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

Dimensionality reduction expression method of mapping knowledge domain on basis of sub-graph division

A knowledge map and expression method technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of not being able to accurately express entity and relationship information, ignoring local features of the map, etc., to achieve improved computing performance and growth speed maintain a smooth effect

Inactive Publication Date: 2018-03-06
SUN YAT SEN UNIV
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical defects of the above prior art that cannot accurately express the information contained in entities and relationships due to ignoring the local features of the graph, the present invention provides a dimensionality reduction expression method for knowledge graphs based on subgraph division

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
  • Dimensionality reduction expression method of mapping knowledge domain on basis of sub-graph division
  • Dimensionality reduction expression method of mapping knowledge domain on basis of sub-graph division
  • Dimensionality reduction expression method of mapping knowledge domain on basis of sub-graph division

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Such as figure 1 As shown, the method provided by the present invention includes the following contents: divide the knowledge map into subgraphs; perform CP tensor decomposition on the divided subgraphs, and obtain entity encoding vectors and relationship encoding vectors as the result output of dimensionality reduction expression.

[0047] In this example, if Figure 8 As shown, the process of dividing the knowledge map into subgraphs is as follows:

[0048] S11. Manually mark the entities in the knowledge map, and mark different entities as core object entities and secondary object entities;

[0049] S12. Push all marked core object entities into the stack K

[0050] S13. Take a core object entity from the stack K as the traversal starting point to perform subgraph traversal;

[0051] S14. Remove the core object entity obtained through traversal from the stack K;

[0052] S15. Determine whether the number of entities in the stack K is 0, and if so, end the subgrap...

Embodiment 2

[0073] The commonly used indicator in the world to measure the encoding effect of entities is AUC (Area Under Curve). The encoded entities are classified into binary values. The better the classification effect, the more reasonable the encoding method, and the higher the value of AUC. The data set of this experiment is the Cora public data set, and the structure of the Cora data is as follows Figure 11 As shown, by comparing the AUC value obtained by this method with other mainstream methods for entity binary classification on the Cora knowledge graph, the histogram is drawn as Figure 12-Figure 13 shown.

[0074] Comparing the computing performance of the subgraph division method and the traditional method, Table 1 lists the four methods completed on the same computer (Intel(R) Core(TM) i5-6600K CPU@3.50GHz) and the same data set The computation time spent on entity encoding.

[0075] Table 1 Performance comparison between the subgraph partition method and the traditional ...

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 relates to a dimensionality reduction expression method of a mapping knowledge domain on the basis of sub-graph division. The dimensionality reduction expression method comprises the following steps: carrying out sub-graph division on the mapping knowledge domain; carrying out CP tensor decomposition on divided sub-graphs to obtain an entity coding vector and a relationship coding vector, and outputting as a dimensionality reduction expression result.

Description

technical field [0001] The present invention relates to the technical field of knowledge graphs, and more specifically, to a dimensionality reduction expression method for knowledge graphs based on subgraph division. Background technique [0002] A knowledge graph is a graph-based data structure consisting of entities and relationships. Its essence is to connect different types of information together to obtain a relational network, thus providing a problem analysis method with "relationship" as the main body. The concept of knowledge graph was first proposed by Google in the United States, and it is mainly used in search engine optimization. Today, it has been widely used in the fields of telecommunications anti-fraud, paper plagiarism detection, Internet finance and life sciences. [0003] In the application process of knowledge graph, two problems need to be solved: one is the filling of missing data; the other is relation extraction and entity classification. The basi...

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): G06F17/30
CPCG06F16/367
Inventor 何兆成卢昱寰陈一贤
Owner SUN YAT SEN UNIV
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