CN106599998A - Method and system for adjusting response of robot based on emotion feature - Google Patents
Method and system for adjusting response of robot based on emotion feature Download PDFInfo
- Publication number
- CN106599998A CN106599998A CN201611093206.9A CN201611093206A CN106599998A CN 106599998 A CN106599998 A CN 106599998A CN 201611093206 A CN201611093206 A CN 201611093206A CN 106599998 A CN106599998 A CN 106599998A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- past
- current
- robot
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Manipulator (AREA)
- Toys (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and a system for adjusting response of a robot based on an emotion feature. The method comprises the steps of obtaining current text information and past text information input by a user; extracting feature information of the user based on the current text information and the past text information, wherein the feature information comprises user emotion feature information and user semantic feature information; obtaining robot semantic feature information, and carrying out information integration by combining with the user emotion feature information to obtain a two-side emotion feature value; and providing a response corresponding to the current text information based on the user semantic feature information and in combination with the two-side emotion feature value. According to the method and the system for adjusting the response of the robot based on the emotion feature, the user emotion feature information and the robot emotion feature information are extracted based on the current text information and the past text information in a man-machine conservation process, the user emotion feature information and the robot emotion feature information are then combined with the user semantic feature information to enable the response provided by the robot to have emotion of the robot, the man-machine conservation becomes more intelligent, and the user experience is further improved.
Description
Technical field
The present invention relates to artificial intelligence field, more particularly to interactive system field.
Background technology
In existing artificial intelligence conversational system, judge that user talks using corpus and template, conversational system
The mode that search is usually used suitably is answered to find.But, not using the emotion of user as clue adjusting back
Strategy is answered, in addition to considering user emotion, robot also should select the strategy responded based on the mood of itself.In person to person
Natural dialogue on, emotion is a key factor, the emotion that the mankind can be according to expressed by other side and itself existing emotion 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 is unable to base to the answer of user
Emotion in the text message of user input, and the emotion with reference to robot itself makes intelligent response, it is impossible to be given
Accurately answer, make user experience low.
The content of the invention
For above-mentioned technical problem, the present invention is provided a kind of method answered based on affective characteristics adjustment robot and is
System, based on the current text information during human-computer dialogue and past text message, extracts user feeling characteristic information and machine
People's emotion characteristic information, in conjunction with user's meaning of one's words characteristic information, makes emotion of the answer with robot that robot is provided, man-machine
Dialogue is more intelligent, further increases Consumer's Experience.
To solve above-mentioned technical problem, the technical scheme that the present invention is provided is：
In a first aspect, the present invention provides a kind of method for adjusting robot answer based on affective characteristics, including：
Step S1, obtains the current text information and past text message of user input；
Step S2, according to the current text information and past text message, extracts the characteristic information of the user, institute
Characteristic information is stated including user feeling characteristic information and user's meaning of one's words characteristic information；
Step S3, obtains robot affective characteristics information, with reference to the user feeling characteristic information, carries out information integration,
Both sides' affective characteristics value is obtained, the robot affective characteristics information was computed with the information of the user mutual by the past
Obtain；
Step S4, according to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, be given it is described ought be above
The corresponding answer of this information.
The invention provides a kind of adjust the method that robot is answered based on affective characteristics, its technical scheme is：First obtain
The current text information of user input and in the past text message；Then, according to the current text information and past text message,
The characteristic information of the user is extracted, the characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information；
Then, robot affective characteristics information is obtained, with reference to the user feeling characteristic information, carries out information integration, obtain both sides' feelings
Sense characteristic value, the robot affective characteristics information is to be computed what is obtained by past and the information of the user mutual；Most
Afterwards, according to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, the current text information is provided corresponding
Answer.
The present invention's adjusts the method that robot is answered based on affective characteristics, based on the current text during human-computer dialogue
Information and in the past text message, extract user feeling characteristic information and robot affective characteristics information, special in conjunction with user's meaning of one's words
Reference ceases, and makes emotion of the answer with robot that robot is provided, and human-computer dialogue is more intelligent, further increases user
Experience.
Further, step S2, specially：
According to the current text information and past text message, the current text information and in the past text message are obtained
In emotional state information, the emotional state information include current emotional states information, user go over main emotional information and
At least one in past secondary emotional information；
According to the current text information and past text message, the current text information and in the past text message are obtained
In text message, the text message includes the current text information and in the past semantics information, the key in text message
At least one in word information, proper noun information and verb information；
According to the current text information and past text message, the current text information and in the past text message are obtained
In topic information, the topic information includes that current staple of conversation information, current secondary topic information, the past staple of conversation are believed
Breath, past secondary topic information, hobby topic information and at least one in hot issue information at present；
According to the current text information and past text message, the current text information and in the past text message are obtained
In sentence pattern, tone information and language performance information, the language performance information include current dominant language behavioural information and time
Want language performance information；
According to the emotional state information, text message, topic information, sentence pattern, tone information and language performance information, carry
The characteristic information of the user is taken out, the characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information.
Further, in step S4, specially：
Data bank is obtained, multiple answers are prestored in the data bank；
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by machine learning algorithm, in institute
State and select in data bank a response as the corresponding answer of the current text information.
Further, in step S4, specially：
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by the method for logic rules, from
It is dynamic to generate the corresponding answer of the current text information：
According to the user semantic characteristic information, emotional characteristics in the semantic feature information is analyzed；
According to emotional characteristics in the semantic feature information, with reference to the mood of the robot, a kind of logical combination is formed；
According to the logical combination, automatically generate from the answer strategy pre-build by the method for logic rules described
The corresponding answer of current text information.
Further, in step S4, specially：
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by the method for machine learning, from
It is dynamic to generate the corresponding answer of the current text information：
According to the user semantic characteristic information, emotional characteristics in the semantic feature information is analyzed；
According to emotional characteristics in the semantic feature information, with reference to the mood of the robot, a kind of Response Policy is formed；
According to the Response Policy, automatically generate or select from the answer strategy pre-build by the method for machine learning
Select the corresponding answer of the generation current text information.
Second aspect, the invention provides a kind of adjust the system that robot is answered based on affective characteristics, including：
Text message acquisition module, for obtaining the current text information and past text message of user input；
Dialogue identification module, for according to the current text information and past text message, extracting the user's
Characteristic information, the characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information；
Robot emotion module, for obtaining robot affective characteristics information, with reference to the user feeling characteristic information, enters
Row information is integrated, and obtains both sides' affective characteristics value, and the robot affective characteristics information is by past and the user mutual
Information be computed obtain；
Dialogue response means, for according to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, being given
The corresponding answer of the current text information.
The a kind of of present invention offer adjusts the system that robot is answered based on affective characteristics, and its technical scheme is：First pass through
Text message acquisition module, for obtaining the current text information and past text message of user input；Then pass through dialogue to know
Other module, for according to the current text information and past text message, extracting the characteristic information of the user, the spy
Reference breath includes user feeling characteristic information and user's meaning of one's words characteristic information；Then by robot emotion module, for obtaining
Robot affective characteristics information, with reference to the user feeling characteristic information, carries out information integration, obtains both sides' affective characteristics value,
The robot affective characteristics information is to be computed what is obtained by past and the information of the user mutual；Finally by dialogue
Response means, for according to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, providing the current text
The corresponding answer of information.
The present invention's adjusts the system that robot is answered based on affective characteristics, based on the current text during human-computer dialogue
Information and in the past text message, extract user feeling characteristic information and robot affective characteristics information, special in conjunction with user's meaning of one's words
Reference ceases, and makes emotion of the answer with robot that robot is provided, and human-computer dialogue is more intelligent, further increases user
Experience.
Further, the dialogue identification module, specifically for：
According to the current text information and past text message, the current text information and in the past text message are obtained
In emotional state information, the emotional state information include current emotional states information, user go over main emotional information and
At least one in past secondary emotional information；
According to the current text information and past text message, the current text information and in the past text message are obtained
In text message, the text message includes the current text information and in the past semantics information, the key in text message
At least one in word information, proper noun information and verb information；
According to the current text information and past text message, the current text information and in the past text message are obtained
In topic information, the topic information includes that current staple of conversation information, current secondary topic information, the past staple of conversation are believed
Breath, past secondary topic information, hobby topic information and at least one in hot issue information at present；
According to the current text information and past text message, the current text information and in the past text message are obtained
In sentence pattern, tone information and language performance information, the language performance information include current dominant language behavioural information and time
Want language performance information；
According to the emotional state information, text message, topic information, sentence pattern, tone information and language performance information, carry
The characteristic information of the user is taken out, the characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information.
Further, the dialogue response means, specifically for：
Data bank is obtained, multiple answers are prestored in the data bank；
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by machine learning algorithm, in institute
State and select in data bank a response as the corresponding answer of the current text information.
Further, the dialogue response means, specifically for：
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by the method for logic rules, from
It is dynamic to generate the corresponding answer of the current text information：
According to the user semantic characteristic information, emotional characteristics in the semantic feature information is analyzed；
According to emotional characteristics in the semantic feature information, with reference to the mood of the robot, a kind of logical combination is formed；
According to the logical combination, automatically generate from the answer strategy pre-build by the method for logic rules described
The corresponding answer of current text information.
Further, the dialogue response means, specifically for：
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by the method for machine learning, from
It is dynamic to generate the corresponding answer of the current text information：
According to the user semantic characteristic information, emotional characteristics in the semantic feature information is analyzed；
According to emotional characteristics in the semantic feature information, with reference to the mood of the robot, a kind of Response Policy is formed；
According to the Response Policy, automatically generate or select from the answer strategy pre-build by the method for machine learning
Select the corresponding answer of the generation current text information.
Description of the drawings
In order to be illustrated more clearly that the specific embodiment of the invention or technical scheme of the prior art, below will be to concrete
The accompanying drawing to be used needed for embodiment or description of the prior art is briefly described.
Fig. 1 shows a kind of method for adjusting robot answer based on affective characteristics that first embodiment of the invention is provided
Flow chart；
Fig. 2 shows a kind of system for adjusting robot answer based on affective characteristics that second embodiment of the invention is provided
Schematic diagram.
Specific 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
Technical scheme is clearly illustrated, therefore is 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 method for adjusting robot answer based on affective characteristics that first embodiment of the invention is provided
Flow chart；As shown in figure 1, the embodiment of the present invention one provides a kind of method for adjusting robot answer based on affective characteristics,
Including：
Step S1, obtains the current text information and past text message of user input；
Step S2, according to current text information and past text message, extracts the characteristic information of user, characteristic information bag
Include user feeling characteristic information and user's meaning of one's words characteristic information；
Step S3, obtains robot affective characteristics information, with reference to user feeling characteristic information, carries out information integration, obtains
Both sides' affective characteristics value, robot affective characteristics information is to be computed what is obtained by the information in past and user mutual；
Step S4, according to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, provides current text information corresponding
Answer.
