CN110019687B - Multi-intention recognition system, method, equipment and medium based on knowledge graph - Google Patents
Multi-intention recognition system, method, equipment and medium based on knowledge graph Download PDFInfo
- Publication number
- CN110019687B CN110019687B CN201910290156.0A CN201910290156A CN110019687B CN 110019687 B CN110019687 B CN 110019687B CN 201910290156 A CN201910290156 A CN 201910290156A CN 110019687 B CN110019687 B CN 110019687B
- Authority
- CN
- China
- Prior art keywords
- text
- graph
- user
- knowledge
- knowledge graph
- 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.)
- Active
Links
Images
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)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a multi-intention recognition system, a method, equipment and a medium based on a knowledge graph, which comprises the following steps: the knowledge graph is used for providing a data base for graph calculation and reasoning; the entity identification module is used for identifying text entities and text attributes from the input text of the user based on the knowledge graph; the graph calculation module is used for performing graph calculation and identifying user problems on the basis of the knowledge graph, the text entities and the text attributes output by the entity identification module; and the interaction module is used for calling the graph calculation module, acquiring the user question, and recalling and generating answers from a knowledge base. According to the invention, multi-intention recognition is automatically carried out according to the knowledge graph, and the method is not limited to punctuation, sentence pattern and syntactic analysis, when the user intention is unclear, intention convergence is realized by automatically asking back, the question recognition rate and accuracy rate are effectively improved, the flexibility of the question-answering robot is greatly improved, and the dialogue is natural.
Description
Technical Field
The invention relates to the technical field of computer question answering, in particular to a knowledge graph-based multi-intention recognition system, a method, equipment and a medium.
Background
Currently in the field of question and answer, traditional multi-intent recognition uses simple punctuation-based sentence segmentation, or combines syntactic analysis, such as "what is called as just guard? How many years should the defense be judged? "based on the punctuations such as question, sentence, exclamation mark, etc., can be divided into two questions," what is the proper defense "," how many years the defense is judged for ", according to the divided questions, recall in the knowledge base through similar matching respectively; for another example, "do killers violate law? How many years are judged? The question-answering system can be divided into 'man-killing illegal', 'judge how many years', the problem after division can be known that the latter sentence lacks the subject through syntactic analysis, and a better question-answering system in the prior art can extract the subject from the former sentence and judge whether the subject should be completed through a model. It can be seen that in the prior art, the questioner can use correct grammatical expression, even correct punctuation, for multi-purpose recognition, and in the actual dialogue question answering, because the questioner has different levels and strong spoken language randomness, more missing contents are possible, more grammatical errors are possible, the questioning purpose is unclear, and the purpose is difficult to be correctly recognized through punctuation and sentence syntactic analysis.
Disclosure of Invention
Aiming at the problems, the invention provides a multi-intention recognition system, a method, equipment and a medium based on a knowledge graph, which can automatically ask an uncertain intention based on a disambiguation model in the process of multi-intention recognition and segmentation of user questions, realize intention convergence, effectively improve the question recognition rate and accuracy rate, greatly improve the flexibility of a question-answering robot and have natural conversation.
The invention specifically comprises the following steps:
a knowledge-graph based multi-intent recognition system, comprising:
the knowledge graph is used for providing a data base for graph calculation and reasoning;
the entity identification module is used for identifying text entities and text attributes from the input text of the user based on the knowledge graph;
the graph calculation module is used for performing graph calculation and identifying user problems on the basis of the knowledge graph, the text entities and the text attributes output by the entity identification module;
and the interaction module is used for calling the graph calculation module, acquiring the user question, and recalling and generating answers from a knowledge base.
Furthermore, the knowledge graph is established according to industries, and different industries respectively correspond to different knowledge graphs; and after the knowledge graph is established, storing the knowledge graph in a graph database in an RDF mode.
Further, the entity identification module is further configured to:
judging whether a text entity identified from a user input text is ambiguous or not, if so, calculating ambiguity classification and ambiguity probability based on a disambiguation model, automatically generating a disambiguation question to ask a user reversely, and carrying out disambiguation on the text entity according to a user answer; otherwise, no processing is performed.
