Electric power work order demand point identification method based on deep learning

• Main Authors: ZHONG ZHENYUAN, ZHU BIN, HONG JIANSHAN, GE YUEJUN, DING JIAHAN, HU RUOYUN, YE HONGDOU, ZHANG SHUANG, WEI XIAOXIONG, LIN SHAOWA, LUO XIN, MA LYUBIN, SHEN HAO, CHEN YIRU, ZHU RUIQIAN, YANG JIANJUN, CHEN BO
• Format: Patent
• Language: Chinese; English
• Published: 15.05.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses an electric power work order appeal point identification method based on deep learning, and relates to the field of electric power work order appeal point identification methods. At present, customer appeal mining efficiency is low, facing massive unstructured text appeals, the customer appeals still stay in a stage of manually processing and analyzing data, and the problems of single data processing mode, high input labor cost, poor real-time performance and the like exist. The method comprises the key steps of establishing an appeal point machine identification labelsystem, performing work order appeal high-dimensional matrix vectorization, performing appeal point machine identification modeling, performing sample learning training, performing similarity model identification classification and the like. By means of the deep learning technology means, the appeal man-machine coupling recognition classification function with machine recognition as the main meansand manual rechecking as