Case-based reasoning (CBR) is an artificial intelligence technology that encodes problem-solving expertise as a database of cases, where each case encodes a solution to a previously-encountered problem. A CBR system solves new problems by searching this database to retrieve the case with the most similar problem description. Then, the system adapts the solution contained within this case in order to address characteristics of the current problem that differ from the problem in the retrieved case. As an enabling technology for intelligent decision-support systems, CBR has several advantages. First, the expertise of the system can be extended to increase the set of situations it can handle by adding new cases to the case base, within minimal and predictable interactions with previously-entered cases. Also, representing expertise as cases simplifies knowledge acquisition because subject matter experts usually find it easier to recall and discuss specific or prototypical situations and their solution, compared to articulating general or abstract principles and reasoning strategies.
Solution
Stottler Henke developed ESTEEM, a case-based reasoning (CBR) development tool that enables non-programmers to build decision-support and problem-solving applications which employ case-based reasoning. ESTEEM provides general purpose case definition facilities, a wide range of case similarity and retrieval options, techniques for incorporating rule-based inference for retrieval and case manipulation, support for nested case-bases, and specification of end-user functionality.
Status
ESTEEM was marketed by Esteem Software Incorporated from 1991 to 2001. Applying Case-Based Reasoningdescribes ESTEEM as being “a good tool for people interested in exploring the potential of CBR within their organizations.”
Additionalinformation
ESTEEM: Enabling Solutions Through Experience Modeling