Further, the graph calculation module performs graph calculation to identify a user problem, and specifically includes:
performing path calculation on the text entity and the text attribute, and when nodes are missing in the path, automatically completing the nodes to obtain a complete path and ensure path connectivity;
and performing intention segmentation according to the path, and identifying the user problem.
A multi-intention recognition method based on knowledge graph comprises the following steps:
identifying text entities and text attributes from the user input text based on the knowledge-graph;
performing graph calculation based on the knowledge graph, the text entity and the text attribute, and identifying a user problem;
and according to the user question, recalling and generating an answer from a knowledge base.
Furthermore, the knowledge graph is established according to industries, and different industries respectively correspond to different knowledge graphs; and after the knowledge graph is established, storing the knowledge graph in a graph database in an RDF mode.
Further, after the text entity and the text attribute are identified from the user input text, the method further includes:
judging whether a text entity identified from a user input text is ambiguous or not, if so, calculating ambiguity classification and ambiguity probability based on a disambiguation model, automatically generating a disambiguation question to ask a user reversely, and carrying out disambiguation on the text entity according to a user answer; otherwise, no processing is performed.
Further, the performing graph calculation and identifying a user problem specifically include:
performing path calculation on the text entity and the text attribute, and when nodes are missing in the path, automatically completing the nodes to obtain a complete path and ensure path connectivity;
and performing intention segmentation according to the path, and identifying the user problem.
An electronic device, comprising: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space enclosed by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory, for performing the above-described knowledge-graph-based multi-intent recognition method.
A computer-readable storage medium storing one or more programs which are executable by one or more processors to implement the above-described knowledge-graph-based multi-intent recognition method.
The invention has the beneficial effects that:
aiming at input texts asked by users, the multi-purpose recognition is automatically carried out according to a knowledge graph, the multi-purpose recognition is not limited to punctuation, sentence pattern and syntactic analysis, the purpose is automatically segmented, and answers are generated; when the user intention is unclear, intention convergence can be realized through automatic question return after self-reasoning, the problem recognition rate and the accuracy rate are effectively improved, the flexibility of the question-answering robot is greatly improved, and the dialogue is natural.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
FIG. 1 is a block diagram of a knowledge-graph based multi-intent recognition system according to an embodiment of the present invention;
FIG. 2 is a schematic view of a knowledge graph according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a path in a graph calculation process according to an embodiment of the present invention;
FIG. 4 is a flowchart of a knowledge-graph based multi-intent recognition method according to an embodiment of the present invention;
FIG. 5 is a flow chart of another knowledge-graph based multi-intent recognition method according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
Referring to fig. 1, an embodiment of a knowledge-graph-based multi-intent recognition system according to the present invention includes:
the knowledge graph 11 is used for providing a data base for graph calculation and reasoning;
an entity identification module 12, configured to identify a text entity and a text attribute from a user input text based on the knowledge graph;
the graph calculation module 13 is used for performing graph calculation and identifying a user problem based on the knowledge graph, the text entity and the text attribute output by the entity identification module;
and the interaction module 14 is used for calling the graph calculation module, acquiring the user question, and recalling and generating an answer from a knowledge base.
Preferably, the knowledge graph is established according to industries, and different industries respectively correspond to different knowledge graphs; after the knowledge graph is established, storing the knowledge graph in a graph database in an RDF mode; taking the securities industry as an example, a schematic diagram of a knowledge map is given, as shown in fig. 2.
Preferably, the entity identification module is further configured to:
judging whether a text entity identified from a user input text is ambiguous or not, if so, calculating ambiguity classification and ambiguity probability based on a disambiguation model, automatically generating a disambiguation question to ask a user reversely, and carrying out disambiguation on the text entity according to a user answer; otherwise, no processing is performed.
