CN108228764A - A kind of single-wheel dialogue and the fusion method of more wheel dialogues - Google Patents
A kind of single-wheel dialogue and the fusion method of more wheel dialogues Download PDFInfo
- Publication number
- CN108228764A CN108228764A CN201711440063.9A CN201711440063A CN108228764A CN 108228764 A CN108228764 A CN 108228764A CN 201711440063 A CN201711440063 A CN 201711440063A CN 108228764 A CN108228764 A CN 108228764A
- Authority
- CN
- China
- Prior art keywords
- wheel
- dialogue
- user
- information
- dialogues
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
- G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
Abstract
The present invention discloses the fusion method of a kind of single-wheel dialogue and more wheel dialogues, the method can adapt to judgement conversational traffic type and call corresponding dialogue mode automatically automatically, dialogue wheel number is reduced in the range of error permission, solves user's specific demand and provisional demand.Single-wheel dialogue and more wheel dialogue fusions are got up, provide answer or the leading question for meeting user view in real time according to the true intention of user session, it avoids that the dialogue of some topic is caused to discuss number is excessive due to model of place flexibility deficiency, seriously affects user experience；It simultaneously can be quick to solve user's variable demand in the case where not influencing steady demand question and answer in the specific demand appearance of user and the provisional change of demand.
Description
Technical field
The present invention relates to the fusion methods of a kind of single-wheel dialogue and more wheel dialogues, belong to artificial intelligence interaction field.
Background technology
Intelligent human-machine interaction system needs to have single-wheel dialogue ability and more wheel dialogue abilities, and single-wheel dialogue is used for solution by no means
The simple question and answer of service class ask questions；More wheel dialogues solve the traffic issues of deep layer complexity.But most man-machine interactive system
Single-wheel conversational system and more wheel conversational systems are often kept apart, and single-wheel are often occurred and are talked with not smart enough and take turns dialogue sometimes more
Excessively complicated phenomenon.Same Scene problem expansion can not be carried out in single-wheel dialog procedure by often occurring user in real scene
Property question and answer, similarly mostly wheel dialog procedures in user suddenly determine terminate dialogue or think to obtain opinions or suggestions as early as possible, but more
Wheel dialogue when dialog model information is imperfect, system can repeatedly guiding property question and answer and prompting, can not or be not easy to spirit
The adjustment for the flow that engages in the dialogue livingly.The above situation has seriously affected the user experience of intelligent human-machine interaction system.
User is possible to just originally belong to the carry out Continuation question and answer of single-wheel conversation content, needs more wheel dialogue technoloygs at this time
Technical support is carried out, while user in mostly wheel dialog procedure terminates dialogue or tied as early as possible in the range of accuracy permission suddenly
Beam is talked with, and single-wheel dialogue mechanism is needed to be supported.The single-wheel of intelligent human-machine interaction system is talked with and what more wheels were talked with organically blends
It can effectively solve the above problems.
Research emphasis is often placed on more wheel dialogues by now common man-machine interactive system, is carried out after getting customer problem
Natural language processing obtains internal information and implicit information, while is engaged in the dialogue scene modeling using contextual information, according to
The information lacked in the information and preset model that are had been provided in dialog procedure carries out targetedly question and answer.As long as in preset model
Information collection work do not complete, system can be continuously generated guided bone question sentence and return to user.Due to model of place flexibility
It is excessive that deficiency may cause the dialogue of some topic to discuss number, seriously affects user experience.Simultaneously user specific demand occur with
And the provisional change of demand is required to man-machine interactive system with elastic mechanism, in the case where not influencing steady demand question and answer,
User's variable demand can quickly be solved.
Invention content
In view of the drawbacks of the prior art, the present invention provides the fusion method of a kind of single-wheel dialogue and more wheel dialogues, can be automatic
It adapts to judgement conversational traffic type and calls corresponding dialogue mode automatically, dialogue wheel number is reduced in the range of error permission,
Solve user's specific demand and provisional demand.
