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

Relationship prediction method based on knowledge map

A knowledge map and prediction method technology, applied in prediction, special data processing applications, instruments, etc., can solve problems such as the complexity of the knowledge map structure and the difficulty of multi-relational prediction, and achieve the effect of improving computing efficiency

Inactive Publication Date: 2018-10-23
HARBIN ENG UNIV
View PDF0 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, scholars at home and abroad are actively researching the relationship prediction method on the knowledge graph, but due to the complexity of the knowledge graph structure, how to better improve the effect of multi-relationship prediction has become a research difficulty

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
  • Relationship prediction method based on knowledge map
  • Relationship prediction method based on knowledge map
  • Relationship prediction method based on knowledge map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described below in conjunction with the accompanying drawings.

[0042] The present invention is based on the current popular knowledge representation learning method, and provides a targeted solution based on the main problem of multi-relational prediction of knowledge graphs. The present invention uses an undirected graph model to represent the knowledge graph, and proposes a relationship prediction algorithm based on the knowledge graph, and the BPTransE algorithm, such as figure 1 The shown BPTransE algorithm specifically includes the following steps:

[0043](1) Construct an effective knowledge map from the triple data set and initialize the parameters;

[0044] (2) Use the TransE algorithm to train each entity and relationship in the knowledge map, and embed the entity and relationship into a low-dimensional vector space;

[0045] (3) extract the relational label of each triplet, and construct the subgraph of each relation; ...

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 relationship prediction method based on a knowledge map, and uses an undirected graph to represent the knowledge map, and provides an improved hybrid relationship predictionalgorithm combining a bidirectional relationship path and an embedded type. The method comprises the following steps: (1) constructing a valid knowledge map of a triplet data set and initializing parameters; (2) training each entity and relationship in the knowledge map with the TransE algorithm, and embedding the entity and relationship into a low-dimensional vector space; 3) extracting the relationship label of each triplet and constructing a subgraph of each relationship; (4) on each relationship subgraph, finding a reachable path between every two entities through iterating, dividing thesubgraph according to the graph structure, and calculating the reliability of each reachable path; (5) iterating every two entities without the direct edge join, and evaluating whether there is a hidden relationship between the two entities through the constructed joint evaluation function and loss function; and (6) complementing the knowledge map structure.

Description

technical field [0001] The invention relates to the field of knowledge graph completion algorithms under the condition of RDF knowledge graphs, in particular to a relationship prediction method based on knowledge graphs. Background technique [0002] The development of information technology is constantly promoting the transformation of Internet technology. As a symbolic technology of the Internet age, Web technology is at the core of this technological transformation. The technology of linking web pages to data is gradually evolving towards the Sematic Web as envisioned by the father of the Web, Berners-Lee. According to W3c's explanation, semantic web is a web of data composed of a piece of data. Semantic web technology provides users with a query environment, and its core essence is to return processed and reasoned knowledge to users in the form of graphics. The knowledge graph technology is the basis and bridge for realizing intelligent semantic retrieval. Traditional ...

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): G06Q10/04G06F17/30
CPCG06Q10/04
Inventor 王念滨秦帅陈锡瑞王红滨周连科白云鹏王勇军何茜茜原明旗陈田田
Owner HARBIN ENG 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