when " 1. I wants to listen song -> (system dials song of singing) -> 2. red bean -> (system response) of Wang Fei ", the
2. there are ambiguities for the user session information " red bean " of interactive round, and then when dialogue management module is responded for " red bean ",
It can be come according to associated knowledge, the candidate answer that will be generated according to " song red bean " in interaction knowledge mapping according to " food is red
Before the candidate answer that beans " generate, and then it will be exported according to the candidate answer that " song red bean " generates as final response.
A chat task is lifted again, it is assumed that has individual to set in conversational system, the fruit liked is apple, is putd question in user
Say that you like the certain kind of berries that pastures, conversational system can know that strawberry refers to fruit, while can be matched to people set in have individual
If the fruit liked is apple, so can correctly and accurately answer such as I like eating apple reply.
S380, related dictionary generation adjusted is based on using the language generation module in dialogue interactive system adjusted
Natural language text corresponding with final response.
If dialogue management module determine computer it is next operation for output voice messaging as with user session pair
The response answered generates natural language text, Jin Erli then then will use language generation module and be based on related dictionary adjusted
The voice that natural language text is converted to flow field with speech synthesis technique, plays to user.
Technical solution provided in an embodiment of the present invention talks with friendship by that will interact knowledge mapping and be used as referring to information to adjust
The dictionary and/or model that each processing module uses in mutual system, to be maintained at the language transmitted between dialogue each module of interactive system
Meaning information is consistent, and then is being made and dialog information pair using dialogue interactive system adjusted referring to interaction knowledge mapping
When the response answered, it is easier to solve ambiguity problem.
Example IV
Fig. 4 is the structural schematic diagram for the more wheel dialogue interaction process devices of one kind that the embodiment of the present invention four provides, applicable
Semantics information transmits inconsistent situation when talking with interactive system processing more wheel dialogue, which can be used software and/or hard
The mode of part realizes, and generally can be integrated in the processor.As shown in figure 4, the device specifically includes: interworking entity obtains module
410, interaction knowledge mapping update module 420, dialogue interactive system adjustment module 430 and dialogue interactive system processing module 440,
Wherein,
Interworking entity obtains module 410, for obtaining true by the current session round when terminating current session round
Fixed target interworking entity；
Interaction knowledge mapping update module 420, for being interacted according to the renewal of knowledge corresponding with the target interworking entity
Knowledge mapping；Wherein, the interactive knowledge mapping is handed over at least one that dialog turns determine that terminated by more taking turns in dialogue
The corresponding knowledge connection of mutual entity；
Talk with interactive system and adjust module 430, for according to the updated interactive knowledge mapping adjustment dialogue interaction
The dictionary and/or model that at least one processing module uses in system；
Talk with interactive system processing module 440, for making when receiving dialog information corresponding with Next dialog round
Response corresponding with the dialog information is made with the dialogue interactive system adjusted.
More wheel dialogue interaction process devices provided in an embodiment of the present invention are obtained when terminating current session round every time
The target interworking entity determined by current session round, according to the renewal of knowledge corresponding with target interworking entity interaction knowledge graph
Spectrum, and then according to the dictionary that at least one processing module uses in updated interactive knowledge mapping adjustment dialogue interactive system
And/or model, make that identical semantics information and knowledge can be shared between each processing module, and then receiving and lower a pair
When talking about the corresponding dialog information of round, corresponding answer is made using dialogue interactive system adjusted, dialogue can be made upper and lower
Identical semantics information and knowledge can be shared between text each other, allows conversation tasks arbitrarily to convert, reaches seamless and integrate with, avoid
Semantics information transmitting between dialogue each module of interactive system generates mistake, in turn results in cross-module semantics information loss or different
The problem of cause.
Further, interaction knowledge mapping update module 420 is specifically used for being inquired according to the target interworking entity general
Knowledge mapping obtains knowledge corresponding with the target interworking entity；More according to knowledge corresponding with the target interworking entity
The new interactive knowledge mapping.
