CN106991124A - Answer method and system based on how interactive situation editor - Google Patents

Answer method and system based on how interactive situation editor Download PDF

Info

Publication number
CN106991124A
CN106991124A CN201710121335.2A CN201710121335A CN106991124A CN 106991124 A CN106991124 A CN 106991124A CN 201710121335 A CN201710121335 A CN 201710121335A CN 106991124 A CN106991124 A CN 106991124A
Authority
CN
China
Prior art keywords
interactive situation
interactive
information
situation
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710121335.2A
Other languages
Chinese (zh)
Inventor
简仁贤
陈镜宇
李琳
姚维民
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Intelligent Technology (shanghai) Co Ltd
Original Assignee
Intelligent Technology (shanghai) Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Intelligent Technology (shanghai) Co Ltd filed Critical Intelligent Technology (shanghai) Co Ltd
Priority to CN201710121335.2A priority Critical patent/CN106991124A/en
Publication of CN106991124A publication Critical patent/CN106991124A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems

Abstract

The man-machine interaction method and system based on how interactive situation that the present invention is provided, method is:Obtain at least one the interactive situation included in the information that user currently inputs;According at least one interactive situation, the one or more interactive situations prestored of correspondence triggering obtain triggering interactive situation, and the interactive situation prestored includes multiple nodes, the different task of each node correspondence;The information currently inputted according to user, analysis obtains current dialogue states;According to the interactive situation of triggering, with reference to current dialogue states, switched between multiple nodes in the interactive situation of triggering, complete the corresponding task of each node, realize human-computer interaction.Present invention employs matched based on the interactive situation in user session content with the interactive situation prestored, make to combine interactive situation in man-machine interactive process, the corresponding task of node in correspondence dialogue is completed, the Intelligence Feedback ability of human-computer interaction can be improved, Consumer's Experience is improved.

