CN107193978A - A kind of many wheel automatic chatting dialogue methods and system based on deep learning - Google Patents
A kind of many wheel automatic chatting dialogue methods and system based on deep learning Download PDFInfo
- Publication number
- CN107193978A CN107193978A CN201710381824.1A CN201710381824A CN107193978A CN 107193978 A CN107193978 A CN 107193978A CN 201710381824 A CN201710381824 A CN 201710381824A CN 107193978 A CN107193978 A CN 107193978A
- Authority
- CN
- China
- Prior art keywords
- user
- dialogue
- entity information
- deep learning
- last round
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/40—Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/26—Techniques for post-processing, e.g. correcting the recognition result
- G06V30/262—Techniques for post-processing, e.g. correcting the recognition result using context analysis, e.g. lexical, syntactic or semantic context
- G06V30/274—Syntactic or semantic context, e.g. balancing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Machine Translation (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a kind of many wheel automatic chatting dialogue methods based on deep learning and system, wherein method includes:Based on the current input processing result of user, user is excavated using deep learning model and currently inputs intention;Currently inputted according to user intention, the chat theme of last round of dialogue and the current input processing result of user judged using deep learning model user currently input intention whether it is consistent with the chat theme of last round of dialogue and according to judged result renewal entity information, then intention and entity information are currently inputted according to user and obtains answer content from default answer database, and user is sent to by content is replied.Beneficial effect:Realize that chat robots, when carrying out continuous many wheel dialogues with user, content, the context information of epicycle dialogue and last round of dialogue can be considered simultaneously, reply more accurate content to user, lifting answer quality.
Description
Technical field
The present invention relates to intelligent chat robots field, more particularly, to a kind of many wheel automatic chattings based on deep learning
Dialogue method and system.
Background technology
In recent years, developing rapidly with artificial intelligence, chat robots also receive the extensive of academia and industrial quarters
Concern.
Chat robots are a kind of programs engaged in the dialogue by the natural language simulation mankind.
Current chat robots are broadly divided into online customer service, entertain, education, personal assistant and intelligent answer this five kinds
Class.No matter which kind of robot can to a certain extent be interacted with user.However, in current chat robot application scene
In, user still occupies leading position.User is in continuous dialogue, and the chat topic of its context has connection and supplement
Property, the characteristics of also having random is redirected between topic.Current chat robots largely stress carrying out single-wheel with user
Interaction so that robot can not obtain the true intention of user well because user chat important information may with
In dialogue before family.This chat mechanism based on single-wheel, have ignored the chat theme and scene point of the former wheels of active user
Analysis, therefore its answer returned can have certain deviation, or even return to the answer of mistake.
Talked with therefore, it is possible to carry out the chat robots of continuous many wheel dialogues with user than Most current based on single-wheel
Chat robots can more meet user's request, and its result returned also more conforms to the expection of user.
The content of the invention
It is an object of the invention to overcome above-mentioned technical deficiency, a kind of many wheel automatic chattings pair based on deep learning are proposed
Method and system are talked about, above-mentioned technical problem of the prior art is solved.
To reach above-mentioned technical purpose, technical scheme provides a kind of many wheel automatic chattings based on deep learning
Dialogue method, including:
S1, the text message for obtaining active user's input and the text message to input obtain user after carrying out word processing
Current input processing result;
S2, based on the current input processing result of the user, user is excavated using deep learning model and currently inputs meaning
Figure;
S3, judge user session whether be the first run dialogue, if not the first run dialogue then currently inputted according to the user
It is intended to, the chat theme of last round of dialogue and the current input processing result of the user judge described using deep learning model
Whether user currently inputs intention consistent with the chat theme of the last round of dialogue;
S4, from each round user input information in extract customizing messages be used as when wheel dialogue entity information, entity information
Memory cell storage entity information, the entity stored in the entity information memory cell is updated according to S3 judged result and is believed
Breath, then currently inputted according to the user be intended to and the entity information memory cell in the entity information that stores from default
Reply database and obtain answer content, and user is sent to by content is replied.
The present invention also provides a kind of many wheel automatic chatting conversational systems based on deep learning, including:
Text information processing module:Obtain the text message of active user's input and word is carried out to the text message of input
The current input processing result of user is obtained after processing;
Current input intention mining module:Based on the current input processing result of the user, come using deep learning model
Excavate user and currently input intention;
Theme judge module:Whether be first run dialogue, then used if not first run dialogue according to described if judging user session
Family currently inputs intention, the chat theme of last round of dialogue and the current input processing result of the user and uses deep learning model
To judge that it is whether consistent with the chat theme of the last round of dialogue that the user currently inputs intention;
Reply module:Customizing messages is extracted from each round user input information as the entity information that wheel is talked with is worked as, in fact
Body information memory cell storage entity information, the reality stored in the entity information memory cell is updated according to S3 judged result
Body information, then currently inputted according to the user be intended to and the entity information memory cell in the entity information that stores from pre-
If answer database obtain reply content, and by reply content be sent to user.
Compared with prior art, beneficial effects of the present invention include:Currently input according to user intention, last round of dialogue
Chat theme and the current input processing result of user judge that the input of user's epicycle chat is intended that using deep learning model
No not consistent with the chat theme of last round of dialogue, whether theme of based on context chatting unanimously updates entity information memory cell
The entity information of middle storage, then currently inputted according to user be intended to and entity information memory cell in the entity information that stores from
It is default answer database obtain reply content, and by reply content be sent to user, it is possible to achieve chat robots with
When family carries out continuous many wheel dialogues, content, the context information of epicycle dialogue and last round of dialogue can be considered simultaneously, is led to
Cross depth learning model and judge that the input of user's epicycle chat is intended to whether consistent with the chat theme of last round of dialogue, Neng Gougeng
Accurately to judge that the input of user's epicycle chat is intended to, so as to reply more accurate content to user, quality is answered in lifting,
Improve user experience.
Brief description of the drawings
Fig. 1 is a kind of many wheel automatic chatting dialogue method flow charts based on deep learning that the present invention is provided;
Fig. 2 is a kind of many wheel automatic chatting dialog system structures block diagrams based on deep learning that the present invention is provided;
Fig. 3 is the structured flowchart of theme judge module in Fig. 2.