In order to solve the technical problem, the technical solution adopted by the present invention is：What a kind of single-wheel dialogue and more wheels were talked with
Fusion method includes the following steps：S01 multi-modal input information input by user), is obtained；S02）, input information is carried out it is real
The extraction of body information and structuring slicing treatment obtain structured text information；S03）, based on structured text information extraction use
Family is intended to；S04）, based on historical information, structured text information and user view, fusion single-wheel conversational system and more wheels pair
Telephone system, adaptive judgement generate the dialogue mode for meeting user's true intention；S05）, based on user view and dialogue mode,
Session operational scenarios are built, obtain structuring leading question or answer；S06）, given birth to based on structuring leading question or answer
Into corresponding natural language problem or answer.
Single-wheel of the present invention is talked with and the fusion methods of more wheel dialogues, and in step S04, single-wheel is completed by caching mechanism
Dialogue and the fusion of more wheel dialogues, the profile history information of the more wheel dialogues of caching mechanism caching and the key message of single-wheel dialogue.
Single-wheel dialogue of the present invention and the mostly fusion method of wheel dialogue, when user switchs to more wheel dialogues by single-wheel dialogue,
The key message of caching single-wheel dialogue first, then more wheel dialog informations based on user carry out judging again for user view again,
Front and rear dialogue is found as unified scene by being intended to decision algorithm, is expanded as more wheel dialogues, is provided and is met user and really anticipate
The reasonability of figure is recommended；If front and rear dialogue is non-unified scene, new round dialogue is directly opened.
Single-wheel of the present invention is talked with and the fusion methods of more wheel dialogues, when user switchs to single-wheel dialogue more by taking turns dialogue,
It is immediately finished more wheels to talk with, more wheel dialogues are converted to single-wheel talks with and empty cache information.
Single-wheel of the present invention dialogue and the fusion methods of more wheel dialogues, multi-modal input information include voice, text and
Touch action.
Single-wheel dialogue of the present invention and the fusion method of more wheel dialogues, obtain multi-modal input information input by user
When, touch action is converted into text message, using based on offline or high in the clouds voice using pre-defined action command collection
Voice document is converted to natural language text or directly receives text message input by user by identification technology, and is supported more
The highest priority of typing while modal data, wherein touch action, phonetic entry priority are taken second place, text input priority
It is minimum.
Single-wheel of the present invention is talked with and the fusion methods of more wheel dialogues, and in step S02, nature is completed by morphological analysis
Participle and the part of speech label of language text, obtain the word collection of natural language text, retain all information of text；Then it utilizes
Syntactic analysis technology obtains grammer dependence and the modified relationship between key message, extracts crucial letter in natural language text
Breath；The gradually layer semantic analysis of word, phrase and sentence is completed in semantic analysis based on semantic network, is finally completed natural language
Structuring slicing treatment obtains structured text information.
Single-wheel of the present invention dialogue and the fusion methods of more wheel dialogues, in step S03, using decision tree or random gloomy
The machine learning method of woods extracts user view, with reference to system history information using structured text information and interrogative sentence type
And current dialog information is realized and is mapped between structured text information and multiple business scenarios.
Single-wheel dialogue of the present invention and the fusion method of more wheel dialogues when extracting user view, carry out multilayer intention and sentence
It is disconnected.
Single-wheel of the present invention is talked with and the fusion methods of more wheel dialogues, in step S05, based on Bayes algorithm inference machines
System and base module interior business information generating structure leading question or answer, Bayes algorithm inference mechanisms are based on
User view and dialogue mode carry out Deep Semantics understanding, build session operational scenarios, and automated reasoning obtains answer or guided bone
The key message of question sentence, and then promote interactive process.
Single-wheel of the present invention is talked with and the fusion methods of more wheel dialogues, flexible dynamic using random algorithm in step S06
The problem of state generating structure leading question or answer correspond to or answer, avoid answer format from ossifing.
Beneficial effects of the present invention：The method of the invention can adapt to judgement conversational traffic type and call phase automatically automatically
The dialogue mode answered reduces dialogue wheel number in the range of error permission, solves user's specific demand and provisional demand.I.e.
The present invention gets up single-wheel dialogue and more wheel dialogue fusions, is provided in real time according to the true intention of user session and meets user view
Answer or leading question, avoid that the dialogue of some topic is caused to discuss number is excessive due to model of place flexibility deficiency, sternly
Ghost image rings user experience；Simultaneously in the specific demand appearance of user and the provisional change of demand, it can be needed not influence to stablize
It is quick to solve user's variable demand in the case of seeking question and answer.
