基于线性扩张的群决策方法

Approach to group decision-making based on linear extensions

针对决策者给出方案集在每个属性下的偏序偏好,且决策者没有确定权重的多属性群决策问题提出了一种新的集结排列方法。该方法首先利用偏序的线性扩张求出方案集在各个属性下的排列概率,进而定义一偏好关系的概念,得到每对方案间的偏好度,然后采用OWA算子对决策群体进行集结,集结后的群体偏好具有偏序特征,能更真实地体现现实的决策问题,并且最大程度地反映了决策群体的偏好。最后给出了算例。

A new aggregating method was presented for ranking alternatives based on partial order preference of groups about each criterion, and decision maker without determining weights. The ranking probability between alternatives for each criterion is worked out by using the linear extensions of the partial order, and then the preference degree between alternatives is obtained through defining the preference relation. Based on OWA operators, the preference information provided by every decision maker is aggregated into group preference and the group preference with partial order characteristic, the participants＇ preference is reflected by the result at most. Finally, a numerical example is used to show the feasibility and effectiveness of the proposed method.