Power distribution network knowledge graph establishing method and device, computer equipment and storage medium

Abstract

The invention provides a power distribution network knowledge graph establishing method and device, computer equipment and a storage medium. The method comprises the steps of obtaining a feature field; based on the feature library, training the feature fields to obtain training data; mapping the training data into corresponding vectors; performing feature association on the corresponding vectors to obtain a training data set; obtaining an objective function through the training data set based on the principle that the space vector distance is minimum; performing iteration processing on the objective function according to the training data set to obtain an iteration result of the objective function; obtaining a minimum value of an iteration result of the objective function, and outputting atraining data set corresponding to the minimum value of the iteration result; and mapping the corresponding training data set into corresponding feature information to obtain a knowledge map. All feature information can be retained in the feature fields, i.e., key information of the feature fields can be extracted, and the feature information can be associated, so that the knowledge map is established, and a user can conveniently analyze the feature fields.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method, device, computer equipment and storage medium for establishing a distribution network knowledge map. Background technique [0002] With the continuous improvement of the distribution network automation level, the safety performance of the distribution network has been significantly improved, but tripping accidents occur from time to time, which has become one of the important factors affecting the safe operation of the distribution network. Whenever a tripping accident occurs, it is necessary to invest a lot of manpower and material resources to investigate hidden dangers, wasting a lot of resources, and most of the user's electricity complaints come from the tripping accident, which has a great impact on improving user satisfaction. Therefore, in-depth research on tripping accidents has become an important measure to improve power reliability and user satisfa...

AI Technical Summary

Problems solved by technology

[0003] The trip data is the first-hand information that intuitively reflects the trip accident, and the trip accident is recorded in detail and completely. Therefore, the analysis of the trip data has become an important research direction to solve the trip accident. Traditionally, the research on the trip data is mostly limited to The application of statistical methods has not deeply excavated the hidden logic behind the trip data, while the research on trip data by machine learning methods is mostly to structure the unstructured trip data first. In the process of structured data, Will destroy the original data, resulting in the loss of many useful information

Images