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

Knowledge graph embedding method based on hierarchical attention

A technology of knowledge graph and attention, applied in the field of knowledge graph, can solve problems such as inability to represent multi-level information, achieve the effect of expanding the embedded perspective and improving the effect

Pending Publication Date: 2021-10-01
GUILIN UNIV OF ELECTRONIC TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The present invention aims to solve the problem that the current knowledge graph embedding model cannot represent multi-level information, and provides a knowledge graph embedding method based on hierarchical attention

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 embedding method based on hierarchical attention
  • Knowledge graph embedding method based on hierarchical attention
  • Knowledge graph embedding method based on hierarchical attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific examples.

[0032] see figure 1 , a knowledge graph embedding method based on hierarchical attention, the nodes of the knowledge graph correspond to entities, and the directed edges connecting the nodes correspond to each other; the steps are as follows:

[0033] Step 1. Construct the original entity embedding vector X according to the multi-order triples of the knowledge graph.

[0034] The structure of the knowledge graph is that nodes correspond to entities, and directed edges corresponding to nodes are connected. Entities and relationships are connected to each other to represent knowledge facts. The most basic knowledge unit in a fact is a triple (h, r, t), where h and t represent the head entity and tail entity, and r represents the relationship between the head entity h and t...

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 embedding method based on hierarchical attention. The method comprises the following steps: firstly, layering a relation path formed by connecting a plurality of entities and relations according to relation connection hops; then constructing a plurality of entities and relationships under different levels into a multi-order triple; distirbuting an attention weight to each triple through a graph attention mechanism; and finally, gathering, by the center node, the multi-level information contained in each order of triple, so that the embedding effect of the knowledge graph is improved.

Description

technical field [0001] The invention relates to the technical field of knowledge graphs, in particular to a knowledge graph embedding method based on hierarchical attention. Background technique [0002] As an important branch of artificial intelligence, knowledge engineering refers to the use of knowledge reasoning by computers to solve various computational problems. Knowledge graph is the latest achievement of knowledge engineering. The resource description framework (RDF) defines triples as knowledge units, and triples are connected to each other to form a huge knowledge graph. With the continuous improvement of industrial encyclopedia maps and vertical field maps, knowledge maps have moved from the research stage to the application field, providing technical support for artificial intelligence applications such as information retrieval, recommendation systems, and intelligent question answering. [0003] Graph embedding technology learns the features of nodes and attri...

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): G06F16/36
CPCG06F16/367
Inventor 李凤英范伟豪董荣胜
Owner GUILIN UNIV OF ELECTRONIC 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com