基于决策偏好距离的多阶段群决策快速集结方法  

Quick preference aggregated method for multi-stage group decision-making based on decision preference distance

作　　者：卢志平[1,2] 陆成裕[2] 

机构地区：[1]合肥工业大学管理学院,安徽合肥230009 [2]广西工学院管理系,广西柳州450006

出　　处：《合肥工业大学学报（自然科学版）》2012年第3期398-402,共5页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(90718037);高等学校博士学科点专项科研基金资助项目(200803590007)

摘　　要：针对具有互反判断矩阵偏好信息的多阶段群决策问题,文章提出了一种基于决策偏好距离的快速集结方法。首先对决策偏好距离相关概念进行定义,阐述了基于决策偏好距离的多阶段群决策集结过程;其次,利用决策偏好距离算法对单一专家的阶段内权重和阶段间权重进行测度,得出最优的专家权重;然后,通过加权几何平均算子拟合出最优的专家判断矩阵和最优的群体决策偏好;最后,给出算例,分析结果表明该方法具有合理性。In order to solve the multi-stage group decision-making problems of preference information in the form of reciprocal judgment matrix,this paper proposes a quick aggregated model based on decision preference distance.Firstly,the related concepts of the decision preference distance are defined,and the whole process of multi-stage group decision-making based on decision preference distance is stated.Then,based on the decision preference distance algorithm,a single expert＇s weight of in-stage and between-stage can be measured to gain the optimized expert＇s weight.Thirdly,the optimized judgment matrix of experts and the optimized decision-making preference of groups are computed out by weighted geometric averaging operator.Finally,an analytical example proves that the decision preference distance model is very effective.

关 键 词：群体决策 多阶段群决策 决策偏好距离 专家阶段权重 

分 类 号：C934[经济管理—管理学]