基于区间证据推理的多属性决策方法

A Multiple Attribute Decision Analysis Based on Interval Evidential Reasoning

针对多属性决策过程中出现属性信息的评估等级以及评估等级信任度不确定问题,提出一种区间证据推理方法。首先,采用区间评估等级以及区间评估等级信任度的形式表达评估信息的不确定性。其次,通过转换公式统一各属性评估的信任识别框架。然后,采用区间证据推理的集成公式集结区间不确定信息,处理评估等级、评估等级信任度和定量属性评估的区间不确定信息的集结问题。最后,采用期望效用理论对方案综合排序。为验证该方法的有效性,以某生鲜电商选择生鲜供应商为例,运用所提方法对区间形式的不确定评估信息进行处理,结果表明,所提方法能够处理属性评估信息的评估等级以及评估等级信任度不确定问题。

An interval evidential reasoning method was proposed to solve the problem of the evaluation level of attribute information and the uncertainty of evaluation level trust in the process of multiple attribute decision making.Firstly,the uncertainty of evaluation information was expressed in the form of interval evaluation level and interval evaluation level trust.Secondly,the trust recognition framework of attribute evaluation was unified by transforming formulas.Then,the integration formula of interval evidential reasoning was used to aggregate the interval uncertain information,to deal with the problem of the aggregation of the interval uncertainty information of the evaluation level,the evaluation level of trust and the quantitative attribute evaluation.Finally,the scheme was sorted synthetically by adopting the theory of expected utility.In order to verify the effectiveness of the proposed method,the proposed method was used to process the uncertain evaluation information in the form of interval,taking a fresh supplier selected by a fresh food E-commerce as an example.The result shows that the proposed method can deal with the evaluation level of attribute evaluation information and uncertainty of evaluation level trust.