The invention provides a kind of adjust the method that robot is answered based on affective characteristics, its technical scheme is：First obtain
The current text information of user input and in the past text message；Then, according to current text information and past text message, extract
Go out the characteristic information of user, characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information；Then, machine is obtained
People's emotion characteristic information, with reference to user feeling characteristic information, carries out information integration, obtains both sides' affective characteristics value, machine human feelings
Sense characteristic information is to be computed what is obtained by the information in past and user mutual；Finally, according to user's meaning of one's words characteristic information, knot
Both sides' affective characteristics value is closed, the corresponding answer of current text information is given.
The present invention's adjusts the method that robot is answered based on affective characteristics, based on the current text during human-computer dialogue
Information and in the past text message, extract user feeling characteristic information and robot affective characteristics information, special in conjunction with user's meaning of one's words
Reference ceases, and makes emotion of the answer with robot that robot is provided, and human-computer dialogue is more intelligent, further increases user
Experience.
Specifically, step S2, specially：
According to current text information and past text message, the mood in current text information and in the past text message is obtained
Status information, emotional state information includes that current emotional states information, user go over main emotional information and in the past secondary mood
At least one in information；
According to current text information and past text message, the text in current text information and in the past text message is obtained
Message, text message includes semantics information, key word information, proper noun letter in current text information and in the past text message
At least one in breath and verb information；
According to current text information and past text message, the topic in current text information and in the past text message is obtained
Information, topic information includes that current staple of conversation information, current secondary topic information, past staple of conversation information, past are secondary
Topic information, hobby topic information and at least one in hot issue information at present；
According to current text information and past text message, the sentence in current text information and in the past text message is obtained
Type, tone information and language performance information, language performance information includes current dominant language behavioural information and secondary language performance
Information；
According to emotional state information, text message, topic information, sentence pattern, tone information and language performance information, extract
The characteristic information of user, characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information.
Current text information can also be combined contextual information, rewrite the information of the rewriting sentence obtained after original sentence
In being added to the source information of characteristic information extraction, with emotional state information, text message, topic information, sentence pattern, tone information and
Language performance information extracts together the characteristic information of user.
Wherein, the information for rewriting sentence is the phenomenon not enough in order to solve some sentence information.
For example：
A:You like seeing a film
B:Like.
But, B merely enters " liking ", and now information content is not enough.If according to rewriting above, will become " to like seeing
Film ", this computer-chronograph can just make more accurate judgement.
Original sentence：Retain the appearance of original sentence, allow computer capacity to access original sentence.Coordinate and rewrite sentence, more
It is fully understood by user input.
For example：
A:We will go to the cinema tomorrow
B:En En.
Now, " En En " can be rewritten into " I will go to the cinema tomorrow ".If retaining former sentence " En En ", input computer becomes
Into " En En+I go to the cinema tomorrow "；Computer it can be understood that into：See a film tomorrow+response problem.Entered by this kind of mode
And obtain more complete information.
Fully analyze the current session text message and past text conversation information of identifying user, the factor of analyzing and processing
It is more, user feeling characteristic information that extraction obtains and user's meaning of one's words characteristic information can be made more accurate, and then provide robot
Answer it is more accurate, it is more intelligent.
Specifically, in step S4, specially：
Data bank is obtained, multiple answers are prestored in data bank；
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by machine learning algorithm, select in data bank
Select one to respond as the corresponding answer of current text information.
The answer that robot is given can select a correspondence and reasonably answer by way of selecting from data bank, lead to
The related algorithm of machine learning is crossed, the answer for providing robot is more intelligent.
Specifically, in step S4, specially：
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by the method for logic rules, automatically generate and work as
The corresponding answer of front text message：
According to user semantic characteristic information, emotional characteristics in the semantic characteristic information of analysis；
According to emotional characteristics in semantic feature information, with reference to the mood of robot, a kind of logical combination is formed；
According to logical combination, from the answer strategy pre-build by the method for logic rules current text is automatically generated
The corresponding answer of information.
Citing is illustrated：
User input：" I and boyfriend say good-bye ", its meaning of one's words is characterized in that：" saying good-bye, boyfriend ", user emotion feature meeting
Deflection " sad ", it is assumed that robot mood now is " neutrality ", then " I is understood that your present sense to have higher chance to answer
Feel, I can accompany you merely to chat " etc. comfort type reply.If robot emotion is " cold and detached ", most probably respond：" En En refuels
～".
Logic rules among these are referred to：Various groups of " meaning of one's words feature " and " both sides' mood " that we pre-establish
Close, if the logical combination that " meaning of one's words feature " and " both sides' mood " in current session content is formed is dropped into by logic rules
Certain combination of the answer strategy that pre-builds of method when, will be in certain response answered and is selected in category.By patrolling
Collecting the method for rule carries out human-computer dialogue, to the answer that user is quick, intelligent, while in view of the mood of both sides, making answer more intelligence
Can, it is more humane.
