基于用户感知度模型的新型客户业务型态应用

New customer business applications based on user perception model

针对如何采用电力大数据来为客户提供更好的服务的问题,提出了根据电力大数据构建用户感知度模型,通过对电力用户所属类别的不同,制定相应的服务制度,降低投诉风险。通过对传统的K-means算法进行改进,改进后的K-means算法误分率得到了降低,并且精度得到了很大提升,随着K值的不断增大,聚类的时间明显低于传统K-means算法,且准确率随着K的增大而提升。通过对电力大数据的采样,预处理后,采用改进后的K-means算法构建用户感知度模型。通过实际案例进行仿真分析,采集了福建省某电力公司9～11月的电力工单数据信息。仿真结果显示,通过对数据的建模处理,获得了高、中、低感知用户分类比例,该比例与实际情况相一致,验证了所提方法的准确性,并且该方法对于提高电力公司服务水平,降低投诉意义重大。

Based on the question of how to provide better service for customers based on how to use the big data of power,this paper proposes a user perception model based on power big data.By different types of power users,the corresponding service system is formulated to reduce the risk of complaint By improving the traditional k-means algorithm,the improved k-means error rate is reduced,and the accuracy is greatly improved.With the increase of K value,the time of clustering is significantly lower than that of traditional k-means algorithm,and the accuracy rate increases with the increase of K.After pretreatment,the improved k-means algorithm is used to construct the user perception model.Through the simulation analysis of the actual case,the data information of power workers single data in September,October and November in Fujian province was collected.Simulation results show that,through the process of data modeling,obtained the high perception,the perception,low perceived user classification proportion,the proportion is consistent with the actual situation,in this paper,the accuracy of the proposed method was verified.The method mentioned in this paper is of great significance to improve the service level of power companies.