Case retrieval method based on multiple heterogeneous attributes and incomplete weight information
ZHANG Kai
HUANG Jingfeng
Abstract：A case retrieval method based on regret theory is proposed to address the problem of case retrieval with multiple heterogeneous attributes and incomplete weight information.By defining the perceived utility function based on attribute similarity and regret theory(RT),and based on multidimensional preference analysis(LINMAP)of linear programming technology,a mathematical programming model for determining attribute weights is constructed.On this basis,calculate the perceived utility and determine a set of similar historical cases,calculate the comprehensive utility of similar historical cases,and obtain the ranking of similar historical cases to obtain the most suitable historical case.Finally,the feasibility and effectiveness of this method were verified through a gas explosion case study.The results indicate that this method can provide more objective and accurate results in calculating case similarity and comprehensive utility.
Keywords：case retrievalregret theorymultiple heterogeneous attributesincomplete weight informationmathematical programming
Publication Date：2024-01-30
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：12( 7-18 )