Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Graph representation method and system based on context information

A contextual information and graph technology, applied in the field of machine learning, can solve the problem of poor graph representation and expressive ability, and achieve the effect of excellent graph representation, excellent effect, and strong interpretability.

Pending Publication Date: 2022-07-29
中译语通信息科技(上海)有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a graph representation method and system based on contextual information, aiming to solve the problem that the traditional transX model in the prior art focuses on the representation of relationships and has a weak ability to express graph representations of entities

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
  • Graph representation method and system based on context information
  • Graph representation method and system based on context information
  • Graph representation method and system based on context information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0060] The main technical problem solved by the embodiment of the present invention is:

[0061] Existing graph representation models, such as the knowledge graph translation transX model, can be combined with vector representation for graph representation. like figure 1 As shown, this figure is a kind of transX model: transE model. In the Entity and Relation Space of the transE model, the transE model regards the relation relation in each triple instance (head, relation, tail) as the translation from the head entity head to the tail entity tail. Model training, continuously adjust h, r and t (the vector of the head entity head, relation relation and tail entity tail), so that (h+r) is as equal to t as possible, that is, h+r=t. For other models of transX, such as transH and transR, they are improvements based...

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 graph representation method and system based on context information, and the method comprises the steps: extracting triple information and context information corresponding to the triple information from an existing data set; encoding the triple information to obtain a feature vector corresponding to the triple information; calculating a context vector corresponding to the context information; training a graph representation model according to the relationship between the feature vector and the context vector until the graph representation model converges; and outputting by using the convergent graph representation model to obtain a graph representation result based on the context information. According to the technical scheme, the problems that in the prior art, a graph representation model focuses on relation representation, and the expression ability of graph representation of an entity is not high can be solved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, and in particular, to a method and system for graph representation based on context information. Background technique [0002] Research in the field of machine learning mainly focuses on representations in the form of vectors, while real-world data cannot be easily represented as vectors because real-world scenarios contain complex graph structures, such as biological networks, computer networks, Sensor networks, social networks, and transportation networks, etc. Thus, using "graph representations" (i.e. graph-based representations), we are able to capture the order, topology, set and other relational properties of structured data. [0003] A "graph representation" is a class of mappings that embed vertices, subgraphs, or whole graphs at points in a low-dimensional vector space; these mappings are then optimized so that they reflect the geometry of the embedding space, and the l...

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): G06F16/28G06N20/00
CPCG06F16/288G06N20/00
Inventor 杨万征蔡超武学敏王雪唐曼
Owner 中译语通信息科技(上海)有限公司
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
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