In accompanying drawing:1st, many wheel automatic chatting conversational systems based on deep learning, 11, text information processing module, 12, when
Preceding input intention mining module, 13, theme judge module, 14, reply module, 131, last round of chat theme vector obtain single
Member, 132, user currently input the vectorial acquiring unit of intention, 133, term vector matrix and part of speech vector matrix acquiring unit, 134,
Judging unit.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
In the chat robots of single-wheel conversational mode, when user's input 1, chat robots are given according to user's input 1
Go out reply 1, when user's input 2, chat robots provide reply 2 according to user's input 2.For example, in the first round talks with, using
Family input 1 is " what day is it today ", and " Wednesday " is replied by robot, and in the second wheel dialogue, user's input 2 is " tomorrow is several
Number ", " on March 30th, 2017 " is replied by robot.
Such single-wheel conversational mode effect or more satisfactory in the simple Chat mode of question-response, however,
If correlation is very strong between the dialogue topic of wheel more than user, then robot cannot be returned by the way of single-wheel dialogue
Multiple, relatively large deviation or mistake can be produced by otherwise replying.For example, as user, next input 3 is " today ", and robot may be returned
Multiple " today is an auspicious day ", at this time robot does not consider the input of the last round of dialogue of user, and it is only according to this
The user of wheel dialogue inputs to reply, and can not so allow many wheel chats to go on well.
In order to solve this problem, chat robots need to combine the chat theme with before user talking with, user are worked as
Preceding input is replied.By considering that user currently inputs, the chat theme of the intention that currently inputs and user's history is sentenced
The true chat theme of disconnected active user, chat robots are given based on real chat theme and replied, so as to lift dialogue matter
Amount.
The invention provides a kind of many wheel automatic chatting dialogue methods based on deep learning, including:
S1, the text message for obtaining active user's input and the text message to input obtain user after carrying out word processing
Current input processing result;
S2, based on the current input processing result of user, user is excavated using deep learning model and currently inputs intention;
S3, judge user session whether be the first run dialogue, if not the first run dialogue then currently inputted according to user intention,
The chat theme of last round of dialogue and the current input processing result of user judge that user currently inputs using deep learning model
Whether consistent with the chat theme of last round of dialogue it is intended to;
S4, from each round user input information in extract customizing messages be used as when wheel dialogue entity information, entity information
Memory cell storage entity information, the entity information stored in entity information memory cell is updated according to S3 judged result, so
Currently inputted according to user afterwards and be intended to obtain from default answer database with the entity information stored in entity information memory cell
Answer content is taken, and user is sent to by content is replied.
Active user is inputted in many wheel automatic chatting dialogue methods of the present invention based on deep learning, step S1
Text message carry out word processing the step of be:
The method of the text message progress participle and part-of-speech tagging inputted to active user, participle and part-of-speech tagging is to be based on
The maximum matching method of global normalization;Such as user's input text message is " ABC ", and participle and part-of-speech tagging result are A/
A B/b C/c, wherein ABC represent the word of composition user's input, and abc represents the part of speech corresponding to user's input word, and for example
User's input text message is that " how is Wuhan weather" participle and part-of-speech tagging result be:" Wuhan/ns weather/n how/
Ryv ", wherein part of speech " ns " represent place name, " n " representation noun, and " ryv " represents predicate interrogative pronoun;Optionally, can also be
After the completion of participle and part-of-speech tagging, the word processing step of stop words is further removed, the step of removing stop words is:
After the completion of participle and part-of-speech tagging stop words in word segmentation result is filtered out using default deactivation vocabulary.
Many wheel automatic chatting dialogue methods of the present invention based on deep learning, the text currently inputted according to user
Information or the text message of last round of dialogue input, excavate user using the deep learning model of LSTM recurrent neural networks and work as
Preceding input intention or the chat theme of last round of dialogue.For example, " how is Wuhan weather for user's input text" input be intended to
Or chat theme is " weather ".User can also input voice information, it is automatic by voice messaging first after input voice information
Speech recognition is text message, then carries out other follow-up operations.
Many wheel automatic chatting dialogue methods of the present invention based on deep learning, utilize LSTM recurrent neural networks
Deep learning model excavates user and can take into account the text message of last round of dialogue input when currently inputting intention so as to excavate
Epicycle user currently inputs intention and more meets context, scene, more accurately.
Many wheel automatic chatting dialogue methods of the present invention based on deep learning, step S3 includes:
Based on the text message of the last round of dialogue input of user, the chat of last round of dialogue is excavated using deep learning model
The chat theme of last round of dialogue is simultaneously expressed as last round of dialogue chat theme vector by theme;
Currently inputted using deep learning model to excavate user after intention, user is currently inputted and is intended to indicate as user
Current input is intended to vector;
Word after participle is represented with term vector, it is with the corresponding part-of-speech tagging of part of speech vector representation word, user is current
Word after all participles and the corresponding part-of-speech tagging of word in input processing result are expressed as term vector matrix and word
Property vector matrix;
Intention vector, term vector matrix, part of speech vector matrix are currently inputted with last round of dialogue chat theme vector, user
For parameter, judge that currently input is intended that user using the deep learning model of convolutional neural networks and LSTM recurrent neural networks
It is no consistent with the chat theme of last round of dialogue.
In many wheel automatic chatting dialogue methods of the present invention based on deep learning, step S4:
Customizing messages is extracted from each round user input information as when the entity information of wheel dialogue, entity information behaviour
Name, place name, telephone number, sex, age, time etc..
According to S3 judgement knot in many wheel automatic chatting dialogue methods of the present invention based on deep learning, step S4
Fruit update entity information memory cell in store entity information the step of be:
If user currently inputs, intention is consistent with the chat theme of last round of dialogue, and the entity of last round of dialogue is believed
Entity information after the entity information that breath and epicycle are talked with is combined is believed to replace the entity of entity information memory cell storage
Breath;
If user currently inputs intention and the chat theme of last round of dialogue is inconsistent, the entity that epicycle is talked with is believed
Cease to replace the entity information of entity information memory cell storage.
In many wheel automatic chatting dialogue methods of the present invention based on deep learning, step S3:
If it is determined that user session is first run dialogue, is then currently inputted according to user and be intended to input information with user's first run
Entity information obtains from default answer database and replies content, and is sent to user by content is replied.
