文献类型：期刊文献

英文题名：Integrated triangular fuzzy KE-GRA-TOPSIS method for dynamic ranking of products of customers' fuzzy Kansei preferences

作者：Liu, Dashuai[1];Zhang, Jie[1];Wang, Chenlu[1];Ci, Weilin[1];Wu, Baoxia[1];Quan, Huafeng[2]

机构：[1]East China Univ Sci & Technol, Sch Art Design & Media, Shanghai, Peoples R China;[2]Guizhou Univ Finance & Econ, Coll Big Data & Stat, Guiyang, Guizhou, Peoples R China

年份：2024

卷号：46

期号：1

起止页码：19

外文期刊名：JOURNAL OF INTELLIGENT & FUZZY SYSTEMS

收录：;EI(收录号：20240515456043);WOS:【SCI-EXPANDED(收录号:WOS:001163267400002)】；

基金：We are genuinely pleased to extend our gratitude to editors and anonymous reviewers for their valuable work. Moreover, this work was in part supported by the National Social Science Fund of China under [21&ZD215], Guizhou Provincial Basic Research Program (Natural Science) (No.ZK[2023]029), Guizhou Provincial Education Department's Project for the Growth of Young Science and Technology Talents (No.KY[2022]209).

语种：英文

外文关键词：TF-KE-GRA-TOPSIS; CRITIC and entropy; game theory; customers' fuzzy Kansei preferences; dynamic ranking of products

摘要：As society evolves, companies produce more homogeneous products, shifting customers' needs from functionality to emotions. Therefore, how quickly customers select products that meet their Kansei preferences has become a key concern. However, customer Kansei preferences vary from person to person and are ambiguous and uncertain, posing a challenge. To address this problem, this paper proposes a TF-KE-GRA-TOPSIS method that integrates triangular fuzzy Kansei engineering (TF-KE) with Grey Relational Analysis (GRA) and Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS). Firstly, a Kansei evaluation system is constructed based on KE and fuzzy theory. A dynamic triangular fuzzy Kansei preference similarity decision matrix (TF-KPSDM) is defined to quantify customer satisfaction with fuzzy Kansei preferences. Secondly, dynamic objective weights are derived using Criteria Importance Though Intercrieria Correlation (CRITIC) and entropy, optimized through game theory to achieve superior combined weights. Thirdly, the GRA-TOPSIS method utilizes the TF-KPSDM and combined weights to rank products. Finally, taking the case of Kansei preference selection for electric bicycles, results indicate that the proposed method robustly avoids rank reversal and achieves greater accuracy than comparative models. This study can help companies dynamically recommend products to customers based on their Kansei preferences, increasing customer satisfaction and sales.