Competence Models and the Maintenance Problem

Abstract

Case-based reasoning (CBR) systems solve problems by retrieving and adapting the solutions to similar problems that have been stored previously as a case base of individual problem solving episodes or cases. The maintenance problem refers to the problem of how to optimize the performance of a CBR system during its operational lifetime. It can have a significant impact on all the knowledge sources associated with a system (the case base, the similarity knowledge, the adaptation knowledge, etc.), and over time, any one, or more, of these knowledge sources may need to be adapted to better fit the current problem-solving environment. For example, many maintenance solutions focus on the maintenance of case knowledge by adding, deleting, or editing cases. This has lead to a renewed interest in the issue of case competence, since many maintenance solutions must ensure that system competence is not adversely affected by the maintenance process. In fact, we argue that ultimately any generic maintenance solution must explicitly incorporate competence factors into its maintenance policies. For this reason, in our work we have focused on developing explanatory and predictive models of case competence that can provide a sound foundation for future maintenance solutions. In this article we provide a comprehensive survey of this research, and we show how these models have been used to develop a number of innovative and successful maintenance solutions to a variety of different maintenance problems.

Coping with Noisy Search Experiences

“…This problem has long been studied in the case-based reasoning literature [16,17], where experience is also collected in a more or less implicit way. With case-base maintenance, however, existing techniques are usually designed to manage case bases with relatively low amounts of noise and work best when relying on an objective measure of when a case can be used to correctly solve some target problem.…”

Credible Case-Based Inference Using Similarity Profiles

“…In fact, much more sophisticated strategies for maintaining a case base are often used in practice [33], including the possibility of removing or replacing stored cases [31,27]. Still, the strategy above is sufficient for our purpose here.…”

A Knowledge-Light Approach to Regression Using Case-Based Reasoning

“…Adding such cases may enable the system to correctly solve similar problems in the future. Another approach is to add cases that increase the coverage of the CB, that is, that extend the range of possible problems that the system can solve [Smyth and Keane 1995;Smyth and McKenna 2001]. A third approach is simply to add all cases that are solved successfully, on the basis that this increases CB density in those areas of domain space where queries most typically occur and consequently where problem solving needs to be most accurate.…”