基于集对分析的多种不确定偏好形式大群体决策方法

A Large Group Decision Method with Different Kinds of Uncertain Preference Based on Set Pair Analysis

针对具有多种不确定偏好形式的多方案大群体决策问题,提出一种基于集对分析的群决策方法。将区间数、三角模糊数以及语言值三种形式的不确定偏好转换为联系数,保留了不确定偏好信息中的确定性与不确定性。提出一种区间聚类算法,在决策成员权重未知的情况下对成员进行赋权。利用加权综合联系数对大群体偏好进行集结,根据方案的集对势大小给出方案的排序。该方法避免了确定权重时的主观性,同时考虑决策信息的确定性与不确定性,提高了决策结果的可信度。通过实例分析验证了方法的有效性和实用性。

For large group decision making problems with different kinds of uncertain preference, a group deci- sion making method is put forward based on set pair analysis. Three kinds of uncertain preference, thus the interval number, triangular fuzzy number and linguistic value, are transformed into contact numbers, which retained the certainty and uncertainty of uncertain preference. Aninterval clustering algorithm has been put for- ward, and it is used to assign weights to the members under the situation that the decision weights of the members are unknown. The weighted comprehensive connection numbers are used to aggregate thepreference of large group. Thenthe order of the schemes is given according to the potential size of the schemes. This method has avoided the subjectivity while the weight is given. At the same time, it considers the certainty and uncertainty of the decision information, and improves the credibility of the decision results. Finally an example proves the validity and oraeticabilitv of the method.