CN109446306A - A kind of intelligent answer method of more wheels dialogue of task based access control driving - Google Patents
A kind of intelligent answer method of more wheels dialogue of task based access control driving Download PDFInfo
- Publication number
- CN109446306A CN109446306A CN201811202665.5A CN201811202665A CN109446306A CN 109446306 A CN109446306 A CN 109446306A CN 201811202665 A CN201811202665 A CN 201811202665A CN 109446306 A CN109446306 A CN 109446306A
- Authority
- CN
- China
- Prior art keywords
- dialogue
- user
- wheels
- task
- access control
- 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
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The invention discloses a kind of intelligent answer methods of more wheels dialogue of task based access control driving, specific method includes carrying out data preparation for different tasks, intent classifier model and element extraction model are obtained by training, pushes method of the progress of every wheel dialogue to complete intelligent answer by taking turns dialogue management mechanism and decision-making mechanism more；Wherein intent classifier model and element extraction model, for analyzing the question sentence of user or the intention and key element of answer content；More wheel dialogue management mechanism and decision-making mechanism effectively assist user to complete to talk with around more wheels of task for the optimal movement by should constantly be taken in next step according to current state decision.A kind of intelligent answer method of more wheels dialogue of task based access control driving of the invention is compared to the prior art, realize that the more wheels for automatically initiating guidance and limiting in range are talked with, the probability of success for improving human-computer interaction can satisfy people for quickly and accurately obtaining the demand of information.
Description
Technical field
The invention belongs to field of human-computer interaction, are related to natural language processing, information management, question answering system etc., especially relate to
And a kind of more wheel dialogue methods and system of task based access control driving.
Background technique
Intelligent Answer System is the automatic machine that can answer any natural language form problem, for specified enquirement, is led to
Analysis semantic information is crossed, so that correct answer is found out in extensive true online text, rather than keyword search engine
The list that several webpages are constituted is returned like that.An important function is more wheels based on context session operational scenarios in intelligent answer
One of interactive and its difficult point.
In practical applications, intelligent Answer System is not simple question-response, and may be complicated Diversification Type knowledge.
Wherein, dialogue management (Dialog Management, DM) controls interactive process, DM according to conversation history information,
It determines currently to the reaction of user.
Existing most more wheel session interaction systems are mostly to pre-define system mode and system acting set；It is being
When system operation, according to the state of current system, selected most from system acting set by a series of strategies or statistical model
One optimal system acting is exported.But there is the Task session of tree hierarchy dependence for each system acting
System, the solution that existing major part takes turns session interaction system more are unsatisfactory.For example, in telecommunications industry, for problem
" broadband troubleshooting ", standard response is that whether guidance inquiry or inquiry user shut down arrearage first, after user response, then
According to the different situation of user, further multiple conditions such as error code, equipment state of guidance inquiry user, could finally be determined
Handle scheme.
And by more wheel session interaction systems of Manual definition's rule, it is complex in task customization, and be easy to appear
The conflict of a plurality of rule；Statistics conversational system based on enhancing study can be learned automatically under the premise of having sufficient training corpus
This tree-like dependence is practised, but corpus obtains hardly possible, and the content comprehensibility learnt is poor, it is difficult to control.
Summary of the invention
The present invention provides a kind of intelligent answer methods of more wheels dialogue of task based access control driving in view of the above problems, mainly pair
Different types of task carries out data preparation, training obtains intent classifier model and element extraction model, provides more wheel dialogue pipes
Reason mechanism and decision-making mechanism complete the intelligent answer of single task or multitask.
The technical solution adopted by the present invention to solve the technical problems is: what a kind of more wheels of task based access control driving were talked with
Intelligent answer method carries out data preparation for different tasks, obtains intent classifier model by training and element extracts mould
Type pushes method of the progress of every wheel dialogue to complete intelligent answer by taking turns dialogue management mechanism and decision-making mechanism more；
Wherein intent classifier model and element extraction model, for analyze user question sentence or answer content intention and be critical to
Element；
More wheel dialogue management mechanism and decision-making mechanism, for by should constantly be taken in next step according to current state decision
Optimal movement effectively assists user to complete to talk with around more wheels of task.
Further, preferred method is,
Intent classifier model and element extraction model are obtained by training, the training includes judging user by logistic regression
Intention whether shift；Specific method is the degree of correlation for comprehensively considering the same task context, by related single feature
Whether the distributed similar feature vector as logistic regression classification of cosine phase Sihe, be intended to shift for judging.
Further, preferred method is that single feature includes TF-IDF, card side, comentropy；Single feature
Basis using Bi-LSTM method training carry out Entity recognition.
Further, preferred method is that more wheel dialogue management mechanism and decision-making mechanism are with user spoken utterances
Element is that conversation mechanism is established in driving；Conversation mechanism includes two kinds:
Single task takes turns dialogue more, and when the element user of the task is not known or provides, data are not full-time, and machine guides user complete
It is provided at element；
Multiple tasks mixing carries out more wheel dialogues, when there is task nest phenomenon, when the rhetorical question number of same problem is more than to use
When the setting value of family, a upper unclosed task is returned to.
Further, preferred method is that key element is classified as to the word slot of entity type first, is identified by word slot
With multiple inquiry, clarification, the accurate concern key point for obtaining user of confirmation movement；
Different tasks is attributed to different classes of intention, passes through intention assessment and the dialogue purpose of determining user.
A kind of intelligent Answer System of more wheels dialogue of task based access control driving, the intelligent Answer System to know accordingly
Know database based on, including natural language processing module, dialogue management module, problem semantic understanding module, answer retrieval obtain
Modulus block and knowledge base component update module；
Natural language processing module, for being pre-processed to user's input problem and knowledge base；
Dialogue management module, the challenge for context question sentence are handled；
Problem semantic understanding module, for carrying out semantic understanding to single problem；
Answer retrieval obtains module, for obtaining problem answers；
Knowledge base component update module is used for more new knowledge base, so that the better organization knowledge of knowledge base, more rapidly prepares retrieval
Answer.