For example, the user enters text, i.e., the user asks the question "i want to buy peace, how to buy", the system recognizes the text entity "peace", attribute "buy";
in general, security may mean security, which is an alternative name of security in China in the field of securities, but the text entity has no ambiguity and does not need disambiguation based on the security industry knowledge graph;
based on the knowledge graph, the stock ticket example of China's security is further identified to belong to the two concepts of harbor stocks and A stocks respectively, and the two concepts are stock sub-concepts, so that the identification result of the user problem is as follows:
entity: chinese safety (isa harbor stock, isa A stock), harbor stock [ isa stock ], A stock [ isa stock ]
The attributes are as follows: purchasing
Because the harbor stock and the A stock belong to the stock, the system can not automatically disambiguate, so the disambiguation problem is automatically generated to ask the user back:
asking whether to purchase the Chinese peace [02318.HK ] or the Chinese peace [601318 ]?
And finally, determining which concept entity the text entity belongs to specifically according to the user response.
Preferably, the graph calculation module performs graph calculation to identify a user problem, and specifically includes:
performing path calculation on the text entity and the text attribute, and when nodes are missing in the path, automatically completing the nodes to obtain a complete path and ensure path connectivity;
and performing intention segmentation according to the path, and identifying the user problem.
In general, a question of inputting text by a user may have 1-3 intentions, a single intention is not considered in the invention, more than 2 intentions are similar to the processing mode of 2 intentions, and therefore, 2 intentions are taken as an example to give a graph calculation embodiment; the path schematic diagram during path calculation is shown in fig. 3, and includes the following calculation conditions:
(1) a, b, identifying two text entities and forming two complete paths, and at the moment, directly performing intention segmentation according to the paths to generate two problems;
(2) c, identifying a text entity, starting from the text entity to form two complete paths, and at the moment, also directly performing intent segmentation according to the paths, and completing the text entity during segmentation to generate two problems;
(3) e, distinguishing two situations, namely identifying a text entity, starting from the text entity to form two complete paths, and carrying out attribute node completion on the two complete paths without the middle part, wherein the two situations are the same as the processing method (2); secondly, a text entity is identified, two paths are formed by starting from the text entity, attribute node completion occurs in the middle, a starting point and an end point are determined from the view of the graph, the middle node is obtained by reasoning, at the moment, intention segmentation is carried out according to the completed paths, the entity is completed during segmentation, two problems are generated, and intention clarification is carried out by asking the user backwards.
Taking b as an example, the user asks the 'delivery rule of port stock and A stock', and the system performs entity identification:
entity: gang, strand a; the attributes are as follows: rules of delivery
According to the knowledge graph, the port attribute has a delivery rule, and the A stock attribute also has a delivery rule, so that the intention splitting is carried out:
entity 1: harbor strand, property: rules of delivery
Problem 1: rules of port stock delivery
Entity 2: strand A, attribute: rules of delivery
Problem 2: and (4) the collection rule of A shares.
As shown in fig. 4, an embodiment of the method for recognizing multiple intents based on knowledge-graph of the present invention includes:
s41: identifying text entities and text attributes from the user input text based on the knowledge-graph;
s42: performing graph calculation based on the knowledge graph, the text entity and the text attribute, and identifying a user problem;
s43: and according to the user question, recalling and generating an answer from a knowledge base.
Preferably, the knowledge graph is established according to industries, and different industries respectively correspond to different knowledge graphs; and after the knowledge graph is established, storing the knowledge graph in a graph database in an RDF mode.
Preferably, after the text entity and the text attribute are identified from the user input text, the method further includes:
judging whether a text entity identified from a user input text is ambiguous or not, if so, calculating ambiguity classification and ambiguity probability based on a disambiguation model, automatically generating a disambiguation question to ask a user reversely, and carrying out disambiguation on the text entity according to a user answer; otherwise, no processing is performed.
Preferably, the performing graph calculation and identifying the user problem specifically include:
performing path calculation on the text entity and the text attribute, and when nodes are missing in the path, automatically completing the nodes to obtain a complete path and ensure path connectivity;
and performing intention segmentation according to the path, and identifying the user problem.