Specifically, in step S4, specially：
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by the method for machine learning, automatically generate and work as
The corresponding answer of front text message：
According to user semantic characteristic information, emotional characteristics in the semantic characteristic information of analysis；
According to emotional characteristics in semantic feature information, with reference to the mood of robot, a kind of Response Policy is formed；
According to Response Policy, life is automatically generated or selected from the answer strategy pre-build by the method for machine learning
Into the corresponding answer of current text information.
Illustrate：
User input：" I and boyfriend say good-bye ", its meaning of one's words is characterized in that：" saying good-bye, boyfriend ", user emotion feature meeting
Deflection " sad ", it is assumed that robot mood now is " neutrality ", then " I is understood that your present sense to have higher chance to answer
Feel, I can accompany you merely to chat " etc. comfort type reply.If robot emotion is " cold and detached ", most probably respond：" En En refuels
～".
Machine learning algorithm among these, is through prior data collection, to allow machine learning " meaning of one's words feature " and " both sides
Mood " and the collocation of " automatically generating response " or " how selection is responded ".
Feedback is responded according to the actual response situation of every user in training data and experiment to be contrasted, if comparing result
It is inconsistent, then the parameter of machine learning is updated, and repeat iteration, when the response produced in training data and with experiment instead
When being fed back to answer uniformity to reach highest, then stop iteration, and training is completed.In the middle of the stage of test, when user is input into one
During this paper sentences, we can pass through passing data train the prediction module come being responded (can automatically generate or
Person is to select suitable response).
Answer strategy is pre-build by the method for machine learning, if " meaning of one's words feature " that include in current text information
The answer strategy that " both sides' mood " is formed, matches with certain in the answer strategy for pre-building, then can automatically generate current
The corresponding answer of text message.The answer strategy in the answer strategy for pre-building if the answer strategy for being formed does not rain
Match somebody with somebody, then the close corresponding answer of answer strategy generating current text information may be selected.By the method for machine learning, it is obtained
The a large amount of and accurate answer answered strategy, provide the user accurate intelligence.
Embodiment two
Fig. 2 shows a kind of system for adjusting robot answer based on affective characteristics that second embodiment of the invention is provided
Schematic diagram.As shown in Fig. 2 the embodiment of the present invention two provides a kind of system for adjusting robot answer based on affective characteristics
10, including：
Text message acquisition module 101, for obtaining the current text information and past text message of user input；
Dialogue identification module 102, for according to current text information and past text message, extracting the feature letter of user
Breath, characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information；
Robot emotion module 103, for obtaining robot affective characteristics information, with reference to user feeling characteristic information, enters
Row information is integrated, and obtains both sides' affective characteristics value, and robot affective characteristics information is information Jing by past and user mutual
Calculate what is obtained；
Dialogue response means 104, for according to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, provide current
The corresponding answer of text message.
The a kind of of present invention offer adjusts the system 10 that robot is answered based on affective characteristics, and its technical scheme is：First lead to
Text message acquisition module 101 is crossed, for obtaining the current text information and past text message of user input；It is right to then pass through
Words identification module 102, for according to current text information and past text message, extracting the characteristic information of user, feature letter
Breath includes user feeling characteristic information and user's meaning of one's words characteristic information；Then by robot emotion module 103, for obtaining machine
Device people's emotion characteristic information, with reference to user feeling characteristic information, carries out information integration, obtains both sides' affective characteristics value, robot
Affective characteristics information is to be computed what is obtained by the information in past and user mutual；Finally by dialogue response means 104, use
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, the corresponding answer of current text information is provided.
The present invention based on affective characteristics adjust robot answer system 10, based on human-computer dialogue during ought be above
This information and in the past text message, extract user feeling characteristic information and robot affective characteristics information, in conjunction with user's meaning of one's words
Characteristic information, makes emotion of the answer with robot that robot is provided, and human-computer dialogue is more intelligent, further increases use
Experience at family.
Specifically, identification module 102 is talked with, specifically for：
According to current text information and past text message, the mood in current text information and in the past text message is obtained
Status information, emotional state information includes that current emotional states information, user go over main emotional information and in the past secondary mood
At least one in information；
According to current text information and past text message, the text in current text information and in the past text message is obtained
Message, text message includes semantics information, key word information, proper noun letter in current text information and in the past text message
At least one in breath and verb information；
According to current text information and past text message, the topic in current text information and in the past text message is obtained
Information, topic information includes that current staple of conversation information, current secondary topic information, past staple of conversation information, past are secondary
Topic information, hobby topic information and at least one in hot issue information at present；
According to current text information and past text message, the sentence in current text information and in the past text message is obtained
Type, tone information and language performance information, language performance information includes current dominant language behavioural information and secondary language performance
Information；
According to emotional state information, text message, topic information, sentence pattern, tone information and language performance information, extract
The characteristic information of user, characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information.
Current text information can also be combined contextual information, rewrite the information of the rewriting sentence obtained after original sentence
In being added to the source information of characteristic information extraction, with emotional state information, text message, topic information, sentence pattern, tone information and
Language performance information extracts together the characteristic information of user.
Wherein, the information for rewriting sentence is the phenomenon not enough in order to solve some sentence information.
For example：
A:You like seeing a film
B:Like.
But, B merely enters " liking ", and now information content is not enough.If according to rewriting above, will become " to like seeing
Film ", this computer-chronograph can just make more accurate judgement.