Further, preferred structure is that natural language processing module includes keyword extracting unit, domain lexicon acquisition
Unit, customer problem element extraction unit；
Keyword extracting unit is marked for inputting problem and knowledge base progress Chinese word segmentation to user with female, so as to key
The extraction of word；
Domain lexicon acquiring unit, for extracting the entity and new word discovery of knowledge base, to obtain domain lexicon；
Customer problem element extraction unit carries out syntactic analysis and semantic character labeling for inputting problem to user, to obtain
Take the Subject, Predicate and Object and agent word denoting the receiver of an action of customer problem.
Further, preferred structure is that dialogue management module includes clause's split cells, problem clarification unit, problem
Question closely unit and context recognition unit；
Clause's split cells, for being split to problem when once inputting multiple problems；
Problem clarifies unit, for when the question sentence of problem is fuzzy to be understood, to problem secondary clearing again；
Problem questions closely unit, for questioning closely to problem and achieving the purpose that answer when problem lacks essential elements；
Context recognition unit, for being identified to context when problem is related to context of co-text；
Problem semantic understanding module, the problem of for by determining user, identification user puts question to and is intended to and the problem of to lacking
Based on context ingredient reverts to semantic complete problem.
Further, preferred structure is knowledge base component update module, for increasing ontology extraction, neck for knowledge base
Domain word extracts, relationship is extracted and the function of inference rule component.
Further, preferred structure is that intelligent Answer System further includes expansion connection module.
A kind of intelligent answer method of more wheels dialogue of task based access control driving of the invention is compared to the prior art, beneficial to imitate
Fruit is as follows:
1, more wheel conversational systems of task-driven type need every wheel to talk with the intention and key message of clear user, pass through system master
It is dynamic to propose inquiry to guide user to select；When user responds, intelligent Answer System increasing in semantic understanding is needed
Addition of constraints condition enables intelligent Answer System to be understood in the node that process is likely to be breached automatically, to guarantee understanding
Correctness.
2, the dialogue purpose that user is determined by intention assessment, it is quasi- by Entity recognition and repeatedly inquiry, clarification, confirmation etc.
The key point for really obtaining user's concern completes the decision and propulsion of every wheel dialogue by exclusive dialogue management mechanism, thus real
It now automatically initiates guidance and limits more wheels dialogue in range, ensure that the progress of man-machine talk effectively, friendly.
3, the probability of success for improving human-computer interaction can satisfy people for quickly and accurately obtaining the demand of information.
Detailed description of the invention
The following further describes the present invention with reference to the drawings.
Attached drawing 1 is a kind of functional block diagram of the intelligent answer method of more wheels dialogue of task based access control driving.
Specific embodiment
Natural language processing (NLP) is a subdomains of artificial intelligence, is dedicated to enabling a computer to understand and locating
Human language is managed, makes understanding of the computer closer to the mankind to language, it is intended to extract information in text data, transport on text
Row model extracts entity.Deep learning enables us to write program to execute such as language translation, semantic understanding and text
The work such as abstract.Natural language understanding NLU: it completes to parse the semanteme of text, extracts key message, such as entity, intention etc..
Spatial term NLG: the natural language text of response is generated for the input of user.Dialogue management: dialog procedure is completed
State controls (tracking), data management, context management (dialog strategy).
More wheels dialogue for task-driven realizes dialogue state tracking, key in complicated guidance and interaction flow
Information extraction, dialog strategy guide and are applied to intelligent Answer System, have important value.When user is with specific purpose
It such as makes a reservation, book tickets, user demand is more complicated, there is many restrictive conditions, it may be necessary to which a point more wheels are stated.On the one hand,
User constantly can modify or improve the demand of oneself in dialog procedure, on the other hand, when the demand of the statement of user is inadequate
When specific or clear, machine can also help user to find satisfied result by inquiry, clarification or confirmation.Work as user
When the demand of statement is not clear enough, machine can side by the more wheel dialogue management mechanism of itself to inquire, clarify or confirm
Formula helps user to find satisfied as a result, can be answered with accurate, succinct natural language or user is guided to complete demand.Task
Driving more wheel conversational systems need every wheel to talk with the intention and key message of clear user, actively propose to inquire by system
To guide user to select；When user responds, intelligent Answer System is needed to increase constraint condition in semantic understanding,
Intelligent Answer System is set to be understood in the node that process is likely to be breached automatically, to guarantee the correctness understood.
The present invention is a kind of intelligent answer method of more wheels dialogue of task based access control driving, and this method includes ownership goal shape
State maintenance, decision and language understanding, wherein further relating to the key technologies such as natural language processing, Knowledge Extraction, machine learning；This hair
The bright dialogue purpose that user is determined by intention assessment is used by the accurate acquisition such as Entity recognition and multiple inquiry, clarification, confirmation
The key point of family concern, the decision and propulsion of every wheel dialogue are completed by exclusive dialogue management mechanism, to realize automatic hair
It plays guidance and limits more wheels dialogue in range, ensure that the progress of man-machine talk effectively, friendly.
The present invention will be further explained below with reference to the attached drawings and specific examples.
Embodiment 1:
A kind of intelligent answer method of more wheels dialogue of task based access control driving of the invention is branch with existing artificial intelligence technology
Support, the comprehensive question answering system based on structural data, the question answering system based on free text and is asked based on " problem answers to "
The core technology in system and other implementations is answered, can support the upper layer applications such as chat, personal assistant, network customer service；By melting
Magnanimity isomery hypermedia data is closed, the data warehouse of intelligent Answer System is pooled；With cores such as entity, event, document, relationships
Based on element, knowledge mapping is constructed.Intelligent response system has first had to data, and data may come from internet and crawl,
It can be existing knowledge base (FAQ) or specific corpus, this relates to the source of data, acquisition, excavation, storage
Deng design.
A kind of core of the intelligent Answer System of more wheels dialogue of task based access control driving is analysis layer, is divided at natural language
Manage (pretreatment) module, dialogue management module, problem semantic understanding module, answer retrieval acquisition module and construction of knowledge base
Update module 5 is most of, in the case where knowledge data has had, can form an intelligent answer system by this 5 modules
System.
