Knowledge graph embedding training method and related device

A technology of knowledge graph and training method, applied in character and pattern recognition, instrument, unstructured text data retrieval, etc., can solve the problem of low accuracy of embedded representation results

Inactive Publication Date: 2021-04-20
SUN YAT SEN UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] This application provides a knowledge graph embedding training method and related devices, which solves the technical problem that in the existing tra

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 embedding training method and related device
  • Knowledge graph embedding training method and related device
  • Knowledge graph embedding training method and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to facilitate understanding, first, the relevant principles and definitions in the knowledge map are explained as follows:

[0046] Such as figure 1 As shown, the knowledge graph uses the graph structure to formally describe and store complex things in the real world and their interrelationships. These structured data usually appear in the form of triples (subject node (h), relation (r), object node (t)), such as (Sun Yat-sen University, founded in 1924), (Sun Yat-sen University, founder , Sun Yat-sen), (1924, 1920s, 1920s) and so on.

[0047] Among them, the negative sample is: for a positive sample (h, r, t), replace the subject node h or the object node t, and sample a negative sample (h', r, t) or (h, r, t '), denoted as (h',r',t').

[0048] There are differences between different negative examples, which means that there are differences in the reference value for model training. However, in the existing model training process, the weights of different ...

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 embedding training method and a related device. The method comprises the steps of obtaining network topology information in a knowledge graph structure; calculating a first similarity distance between different entity nodes in the knowledge graph according to a similarity calculation method and the network topology information; calculating a second similarity distance between the positive sample and the negative sample based on the first similarity distance and entity nodes included in the positive sample and the negative sample in the knowledge graph; calculating a comprehensive weight corresponding to each negative sample according to the second similarity distance corresponding to each negative sample; and according to the positive sample, the negative sample, each negative sample and the corresponding comprehensive weight, carrying out model training of a corresponding type to obtain knowledge graph embedding representation. The technical problem that in the existing training process of knowledge graph embedding, different negative samples are regarded as the same kernel, and consequently the result accuracy of embedding representation is possibly low is solved.

Description

technical field [0001] The present application relates to the technical field of knowledge graphs, in particular to a knowledge graph embedding training method and related devices. Background technique [0002] The so-called knowledge graph is a semantic network that reveals the relationship between entities. It uses the graph structure to formally describe and store complex things in the real world and their relationships. The development of knowledge graph embedding research has enabled a large number of human character symbol datasets in the real world to be understood, utilized and expanded by machines. Therefore, the emergence of knowledge graphs has enabled related applications such as intelligent search, personalized recommendation, and intelligent question answering to perform better. . But the real world is extremely complex, and it is an extremely large project to include all the relationships in the real world. [0003] The work of knowledge graph embedding is t...

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): G06F16/36G06K9/62G06N20/00
Inventor 陈川杜尔鑫郑子彬
Owner SUN YAT SEN UNIV
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap