作　　者： (张发明）; (于婷）; (赵静）;

机构地区： 南昌大学经济管理学院,江西南昌330031

出　　处： 《模糊系统与数学》 2017年第4期124-134,共11页

摘　　要： 针对语言型评价信息在动态群体评价中的有效集结问题,提出了一种新的时序特征下语言评价信息的激励性集结方法。首先,考虑指标的时序变异特征,通过熵权的相对变异度来修正指标熵权得到各阶段指标的可信权重;其次,给出二元语义时序激励算子(time ordered incentive operator,TOI)的定义,引入柔性时间权重和激励性调节系数,进行评价信息的激励性集结;最后,以某运载火箭研究院对其供应商的合作效果评价为背景进行算例研究。结果表明:所提方法是进行语言型动态群体评价的有效方法,具有良性的激励引导作用,且能在一定程度上避免以往语言信息处理所造成的信息扭曲和损失,为解决动态群体评价问题提供了一种新途径。 With respect to the problem that linguistic group assessment information needs to beeffectively aggregated in dynamie group evaluation, an incentive aggregation method of linguistieassessment information based on time series characteristics is proposed. Firstly, considering the timeseries characteristic, the indicators weights of each phases are determined by relative coefficient ofvariation. Then, this paper presents two-tuple linguistic time ordered incentive （TOI） operator, whileintroduce the method to calculate time weights and incentive regulation factor in order to aggregateinformation effectively. Finally, an example is presented and studied. The results show the proposedmethod is effective. It not only has positive function of motivation and guidance but also avoidsdistortion and loss of information to a certain extent. It provides a new way of the dynamic groupevaluation.

关 键 词： 综合评价 动态群体评价 二元语义 可信权重 激励