To further illustrate the present invention, another embodiment of a knowledge-graph-based multi-intent recognition method is provided, as shown in fig. 5, including:
s51: receiving a user question;
s52: performing text entity and attribute identification on the user question;
s53: judging whether the identified text entity is a multi-entity or an attribute branch, if so, entering S54; otherwise, judging that the user question is a single intention;
meanwhile, judging whether the identified text entity has an uncertain superior, if so, asking the user in reverse to obtain the user selection and clear intention; otherwise, the intention can be directly made clear;
s54: performing intention segmentation according to a path calculation result;
s55: and obtaining a segmented intention list.
An embodiment of the present invention further provides an electronic device, as shown in fig. 6, which can implement the processes in the embodiments shown in fig. 4 to 5 of the present invention, and as shown in fig. 6, the electronic device may include: the electronic device comprises a shell 61, a processor 62, a memory 63, a circuit board 64 and a power circuit 65, wherein the circuit board 64 is arranged inside a space enclosed by the shell 61, and the processor 62 and the memory 63 are arranged on the circuit board 64; a power supply circuit 65 for supplying power to each circuit or device of the electronic apparatus; the memory 63 is used to store executable program code; the processor 62 executes a program corresponding to the executable program code by reading the executable program code stored in the memory 63, for executing the method described in any of the foregoing embodiments.
The specific execution process of the above steps by the processor 62 and the steps further executed by the processor 62 by running the executable program code may refer to the description of the embodiment shown in fig. 4 to 5 of the present invention, and are not described herein again.
The electronic device exists in a variety of forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include: smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. This type of device comprises: audio, video players (e.g., ipods), handheld game consoles, electronic books, and smart toys and portable car navigation devices.
(4) A server: the device for providing the computing service comprises a processor, a hard disk, a memory, a system bus and the like, and the server is similar to a general computer architecture, but has higher requirements on processing capacity, stability, reliability, safety, expandability, manageability and the like because of the need of providing high-reliability service.
(5) And other electronic equipment with data interaction function.
Embodiments of the present invention also provide a computer-readable storage medium storing one or more programs, which are executable by one or more processors to implement the aforementioned method of knowledge-graph based multi-intent recognition.
Aiming at input texts asked by users, the multi-purpose recognition is automatically carried out according to a knowledge graph, the multi-purpose recognition is not limited to punctuation, sentence pattern and syntactic analysis, the purpose is automatically segmented, and answers are generated; when the user intention is unclear, intention convergence can be realized through automatic question return after self-reasoning, the problem recognition rate and the accuracy rate are effectively improved, the flexibility of the question-answering robot is greatly improved, and the dialogue is natural.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (4)
1. A knowledge-graph-based multi-intent recognition system, comprising: the knowledge graph is used for providing a data base for graph calculation and reasoning; the entity identification module is used for identifying text entities and text attributes from the input text of the user based on the knowledge graph; the graph calculation module is used for performing graph calculation and identifying user problems on the basis of the knowledge graph, the text entities and the text attributes output by the entity identification module; the interaction module is used for calling the graph calculation module, acquiring the user question, and recalling and generating answers from a knowledge base;
the knowledge graph is established according to industries, and different industries respectively correspond to different knowledge graphs; after the knowledge graph is established, storing the knowledge graph in a graph database;
the entity identification module is further configured to: judging whether a text entity identified from a user input text is ambiguous or not, if so, calculating ambiguity classification and ambiguity probability based on a disambiguation model, automatically generating a disambiguation question to ask a user reversely, and carrying out disambiguation on the text entity according to a user answer; otherwise, no processing is carried out;
the graph calculation module performs graph calculation to identify a user problem, and specifically includes: performing path calculation on the text entity and the text attribute, and when nodes are missing in the path, automatically completing the nodes to obtain a complete path; and performing intention segmentation according to the path, and identifying the user problem.