The present invention also provides a kind of many wheel automatic chatting conversational systems 1 based on deep learning, including:
Text information processing module 11:Obtain the text message of active user's input and style of writing is entered to the text message of input
The current input processing result of user is obtained after word processing;
Current input intention mining module 12:Based on the current input processing result of user, dug using deep learning model
Pick user currently inputs intention;
Theme judge module 13:Whether be first run dialogue, if not first run dialogue then according to user if judging user session
Current input is intended to, the chat theme of last round of dialogue and the current input processing result of user are judged using deep learning model
Whether user currently inputs intention consistent with the chat theme of last round of dialogue;
Reply module 14:Customizing messages is extracted as the entity information for working as wheel dialogue from each round user input information,
Entity information memory cell storage entity information, the entity stored in entity information memory cell is updated according to S3 judged result
Information, then currently inputs intention and the entity information stored in entity information memory cell from default answer number according to user
Obtained according to storehouse and reply content, and user is sent to by content is replied.
In many wheel automatic chatting conversational systems 1 of the present invention based on deep learning, text information processing module 11:
Participle and part-of-speech tagging are carried out to the text message that active user inputs.
Many wheel automatic chatting conversational systems 1 of the present invention based on deep learning, theme judge module 13 includes:
Last round of chat theme vector acquiring unit 131:Based on the text message of the last round of dialogue input of user, depth is used
Degree learning model excavates the chat theme of last round of dialogue and the chat theme of last round of dialogue is expressed as into last round of dialogue and chats
Its theme vector;
User currently inputs the vectorial acquiring unit 132 of intention:User is excavated using deep learning model and currently inputs meaning
After figure, user is currently inputted to be intended to indicate as user currently input intention vector;
Term vector matrix and part of speech vector matrix acquiring unit 133:Word after participle is represented with term vector, with part of speech to
Amount represents the corresponding part-of-speech tagging of word, and the word after all participles in the current input processing result of user is corresponding with word
Part-of-speech tagging be expressed as term vector matrix and part of speech vector matrix;
Judging unit 134:With last round of dialogue chat theme vector, user currently input intention vector, term vector matrix,
Part of speech vector matrix is parameter, judges that user works as using the deep learning model of convolutional neural networks and LSTM recurrent neural networks
Whether preceding input is intended to consistent with the chat theme of last round of dialogue.
Many wheel automatic chatting conversational systems 1 of the present invention based on deep learning, are replied in module 14:
If user currently inputs, intention is consistent with the chat theme of last round of dialogue, and the entity of last round of dialogue is believed
Entity information after the entity information that breath and epicycle are talked with is combined is believed to replace the entity of entity information memory cell storage
Breath;If user currently inputs intention and the chat theme of last round of dialogue is inconsistent, the entity information that epicycle is talked with is come
Replace the entity information of entity information memory cell storage.
In many wheel automatic chatting conversational systems 1 of the present invention based on deep learning, theme judge module 13:
If it is determined that user session is first run dialogue, is then currently inputted according to user and be intended to input information with user's first run
Entity information obtains from default answer database and replies content, and is sent to user by content is replied.
Compared with prior art, beneficial effects of the present invention include:Currently input according to user intention, last round of dialogue
Chat theme and the current input processing result of user judge that the input of user's epicycle chat is intended that using deep learning model
No not consistent with the chat theme of last round of dialogue, whether theme of based on context chatting unanimously updates entity information memory cell
The entity information of middle storage, then currently inputted according to user be intended to and entity information memory cell in the entity information that stores from
It is default answer database obtain reply content, and by reply content be sent to user, it is possible to achieve chat robots with
When family carries out continuous many wheel dialogues, content, the context information of epicycle dialogue and last round of dialogue can be considered simultaneously, is led to
Cross depth learning model and judge that the input of user's epicycle chat is intended to whether consistent with the chat theme of last round of dialogue, Neng Gougeng
Accurately to judge that the input of user's epicycle chat is intended to, so as to reply more accurate content to user, quality is answered in lifting,
Improve user experience.
The embodiment of present invention described above, is not intended to limit the scope of the present invention..Any basis
Various other corresponding changes and deformation that the technical concept of the present invention is made, should be included in the guarantor of the claims in the present invention
In the range of shield.
Claims (10)
1. a kind of many wheel automatic chatting dialogue methods based on deep learning, it is characterised in that including step:
S1, the text message for obtaining active user's input simultaneously carry out obtaining user after word processing current to the text message of input
Input processing result;
S2, based on the current input processing result of the user, user is excavated using deep learning model and currently inputs intention;
S3, judge user session whether be the first run dialogue, if not the first run dialogue then according to the user currently input intention,
The chat theme of last round of dialogue and the current input processing result of the user judge the user using deep learning model
Whether current input is intended to consistent with the chat theme of the last round of dialogue;
S4, the entity information that extraction customizing messages takes turns dialogue as working as from each round user input information, entity information are stored
Unit storage entity information, the entity information stored in entity information memory cell, Ran Hougen are updated according to S3 judged result
Currently inputted according to the user and be intended to obtain from default answer database with the entity information stored in entity information memory cell
Answer content is taken, and user is sent to by content is replied.
2. many wheel automatic chatting dialogue methods as claimed in claim 1 based on deep learning, it is characterised in that in step S1
To active user input text message carry out word processing the step of be:
Participle and part-of-speech tagging are carried out to the text message that the active user inputs.
3. many wheel automatic chatting dialogue methods as claimed in claim 2 based on deep learning, it is characterised in that step S3 bags
Include:
Based on the text message of the last round of dialogue input of user, the chat of the last round of dialogue is excavated using deep learning model
The chat theme of the last round of dialogue is simultaneously expressed as last round of dialogue chat theme vector by theme;
The user is excavated using deep learning model currently to input after intention, by the user currently input be intended to indicate for
User currently inputs intention vector;
Word after participle is represented with term vector, it is with the corresponding part-of-speech tagging of part of speech vector representation word, the user is current
Word after all participles and the corresponding part-of-speech tagging of word in input processing result are expressed as term vector matrix and word
Property vector matrix;
Vectorial, the described term vector matrix of intention is currently inputted with last round of dialogue chat theme vector, the user, it is described
Part of speech vector matrix is parameter, and described use is judged using the deep learning model of convolutional neural networks and LSTM recurrent neural networks
Whether family currently inputs intention consistent with the chat theme of the last round of dialogue.
4. many wheel automatic chatting dialogue methods as claimed in claim 1 based on deep learning, it is characterised in that in step S4
It is according to the step of the entity information stored in S3 judged result renewal entity information memory cell:
If it is consistent with the chat theme of the last round of dialogue that the user currently inputs intention, by the reality of last round of dialogue
Entity information after body information and the entity information of epicycle dialogue are combined replaces entity information memory cell storage entity
Information;
If the user currently inputs intention and the chat theme of the last round of dialogue is inconsistent, the reality that epicycle is talked with
Body information replaces entity information memory cell storage entity information.