Wherein, the interactive knowledge mapping includes having terminated at least one that dialog turns determine with by taking turns in dialogue more
The corresponding knowledge of interworking entity, alternatively,
The interactive knowledge mapping includes being directed toward to have terminated at least one that dialog turns determine with by taking turns in dialogue more
The link of the corresponding knowledge of interworking entity.
Specifically, the processing module in the dialogue interactive system include: speech recognition module, it is semantic understanding module, right
Talk about management module and language generation module.
Further, dialogue interactive system adjustment module 430 specifically includes at least following units,
The first adjustment unit, for being adjusted in the speech recognition module according to the updated interactive knowledge mapping
Related dictionary and language model weight；
Second adjustment unit, for being adjusted in the semantic understanding module according to the updated interactive knowledge mapping
Related dictionary and intent classifier Model Weight；And
Third adjustment unit, for adjusting the dialogue management module and institute according to the updated interactive knowledge mapping
Related dictionary in predicate speech very generation module.
Specifically, dialogue interactive system processing module 440 is used to receive dialogue letter corresponding with Next dialog round
When breath, related dictionary and voice mould adjusted are based on using the speech recognition module in the dialogue interactive system adjusted
Type carries out speech recognition to the dialog information；
Related dictionary adjusted and meaning are based on using the semantic understanding module in the dialogue interactive system adjusted
Figure disaggregated model carries out semantic analysis to the recognition result that the speech recognition exports；
Using the dialogue management module in the dialogue interactive system adjusted be based on related dictionary adjusted and
The interactive knowledge mapping carries out reference resolution to the analysis result that the semantic understanding module exports, semantic slot position is inherited and is appointed
Business Parameter analysis of electrochemical operation, generates candidate answer corresponding with the dialog information, and then make corresponding with the dialog information
Final response；
Related dictionary adjusted is based on using the language generation module in the dialogue interactive system adjusted to generate
Natural language text corresponding with the final response.
Wherein, the conversation type of the candidate answer includes at least following one: Task, chat type and question and answer type.
Since more wheels dialogue interaction process device that the embodiment of the present invention is introduced is that can execute in the embodiment of the present invention
More wheels dialogue interaction processing method device, so based on more wheels described in the embodiment of the present invention talk with interaction process side
Method, those skilled in the art can understand the specific embodiment of more wheels dialogue interaction process device of the embodiment of the present invention
And its various change form, so how to be realized in the embodiment of the present invention at this for more wheel dialogue interaction process devices
More wheel dialogue interaction processing methods are no longer discussed in detail.As long as those skilled in the art implement more wheels in the embodiment of the present invention
Talk with device used by interaction processing method, belongs to the range to be protected of the application.
Embodiment five
The embodiment of the invention provides a kind of electronic equipment, as shown in Figure 5, comprising: at least one processor
(processor)51；And at least one processor (memory) 52, the bus 53 being connect with the processor 51；Wherein,
The processor 51, memory 52 complete mutual communication by the bus 53；
Memory 52 be used as a kind of non-transient computer readable storage medium, can be used for storing software program, computer can
Program and module are executed, such as the corresponding program instruction/mould of the more wheel dialogue interaction processing methods of one of embodiment of the present invention
(for example, attached shown in Fig. 4: interworking entity obtains module 410, interaction knowledge mapping update module 420, dialogue interactive system to block
Adjust module 430 and dialogue interactive system processing module 440).The processor 51 is used to call the journey in the memory 52
Sequence instruction/module, to execute a kind of steps taken turns in dialogue interaction processing methods in above method embodiment more.
Memory 52 may include storing program area and storage data area, wherein storing program area can storage program area,
Application program required at least one function；Storage data area, which can be stored, uses created data according to electronic equipment
Deng.In addition, memory 52 may include high-speed random access memory, it can also include non-transitory memory, for example, at least
One disk memory, flush memory device or other non-transitory solid-state memories.In some embodiments, memory 52
Optional includes the memory remotely located relative to processor 51, these remote memories can be set by network connection to terminal
It is standby.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Embodiment six
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage
Medium storing computer instruction, the computer instruction make the computer execute one kind provided by above-mentioned each method embodiment
More wheel dialogue interaction processing methods, this method comprises:.
When terminating current session round, the target interworking entity determined by the current session round is obtained；
According to the renewal of knowledge corresponding with target interworking entity interaction knowledge mapping；Wherein, the interactive knowledge graph
Spectrum with by take turns more talk in terminated the corresponding knowledge connection of at least one interworking entity that dialog turns determine；
It is used according at least one processing module in the updated interactive knowledge mapping adjustment dialogue interactive system
Dictionary and/or model；
When receiving dialog information corresponding with Next dialog round, done using the dialogue interactive system adjusted
Response corresponding with the dialog information out.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
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 Jie
The example of matter.
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.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application, and technology between each embodiment
The permutation and combination of feature should also be fallen under the scope of the present invention.To those skilled in the art, the application can be with
There are various modifications and variations.All any modification, equivalent replacement, improvement and so within the spirit and principles of the present application,
It should be included within the scope of claims hereof.
Claims (10)
1. a kind of more wheel dialogue interaction processing methods characterized by comprising
When terminating current session round, the target interworking entity determined by the current session round is obtained；
According to the renewal of knowledge corresponding with target interworking entity interaction knowledge mapping；Wherein, the interactive knowledge mapping with
By taking turns the corresponding knowledge connection of at least one interworking entity for having terminated dialog turns and having determined in dialogue more；
According to the dictionary that at least one processing module uses in the updated interactive knowledge mapping adjustment dialogue interactive system
And/or model；
When receiving dialog information corresponding with Next dialog round, using the dialogue interactive system adjusted make with
The corresponding response of the dialog information.
2. the method according to claim 1, wherein basis knowledge corresponding with the target interworking entity
Update interaction knowledge mapping, comprising:
World knowledge map is inquired according to the target interworking entity, obtains knowledge corresponding with the target interworking entity；
According to the renewal of knowledge interactive knowledge mapping corresponding with the target interworking entity.
3. method according to claim 1 or 2, which is characterized in that the interactive knowledge mapping include with by taking turns dialogue more
In terminated dialog turns determine the corresponding knowledge of at least one interworking entity, alternatively,
The interactive knowledge mapping includes being directed toward to interact with by taking turns at least one that dialog turns determine that terminated in dialogue more
The link of the corresponding knowledge of entity.
4. the method according to claim 1, wherein the processing module in the dialogue interactive system includes: language
Sound identification module, semantic understanding module, dialogue management module and language generation module.
5. according to the method described in claim 4, it is characterized in that, described adjust according to the updated interactive knowledge mapping
The dictionary and/or model that at least one processing module uses in dialogue interactive system, including one at least following:
Related dictionary and language model in the speech recognition module are adjusted according to the updated interactive knowledge mapping
Weight；
The related dictionary and intent classifier in the semantic understanding module are adjusted according to the updated interactive knowledge mapping
Model Weight；And
It is adjusted in the dialogue management module and the language very generation module according to the updated interactive knowledge mapping
Related dictionary.
6. according to the method described in claim 5, it is characterized in that, being made using the dialogue interactive system adjusted and institute
State the corresponding response of dialog information, comprising:
Related dictionary and voice mould adjusted are based on using the speech recognition module in the dialogue interactive system adjusted
Type carries out speech recognition to the dialog information；
Related dictionary adjusted and intention point are based on using the semantic understanding module in the dialogue interactive system adjusted
Class model carries out semantic analysis to the recognition result that the speech recognition exports；
Related dictionary adjusted and described is based on using the dialogue management module in the dialogue interactive system adjusted
Interaction knowledge mapping carries out reference resolution to the analysis result that the semantic understanding module exports, semantic slot position is inherited and task is joined
Number parsing operation, generates candidate answer corresponding with the dialog information, and then makes corresponding with the dialog information final
Response；
Related dictionary generation adjusted and institute are based on using the language generation module in the dialogue interactive system adjusted
State the corresponding natural language text of final response.
