A method, system, and application for entity relationship completion for power equipment.

By generating a set of associated path features through a path sorting algorithm and combining it with multi-hop path information to complete the relationship between power equipment, the problem of low computational efficiency and accuracy in existing technologies is solved. This achieves efficient and interpretable power equipment relationship completion, improving the efficiency of power equipment management and data storage.

CN116011564BActive Publication Date: 2026-06-30GUILIN UNIV OF ELECTRONIC TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
GUILIN UNIV OF ELECTRONIC TECH
Filing Date
2022-12-28
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing technologies are not efficient and accurate in computationally intensive and complex knowledge graphs with large scale and multiple relationships, and lack interpretability, failing to effectively reflect the relationships between power equipment.

Method used

An entity relationship completion method based on path sorting algorithm is adopted. By generating a set of associated path features through random walk and depth-first search, and combining multi-hop path information between power equipment, a machine learning classification algorithm is used to predict and complete the relationship.

Benefits of technology

It improves the computational efficiency and accuracy of large-scale knowledge graphs, perfects the knowledge graph of power equipment, enhances the management level of power equipment and the efficiency of data storage, and ensures the safe operation of the power grid.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116011564B_ABST
    Figure CN116011564B_ABST
Patent Text Reader

Abstract

This invention belongs to the field of machine learning algorithm application technology. It discloses a method, system, and application for entity relationship completion in power equipment. The method involves collecting data resources related to power equipment in a power distribution network, analyzing the collected information, extracting entities, attributes, and relationships between entities from various data sources to form an ontological knowledge representation, and determining the entities and relationships to be analyzed. The data extracted from the data sources undergoes knowledge fusion processing and is ultimately stored in a knowledge base in the form of triples. From the obtained power equipment knowledge base, pairs of power equipment entities with the same relationships as those extracted are obtained from existing knowledge graphs. The association paths between these pairs are used as features. A set of relationship paths connecting two power equipment entities is analyzed to predict specific or missing relationships between these two entities. This invention not only has high accuracy but also significantly improves computational efficiency.
Need to check novelty before this filing date? Find Prior Art