Automatic Identification Algorithm for Electricity Information Labels Based on Time Series Algorithm and Matching Degree
Electricity information generally presents the characteristics of large amount of data and low information value densi-ty.In order to improve the utilization of electricity information,an automatic identification algorithm of electricity information labels based on time series algorithm and matching degree is studied.This paper carries out labeling processing of power con-sumption information,and standard four types of label words,i.e.,source label words,time label words,content label words and frequency label words.The time series algorithm is used to serialize and process electricity information labels,calculate the matching degree between two electricity information label sequences,and automatically identify electricity information labels.The results show that the area under the ROC curve(AUC)of five electricity information samples is between 0.85～1.0,which is more accurate,and the robustness of the automatic identification performance of electricity information labels is better.
time series algorithmpower consumption informationlabelautomatic identification algorithm
万方数据
维普