7. according to the method described in claim 6, it is characterized in that, the conversation type of the candidate answer includes at least following one
: Task, chat type and question and answer type.
8. a kind of more wheel dialogue interaction process devices characterized by comprising
Interworking entity obtains module, for obtaining the mesh determined by the current session round when terminating current session round
Mark interworking entity；
Interaction knowledge mapping update module, for according to the renewal of knowledge corresponding with target interworking entity interaction knowledge graph
Spectrum；Wherein, the interactive knowledge mapping with by take turns more dialogue at least one interworking entity for having terminated dialog turns and having determined
Corresponding knowledge connection；
Talk with interactive system and adjust module, for being talked in interactive system extremely according to the updated interactive knowledge mapping adjustment
The dictionary and/or model that a few processing module uses；
Talk with interactive system processing module, for using adjustment when receiving dialog information corresponding with Next dialog round
The dialogue interactive system afterwards makes response corresponding with the dialog information.
9. a kind of electronic equipment characterized by comprising
At least one processor；
And at least one processor, the bus being connected to the processor；Wherein,
The processor, memory complete mutual communication by the bus；
The processor is used to call the program instruction in the memory, any into claim 7 with perform claim requirement 1
More wheels described in talk with interaction processing method.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Store up computer instruction, the computer instruction requires the computer perform claim 1 to described in any one of claim 7
More wheel dialogue interaction processing methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811446940.8A CN109616108B (en) | 2018-11-29 | 2018-11-29 | Multi-turn dialogue interaction processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811446940.8A CN109616108B (en) | 2018-11-29 | 2018-11-29 | Multi-turn dialogue interaction processing method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109616108A true CN109616108A (en) | 2019-04-12 |
| CN109616108B CN109616108B (en) | 2022-05-31 |
Family
ID=66005502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811446940.8A Active CN109616108B (en) | 2018-11-29 | 2018-11-29 | Multi-turn dialogue interaction processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109616108B (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110032633A (en) * | 2019-04-17 | 2019-07-19 | 腾讯科技（深圳）有限公司 | More wheel dialog process method, apparatus and equipment |
| CN110111795A (en) * | 2019-04-23 | 2019-08-09 | 维沃移动通信有限公司 | A kind of method of speech processing and terminal device |
| CN110175226A (en) * | 2019-05-09 | 2019-08-27 | 厦门邑通软件科技有限公司 | A kind of dialogue decision-making technique based on various dimensions scene analysis |
| CN110222162A (en) * | 2019-05-10 | 2019-09-10 | 天津中科智能识别产业技术研究院有限公司 | A kind of intelligent answer method based on natural language processing and knowledge mapping |
| CN110347816A (en) * | 2019-07-15 | 2019-10-18 | 腾讯科技（上海）有限公司 | A kind of information recommendation method and device |
| CN110543556A (en) * | 2019-09-05 | 2019-12-06 | 出门问问信息科技有限公司 | Dialogue configuration method, storage medium and electronic equipment |
| CN110706702A (en) * | 2019-10-15 | 2020-01-17 | 芜湖盟博科技有限公司 | Infinite stage multi-turn dialogue method for speech recognition |
| CN110737765A (en) * | 2019-10-25 | 2020-01-31 | 上海喜马拉雅科技有限公司 | Dialogue data processing method for multi-turn dialogue and related device |
