Automating case selection in the construction of a case library

摘要

An approach to case selection in the construction of a case library is presented in which the most useful case to be added to the library is identified by evaluation of the additional coverage provided by candidate cases. Cases that can be solved by the addition of a candidate case to the library are discovered in the approach by reversing the direction of case-based reasoning. The computational effort required in the evaluation of candidate cases can be reduced by focusing the search on a specified region of the problem space. The approach has been implemented in CaseMaker, an intelligent case-acquisition tool designed to support the authoring process in a case-based reasoner for estimation tasks.