Using case-based techniques to enhance constraint satisfaction problem solving
Ye Huang · Applied Artificial Intelligence · 1996
This article reports on investigations using case-based reasoning to deal with large constraint satisfaction problems associated with the assembly of holiday packages. The system aims to reduce the amount of consistency checking in terms of database queries. The holiday reservation problem is characterized by exhibiting large cardinality in the constraint tables. In order to reduce the load on the database server, issues concerning the similarity measurement, the quality of the exemplars in the case base, and the conflict ordering problem are addressed. Methods of improving system performance by using case-based techniques have been presented. Empirical results are reported to demonstrate the effectiveness of these methods. Ways of forming a hybrid system using the case-based techniques and a constructive approach to achieve a better overall performance are also outlined.