CN113139041A - Modularized intelligent question-answering method and system - Google Patents
Modularized intelligent question-answering method and system Download PDFInfo
- Publication number
- CN113139041A CN113139041A CN202110423169.8A CN202110423169A CN113139041A CN 113139041 A CN113139041 A CN 113139041A CN 202110423169 A CN202110423169 A CN 202110423169A CN 113139041 A CN113139041 A CN 113139041A
- Authority
- CN
- China
- Prior art keywords
- module
- intelligent
- question
- chatting
- aiml
- 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
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
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
-
- 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
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a modular intelligent question answering method and system. The intelligent question answering module is applied to the intelligent robot and provides an intelligent question answering module for the intelligent robot. The method and the system comprise a text input module, an intention recognition module, an AIML chatting module, a knowledge graph module and an intelligent retrieval module. The text input module receives user input, and can manually input text or convert the text into characters for voice; the intention identification module classifies the problems based on semantic analysis and identifies task-type and non-task-type problems; the AIML chatting module presets chatting questions based on AIML; the knowledge graph module queries problems based on wikidata data; and the intelligent retrieval module is used as the last module to call the hundred-degree retrieval result and return the result. The intelligent question and answer system integrates the chatting module, the knowledge map module and the intelligent search module, provides a rich knowledge base for the household intelligent robot, and can conveniently expand and disassemble each module as an independent service, thereby meeting the intelligent question and answer requirement of the household robot.
Description
Technical Field
The invention relates to a modular intelligent question answering method and system, and belongs to the technical field of knowledge maps and natural language understanding.
Background
With the rapid development of artificial intelligence technology, intelligent question-answering robots are widely applied in different fields and scenes, but domestic intelligent question-answering robots are not yet popularized, the existing robots usually ask questions and answer questions in specific fields, the scenes are single, and the application to domestic intelligent robots is not very good in universality.
In order to solve the problems, an intelligent question and answer method which integrates chatting, knowledge maps and an intelligent search module, provides a rich knowledge base for a household intelligent robot, can be conveniently expanded and disassembled as independent services and can meet the intelligent question and answer requirements of the household robot is urgently needed.
Disclosure of Invention
The invention aims to provide a modular intelligent question-answering method and a modular intelligent question-answering system, which not only provide a rich knowledge base for a household intelligent robot, but also can conveniently expand and disassemble each module as an independent service.
In order to achieve the purpose, the invention is realized by the following technical scheme:
a modularized intelligent question-answering system comprises a text input module, an intention identification module, an AIML chatting module, a knowledge graph module and an intelligent retrieval module;
the text input module receives user input, and can manually input text or convert the text into characters for voice;
the intention identification module classifies the problems based on semantic analysis and identifies task-type and non-task-type problems;
the AIML chatting module is used for presetting chatting problems based on AIML and can be conveniently expanded;
the knowledge graph module queries the data in the Blazegraph database;
and the intelligent retrieval module is used as the last module to call the third-party Baidu interface query result and return the third-party Baidu interface query result.
Preferably, the knowledge graph module performs question queries on data in the blackegraph database using SPARQL statements based on wikidata data.
A modular intelligent question answering method comprises the following steps:
step 1: a user inputs a sentence of natural language through a text input module;
step 2: after receiving text input, the intention identification module analyzes the intention by using a semantic analysis and natural language processing method, identifies task type question and non-task type question, if the question is task type, other task type question processing modules are called, and if the question is non-task type question, a chatting module is called;
and step 3: the chatting module presets chatting corpora in advance based on the AIML and can extend the corpora at any time; if the answer is not matched in the chatting module, entering a knowledge graph-based module;
and 4, step 4: after entering a knowledge graph module, extracting entities and attributes through a semantic analysis module, generating a SPARQL statement, calling wikitata to execute SPARQL query, and if the knowledge graph module does not match answers, entering an intelligent retrieval module;
and 5: and after entering the intelligent retrieval module, calling a third-party Baidu interface for searching, acquiring a question answer and returning the question answer to the intelligent robot.
The invention has the advantages that: the intelligent question and answer system integrates the chatting module, the knowledge map module and the intelligent search module, provides a rich knowledge base for the household intelligent robot, and can conveniently expand and disassemble each module as an independent service, thereby meeting the intelligent question and answer requirement of the household robot.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
FIG. 1 is a schematic view of the flow structure of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A modularized intelligent question-answering system comprises a text input module, an intention identification module, an AIML chatting module, a knowledge graph module and an intelligent retrieval module; the text input module receives user input, and can manually input text or convert the text into characters for voice; the intention identification module classifies the problems based on semantic analysis and identifies task-type and non-task-type problems; the AIML chatting module is used for presetting chatting problems based on AIML and can be conveniently expanded; the knowledge graph module queries the data in the Blazegraph database; and the intelligent retrieval module is used as the last module to call the third-party Baidu interface query result and return the third-party Baidu interface query result. And the knowledge map module performs problem query on data in the Blazegraph database by using a SPARQL statement based on wikidata data.
A modular intelligent question answering method comprises the following steps:
step 1: a user inputs a sentence of natural language through a text input module;
step 2: after receiving text input, the intention identification module analyzes the intention by using a semantic analysis and natural language processing method, identifies task type question and non-task type question, if the question is task type, other task type question processing modules are called, and if the question is non-task type question, a chatting module is called;
and step 3: the chatting module presets chatting corpora in advance based on the AIML and can extend the corpora at any time; if the answer is not matched in the chatting module, entering a knowledge graph-based module;
and 4, step 4: after entering a knowledge graph module, extracting entities and attributes through a semantic analysis module, generating a SPARQL statement, calling wikitata to execute SPARQL query, and if the knowledge graph module does not match answers, entering an intelligent retrieval module;
and 5: and after entering the intelligent retrieval module, calling a third-party Baidu interface for searching, acquiring a question answer and returning the question answer to the intelligent robot.
Claims (3)
1. A modularized intelligent question-answering system is characterized by comprising a text input module, an intention recognition module, an AIML chatting module, a knowledge graph module and an intelligent retrieval module;
the text input module receives user input, and can manually input text or convert the text into characters for voice;
the intention identification module classifies the problems based on semantic analysis and identifies task-type and non-task-type problems;
the AIML chatting module is used for presetting chatting problems based on AIML and can be conveniently expanded;
the knowledge graph module queries the data in the Blazegraph database;
and the intelligent retrieval module is used as the last module to call the third-party Baidu interface query result and return the third-party Baidu interface query result.
2. The modular intelligent question-answering method according to claim 1, wherein the knowledge graph module performs question queries on data in the bluzegraph database using SPARQL sentences based on wikidata data.
3. A modular intelligent question-answering method using claim 1, characterized by comprising the steps of:
step 1: a user inputs a sentence of natural language through a text input module;
step 2: after receiving text input, the intention identification module analyzes the intention by using a semantic analysis and natural language processing method, identifies task type question and non-task type question, if the question is task type, other task type question processing modules are called, and if the question is non-task type question, a chatting module is called;
and step 3: the chatting module presets chatting corpora in advance based on the AIML and can extend the corpora at any time; if the answer is not matched in the chatting module, entering a knowledge graph-based module;
and 4, step 4: after entering a knowledge graph module, extracting entities and attributes through a semantic analysis module, generating a SPARQL statement, calling wikitata to execute SPARQL query, and if the knowledge graph module does not match answers, entering an intelligent retrieval module;
and 5: and after entering the intelligent retrieval module, calling a third-party Baidu interface for searching, acquiring a question answer and returning the question answer to the intelligent robot.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110423169.8A CN113139041A (en) | 2021-04-20 | 2021-04-20 | Modularized intelligent question-answering method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110423169.8A CN113139041A (en) | 2021-04-20 | 2021-04-20 | Modularized intelligent question-answering method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113139041A true CN113139041A (en) | 2021-07-20 |
Family
ID=76812957
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110423169.8A Pending CN113139041A (en) | 2021-04-20 | 2021-04-20 | Modularized intelligent question-answering method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113139041A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113821621A (en) * | 2021-09-28 | 2021-12-21 | 中电万维信息技术有限责任公司 | Open intelligent customer service system based on deep learning |
CN115146066A (en) * | 2022-09-05 | 2022-10-04 | 深圳市华付信息技术有限公司 | Man-machine interaction method, device, equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110765257A (en) * | 2019-12-30 | 2020-02-07 | 杭州识度科技有限公司 | Intelligent consulting system of law of knowledge map driving type |
CN112035640A (en) * | 2020-08-31 | 2020-12-04 | 重庆长安汽车股份有限公司 | Refined question-answering method based on intelligent question-answering robot, storage medium and intelligent equipment |
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 |
CN112527965A (en) * | 2020-12-18 | 2021-03-19 | 国家电网有限公司客户服务中心 | Automatic question answering implementation method and device based on combination of professional library and chatting library |
CN112632239A (en) * | 2020-12-11 | 2021-04-09 | 南京三眼精灵信息技术有限公司 | Brain-like question-answering system based on artificial intelligence technology |
-
2021
- 2021-04-20 CN CN202110423169.8A patent/CN113139041A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110765257A (en) * | 2019-12-30 | 2020-02-07 | 杭州识度科技有限公司 | Intelligent consulting system of law of knowledge map driving type |
CN112035640A (en) * | 2020-08-31 | 2020-12-04 | 重庆长安汽车股份有限公司 | Refined question-answering method based on intelligent question-answering robot, storage medium and intelligent equipment |
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 |
CN112632239A (en) * | 2020-12-11 | 2021-04-09 | 南京三眼精灵信息技术有限公司 | Brain-like question-answering system based on artificial intelligence technology |
CN112527965A (en) * | 2020-12-18 | 2021-03-19 | 国家电网有限公司客户服务中心 | Automatic question answering implementation method and device based on combination of professional library and chatting library |
Non-Patent Citations (1)
Title |
---|
理查德·M.里斯: "《Java自然语言处理》", 31 July 2020 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113821621A (en) * | 2021-09-28 | 2021-12-21 | 中电万维信息技术有限责任公司 | Open intelligent customer service system based on deep learning |
CN113821621B (en) * | 2021-09-28 | 2023-10-27 | 中电万维信息技术有限责任公司 | Open intelligent customer service system based on deep learning |
CN115146066A (en) * | 2022-09-05 | 2022-10-04 | 深圳市华付信息技术有限公司 | Man-machine interaction method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020258654A1 (en) | Answer acquisition method and device | |
CN108345690B (en) | Intelligent question and answer method and system | |
CN106777018B (en) | Method and device for optimizing input sentences in intelligent chat robot | |
CN107153965A (en) | A kind of intelligent customer service solution of multiple terminals | |
CN113139041A (en) | Modularized intelligent question-answering method and system | |
CN104598445A (en) | Automatic question-answering system and method | |
WO2020253064A1 (en) | Speech recognition method and apparatus, and computer device and storage medium | |
CN109460459A (en) | A kind of conversational system automatic optimization method based on log study | |
CN110266900A (en) | Recognition methods, device and the customer service system that client is intended to | |
CN110825865A (en) | Multi-round conversation intelligent customer service system based on special word correction and cold start | |
CN112507089A (en) | Intelligent question-answering engine based on knowledge graph and implementation method thereof | |
CN108763355B (en) | User-based intelligent robot interactive data processing system and method | |
CN117370493A (en) | Intelligent interaction method and device for system based on large language model | |
CN111353026A (en) | Intelligent law attorney assistant customer service system | |
CN110362664A (en) | A kind of pair of chat robots FAQ knowledge base storage and matched method and device | |
CN112527983A (en) | Man-machine natural interaction service system for personalized government affairs | |
CN116226338A (en) | Multi-round dialogue system and method based on searching and generating fusion | |
CN112287082A (en) | Data processing method, device, equipment and storage medium combining RPA and AI | |
CN112685545A (en) | Intelligent voice interaction method and system based on multi-core word matching | |
CN114138957A (en) | Virtual customer service intelligent consultation method and system | |
CN113609268A (en) | Intelligent psychological knowledge question-answering method and device based on knowledge graph | |
CN112015920A (en) | Intelligent auxiliary learning system based on knowledge graph and edge calculation | |
CN113297361B (en) | Intelligent question-answer interaction system and method based on visual flow chart | |
CN115577092B (en) | User speech processing method and device, electronic equipment and computer storage medium | |
JPS63106042A (en) | Method for recognizing intention of conversation text |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210720 |