不完全信息下基于证据推理的多属性决策方法研究  

A Method of Multi-attribute Decision-making with Incomplete Information Based on Evidence Reasoning

作　　者：张洪涛[1] 王慧[1] 马驰[1] 

机构地区：[1]安徽理工大学理学院,安徽淮南232001

出　　处：《安徽理工大学学报（自然科学版）》2008年第3期87-92,共6页Journal of Anhui University of Science and Technology:Natural Science

基　　金：安徽省教育厅自然科学研究资助项目(KJ2008B148);安徽省教育厅人文社会科学研究资助项目(KJ2008B190);安徽理工大学硕博基金资助项目(2007yb51);安徽理工大学青年基金资助项目

摘　　要：针对不完全信息下多属性群体决策中存在的问题,提出一种基于证据推理的多属性群体决策方法。该方法首先应用灰色白化权函数将定量属性定性化,然后针对不同专家知识背景的不同,构建基于属性的专家赋权方法,用证据推理方法将不完全信息下的多个专家的意见进行集结,并应用效用理论对方案进行排序择优。最后通过一个算例验证该方法的有效性和可行性。A new decision-making approach based on evidence reasoning was proposed for multi-attribute group decision- making with incomplete information. Firstly quantitative attributes were converted to qualitative ones by the whitenization weight function. Then the weights of experts on the attributes were given based on the experts＇ knowledge. The evaluation values to the attributes given by experts were combined by evidence reasoning and all decision alternatives were ranked by using utility theory. Finally the feasibility and validity of the method was verified by an example.

关 键 词：证据推理 不完全信息 白化权函数 多属性群决策 

分 类 号：C934[经济管理—管理学]