5. many wheel automatic chatting dialogue methods as claimed in claim 1 based on deep learning, it is characterised in that step S3
In:
If it is determined that user session is first run dialogue, is then currently inputted according to the user and be intended to input information with user's first run
Entity information obtains from default answer database and replies content, and is sent to user by content is replied.
6. a kind of many wheel automatic chatting conversational systems based on deep learning, it is characterised in that including step:
Text information processing module:Obtain the text message of active user's input and word processing is carried out to the text message of input
After obtain the current input processing result of user;
Current input intention mining module:Based on the current input processing result of the user, excavated using deep learning model
User currently inputs intention;
Theme judge module:Whether be first run dialogue, then worked as if not first run dialogue according to the user if judging user session
Preceding input is intended to, the chat theme of last round of dialogue and the current input processing result of the user are sentenced using deep learning model
Whether the user of breaking currently inputs intention consistent with the chat theme of the last round of dialogue;
Reply module:Customizing messages is extracted from each round user input information as when the entity information of wheel dialogue, entity is believed
Memory cell storage entity information is ceased, the entity information stored in entity information memory cell is updated according to S3 judged result,
Then intention and the entity information stored in entity information memory cell are currently inputted from default answer number according to the user
Obtained according to storehouse and reply content, and user is sent to by content is replied.
7. many wheel automatic chatting conversational systems as claimed in claim 6 based on deep learning, it is characterised in that text message
In processing module:
Participle and part-of-speech tagging are carried out to the text message that the active user inputs.
8. many wheel automatic chatting conversational systems as claimed in claim 7 based on deep learning, it is characterised in that theme judges
Module includes:
Last round of chat theme vector acquiring unit:Based on the text message of the last round of dialogue input of user, deep learning is used
Model excavates the chat theme of the last round of dialogue and the chat theme of the last round of dialogue is expressed as into last round of dialogue
Chat theme vector;
User currently inputs the vectorial acquiring unit of intention:The user is excavated using deep learning model and currently inputs intention
Afterwards, the user currently input is intended to indicate and intention vector is currently inputted for user;
Term vector matrix and part of speech vector matrix acquiring unit:Word after participle is represented with term vector, with part of speech vector representation
The corresponding part-of-speech tagging of word, the word and word after all participles in the current input processing result of the user is corresponding
Part-of-speech tagging is expressed as term vector matrix and part of speech vector matrix;
Judging unit:Vectorial, the described term vector of intention is currently inputted with the last round of dialogue chat theme vector, the user
Matrix, the part of speech vector matrix are parameter, utilize convolutional neural networks and the deep learning model of LSTM recurrent neural networks
Judge whether the user currently inputs intention consistent with the chat theme of the last round of dialogue.
9. many wheel automatic chatting conversational systems as claimed in claim 6 based on deep learning, it is characterised in that reply module
In:
If it is consistent with the chat theme of the last round of dialogue that the user currently inputs intention, by the reality of last round of dialogue
Entity information after body information and the entity information of epicycle dialogue are combined replaces entity information memory cell storage entity
Information;
If the user currently inputs intention and the chat theme of the last round of dialogue is inconsistent, the reality that epicycle is talked with
Body information replaces entity information memory cell storage entity information.
10. many wheel automatic chatting conversational systems as claimed in claim 6 based on deep learning, it is characterised in that theme is sentenced
In disconnected module:
If it is determined that user session is first run dialogue, is then currently inputted according to the user and be intended to input information with user's first run
Entity information obtains from default answer database and replies content, and is sent to user by content is replied.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710381824.1A CN107193978A (en) | 2017-05-26 | 2017-05-26 | A kind of many wheel automatic chatting dialogue methods and system based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710381824.1A CN107193978A (en) | 2017-05-26 | 2017-05-26 | A kind of many wheel automatic chatting dialogue methods and system based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107193978A true CN107193978A (en) | 2017-09-22 |
Family
ID=59875986
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710381824.1A Pending CN107193978A (en) | 2017-05-26 | 2017-05-26 | A kind of many wheel automatic chatting dialogue methods and system based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107193978A (en) |
Cited By (57)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107738260A (en) * | 2017-10-27 | 2018-02-27 | 扬州制汇互联信息技术有限公司 | One kind dialogue robot system |
CN107832439A (en) * | 2017-11-16 | 2018-03-23 | 百度在线网络技术(北京)有限公司 | Method, system and the terminal device of more wheel state trackings |