Description of the drawings
Fig. 1 is the flow chart of the present invention.
Specific embodiment
The present invention is further illustrated in the following with reference to the drawings and specific embodiments.
Embodiment 1
The present embodiment discloses the fusion method of a kind of single-wheel dialogue and more wheel dialogues, includes the following steps：
S01）, obtain the multi-modal input information of user；
In the present embodiment, input information is including but not limited to voice, text, touch action.
When obtaining multi-modal user's input information, contact action is converted into text envelope using pre-defined action command collection
Voice document is converted to natural language text again or directly by breath using the speech recognition technology based on offline either high in the clouds
Receive text message input by user；And typing while input module support multi-modal data.Wherein contact action
Highest priority, phonetic entry priority are taken second place, and text input priority is minimum.
S02）, the extraction of entity information and structuring slicing treatment are carried out to input information, obtain structured text information；
Based on specific input finish message analysis, structuring, Slice and the various dimensions definition of finishing service are specifically complete
Extraction and multi-level multidimensional scale designation into entity information.
In the present embodiment, the participle of natural language text is completed by morphological analysis and part of speech marks, obtains natural language
The word collection of text retains all information of text；Then syntactic analysis technology, such as finite graph analytic approach, phrase knot are utilized
Structure analysis, complete grammer, local grammer and dependency analysis etc. obtain the grammer dependence between key message, modified relationship
Etc., extract key message in natural language text；Semantic analysis completes word, phrase and sentence gradually based on semantic network
Layer semantic analysis.The structuring slicing treatment of natural language is finally completed, obtains structured text information.
S03）, using machine learning algorithm, structured text information and interrogative sentence type is utilized to extract user view；
In the present embodiment, machine learning algorithm includes but not limited to decision tree, random forests algorithm etc..With reference to system history information
And current dialog information is realized and is mapped between structured text information and multiple business scenarios.
In the present embodiment, when extracting user view, carry out multilayer and be intended to judge, can effectively avoid sorted in business scenario
The problem of being intended to excessively refinement when thin.Such as " I wants to handle endowment insurance ", at this time user be intended to endowment insurance correlation industry
Business goes where to handle.System should recommend window, be not easy carrying out refinement judgement, that is to say, that without judging endowment insurance subservice
（Such as open an account, payment, relationship transfer）.But if user proposes " handling what material is endowment insurance need ", due to endowment
It is different to insure each subservice material requested, therefore needs to refine intention.
S04）, based on historical information, structured text information and user view, adaptive judgement dialogue mode is completed
Single-wheel talks with and takes turns organically blending for conversational system more, and generation meets the dialogue mode of user's true intention；
In the present embodiment, single-wheel dialogue is completed by caching mechanism and takes turns organically blending for dialogue more, caching mechanism preserves history
Dialog information.It is with the different places of other intelligent interactive systems：The profile history information of more wheel dialogues is not only preserved, and
And preserve the key message of script single-wheel dialogue.Caching mechanism is to realize single more wheel dialogue fusion premises.
In the present embodiment, when user switchs to more wheel dialogues by single-wheel dialogue, the key message of single-wheel dialogue is cached first, so
More wheel dialog informations based on user carry out judging again for user view again afterwards, find that front and rear dialogue is by being intended to decision algorithm
Unification scene is expanded and is talked with for more wheels, provides the reasonability recommendation for meeting user's true intention；If front and rear dialogue is non-
Unified scene then directly opens new round dialogue.
Such as during user's progress single-wheel dialogue, " today, how is weather " is that single-wheel is talked with, and " today is fine for robot response
My god, have gentle breeze ".Entire dialogue has been completed, and cache Weather information this moment, if user continues to put question to " should what to wear "
When, judging again for user view is carried out first, finds that front and rear dialogue for unified scene, is then opened up by being intended to decision algorithm
It opens up to take turns dialogue more, recommends to the reasonability for meeting user's true intention.Otherwise new round dialogue is directly opened.
In the present embodiment, when user switchs to single-wheel dialogue by taking turns dialogue more, more wheel dialogues are immediately finished, dialogue turn will be taken turns more
Single-wheel is changed to talk with and empty cache information.
