混合多属性群决策中的群体一致性分析方法

A Method for Consensus Analysis in Hybrid Multiple Attribute Group Decision Making

本文针对一类属性值为精确实数、区间数和语言值的混合型多属性群决策问题,提出了一种群体一致性分析方法。在该方法中,计算群体一致度时,首先根据专家提供的评价信息在属性层面上计算专家之间的差异度,再由此得到群体一致度,计算过程中不需进行数据类型转换,避免了数据类型转换造成的信息损失;当群体不一致时,在属性层面上给出相应的调整策略,可以使专家有针对性地修改相应属性上的评价信息,使群体尽快达成一致,同时避免了专家评价信息的过度修改。最后通过一个实例分析验证了该方法的可行性和有效性。

An approach of consensus analysis among group opinions is proposed considering the problem of hybrid multiple attribute group decision making which involves real numbers, interval numbers and linguistic assessments. In calculating the degree of group consensus, the proposed approach obtains the degree of group consensus by spotting the difference of any pair of experts according to their evaluattion information with respect to each attribute. In the process of calculating, data type does not need any conversion, which, in turn, secures no information losses. When the group is not in consensus, a feedback mechanism is developed on the attribute level to prompt the experts to revise the evaluation information of relevant attribute, thus to reach the group consensus. Experts target revising the relevant attribute of evaluation information making the group agree each other as soon as possible. At the same time, excessive modification of evaluation information can be avoided. Finally, an example is given to illustrate the feasibility and validity of the proposed method.