CN107967304A (en) * | 2017-11-10 | 2018-04-27 | 北京众标智能科技有限公司 | Session interaction processing method, device and electronic equipment |
CN108108340A (en) * | 2017-11-28 | 2018-06-01 | 北京光年无限科技有限公司 | For the dialogue exchange method and system of intelligent robot |
CN108114469A (en) * | 2018-01-29 | 2018-06-05 | 北京神州泰岳软件股份有限公司 | Game interaction method, apparatus, terminal and game interaction model based on dialogue |
CN108376144A (en) * | 2018-01-12 | 2018-08-07 | 上海大学 | Man-machine more wheel dialogue methods that scene based on deep neural network automatically switches |
CN108415939A (en) * | 2018-01-25 | 2018-08-17 | 北京百度网讯科技有限公司 | Dialog process method, apparatus, equipment and computer readable storage medium based on artificial intelligence |
CN108920604A (en) * | 2018-06-27 | 2018-11-30 | 百度在线网络技术(北京)有限公司 | Voice interactive method and equipment |
CN108959421A (en) * | 2018-06-08 | 2018-12-07 | 三角兽(北京)科技有限公司 | Candidate replys evaluating apparatus and inquiry reverting equipment and its method, storage medium |
CN108959482A (en) * | 2018-06-21 | 2018-12-07 | 北京慧闻科技发展有限公司 | Single-wheel dialogue data classification method, device and electronic equipment based on deep learning |
CN109086329A (en) * | 2018-06-29 | 2018-12-25 | 出门问问信息科技有限公司 | Dialogue method and device are taken turns in progress based on topic keyword guidance more |
CN109241250A (en) * | 2018-07-25 | 2019-01-18 | 南京瓦尔基里网络科技有限公司 | A kind of dialogue of policing rule promotes and intention method of discrimination and system |
CN109446307A (en) * | 2018-10-16 | 2019-03-08 | 浪潮软件股份有限公司 | A kind of method for realizing dialogue management in Intelligent dialogue |
CN109461448A (en) * | 2018-12-11 | 2019-03-12 | 百度在线网络技术(北京)有限公司 | Voice interactive method and device |
CN109582767A (en) * | 2018-11-21 | 2019-04-05 | 北京京东尚科信息技术有限公司 | Conversational system processing method, device, equipment and readable storage medium storing program for executing |
CN109727041A (en) * | 2018-07-03 | 2019-05-07 | 平安科技(深圳)有限公司 | Intelligent customer service takes turns answering method, equipment, storage medium and device more |
CN109885810A (en) * | 2019-01-17 | 2019-06-14 | 平安城市建设科技(深圳)有限公司 | Nan-machine interrogation's method, apparatus, equipment and storage medium based on semanteme parsing |
CN109885652A (en) * | 2019-01-25 | 2019-06-14 | 北京奇艺世纪科技有限公司 | A kind of operation executes method, apparatus and computer readable storage medium |
WO2019118254A1 (en) * | 2017-12-15 | 2019-06-20 | Microsoft Technology Licensing, Llc | Chatbot integrating derived user intent |
CN109995642A (en) * | 2017-12-29 | 2019-07-09 | Tcl集团股份有限公司 | A kind of method and device automatically generating quickly revert, instant communicating system |
CN110019716A (en) * | 2017-12-15 | 2019-07-16 | 上海智臻智能网络科技股份有限公司 | More wheel answering methods, terminal device and storage medium |
CN110020014A (en) * | 2017-12-15 | 2019-07-16 | 上海智臻智能网络科技股份有限公司 | More wheel question and answer systems |
CN110209791A (en) * | 2019-06-12 | 2019-09-06 | 百融云创科技股份有限公司 | It is a kind of to take turns dialogue intelligent speech interactive system and device more |
CN110232108A (en) * | 2019-05-13 | 2019-09-13 | 华为技术有限公司 | Interactive method and conversational system |
CN110334254A (en) * | 2019-06-26 | 2019-10-15 | Oppo广东移动通信有限公司 | Information query method, device, terminal and storage medium |
CN110378485A (en) * | 2019-06-03 | 2019-10-25 | 广东幽澜机器人科技有限公司 | A kind of robot self study new business knowledge method and device |
CN110399456A (en) * | 2019-06-06 | 2019-11-01 | 深思考人工智能机器人科技(北京)有限公司 | A kind of method and device of problem dialogue completion |
CN110569337A (en) * | 2018-06-06 | 2019-12-13 | 国际商业机器公司 | Supporting combination of intents in a conversation |
CN110609893A (en) * | 2019-09-24 | 2019-12-24 | 大众问问(北京)信息科技有限公司 | Question-answer interaction method, device, equipment and storage medium in multi-turn conversation scene |
CN110633358A (en) * | 2018-05-31 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Method, apparatus and medium for processing robot and user session |
WO2020000147A1 (en) * | 2018-06-25 | 2020-01-02 | Microsoft Technology Licensing, Llc | Topic guiding in a conversation |
CN110659355A (en) * | 2018-06-29 | 2020-01-07 | 南京芝兰人工智能技术研究院有限公司 | Conversation control method and system |
CN110689393A (en) * | 2018-07-06 | 2020-01-14 | 阿里巴巴集团控股有限公司 | Man-machine interaction method, device, system and storage medium |
CN110717027A (en) * | 2019-10-18 | 2020-01-21 | 易小博(武汉)科技有限公司 | Multi-round intelligent question-answering method, system, controller and medium |
CN110728356A (en) * | 2019-09-17 | 2020-01-24 | 阿里巴巴集团控股有限公司 | Dialogue method and system based on recurrent neural network and electronic equipment |
WO2020020041A1 (en) * | 2018-07-27 | 2020-01-30 | 北京京东尚科信息技术有限公司 | Sentence processing method and system and electronic device |
CN110765338A (en) * | 2018-07-26 | 2020-02-07 | 北京搜狗科技发展有限公司 | Data processing method and device and data processing device |
CN110765312A (en) * | 2018-07-10 | 2020-02-07 | 阿里巴巴集团控股有限公司 | Man-machine interaction and content search method, device, equipment and storage medium |
CN110795531A (en) * | 2019-10-10 | 2020-02-14 | 卓尔智联(武汉)研究院有限公司 | Intention identification method, device and storage medium |
CN111046149A (en) * | 2018-10-12 | 2020-04-21 | 中国移动通信有限公司研究院 | Content recommendation method and device, electronic equipment and storage medium |
CN111177358A (en) * | 2019-12-31 | 2020-05-19 | 华为技术有限公司 | Intention recognition method, server, and storage medium |
CN111522933A (en) * | 2020-04-23 | 2020-08-11 | 深圳追一科技有限公司 | Conversation process control method, device, equipment and medium |
WO2020177592A1 (en) * | 2019-03-05 | 2020-09-10 | 京东方科技集团股份有限公司 | Painting question answering method and device, painting question answering system, and readable storage medium |
CN111901220A (en) * | 2019-05-06 | 2020-11-06 | 华为技术有限公司 | Method for determining chat robot and response system |