For example user take turns when talking with more, unexpected side-track, it, also should be immediately even if mostly wheel dialogue problem is not over
Terminate.Specifically.Such as " I have a headache where should go ", system respond " you have cough or fever ".Then it uses
Family ask a question suddenly " toilet is at which " more wheel dialogues should be immediately finished at this time and will take turns dialogue more and be converted to single-wheel talk with and empty
Cache information.
The single-wheel dialogue of this method and more wheel dialogue syncretizing mechanism broken between the dialogue of interactive system different mode every
It cuts off from, the mutual conversion between single-wheel dialogue and more wheel dialogues is flexibly realized based on user session information in dialog procedure, is enhanced
System list takes turns dialogue ability more, promotes user experience.
S05）, asked based on Bayes algorithms inference mechanism and base module interior business information generating structure guided bone
Topic or answer；
In the present embodiment, inference mechanism includes but are not limited to Bayes algorithm inference mechanisms.Bayes algorithm inference mechanisms are based on
User view and dialogue mode carry out Deep Semantics understanding, build session operational scenarios, and automated reasoning obtains answer or guided bone
The key message of question sentence, and then promote interactive process.Inference mechanism so that knowledge base record one quantity of quantity can be handled
The problem of grade or multiple orders of magnitude.
S06）, based on structuring leading question, either answer generates corresponding natural language problem or answer.Mainly
Complete structural data and unstructured processing.In the present embodiment, using random algorithm, the corresponding problem of flexible dynamic generation and answer
Case avoids answer format from ossifing.
Described above is only the basic principle and preferred embodiment of the present invention, and those skilled in the art do according to the present invention
The improvement and replacement gone out, belongs to the scope of protection of the present invention.
Claims (11)
1. a kind of single-wheel dialogue and the fusion method of more wheel dialogues, it is characterised in that：Include the following steps：S01 user), is obtained
The multi-modal input information of input；S02）, the extraction of entity information and structuring slicing treatment are carried out to input information, tied
Structure text message；S03）, based on structured text information extraction user view；S04）, based on historical information, structured text
Information and user view, fusion single-wheel conversational system and more wheel conversational systems, adaptive judgement generation meet user and really anticipate
The dialogue mode of figure；S05）, based on user view and dialogue mode, build session operational scenarios, obtain structuring leading question or
Person's answer；S06）, based on structuring leading question, either answer generates corresponding natural language problem or answer.
2. single-wheel dialogue according to claim 1 and the fusion method of more wheel dialogues, it is characterised in that：In step S04, lead to
Cross the fusion that caching mechanism completes single-wheel dialogue and more wheel dialogues, the profile history information and list of the more wheel dialogues of caching mechanism caching
Take turns the key message of dialogue.
3. single-wheel dialogue according to claim 1 or 2 and the fusion method of more wheel dialogues, it is characterised in that：User is by list
Wheel dialogue switch to cache the key message of single-wheel dialogue first when taking turns dialogue, then more wheel dialog informations based on user again
Judging again for user view is carried out, finds that front and rear dialogue for unified scene, is expanded as more wheels pair by being intended to decision algorithm
Words provide the reasonability recommendation for meeting user's true intention；If front and rear dialogue is non-unified scene, a new round is directly opened
Dialogue.
4. single-wheel dialogue according to claim 1 or 2 and the fusion method of more wheel dialogues, it is characterised in that：User is by more
When wheel dialogue switchs to single-wheel dialogue, more wheel dialogues are immediately finished, more wheel dialogues are converted to single-wheel talks with and empty cache information.
5. single-wheel dialogue according to claim 1 and the fusion method of more wheel dialogues, it is characterised in that：Multi-modal input letter
Breath includes voice, text and touch action.
6. single-wheel dialogue according to claim 5 and the fusion method of more wheel dialogues, it is characterised in that：Obtain user's input
Multi-modal input information when, using pre-defined action command collection by touch action be converted to text message, using based on from
Voice document is converted to natural language text or directly receives text input by user by the speech recognition technology in line either high in the clouds
This information, and while support multi-modal data typing, wherein touch action highest priority, the preferential level of phonetic entry
It, text input priority is minimum.
