基于混合型评价矩阵的多属性群决策方法

Multi-attribute group decision making method based on hybrid evaluation matrix

本文针对具有语言型、直觉模糊数和区间直觉模糊数三种评价信息的混合型多属性群决策问题,提出一种基于属性权重和专家权重均未知的决策方法.首先,定义新的转换函数,可将不同粒度的语言评价信息统一成区间直觉模糊数;然后,基于支持度确定未知属性权重,并在综合考虑区间直觉模糊数熵值和相似度的基础上,建立了一种新的专家权重确定模型;在将混合型决策矩阵转换成区间直觉模糊决策矩阵后,利用IIFWA算子依次集结个体决策矩阵,从而得出方案集的排序.最后,应用在ERP选优问题中,验证了方法的有效性.

In this paper, we investigate a multi-attribute group decision making method with unknown attributes＇ weights and experts＇ weights in which the information provided by each decision maker in ex- pressed as the hybrid decision matrix where each of the elements is expressed by intuitionistic fuzzy number, interval-valued intuitionistic fuzzy number and linguistic labels. First, define a transformation function which can change multi-granularity linguistic variables to interval-valued intuitionistic fuzzy numbers. Then, ensure the unknown attributes＇ weights based on the support degrees, and next establish a model to ensure the weights of decision makers which considering the entropy and similarity of interval-valued intuitionistic fuzzy numbers. After transform hybrid decision matrices to interval-valued intuitionistic fuzzy matrices, we can aggregate these individual decision matrices by using IIFWA operation for ranking alternatives. Finally, an illustrative example for supplier selection is given to prove this method.