Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Question answering system construction method and system based on military domain knowledge graph

A technology of domain knowledge and question answering system, applied in the fields of semantic tool creation, unstructured text data retrieval, semantic analysis, etc., can solve problems such as lack of knowledge and blankness, and achieve the effect of accurate and efficient recognition of the battlefield situation

Pending Publication Date: 2021-12-17
NAT UNIV OF DEFENSE TECH
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most military users often do not have the above capabilities, and the current automatic question answering system for knowledge graphs in the military field is still blank

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
  • Question answering system construction method and system based on military domain knowledge graph
  • Question answering system construction method and system based on military domain knowledge graph
  • Question answering system construction method and system based on military domain knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0034] like figure 1 As shown, the question answering system construction method based on the knowledge map in the military field of this embodiment includes steps:

[0035] 1) Ontology modeling using hybrid ontology method;

[0036] 2) Use data from different sources to build a knowledge map for the military field and store it in the graph database;

[0037] 3) Collect battlefield information knowledge question-and-answer questions in the form of questionnaires, and build knowledge question-and-answer query templates centered on the query intentions in the questions;

[0038] 4) Input natural language questions, classify the questions, and obtain classification results;

[0039] 5) matching the corresponding query template for the question sentence according to the classification result;

[0040] 6) Find out the entity in the question sent...

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 question answering system construction method and system based on military domain knowledge graph. The method comprises the following steps: 1) carrying out ontology modeling by adopting a mixed ontology method; 2) constructing a military field-oriented knowledge graph by using data from different sources, and storing the knowledge graph in a graph database; 3) collecting battlefield information knowledge question and answer sentences in a questionnaire mode, and constructing a knowledge question and answer query template by taking query intentions in the question sentences as centers; 4) inputting natural language questions, and classifying the questions to obtain a classification result; 5) matching a corresponding query template for the question according to the classification result; 6) finding out an entity in the question to perfect the query statement; and 7) searching answers in the graph database through the query statement, and returning the answers. According to the invention, the user is helped to quickly and accurately recommend the battlefield situation knowledge from the military knowledge graph in a natural language question form, so that a commander can accurately and efficiently recognize the battlefield situation, and the method has important application value.

Description

technical field [0001] The present invention mainly relates to the technical field of artificial intelligence, and in particular to a method and system for constructing a question answering system based on knowledge graphs in the military field. Background technique [0002] Knowledge graph is a knowledge system formed by structuring human knowledge, which contains basic facts, general rules and other relevant information, and can be used for information retrieval, reasoning and decision-making and other intelligent technologies. The earliest application of knowledge graph was to improve the capabilities of search engines, and later it showed rich application value in many fields such as auxiliary question answering, natural language understanding, and recommendation calculation. Understanding the user's query intention is to construct the user's query input into a structured statement, or let the user directly propose a structured query. However, this method requires the us...

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): G06F16/332G06F16/33G06F16/35G06F16/36G06F40/186G06F40/242G06F40/247G06F40/295G06F40/30
CPCG06F16/3329G06F16/3344G06F16/35G06F16/367G06F40/186G06F40/242G06F40/247G06F40/295G06F40/30
Inventor 黄健周葱刘权龚建兴马可张中杰
Owner NAT UNIV OF DEFENSE TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products