Unlock instant, AI-driven research and patent intelligence for your innovation.

Construction of graph convolution network learning model based on ontology semantics

A convolutional network and learning model technology, applied in the field of knowledge map representation learning, can solve the problems of few researches on neural network reasoning methods, and achieve the effect of improving performance

Inactive Publication Date: 2021-04-09
TIANJIN UNIV
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

To date, little research has been done on neural network-based inference methods

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
  • Construction of graph convolution network learning model based on ontology semantics
  • Construction of graph convolution network learning model based on ontology semantics
  • Construction of graph convolution network learning model based on ontology semantics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention is completed through 8 steps, that is, step 1, input knowledge map data; step 2, calculation of convolutional neural network of relation graph; step 3, entity embedding E: step 4, calculation of DistMult decoder: step 5, relation embedding R: Step 6, conduct rule reasoning: Step 7, judge whether the target number of iterations is reached: Step 8, the knowledge map after training. Below in conjunction with accompanying drawing, further illustrate the present invention as follows:

[0041] Such as Figure 1-8 Shown: IterG, a graph convolutional learning model based on ontology semantics, see the IterG model framework figure 1 As shown, it mainly includes two parts: the graph self-encoding layer and the reasoning layer. The IterG model integrates the ontology semantic information in the knowledge graph into the graph convolutional neural network for the first time, and organically and seamlessly integrates the ontology semantics in the knowledge grap...

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 construction of a graph convolution network learning model based on ontology semantics. The construction comprises the steps of inputting knowledge graph data; calculating a relation graph convolutional neural network; and entity embedding E: DistMult decoder calculation: relationship embedding R: rule reasoning: judging whether target iteration number is reached: a trained knowledge graph. According to the invention, the boundary of rule learning and a graph convolution network can be eliminated through a built IterG model, and the ontology semantic information is organically and seamlessly fused into the graph convolution network model through rule learning.

Description

technical field [0001] The present invention relates to the field of knowledge map representation learning, in particular to the construction of a graph convolutional network learning model based on ontology semantics. Background technique [0002] With the rapid development of artificial intelligence, knowledge graph (Knowledge Graph) has been widely recognized as an important part of many artificial intelligence technologies and systems. A large number of knowledge graphs, such as YAGO, WordNet, and Freebase have been developed. The knowledge graph contains a large amount of prior knowledge and can manage data efficiently. They have been widely used in question answering systems, search engines, and recommender systems. Knowledge graphs can mine, organize, and effectively manage knowledge from large-scale data, thereby improving the quality of information services and providing users with smarter services. All these aspects rely on the support of knowledge reasoning rat...

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): G06N3/04G06N3/08G06N5/04G06F16/36G06F40/30
CPCG06N3/08G06N5/04G06F16/367G06F40/30G06N3/045
Inventor 王鑫梁兴亚
Owner TIANJIN UNIV