earticle

영어

Case-Based Reasoning (CBR) is widely used for problem solving in many fields, but there still exist limitations for the problems with dynamic characteristics. This work tries to introduce approaches in Sequence Pattern Mining (SPM) to extend the capability of CBR for solving problems described with sequential data. We propose a SPM algorithm named wGSP, which takes user’s different concerns on events into consideration by weight setting, to discover typical patterns in case base. Then the support information of cases to typical patterns is used to depict cases and facilitate efficient case retrieval. The contribution of this work lies in two aspects: firstly it is an improvement to traditional CBR method for coping with sequential data based cases with better interpretability and higher efficiency; secondly, it provides flexibility for parameters setting in SPM to satisfy the personalized preferences of users. Finally through a calculating instance, the advantages and effectiveness of the two-step CBR method based on sequential data is illustrated.