Description

Answer method and system based on how interactive situation editor
Technical field
The present invention relates to artificial intelligence field, more particularly to interactive system field.
Background technology
In existing artificial intelligence conversational system, the conversation content of user is judged using corpus and template, and Generation is answered.But how this responds conversational system, but answer strategy is not adjusted with reference to the emotion that user expresses, provide band thoughts The answer of feelings.
On the natural dialogue of person to person, emotion is a key factor, the emotion that the mankind can be according to expressed by other side come The answer strategy of oneself is adjusted, the effect of communication is reached.
Therefore, defect of the prior art is that in artificial intelligence dialog procedure, robot can not be combined and included in dialogue Dialogue scene interacted with user, prevent robot from provided according to different dialogue scenes meet under the situation return Answer, easily cause the erroneous answers that robot is provided, make user experience low.
The content of the invention
For above-mentioned technical problem, the present invention provides a kind of man-machine interaction method and system based on how interactive situation, adopted With being matched based on the interactive situation in user session content with the interactive situation prestored, make in man-machine interactive process With reference to interactive situation, the corresponding task of node in correspondence dialogue is completed, it is personal due to including the emotion of user in interactive situation The information such as feature, therefore in this way, the Intelligence Feedback ability of human-computer interaction can be improved, Consumer's Experience is improved.
In order to solve the above technical problems, the technical scheme that the present invention is provided is:
In a first aspect, the present invention provides a kind of man-machine interaction method based on how interactive situation, including:
Step S1, obtains mutual comprising at least one in the information that user currently inputs, the information that the user currently inputs Emotionally border;
Step S2, according at least one described interactive situation, correspondence triggers one or more interactive situations prestored, Obtain triggering interactive situation, the interactive situation prestored includes multiple nodes, the different task of each node correspondence;
Step S3, the information currently inputted according to the user, analysis obtains current dialogue states, the current session shape The userspersonal information included in the information that state is currently inputted according to the user obtains;
Step S4, according to the interactive situation of the triggering, with reference to the current dialogue states, in the interactive situation of the triggering Multiple nodes between switch over, complete the corresponding task of each node, realize human-computer interaction.
The man-machine interaction method based on how interactive situation that the present invention is provided, its technical scheme is:Obtain user currently defeated At least one interactive situation is included in the information entered, the information that the user currently inputs;According to it is described at least one mutually emotionally Border, the one or more interactive situations prestored of correspondence triggering obtain triggering interactive situation, it is described prestore mutually emotionally Border includes multiple nodes, the different task of each node correspondence;The information currently inputted according to the user, analysis is worked as The userspersonal information included in preceding dialogue state, the information that the current dialogue states are currently inputted according to the user obtains ;According to the interactive situation of triggering, with reference to the current dialogue states, multiple nodes in the interactive situation of the triggering it Between switch over, complete the corresponding task of each node, realize human-computer interaction.
The present invention the answer method based on how interactive situation editor, employ based in user session content mutually emotionally Border is matched with the interactive situation prestored, is made to combine interactive situation in man-machine interactive process, is completed in correspondence dialogue The corresponding task of node, due to including the emotion of user in interactive situation, the information such as personal characteristics, therefore in this way, The Intelligence Feedback ability of human-computer interaction can be improved, Consumer's Experience is improved.
Further, the interactive situation prestored is obtained by the method for human-edited or machine learning.
Further, in addition to, the interactive situation that prestores updates step:
Obtain the text message that repeatedly inputs of user, and it is corresponding multiple to obtain the text message that the user repeatedly inputs Interactive situation;
The multiple interactive situation is combined, multiple new interactive situations, the multiple new interactive situation are formed Quantity be more than the multiple interactive situation quantity.
Further, the step S2, according at least one described interactive situation, correspondence triggering is one or more to deposit in advance The interactive situation of storage, obtains triggering interactive situation, is specially:
Obtain the interactive situation editor demand information at least one described interactive situation;
By the interactive situation editor demand information at least one described interactive situation with it is described prestore mutually emotionally Border is matched, and obtains triggering interactive situation.
Further, the step S3, be specially:
Obtain the dialog information before feedback information, the data information of individual subscriber, preference information and the user of user, institute The feedback information for stating user is the corresponding feedback information of information that the user currently inputs;
According to the dialogue letter before the feedback information of the user, the data information of individual subscriber, preference information and user Breath, the information currently inputted with reference to the user, analysis obtains current dialogue states.
Further, the step S4, be specially:
