A knowledge graph representation learning method based on multiple semantics

A technology of knowledge graphs and learning methods, applied in semantic analysis, database models, special data processing applications, etc., can solve problems such as inability to accurately represent connections

Active Publication Date: 2021-06-08
GUILIN UNIV OF ELECTRONIC TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] What the present invention aims to solve is the problem that existing knowledge map representation learning methods cannot accurately represent the relationship between entities under different semantics, and provides a knowledge map representation learning method based on multiple semantics to improve knowledge Spectral Accuracy

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
  • A knowledge graph representation learning method based on multiple semantics
  • A knowledge graph representation learning method based on multiple semantics
  • A knowledge graph representation learning method based on multiple semantics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will refer to and give examples to describe the present invention in more detail.

[0033] In the prior art, only the difference between entities and relations under the same semantic relationship type is considered, and the different semantics of the relationship in the triple structure information is not fully considered, and there are many learning parameters, so it cannot be accurately represented The connection between entities and relations is also not well applied to large-scale knowledge graphs. The present invention fully considers the different semantics of the relationship in the triple structure information of the knowledge map, and defines the relationship matrix M according to the different semantics of the relationship r . And the knowledge is expressed in the form of a typical (entity 1, relation, entity 2) triple, and ...

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 map representation learning method based on multiple semantics. Firstly, different semantics of relations are considered, a translation-based model between entity vectors and relational vectors is adopted, and different semantics of relations in a triple structure are used in combination with headers. The projection vector of the tail entity defines the relationship matrix, and well represents the correlation between the entity vector and the relationship vector in the triplet, without introducing more parameters; then use the loss function to associate the entity vector and the relationship vector , and optimize the loss function, when the optimization goal is achieved, the vector of each entity and the vector of the relationship in the knowledge graph can be learned. The invention solves the heterogeneity and imbalance of entities and relationships in the knowledge base, more accurately represents the entities and relationships and their interrelationships, and applies it to large-scale knowledge graphs.

Description

technical field [0001] The invention relates to the technical field of knowledge graphs, in particular to a knowledge graph representation learning method based on multiple semantics. Background technique [0002] With the rapid development of today's society, we have gradually entered an era of information and intelligence. Masses of new data and information are generated every day in different forms. The mobile Internet has become the most effective and convenient information acquisition platform in today's society. Users' demand for real information acquisition is increasingly urgent. How to obtain effective information from massive data has become a major problem in many fields. The knowledge graph came into being from this. [0003] As a new knowledge representation method, knowledge graph belongs to the category of semantic web. Its goal is to describe various entities and concepts in the real world, as well as the association between these entities and concepts, and...

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 Patents(China)
IPC IPC(8): G06F16/28G06F40/30
CPCG06F16/288G06F40/30
Inventor 常亮栗永芳祝曼丽古天龙徐周波
Owner GUILIN UNIV OF ELECTRONIC TECH
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