CN110019687A - A kind of more intention assessment systems, method, equipment and the medium of knowledge based map - Google Patents
A kind of more intention assessment systems, method, equipment and the medium of knowledge based map Download PDFInfo
- Publication number
- CN110019687A CN110019687A CN201910290156.0A CN201910290156A CN110019687A CN 110019687 A CN110019687 A CN 110019687A CN 201910290156 A CN201910290156 A CN 201910290156A CN 110019687 A CN110019687 A CN 110019687A
- Authority
- CN
- China
- Prior art keywords
- text
- knowledge
- user
- carried out
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses more intention assessment systems, method, equipment and the media of a kind of knowledge based map, comprising: knowledge mapping provides data basis with reasoning for calculating for figure;Entity recognition module inputs in text from user for being based on the knowledge mapping and identifies text entities and text attribute;Figure computing module carries out figure calculating, identifies customer problem for text entities and text attribute based on the knowledge mapping, Entity recognition module output;Interactive module obtains the customer problem, answer is carried out from knowledge base and recalls and generates for calling the figure computing module.The present invention carries out more intention assessments according to knowledge mapping automatically, punctuate, clause and syntactic analysis is not limited to, when user is intended to unclear, intention convergence is realized by asking in reply automatically, problem identification rate and accuracy rate are effectively improved, nature is talked in the flexibility of significant increase question and answer robot.
Description
Technical field
The present invention relates to computer question and answer technical fields, and in particular to a kind of more intention assessment systems of knowledge based map
System, method, equipment and medium.
Background technique
At present in question and answer field, traditional more intention assessments are based on the cutting of punctuate sentence using simple, or combine syntax
Analysis, such as " what cries self-defence? will how many year be sentenced by defending improperly? " based on say hello, the punctuates such as fullstop, exclamation, can be with cutting
At two problems " what is self-defence ", " how many year will be sentenced by defending improperly ", according to the problem after cutting, respectively in knowledge base
In recalled by Similarity matching;For another example " murder illegal? how many year sentenced? " it can be " murdering illegal " with cutting, " sentence how many
Year ", at this time the problem after cutting by known to syntactic analysis below one lack subject, that does in the prior art relatively good asks
The system of answering can extract subject from previous sentence, and judge whether subject should completion by model.As it can be seen that the prior art is to more meanings
Figure identification requires quizmaster to be able to use correct grammatical representation, even with correct punctuate, and in actually dialogue question and answer,
Since the level of quizmaster is irregular and spoken random stronger, may there is a content more lacked, syntax error also compared with
It is more, there is a situation where to put question to intention unclear, correctly identification is difficult by punctuate and clause syntactic analysis and is wherein intended to.
Summary of the invention
In view of the above-mentioned problems, the present invention provides more intention assessment systems, method, equipment and the Jie of a kind of knowledge based map
Matter carries out in more intention assessments and dicing process to customer problem, automatic to the progress of uncertain intention anti-based on model is disambiguated
It asks, realizes and be intended to convergence, effectively improve problem identification rate and accuracy rate, the flexibility of significant increase question and answer robot, dialogue is certainly
So.
The present invention specifically:
A kind of more intention assessment systems of knowledge based map, comprising:
Knowledge mapping provides data basis with reasoning for calculating for figure;
Entity recognition module inputs in text from user for being based on the knowledge mapping and identifies text entities and text
This attribute;
Figure computing module, for text entities and text based on the knowledge mapping, Entity recognition module output
Attribute carries out figure calculating, identifies customer problem;
Interactive module obtains the customer problem, answer is carried out from knowledge base and is called together for calling the figure computing module
It returns and generates.
Further, the knowledge mapping is established according to industry, and different industries respectively correspond different knowledge mappings;
After the completion of the knowledge mapping is established, it is stored in chart database in the form of RDF.
Further, the Entity recognition module is also used to:
Judge to input whether the text entities identified in text have ambiguity from user, if then calculating based on disambiguation model
Ambiguity classification and ambiguity probability out, and automatically generate disambiguation problem and asked in reply to user, it is answered according to user to the text entities
Carry out disambiguation processing;Otherwise it is not processed.