Natural language processing NLP module: the module belongs to preprocessing module, mainly to user input problem and knowledge base into
Row pretreatment, such as Chinese word segmentation, part-of-speech tagging, use for subsequent keyword extraction；Extract the entity and neologisms of corpus
It was found that obtaining domain lexicon；By syntactic analysis and semantic character labeling, the Subject, Predicate and Object of customer problem is obtained, agent word denoting the receiver of an action (is applied
Thing: grammatically refer to the main body of movement, that is, sending movement or changed persons or things.Word denoting the receiver of an action: grammatically refer to movement
Object, that is, the persons or things dominated by movement) etc..
Dialogue management module: the module belongs to the challenge processing of context: if problem once inputs multiple problems, needing
Carry out clause's fractionation；Question sentence is fuzzy to be understood, problem secondary clearing again is needed；Problem lack must element, need to question closely and reach
To answer purpose；Problem is related to context of co-text, needs context identification etc..
Problem semantic understanding module: first to single problem carry out semantic understanding: as determine user be problem or chat
It；What is asked is which class business or classification problem, convenient for quickly positioning；The intention that identification user asks, actually or consulting purchase
Deng；To ingredient the problem of lacking, semantic complete problem is based on context reverted to, convenient for retrieval answer.Deep Semantics analysis
Mainly understand the real semantic of problem and handle challenge, multiple problems are split, it is extensive based on context to carry out default sentence
Multiple and intention understands, can extract semantic rules for a variety of ways to put questions, carry out rule match, carries out similarity to the result of retrieval
It calculates, finds out optimum answer.
Answer retrieval obtains module: the module is mainly that answer obtains module, if knowledge base is FAQ, is then needed to problem
Repeated, or problem normalized into FAQ library standard problem, in the case where, can directly according to keyword retrieval,
The result of return carries out similarity calculation, and answer sequence finally returns that answer；For example knowledge base then needs to carry out semantic retrieval,
And carry out certain reasoning；For example document then needs to carry out automatic abstract, finds answer.
Construction of knowledge base update module: building knowledge base can better organization knowledge, more rapidly prepare retrieval answer, and
FAQ is combined, and question answering system is made to be applicable in various corpus, and is not limited solely to FAQ, needs to include that ontology extracts, domain term mentions
Take, relationship extract, inference rule building etc. functions.
The present invention also provides the expansion interface module for receiving new technology in bottom, can support richer upper layer application.
In addition, the present invention also protects a kind of intelligent answer method of more wheels dialogue of task based access control driving, certainly with user
Task names, the element of upload of definition mark corpus and the text feature of dialogue corpus is trained, and form intention assessment mould
Type and element extraction model, for analyzing the intention and key element of user's question sentence or answer content.The wherein text that training uses
Eigen not only used the features such as TF-IDF, card side, comentropy, also comprehensively consider the correlation of the same task context
Degree uses the distributed similar feature vector classified as logistic regression of cosine phase Sihe of above several single features, to sentence
Whether disconnected intention shifts.Entity recognition is separately carried out using the training of Bi-LSTM method on the basis of these features.
The cosine similarity calculated between vector is the traditional method of Similarity measures for vector space model.It is remaining
Details are not described herein for string similarity algorithm, and (personalized search of Journal of Software, 2003, Vol.14, NO.5 Cempetency-based education is calculated
It is described in method).
More wheel dialogue management mechanism and decision-making mechanism, for by should constantly be adopted in next step according to current state decision
The optimal movement taken effectively assists user to complete to talk with around more wheels of task.
More wheel dialogue management mechanism and decision-making mechanism are to establish conversation mechanism with the element of user spoken utterances for driving；
Conversation mechanism includes two kinds:
Single task takes turns dialogue more, and when the element user of the task is not known or provides, data are not full-time, and machine guides user complete
It is provided at element；
Multiple tasks mixing carries out more wheel dialogues, when there is task nest phenomenon, when the rhetorical question number of same problem is more than to use
When the setting value of family, a upper unclosed task is returned to.
Key element is classified as to the word slot of entity type first, it is dynamic by the identification of word slot and repeatedly inquiry, clarification, confirmation
Make the accurate concern key point for obtaining user；
Different tasks is attributed to different classes of intention, passes through intention assessment and the dialogue purpose of determining user.
Dialog management system through the invention improves the probability of success of human-computer interaction, it is ensured that man-machine talk has
Effect, friendly progress.People be can satisfy for quickly and accurately obtaining the demand of information.It can solve and customized in business
The Intelligent dialogue of scene.
The technical personnel in the technical field can readily realize the present invention with the above specific embodiments,.But it should manage
Solution, the present invention is not limited to above-mentioned several specific embodiments.On the basis of the disclosed embodiments, the technical field
Technical staff can arbitrarily combine different technical features, to realize different technical solutions.
Claims (10)
1. a kind of intelligent answer method of more wheels dialogue of task based access control driving, which is characterized in that carried out for different tasks
Data preparation obtains intent classifier model and element extraction model by training, by taking turns dialogue management mechanism and decision machine more
System pushes method of the progress of every wheel dialogue to complete intelligent answer；
Wherein intent classifier model and element extraction model, for analyze user question sentence or answer content intention and be critical to
Element；
More wheel dialogue management mechanism and decision-making mechanism, for by should constantly be taken in next step according to current state decision
Optimal movement effectively assists user to complete to talk with around more wheels of task.
2. a kind of intelligent answer method of more wheels dialogue of task based access control driving according to claim 1, which is characterized in that
Intent classifier model and element extraction model are obtained by training, the training includes judging user by logistic regression
Intention whether shift；Specific method is the degree of correlation for comprehensively considering the same task context, by related single feature
Whether the distributed similar feature vector as logistic regression classification of cosine phase Sihe, be intended to shift for judging.