Obtain at least one node in the interactive situation of the triggering, the different task of each node correspondence;
According at least one node in the interactive situation of the triggering, with reference to the current dialogue states, described touch is completed The corresponding task of at least one node in the interactive situation of hair, realizes human-computer interaction.
Second aspect, the invention provides a kind of human-computer interaction system based on how interactive situation, including:
Data obtaining module, is included for obtaining in the information that user currently inputs, the information that the user currently inputs At least one interactive situation;
Interactive situation trigger module, for according at least one described interactive situation, correspondence triggering to be one or more in advance The interactive situation of storage, obtains triggering interactive situation, the interactive situation prestored includes multiple nodes, each node The different task of correspondence;
Current dialogue states module, for the information currently inputted according to the user, analysis obtains current dialogue states, The userspersonal information included in the information that the current dialogue states are currently inputted according to the user obtains;
Human-computer interaction module, for according to the interactive situation of the triggering, with reference to the current dialogue states, in the triggering Switched between multiple nodes in interactive situation, complete the corresponding task of each node, realize human-computer interaction.
A kind of human-computer interaction system based on how interactive situation that the present invention is provided, its technical scheme is:Obtained by information Modulus block, it is mutual emotionally comprising at least one in the information that user currently inputs, the information that the user currently inputs for obtaining Border;By interactive situation trigger module, for according at least one described interactive situation, correspondence triggering is one or more to deposit in advance The interactive situation of storage, obtains triggering interactive situation, the interactive situation prestored includes multiple nodes, each node pair Answer different tasks;
By current dialogue states module, for the information currently inputted according to the user, analysis obtains current session The userspersonal information included in state, the information that the current dialogue states are currently inputted according to the user obtains;Finally It is interactive in the triggering with reference to the current dialogue states for according to the interactive situation of the triggering by human-computer interaction module Switched between multiple nodes in situation, complete the corresponding task of each node, realize human-computer interaction.
The present invention the human-computer interaction system based on how interactive situation, employ based in user session content mutually emotionally Border is matched with the interactive situation prestored, is made to combine interactive situation in man-machine interactive process, is completed in correspondence dialogue The corresponding task of node, due to including the emotion of user in interactive situation, the information such as personal characteristics, therefore in this way, The Intelligence Feedback ability of human-computer interaction can be improved, Consumer's Experience is improved.
Further, in addition to, the interactive situation update module prestored, specifically for:
Obtain the text message that repeatedly inputs of user, and it is corresponding multiple to obtain the text message that the user repeatedly inputs Interactive situation;
The multiple interactive situation is combined, multiple new interactive situations, the multiple new interactive situation are formed Quantity be more than the multiple interactive situation quantity.
Further, the interactive situation trigger module, specifically for:
Obtain the interactive situation editor demand information at least one described interactive situation;
By the interactive situation editor demand information at least one described interactive situation with it is described prestore mutually emotionally Border is matched, and obtains triggering interactive situation.
Further, the current dialogue states module, specifically for:
Obtain the dialog information before feedback information, the data information of individual subscriber, preference information and the user of user, institute The feedback information for stating user is the corresponding feedback information of information that the user currently inputs;
According to the dialogue letter before the feedback information of the user, the data information of individual subscriber, preference information and user Breath, the information currently inputted with reference to the user, analysis obtains current dialogue states.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art The accompanying drawing used required in embodiment or description of the prior art is briefly described.
Fig. 1 shows a kind of stream for man-machine interaction method based on how interactive situation that first embodiment of the invention is provided Cheng Tu;
Fig. 2 shows a kind of letter for man-machine interaction method based on how interactive situation that first embodiment of the invention is provided Single session node editor's schematic diagram;
Fig. 3 shows a kind of showing for human-computer interaction system based on how interactive situation that first embodiment of the invention is provided It is intended to.
Embodiment
The embodiment of technical solution of the present invention is described in detail below in conjunction with accompanying drawing.Following examples are only used for Clearly illustrate technical scheme, therefore be intended only as example, and the protection of the present invention can not be limited with this Scope.
Embodiment one
Fig. 1 shows a kind of stream for man-machine interaction method based on how interactive situation that first embodiment of the invention is provided Cheng Tu;As shown in figure 1, a kind of man-machine interaction method based on how interactive situation that embodiment one is provided, including:
Step S1, obtains mutual emotionally comprising at least one in the information that user currently inputs, the information that user currently inputs Border;