Further, the figure computing module carries out figure calculating, identifies customer problem, specifically includes:
Path computing is carried out to the text entities and text attribute, when lacking node in path, to the node into
Row auto-complete, obtains fullpath, it is ensured that path connectivity;
Intention cutting is carried out according to path, identifies customer problem.
A kind of more intension recognizing methods of knowledge based map, comprising:
Knowledge based map inputs in text from user and identifies text entities and text attribute;
Based on the knowledge mapping, text entities and text attribute, figure calculating is carried out, identifies customer problem;
According to the customer problem, answer is carried out from knowledge base and recalls and generates.
Further, the knowledge mapping is established according to industry, and different industries respectively correspond different knowledge mappings;
After the completion of the knowledge mapping is established, it is stored in chart database in the form of RDF.
It is further, described after identifying text entities and text attribute in user's input text, further includes:
Judge to input whether the text entities identified in text have ambiguity from user, if then calculating based on disambiguation model
Ambiguity classification and ambiguity probability out, and automatically generate disambiguation problem and asked in reply to user, it is answered according to user to the text entities
Carry out disambiguation processing;Otherwise it is not processed.
Further, described to carry out figure calculating, it identifies customer problem, specifically includes:
Path computing is carried out to the text entities and text attribute, when lacking node in path, to the node into
Row auto-complete, obtains fullpath, it is ensured that path connectivity;
Intention cutting is carried out according to path, identifies customer problem.
A kind of electronic equipment, comprising: shell, processor, memory, circuit board and power circuit, wherein circuit board placement
In the space interior that shell surrounds, processor and memory setting are on circuit boards;Power circuit, for being above-mentioned electronic equipment
Each circuit or device power supply;Memory is for storing executable program code;Processor is stored by reading in memory
Executable program code run program corresponding with executable program code, for executing the more of above-mentioned knowledge based map
Intension recognizing method.
A kind of computer readable storage medium is stored with one or more program, and one or more of programs can
It is executed by one or more processor, to realize more intension recognizing methods of above-mentioned knowledge based map.
The beneficial effects of the present invention are embodied in:
The present invention is directed to the input text that user puts question to, and carries out more intention assessments automatically according to knowledge mapping, is not limited to
Punctuate, clause and syntactic analysis, and cutting is carried out to intention is automatic, and carry out answer generation;It, can be certainly when user is intended to unclear
After row reasoning, intention convergence is realized by asking in reply automatically, effectively improves problem identification rate and accuracy rate, significant increase question and answer machine
Nature is talked in the flexibility of people.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art are briefly described.In all the appended drawings, similar element
Or part is generally identified by similar appended drawing reference.In attached drawing, each element or part might not be drawn according to actual ratio.
Fig. 1 is a kind of more intention assessment system construction drawings of knowledge based map of the embodiment of the present invention;
Fig. 2 is a kind of knowledge mapping schematic diagram of the embodiment of the present invention;
Fig. 3 is the path schematic diagram in a kind of figure calculating process of the embodiment of the present invention;
Fig. 4 is a kind of more intension recognizing method flow charts of knowledge based map of the embodiment of the present invention;
Fig. 5 is more intension recognizing method flow charts of another kind of embodiment of the present invention knowledge based map;
Fig. 6 is a kind of electronic equipment of embodiment of the present invention structural schematic diagram.
Specific embodiment
It is described in detail below in conjunction with embodiment of the attached drawing to technical solution of the present invention.Following embodiment is only used for
Clearly illustrate technical solution of the present invention, therefore be only used as example, and cannot be used as a limitation and limit protection model of the invention
It encloses.
It should be noted that unless otherwise indicated, technical term or scientific term used in this application should be this hair
The ordinary meaning that bright one of ordinary skill in the art are understood.
