Preference-Based CBR: A Search-Based Problem Solving Framework

摘要: Preference-based CBR is conceived as a case-based reasoning methodology in which problem solving experience mainly represented the form of contextualized preferences, namely preferences for candidate solutions context target to be solved. This paper continuation recent work on formalization preference-based that was focused an essential part methodology: method predict most plausible solution given set other solutions, deemed relevant at hand. Here, we go one step further by embedding this more general search-based framework. In framework, formalized search process, space traversed through application adaptation operators, and choice these operators guided preferences. The effectiveness approach illustrated two case studies, from field bioinformatics related computer cooking domain.