Electricity stealing and electric leakage user identification method and device, computer equipment and storage medium

Abstract

The invention relates to an electricity stealing and electric leakage user identification method and device, computer equipment and a storage medium, and the method comprises the steps of obtaining to-be-identified abnormal data, so as to obtain to-be-identified data; performing feature extraction on the to-be-identified data to obtain feature data; inputting the feature data into an identification model for user identification to obtain an identification result; feeding back an identification result to the terminal, wherein the identification model is obtained by training a random forest model by taking a plurality of characteristic data related to electricity stealing and electric leakage and characteristic data related to non-electricity stealing and electric leakage as data sets. The invention comprises acquiring data to be identified; the data is input into the recognition model to be automatically recognized, the recognition result can be obtained; the recognition model is a random forest model formed after iterative optimization is conducted through a particle swarm optimization algorithm, the classification accuracy is high, key features of electricity stealing and leakageusers are extracted, the electricity stealing and leakage users are recognized, the efficiency is high, and the accuracy is high.

Description

technical field [0001] The present invention relates to electricity data identification method, more specifically refers to the user identification method, device, computer equipment and storage medium of electricity stealing and leakage. Background technique [0002] With the rapid development of social economy, power resources play an increasingly important role in people's daily life. However, in order to reduce the expenditure of power resource costs, individual users steal electricity through deceptive means such as stealing electricity and fraud, which has caused serious economic losses to the power company. To solve this problem, the power company has taken many measures to inspect and rectify, and achieved certain results. [0003] The traditional anti-theft and leakage methods are mainly to find electricity theft or metering device failure through regular inspections, regular calibration of meters, and user reports of electricity theft. However, this method is too ...

AI Technical Summary

Problems solved by technology

[0003] The traditional anti-theft and leakage methods are mainly to find electricity theft or metering device failure through regular inspections, regular calibration of meters, and user reports of electricity theft. However, this method is too dependent on people, and the goal of leak detection Not clear, there are congenital defects and deficiencies; moreover, with the generalization and diversification of the phenomenon of electricity theft and leakage, the manual inspection of electricity theft is inefficient, the process is complicated, and the subjectivity is too strong. Judging based on experience

The existing electric power metering automation system can collect electricity load data such as current and voltage of each phase, as well as user abnormal data. The abnormal warning information and electricity load data can reflect the user's electricity consumption. and on-site inspections to find out the users who steal electricity and leak electricity and enter them into the system, but there is no way to automatically extract the key features of users who steal electricity and leak electricity, and automatically identify users who steal electricity and leak electricity, and the efficiency is low

Images