As shown in Figure 1, for a kind of more intention assessment system embodiments of knowledge based map of the present invention, comprising:
Knowledge mapping 11 provides data basis with reasoning for calculating for figure;
Entity recognition module 12, for be based on the knowledge mapping, from user input text in identify text entities and
Text attribute;
Figure computing module 13, for text entities and text based on the knowledge mapping, Entity recognition module output
This attribute carries out figure calculating, identifies customer problem;
Interactive module 14 obtains the customer problem, answer is carried out from knowledge base for calling the figure computing module
It recalls and generates.
Preferably, the knowledge mapping is established according to industry, and different industries respectively correspond different knowledge mappings;Institute
After the completion of stating knowledge mapping foundation, it is stored in chart database in the form of RDF;By taking securities industry as an example, a kind of knowledge graph is provided
Schematic diagram is composed, as shown in Figure 2.
Preferably, the Entity recognition module is also used to:
Judge to input whether the text entities identified in text have ambiguity from user, if then calculating based on disambiguation model
Ambiguity classification and ambiguity probability out, and automatically generate disambiguation problem and asked in reply to user, it is answered according to user to the text entities
Carry out disambiguation processing;Otherwise it is not processed.
For example, user inputs text, i.e. user puts question to " I wants to buy safety how to buy ", and it is " flat that system identification goes out text entities
Peace ", attribute " purchase ";
Under normal conditions, safety may be the safe and sound meaning, and in field of securities, safety is the nickname of Chinese safety,
But it is based on securities industry knowledge mapping, text entity does not have ambiguity, without disambiguating;
Knowledge based map further identifies that this stock example of Chinese safety is belonging respectively to Hong Kong stock and A-share two general
Under thought, the two concepts are the sub- concept of stock, therefore the recognition result of the customer problem are as follows:
Entity: Chinese safety [isa Hong Kong stock, isa A-share], Hong Kong stock [isa stock], A-share [isa stock]
Attribute: purchase
Since Hong Kong stock and A-share belong to stock, system can not disambiguate automatically, therefore it is anti-to user to automatically generate disambiguation problem
It asks:
It may I ask the Chinese safety [02318.HK] of purchase or Chinese safety [601318]?
It is finally answered according to user, to determine which conceptual entity text entities particularly belong to.
Preferably, the figure computing module carries out figure calculating, identifies customer problem, specifically includes:
Path computing is carried out to the text entities and text attribute, when lacking node in path, to the node into
Row auto-complete, obtains fullpath, it is ensured that path connectivity;
Intention cutting is carried out according to path, identifies customer problem.
Under normal circumstances, the problem that user inputs text may have 1-3 intention, and Dan Yitu does not consider in the present invention
In range, 2 or more intentions are similar with the processing mode that 2 are intended to, therefore by taking 2 are intended to as an example, and it is real to provide a kind of figure calculating
Apply example;Wherein, path schematic diagram when path computing as shown in figure 3, and including following calculated case:
(1) a, b recognize two text entities, and constitute two fullpaths, can directly carry out at this time according to path
It is intended to cutting, generates two problems;
(2) c, d recognize a text entities, constitute two fullpaths from text entity, equally may be used at this time
Directly to carry out intention cutting according to path, completion text entities when cutting generate two problems;
(3) e in two kinds of situation, first is that recognizing a text entities, constitutes two complete roads from text entity
Diameter, centre do not occur attribute node completion, at this time with the processing method of (2);Second is that a text entities are recognized, from the text
Entity, which sets out, constitutes two paths, and attribute node completion occurs in centre, and from figure, determination is starting point and terminal, middle node
Point obtains for reasoning, need to carry out intention cutting according to the path after completion at this time, and completion entity when cutting generates two problems,
And by carrying out intention clarification to user's rhetorical question.
By taking b as an example, user puts question to " acceptance of Hong Kong stock and A-share rule ", and system carries out Entity recognition:
Entity: Hong Kong stock, A-share;Attribute: acceptance, rule
According to knowledge mapping, Hong Kong stock attribute has acceptance rule, and A-share attribute also has acceptance rule, therefore carries out intention fractionation:
Entity 1: Hong Kong stock, attribute: acceptance rule
Problem 1: the acceptance rule of Hong Kong stock
2:A strands of entity, attribute: acceptance rule
The acceptance rule that 2:A strands of problem ".