| CN110827831A (en) * | 2019-11-15 | 2020-02-21 | 广州洪荒智能科技有限公司 | Voice information processing method, device, equipment and medium based on man-machine interaction |
| CN110909159A (en) * | 2019-09-29 | 2020-03-24 | 珠海格力电器股份有限公司 | User intention identification method, device, terminal and storage medium |
| CN111026886A (en) * | 2019-12-26 | 2020-04-17 | 成都航天科工大数据研究院有限公司 | Multi-round dialogue processing method for professional scene |
| CN111178940A (en) * | 2019-12-11 | 2020-05-19 | 北京明略软件系统有限公司 | Method and system for automatically generating sales call technology map |
| CN111177358A (en) * | 2019-12-31 | 2020-05-19 | 华为技术有限公司 | Intention recognition method, server, and storage medium |
| CN111222323A (en) * | 2019-12-30 | 2020-06-02 | 深圳市优必选科技股份有限公司 | Word slot extraction method, word slot extraction device and electronic equipment |
| CN111339283A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Method and device for providing customer service answers aiming at user questions |
| CN111341308A (en) * | 2020-02-12 | 2020-06-26 | 百度在线网络技术（北京）有限公司 | Method and apparatus for outputting information |
| CN111651615A (en) * | 2020-07-24 | 2020-09-11 | 上海茂声智能科技有限公司 | Method and system for man-machine interaction based on knowledge graph |
| WO2020216064A1 (en) * | 2019-04-24 | 2020-10-29 | 京东方科技集团股份有限公司 | Speech emotion recognition method, semantic recognition method, question-answering method, computer device and computer-readable storage medium |
| CN111966803A (en) * | 2020-08-03 | 2020-11-20 | 深圳市欢太科技有限公司 | Dialogue simulation method, dialogue simulation device, storage medium and electronic equipment |
| WO2020238341A1 (en) * | 2019-05-31 | 2020-12-03 | 华为技术有限公司 | Speech recognition method, apparatus and device, and computer-readable storage medium |
| CN112164401A (en) * | 2020-09-18 | 2021-01-01 | 广州小鹏汽车科技有限公司 | Voice interaction method, server and computer-readable storage medium |
| CN112215010A (en) * | 2019-07-10 | 2021-01-12 | 北京猎户星空科技有限公司 | Semantic recognition method and equipment |
| CN112364147A (en) * | 2020-12-01 | 2021-02-12 | 四川长虹电器股份有限公司 | Cross-domain multi-turn dialogue method based on knowledge graph and implementation system |
| CN112445902A (en) * | 2019-09-04 | 2021-03-05 | 深圳Tcl数字技术有限公司 | Method for identifying user intention in multi-turn conversation and related equipment |
| CN112463939A (en) * | 2020-11-12 | 2021-03-09 | 深圳市欢太科技有限公司 | Man-machine conversation method, system, service device and computer storage medium |
| CN112487137A (en) * | 2019-09-12 | 2021-03-12 | 甲骨文国际公司 | Streamlining conversation processing using integrated shared resources |
| CN112581955A (en) * | 2020-11-30 | 2021-03-30 | 广州橙行智动汽车科技有限公司 | Voice control method, server, voice control system and readable storage medium |
| CN112911073A (en) * | 2019-04-30 | 2021-06-04 | 五竹科技(北京)有限公司 | Intelligent knowledge graph construction method and device for outbound process conversation content |
| CN113470625A (en) * | 2021-06-30 | 2021-10-01 | 西安力传智能技术有限公司 | Voice conversation processing method, device, equipment and storage medium |
| CN114144773A (en) * | 2019-08-01 | 2022-03-04 | 国际商业机器公司 | Adjusting conversational flow based on behavior in human-machine cognitive interactions |
| CN115186147A (en) * | 2022-05-31 | 2022-10-14 | 华院计算技术(上海)股份有限公司 | Method and device for generating conversation content, storage medium and terminal |
| CN116501592A (en) * | 2023-06-19 | 2023-07-28 | 阿里巴巴（中国）有限公司 | Man-machine interaction data processing method and server |
| CN117496973A (en) * | 2024-01-02 | 2024-02-02 | 四川蜀天信息技术有限公司 | Method, device, equipment and medium for improving man-machine conversation interaction experience |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160163311A1 (en) * | 2014-12-09 | 2016-06-09 | Microsoft Technology Licensing, Llc | Communication system |
| CN106649694A (en) * | 2016-12-19 | 2017-05-10 | 北京云知声信息技术有限公司 | Method and device for identifying user's intention in voice interaction |
| CN107704612A (en) * | 2017-10-23 | 2018-02-16 | 北京光年无限科技有限公司 | Dialogue exchange method and system for intelligent robot |
| CN107943998A (en) * | 2017-12-05 | 2018-04-20 | 竹间智能科技（上海）有限公司 | A kind of human-machine conversation control system and method for knowledge based collection of illustrative plates |
-
2018
- 2018-11-29 CN CN201811446940.8A patent/CN109616108B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160163311A1 (en) * | 2014-12-09 | 2016-06-09 | Microsoft Technology Licensing, Llc | Communication system |
| CN106649694A (en) * | 2016-12-19 | 2017-05-10 | 北京云知声信息技术有限公司 | Method and device for identifying user's intention in voice interaction |
| CN107704612A (en) * | 2017-10-23 | 2018-02-16 | 北京光年无限科技有限公司 | Dialogue exchange method and system for intelligent robot |
| CN107943998A (en) * | 2017-12-05 | 2018-04-20 | 竹间智能科技（上海）有限公司 | A kind of human-machine conversation control system and method for knowledge based collection of illustrative plates |
Cited By (51)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110032633B (en) * | 2019-04-17 | 2021-03-23 | 腾讯科技（深圳）有限公司 | Multi-turn dialogue processing method, device and equipment |
| CN110032633A (en) * | 2019-04-17 | 2019-07-19 | 腾讯科技（深圳）有限公司 | More wheel dialog process method, apparatus and equipment |
| CN110111795B (en) * | 2019-04-23 | 2021-08-27 | 维沃移动通信有限公司 | Voice processing method and terminal equipment |
| CN110111795A (en) * | 2019-04-23 | 2019-08-09 | 维沃移动通信有限公司 | A kind of method of speech processing and terminal device |
| WO2020216064A1 (en) * | 2019-04-24 | 2020-10-29 | 京东方科技集团股份有限公司 | Speech emotion recognition method, semantic recognition method, question-answering method, computer device and computer-readable storage medium |
| CN112911073A (en) * | 2019-04-30 | 2021-06-04 | 五竹科技(北京)有限公司 | Intelligent knowledge graph construction method and device for outbound process conversation content |
| CN110175226A (en) * | 2019-05-09 | 2019-08-27 | 厦门邑通软件科技有限公司 | A kind of dialogue decision-making technique based on various dimensions scene analysis |
| CN110222162A (en) * | 2019-05-10 | 2019-09-10 | 天津中科智能识别产业技术研究院有限公司 | A kind of intelligent answer method based on natural language processing and knowledge mapping |
| WO2020238341A1 (en) * | 2019-05-31 | 2020-12-03 | 华为技术有限公司 | Speech recognition method, apparatus and device, and computer-readable storage medium |
| CN112215010A (en) * | 2019-07-10 | 2021-01-12 | 北京猎户星空科技有限公司 | Semantic recognition method and equipment |
| CN110347816A (en) * | 2019-07-15 | 2019-10-18 | 腾讯科技（上海）有限公司 | A kind of information recommendation method and device |
| CN110347816B (en) * | 2019-07-15 | 2023-08-04 | 腾讯科技（上海）有限公司 | Information recommendation method and device |
| CN114144773B (en) * | 2019-08-01 | 2022-10-28 | 国际商业机器公司 | Adjusting conversational flow based on behavior in human-machine cognitive interactions |
| CN114144773A (en) * | 2019-08-01 | 2022-03-04 | 国际商业机器公司 | Adjusting conversational flow based on behavior in human-machine cognitive interactions |
| CN112445902A (en) * | 2019-09-04 | 2021-03-05 | 深圳Tcl数字技术有限公司 | Method for identifying user intention in multi-turn conversation and related equipment |
| CN110543556A (en) * | 2019-09-05 | 2019-12-06 | 出门问问信息科技有限公司 | Dialogue configuration method, storage medium and electronic equipment |
| CN112487137B (en) * | 2019-09-12 | 2023-11-03 | 甲骨文国际公司 | Streamlining dialog processing using integrated shared resources |
| CN112487137A (en) * | 2019-09-12 | 2021-03-12 | 甲骨文国际公司 | Streamlining conversation processing using integrated shared resources |
| CN110909159A (en) * | 2019-09-29 | 2020-03-24 | 珠海格力电器股份有限公司 | User intention identification method, device, terminal and storage medium |
| CN110706702B (en) * | 2019-10-15 | 2021-11-09 | 芜湖盟博科技有限公司 | Infinite stage multi-turn dialogue method for speech recognition |
| CN110706702A (en) * | 2019-10-15 | 2020-01-17 | 芜湖盟博科技有限公司 | Infinite stage multi-turn dialogue method for speech recognition |
| CN110737765A (en) * | 2019-10-25 | 2020-01-31 | 上海喜马拉雅科技有限公司 | Dialogue data processing method for multi-turn dialogue and related device |
| CN110827831A (en) * | 2019-11-15 | 2020-02-21 | 广州洪荒智能科技有限公司 | Voice information processing method, device, equipment and medium based on man-machine interaction |
| CN111178940B (en) * | 2019-12-11 | 2023-09-01 | 北京明略软件系统有限公司 | Method and system for automatically generating sales call operation map |
| CN111178940A (en) * | 2019-12-11 | 2020-05-19 | 北京明略软件系统有限公司 | Method and system for automatically generating sales call technology map |
| CN111026886B (en) * | 2019-12-26 | 2023-05-02 | 成都航天科工大数据研究院有限公司 | Multi-round dialogue processing method for professional scene |
| CN111026886A (en) * | 2019-12-26 | 2020-04-17 | 成都航天科工大数据研究院有限公司 | Multi-round dialogue processing method for professional scene |
| CN111222323A (en) * | 2019-12-30 | 2020-06-02 | 深圳市优必选科技股份有限公司 | Word slot extraction method, word slot extraction device and electronic equipment |
| CN111177358A (en) * | 2019-12-31 | 2020-05-19 | 华为技术有限公司 | Intention recognition method, server, and storage medium |
| CN111177358B (en) * | 2019-12-31 | 2023-05-12 | 华为技术有限公司 | Intention recognition method, server and storage medium |
| CN111341308A (en) * | 2020-02-12 | 2020-06-26 | 百度在线网络技术（北京）有限公司 | Method and apparatus for outputting information |
| CN111341308B (en) * | 2020-02-12 | 2023-07-21 | 百度在线网络技术（北京）有限公司 | Method and device for outputting information |
| CN111339283A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Method and device for providing customer service answers aiming at user questions |
| CN111339283B (en) * | 2020-05-15 | 2020-08-21 | 支付宝(杭州)信息技术有限公司 | Method and device for providing customer service answers aiming at user questions |
| CN111651615A (en) * | 2020-07-24 | 2020-09-11 | 上海茂声智能科技有限公司 | Method and system for man-machine interaction based on knowledge graph |
| CN111651615B (en) * | 2020-07-24 | 2023-06-13 | 上海茂声智能科技有限公司 | Method and system for human-computer interaction based on knowledge graph |
| CN111966803A (en) * | 2020-08-03 | 2020-11-20 | 深圳市欢太科技有限公司 | Dialogue simulation method, dialogue simulation device, storage medium and electronic equipment |
| CN111966803B (en) * | 2020-08-03 | 2024-04-12 | 深圳市欢太科技有限公司 | Dialogue simulation method and device, storage medium and electronic equipment |
| CN112164401A (en) * | 2020-09-18 | 2021-01-01 | 广州小鹏汽车科技有限公司 | Voice interaction method, server and computer-readable storage medium |
| CN112164401B (en) * | 2020-09-18 | 2022-03-18 | 广州小鹏汽车科技有限公司 | Voice interaction method, server and computer-readable storage medium |
| CN112463939A (en) * | 2020-11-12 | 2021-03-09 | 深圳市欢太科技有限公司 | Man-machine conversation method, system, service device and computer storage medium |
| CN112581955B (en) * | 2020-11-30 | 2024-03-08 | 广州橙行智动汽车科技有限公司 | Voice control method, server, voice control system, and readable storage medium |
| CN112581955A (en) * | 2020-11-30 | 2021-03-30 | 广州橙行智动汽车科技有限公司 | Voice control method, server, voice control system and readable storage medium |
| CN112364147A (en) * | 2020-12-01 | 2021-02-12 | 四川长虹电器股份有限公司 | Cross-domain multi-turn dialogue method based on knowledge graph and implementation system |
| CN113470625A (en) * | 2021-06-30 | 2021-10-01 | 西安力传智能技术有限公司 | Voice conversation processing method, device, equipment and storage medium |
| CN115186147B (en) * | 2022-05-31 | 2023-08-25 | 华院计算技术(上海)股份有限公司 | Dialogue content generation method and device, storage medium and terminal |
