基于离散时间最优控制的在线信誉评价模型  

An online credit evaluation model based on the discrete time optimal control

作　　者：张超宁 张莹[1] 徐应涛[1] ZHANG Chaoning;ZHANG Ying;XU Yingtao(College of Mathematics,Physics and Information Engineering,Zhejiang Normal University,Jinhua 321004,China)

机构地区：[1]浙江师范大学数理与信息工程学院,浙江金华321004

出　　处：《浙江师范大学学报（自然科学版）》2018年第4期383-389,共7页Journal of Zhejiang Normal University:Natural Sciences

基　　金：浙江省科技厅资助项目(2017C32034);浙江省教育厅科研项目(Y201636028)

摘　　要：考虑C2C电子商务消费模式中在线信誉评价问题.为了分析最优信誉投入策略,首先构建了含控制变量全变差项的基于离散时间最优控制的系统信誉评价模型,利用等价问题转化和约束转化技术,将非光滑最优控制模型转化为标准形式;其次利用罚函数法及C-E算法求解转化后的最优控制问题;最后用数值算例验证了模型的有效性.结果表明:该模型能够有效预防信誉炒作,并且能动态体现交易双方的信誉情况.It was considered the issue of online reputation evaluation in C2C e-commerce consumption patterns.In order to analyze the optimal reputation investment strategy,firstly,a system reputation evaluation model was built based on the discrete time optimal control.The model included the total variation of control variables,and the non-smooth optimal control model was transformed into the standard form by the equivalent problem transformation and constraint transformation techniques.Secondly,the penalty function method and C-E algorithm were used to solve the optimal control.The numerical example demonstrated that the model could effectively prevented the reputation speculation and could dynamically reflected the credit worthiness of both parties.

关 键 词：信誉评价 最优控制 约束转化 罚函数 

分 类 号：O241.7[理学—计算数学]