CN112256825A (en) * | 2020-10-19 | 2021-01-22 | 平安科技(深圳)有限公司 | Medical field multi-turn dialogue intelligent question-answering method and device and computer equipment |
WO2021042902A1 (en) * | 2019-09-04 | 2021-03-11 | 深圳Tcl数字技术有限公司 | User intention identification method in multi-round dialogue and related device |
CN112487158A (en) * | 2020-11-06 | 2021-03-12 | 泰康保险集团股份有限公司 | Problem positioning method and device for multi-turn conversation |
CN112527998A (en) * | 2020-12-22 | 2021-03-19 | 深圳市优必选科技股份有限公司 | Reply recommendation method, reply recommendation device and intelligent device |
CN112836028A (en) * | 2021-01-13 | 2021-05-25 | 国家电网有限公司客户服务中心 | Multi-turn dialogue method and system based on machine learning |
US11032217B2 (en) | 2018-11-30 | 2021-06-08 | International Business Machines Corporation | Reusing entities in automated task-based multi-round conversation |
CN113515604A (en) * | 2021-05-12 | 2021-10-19 | 山东浪潮科学研究院有限公司 | Method for tracking entity of chat robot |
US11423227B2 (en) | 2020-02-13 | 2022-08-23 | International Business Machines Corporation | Weak supervised abnormal entity detection |
CN115168593A (en) * | 2022-09-05 | 2022-10-11 | 深圳爱莫科技有限公司 | Intelligent dialogue management system, method and processing equipment capable of self-learning |
CN115293132A (en) * | 2022-09-30 | 2022-11-04 | 腾讯科技(深圳)有限公司 | Conversation processing method and device of virtual scene, electronic equipment and storage medium |
CN111026843B (en) * | 2019-12-02 | 2023-03-14 | 北京智乐瑟维科技有限公司 | Artificial intelligent voice outbound method, system and storage medium |
US12002459B2 (en) | 2021-02-24 | 2024-06-04 | International Business Machines Corporation | Autonomous communication initiation responsive to pattern detection |
US12021800B2 (en) | 2018-06-25 | 2024-06-25 | Microsoft Technology Licensing, Llc | Topic guiding in a conversation |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101075435A (en) * | 2007-04-19 | 2007-11-21 | 深圳先进技术研究院 | Intelligent chatting system and its realizing method |
CN106095834A (en) * | 2016-06-01 | 2016-11-09 | 竹间智能科技(上海)有限公司 | Intelligent dialogue method and system based on topic |
CN106599196A (en) * | 2016-12-14 | 2017-04-26 | 竹间智能科技(上海)有限公司 | Artificial intelligence conversation method and system |
CN106649739A (en) * | 2016-12-23 | 2017-05-10 | 深圳市空谷幽兰人工智能科技有限公司 | Multi-round interactive information inheritance recognition method, apparatus and interactive system |
CN106683672A (en) * | 2016-12-21 | 2017-05-17 | 竹间智能科技(上海)有限公司 | Intelligent dialogue method and system based on emotion and semantics |
-
2017
- 2017-05-26 CN CN201710381824.1A patent/CN107193978A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101075435A (en) * | 2007-04-19 | 2007-11-21 | 深圳先进技术研究院 | Intelligent chatting system and its realizing method |
CN106095834A (en) * | 2016-06-01 | 2016-11-09 | 竹间智能科技(上海)有限公司 | Intelligent dialogue method and system based on topic |
CN106599196A (en) * | 2016-12-14 | 2017-04-26 | 竹间智能科技(上海)有限公司 | Artificial intelligence conversation method and system |
CN106683672A (en) * | 2016-12-21 | 2017-05-17 | 竹间智能科技(上海)有限公司 | Intelligent dialogue method and system based on emotion and semantics |
CN106649739A (en) * | 2016-12-23 | 2017-05-10 | 深圳市空谷幽兰人工智能科技有限公司 | Multi-round interactive information inheritance recognition method, apparatus and interactive system |
Non-Patent Citations (4)
Title |
---|
余涛,余彬: "《智能空间》", 31 May 2011, 浙江工商大学出版社 * |
李海生: "《知识管理技术与应用》", 30 April 2012, 北京邮电大学出版社 * |
范立荣: "《现代秘书工作手册》", 30 September 2012, 首都经济贸易大学出版社 * |
隋志军: "《化工数值计算与MATLAB》", 31 March 2015, 华东理工大学出版社 * |
Cited By (83)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107738260A (en) * | 2017-10-27 | 2018-02-27 | 扬州制汇互联信息技术有限公司 | One kind dialogue robot system |
CN107738260B (en) * | 2017-10-27 | 2023-06-06 | 扬州制汇互联信息技术有限公司 | Dialogue robot system |
CN107967304A (en) * | 2017-11-10 | 2018-04-27 | 北京众标智能科技有限公司 | Session interaction processing method, device and electronic equipment |
CN107832439A (en) * | 2017-11-16 | 2018-03-23 | 百度在线网络技术(北京)有限公司 | Method, system and the terminal device of more wheel state trackings |
CN107832439B (en) * | 2017-11-16 | 2019-03-08 | 百度在线网络技术(北京)有限公司 | Method, system and the terminal device of more wheel state trackings |
US10664755B2 (en) | 2017-11-16 | 2020-05-26 | Baidu Online Network Technology (Beijing) Co., Ltd. | Searching method and system based on multi-round inputs, and terminal |
CN108108340A (en) * | 2017-11-28 | 2018-06-01 | 北京光年无限科技有限公司 | For the dialogue exchange method and system of intelligent robot |
CN108108340B (en) * | 2017-11-28 | 2021-07-23 | 北京光年无限科技有限公司 | Dialogue interaction method and system for intelligent robot |
US11200506B2 (en) | 2017-12-15 | 2021-12-14 | Microsoft Technology Licensing, Llc | Chatbot integrating derived user intent |
CN110020014A (en) * | 2017-12-15 | 2019-07-16 | 上海智臻智能网络科技股份有限公司 | More wheel question and answer systems |
CN110019716A (en) * | 2017-12-15 | 2019-07-16 | 上海智臻智能网络科技股份有限公司 | More wheel answering methods, terminal device and storage medium |
WO2019118254A1 (en) * | 2017-12-15 | 2019-06-20 | Microsoft Technology Licensing, Llc | Chatbot integrating derived user intent |
CN109995642A (en) * | 2017-12-29 | 2019-07-09 | Tcl集团股份有限公司 | A kind of method and device automatically generating quickly revert, instant communicating system |
CN108376144B (en) * | 2018-01-12 | 2021-10-12 | 上海大学 | Man-machine multi-round conversation method for automatic scene switching based on deep neural network |
CN108376144A (en) * | 2018-01-12 | 2018-08-07 | 上海大学 | Man-machine more wheel dialogue methods that scene based on deep neural network automatically switches |
CN108415939A (en) * | 2018-01-25 | 2018-08-17 | 北京百度网讯科技有限公司 | Dialog process method, apparatus, equipment and computer readable storage medium based on artificial intelligence |
CN108415939B (en) * | 2018-01-25 | 2021-04-16 | 北京百度网讯科技有限公司 | Dialog processing method, device and equipment based on artificial intelligence and computer readable storage medium |
CN108114469A (en) * | 2018-01-29 | 2018-06-05 | 北京神州泰岳软件股份有限公司 | Game interaction method, apparatus, terminal and game interaction model based on dialogue |
CN110633358A (en) * | 2018-05-31 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Method, apparatus and medium for processing robot and user session |
CN110569337A (en) * | 2018-06-06 | 2019-12-13 | 国际商业机器公司 | Supporting combination of intents in a conversation |
CN108959421A (en) * | 2018-06-08 | 2018-12-07 | 三角兽(北京)科技有限公司 | Candidate replys evaluating apparatus and inquiry reverting equipment and its method, storage medium |
CN108959482B (en) * | 2018-06-21 | 2022-01-21 | 北京慧闻科技(集团)有限公司 | Single-round dialogue data classification method and device based on deep learning and electronic equipment |
CN108959482A (en) * | 2018-06-21 | 2018-12-07 | 北京慧闻科技发展有限公司 | Single-wheel dialogue data classification method, device and electronic equipment based on deep learning |
WO2020000147A1 (en) * | 2018-06-25 | 2020-01-02 | Microsoft Technology Licensing, Llc | Topic guiding in a conversation |
US12021800B2 (en) | 2018-06-25 | 2024-06-25 | Microsoft Technology Licensing, Llc | Topic guiding in a conversation |
CN108920604B (en) * | 2018-06-27 | 2019-08-13 | 百度在线网络技术(北京)有限公司 | Voice interactive method and equipment |
US10984793B2 (en) | 2018-06-27 | 2021-04-20 | Baidu Online Network Technology (Beijing) Co., Ltd. | Voice interaction method and device |
CN108920604A (en) * | 2018-06-27 | 2018-11-30 | 百度在线网络技术(北京)有限公司 | Voice interactive method and equipment |
CN110659355A (en) * | 2018-06-29 | 2020-01-07 | 南京芝兰人工智能技术研究院有限公司 | Conversation control method and system |
CN109086329A (en) * | 2018-06-29 | 2018-12-25 | 出门问问信息科技有限公司 | Dialogue method and device are taken turns in progress based on topic keyword guidance more |
CN109086329B (en) * | 2018-06-29 | 2021-01-05 | 出门问问信息科技有限公司 | Topic keyword guide-based multi-turn conversation method and device |
CN109727041A (en) * | 2018-07-03 | 2019-05-07 | 平安科技(深圳)有限公司 | Intelligent customer service takes turns answering method, equipment, storage medium and device more |
CN109727041B (en) * | 2018-07-03 | 2023-04-18 | 平安科技(深圳)有限公司 | Intelligent customer service multi-turn question and answer method, equipment, storage medium and device |
CN110689393B (en) * | 2018-07-06 | 2022-08-02 | 阿里巴巴集团控股有限公司 | Man-machine interaction method, device, system and storage medium |
CN110689393A (en) * | 2018-07-06 | 2020-01-14 | 阿里巴巴集团控股有限公司 | Man-machine interaction method, device, system and storage medium |
CN110765312A (en) * | 2018-07-10 | 2020-02-07 | 阿里巴巴集团控股有限公司 | Man-machine interaction and content search method, device, equipment and storage medium |
CN109241250A (en) * | 2018-07-25 | 2019-01-18 | 南京瓦尔基里网络科技有限公司 | A kind of dialogue of policing rule promotes and intention method of discrimination and system |
CN110765338A (en) * | 2018-07-26 | 2020-02-07 | 北京搜狗科技发展有限公司 | Data processing method and device and data processing device |
WO2020020041A1 (en) * | 2018-07-27 | 2020-01-30 | 北京京东尚科信息技术有限公司 | Sentence processing method and system and electronic device |
CN111046149A (en) * | 2018-10-12 | 2020-04-21 | 中国移动通信有限公司研究院 | Content recommendation method and device, electronic equipment and storage medium |
CN109446307A (en) * | 2018-10-16 | 2019-03-08 | 浪潮软件股份有限公司 | A kind of method for realizing dialogue management in Intelligent dialogue |
CN109582767B (en) * | 2018-11-21 | 2024-05-17 | 北京京东尚科信息技术有限公司 | Dialogue system processing method, device, equipment and readable storage medium |
CN109582767A (en) * | 2018-11-21 | 2019-04-05 | 北京京东尚科信息技术有限公司 | Conversational system processing method, device, equipment and readable storage medium storing program for executing |
US11032217B2 (en) | 2018-11-30 | 2021-06-08 | International Business Machines Corporation | Reusing entities in automated task-based multi-round conversation |
CN109461448A (en) * | 2018-12-11 | 2019-03-12 | 百度在线网络技术(北京)有限公司 | Voice interactive method and device |
CN109885810A (en) * | 2019-01-17 | 2019-06-14 | 平安城市建设科技(深圳)有限公司 | Nan-machine interrogation's method, apparatus, equipment and storage medium based on semanteme parsing |
CN109885652A (en) * | 2019-01-25 | 2019-06-14 | 北京奇艺世纪科技有限公司 | A kind of operation executes method, apparatus and computer readable storage medium |
CN111666006A (en) * | 2019-03-05 | 2020-09-15 | 京东方科技集团股份有限公司 | Method and device for drawing question and answer, drawing question and answer system and readable storage medium |
WO2020177592A1 (en) * | 2019-03-05 | 2020-09-10 | 京东方科技集团股份有限公司 | Painting question answering method and device, painting question answering system, and readable storage medium |
CN111901220A (en) * | 2019-05-06 | 2020-11-06 | 华为技术有限公司 | Method for determining chat robot and response system |
CN111901220B (en) * | 2019-05-06 | 2021-12-03 | 华为技术有限公司 | Method for determining chat robot and response system |
CN110232108A (en) * | 2019-05-13 | 2019-09-13 | 华为技术有限公司 | Interactive method and conversational system |
CN110232108B (en) * | 2019-05-13 | 2023-02-03 | 华为技术有限公司 | Man-machine conversation method and conversation system |
CN110378485B (en) * | 2019-06-03 | 2021-05-11 | 广东幽澜机器人科技有限公司 | Robot self-learning new business knowledge method and device |
CN110378485A (en) * | 2019-06-03 | 2019-10-25 | 广东幽澜机器人科技有限公司 | A kind of robot self study new business knowledge method and device |
CN110399456A (en) * | 2019-06-06 | 2019-11-01 | 深思考人工智能机器人科技(北京)有限公司 | A kind of method and device of problem dialogue completion |
CN110209791B (en) * | 2019-06-12 | 2021-03-26 | 百融云创科技股份有限公司 | Multi-round dialogue intelligent voice interaction system and device |
CN110209791A (en) * | 2019-06-12 | 2019-09-06 | 百融云创科技股份有限公司 | It is a kind of to take turns dialogue intelligent speech interactive system and device more |
CN110334254A (en) * | 2019-06-26 | 2019-10-15 | Oppo广东移动通信有限公司 | Information query method, device, terminal and storage medium |