| CN115186147A (en) * | 2022-05-31 | 2022-10-14 | 华院计算技术(上海)股份有限公司 | Method and device for generating conversation content, storage medium and terminal |
| CN116501592A (en) * | 2023-06-19 | 2023-07-28 | 阿里巴巴（中国）有限公司 | Man-machine interaction data processing method and server |
| CN116501592B (en) * | 2023-06-19 | 2023-09-19 | 阿里巴巴（中国）有限公司 | Man-machine interaction data processing method and server |
| CN117496973A (en) * | 2024-01-02 | 2024-02-02 | 四川蜀天信息技术有限公司 | Method, device, equipment and medium for improving man-machine conversation interaction experience |
| CN117496973B (en) * | 2024-01-02 | 2024-03-19 | 四川蜀天信息技术有限公司 | Method, device, equipment and medium for improving man-machine conversation interaction experience |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109616108B (en) | 2022-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109616108A (en) | More wheel dialogue interaction processing methods, device, electronic equipment and storage medium | |
| CN105702248B (en) | For operating the electronic equipment and method, storage medium of intelligent automation assistant | |
| CN110377716B (en) | Interaction method and device for conversation and computer readable storage medium | |
| WO2018133761A1 (en) | Method and device for man-machine dialogue | |
| CN106611597B (en) | Voice awakening method and device based on artificial intelligence | |
| CN106297789B (en) | Personalized interaction method and system for intelligent robot | |
| CN108255934A (en) | A kind of sound control method and device | |
| EP3485492A1 (en) | Multi-user authentication on a device | |
| CN109243468A (en) | Audio recognition method, device, electronic equipment and storage medium | |
| CN111837116B (en) | Method for automatically constructing or updating dialog flow management model of dialog type AI system | |
| KR20180070684A (en) | Parameter collection and automatic dialog generation in dialog systems | |
| CN106796788A (en) | Automatic speech recognition is improved based on user feedback | |
| CN109215630B (en) | Real-time voice recognition method, device, equipment and storage medium | |
| CN111090728A (en) | Conversation state tracking method and device and computing equipment | |
| CN103635963A (en) | Cross-lingual initialization of language models | |
| CN108899013A (en) | Voice search method, device and speech recognition system | |
| CN108763495A (en) | Interactive method, system, electronic equipment and storage medium | |
| US11200885B1 (en) | Goal-oriented dialog system | |
| CN108877800A (en) | Voice interactive method, device, electronic equipment and readable storage medium storing program for executing | |
| US11132994B1 (en) | Multi-domain dialog state tracking | |
| CN110019691A (en) | Conversation message treating method and apparatus | |
| EP2879062A2 (en) | A system and a method for providing a dialog with a user | |
| CN110223692A (en) | More wheel dialogue methods and system for voice dialogue platform across technical ability | |
| CN109767763A (en) | It is customized wake up word determination method and for determine it is customized wake up word device | |
| CN109427325A (en) | Speech synthesis dictionary diostribution device, speech synthesis system and program 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211119 Address after: 210038 8th floor, building D11, Hongfeng science and Technology Park, Nanjing Economic and Technological Development Zone, Jiangsu Province Applicant after: New Technology Co.,Ltd. Applicant after: Volkswagen (China) Investment Co., Ltd Address before: Room 501, floor 5, No. 67, North Fourth Ring West Road, Fengtai District, Beijing 100080 Applicant before: Beijing Yufanzhi Information Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |