Research on Multi-Attribute Decision Making Based on Data Mining Under the Dynamic Hybrid Trust Network
Aiming at the problem that the relationship between experts is no longer an independent multi-attribute group decision-making under the development of big data and network environment, a PROMETHEE multi-attribute decision-making method based on data mining under dynamic hybrid trust network is proposed. Firstly, the evaluation similarity based on degree centrality and the expert trust value based on K-hop centrality are considered in the social network to obtain the weight of experts. Secondly, since the expert weight will be affected by the attribute weight to a certain extent, the public-level attribute weight is obtained through data crawling and TF-IDF technology, and the comprehensive attribute weight is obtained by combining the expert-level attribute weight. In addition, establishing a minimum adjustment cost model enables experts to form a dynamic consensus reaching process in the composed hybrid trust network. Finally, in order to express the evaluation information of experts more accurately in a complex language environment, the probabilistic language PROMETHEE method is introduced and applied to the site selection evaluation of charging and swapping stations, which reflects the feasibility and effectiveness of the proposed method through the comparison of decision-making methods and parameter sensitivity analysis.Aiming at the problem that the relationship between experts is no longer an independent multi-attribute group decision-making under the development of big data and network environment, a PROMETHEE multi-attribute decision-making method based on data mining under dynamic hybrid trust network is proposed. Firstly, the evaluation similarity based on degree centrality and the expert trust value based on K-hop centrality are considered in the social network to obtain the weight of experts. Secondly, since the expert weight will be affected by the attribute weight to a certain extent, the public-level attribute weight is obtained through data crawling and TF-IDF technology, and the comprehensive attribute weight is obtained by combining the expert-level attribute weight. In addition, establishing a minimum adjustment cost model enables experts to form a dynamic consensus reaching process in the composed hybrid trust network. Finally, in order to express the evaluation information of experts more accurately in a complex language environment, the probabilistic language PROMETHEE method is introduced and applied to the site selection evaluation of charging and swapping stations, which reflects the feasibility and effectiveness of the proposed method through the comparison of decision-making methods and parameter sensitivity analysis