Step S2, according at least one interactive situation, the one or more interactive situations prestored of correspondence triggering are obtained The interactive situation of triggering, the interactive situation prestored includes multiple nodes, the different task of each node correspondence;
Step S3, the information currently inputted according to user, analysis obtain current dialogue states, current dialogue states according to The userspersonal information included in the information that family is currently inputted obtains;
Step S4, according to the interactive situation of triggering, with reference to current dialogue states, multiple nodes in the interactive situation of triggering it Between switch over, complete the corresponding task of each node, realize human-computer interaction.
The man-machine interaction method based on how interactive situation that the present invention is provided, its technical scheme is:Obtain user currently defeated At least one interactive situation is included in the information entered, the information that user currently inputs;Interaction is included at least one interactive situation Situation editor's demand information;According at least one interactive situation, by the interactive situation editor demand at least one interactive situation Information is matched with the interactive situation prestored, the one or more interactive situations prestored of correspondence triggering, is touched The interactive situation of hair;The interactive situation wherein prestored includes multiple nodes, the different task of each node correspondence;
Then the userspersonal information included in the information currently inputted according to user, wherein, userspersonal information includes But the dialog information before the feedback information of user, the data information of individual subscriber, preference information and user is not limited to, user's Feedback information is the corresponding feedback information of information that user currently inputs;Individual character, emotion of user etc. can be reflected in these information, Current dialogue states can be obtained by analysis.
Finally obtain at least one node in the interactive situation of triggering;With reference to current dialogue states, triggering is completed mutually emotionally The corresponding task of at least one node in border, wherein, if multiple nodes are included in the interactive situation of triggering, according in dialogue Hold, be sequentially completed the corresponding task of node in sequence, the corresponding task of node can be provide corresponding answer or The task (ordering air ticket task dispatching) included in user's input information is completed, human-computer interaction is realized.
The present invention the man-machine interaction method based on how interactive situation, employ based in user session content mutually emotionally Border is matched with the interactive situation prestored, is made to combine interactive situation in man-machine interactive process, is completed in correspondence dialogue The corresponding task of node, due to including the emotion of user in interactive situation, the information such as personal characteristics, therefore in this way, The Intelligence Feedback ability of human-computer interaction can be improved, Consumer's Experience is improved.
Preferably, the interactive situation prestored is obtained by the method for human-edited or machine learning.
By the method or artificial method of machine learning, some interactive situations are prestored, are compiled for editing scene Volume task, obtains the interactive situation needed in user version information, with reference to interactive situation, the answer provided, it is considered to user Emotion, in this way, reduces the error rate of answer, improves Consumer's Experience.
Wherein, the interactive situation prestored is wrapped according in field feedback during human-computer dialogue or passing dialogue The foundation such as the tone, the emotion information that contain.
Referring to Fig. 2, the editor of the interactive situation prestored is obtained by editing each node, with reference to figure 2, the node editor of simple dialog is illustrated:
Prospective users are inputted:Good morning!
According to the node of first pre-editing, the condition judgment according to user feedback:Time is morning;
It is then back to the dialogue of user:Today, weather was pretty good!Into next node, carried out according to the input of user next The editor of node.
Preferably, in addition to, the interactive situation that prestores updates step:
The text message that user repeatedly inputs is obtained, and obtains the corresponding multiple interactions of text message that user repeatedly inputs Situation;
Multiple interactive situations are combined, multiple new interactive situations are formed, the quantity of multiple new interactive situations is big In the quantity of multiple interactive situations.
The interactive situation prestored is generally obtained by way of human-edited, therefore, and dialogue scene is passed through into combination Form be extended, realize renewal to the dialogue scene in drama, it is not necessary to previously generate substantial amounts of dialogue scene storage Get up, solve memory space, improve operational efficiency.
Furthermore it is also possible to based on the interactive situation in each human-computer dialogue, be automatically generated by the method for machine learning Some new interactive situations, expand substantial amounts of dialogue scenarios with a small amount of limited dialogue scenarios, enable robot according to difference Dialogue scenarios provide the answer met under the scene, so as to reduce the error rate of answer, improve Consumer's Experience.
Fig. 3 shows a kind of showing for human-computer interaction system based on how interactive situation that first embodiment of the invention is provided It is intended to.As shown in figure 3, embodiment one provides a kind of human-computer interaction system 10 based on how interactive situation, including:
Data obtaining module 101, for obtaining in the information that user currently inputs, the information that user currently inputs comprising extremely A few interactive situation;
Interactive situation trigger module 102, for according at least one interactive situation, correspondence triggering is one or more to deposit in advance The interactive situation of storage, obtains triggering interactive situation, and the interactive situation prestored includes multiple nodes, and each node correspondence is not Same task;
