Knowledge graph completion method and device, equipment and storage medium

A knowledge map and completion technology, applied in the field of knowledge map processing, can solve problems such as poor scalability and low accuracy of knowledge map completion models

Active Publication Date: 2020-12-04
SHENZHEN TECH UNIV
View PDF7 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a knowledge map completion method, device, equipment and storage medium, aiming to solve the problems caused by the existing knowledge map completion model introducing new entities from outside to expand the existing knowledge map scale The problem of low accuracy and poor scalability of the knowledge graph completion model

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 and device, equipment and storage medium
  • Knowledge graph completion method and device, equipment and storage medium
  • Knowledge graph completion method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] figure 1 The implementation process of the knowledge graph completion method provided by the first embodiment of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0051] In step S101, the input knowledge map completion request is received, and the semantic association information between entities and relationships in the knowledge map is extracted from the entity description text information of the knowledge map using the preset association information extraction model according to the knowledge map completion request .

[0052] The embodiment of the present invention is suitable for question answering systems or recommendation systems using knowledge graphs, especially for question answering systems or recommendation systems that complement knowledge graphs by introducing external text information, so that users can be accurately informed by ...

Embodiment 2

[0150] figure 2 It shows the schematic structure of the knowledge graph completion device provided by Embodiment 2 of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0151] The associated information acquisition unit 21 is configured to receive an input knowledge map completion request, and use a preset associated information extraction model to extract information between entities and relationships in the knowledge map from the entity description text information of the knowledge map according to the knowledge map completion request. Semantic association information.

[0152] The graph reconstruction unit 22 is configured to associate the semantic association information with the knowledge graph, and reconstruct the associated knowledge graph to obtain a reconstructed knowledge graph.

[0153] The input sequence acquisition unit 23 is configured to combi...

Embodiment 3

[0159] image 3 The structure of the computing device provided by the third embodiment of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0160] The computing device 3 of the embodiment of the present invention includes a processor 30 , a memory 31 and a computer program 32 stored in the memory 31 and operable on the processor 30 . When the processing 30 executes the computer program 32, the steps in the above embodiment of the knowledge graph completion method are realized, for example figure 1 Steps S101 to S106 are shown. Alternatively, when the processor 30 executes the computer program 32, the functions of the units in the above-mentioned device embodiments are realized, for example figure 2 Function of units 21 to 26 shown.

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 belongs to the technical field of knowledge graph processing, and particularly relates to a knowledge graph completion method and device, equipment and a storage medium. Semantic association information between entities and relations in a knowledge graph is extracted from entity description text information of the knowledge graph through a preset association information extraction model; The semantic association information and the knowledge graph are associated and reconstructed, the entity description text input sequence is encoded through a deep BiGRU network and a preset association enhancement model to obtain encoded entity association sequence information, the entity association sequence information is decoded through a one-way GRU network. Each candidate entity is scored in the decoded knowledge graph, and each entity in the entity description text data set is sequentially linked to the candidate entity with the highest comprehensive score in the knowledge graph soas to complement the knowledge graph, thereby enhancing semantic association information of the existing knowledge graph.

Description

technical field [0001] The invention belongs to the technical field of knowledge graph processing, and in particular relates to a knowledge graph complement method, device, equipment and storage medium. Background technique [0002] With the continuous increase of the number of Internet users, the amount of data in the network also shows an exponential growth trend. However, due to the characteristics of large scale, heterogeneous multi-source and loose structure of network data, people can obtain useful data from network data. Information has become extremely difficult. In this context, knowledge graph technology was officially proposed by Google in 2012 and has received extensive attention from researchers. [0003] Among them, knowledge map completion task is a main research direction in knowledge map technology. By completing the existing knowledge map, it makes it easier for people to obtain useful data information from network data. The main methods of existing knowle...

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): G06F16/36G06F40/30G06N3/04G06N3/08
CPCG06F16/367G06F40/30G06N3/08G06N3/045Y02D10/00
Inventor 傅向华谢文豪
Owner SHENZHEN TECH 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