Method for predicting complaints caused by power failure

Abstract

The invention relates to a method for predicting complaints caused by power failure. Power failure information, client standing book information and user telephone traffic information in a state gridPMS2.0 system, a marketing system and a 95598 customer service system are collected, and data of each dimension is obtained. The data in the three systems are associated through the user station areanumber and the user account number, so that the telephone traffic data in the power failure period and the telephone traffic data in the non-power-failure period are distinguished; for telephone traffic data in a power failure period, firstly, an entropy method is used for determining the power failure duration, whether the power failure is notified in advance or not, and the weight of features influencing telephone traffic data of the peak power failure time; and then according to the influence weight, the difference of the outage event on the outage traffic data between the transformer areasis shielded, and on the basis, depicting the sensitivity degree of the power consumer according to the daily telephone traffic data and the outage traffic data. According to the method, the prediction range is expanded, and the alarm judgment mode is closer to reality.

Description

technical field [0001] The invention relates to the technical field of information technology, in particular to a method for predicting complaints caused by power outages. Background technique [0002] At present, complaints caused by frequent power outages account for a large proportion of customer complaints. According to the analysis of complaint data provided by State Grid Jibei Electric Power Co., Ltd., frequent power outages account for about 40% of the total complaints. It even accounts for 50% of the total complaints. Therefore literature ([1]Xu Xin, Wang Li, Sun Zhijie, Gong Dongmei, Zhang Lingyu, Liu Xiaowei, Qin Fengyuan. An Early Warning Model for Frequent Power Outage Complaints Based on Data Mining[J]. Information Recording Materials, 2017,18(02): 64-66. ) describes a complaint early warning model for frequent power outages, which stipulates that three or more power outages for the same user within two months are regarded as frequent power outages, and with th...

AI Technical Summary

Problems solved by technology

[0003] The frequent power outage data and address information in the literature all come from the content of the work order. Due to the limited work order data and the actual effect of the word segmentation algorithm is greatly affected by the work order filling specifications, it is impossible to achieve accurate statistics of the frequent power outage data and address information; It is proposed to issue a complaint warning for three or more power outages within two months, but in fact, the complaint warning for users should be based on the user's actual feelings. Reason: Not all complaints caused by frequent power outages are reflected in the work order, and some frequent power outages cause customer dissatisfaction, which will cause negative emotions and additional customer service services (such as: return visits, explanations), resulting in some complaints caused by frequent power outages. Work orders will be transformed into complaints about poor customer service attitudes and unacceptable explanations, resulting in accurate data grasping

Images