Electric power asset heterogeneous data fusion method based on knowledge graph

Abstract

The invention discloses an electric power asset heterogeneous data fusion method based on a knowledge graph. The method comprises the steps of firstly constructing a power asset knowledge graph model,extracting knowledge in the acquired power asset data through a power asset knowledge graph model then to achieve data fusion specifications, calculating relationships among the extracted knowledge entities by adopting a similarity comparison method based on named entity attribute relationships and an entity alignment algorithm, and performing multi-data-source knowledge fusion, the power asset data comprising structured data, semi-structured data and unstructured data. According to the design, comprehensive and accurate fusion of the multi-source heterogeneous data of the power assets is achieved, and good maintainability and expandability are achieved.

Description

technical field [0001] The invention belongs to the field of power grid heterogeneous data fusion, and in particular relates to a knowledge graph-based power asset heterogeneous data fusion method. Background technique [0002] In the power grid system, the level of power asset management is a decisive factor for the comprehensive benefits of power grid enterprises. High-level power asset management can provide scientific and rational guidance for the cost and expenditure of power grid enterprises, and can be used in all aspects of power grid system operation. Effective management and control of power assets in each stage. Power grid enterprises have attached great importance to power asset management and conducted extensive research, but there are still some problems in the process of application. In the life cycle management of power assets, all kinds of data of power assets are stored in different management systems, and it is difficult to accurately describe the attribu...

AI Technical Summary

Problems solved by technology

These data are difficult to share, and the information is incompatible, forming "information islands" one by one. In addition, the characteristics of complex and diverse power data, large quantity, real-time, and distribution have brought difficulties to the power data fusion work.

At present, the vast majority of data fusion research is carried out for specific problems in specific application fields, and establishes intuitive fusion criteria according to the types of problems without forming a complete theoretical framework and fusion model; and most data fusion It synthesizes information through a simple method, and does not make full use of the redundant information provided by multiple data sources

Images