As shown in figure 4, for a kind of more intension recognizing method embodiments of knowledge based map of the present invention, comprising:
S41: knowledge based map inputs in text from user and identifies text entities and text attribute;
S42: being based on the knowledge mapping, text entities and text attribute, carries out figure calculating, identifies customer problem;
S43: according to the customer problem, answer is carried out from knowledge base and recalls and generates.
Preferably, the knowledge mapping is established according to industry, and different industries respectively correspond different knowledge mappings;Institute
After the completion of stating knowledge mapping foundation, it is stored in chart database in the form of RDF.
It is preferably, described after identifying text entities and text attribute in user's input text, further includes:
Judge to input whether the text entities identified in text have ambiguity from user, if then calculating based on disambiguation model
Ambiguity classification and ambiguity probability out, and automatically generate disambiguation problem and asked in reply to user, it is answered according to user to the text entities
Carry out disambiguation processing;Otherwise it is not processed.
Preferably, described to carry out figure calculating, it identifies customer problem, specifically includes:
Path computing is carried out to the text entities and text attribute, when lacking node in path, to the node into
Row auto-complete, obtains fullpath, it is ensured that path connectivity;
Intention cutting is carried out according to path, identifies customer problem.
For further the present invention will be described, the more intension recognizing methods for providing another knowledge based map are implemented
Example, as shown in Figure 5, comprising:
S51: it receives user and puts question to;
S52: the user is putd question to and carries out text entities and Attribute Recognition;
S53: whether the text entities for judging identification are multiple entity or attribute branch, if then entering S54;Otherwise determine to use
It is Dan Yitu that family, which is putd question to,;
Meanwhile judging whether the text entities of identification have uncertain higher level, if then asking in reply to user, obtain user's choosing
It selects, is clearly intended to;Otherwise directly can clearly be intended to;
S54: intention cutting is carried out according to path computation result;
S55: the intention list after obtaining cutting.
The embodiment of the present invention also provides a kind of electronic equipment, as shown in fig. 6, may be implemented to implement shown in Fig. 4-5 of the present invention
The process of example, as shown in fig. 6, above-mentioned electronic equipment may include: shell 61, processor 62, memory 63, circuit board 64 and electricity
Source circuit 65, wherein circuit board 64 is placed in the space interior that shell 61 surrounds, and processor 62 and memory 63 are arranged in circuit
On plate 64;Power circuit 65, for each circuit or the device power supply for above-mentioned electronic equipment;Memory 63 is for storing and can hold
Line program code;Processor 62 is run and executable program generation by reading the executable program code stored in memory 63
The corresponding program of code, for executing method described in aforementioned any embodiment.
Processor 62 to the specific implementation procedures of above-mentioned steps and processor 62 by operation executable program code come
The step of further executing may refer to the description of Fig. 4-5 illustrated embodiment of the present invention, and details are not described herein.
The electronic equipment exists in a variety of forms, including but not limited to:
(1) mobile communication equipment: the characteristics of this kind of equipment is that have mobile communication function, and to provide speech, data
Communication is main target.This Terminal Type includes: smart phone (such as iPhone), multimedia handset, functional mobile phone and low
Hold mobile phone etc..
(2) super mobile personal computer equipment: this kind of equipment belongs to the scope of personal computer, there is calculating and processing function
Can, generally also have mobile Internet access characteristic.This Terminal Type includes: PDA, MID and UMPC equipment etc., such as iPad.
(3) portable entertainment device: this kind of equipment can show and play multimedia content.Such equipment include: audio,
Video player (such as iPod), handheld device, e-book and intelligent toy and portable car-mounted navigation equipment.
(4) server: providing the equipment of the service of calculating, and the composition of server includes that processor, hard disk, memory, system are total
Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, in processing energy
Power, stability, reliability, safety, scalability, manageability etc. are more demanding.
(5) other electronic equipments with data interaction function.
The embodiment of the present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
There is one or more program, one or more of programs can be executed by one or more processor, aforementioned to realize
More intension recognizing methods of knowledge based map.
The present invention is directed to the input text that user puts question to, and carries out more intention assessments automatically according to knowledge mapping, is not limited to
Punctuate, clause and syntactic analysis, and cutting is carried out to intention is automatic, and carry out answer generation;It, can be certainly when user is intended to unclear
After row reasoning, intention convergence is realized by asking in reply automatically, effectively improves problem identification rate and accuracy rate, significant increase question and answer machine
Nature is talked in the flexibility of people.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme should all cover within the scope of the claims and the description of the invention.
Claims (10)
1. a kind of more intention assessment systems of knowledge based map characterized by comprising
Knowledge mapping provides data basis with reasoning for calculating for figure;
Entity recognition module inputs in text from user for being based on the knowledge mapping and identifies text entities and text category
Property;
Figure computing module, text entities and text attribute for being exported based on the knowledge mapping, the Entity recognition module,
Figure calculating is carried out, identifies customer problem;
Interactive module obtains the customer problem for calling the figure computing module, carried out from knowledge base answer recall and
It generates.
2. the system as claimed in claim 1, which is characterized in that the knowledge mapping is established according to industry, different industries
Respectively correspond different knowledge mappings;After the completion of the knowledge mapping is established, it is stored in chart database.
3. system as claimed in claim 2, which is characterized in that the Entity recognition module is also used to:
Judge to input whether the text entities identified in text have ambiguity from user, if then calculating discrimination based on disambiguation model
Justice classification and ambiguity probability, and automatically generate disambiguation problem and asked in reply to user, it is answered according to user and the text entities is carried out
Disambiguation processing;Otherwise it is not processed.
4. system as claimed in claim 3, which is characterized in that the figure computing module carries out figure calculating, identifies customer problem,
It specifically includes:
Path computing is carried out to the text entities and text attribute, when lacking node in path, the node is carried out certainly
Dynamic completion, obtains fullpath;
Intention cutting is carried out according to path, identifies customer problem.
5. a kind of more intension recognizing methods of knowledge based map characterized by comprising
Knowledge based map inputs in text from user and identifies text entities and text attribute;
Based on the knowledge mapping, text entities and text attribute, figure calculating is carried out, identifies customer problem;
According to the customer problem, answer is carried out from knowledge base and recalls and generates.
6. method as claimed in claim 5, which is characterized in that the knowledge mapping is established according to industry, different industries
Respectively correspond different knowledge mappings;After the completion of the knowledge mapping is established, it is stored in chart database.
7. method as claimed in claim 6, which is characterized in that described input in text from user identifies text entities and text
After this attribute, the method also includes:
Judge to input whether the text entities identified in text have ambiguity from user, if then calculating discrimination based on disambiguation model
Justice classification and ambiguity probability, and automatically generate disambiguation problem and asked in reply to user, it is answered according to user and the text entities is carried out
Disambiguation processing;Otherwise it is not processed.
8. the method for claim 7, which is characterized in that it is described to carry out figure calculating, it identifies customer problem, specifically includes:
Path computing is carried out to the text entities and text attribute, when lacking node in path, the node is carried out certainly
Dynamic completion, obtains fullpath;
Intention cutting is carried out according to path, identifies customer problem.
9. a kind of electronic equipment, which is characterized in that the electronic equipment includes: shell, processor, memory, circuit board and electricity
Source circuit, wherein circuit board is placed in the space interior that shell surrounds, and processor and memory setting are on circuit boards;Power supply
Circuit, for each circuit or the device power supply for above-mentioned electronic equipment;Memory is for storing executable program code;Processing
Device runs program corresponding with executable program code by reading the executable program code stored in memory, for holding
Row claim 5-8 any methods.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage have one or
Multiple programs, one or more of programs can be executed by one or more processor, to realize that claim 5-8 are appointed
Method described in one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910290156.0A CN110019687B (en) | 2019-04-11 | 2019-04-11 | Multi-intention recognition system, method, equipment and medium based on knowledge graph |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910290156.0A CN110019687B (en) | 2019-04-11 | 2019-04-11 | Multi-intention recognition system, method, equipment and medium based on knowledge graph |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110019687A true CN110019687A (en) | 2019-07-16 |
CN110019687B CN110019687B (en) | 2021-03-23 |
Family
ID=67191129
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910290156.0A Active CN110019687B (en) | 2019-04-11 | 2019-04-11 | Multi-intention recognition system, method, equipment and medium based on knowledge graph |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110019687B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110704641A (en) * | 2019-10-11 | 2020-01-17 | 零犀(北京)科技有限公司 | Ten-thousand-level intention classification method and device, storage medium and electronic equipment |
CN111428018A (en) * | 2020-03-26 | 2020-07-17 | 中国建设银行股份有限公司 | Intelligent question and answer method and device |
CN111666399A (en) * | 2020-06-23 | 2020-09-15 | 中国平安人寿保险股份有限公司 | Intelligent question and answer method and device based on knowledge graph and computer equipment |
CN112560477A (en) * | 2020-12-09 | 2021-03-26 | 中科讯飞互联(北京)信息科技有限公司 | Text completion method, electronic device and storage device |
CN112650859A (en) * | 2020-12-29 | 2021-04-13 | 北京欧拉认知智能科技有限公司 | User intention identification method, user intention identification equipment and model construction method |
CN113239146A (en) * | 2021-05-12 | 2021-08-10 | 平安科技(深圳)有限公司 | Response analysis method, device, equipment and storage medium |
CN113377943A (en) * | 2021-08-16 | 2021-09-10 | 中航信移动科技有限公司 | Multi-round intelligent question-answering data processing system |
WO2022252351A1 (en) * | 2021-06-02 | 2022-12-08 | 上海擎感智能科技有限公司 | Control method and control system of in-vehicle infotainment system |
CN116432615A (en) * | 2023-06-12 | 2023-07-14 | 中国第一汽车股份有限公司 | Text processing method and device |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102982097A (en) * | 2011-11-03 | 2013-03-20 | 微软公司 | Domains for knowledge-based data quality solution |
CN105701253A (en) * | 2016-03-04 | 2016-06-22 | 南京大学 | Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method |
CN105760514A (en) * | 2016-02-24 | 2016-07-13 | 西安交通大学 | Method for automatically obtaining short text of knowledge domain from community question-and-answer website |
US20160203412A1 (en) * | 2014-12-12 | 2016-07-14 | International Business Machines Corporation | Inferred Facts Discovered through Knowledge Graph Derived Contextual Overlays |
CN106095932A (en) * | 2016-06-13 | 2016-11-09 | 竹间智能科技(上海)有限公司 | Encyclopaedic knowledge question sentence recognition methods and device |
CN106934012A (en) * | 2017-03-10 | 2017-07-07 | 上海数眼科技发展有限公司 | A kind of question answering in natural language method and system of knowledge based collection of illustrative plates |
CN107958091A (en) * | 2017-12-28 | 2018-04-24 | 北京贝塔智投科技有限公司 | A kind of NLP artificial intelligence approaches and interactive system based on financial vertical knowledge mapping |
CN107992543A (en) * | 2017-11-27 | 2018-05-04 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer-readable recording medium |
CN108196880A (en) * | 2017-12-11 | 2018-06-22 | 北京大学 | Software project knowledge mapping method for automatically constructing and system |
US20180341650A1 (en) * | 2012-02-02 | 2018-11-29 | Visa International Service Association | Multi-source, multi-dimensional, cross-entity, multimedia analytical model sharing database platform apparatuses, methods and systems |
CN109033260A (en) * | 2018-07-06 | 2018-12-18 | 天津大学 | Knowledge mapping Interactive Visualization querying method based on RDF |
CN109033135A (en) * | 2018-06-06 | 2018-12-18 | 北京大学 | A kind of natural language querying method and system of software-oriented project knowledge map |
CN109241078A (en) * | 2018-08-30 | 2019-01-18 | 中国地质大学(武汉) | A kind of knowledge mapping hoc queries method based on hybrid database |
CN109344240A (en) * | 2018-09-21 | 2019-02-15 | 联想(北京)有限公司 | A kind of data processing method, server and electronic equipment |
CN109492077A (en) * | 2018-09-29 | 2019-03-19 | 北明智通(北京)科技有限公司 | The petrochemical field answering method and system of knowledge based map |
CN109522465A (en) * | 2018-10-22 | 2019-03-26 | 国家电网公司 | The semantic searching method and device of knowledge based map |
-
2019
- 2019-04-11 CN CN201910290156.0A patent/CN110019687B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102982097A (en) * | 2011-11-03 | 2013-03-20 | 微软公司 | Domains for knowledge-based data quality solution |
US20180341650A1 (en) * | 2012-02-02 | 2018-11-29 | Visa International Service Association | Multi-source, multi-dimensional, cross-entity, multimedia analytical model sharing database platform apparatuses, methods and systems |
US20160203412A1 (en) * | 2014-12-12 | 2016-07-14 | International Business Machines Corporation | Inferred Facts Discovered through Knowledge Graph Derived Contextual Overlays |
CN105760514A (en) * | 2016-02-24 | 2016-07-13 | 西安交通大学 | Method for automatically obtaining short text of knowledge domain from community question-and-answer website |
CN105701253A (en) * | 2016-03-04 | 2016-06-22 | 南京大学 | Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method |
CN106095932A (en) * | 2016-06-13 | 2016-11-09 | 竹间智能科技(上海)有限公司 | Encyclopaedic knowledge question sentence recognition methods and device |
CN106934012A (en) * | 2017-03-10 | 2017-07-07 | 上海数眼科技发展有限公司 | A kind of question answering in natural language method and system of knowledge based collection of illustrative plates |
CN107992543A (en) * | 2017-11-27 | 2018-05-04 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer-readable recording medium |
CN108196880A (en) * | 2017-12-11 | 2018-06-22 | 北京大学 | Software project knowledge mapping method for automatically constructing and system |
CN107958091A (en) * | 2017-12-28 | 2018-04-24 | 北京贝塔智投科技有限公司 | A kind of NLP artificial intelligence approaches and interactive system based on financial vertical knowledge mapping |
CN109033135A (en) * | 2018-06-06 | 2018-12-18 | 北京大学 | A kind of natural language querying method and system of software-oriented project knowledge map |
CN109033260A (en) * | 2018-07-06 | 2018-12-18 | 天津大学 | Knowledge mapping Interactive Visualization querying method based on RDF |
CN109241078A (en) * | 2018-08-30 | 2019-01-18 | 中国地质大学(武汉) | A kind of knowledge mapping hoc queries method based on hybrid database |
CN109344240A (en) * | 2018-09-21 | 2019-02-15 | 联想(北京)有限公司 | A kind of data processing method, server and electronic equipment |
CN109492077A (en) * | 2018-09-29 | 2019-03-19 | 北明智通(北京)科技有限公司 | The petrochemical field answering method and system of knowledge based map |
CN109522465A (en) * | 2018-10-22 | 2019-03-26 | 国家电网公司 | The semantic searching method and device of knowledge based map |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110704641B (en) * | 2019-10-11 | 2023-04-07 | 零犀(北京)科技有限公司 | Ten-thousand-level intention classification method and device, storage medium and electronic equipment |
CN110704641A (en) * | 2019-10-11 | 2020-01-17 | 零犀(北京)科技有限公司 | Ten-thousand-level intention classification method and device, storage medium and electronic equipment |
CN111428018A (en) * | 2020-03-26 | 2020-07-17 | 中国建设银行股份有限公司 | Intelligent question and answer method and device |
