A knowledge graph representation method based on multi-core Gaussian distribution

A knowledge map and Gaussian distribution technology, applied in the creation of semantic tools, unstructured text data retrieval, etc., can solve problems such as semantic information confusion, achieve better results, simplify the training process, and resolve semantic ambiguity

Active Publication Date: 2021-08-06
GUANGDONG UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in fact, an entity may have different semantics. For example, "apple" may represent a company or a fruit. These are two completely different semantics. Only one point will cause semantic information confusion.

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 method based on multi-core Gaussian distribution
  • A knowledge graph representation method based on multi-core Gaussian distribution
  • A knowledge graph representation method based on multi-core Gaussian distribution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The specific embodiment of the present invention will be further described below in conjunction with accompanying drawing:

[0021] Such as figure 1 As shown, a knowledge map representation method based on multi-core Gaussian distribution, including negative sample sampling, multi-core Gaussian distribution of entity and relationship representation, using the translation distance model based on translation ideas to learn the representation of entities and relationships, specifically includes the following steps :

[0022] S1), randomly initialize entities and relationships, assuming that the knowledge map is composed of entity sets S=(s 1 ,s 2 ,...,s n ) and relation set R=(r 1 , r 2 ,...,r z ), where n represents the number of entities and z represents the number of relationships;

[0023] In the knowledge graph, each fact is represented by a triplet (source entity h, relation r, target entity t);

[0024] Each entity in the knowledge graph has k semantics, 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 present invention relates to the field of deep learning technology, specifically a knowledge map representation method based on multi-core Gaussian distribution, including negative sample sampling, multi-core Gaussian distribution of entity and relationship representation, and using a translational distance model based on translation ideas to represent entities and relationships To learn, the present invention uses multi-core Gaussian distribution to represent each entity in the knowledge map, considering the characteristics of entities with multiple semantics and the natural attributes of each semantic range, and to a certain extent solves the problem of entities in the knowledge map because The problem of semantic ambiguity caused by multi-semantic features also improves the shortcomings of traditional methods that do not consider the scope of semantics to a certain extent. At the same time, compared with other methods, the training process of this method is simple and the effect is better.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a knowledge map representation method based on multi-core Gaussian distribution. Background technique [0002] In recent years, the research on artificial intelligence and knowledge graph has attracted much attention. The method of using knowledge graph as a known knowledge and combining various deep learning algorithms to improve the effect of various artificial intelligence tasks is also a research hotspot in recent years. , such as robotic systems based on knowledge graphs. The effective expression of knowledge graphs is the basic work of research and utilization of knowledge graphs. It can associate messy data and organize them into structured knowledge for users. This feature determines that it will have important applications in many fields. For example, existing search engines search based on keyword matching, and when the knowledge graph is established, after enter...

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): G06F16/36
Inventor 郝志峰柯妍蓉蔡瑞初陈炳丰
Owner GUANGDONG UNIV OF 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