7. single-wheel dialogue according to claim 1 and the fusion method of more wheel dialogues, it is characterised in that：In step S02, lead to
It crosses morphological analysis and completes the participle of natural language text and part of speech label, obtain the word collection of natural language text, retain text
All information；Then grammer dependence and the modified relationship between key message are obtained using syntactic analysis technology, extracted
Key message in natural language text；The gradually layer semanteme point of word, phrase and sentence is completed in semantic analysis based on semantic network
Analysis is finally completed the structuring slicing treatment of natural language, obtains structured text information.
8. single-wheel dialogue according to claim 1 and the fusion method of more wheel dialogues, it is characterised in that：In step S03, adopt
With decision tree or the machine learning method of random forest, extract user using structured text information and interrogative sentence type and anticipate
Figure is realized with reference to system history information and current dialog information and is mapped between structured text information and multiple business scenarios.
9. the fusion method of the single-wheel dialogue and more wheel dialogues according to claim 1 or 8, it is characterised in that：Extract user
During intention, carry out multilayer and be intended to judge.
10. single-wheel dialogue according to claim 1 and the fusion method of more wheel dialogues, it is characterised in that：In step S05,
Based on Bayes algorithms inference mechanism and base module interior business information generating structure leading question or answer,
Bayes algorithms inference mechanism is based on user view and dialogue mode, carries out Deep Semantics understanding, builds session operational scenarios, automatically
Reasoning obtains the key message of answer or guided bone question sentence, and then promotes interactive process.
11. single-wheel dialogue according to claim 1 and the fusion method to wheel dialogue, it is characterised in that：In step S06,
Using random algorithm, the problem of flexible dynamic generation structuring leading question or answer correspond to or answer avoid answer lattice
Formula ossifys.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711440063.9A CN108228764A (en) | 2017-12-27 | 2017-12-27 | A kind of single-wheel dialogue and the fusion method of more wheel dialogues |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711440063.9A CN108228764A (en) | 2017-12-27 | 2017-12-27 | A kind of single-wheel dialogue and the fusion method of more wheel dialogues |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108228764A true CN108228764A (en) | 2018-06-29 |
Family
ID=62648919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711440063.9A Pending CN108228764A (en) | 2017-12-27 | 2017-12-27 | A kind of single-wheel dialogue and the fusion method of more wheel dialogues |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108228764A (en) |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109033277A (en) * | 2018-07-10 | 2018-12-18 | 广州极天信息技术股份有限公司 | Class brain system, method, equipment and storage medium based on machine learning |
| CN109063840A (en) * | 2018-07-10 | 2018-12-21 | 广州极天信息技术股份有限公司 | A kind of Interactive Dynamic inference method and device |
| CN109145168A (en) * | 2018-07-11 | 2019-01-04 | 广州极天信息技术股份有限公司 | A kind of expert service robot cloud platform |
| CN109146610A (en) * | 2018-07-16 | 2019-01-04 | 众安在线财产保险股份有限公司 | It is a kind of intelligently to insure recommended method, device and intelligence insurance robot device |
| 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 |
| CN109448730A (en) * | 2018-11-27 | 2019-03-08 | 广州广电运通金融电子股份有限公司 | A kind of automatic speech quality detecting method, system, device 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 |
| CN109446306A (en) * | 2018-10-16 | 2019-03-08 | 浪潮软件股份有限公司 | Task-driven multi-turn dialogue-based intelligent question and answer method |
| CN109460451A (en) * | 2018-09-29 | 2019-03-12 | 厦门快商通信息技术有限公司 | Actively obtain method, the intelligent customer service method and system of user information |
| CN109473100A (en) * | 2018-11-12 | 2019-03-15 | 四川驹马科技有限公司 | Business scenario voice man-machine interaction method and its system based on speech recognition |
| CN109710737A (en) * | 2018-12-21 | 2019-05-03 | 神思电子技术股份有限公司 | A kind of intelligent inference method based on structuralized query |
| CN109754806A (en) * | 2019-03-21 | 2019-05-14 | 问众智能信息科技（北京）有限公司 | A kind of processing method, device and the terminal of more wheel dialogues |
| CN110032633A (en) * | 2019-04-17 | 2019-07-19 | 腾讯科技（深圳）有限公司 | More wheel dialog process method, apparatus and equipment |
| CN110059170A (en) * | 2019-03-21 | 2019-07-26 | 北京邮电大学 | More wheels based on user's interaction talk with on-line training method and system |
| CN110175223A (en) * | 2019-05-29 | 2019-08-27 | 北京搜狗科技发展有限公司 | A kind of method and device that problem of implementation generates |
| 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 |
| CN111210824A (en) * | 2018-11-21 | 2020-05-29 | 深圳绿米联创科技有限公司 | Voice information processing method and device, electronic equipment and storage medium |
| CN111309914A (en) * | 2020-03-03 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Method and device for classifying multiple rounds of conversations based on multiple model results |
| CN111324712A (en) * | 2020-02-18 | 2020-06-23 | 山东汇贸电子口岸有限公司 | Dialogue reply method and server |
| CN111339283A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Method and device for providing customer service answers aiming at user questions |
| CN111428483A (en) * | 2020-03-31 | 2020-07-17 | 华为技术有限公司 | Voice interaction method and device and terminal equipment |
| CN111737442A (en) * | 2020-08-13 | 2020-10-02 | 北京福佑多多信息技术有限公司 | Intelligent customer service multi-round session management method and device |
| CN111753061A (en) * | 2019-03-27 | 2020-10-09 | 北京猎户星空科技有限公司 | Multi-turn conversation processing method and device, electronic equipment and storage medium |
| CN112530422A (en) * | 2020-11-04 | 2021-03-19 | 联想(北京)有限公司 | Response processing method, intelligent device and storage medium |
| CN114722839A (en) * | 2022-06-01 | 2022-07-08 | 阿里巴巴达摩院(杭州)科技有限公司 | Man-machine collaborative dialogue interaction system and method |
| CN114840653A (en) * | 2022-04-26 | 2022-08-02 | 北京百度网讯科技有限公司 | Dialogue processing method, device, equipment and storage medium |
| CN115238101A (en) * | 2022-09-23 | 2022-10-25 | 中国电子科技集团公司第十研究所 | Multi-engine intelligent question-answering system oriented to multi-type knowledge base |
| CN116775815A (en) * | 2022-03-07 | 2023-09-19 | 腾讯科技（深圳）有限公司 | Dialogue data processing method and device, electronic equipment and storage medium |
| CN117743557A (en) * | 2024-02-08 | 2024-03-22 | 卓智网络科技有限公司 | Intelligent customer service method, intelligent customer service device, server and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011001370A1 (en) * | 2009-06-29 | 2011-01-06 | Avraham Ben-David | Intelligent home automation |
| CN105094315A (en) * | 2015-06-25 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for smart man-machine chat based on artificial intelligence |
| CN106205612A (en) * | 2016-07-08 | 2016-12-07 | 北京光年无限科技有限公司 | Information processing method and system towards intelligent robot |
| CN107133345A (en) * | 2017-05-22 | 2017-09-05 | 北京百度网讯科技有限公司 | Exchange method and device based on artificial intelligence |
| CN107180080A (en) * | 2017-04-28 | 2017-09-19 | 北京神州泰岳软件股份有限公司 | A kind of intelligent answer method and device of many interactive modes |
-
2017
- 2017-12-27 CN CN201711440063.9A patent/CN108228764A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011001370A1 (en) * | 2009-06-29 | 2011-01-06 | Avraham Ben-David | Intelligent home automation |
| CN105094315A (en) * | 2015-06-25 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for smart man-machine chat based on artificial intelligence |
| CN106205612A (en) * | 2016-07-08 | 2016-12-07 | 北京光年无限科技有限公司 | Information processing method and system towards intelligent robot |
| CN107180080A (en) * | 2017-04-28 | 2017-09-19 | 北京神州泰岳软件股份有限公司 | A kind of intelligent answer method and device of many interactive modes |
| CN107133345A (en) * | 2017-05-22 | 2017-09-05 | 北京百度网讯科技有限公司 | Exchange method and device based on artificial intelligence |
Non-Patent Citations (1)
| Title |
|---|
| 洪增林: "服务机器人的知识表达和智能推理", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109033277A (en) * | 2018-07-10 | 2018-12-18 | 广州极天信息技术股份有限公司 | Class brain system, method, equipment and storage medium based on machine learning |
| CN109063840A (en) * | 2018-07-10 | 2018-12-21 | 广州极天信息技术股份有限公司 | A kind of Interactive Dynamic inference method and device |
| CN109145168A (en) * | 2018-07-11 | 2019-01-04 | 广州极天信息技术股份有限公司 | A kind of expert service robot cloud platform |
| CN109146610A (en) * | 2018-07-16 | 2019-01-04 | 众安在线财产保险股份有限公司 | It is a kind of intelligently to insure recommended method, device and intelligence insurance robot device |
| 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 |
| CN109460451A (en) * | 2018-09-29 | 2019-03-12 | 厦门快商通信息技术有限公司 | Actively obtain method, the intelligent customer service method and system of user information |
| 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 |
| CN109446306A (en) * | 2018-10-16 | 2019-03-08 | 浪潮软件股份有限公司 | Task-driven multi-turn dialogue-based intelligent question and answer method |
| CN109473100A (en) * | 2018-11-12 | 2019-03-15 | 四川驹马科技有限公司 | Business scenario voice man-machine interaction method and its system based on speech recognition |
| CN111210824A (en) * | 2018-11-21 | 2020-05-29 | 深圳绿米联创科技有限公司 | Voice information processing method and device, electronic equipment and storage medium |
| CN109448730A (en) * | 2018-11-27 | 2019-03-08 | 广州广电运通金融电子股份有限公司 | A kind of automatic speech quality detecting method, system, device and storage medium |
| CN109710737A (en) * | 2018-12-21 | 2019-05-03 | 神思电子技术股份有限公司 | A kind of intelligent inference method based on structuralized query |
| CN109710737B (en) * | 2018-12-21 | 2021-01-22 | 神思电子技术股份有限公司 | Intelligent reasoning method based on structured query |
| CN109754806A (en) * | 2019-03-21 | 2019-05-14 | 问众智能信息科技（北京）有限公司 | A kind of processing method, device and the terminal of more wheel dialogues |
| CN110059170A (en) * | 2019-03-21 | 2019-07-26 | 北京邮电大学 | More wheels based on user's interaction talk with on-line training method and system |
| CN110059170B (en) * | 2019-03-21 | 2022-04-26 | 北京邮电大学 | Multi-turn dialogue online training method and system based on user interaction |
| CN111753061B (en) * | 2019-03-27 | 2024-03-12 | 北京猎户星空科技有限公司 | Multi-round dialogue processing method and device, electronic equipment and storage medium |
| CN111753061A (en) * | 2019-03-27 | 2020-10-09 | 北京猎户星空科技有限公司 | Multi-turn conversation processing method and device, electronic equipment and storage medium |
| CN110032633A (en) * | 2019-04-17 | 2019-07-19 | 腾讯科技（深圳）有限公司 | More wheel dialog process method, apparatus and equipment |
| CN110032633B (en) * | 2019-04-17 | 2021-03-23 | 腾讯科技（深圳）有限公司 | Multi-turn dialogue processing method, device and equipment |
| CN110175223A (en) * | 2019-05-29 | 2019-08-27 | 北京搜狗科技发展有限公司 | A kind of method and device that problem of implementation generates |
| 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 |
| 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 |
| CN111324712A (en) * | 2020-02-18 | 2020-06-23 | 山东汇贸电子口岸有限公司 | Dialogue reply method and server |
| CN111309914A (en) * | 2020-03-03 | 2020-06-19 | 支付宝(杭州)信息技术有限公司 | Method and device for classifying multiple rounds of conversations based on multiple model results |
| CN111309914B (en) * | 2020-03-03 | 2023-05-09 | 支付宝(杭州)信息技术有限公司 | Classification method and device for multi-round conversations based on multiple model results |
| CN111428483A (en) * | 2020-03-31 | 2020-07-17 | 华为技术有限公司 | Voice interaction method and device and terminal equipment |
| CN111339283A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Method and device for providing customer service answers aiming at user questions |
| CN111339283B (en) * | 2020-05-15 | 2020-08-21 | 支付宝(杭州)信息技术有限公司 | Method and device for providing customer service answers aiming at user questions |
| CN111737442A (en) * | 2020-08-13 | 2020-10-02 | 北京福佑多多信息技术有限公司 | Intelligent customer service multi-round session management method and device |
| CN112530422A (en) * | 2020-11-04 | 2021-03-19 | 联想(北京)有限公司 | Response processing method, intelligent device and storage medium |
| CN116775815A (en) * | 2022-03-07 | 2023-09-19 | 腾讯科技（深圳）有限公司 | Dialogue data processing method and device, electronic equipment and storage medium |
| CN116775815B (en) * | 2022-03-07 | 2024-04-26 | 腾讯科技（深圳）有限公司 | Dialogue data processing method and device, electronic equipment and storage medium |
| CN114840653A (en) * | 2022-04-26 | 2022-08-02 | 北京百度网讯科技有限公司 | Dialogue processing method, device, equipment and storage medium |
| CN114840653B (en) * | 2022-04-26 | 2023-08-01 | 北京百度网讯科技有限公司 | Dialogue processing method, device, equipment and storage medium |
| CN114722839A (en) * | 2022-06-01 | 2022-07-08 | 阿里巴巴达摩院(杭州)科技有限公司 | Man-machine collaborative dialogue interaction system and method |
| CN114722839B (en) * | 2022-06-01 | 2022-10-11 | 阿里巴巴达摩院(杭州)科技有限公司 | Man-machine cooperative dialogue interaction system and method |
| CN115238101A (en) * | 2022-09-23 | 2022-10-25 | 中国电子科技集团公司第十研究所 | Multi-engine intelligent question-answering system oriented to multi-type knowledge base |
| CN117743557A (en) * | 2024-02-08 | 2024-03-22 | 卓智网络科技有限公司 | Intelligent customer service method, intelligent customer service device, server and storage medium |
| CN117743557B (en) * | 2024-02-08 | 2024-06-04 | 卓智网络科技有限公司 | Intelligent customer service method, intelligent customer service device, server and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108228764A (en) | A kind of single-wheel dialogue and the fusion method of more wheel dialogues | |
| CN108197191B (en) | A kind of scene intention interrupt method of more wheel dialogues | |
| CN110704641B (en) | Ten-thousand-level intention classification method and device, storage medium and electronic equipment | |
| US11315560B2 (en) | Method for conducting dialog between human and computer | |
| CN112100349B (en) | Multi-round dialogue method and device, electronic equipment and storage medium | |
| CN111651609A (en) | Multi-turn dialogue method and system integrating knowledge graph and emotion supervision | |
| KR20190004495A (en) | Method, Apparatus and System for processing task using chatbot | |
| CN111708869B (en) | Processing method and device for man-machine conversation | |
| JP7313455B2 (en) | speaking agent | |
| WO2017094911A1 (en) | Method for processing utterances | |
| CN111191450B (en) | Corpus cleaning method, corpus input device and computer readable storage medium | |
| CN106504768A (en) | Phone testing audio frequency classification method and device based on artificial intelligence | |
| CN111212190A (en) | Conversation management method, device and system based on conversation strategy management | |
| CN111445898B (en) | Language identification method and device, electronic equipment and storage medium | |
| CN111858854B (en) | Question-answer matching method and relevant device based on historical dialogue information | |
| CA2540557A1 (en) | Apparatus and method for model adaptation for spoken language understanding | |
| CN112860871B (en) | Natural language understanding model training method, natural language understanding method and device | |
| CN110225210A (en) | Based on call abstract Auto-writing work order method and system | |
| CN112632244A (en) | Man-machine conversation optimization method and device, computer equipment and storage medium | |
| CN106204295A (en) | Social contact method based on natural language and device | |
| CN108595609A (en) | Generation method, system, medium and equipment are replied by robot based on personage IP | |
| CN111128175B (en) | Spoken language dialogue management method and system | |
| CN115146124A (en) | Question-answering system response method and device, equipment, medium and product thereof | |
| CN114265921A (en) | Question-answer knowledge base construction method and device, equipment, medium and product thereof | |
| CN111581347B (en) | Sentence similarity matching method and device |
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: 20180629 |