CN111428018B (en) * | 2020-03-26 | 2024-02-06 | 中国建设银行股份有限公司 | Intelligent question-answering method and device |
CN111666399A (en) * | 2020-06-23 | 2020-09-15 | 中国平安人寿保险股份有限公司 | Intelligent question and answer method and device based on knowledge graph and computer equipment |
CN112560477A (en) * | 2020-12-09 | 2021-03-26 | 中科讯飞互联(北京)信息科技有限公司 | Text completion method, electronic device and storage device |
CN112560477B (en) * | 2020-12-09 | 2024-04-16 | 科大讯飞(北京)有限公司 | Text completion method, electronic equipment and storage device |
CN112650859A (en) * | 2020-12-29 | 2021-04-13 | 北京欧拉认知智能科技有限公司 | User intention identification method, user intention identification equipment and model construction method |
CN113239146A (en) * | 2021-05-12 | 2021-08-10 | 平安科技(深圳)有限公司 | Response analysis method, device, equipment and storage medium |
CN113239146B (en) * | 2021-05-12 | 2023-07-28 | 平安科技(深圳)有限公司 | Response analysis method, device, equipment and storage medium |
WO2022252351A1 (en) * | 2021-06-02 | 2022-12-08 | 上海擎感智能科技有限公司 | Control method and control system of in-vehicle infotainment system |
CN113377943A (en) * | 2021-08-16 | 2021-09-10 | 中航信移动科技有限公司 | Multi-round intelligent question-answering data processing system |
CN113377943B (en) * | 2021-08-16 | 2022-03-25 | 中航信移动科技有限公司 | Multi-round intelligent question-answering data processing system |
CN116432615A (en) * | 2023-06-12 | 2023-07-14 | 中国第一汽车股份有限公司 | Text processing method and device |
Also Published As
Publication number | Publication date |
---|---|
CN110019687B (en) | 2021-03-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110019687A (en) | A kind of more intention assessment systems, method, equipment and the medium of knowledge based map | |
CN107147618A (en) | A kind of user registering method, device and electronic equipment | |
CN103413549B (en) | The method of interactive voice, system and interactive terminal | |
WO2019084810A1 (en) | Information processing method and terminal, and computer storage medium | |
CN107146602A (en) | A kind of audio recognition method, device and electronic equipment | |
CN112365892A (en) | Man-machine interaction method, device, electronic device and storage medium | |
CN111428010B (en) | Man-machine intelligent question-answering method and device | |
CN111737987B (en) | Intention recognition method, device, equipment and storage medium | |
US11176466B2 (en) | Enhanced conversational bots processing | |
CN108509416A (en) | Sentence realizes other method and device, equipment and storage medium | |
JP2013167765A (en) | Knowledge amount estimation information generating apparatus, and knowledge amount estimating apparatus, method and program | |
CN112468659A (en) | Quality evaluation method, device, equipment and storage medium applied to telephone customer service | |
CN112364622A (en) | Dialog text analysis method, dialog text analysis device, electronic device and storage medium | |
CN114003682A (en) | Text classification method, device, equipment and storage medium | |
CN113468894A (en) | Dialogue interaction method and device, electronic equipment and computer-readable storage medium | |
CN112632248A (en) | Question answering method, device, computer equipment and storage medium | |
CN111027316A (en) | Text processing method and device, electronic equipment and computer readable storage medium | |
CN109002477B (en) | Information processing method, device, terminal and medium | |
CN113051384A (en) | User portrait extraction method based on conversation and related device | |
CN117370512A (en) | Method, device, equipment and storage medium for replying to dialogue | |
CN114490955A (en) | Intelligent dialogue method, device, equipment and computer storage medium | |
CN110288996A (en) | A kind of speech recognition equipment and audio recognition method | |
Venkateswaran et al. | DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning | |
CN112632234A (en) | Human-computer interaction method and device, intelligent robot and storage medium | |
CN111723198A (en) | Text emotion recognition method and device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |