A Method and Device for Entity Alignment Based on Edge Type Attention Mechanism

An attention, entity pairing technology, applied in computer parts, instruments, data processing applications, etc., can solve problems such as insufficient utilization of relationship attributes, ignoring the role of relationship type information, and inability to ensure relationship consistency, etc., to achieve optimization. Embedding representation, practicability is simple and reliable, and practicability is good

Active Publication Date: 2022-02-22
STATE GRID HUNAN ELECTRIC POWER +2
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, previous methods treat neighbor nodes equally, so they cannot perceive the weight of the relationship, nor can they guarantee the consistency of the same type of relationship in the training process.
The second is that the relationship attributes have not been fully utilized, and the aligned nodes are also aligned with the surrounding relationships. Effective use of relationship attribute information can obtain better entity embedding, such as in figure 2 Among them, the relationship type, unit, and material connected to the Chinese entity resistor, and the relationship type (type), unit (unit), and material (material) connected to the English entity resistance are aligned
[0005] In summary, current KG entity alignment methods ignore the role of relation type information in entity alignment

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
  • A Method and Device for Entity Alignment Based on Edge Type Attention Mechanism
  • A Method and Device for Entity Alignment Based on Edge Type Attention Mechanism
  • A Method and Device for Entity Alignment Based on Edge Type Attention Mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Such as image 3 Shown is a schematic diagram of the method flow of the method of the present invention: the entity alignment method based on the edge type attention mechanism provided by the present invention includes the following steps:

[0050] S1. Taking the entity alignment of the power knowledge graph as an example, construct the type dual graph of the power knowledge graph; specifically, the following steps are used to construct the type dual graph:

[0051] A type of edge in the knowledge graph represents a node in the dual graph of the type, and two types of edges in the knowledge graph are connected to a point, so there is an edge connection between the points in the dual graph of the corresponding type. The schematic diagram of the type dual graph is shown in Figure 4 As shown, the power knowledge graph is G, and the type dual graph is G r , assuming that there are three types of edges r in the original knowledge graph 1 、r 2 and r 3 , corresponding to...

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 an entity alignment method based on an edge type attention mechanism, including constructing a type dual graph of an electric power knowledge map; using an attribute attention mechanism to train node features of a type dual graph and obtaining the embedding of each node in the type dual graph ; Convert the nodes in the type dual graph to the attention coefficient of the relationship in the knowledge graph, and gather the neighbor entity and relationship information according to the relationship attention coefficient of the nodes in the knowledge graph, and get the final structured embedding result; calculate the loss function and align entities in different knowledge graphs to obtain entity pairs aligned with entities in different knowledge graphs. The invention also discloses a device for realizing the entity alignment method based on the edge type attention mechanism. The invention broadens the thought of relational information mining, excavates the structural features of entities, and has high precision, good practicability, simplicity and reliability.

Description

technical field [0001] The invention belongs to the field of power system big data processing, and in particular relates to an entity alignment method and device based on an edge type attention mechanism. Background technique [0002] In the task of building a large-scale knowledge base, it is necessary to process a large amount of entity data from multi-source knowledge bases, which are usually stored in the knowledge base in the form of knowledge graphs, such as figure 1 shown. Therefore, at the beginning of building a knowledge base, it is first necessary to establish a knowledge fusion method to fuse multi-source knowledge graphs. Due to the different sources of information in different knowledge bases, as well as the differences in manual definition and proofreading, semantically identical entities will have different representations in different knowledge bases. Entities with the same name may represent semantically the same thing, or two things. Therefore, before k...

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 Patents(China)
IPC IPC(8): G06F16/36G06K9/62G06Q50/06
CPCG06F16/367G06Q50/06G06F18/214
Inventor 陈毅波向行熊帆高建良何智强陈远扬田建伟蒋破荒黄鑫杨芳僚孙毅臻朱宏宇祝视张宇翔李浩志
Owner STATE GRID HUNAN ELECTRIC POWER
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