Quantitative evaluation method for emotion index of electricity customer

Abstract

The invention relates to a quantitative evaluation method for an emotion index of an electricity customer. The method comprises the following steps: establishing four independent data modules, namelya positive sentiment word module, a negative sentiment word module, a negative word module and an adverb module; converting all the incoming call information of the client into text information; splitting the text into M sentences by taking the sentences as units; for the jth sentence, splitting the sentence into N vector word groups; calculating an emotion score Qj of the jth sentence; and addingthe M Qj values to obtain a total sentiment value Q < total > of the text. According to the invention, through mining the text data, automatic identification of the customer service risk is realized,the problems of incompleteness, non-timeliness and non-objectivity in manual identification of the customer risk are eliminated by a technical means, and the risk early warning work quality and efficiency can be improved.

Description

Technical field: [0001] The invention relates to the technical field of customer service by means of a computer system, in particular to a method for quantitatively evaluating electricity customer sentiment index. Background technique: [0002] With the continuous development of social economy and the improvement of living standards, the demands of power customers are becoming more and more diverse, and the expectations for power supply services are getting higher and higher. Today, with the deepening reform of the electricity market, if power supply companies want to consolidate their market share in the industry competition, they must accurately grasp customer demands, timely warn of customer dissatisfaction, and finally achieve the goal of providing customers with services beyond expectations to ensure that customers loyalty. [0003] The 95598 power supply service hotline has a daily business volume of 200,000 to 300,000 calls, and customers' appeals, emotions, and expe...

AI Technical Summary

Problems solved by technology

The accuracy and timeliness of artificial reporting is limited by the service awareness of the customer service specialists, and the description of risks also needs to be completed by the customer service specialists. First of all, due to the understanding and writing skills of the customer service specialists, risk information is prone to information in the transmission process Attenuation, dropout, distortion and other issues

To sum up, in order to solve the problems of incomplete information records, unobjective judgments, and untimely submission of current power customer service risk artificial warnings, etc.

Images