Current dialogue states module 103, for the information currently inputted according to user, analysis obtains current dialogue states, The userspersonal information included in the information that current dialogue states are currently inputted according to user obtains;
Human-computer interaction module 104, for according to the interactive situation of triggering, with reference to current dialogue states, in the interactive situation of triggering In multiple nodes between switch over, complete the corresponding task of each node, realize human-computer interaction.
A kind of human-computer interaction system 10 based on how interactive situation that the present invention is provided, its technical scheme is:Pass through information Acquisition module 101, it is mutual emotionally comprising at least one in the information that user currently inputs, the information that user currently inputs for obtaining Border;By interactive situation trigger module 102, for according at least one interactive situation, correspondence triggering is one or more to deposit in advance The interactive situation of storage, obtains triggering interactive situation, and the interactive situation prestored includes multiple nodes, and each node correspondence is not Same task;
By current dialogue states module 103, for the information currently inputted according to user, analysis obtains current session shape The userspersonal information included in state, the information that current dialogue states are currently inputted according to user obtains;Finally by man-machine mutual Dynamic model block 104, for according to the interactive situation of triggering, with reference to current dialogue states, multiple nodes in the interactive situation of triggering it Between switch over, complete the corresponding task of each node, realize human-computer interaction.
The present invention the human-computer interaction system based on how interactive situation, employ based in user session content mutually emotionally Border is matched with the interactive situation prestored, is made to combine interactive situation in man-machine interactive process, is completed in correspondence dialogue The corresponding task of node, due to including the emotion of user in interactive situation, the information such as personal characteristics, therefore in this way, The Intelligence Feedback ability of human-computer interaction can be improved, Consumer's Experience is improved.
Preferably, in addition to, the interactive situation update module prestored, specifically for:
The text message that user repeatedly inputs is obtained, and obtains the corresponding multiple interactions of text message that user repeatedly inputs Situation;
Multiple interactive situations are combined, multiple new interactive situations are formed, the quantity of multiple new interactive situations is big In the quantity of multiple interactive situations.
The interactive situation prestored is generally obtained by way of human-edited, therefore, and dialogue scene is passed through into combination Form be extended, realize renewal to the dialogue scene in drama, it is not necessary to previously generate substantial amounts of dialogue scene storage Get up, solve memory space, improve operational efficiency.
Furthermore it is also possible to based on the interactive situation in each human-computer dialogue, be automatically generated by the method for machine learning Some new interactive situations, expand substantial amounts of dialogue scenarios with a small amount of limited dialogue scenarios, enable robot according to difference Dialogue scenarios provide the answer met under the scene, so as to reduce the error rate of answer, improve Consumer's Experience.
Specifically, interactive situation trigger module, specifically for:
Obtain the interactive situation editor demand information at least one interactive situation;
By the interactive situation editor demand information at least one interactive situation and the interactive situation prestored progress Match somebody with somebody, obtain triggering interactive situation.
Specifically, current dialogue states module, specifically for:
The dialog information before feedback information, the data information of individual subscriber, preference information and the user of user is obtained, is used The feedback information at family is the corresponding feedback information of information that user currently inputs;
According to the dialog information before the feedback information of user, the data information of individual subscriber, preference information and user, knot The information that family is currently inputted is shared, analysis obtains current dialogue states.
Embodiment two
The man-machine interaction method and the embodiment of the present invention two based on how interactive situation provided based on the embodiment of the present invention one The human-computer interaction system 10 based on how interactive situation provided, is said by the specific human-computer interaction process in the present embodiment It is bright:
User says:" weekend is good boring ";
Some interactive situation is triggered, into first (dialogue) node of the interactive situation, out of just user input Appearance may determine that the current dialogue state of the user is " feeling bad ", then according to this node, provide answer:" whether Go out for a walk ";
User answers:" good ".
Then the interactive situation of hot spot nearby is recommended in triggering, into the node of the interactive situation, according to returning for user Answer, judge that user wants to go out to take a walk, then according to this node, provide answer:" going to neighbouring XX parks, let's go ".
By parity of reasoning, by one or more interactive situations realized and defined, it may be considered that into user's current session Emotion, provide more intelligent answer, improve user and the Interactive Experience in the machine human world.
Finally it should be noted that:Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations;To the greatest extent The present invention is described in detail with reference to foregoing embodiments for pipe, it will be understood by those within the art that:Its according to The technical scheme described in foregoing embodiments can so be modified, or which part or all technical characteristic are entered Row equivalent substitution;And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology The scope of scheme, it all should cover among the claim of the present invention and the scope of specification.

