Rule Base Partitioning for Constructing Meta-rule

Abstract

Expert system technology becomes more and more important for next generation computer systems. A rule base is a widely used approach to construct an expert system, where knowledge and expertise are represented as production rules. However, due to the growth of rule base usage, the scale of rule base is increasing and hence many management related issues arise. By considering not only the structural relatedness between rules but also the semantic relatedness of rules, RP-MES is proposed combining both rule base partitioning mechanism and meta-rule construction mechanism to solve these issues in this paper. An Intrusion Detection prototype System is also designed and implemented based on RP-MES, and some experiments have been done to evaluate the system performance. The experimental results show that RP-MES can improve the accuracy of the inference results, and that the performance of RP-MES is better than that of original rule base without partitioning.