摘要
本文针对群决策中专家权重及指标权重难以确定的问题,提出一种在权重信息完全未知情况下的基于证据距离和模糊熵权变换的多属性群决策方法,其核心在于如何仅通过决策矩阵客观地确定决策者权重及指标权重。通过信息熵和证据距离确定专家权重,并利用模糊变换原理,将专家权重向量与指标熵权矩阵合成,得到统一的群体决策指标权重;最后使用线性加权法集成所有专家对备选方案的评价信息,得到整个方案集的排序。实验结果及相关讨论表明,该方法概念清晰,计算量适中,具有较强的客观性,而且易于机器实现,是一种可行、有效的多属性群决策方法。最后将该方法推广到属性值由精确数、语言值、区间数、直觉模糊数等多种形式构成的混合型多属性群决策中。
In view of the hard problem that the weights of decision makers and criteria are usually vague and imprecise in group decision making process, we propose a linear method of multi-attribute group decision making with complete ignorance of weight information, with the emphasis on how to objectively determine the weights of decision makers and the weights of criteria only by decision matrices. We firstly introome of fuzzy transformation to obtain the united weights of criteria in group decision making. Finally a linear weighted method is utilized to aggregate individual opinions of decision makers for rating the importance of alternatives. Two numerical examples for supplier selection and some relevant discussion are given to examine the feasibility and validity of the presented approach, which is characterized by clear concept, mod- erate computational complexity, strong objective, and easy machine implementation. In the end we extend it to hybrid multiple attribute group decision making with attribute values in the various forms of precise numbers, linguistic terms, intervals, and intuitionistic fuzzy numbers.
出处
《中国管理科学》
CSSCI
北大核心
2011年第5期94-103,共10页
Chinese Journal of Management Science
基金
国家自然科学基金项目(70972058)
教育部社科研究青年基金项目(10YJC630063)
关键词
多属性
群决策
权重
信息熵
证据距离
multiple attribute
group decision making
weights
information entropy
evidential distance