Claims (10)

1. the man-machine interaction method based on how interactive situation, it is characterised in that including:
Step S1, obtains mutual emotionally comprising at least one in the information that user currently inputs, the information that the user currently inputs Border;
Step S2, according at least one described interactive situation, the one or more interactive situations prestored of correspondence triggering are obtained The interactive situation of triggering, the interactive situation prestored includes multiple nodes, the different task of each node correspondence;
Step S3, the information currently inputted according to the user, analysis obtains current dialogue states, the current dialogue states root The userspersonal information included in the information currently inputted according to the user obtains;
Step S4 is more in the interactive situation of the triggering with reference to the current dialogue states according to the interactive situation of the triggering Switched between individual node, complete the corresponding task of each node, realize human-computer interaction.
2. the man-machine interaction method according to claim 1 based on how interactive situation, it is characterised in that described to prestore Interactive situation obtained by the method for human-edited or machine learning.
3. the man-machine interaction method according to claim 1 based on how interactive situation, it is characterised in that also include, in advance The interactive situation of storage updates step:
The text message that user repeatedly inputs is obtained, and obtains the corresponding multiple interactions of text message that the user repeatedly inputs Situation;
The multiple interactive situation is combined, multiple new interactive situations, the number of the multiple new interactive situation are formed Quantity of the amount more than the multiple interactive situation.
4. the man-machine interaction method according to claim 1 based on how interactive situation, it is characterised in that the step S2, According at least one described interactive situation, the one or more interactive situations prestored of correspondence triggering obtain triggering mutually emotionally Border, be specially:
Obtain the interactive situation editor demand information at least one described interactive situation;
Interactive situation editor demand information at least one described interactive situation is entered with the interactive situation prestored Row matching, obtains triggering interactive situation.
5. the man-machine interaction method according to claim 1 based on how interactive situation, it is characterised in that
The step S3, be specially:
Obtain the dialog information before feedback information, the data information of individual subscriber, preference information and the user of user, the use The feedback information at family is the corresponding feedback information of information that the user currently inputs;
According to the dialog information before the feedback information of the user, the data information of individual subscriber, preference information and user, knot The information that the user currently inputs is closed, analysis obtains current dialogue states.
6. the man-machine interaction method according to claim 1 based on how interactive situation, it is characterised in that
The step S4, be specially:
Obtain at least one node in the interactive situation of the triggering, the different task of each node correspondence;
According at least one node in the interactive situation of the triggering, with reference to the current dialogue states, the triggering is completed mutual Emotionally the corresponding task of at least one node in border, realizes human-computer interaction.
7. the human-computer interaction system based on how interactive situation, it is characterised in that including:
Data obtaining module, for obtaining in the information that user currently inputs, the information that the user currently inputs comprising at least One interactive situation;
Interactive situation trigger module, for according at least one described interactive situation, correspondence triggering is one or more to be prestored Interactive situation, obtain triggering interactive situation, the interactive situation prestored includes multiple nodes, each node correspondence Different tasks;
Current dialogue states module, for the information currently inputted according to the user, analysis obtains current dialogue states, described The userspersonal information included in the information that current dialogue states are currently inputted according to the user obtains;
Human-computer interaction module, it is interactive in the triggering with reference to the current dialogue states for according to the interactive situation of the triggering Switched between multiple nodes in situation, complete the corresponding task of each node, realize human-computer interaction.
8. the human-computer interaction system according to claim 7 based on how interactive situation, it is characterised in that
Also include, the interactive situation update module prestored, specifically for:
The text message that user repeatedly inputs is obtained, and obtains the corresponding multiple interactions of text message that the user repeatedly inputs Situation;
The multiple interactive situation is combined, multiple new interactive situations, the number of the multiple new interactive situation are formed Quantity of the amount more than the multiple interactive situation.
9. the human-computer interaction system according to claim 7 based on how interactive situation, it is characterised in that
The interactive situation trigger module, specifically for:
Obtain the interactive situation editor demand information at least one described interactive situation;
Interactive situation editor demand information at least one described interactive situation is entered with the interactive situation prestored Row matching, obtains triggering interactive situation.
10. the human-computer interaction system according to claim 7 based on how interactive situation, it is characterised in that
The current dialogue states module, specifically for:
Obtain the dialog information before feedback information, the data information of individual subscriber, preference information and the user of user, the use The feedback information at family is the corresponding feedback information of information that the user currently inputs;
According to the dialog information before the feedback information of the user, the data information of individual subscriber, preference information and user, knot The information that the user currently inputs is closed, analysis obtains current dialogue states.
CN201710121335.2A 2017-03-02 2017-03-02 Answer method and system based on how interactive situation editor Pending CN106991124A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710121335.2A CN106991124A (en) 2017-03-02 2017-03-02 Answer method and system based on how interactive situation editor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710121335.2A CN106991124A (en) 2017-03-02 2017-03-02 Answer method and system based on how interactive situation editor

Publications (1)

Publication Number Publication Date
CN106991124A true CN106991124A (en) 2017-07-28

Family

ID=59412633

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710121335.2A Pending CN106991124A (en) 2017-03-02 2017-03-02 Answer method and system based on how interactive situation editor

Country Status (1)

Country Link
CN (1) CN106991124A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108829654A (en) * 2018-05-30 2018-11-16 互影科技(北京)有限公司 A kind of interaction script editor's method and apparatus
CN110209792A (en) * 2019-06-13 2019-09-06 苏州思必驰信息科技有限公司 Talk with painted eggshell generation method and system

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103000052A (en) * 2011-09-16 2013-03-27 上海先先信息科技有限公司 Man-machine interactive spoken dialogue system and realizing method thereof
CN104809103A (en) * 2015-04-29 2015-07-29 北京京东尚科信息技术有限公司 Man-machine interactive semantic analysis method and system
WO2016065020A2 (en) * 2014-10-21 2016-04-28 Robert Bosch Gmbh Method and system for automation of response selection and composition in dialog systems
CN105912692A (en) * 2016-04-22 2016-08-31 华讯方舟科技有限公司 Intelligent voice dialogue method and apparatus
CN106055662A (en) * 2016-06-02 2016-10-26 竹间智能科技(上海)有限公司 Emotion-based intelligent conversation method and system
CN106096717A (en) * 2016-06-03 2016-11-09 北京光年无限科技有限公司 Information processing method and system towards intelligent robot
US20160365091A1 (en) * 2015-06-11 2016-12-15 International Business Machines Corporation Analysis of Professional-Client Interactions
CN106448670A (en) * 2016-10-21 2017-02-22 竹间智能科技(上海)有限公司 Dialogue automatic reply system based on deep learning and reinforcement learning

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103000052A (en) * 2011-09-16 2013-03-27 上海先先信息科技有限公司 Man-machine interactive spoken dialogue system and realizing method thereof
WO2016065020A2 (en) * 2014-10-21 2016-04-28 Robert Bosch Gmbh Method and system for automation of response selection and composition in dialog systems
CN104809103A (en) * 2015-04-29 2015-07-29 北京京东尚科信息技术有限公司 Man-machine interactive semantic analysis method and system
US20160365091A1 (en) * 2015-06-11 2016-12-15 International Business Machines Corporation Analysis of Professional-Client Interactions
CN105912692A (en) * 2016-04-22 2016-08-31 华讯方舟科技有限公司 Intelligent voice dialogue method and apparatus
CN106055662A (en) * 2016-06-02 2016-10-26 竹间智能科技(上海)有限公司 Emotion-based intelligent conversation method and system
CN106096717A (en) * 2016-06-03 2016-11-09 北京光年无限科技有限公司 Information processing method and system towards intelligent robot
CN106448670A (en) * 2016-10-21 2017-02-22 竹间智能科技(上海)有限公司 Dialogue automatic reply system based on deep learning and reinforcement learning

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
罗广清: "基于中文文本情感分类的情感宣泄系统的研究与实现", 《中国优秀硕士论文全文数据库 信息科技辑》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108829654A (en) * 2018-05-30 2018-11-16 互影科技(北京)有限公司 A kind of interaction script editor's method and apparatus
CN110209792A (en) * 2019-06-13 2019-09-06 苏州思必驰信息科技有限公司 Talk with painted eggshell generation method and system
CN110209792B (en) * 2019-06-13 2021-07-06 思必驰科技股份有限公司 Method and system for generating dialogue color eggs

Similar Documents

Publication Publication Date Title
CN105807933B (en) A kind of man-machine interaction method and device for intelligent robot
Cassell et al. Fully embodied conversational avatars: Making communicative behaviors autonomous
WO2019169854A1 (en) Human-computer interaction method, and interactive robot
CN110413841A (en) Polymorphic exchange method, device, system, electronic equipment and storage medium
CN110286756A (en) Method for processing video frequency, device, system, terminal device and storage medium
CN110400251A (en) Method for processing video frequency, device, terminal device and storage medium
CN105704013A (en) Context-based topic updating data processing method and apparatus
CN106020488A (en) Man-machine interaction method and device for conversation system
CN106599998A (en) Method and system for adjusting response of robot based on emotion feature
CN107894831A (en) A kind of interaction output intent and system for intelligent robot
CN107480766B (en) Method and system for content generation for multi-modal virtual robots
CN109240670A (en) Modular software development methodology, system, equipment and medium
CN105798918A (en) Interactive method and device for intelligent robot
CN107807734A (en) A kind of interaction output intent and system for intelligent robot
CN105912530A (en) Intelligent robot-oriented information processing method and system
CN105843382A (en) Man-machine interaction method and device
CN106503786A (en) Multi-modal exchange method and device for intelligent robot
CN109948151A (en) The method for constructing voice assistant
CN109032328A (en) A kind of exchange method and system based on visual human
CN106126636B (en) A kind of man-machine interaction method and device towards intelligent robot
CN110347817A (en) Intelligent response method and device, storage medium, electronic equipment
CN109800295A (en) The emotion session generation method being distributed based on sentiment dictionary and Word probability
CN106471572A (en) A kind of method of simultaneous voice and virtual acting, system and robot
CN106991124A (en) Answer method and system based on how interactive situation editor
Abdul‐Massih et al. Motion style retargeting to characters with different morphologies

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170728