Knowledge graph construction method, knowledge graph construction system and computer equipment

A knowledge map and construction method technology, applied in the field of computer software, can solve problems such as the absence of data sources, the inability to completely eliminate entity noise and ambiguity, and the inability to guarantee the quality of knowledge maps

Pending Publication Date: 2021-03-02
江苏鲸准数科信息产业发展有限责任公司
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the currently disclosed construction method of the indicator map, there is no corresponding processing for the data source, so that the extracted knowledge unit contains too much noise or ambigu

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 construction method, knowledge graph construction system and computer equipment
  • Knowledge graph construction method, knowledge graph construction system and computer equipment
  • Knowledge graph construction method, knowledge graph construction system and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Such as figure 1 As shown, a method for constructing a knowledge map, the application scenario is an investor-oriented enterprise knowledge map, including

[0059] Construct an ontology model, and construct an ontology model according to the data source and business characteristics related to the field where the enterprise is located;

[0060] Knowledge extraction, identify the named entity of the entity of the current data source to obtain multiple named entities; connect multiple named entities to obtain multiple entity relationships; extract by combining graph database, relational database and document database The knowledge unit is stored;

[0061] Knowledge fusion, identifying similar entities through entity linking, associating different expressions of the same entity; and merging different attributes of the same entity or different attribute values ​​of the same attribute of the same entity, while removing duplicate entities, attributes, and relationships;

[0...

Embodiment 2

[0092] A method for constructing an insect knowledge graph, comprising

[0093] Build an ontology model, and build an ontology model based on data sources related to the biological field and insect characteristics;

[0094] Knowledge extraction, identify the named entity of the entity of the current data source to obtain multiple named entities; connect multiple named entities to obtain multiple entity relationships; extract by combining graph database, relational database and document database The knowledge unit is stored;

[0095] Knowledge fusion, identifying similar entities through entity linking, associating different expressions of the same entity; and merging different attributes of the same entity or different attribute values ​​of the same attribute of the same entity, while removing duplicate entities, attributes, and relationships;

[0096] Entity disambiguation, to obtain all target objects that refer to entity items that have not been disambiguated, use database...

Embodiment 3

[0127] A system for building knowledge graphs, including

[0128] The data source collection unit is used to collect relevant data sources in the field of the predetermined scene;

[0129] An entity modeling unit, configured to establish an entity model according to relevant data sources in the domain of the predetermined scene;

[0130] The knowledge extraction unit is used to identify the named entity of the entity of the data source to obtain multiple named entities; connect multiple named entities to obtain multiple entity relationships; through the combination of graph database, relational database and document database Extracted knowledge units and store them;

[0131] The knowledge fusion unit is used to identify similar entities and associate different expressions of the same entity; and merge different attributes of the same entity or different attribute values ​​of the same attribute of the same entity, and remove duplicate entities, attributes and relationships;

...

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 construction method, which comprises the steps of constructing an ontology model, and constructing the ontology model according to data sources and service features related to a domain where a preset application scene is located; carrying out knowledge extraction and knowledge fusion, and removing repeated entities, attributes and relations; carrying out entity disambiguation, calculating similarity according to the extracted keywords, and removing entities of which the similarity is lower than a first preset threshold in the text information; carryingout knowledge processing, processing the knowledge graph after knowledge fusion and entity disambiguation, and constructing the knowledge graph of the enterprise. The invention further discloses a knowledge graph construction system and computer equipment. In the steps of knowledge fusion and entity disambiguation, repeated entities with ambiguity, polysemy and the like are removed, and a high-quality knowledge graph is constructed.

Description

technical field [0001] The present invention relates to the technical field of computer software, in particular to a method for constructing an enterprise knowledge map and its system and application. Background technique [0002] The research on knowledge graph (Knowledge graph) can be traced back to 1977. At the Fifth International Conference on Artificial Intelligence, American computer scientist Feigenbaum B.A. first proposed the concept of knowledge engineering. Knowledge engineering is a system that uses the existing knowledge in the knowledge base to solve the problems raised by users, the most classic of which is the expert system. In 2012, Google (Google) released the knowledge map project and announced that it would build a next-generation intelligent search engine based on it. Through the description of various entities and their relationships in the objective real world, the project forms a huge semantic structure network map, which connects all kinds of complic...

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
IPC IPC(8): G06F16/36G06F40/284G06F40/295G06F40/30G06K9/62
CPCG06F16/367G06F40/284G06F40/295G06F40/30G06F18/22
Inventor 柴源
Owner 江苏鲸准数科信息产业发展有限责任公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap