Knowledge graph-based question and answer implementation method and system

A technology of knowledge graph and implementation method, applied in the field of knowledge graph-based question answering implementation method and system, which can solve problems such as language incomputability, and achieve the effects of accurate content, optimized user experience, and fast search speed

Inactive Publication Date: 2021-02-05
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

To establish a question answering system for knowledge graphs, two core issues need to be solved: (1) Understand the semantics of questions - there are thousands of relationships in knowledge graphs, and a relationship can have thousands of questioning methods. For different question forms, Question answering systems use different representation methods, and these question representations must satisfy the ability to normalize questions with the same semantics and distinguish questions with different intentions; (2) user queries are usually expressed in natural language, such languages ​​cannot be directly expressed by knowledge map to calculate

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Knowledge graph-based question and answer implementation method and system
  • Knowledge graph-based question and answer implementation method and system
  • Knowledge graph-based question and answer implementation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] Such as figure 1 As shown, a question answering method based on knowledge graph includes the following steps:

[0045] Step S1, the natural language query is passed through the entity recognition model, and the subject entity mention is extracted;

[0046] Step S2, linking the subject entity mention to the corresponding entity in the knowledge graph, and placing the corresponding entity in the candidate entity set;

[0047] Step S3. Based on the knowledge map, each candidate entity in the candidate entity set is found to be connected to it, and placed in the candidate relationship set;

[0048] Step S4, replacing the entity mentions in the natural language query text with uniform invalid characters, and inputting the replaced query text and candidate relations into the relation extraction model to obtain the semantic relations of the query text;

[0049] Step S5, filtering out invalid entities in the candidate entity set based on the semantic relationship of the query...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a knowledge graph-based question and answer implementation method. The method comprises the following steps of: when a natural language query instruction of a user is received,firstly, carrying out entity mention extraction and entity linking on a query statement of the user to obtain a candidate entity set and a candidate relationship set of a query text; scoring the relationship matching degree between the query text and the candidate relationship set by using a relationship extraction technology, selecting the relationship with the highest score as a semantic relationship corresponding to the natural language query text, filtering out invalid entities in the candidate entity set based on the semantic relationship of the query text, and finding out semantic entities of the query text; constructing a query mode graph based on the extracted semantic entities and semantic relationships, and finding all matching items matched with the query mode graph in the knowledge graph, the matching items being answers retrieved by natural language query based on the knowledge graph. The invention further discloses a question and answer implementation system based on theknowledge graph. According to the invention, the user experience is optimized.

Description

technical field [0001] The present invention relates to the technical field of knowledge graph retrieval, in particular to a method and system for realizing question and answer based on knowledge graph. Background technique [0002] Knowledge graph organizes massive information in a structured way and efficiently provides answers to users' queries. Therefore, it has attracted widespread attention in academia and industry in recent years. In the knowledge graph, the query calculation mainly adopts the method of structural matching. That is, given a query pattern graph and a knowledge graph, find all matches in the knowledge graph that match the query pattern graph. [0003] The key to query knowledge graph lies in query comprehension and query calculation. To establish a question answering system for knowledge graphs, two core issues need to be solved: (1) Understand the semantics of questions - there are thousands of relationships in knowledge graphs, and a relationship ca...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F40/35G06F40/295G06N3/04
CPCG06F16/3329G06F40/35G06F40/295G06N3/044G06N3/045
Inventor 杨兰王欣展华益骆敏蒋伟
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products