摘要
针对目前多阶段交互式群体评价研究大多是基于单一评价信息且多适用于中小规模群体的不足,提出了一种大规模混合信息下的交互式群体评价方法.文章首先选用不同的函数对混合信息进行一致化处理;其次运用语言系统聚类的方法对评价群体进行划分,并在每类中选取一个"委托者"来进行下轮的交互;然后给出了稳定性和一致性指标,以此来判断交互终止;最后在密度加权平均算子和认可度诱导语言算术加权集结(RLOWA)算子的基础上,对评价信息进行单轮和多轮的集结.算例验证了方法的有效性和普适性.
In multi-stage interactive group evaluation studies are mostly based on single assessment information and more suitable for small and medium-sized group, this paper proposes a method about large-scale interactive group evaluation under the blend information. First, we choose different function to process the mixed information; Secondly, by using the linguistic system clustering method to take a classification for the evalnation group, we select a consignor in each type for the next interact; Then, the stability and consistency index is given to determine the interaction end; Finally,using the density weighted average operator and induced language recognition arithmetic weighted aggregation (RLOWA) operator to rally the evaluation information in single wheel and several rounds. Numerical examples illustrate the effectiveness and the universality of the method.
出处
《系统科学与数学》
CSCD
北大核心
2017年第12期2400-2411,共12页
Journal of Systems Science and Mathematical Sciences
基金
国家自然科学基金(71361021
41661116)
江西省教育厅科技资助项目(GJJ150027)
江西省社会科学"十二五规划"重点项目(15ZQZD01)
江西省学位与研究生教改研究重点项目(JXYJG-2014-002)
江西省赣鄱英才555工程项目
江西省青年科学家(井冈之星)项目资助课题
关键词
大规模
混合信息
交互式
群体评价
Large scale, blend information, interactive evaluation, group evaluation