Original sentence：Retain the appearance of original sentence, allow computer capacity to access original sentence.Coordinate and rewrite sentence, more
It is fully understood by user input.
For example：
A:We will go to the cinema tomorrow
B:En En.
Now, " En En " can be rewritten into " I will go to the cinema tomorrow ".If retaining former sentence " En En ", input computer becomes
Into " En En+I go to the cinema tomorrow "；Computer it can be understood that into：See a film tomorrow+response problem.Entered by this kind of mode
And obtain more complete information.
Fully analyze the current session text message and past text conversation information of identifying user, the factor of analyzing and processing
It is more, user feeling characteristic information that extraction obtains and user's meaning of one's words characteristic information can be made more accurate, and then provide robot
Answer it is more accurate, it is more intelligent.
Specifically, response means 104 are talked with, specifically for：
Data bank is obtained, multiple answers are prestored in data bank；
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by machine learning algorithm, select in data bank
Select one to respond as the corresponding answer of current text information.
The answer that robot is given can select a correspondence and reasonably answer by way of selecting from data bank, lead to
The related algorithm of machine learning is crossed, the answer for providing robot is more intelligent.
Specifically, response means 104 are talked with, specifically for：
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by the method for logic rules, automatically generate and work as
The corresponding answer of front text message：
According to user semantic characteristic information, emotional characteristics in the semantic characteristic information of analysis；
According to emotional characteristics in semantic feature information, with reference to the mood of robot, a kind of logical combination is formed；
According to logical combination, from the answer strategy pre-build by the method for logic rules current text is automatically generated
The corresponding answer of information.
Citing is illustrated：
User input：" I and boyfriend say good-bye ", its meaning of one's words is characterized in that：" saying good-bye, boyfriend ", user emotion feature meeting
Deflection " sad ", it is assumed that robot mood now is " neutrality ", then " I is understood that your present sense to have higher chance to answer
Feel, I can accompany you merely to chat " etc. comfort type reply.If robot emotion is " cold and detached ", most probably respond：" En En refuels
～".
Logic rules among these are referred to：Various groups of " meaning of one's words feature " and " both sides' mood " that we pre-establish
Close, if the logical combination that " meaning of one's words feature " and " both sides' mood " in current session content is formed is dropped into by logic rules
Certain combination of the answer strategy that pre-builds of method when, will be in certain response answered and is selected in category.By patrolling
Collecting the method for rule carries out human-computer dialogue, to the answer that user is quick, intelligent, while in view of the mood of both sides, making answer more intelligence
Can, it is more humane.
Specifically, response means 104 are talked with, specifically for：
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by the method for machine learning, automatically generate and work as
The corresponding answer of front text message：
According to user semantic characteristic information, emotional characteristics in the semantic characteristic information of analysis；
According to emotional characteristics in semantic feature information, with reference to the mood of robot, a kind of Response Policy is formed；
According to Response Policy, life is automatically generated or selected from the answer strategy pre-build by the method for machine learning
Into the corresponding answer of current text information.
It is same to illustrate：
User input：" I and boyfriend say good-bye ", its meaning of one's words is characterized in that：" saying good-bye, boyfriend ", user emotion feature meeting
Deflection " sad ", it is assumed that robot mood now is " neutrality ", then " I is understood that your present sense to have higher chance to answer
Feel, I can accompany you merely to chat " etc. comfort type reply.If robot emotion is " cold and detached ", most probably respond：" En En refuels
～".
Machine learning algorithm among these, is through prior data collection, to allow machine learning " meaning of one's words feature " and " both sides
Mood " and the collocation of " automatically generating response " or " how selection is responded ".
Feedback is responded according to the actual response situation of every user in training data and experiment to be contrasted, if comparing result
It is inconsistent, then the parameter of machine learning is updated, and repeat iteration, when the response produced in training data and with experiment instead
When being fed back to answer uniformity to reach highest, then stop iteration, and training is completed.In the middle of the stage of test, when user is input into one
During this paper sentences, we can pass through passing data train the prediction module come being responded (can automatically generate or
Person is to select suitable response).
Answer strategy is pre-build by the method for machine learning, if " meaning of one's words feature " that include in current text information
The answer strategy that " both sides' mood " is formed, matches with certain in the answer strategy for pre-building, then can automatically generate current
The corresponding answer of text message.The answer strategy in the answer strategy for pre-building if the answer strategy for being formed does not rain
Match somebody with somebody, then the close corresponding answer of answer strategy generating current text information may be selected.By the method for machine learning, it is obtained
The a large amount of and accurate answer answered strategy, provide the user accurate intelligence；The answer of robot, can be according to current " meaning of one's words, use
Family emotion, robot emotion " is responding.
Finally it should be noted that：Various embodiments above only to illustrate technical scheme, rather than a limitation；To the greatest extent
Pipe has been described in detail with reference to foregoing embodiments to the present invention, it will be understood by those within the art that：Its according to
So the technical scheme described in foregoing embodiments can be modified, either which part or all technical characteristic are entered
Row equivalent；And these modifications or replacement, do not make the essence disengaging various embodiments of the present invention technology of appropriate technical solution
The scope of scheme, it all should cover in the middle of the claim of the present invention and the scope of specification.
