An opinions-updating model for large-scale group decision-making driven by autonomous learning

This paper aspires to explore and construct a more objective and automated large-scale group decision-making (LSGDM) model. The concept of vacillation degree based on probabilistic double hierarchy linguistic term set is proposed to describe the characteristics of decision makers (DMs). The criteria weights are obtained by entropy measure, and then a clustering method is constructed. Moreover, the autonomous learning probability is presented to characterize the extent to which DMs accept the opinions of others. The complex connections between DMs can be more clearly described by visualizing the autonomous learning. Considering the deficiencies of the existing feedback adjustment mechanism on the setting of the suggested adjustment range, the autonomous learning and opinions-updating process for internal and external subgroups are designed. Then consensus judgment method is also proposed from subgroups and group. Based on the above work, an opinions-updating model for LSGDM driven by autonomous learning is constructed. The validity of the model is verified by a case study of emergency medical service agency selection. Finally, three simulation models and comparative analysis are established to test the opinions-updating model.