考虑专家风险偏好的区间直觉模糊多属性决策方法

An Interval-Valued Intuitionistic Fuzzy and Multi-Attribute Decision-Making Method that Refers to the Risk Preferences of Experts

针对决策信息为区间直觉模糊数且属性权重未知的多属性决策问题,提出了考虑专家风险偏好的决策方法。该方法基于专家对风险的偏好程度,构建了一种新的得分函数(P-λ记分函数),据此提出一种区间直觉模糊属性熵权法。同时,定义了考虑专家风险偏好的区间直觉模糊数相关系数,并构造备选方案与理想方案和临界方案属性值相关系数矩阵。然后,集结属性权重和矩阵信息,计算出各种风险偏好情形下的相对贴近度值并得到方案集的综合排序结果。最后,通过算例分析来阐明该方法的有效性。

Faced with the multi-attribute decision-making problems of the interval-valued intuitionistic fuzzy set and uncertain attribute weight, the author proposes a decision method by referring to the risk preferences of experts. Based on those preferences, the author builds a new score function （P-kscore function） and puts forward an interval-valued intuitionistic fuzzy entropy method accordingly. At the same time, this paper defines the correlation coefficient of interval-valued intuitionistic fuzzy set by referring to the experts＇ risk preferences and constructs the correlation coefficient matrix of the alternative, the ideal and the critical schemes＇ attribute value. Then, it gathers attribute weight and matrix information to figure out the relative value by considering the different risk preferences of experts and get a comprehensive ranking result among these alternative schemes. Finally, it uses an example to illustrate the validity of this method.