Abstract:

There are significant differences in the professional background of decision-makers and the concerned degree of evaluation object attributes, however a few Fuzzy Multiple Attribute Decision-making（FMAD） methods take into account the decision-makers weight and the role of core ratings for final evaluation. Regarding that, this paper designs Integral Fuzzy Ranking Method（IFRM）. Firstly, linguistic variables are quantified as triangular fuzzy number based on fuzzy theory. Then, decision-makers weight is updated until it is stable, according to the gap between individual evaluation and aggregate evaluation. After that, the information entropy of core rating is calculated by entropy method to determinethe attribute weight and the comprehensive aggregated fuzzy rating of evaluation. Further, the preference degree between any two schemes is provided to form ranking with the largest confidence degree based on the integral fuzzy preference. Finally, taking some brand share bicycle as an example, the characteristics and schemes ranking of common Multi-Attribute Decision-making（MAD） methods are compared. The analysis shows that schemes ranked by IFRM are provided with higher consistency and confidence. Meanwhile, IFRM is feasible, effective and superiority to solve the fuzzy MAD problems.

Key words: triangular fuzzy numbers, core rating, fuzzy preference, decision-makers weight, ranking confidence

摘要：

决策者的专业背景、评价对象属性的受关注度均存在显著差异，而鲜有模糊多属性决策（Fuzzy Multiple Attribute Decision-making，FMAD）方法考虑决策者权重和属性核心评级对评价结果的作用，对此设计积分式模糊排序方法（Integral Fuzzy Ranking Method，IFRM）。在模糊理论的基础上，将语言变量量化为三角模糊数；根据个体评价与集结评价间的差距，更新决策者权重直至稳定；运用熵权法计算核心评级的信息熵，确定属性权重及评价对象的综合集结模糊评级，并基于积分式模糊偏好，给出任意两个方案间的偏好度，进而形成置信度最大的排序。以某品牌的共享单车为例，对比了常见多属性决策（Multi-Attribute Decision-making，MAD）方法的特点和方案排序结果，分析表明IFRM方案的排序结果有较高的一致性与置信度，对于解决模糊MAD问题具有可行性、有效性和优越性。

关键词: 三角模糊数, 核心评级, 模糊偏好, 决策者权重, 排序置信度