2. A multi-intention recognition method based on knowledge graph is characterized by comprising the following steps:
identifying text entities and text attributes from the user input text based on the knowledge-graph;
performing graph calculation based on the knowledge graph, the text entity and the text attribute, and identifying a user problem; according to the user question, answer recall and generation are carried out from a knowledge base;
the knowledge graph is established according to industries, and different industries respectively correspond to different knowledge graphs; after the knowledge graph is established, storing the knowledge graph in a graph database;
after the text entity and the text attribute are identified from the user input text, the method further comprises: judging whether a text entity identified from a user input text is ambiguous or not, if so, calculating ambiguity classification and ambiguity probability based on a disambiguation model, automatically generating a disambiguation question to ask a user reversely, and carrying out disambiguation on the text entity according to a user answer; otherwise, no processing is carried out;
the graph calculation and user problem identification specifically comprise: performing path calculation on the text entity and the text attribute, and when nodes are missing in the path, automatically completing the nodes to obtain a complete path; and performing intention segmentation according to the path, and identifying the user problem.
3. An electronic device, characterized in that the electronic device comprises: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space enclosed by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; the processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory, for performing the method of claim 2.
4. A computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs which are executable by one or more processors to implement the method of claim 2.
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 CN110019687A (en) | 2019-07-16 |
| CN110019687B true 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) |
Families Citing this family (9)
| 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 |
| 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 |
| 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 |
| 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 |
| CN115440200B (en) * | 2021-06-02 | 2024-03-12 | 上海擎感智能科技有限公司 | Control method and control system of vehicle-mounted 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 |
Citations (14)
| 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 |
| 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 |
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2013214801B2 (en) * | 2012-02-02 | 2018-06-21 | Visa International Service Association | Multi-source, multi-dimensional, cross-entity, multimedia database platform apparatuses, methods and systems |
| US10565508B2 (en) * | 2014-12-12 | 2020-02-18 | International Business Machines Corporation | Inferred facts discovered through knowledge graph derived contextual overlays |
-
2019
- 2019-04-11 CN CN201910290156.0A patent/CN110019687B/en active Active
Patent Citations (14)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110019687A (en) | 2019-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110019687B (en) | Multi-intention recognition system, method, equipment and medium based on knowledge graph | |
| US11152007B2 (en) | Method, and device for matching speech with text, and computer-readable storage medium | |
| CN110349572B (en) | Voice keyword recognition method and device, terminal and server | |
| CN112417102B (en) | Voice query method, device, server and readable storage medium | |
| CN111949787A (en) | Automatic question-answering method, device, equipment and storage medium based on knowledge graph | |
| CN111177359A (en) | Multi-turn dialogue method and device | |
| CN115357704B (en) | Processing method and related device for heterogeneous plot nodes in voice interaction novel | |
| CN109460503B (en) | Answer input method, answer input device, storage medium and electronic equipment | |
| CN110795544B (en) | Content searching method, device, equipment and storage medium | |
| CN109492085B (en) | Answer determination method, device, terminal and storage medium based on data processing | |
| CN112686051B (en) | Semantic recognition model training method, recognition method, electronic device and storage medium | |
| CN114757176A (en) | Method for obtaining target intention recognition model and intention recognition method | |
| CN110727782A (en) | Question and answer corpus generation method and system | |
| CN113468894A (en) | Dialogue interaction method and device, electronic equipment and computer-readable storage medium | |
| CN112183098A (en) | Session processing method and device, storage medium and electronic device | |
| CN107657949A (en) | The acquisition methods and device of game data | |
| CN115470318A (en) | Customer service problem processing method and device | |
| CN117194730B (en) | Intention recognition and question answering method and device, electronic equipment and storage medium | |
| CN110750633B (en) | Method and device for determining answer of question | |
| CN117421403A (en) | Intelligent dialogue method and device and electronic equipment | |
| CN117370512A (en) | Method, device, equipment and storage medium for replying to dialogue | |
| CN110263346B (en) | Semantic analysis method based on small sample learning, electronic equipment and storage medium | |
| CN111753062A (en) | Method, device, equipment and medium for determining session response scheme | |
| CN114818665B (en) | Multi-purpose recognition method and system based on bert+bilstm+crf and xgboost model | |
| CN111324712A (en) | Dialogue reply method and server |
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 |