3. a kind of intelligent answer method of more wheels dialogue of task based access control driving according to claim 2, which is characterized in that
Single feature includes TF-IDF, card side, comentropy；The basis of single feature is carried out using the training of Bi-LSTM method
Entity recognition.
4. a kind of intelligent answer method of more wheels dialogue of task based access control driving according to claim 1, which is characterized in that
More wheel dialogue management mechanism and decision-making mechanism are to establish conversation mechanism with the element of user spoken utterances for driving；Conversation mechanism
Including two kinds:
Single task takes turns dialogue more, and when the element user of the task is not known or provides, data are not full-time, and machine guides user complete
It is provided at element；
Multiple tasks mixing carries out more wheel dialogues, when there is task nest phenomenon, when the rhetorical question number of same problem is more than to use
When the setting value of family, a upper unclosed task is returned to.
5. a kind of intelligent answer method of more wheels dialogue of task based access control driving according to claim 4, which is characterized in that
Key element is classified as to the word slot of entity type first, is acted by the identification of word slot and multiple inquiry, clarification, confirmation quasi-
Really obtain the concern key point of user；
Different tasks is attributed to different classes of intention, passes through intention assessment and the dialogue purpose of determining user.
6. a kind of intelligent Answer System of more wheels dialogue of task based access control driving, which is characterized in that the intelligent Answer System
Based on corresponding knowledge data base, including natural language processing module, dialogue management module, problem semantic understanding module,
Answer retrieval obtains module and knowledge base component update module；
Natural language processing module, for being pre-processed to user's input problem and knowledge base；
Dialogue management module, the challenge for context question sentence are handled；
Problem semantic understanding module, for carrying out semantic understanding to single problem；
Answer retrieval obtains module, for obtaining problem answers；
Knowledge base component update module is used for more new knowledge base, so that the better organization knowledge of knowledge base, more rapidly prepares retrieval
Answer.
7. a kind of intelligent Answer System of more wheels dialogue of task based access control driving according to claim 6, which is characterized in that
Natural language processing module includes keyword extracting unit, domain lexicon acquiring unit, customer problem element extraction unit；
Keyword extracting unit is marked for inputting problem and knowledge base progress Chinese word segmentation to user with female, so as to key
The extraction of word；
Domain lexicon acquiring unit, for extracting the entity and new word discovery of knowledge base, to obtain domain lexicon；
Customer problem element extraction unit carries out syntactic analysis and semantic character labeling for inputting problem to user, to obtain
Take the Subject, Predicate and Object and agent word denoting the receiver of an action of customer problem.
8. a kind of intelligent Answer System of more wheels dialogue of task based access control driving according to claim 6, which is characterized in that
Dialogue management module includes clause's split cells, problem clarifies unit, problem questions closely unit and context recognition unit；
Clause's split cells, for being split to problem when once inputting multiple problems；
Problem clarifies unit, for when the question sentence of problem is fuzzy to be understood, to problem secondary clearing again；
Problem questions closely unit, for questioning closely to problem and achieving the purpose that answer when problem lacks essential elements；
Context recognition unit, for being identified to context when problem is related to context of co-text；
Problem semantic understanding module, the problem of for by determining user, identification user puts question to and is intended to and the problem of to lacking
Based on context ingredient reverts to semantic complete problem.
9. a kind of intelligent Answer System of more wheels dialogue of task based access control driving according to claim 6, which is characterized in that
Knowledge base component update module, for increasing for knowledge base, ontology is extracted, domain term is extracted, relationship is extracted and inference rule component
Function.
10. a kind of intelligent Answer System of more wheels dialogue of task based access control driving according to claim 6, feature exist
In intelligent Answer System further includes expansion connection module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811202665.5A CN109446306A (en) | 2018-10-16 | 2018-10-16 | A kind of intelligent answer method of more wheels dialogue of task based access control driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811202665.5A CN109446306A (en) | 2018-10-16 | 2018-10-16 | A kind of intelligent answer method of more wheels dialogue of task based access control driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109446306A true CN109446306A (en) | 2019-03-08 |
Family
ID=65546300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811202665.5A Pending CN109446306A (en) | 2018-10-16 | 2018-10-16 | A kind of intelligent answer method of more wheels dialogue of task based access control driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446306A (en) |
Cited By (56)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109871129A (en) * | 2019-03-22 | 2019-06-11 | 深圳追一科技有限公司 | Man-machine interaction method, device, customer service equipment and storage medium |
| 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 |
| CN110096593A (en) * | 2019-04-22 | 2019-08-06 | 南京硅基智能科技有限公司 | A method of the outer paging system of building intelligence |
| CN110096583A (en) * | 2019-05-09 | 2019-08-06 | 苏州思必驰信息科技有限公司 | Multi-field dialog management system and its construction method |
| CN110096579A (en) * | 2019-04-23 | 2019-08-06 | 南京硅基智能科技有限公司 | A kind of more wheel dialogue methods |
| CN110096567A (en) * | 2019-03-14 | 2019-08-06 | 中国科学院自动化研究所 | Selection method, system are replied in more wheels dialogue based on QA Analysis of Knowledge Bases Reasoning |
| CN110110338A (en) * | 2019-05-13 | 2019-08-09 | 哈尔滨理工大学 | A kind of Dialogue management model application method based on LSTM and slot filling |
| CN110188163A (en) * | 2019-04-13 | 2019-08-30 | 上海策友信息科技有限公司 | Data intelligence processing system based on natural language |
| CN110263346A (en) * | 2019-06-27 | 2019-09-20 | 卓尔智联(武汉)研究院有限公司 | Lexical analysis method, electronic equipment and storage medium based on small-sample learning |
| CN110297702A (en) * | 2019-05-27 | 2019-10-01 | 北京蓦然认知科技有限公司 | A kind of multi-task parallel treating method and apparatus |
| CN110321472A (en) * | 2019-06-12 | 2019-10-11 | 中国电子科技集团公司第二十八研究所 | Public sentiment based on intelligent answer technology monitors system |
| CN110377720A (en) * | 2019-07-26 | 2019-10-25 | 中国工商银行股份有限公司 | The more wheel exchange methods of intelligence and system |
| CN110443355A (en) * | 2019-08-06 | 2019-11-12 | 苏州思必驰信息科技有限公司 | Dialogue method and system applied to compound conversation tasks |
| CN110543587A (en) * | 2019-07-24 | 2019-12-06 | 湖北爱运动体育信息科技有限公司 | sports fitness communication platform based on Internet of things |
| 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 |
| CN110727776A (en) * | 2019-10-12 | 2020-01-24 | 一汽轿车股份有限公司 | Automobile question-answer interaction system and method based on artificial intelligence |
| CN110727783A (en) * | 2019-10-23 | 2020-01-24 | 支付宝(杭州)信息技术有限公司 | Method and device for asking question of user based on dialog system |
| CN110795529A (en) * | 2019-09-05 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Model management method, model management device, storage medium and electronic equipment |
| CN111026886A (en) * | 2019-12-26 | 2020-04-17 | 成都航天科工大数据研究院有限公司 | Multi-round dialogue processing method for professional scene |
| CN111090730A (en) * | 2019-12-05 | 2020-05-01 | 中科数智(北京)科技有限公司 | Intelligent voice scheduling system and method |
| CN111314451A (en) * | 2020-02-07 | 2020-06-19 | 普强时代(珠海横琴)信息技术有限公司 | Language processing system based on cloud computing application |
| 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 |
| CN111522923A (en) * | 2020-03-31 | 2020-08-11 | 华东师范大学 | Multi-round task type conversation state tracking method |
| CN111553162A (en) * | 2020-04-28 | 2020-08-18 | 腾讯科技（深圳）有限公司 | Intention identification method and related 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 |
| CN111831360A (en) * | 2020-07-15 | 2020-10-27 | 神思电子技术股份有限公司 | Distributed deployment method of question-answering system based on context state |
| CN111881267A (en) * | 2020-05-25 | 2020-11-03 | 重庆兆光科技股份有限公司 | Method, system, equipment and medium for extracting key sentences in dialogue corpus |
| CN112131360A (en) * | 2020-09-04 | 2020-12-25 | 交通银行股份有限公司太平洋信用卡中心 | Intelligent multi-turn dialogue customization method and system |
| CN112182171A (en) * | 2020-09-18 | 2021-01-05 | 国网湖南省电力有限公司 | Method and device for constructing operation assistant based on human-computer conversation dispatching robot |
| CN112199486A (en) * | 2020-10-21 | 2021-01-08 | 中国电子科技集团公司第十五研究所 | Task type multi-turn conversation method and system for office scene |
| CN112214589A (en) * | 2020-10-19 | 2021-01-12 | 焦点科技股份有限公司 | Method for multi-round session framework based on cold start |
| CN112231537A (en) * | 2020-11-09 | 2021-01-15 | 张印祺 | Intelligent reading system based on deep learning and web crawler |
| CN112307188A (en) * | 2020-12-30 | 2021-02-02 | 北京百度网讯科技有限公司 | Dialog generation method, system, electronic device and readable storage medium |
| CN112380332A (en) * | 2020-11-17 | 2021-02-19 | 深圳追一科技有限公司 | Interactive knowledge feedback method, device and computer storage medium |
| CN112417894A (en) * | 2020-12-10 | 2021-02-26 | 上海方立数码科技有限公司 | Conversation intention identification method and system based on multi-task learning |
| WO2021035578A1 (en) * | 2019-08-28 | 2021-03-04 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for question recommendation |
| CN112445902A (en) * | 2019-09-04 | 2021-03-05 | 深圳Tcl数字技术有限公司 | Method for identifying user intention in multi-turn conversation and related equipment |
| CN112528002A (en) * | 2020-12-23 | 2021-03-19 | 北京百度网讯科技有限公司 | Dialog recognition method and device, electronic equipment and storage medium |
| CN112560429A (en) * | 2020-12-23 | 2021-03-26 | 信雅达科技股份有限公司 | Intelligent training detection method and system based on deep learning |
| CN112686674A (en) * | 2020-12-25 | 2021-04-20 | 科讯嘉联信息技术有限公司 | Customer service conversation work order summarizing method |
| CN112749263A (en) * | 2020-11-12 | 2021-05-04 | 国衡智慧城市科技研究院(北京)有限公司 | Multi-round answer generation system based on single question |
| CN112905780A (en) * | 2021-03-31 | 2021-06-04 | 闽江学院 | Artificial intelligence dialogue device |
| CN112905747A (en) * | 2021-03-08 | 2021-06-04 | 国能大渡河流域水电开发有限公司 | Professional system archive question-answering robot system based on semantic analysis technology |
| CN112905781A (en) * | 2021-03-31 | 2021-06-04 | 闽江学院 | Artificial intelligence dialogue method |
| CN112925897A (en) * | 2021-04-12 | 2021-06-08 | 辽宁工程技术大学 | Human-computer dialogue system based on task type and its realizing method |
| CN113132214A (en) * | 2019-12-31 | 2021-07-16 | 深圳市优必选科技股份有限公司 | Conversation method, device, server and storage medium |
| CN113139044A (en) * | 2021-05-10 | 2021-07-20 | 中国电子科技集团公司第二十八研究所 | Question-answering multi-turn dialogue method supporting multi-intention switching for question-answering system |
| CN113139045A (en) * | 2021-05-13 | 2021-07-20 | 八维(杭州)科技有限公司 | Selective question-answering method based on task driving type man-machine conversation |
| CN113377934A (en) * | 2021-05-21 | 2021-09-10 | 海南师范大学 | System and method for realizing intelligent customer service |
| CN113569020A (en) * | 2021-06-22 | 2021-10-29 | 复旦大学 | Dialogue management method for fusing knowledge reasoning and knowledge guiding in intelligent conversation system |
| CN113590776A (en) * | 2021-06-23 | 2021-11-02 | 北京百度网讯科技有限公司 | Text processing method and device based on knowledge graph, electronic equipment and medium |
| CN114152444A (en) * | 2021-10-20 | 2022-03-08 | 中国航发四川燃气涡轮研究院 | Portable auxiliary system for mounting and troubleshooting engine rack and using method |
| CN115617972A (en) * | 2022-12-14 | 2023-01-17 | 成都明途科技有限公司 | Robot dialogue method, device, electronic equipment and storage medium |
| CN117573834A (en) * | 2023-11-30 | 2024-02-20 | 北京快牛智营科技有限公司 | Multi-robot dialogue method and system for software-oriented instant service platform |
| CN117743559A (en) * | 2024-02-20 | 2024-03-22 | 厦门国际银行股份有限公司 | Multi-round dialogue processing method, device and equipment based on RAG |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120306741A1 (en) * | 2011-06-06 | 2012-12-06 | Gupta Kalyan M | System and Method for Enhancing Locative Response Abilities of Autonomous and Semi-Autonomous Agents |
| CN106503046A (en) * | 2016-09-21 | 2017-03-15 | 北京光年无限科技有限公司 | Exchange method and system based on intelligent robot |
| CN106503156A (en) * | 2016-10-24 | 2017-03-15 | 北京百度网讯科技有限公司 | Man-machine interaction method and device based on artificial intelligence |
| CN108170764A (en) * | 2017-12-25 | 2018-06-15 | 上海大学 | A kind of man-machine more wheel dialog model construction methods based on scene context |
| CN108197191A (en) * | 2017-12-27 | 2018-06-22 | 神思电子技术股份有限公司 | A kind of scene of more wheel dialogues is intended to interrupt method |
| CN108228764A (en) * | 2017-12-27 | 2018-06-29 | 神思电子技术股份有限公司 | A kind of single-wheel dialogue and the fusion method of more wheel dialogues |
| CN108446286A (en) * | 2017-02-16 | 2018-08-24 | 阿里巴巴集团控股有限公司 | A kind of generation method, device and the server of the answer of natural language question sentence |
-
2018
- 2018-10-16 CN CN201811202665.5A patent/CN109446306A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120306741A1 (en) * | 2011-06-06 | 2012-12-06 | Gupta Kalyan M | System and Method for Enhancing Locative Response Abilities of Autonomous and Semi-Autonomous Agents |
| CN106503046A (en) * | 2016-09-21 | 2017-03-15 | 北京光年无限科技有限公司 | Exchange method and system based on intelligent robot |
| CN106503156A (en) * | 2016-10-24 | 2017-03-15 | 北京百度网讯科技有限公司 | Man-machine interaction method and device based on artificial intelligence |
| CN108446286A (en) * | 2017-02-16 | 2018-08-24 | 阿里巴巴集团控股有限公司 | A kind of generation method, device and the server of the answer of natural language question sentence |
| CN108170764A (en) * | 2017-12-25 | 2018-06-15 | 上海大学 | A kind of man-machine more wheel dialog model construction methods based on scene context |
| CN108197191A (en) * | 2017-12-27 | 2018-06-22 | 神思电子技术股份有限公司 | A kind of scene of more wheel dialogues is intended to interrupt method |
| CN108228764A (en) * | 2017-12-27 | 2018-06-29 | 神思电子技术股份有限公司 | A kind of single-wheel dialogue and the fusion method of more wheel dialogues |
Cited By (81)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110096567A (en) * | 2019-03-14 | 2019-08-06 | 中国科学院自动化研究所 | Selection method, system are replied in more wheels dialogue based on QA Analysis of Knowledge Bases Reasoning |
| 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 |
| CN109871129B (en) * | 2019-03-22 | 2022-03-11 | 深圳追一科技有限公司 | Human-computer interaction method and device, customer service equipment and storage medium |
| CN109871129A (en) * | 2019-03-22 | 2019-06-11 | 深圳追一科技有限公司 | Man-machine interaction method, device, customer service 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 |
| 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 |
| CN110188163A (en) * | 2019-04-13 | 2019-08-30 | 上海策友信息科技有限公司 | Data intelligence processing system based on natural language |
| CN110096593A (en) * | 2019-04-22 | 2019-08-06 | 南京硅基智能科技有限公司 | A method of the outer paging system of building intelligence |
| CN110096579A (en) * | 2019-04-23 | 2019-08-06 | 南京硅基智能科技有限公司 | A kind of more wheel dialogue methods |
| CN110096583B (en) * | 2019-05-09 | 2021-05-14 | 思必驰科技股份有限公司 | Multi-field dialogue management system and construction method thereof |
| CN110096583A (en) * | 2019-05-09 | 2019-08-06 | 苏州思必驰信息科技有限公司 | Multi-field dialog management system and its construction method |
| CN110110338A (en) * | 2019-05-13 | 2019-08-09 | 哈尔滨理工大学 | A kind of Dialogue management model application method based on LSTM and slot filling |
| CN110297702A (en) * | 2019-05-27 | 2019-10-01 | 北京蓦然认知科技有限公司 | A kind of multi-task parallel treating method and apparatus |
| CN110297702B (en) * | 2019-05-27 | 2021-06-18 | 北京蓦然认知科技有限公司 | Multitask parallel processing method and device |
| CN110321472A (en) * | 2019-06-12 | 2019-10-11 | 中国电子科技集团公司第二十八研究所 | Public sentiment based on intelligent answer technology monitors system |
| CN110263346B (en) * | 2019-06-27 | 2023-01-24 | 卓尔智联(武汉)研究院有限公司 | Semantic analysis method based on small sample learning, electronic equipment and storage medium |
| CN110263346A (en) * | 2019-06-27 | 2019-09-20 | 卓尔智联(武汉)研究院有限公司 | Lexical analysis method, electronic equipment and storage medium based on small-sample learning |
| CN110543587A (en) * | 2019-07-24 | 2019-12-06 | 湖北爱运动体育信息科技有限公司 | sports fitness communication platform based on Internet of things |
| CN110377720B (en) * | 2019-07-26 | 2022-02-11 | 中国工商银行股份有限公司 | Intelligent multi-round interaction method and system |
| CN110377720A (en) * | 2019-07-26 | 2019-10-25 | 中国工商银行股份有限公司 | The more wheel exchange methods of intelligence and system |
| CN110443355A (en) * | 2019-08-06 | 2019-11-12 | 苏州思必驰信息科技有限公司 | Dialogue method and system applied to compound conversation tasks |
| CN110443355B (en) * | 2019-08-06 | 2021-11-16 | 思必驰科技股份有限公司 | Conversation method and system applied to compound conversation task |
| WO2021035578A1 (en) * | 2019-08-28 | 2021-03-04 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for question recommendation |
| CN112445902A (en) * | 2019-09-04 | 2021-03-05 | 深圳Tcl数字技术有限公司 | Method for identifying user intention in multi-turn conversation and related equipment |
| CN110795529A (en) * | 2019-09-05 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Model management method, model management device, storage medium and electronic equipment |
| CN110795529B (en) * | 2019-09-05 | 2023-07-25 | 腾讯科技（深圳）有限公司 | Model management method and device, storage medium and electronic equipment |
| CN110727776A (en) * | 2019-10-12 | 2020-01-24 | 一汽轿车股份有限公司 | Automobile question-answer interaction system and method based on artificial intelligence |
| CN110727776B (en) * | 2019-10-12 | 2023-05-12 | 一汽奔腾轿车有限公司 | Automobile question-answering interaction system and interaction method based on artificial intelligence |
| 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 |
| CN110727783B (en) * | 2019-10-23 | 2021-03-02 | 支付宝(杭州)信息技术有限公司 | Method and device for asking question of user based on dialog system |
| CN110727783A (en) * | 2019-10-23 | 2020-01-24 | 支付宝(杭州)信息技术有限公司 | Method and device for asking question of user based on dialog system |
| CN111090730A (en) * | 2019-12-05 | 2020-05-01 | 中科数智(北京)科技有限公司 | Intelligent voice scheduling system and method |
| CN111026886B (en) * | 2019-12-26 | 2023-05-02 | 成都航天科工大数据研究院有限公司 | Multi-round dialogue processing method for professional scene |
| CN111026886A (en) * | 2019-12-26 | 2020-04-17 | 成都航天科工大数据研究院有限公司 | Multi-round dialogue processing method for professional scene |
| CN113132214A (en) * | 2019-12-31 | 2021-07-16 | 深圳市优必选科技股份有限公司 | Conversation method, device, server and storage medium |
| CN111314451A (en) * | 2020-02-07 | 2020-06-19 | 普强时代(珠海横琴)信息技术有限公司 | Language processing system based on cloud computing application |
| 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 |
| CN111522923A (en) * | 2020-03-31 | 2020-08-11 | 华东师范大学 | Multi-round task type conversation state tracking method |
| CN111522923B (en) * | 2020-03-31 | 2023-04-28 | 华东师范大学 | Multi-round task type dialogue state tracking method |
| CN111553162A (en) * | 2020-04-28 | 2020-08-18 | 腾讯科技（深圳）有限公司 | Intention identification method and related device |
| CN111553162B (en) * | 2020-04-28 | 2023-09-22 | 腾讯科技（深圳）有限公司 | Intention recognition method and related device |
| CN111881267A (en) * | 2020-05-25 | 2020-11-03 | 重庆兆光科技股份有限公司 | Method, system, equipment and medium for extracting key sentences in dialogue corpus |
| CN111831360A (en) * | 2020-07-15 | 2020-10-27 | 神思电子技术股份有限公司 | Distributed deployment method of question-answering system based on context state |
| CN111831360B (en) * | 2020-07-15 | 2023-06-20 | 神思电子技术股份有限公司 | Distributed deployment method of question-answering system based on context state |
| CN112131360A (en) * | 2020-09-04 | 2020-12-25 | 交通银行股份有限公司太平洋信用卡中心 | Intelligent multi-turn dialogue customization method and system |
| CN112182171A (en) * | 2020-09-18 | 2021-01-05 | 国网湖南省电力有限公司 | Method and device for constructing operation assistant based on human-computer conversation dispatching robot |
| CN112214589A (en) * | 2020-10-19 | 2021-01-12 | 焦点科技股份有限公司 | Method for multi-round session framework based on cold start |
| CN112214589B (en) * | 2020-10-19 | 2022-08-09 | 焦点科技股份有限公司 | Method for multi-round session framework based on cold start |
| CN112199486A (en) * | 2020-10-21 | 2021-01-08 | 中国电子科技集团公司第十五研究所 | Task type multi-turn conversation method and system for office scene |
| CN112231537A (en) * | 2020-11-09 | 2021-01-15 | 张印祺 | Intelligent reading system based on deep learning and web crawler |
| CN112749263A (en) * | 2020-11-12 | 2021-05-04 | 国衡智慧城市科技研究院(北京)有限公司 | Multi-round answer generation system based on single question |
| CN112380332A (en) * | 2020-11-17 | 2021-02-19 | 深圳追一科技有限公司 | Interactive knowledge feedback method, device and computer storage medium |
| CN112417894A (en) * | 2020-12-10 | 2021-02-26 | 上海方立数码科技有限公司 | Conversation intention identification method and system based on multi-task learning |
| CN112560429A (en) * | 2020-12-23 | 2021-03-26 | 信雅达科技股份有限公司 | Intelligent training detection method and system based on deep learning |
| CN112528002A (en) * | 2020-12-23 | 2021-03-19 | 北京百度网讯科技有限公司 | Dialog recognition method and device, electronic equipment and storage medium |
| CN112528002B (en) * | 2020-12-23 | 2023-07-18 | 北京百度网讯科技有限公司 | Dialogue identification method, device, electronic equipment and storage medium |
| CN112686674A (en) * | 2020-12-25 | 2021-04-20 | 科讯嘉联信息技术有限公司 | Customer service conversation work order summarizing method |
| CN112307188A (en) * | 2020-12-30 | 2021-02-02 | 北京百度网讯科技有限公司 | Dialog generation method, system, electronic device and readable storage medium |
| CN112905747A (en) * | 2021-03-08 | 2021-06-04 | 国能大渡河流域水电开发有限公司 | Professional system archive question-answering robot system based on semantic analysis technology |
| CN112905781A (en) * | 2021-03-31 | 2021-06-04 | 闽江学院 | Artificial intelligence dialogue method |
| CN112905780A (en) * | 2021-03-31 | 2021-06-04 | 闽江学院 | Artificial intelligence dialogue device |
| CN112905780B (en) * | 2021-03-31 | 2022-04-29 | 闽江学院 | Artificial intelligence dialogue device |
| CN112905781B (en) * | 2021-03-31 | 2022-05-03 | 闽江学院 | Artificial intelligence dialogue method |
| CN112925897A (en) * | 2021-04-12 | 2021-06-08 | 辽宁工程技术大学 | Human-computer dialogue system based on task type and its realizing method |
| CN113139044A (en) * | 2021-05-10 | 2021-07-20 | 中国电子科技集团公司第二十八研究所 | Question-answering multi-turn dialogue method supporting multi-intention switching for question-answering system |
| CN113139045A (en) * | 2021-05-13 | 2021-07-20 | 八维(杭州)科技有限公司 | Selective question-answering method based on task driving type man-machine conversation |
| CN113139045B (en) * | 2021-05-13 | 2023-05-05 | 八维(杭州)科技有限公司 | Selective question-answering method based on task-driven man-machine dialogue |
| CN113377934A (en) * | 2021-05-21 | 2021-09-10 | 海南师范大学 | System and method for realizing intelligent customer service |
| CN113377934B (en) * | 2021-05-21 | 2022-07-05 | 海南师范大学 | System and method for realizing intelligent customer service |
| CN113569020B (en) * | 2021-06-22 | 2023-10-10 | 复旦大学 | Dialogue management method for integrating knowledge reasoning and knowledge guiding in intelligent dialogue system |
| CN113569020A (en) * | 2021-06-22 | 2021-10-29 | 复旦大学 | Dialogue management method for fusing knowledge reasoning and knowledge guiding in intelligent conversation system |
| CN113590776A (en) * | 2021-06-23 | 2021-11-02 | 北京百度网讯科技有限公司 | Text processing method and device based on knowledge graph, electronic equipment and medium |
| CN113590776B (en) * | 2021-06-23 | 2023-12-12 | 北京百度网讯科技有限公司 | Knowledge graph-based text processing method and device, electronic equipment and medium |
| CN114152444B (en) * | 2021-10-20 | 2023-09-15 | 中国航发四川燃气涡轮研究院 | Portable auxiliary system for mounting and troubleshooting engine bench and use method thereof |
| CN114152444A (en) * | 2021-10-20 | 2022-03-08 | 中国航发四川燃气涡轮研究院 | Portable auxiliary system for mounting and troubleshooting engine rack and using method |
| CN115617972A (en) * | 2022-12-14 | 2023-01-17 | 成都明途科技有限公司 | Robot dialogue method, device, electronic equipment and storage medium |
| CN117573834A (en) * | 2023-11-30 | 2024-02-20 | 北京快牛智营科技有限公司 | Multi-robot dialogue method and system for software-oriented instant service platform |
| CN117573834B (en) * | 2023-11-30 | 2024-04-16 | 北京快牛智营科技有限公司 | Multi-robot dialogue method and system for software-oriented instant service platform |
| CN117743559A (en) * | 2024-02-20 | 2024-03-22 | 厦门国际银行股份有限公司 | Multi-round dialogue processing method, device and equipment based on RAG |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446306A (en) | A kind of intelligent answer method of more wheels dialogue of task based access control driving | |
| CN109493166B (en) | Construction method for task type dialogue system aiming at e-commerce shopping guide scene | |
| CN107329967B (en) | Question answering system and method based on deep learning | |
| CN110175227B (en) | Dialogue auxiliary system based on team learning and hierarchical reasoning | |
| CN110364251B (en) | Intelligent interactive diagnosis guide consultation system based on machine reading understanding | |
| CN106295792B (en) | Dialogue data interaction processing method and device based on multi-model output | |
| CN111651609A (en) | Multi-turn dialogue method and system integrating knowledge graph and emotion supervision | |
| CN109460457A (en) | Text sentence similarity calculating method, intelligent government affairs auxiliary answer system and its working method | |
| CN111666381B (en) | Task type question-answer interaction system oriented to intelligent control | |
| CN108984778A (en) | A kind of intelligent interaction automatically request-answering system and self-teaching method | |
| KR20190133931A (en) | Method to response based on sentence paraphrase recognition for a dialog system | |
| CN109460459B (en) | Log learning-based dialogue system automatic optimization method | |
| CN109857846B (en) | Method and device for matching user question and knowledge point | |
| US20230394247A1 (en) | Human-machine collaborative conversation interaction system and method | |
| CN110210036A (en) | A kind of intension recognizing method and device | |
| CN117271767B (en) | Operation and maintenance knowledge base establishing method based on multiple intelligent agents | |
| CN112115242A (en) | Intelligent customer service question-answering system based on naive Bayes classification algorithm | |
| Chandiok et al. | CIT: Integrated cognitive computing and cognitive agent technologies based cognitive architecture for human-like functionality in artificial systems | |
| CN115392264A (en) | RASA-based task-type intelligent multi-turn dialogue method and related equipment | |
| CN114648016A (en) | Event argument extraction method based on event element interaction and tag semantic enhancement | |
| CN116166688A (en) | Business data retrieval method, system and processing equipment based on natural language interaction | |
| US11314534B2 (en) | System and method for interactively guiding users through a procedure | |
| CN111368540B (en) | Keyword information extraction method based on semantic role analysis | |
| KR102240910B1 (en) | Korean Customer Service Associate Assist System based on Machine Learning | |
| CN115905187B (en) | Intelligent proposition system oriented to cloud computing engineering technician authentication |
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 |
Application publication date: 20190308 |
|
| RJ01 | Rejection of invention patent application after publication |