基于Louvain方法的社会网络大群体决策交互共识模型  

An interactive consensus model for large scale group decision making with social network based on Louvain method

作　　者：赵萌[1,2] 李子超 高美 沈哲[2] ZHAO Meng;LI Zichao;GAO Mei;Shen Zhe(School of Business Administration,Northeastern University,Shenyang 110819,China;Northeastern University at Qinhuangdao,Qinhuangdao 066004,China;School of Software&Microelectronics,Peking University,Beijing 102600,China;School of management,Harbin Institute of Technology,Harbin 150001,China)

机构地区：[1]东北大学工商管理学院,辽宁沈阳110819 [2]东北大学秦皇岛分校,河北秦皇岛066004 [3]北京大学软件与微电子学院,北京102600 [4]哈尔滨工业大学经济与管理学院,黑龙江哈尔滨150001

出　　处：《管理工程学报》2021年第4期152-161,共10页Journal of Industrial Engineering and Engineering Management

基　　金：国家自然科学基金资助项目(71701037);中央高校基本科研业务费资助项目(N182304025);河北自然科学基金资助项目(F2017501072)。

摘　　要：由于社会网络分析可以反映决策者在大群体决策(large group decision making,LGDM)共识问题中的社会关系,因此研究基于社会网络的LGDM共识问题具有现实意义。本文通过考虑决策者之间的社会网络关系,提出了一种交互式共识模型:首先,根据决策者之间的社会关系,采用Louvain方法对网络进行聚类,以降低大规模社会网络的复杂性;然后,基于可能性分布的犹豫模糊元素来表示每个子群的偏好,根据社会网络分析的中心性,计算决策者和子群权重;随后,给出三个层次的共识测量和反馈机制,来加速共识的达成过程。该模型在一致性调整过程中,整个社会网络也随之更新,允许子群分类的改变,而且考虑决策者的交互使结果更容易被接受。最后,通过案例分析验证方法的可行性,并通过与现有方法的比较,说明了方法的优越性。Due to the growth of the large-scale interaction between users,some researchers have noticed the problem of Large Group Decision Making(LGDM).It is more difficult to obtain consensus among participants than traditional GDM issues.Therefore,reaching a consensus has become a basic issue for LGDM.As the LGDM consensus problems have begun to attract more attention,some researchers have solved the LGDM consensus problem by directly using the traditional GDM consensus model,but the result is with a large number of calculations and complex steps.Therefore,some researchers began to reduce the dimensions of LGDM problems through clustering algorithms.However,most traditional clustering algorithms used in these studies,such as K-means and PAM,require that k value is subjectively predetermined.Unfortunately,there are no specific theoretical guidelines to set the k value.In addition,researchers also proposed some models to improve the consensus of LGDM consensus problems.Those models are mainly divided into automatic methods and interactive methods.The automatic feedback mechanism is time-saving,while the interactive feedback mechanism requires expert interaction,but the results obtained are more accurate.However,both automatic and interactive methods have drawbacks.The results obtained by automated models are not precise enough,and interactive models require more time and effort.Moreover,most studies assume that all decision makers are independent,and few studies consider social relationships between decision makers.Social networks can not only enrich and improve the preference information of decision makers,but also promote the consensus process.Social networks have certain advantages in solving the complexity of LGDM issues.Some studies have done a great achievement to the application of SN in LGDM,but most of these studies only focus on the selection process and do not refer to consensus and consensus improving process.Therefore,by considering social network information among decision makers,a new interactive consensus m

关 键 词：大规模群体决策 社会网络 Louvain方法 共识模型 基于可能性分布的犹豫模糊元素 

分 类 号：C934[经济管理—管理学]