WO2021042902A1 (en) * | 2019-09-04 | 2021-03-11 | 深圳Tcl数字技术有限公司 | User intention identification method in multi-round dialogue and related device |
CN110728356A (en) * | 2019-09-17 | 2020-01-24 | 阿里巴巴集团控股有限公司 | Dialogue method and system based on recurrent neural network and electronic equipment |
CN110728356B (en) * | 2019-09-17 | 2023-08-04 | 创新先进技术有限公司 | Dialogue method and system based on cyclic neural network and electronic equipment |
CN110609893A (en) * | 2019-09-24 | 2019-12-24 | 大众问问(北京)信息科技有限公司 | Question-answer interaction method, device, equipment and storage medium in multi-turn conversation scene |
CN110795531A (en) * | 2019-10-10 | 2020-02-14 | 卓尔智联(武汉)研究院有限公司 | Intention identification method, device and storage medium |
CN110795531B (en) * | 2019-10-10 | 2023-01-20 | 卓尔智联(武汉)研究院有限公司 | Intention identification method, device and storage medium |
CN110717027A (en) * | 2019-10-18 | 2020-01-21 | 易小博(武汉)科技有限公司 | Multi-round intelligent question-answering method, system, controller and medium |
CN111026843B (en) * | 2019-12-02 | 2023-03-14 | 北京智乐瑟维科技有限公司 | Artificial intelligent voice outbound method, system and storage medium |
CN111177358A (en) * | 2019-12-31 | 2020-05-19 | 华为技术有限公司 | Intention recognition method, server, and storage medium |
CN111177358B (en) * | 2019-12-31 | 2023-05-12 | 华为技术有限公司 | Intention recognition method, server and storage medium |
US11423227B2 (en) | 2020-02-13 | 2022-08-23 | International Business Machines Corporation | Weak supervised abnormal entity detection |
CN111522933A (en) * | 2020-04-23 | 2020-08-11 | 深圳追一科技有限公司 | Conversation process control method, device, equipment and medium |
CN112256825A (en) * | 2020-10-19 | 2021-01-22 | 平安科技(深圳)有限公司 | Medical field multi-turn dialogue intelligent question-answering method and device and computer equipment |
WO2021189921A1 (en) * | 2020-10-19 | 2021-09-30 | 平安科技(深圳)有限公司 | Intelligent question answering method and apparatus for multi-round dialog in medical field, and computer device |
CN112487158B (en) * | 2020-11-06 | 2023-05-05 | 泰康保险集团股份有限公司 | Multi-round dialogue problem positioning method and device |
CN112487158A (en) * | 2020-11-06 | 2021-03-12 | 泰康保险集团股份有限公司 | Problem positioning method and device for multi-turn conversation |
CN112527998A (en) * | 2020-12-22 | 2021-03-19 | 深圳市优必选科技股份有限公司 | Reply recommendation method, reply recommendation device and intelligent device |
CN112836028A (en) * | 2021-01-13 | 2021-05-25 | 国家电网有限公司客户服务中心 | Multi-turn dialogue method and system based on machine learning |
US12002459B2 (en) | 2021-02-24 | 2024-06-04 | International Business Machines Corporation | Autonomous communication initiation responsive to pattern detection |
CN113515604A (en) * | 2021-05-12 | 2021-10-19 | 山东浪潮科学研究院有限公司 | Method for tracking entity of chat robot |
CN113515604B (en) * | 2021-05-12 | 2023-06-20 | 山东浪潮科学研究院有限公司 | Chatting robot entity tracking method |
CN115168593A (en) * | 2022-09-05 | 2022-10-11 | 深圳爱莫科技有限公司 | Intelligent dialogue management system, method and processing equipment capable of self-learning |
CN115293132A (en) * | 2022-09-30 | 2022-11-04 | 腾讯科技(深圳)有限公司 | Conversation processing method and device of virtual scene, electronic equipment and storage medium |
WO2024066920A1 (en) * | 2022-09-30 | 2024-04-04 | 腾讯科技(深圳)有限公司 | Processing method and apparatus for dialogue in virtual scene, and electronic device, computer program product and computer storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107193978A (en) | A kind of many wheel automatic chatting dialogue methods and system based on deep learning | |
CN105512228B (en) | A kind of two-way question and answer data processing method and system based on intelligent robot | |
US10438586B2 (en) | Voice dialog device and voice dialog method | |
CN105704013B (en) | Topic based on context updates data processing method and device | |
CN106777018B (en) | Method and device for optimizing input sentences in intelligent chat robot | |
CN106469554B (en) | A kind of adaptive recognition methods and system | |
CN105355200B (en) | System and method for directly training and modifying robot interactive content | |
CN106020488A (en) | Man-machine interaction method and device for conversation system | |
CN110059169B (en) | Intelligent robot chat context implementation method and system based on corpus labeling | |
US20200233908A1 (en) | Interactive system and computer program therefor | |
CN111191450A (en) | Corpus cleaning method, corpus entry device and computer-readable storage medium | |
WO2021135457A1 (en) | Recurrent neural network-based emotion recognition method, apparatus, and storage medium | |
KR20160029895A (en) | Apparatus and method for recommending emotion-based character | |
CN116303949B (en) | Dialogue processing method, dialogue processing system, storage medium and terminal | |
US20100106789A1 (en) | Chatting System, Method And Apparatus For Virtual Pet | |
CN108595609A (en) | Generation method, system, medium and equipment are replied by robot based on personage IP | |
CN116049360A (en) | Intelligent voice dialogue scene conversation intervention method and system based on client image | |
CN108304561B (en) | A kind of semantic understanding method, equipment and robot based on finite data | |
CN115309877A (en) | Dialog generation method, dialog model training method and device | |
CN111199149A (en) | Intelligent statement clarifying method and system for dialog system | |
CN112488239A (en) | Method and apparatus for artificial intelligence based computer-aided uniform system | |
CN107103083A (en) | A kind of method that robot realizes intelligent session | |
CN113360001A (en) | Input text processing method and device, electronic equipment and storage medium | |
CN116168119A (en) | Image editing method, image editing device, electronic device, storage medium, and program product | |
CN113569017B (en) | Model processing 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170922 |