Z概率语言术语集环境下改进的PROMETHEE Ⅱ方法及其应用  

An improved PROMETHEE II method and its application in Z probabilistic linguistic term sets circumstances

作　　者：何昳 毛军军[1,2] 邓丽君 HE Yi;MAO Junjun;DENG Lijun(School of Big Data and Statistics,Anhui University,Hefei 230601,China;Key Laboratory of Intelligent Computing&Signal Processing,Ministry of Education(Anhui University),Hefei 230601,China)

机构地区：[1]安徽大学大数据与统计学院,合肥230601 [2]计算智能与信号处理教育部重点实验室(安徽大学),合肥230601

出　　处：《延边大学学报（自然科学版）》2023年第3期223-229,共7页Journal of Yanbian University（Natural Science Edition）

基　　金：国家自然科学基金面上项目(72171002);安徽省省级研究生教育教学改革研究项目(2022jyjxggyj135)。

摘　　要：针对属性权重未知的多属性决策问题,在Z概率语言术语集(ZPLTS)环境下,提出了一种改进的PROMETHEE Ⅱ (preference ranking organization method for enrichment evaluations Ⅱ)方法.在该方法中,各评价信息的综合可靠度由评价本身的可靠度和决策者给出的可靠度来确定,并由此进一步确定属性的权重;距离测度采用扩展的欧式距离,该方法在ZPLTS环境下能够克服不同Z概率语言值(ZPLVs)之间的距离均为0所带来的决策偏差.实例研究表明,该方法在反映原始数据信息和确定未知属性权重方面显著优于TOPSIS方法和传统的PROMETHEE Ⅱ方法,因此该方法可应用于多属性决策问题中.For multi-attribute decision problems with unknown attribute weights,an improved PROMETHEE II(preference ranking organization method for enrichment evaluations II)method was proposed in the ZPLTS(Z probabilistic linguistic term sets)environment.In this method,the comprehensive reliability of each evaluation information was determined by the reliability of the evaluation itself and the reliability given by the decision maker,and the weights of the attributes were further determined.The distance measure adopts extended Euclidean distance,which can overcome that the deviation of decision results caused by the distance between different ZPLVs being 0 in the ZPLTS environment.The practical application shows that this method significantly outperforms the TOPSIS method and the traditional PROMETHEE II method in reflecting the original data information and determining the weights of unknown attributes.Therefore,this method can be applied to multi-attribute decision problems.

关 键 词：多属性决策问题 改进的PROMETHEEⅡ方法 可靠度 Z概率语言术语集 属性权重 距离测度 

分 类 号：C934[经济管理—管理学]