主观信任评估模型与决策方法的研究  

Research of Subjective Trust Evaluation Model and Decision-making

作　　者：杨玉丽[1,2] 彭新光[1] 王峥[1] 

机构地区：[1]太原理工大学计算机科学与技术学院,太原030024 [2]运城学院公共计算机教学部,运城044000

出　　处：《计算机科学》2015年第1期170-174,共5页Computer Science

基　　金：山西省留学基金项目(2009-28);山西自然科学基金项目(2009011022-2)资助

摘　　要：在网上交易中,针对传统的信用度评估方法不能有效地描述商家信用度的时效性和风险性等特征的问题,提出基于多属性正态云的信任评估方法。首先生成包含5个等级的信任基云;然后引入时间衰减因子,分别从平均水平和变化率两个角度描述商家信用度历史信息,生成对应的声誉云和风险云;最后,由声誉云和风险云合成综合信任云,并计算其信任等级及信任分值。实验结果表明,该评估模型具有可行性和有效性,可为用户提供直观、有效的信任决策依据。Since traditional credit evaluation methods can not describe the business＇s creditworthiness characteristics of timeliness and risk effectively in electronic commerce transactions,a new subjective trust evaluation method based on multi-attribute normal cloud model was presented.Firstly,the standard trust cloud including five levels is generated.Then inducting time attenuation factor,the reputation cloud and risk cloud are designed to depict the average level and change rate about the credit history information respectively.Finally,the comprehensive trust cloud is synthesized with the reputation cloud and risk cloud,and its trust level and trust scores are calculated.Simulation result shows the feasibility and effectiveness of the evaluation model,which can assist people to finish trust decision-making intuitively and efficiently.

关 键 词：主观信任 信任决策 云模型 衰减因子 相似度 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]