Unlock instant, AI-driven research and patent intelligence for your innovation.

Graph embedding method and device for knowledge graph and electronic equipment

A technology of knowledge graph and graph embedding, which is applied in neural learning methods, special data processing applications, biological neural network models, etc., and can solve problems such as missing information, unfavorable graph data mining, and high complexity of heterogeneous knowledge graphs

Pending Publication Date: 2021-12-07
HANGZHOU HIKVISION DIGITAL TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the heterogeneous knowledge graph contains nodes used to represent a variety of different types of objects, as well as the interactive information generated between different types of objects, resulting in a high degree of complexity in the heterogeneous knowledge graph, and the random walk method is often only able to determine It is difficult to effectively embed the global features of the knowledge map into the representation, resulting in the loss of more information in the knowledge map in the obtained representation, which is not conducive to subsequent graph data mining.

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
  • Graph embedding method and device for knowledge graph and electronic equipment
  • Graph embedding method and device for knowledge graph and electronic equipment
  • Graph embedding method and device for knowledge graph and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0093] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0094] In order to better describe the graph embedding method of the knowledge map provided by the embodiment of the present invention, the knowledge map provided by the embodiment of the present invention will be described below, which can be found in figure 1 , figure 1 Shown is a schematic structural diagram of the knowledge map provided by the embodiment of the present invention, which includes:

[0095] The first type of nodes 110 , the second type of no...

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 embodiment of the invention provides a graph embedding method and device for a knowledge graph and electronic equipment. The method comprises the steps that topological information of a first type of nodes and topological information of a second type of nodes are obtained, the topological information is features of objects represented by the first type of nodes, and interaction exists between the objects represented by the first type of nodes and the objects represented by the second type of nodes; for each type of nodes in the first type of nodes and the second type of nodes, graph feature extraction is performed on the topological information of the type of nodes according to the topological information of the type of nodes to obtain deep features of the type of nodes; according to the interaction information between the first type of nodes and the second type of nodes, graph feature extraction is carried out on the deep features of the first type of nodes and the deep features of the second type of nodes, and object representation of the first type of nodes and object representation of the second type of nodes are obtained. According to the method and the device, information lost when the heterogeneous knowledge graph is embedded can be reduced.

Description

technical field [0001] The invention relates to the technical field of graph data mining, in particular to a graph embedding method, device and electronic equipment of a knowledge graph. Background technique [0002] In the field of graph data mining technology, the knowledge graph (Knowledge Graph) is often used to describe the relationship between different objects. The nodes in the knowledge graph can be used to represent objects or features, and the edges can be used to represent the connected nodes. Relationships exist between the objects or features of . If the knowledge graph contains different types of object nodes, the knowledge graph is called a heterogeneous knowledge graph. For example, some nodes in the knowledge graph are used to represent users, and the other part of nodes are used to represent items. [0003] As a kind of graph data, the knowledge map has a high dimensionality, which is not conducive to processing by electronic devices. Therefore, the 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): G06F16/901G06N3/04G06N3/08
CPCG06F16/9024G06N3/049G06N3/08G06N3/045
Inventor 付尧
Owner HANGZHOU HIKVISION DIGITAL TECH