Claims (10)
1. the method that robot is answered is adjusted based on affective characteristics, it is characterised in that include：
Step S1, obtains the current text information and past text message of user input；
Step S2, according to the current text information and past text message, extracts the characteristic information of the user, the spy
Reference breath includes user feeling characteristic information and user's meaning of one's words characteristic information；
Step S3, obtains robot affective characteristics information, with reference to the user feeling characteristic information, carries out information integration, obtains
Both sides' affective characteristics value, the robot affective characteristics information is to be computed obtaining by past and the information of the user mutual
's；
Step S4, according to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, provides the current text letter
Cease corresponding answer.
It is 2. according to claim 1 that the method that robot is answered is adjusted based on affective characteristics, it is characterised in that
Step S2, specially：
According to the current text information and past text message, in obtaining the current text information and in the past text message
Emotional state information, the emotional state information includes that current emotional states information, user go over main emotional information and past
At least one in secondary emotional information；
According to the current text information and past text message, in obtaining the current text information and in the past text message
Text message, the text message includes semantics information, keyword letter in the current text information and in the past text message
At least one in breath, proper noun information and verb information；
According to the current text information and past text message, in obtaining the current text information and in the past text message
Topic information, the topic information include current staple of conversation information, current secondary topic information, past staple of conversation information,
Past secondary topic information, hobby topic information and at least one in hot issue information at present；
According to the current text information and past text message, in obtaining the current text information and in the past text message
Sentence pattern, tone information and language performance information, the language performance information includes current dominant language behavioural information and secondary language
Speech behavioural information；
According to the emotional state information, text message, topic information, sentence pattern, tone information and language performance information, extract
The characteristic information of the user, the characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information.
It is 3. according to claim 1 that the method that robot is answered is adjusted based on affective characteristics, it is characterised in that
In step S4, specially：
Data bank is obtained, multiple answers are prestored in the data bank；
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by machine learning algorithm, in the money
One is selected to respond as the corresponding answer of the current text information in material storehouse.
It is 4. according to claim 1 that the method that robot is answered is adjusted based on affective characteristics, it is characterised in that
In step S4, specially：
It is automatically raw by the method for logic rules with reference to both sides' affective characteristics value according to user's meaning of one's words characteristic information
Into the corresponding answer of the current text information：
According to the user semantic characteristic information, emotional characteristics in the semantic feature information is analyzed；
According to emotional characteristics in the semantic feature information, with reference to the mood of the robot, a kind of logical combination is formed；
According to the logical combination, automatically generate from the answer strategy pre-build by the method for logic rules described current
The corresponding answer of text message.
It is 5. according to claim 1 that the method that robot is answered is adjusted based on affective characteristics, it is characterised in that
In step S4, specially：
It is automatically raw by the method for machine learning with reference to both sides' affective characteristics value according to user's meaning of one's words characteristic information
Into the corresponding answer of the current text information：
According to the user semantic characteristic information, emotional characteristics in the semantic feature information is analyzed；
According to emotional characteristics in the semantic feature information, with reference to the mood of the robot, a kind of Response Policy is formed；
According to the Response Policy, life is automatically generated or selected from the answer strategy pre-build by the method for machine learning
Into the corresponding answer of the current text information.
6. the system that robot is answered is adjusted based on affective characteristics, it is characterised in that include：
Text message acquisition module, for obtaining the current text information and past text message of user input；
Dialogue identification module, for according to the current text information and past text message, extracting the feature of the user
Information, the characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information；
Robot emotion module, for obtaining robot affective characteristics information, with reference to the user feeling characteristic information, carries out letter
Breath is integrated, and obtains both sides' affective characteristics value, and the robot affective characteristics information is the letter by the past with the user mutual
Breath is computed what is obtained；
Dialogue response means, for according to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, provide described
The corresponding answer of current text information.
It is 7. according to claim 6 that the system that robot is answered is adjusted based on affective characteristics, it is characterised in that
The dialogue identification module, specifically for：
According to the current text information and past text message, in obtaining the current text information and in the past text message
Emotional state information, the emotional state information includes that current emotional states information, user go over main emotional information and past
At least one in secondary emotional information；
According to the current text information and past text message, in obtaining the current text information and in the past text message
Text message, the text message includes semantics information, keyword letter in the current text information and in the past text message
At least one in breath, proper noun information and verb information；
According to the current text information and past text message, in obtaining the current text information and in the past text message
Topic information, the topic information include current staple of conversation information, current secondary topic information, past staple of conversation information,
Past secondary topic information, hobby topic information and at least one in hot issue information at present；
According to the current text information and past text message, in obtaining the current text information and in the past text message
Sentence pattern, tone information and language performance information, the language performance information includes current dominant language behavioural information and secondary language
Speech behavioural information；
According to the emotional state information, text message, topic information, sentence pattern, tone information and language performance information, extract
The characteristic information of the user, the characteristic information includes user feeling characteristic information and user's meaning of one's words characteristic information.
It is 8. according to claim 6 that the system that robot is answered is adjusted based on affective characteristics, it is characterised in that
The dialogue response means, specifically for：
Data bank is obtained, multiple answers are prestored in the data bank；
According to user's meaning of one's words characteristic information, with reference to both sides' affective characteristics value, by machine learning algorithm, in the money
One is selected to respond as the corresponding answer of the current text information in material storehouse.
It is 9. according to claim 6 that the system that robot is answered is adjusted based on affective characteristics, it is characterised in that
The dialogue response means, specifically for：
It is automatically raw by the method for logic rules with reference to both sides' affective characteristics value according to user's meaning of one's words characteristic information
Into the corresponding answer of the current text information：
According to the user semantic characteristic information, emotional characteristics in the semantic feature information is analyzed；
According to emotional characteristics in the semantic feature information, with reference to the mood of the robot, a kind of logical combination is formed；
According to the logical combination, automatically generate from the answer strategy pre-build by the method for logic rules described current
The corresponding answer of text message.
It is 10. according to claim 6 that the system that robot is answered is adjusted based on affective characteristics, it is characterised in that
The dialogue response means, specifically for：
It is automatically raw by the method for machine learning with reference to both sides' affective characteristics value according to user's meaning of one's words characteristic information
Into the corresponding answer of the current text information：
According to the user semantic characteristic information, emotional characteristics in the semantic feature information is analyzed；
According to emotional characteristics in the semantic feature information, with reference to the mood of the robot, a kind of Response Policy is formed；
According to the Response Policy, life is automatically generated or selected from the answer strategy pre-build by the method for machine learning
Into the corresponding answer of the current text information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611093206.9A CN106599998B (en) | 2016-12-01 | 2016-12-01 | The method and system answered based on affective characteristics adjustment robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611093206.9A CN106599998B (en) | 2016-12-01 | 2016-12-01 | The method and system answered based on affective characteristics adjustment robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106599998A true CN106599998A (en) | 2017-04-26 |
| CN106599998B CN106599998B (en) | 2019-02-01 |
Family
ID=58595972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611093206.9A Active CN106599998B (en) | 2016-12-01 | 2016-12-01 | The method and system answered based on affective characteristics adjustment robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106599998B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301168A (en) * | 2017-06-01 | 2017-10-27 | 深圳市朗空亿科科技有限公司 | Intelligent robot and its mood exchange method, system |
| CN107329986A (en) * | 2017-06-01 | 2017-11-07 | 竹间智能科技（上海）有限公司 | The interactive method and device recognized based on language performance |
| CN107423364A (en) * | 2017-06-22 | 2017-12-01 | 百度在线网络技术（北京）有限公司 | Answer words art broadcasting method, device and storage medium based on artificial intelligence |
| CN108053826A (en) * | 2017-12-04 | 2018-05-18 | 泰康保险集团股份有限公司 | For the method, apparatus of human-computer interaction, electronic equipment and storage medium |
| CN109129467A (en) * | 2018-07-27 | 2019-01-04 | 南京阿凡达机器人科技有限公司 | A kind of robot interactive method and system based on cognition |
| CN109202922A (en) * | 2017-07-03 | 2019-01-15 | 北京光年无限科技有限公司 | The man-machine interaction method and device based on emotion for robot |
| WO2019098185A1 (en) * | 2017-11-16 | 2019-05-23 | 株式会社Ｎｔｔドコモ | Dialog text generation system and dialog text generation program |
| WO2020098756A1 (en) * | 2018-11-16 | 2020-05-22 | 深圳Tcl新技术有限公司 | Emotion-based voice interaction method, storage medium and terminal device |
| CN111310460A (en) * | 2018-12-12 | 2020-06-19 | Tcl集团股份有限公司 | Statement adjusting method and device |
| CN111788621A (en) * | 2018-02-27 | 2020-10-16 | 微软技术许可有限责任公司 | Personal virtual digital assistant |
| CN112000781A (en) * | 2020-07-20 | 2020-11-27 | 北京百度网讯科技有限公司 | Information processing method and device in user conversation, electronic equipment and storage medium |
| WO2021047233A1 (en) * | 2019-09-10 | 2021-03-18 | 苏宁易购集团股份有限公司 | Deep learning-based emotional speech synthesis method and device |
| CN113076407A (en) * | 2021-03-22 | 2021-07-06 | 联想(北京)有限公司 | Information processing method and device |
| CN117808011A (en) * | 2024-03-01 | 2024-04-02 | 青岛网信信息科技有限公司 | Chat robot method, medium and system with simulated emotion |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593054A (en) * | 2013-11-25 | 2014-02-19 | 北京光年无限科技有限公司 | Question-answering system combining emotion recognition and output |
| 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 |
-
2016
- 2016-12-01 CN CN201611093206.9A patent/CN106599998B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593054A (en) * | 2013-11-25 | 2014-02-19 | 北京光年无限科技有限公司 | Question-answering system combining emotion recognition and output |
| 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 |
Non-Patent Citations (1)
| 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"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301168A (en) * | 2017-06-01 | 2017-10-27 | 深圳市朗空亿科科技有限公司 | Intelligent robot and its mood exchange method, system |
| CN107329986A (en) * | 2017-06-01 | 2017-11-07 | 竹间智能科技（上海）有限公司 | The interactive method and device recognized based on language performance |
| CN107423364A (en) * | 2017-06-22 | 2017-12-01 | 百度在线网络技术（北京）有限公司 | Answer words art broadcasting method, device and storage medium based on artificial intelligence |
| CN107423364B (en) * | 2017-06-22 | 2024-01-26 | 百度在线网络技术（北京）有限公司 | Method, device and storage medium for answering operation broadcasting based on artificial intelligence |
| CN109202922A (en) * | 2017-07-03 | 2019-01-15 | 北京光年无限科技有限公司 | The man-machine interaction method and device based on emotion for robot |
| CN109202922B (en) * | 2017-07-03 | 2021-01-22 | 北京光年无限科技有限公司 | Emotion-based man-machine interaction method and device for robot |
| WO2019098185A1 (en) * | 2017-11-16 | 2019-05-23 | 株式会社Ｎｔｔドコモ | Dialog text generation system and dialog text generation program |
| JPWO2019098185A1 (en) * | 2017-11-16 | 2020-07-09 | 株式会社Ｎｔｔドコモ | Utterance sentence generation system and utterance sentence generation program |
| CN108053826A (en) * | 2017-12-04 | 2018-05-18 | 泰康保险集团股份有限公司 | For the method, apparatus of human-computer interaction, electronic equipment and storage medium |
| CN108053826B (en) * | 2017-12-04 | 2021-01-15 | 泰康保险集团股份有限公司 | Method and device for man-machine interaction, electronic equipment and storage medium |
| CN111788621A (en) * | 2018-02-27 | 2020-10-16 | 微软技术许可有限责任公司 | Personal virtual digital assistant |
| CN111788621B (en) * | 2018-02-27 | 2022-06-03 | 微软技术许可有限责任公司 | Personal virtual digital assistant |
| CN109129467B (en) * | 2018-07-27 | 2022-03-25 | 南京阿凡达机器人科技有限公司 | Robot interaction method and system based on cognition |
| CN109129467A (en) * | 2018-07-27 | 2019-01-04 | 南京阿凡达机器人科技有限公司 | A kind of robot interactive method and system based on cognition |
| WO2020098756A1 (en) * | 2018-11-16 | 2020-05-22 | 深圳Tcl新技术有限公司 | Emotion-based voice interaction method, storage medium and terminal device |
| US11640832B2 (en) | 2018-11-16 | 2023-05-02 | Shenzhen Tcl New Technology Co., Ltd. | Emotion-based voice interaction method, storage medium and terminal device using pitch, fluctuation and tone |
| CN111310460A (en) * | 2018-12-12 | 2020-06-19 | Tcl集团股份有限公司 | Statement adjusting method and device |
| WO2021047233A1 (en) * | 2019-09-10 | 2021-03-18 | 苏宁易购集团股份有限公司 | Deep learning-based emotional speech synthesis method and device |
| CN112000781A (en) * | 2020-07-20 | 2020-11-27 | 北京百度网讯科技有限公司 | Information processing method and device in user conversation, electronic equipment and storage medium |
| CN112000781B (en) * | 2020-07-20 | 2023-07-21 | 北京百度网讯科技有限公司 | Information processing method and device in user dialogue, electronic equipment and storage medium |
| CN113076407A (en) * | 2021-03-22 | 2021-07-06 | 联想(北京)有限公司 | Information processing method and device |
| CN117808011A (en) * | 2024-03-01 | 2024-04-02 | 青岛网信信息科技有限公司 | Chat robot method, medium and system with simulated emotion |
| CN117808011B (en) * | 2024-03-01 | 2024-06-04 | 青岛网信信息科技有限公司 | Chat robot method, medium and system with simulated emotion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106599998B (en) | 2019-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106599998B (en) | The method and system answered based on affective characteristics adjustment robot | |
| Zhou et al. | Emotional chatting machine: Emotional conversation generation with internal and external memory | |
| CN105334743B (en) | A kind of intelligent home furnishing control method and its system based on emotion recognition | |
| Bang et al. | Example-based chat-oriented dialogue system with personalized long-term memory | |
| Kamaruddin et al. | Cultural dependency analysis for understanding speech emotion | |
| CN109918650B (en) | Interview intelligent robot device capable of automatically generating interview draft and intelligent interview method | |
| CN105893344A (en) | User semantic sentiment analysis-based response method and device | |
| CN106776926A (en) | Improve the method and system of responsibility when robot talks with | |
| KR20140042994A (en) | Machine learning based of artificial intelligence conversation system using personal profiling information to be extracted automatically from the conversation contents with the virtual agent | |
| CN110297907A (en) | Generate method, computer readable storage medium and the terminal device of interview report | |
| KR20130128717A (en) | Conversation managemnt system and method thereof | |
| CN106855879A (en) | The robot that artificial intelligence psychology is seeked advice from music | |
| CN106815321A (en) | Chat method and device based on intelligent chat robots | |
| Shen et al. | Kwickchat: A multi-turn dialogue system for aac using context-aware sentence generation by bag-of-keywords | |
| JP7096172B2 (en) | Devices, programs and methods for generating dialogue scenarios, including utterances according to character. | |
| CN108595609A (en) | Generation method, system, medium and equipment are replied by robot based on personage IP | |
| CN106775665A (en) | The acquisition methods and device of the emotional state change information based on sentiment indicator | |
| CN107066568A (en) | The interactive method and device predicted based on user view | |
| CN110516035A (en) | A kind of man-machine interaction method and system of mixing module | |
| CN110457424A (en) | Generate method, computer readable storage medium and the terminal device of interview report | |
| CN106777364A (en) | Artificial intelligence response method and device that topic drives | |
| CN113591489B (en) | Voice interaction method and device and related equipment | |
| Miehle et al. | Estimating user communication styles for spoken dialogue systems | |
| CN117235354A (en) | User personalized service strategy and system based on multi-mode large model | |
| CN111490929A (en) | Video clip pushing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |