Check patentability & draft patents in minutes with Patsnap Eureka AI!

Knowledge graph completion method

A technology of knowledge map and completion, applied in the field of knowledge map, to achieve the effect of highlighting important semantics, flexible weight calculation, and realizing the aggregation of relationship path features

Active Publication Date: 2021-09-07
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Traditional methods mostly use single-dimensional semantic information to model knowledge graphs. ConvE uses a single triple pair to model, while RSN only uses path semantics. These models have certain limitations in their expressive capabilities.

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 completion method
  • Knowledge graph completion method
  • Knowledge graph completion method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] figure 1 It is a flowchart of a knowledge graph completion method of the present invention;

[0056] In this example, if figure 1 As shown, a knowledge graph completion method of the present invention includes the following steps:

[0057] S1. Obtain knowledge graph;

[0058] Download the knowledge map KG, such as figure 2 As shown, the knowledge graph is composed of triplets, and each triplet includes a head entity h, a relationship r and a tail entity t, where the i-th triplet is recorded as (h i ,r i ,t i ), i=1, 2, ... represents the triplet numbering; in this embodiment, such as figure 2 As shown, take the triplet (Larry Ellison, leadership, Oracle) as an example, where the head entity h is Larry Ellison, the relationship r is leadership, and the tail entity t is Oracle.

[0059] get each relation r i A textual description of T i ,T i Including the textual description of the entity type and the textual description of the relationship itself; in this emb...

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 completion method, which comprises the following steps of: firstly downloading a knowledge graph and acquiring text description of each relationship, then acquiring vector initialization of each relationship based on a text embedding mode, and inputting the vector initialization of each relationship into the downloaded knowledge graph to obtain a new knowledge graph; a user provides a to-be-complemented triple, a head entity and a tail entity of the to-be-complemented triple are input into an MSNN network, and in the MSNN network, context information and relation path features of the entities are extracted through two parallel sub-networks respectively; and finally, inferring a missing relationship according to the context information and the relationship path characteristics, and complementing the missing relationship into the original knowledge graph.

Description

technical field [0001] The invention belongs to the technical field of knowledge graphs, and more specifically, relates to a knowledge graph complement method. Background technique [0002] With the vigorous development of Internet technology, under the historical wave of artificial intelligence, big data provides convenience for people's life, but also poses formidable challenges. In the face of multi-source heterogeneous data, how to effectively filter out the required information from massive structured and unstructured data is an important issue. The emergence of the concept of knowledge graph provides a feasible solution to this problem. Knowledge graph can reduce the barriers of human-computer interaction, let simple computers strengthen human knowledge, and make computers more intelligent and automatic. Google first proposed the concept of knowledge graph (Knowledge Graph, KG) in 2012. From the definition of knowledge graph, we can know that knowledge graph is essent...

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): G06F16/36G06F40/211G06F40/295G06F40/30G06N3/04G06N3/08
CPCG06F16/367G06F40/295G06F40/211G06F40/30G06N3/08G06N3/044
Inventor 徐杰黄云扬周双张昱航冯渝荏
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com