产生式规则库的求精研究  

A STUDY ON RULE BASE REFINEMENT

作　　者：孙运传[1] 别荣芳[1] 

机构地区：[1]北京师范大学信息科学学院计算机系,北京100875

出　　处：《北京师范大学学报（自然科学版）》2003年第4期435-443,共9页Journal of Beijing Normal University(Natural Science)

基　　金：国家自然科学基金 (青年 )资助项目 (10 0 0 10 0 6 )

摘　　要：把规则库中的冗余规则分为蕴涵规则冗余、抽象规则冗余和死规则冗余 3类 ,提出利用文字集的闭包和规则抽象分别处理蕴涵规则冗余和抽象规则冗余 ,给出了相关的算法 ,并针对蕴涵冗余开发了有效的软件工具 .同时讨论了规则库的一致性 ,给出相应的处理策略 ,考察了规则库求精在网络知识管理、Internet结构分析和DataMining中的应用 .To eliminate redundancy and guarantee consistency are the two main points of the study on rule base refinement which plays important roles in enhancing the efficacy and efficiency of utilizing a rule base. Here redundancies in a rule base are classified into three types: implication-rule redundancy, abstraction-rule redundancy and dead-end-condition redundancy. Two approaches are proposed: one is to remove implication redundant rules by using the closure of literal set, and the other is to remove abstraction redundant rules by using rule-abstraction. A software is developed to support the first approach. Experiments show that the tool works correctly and efficiently. This paper also discusses the consistency of the rule base and relevant strategies in dealing with inconsistency and brings forward applications of rule base refinement to Internet and Data Mining, etc..

关 键 词：规则抽象 规则库求精 冗余规则 专家系统 

分 类 号：TP301.1[自动化与计算机技术—计算机系统结构]