摘要： 针对增量式更新关联规则算法FUP会产生大量候选项集和多次扫描数据库的问题，提出改进算法PFUP。该算法借鉴强频繁项集概念，利用强频繁项集连接生成小数量的候选项集，采用预剪枝策略减少对数据库的扫描次数。仿真实验表明，在数据库和支持度相同的情况下，PFUP算法的执行时间比FUP算法减少了50%左右。

关键词: 关联规则, FUP算法, PFUP算法, UWEP算法

Abstract: Fast Update(FUP) algorithm always produces a lot of candidate itemsets and scans database many times. An improved Pruning and Fast Updating(PFUP) algorithm is presented to solve such two bottleneck problems of FUP. PFUP algorithm joins strong large itemsets into small quantitative of candidate itemsets based on strong large itemsets concept, and adopts early pruning strategy to cut down the times of scanning database. Simulation shows that the execution time of PFUP algorithm reduces to about 50% compared with FUP algorithm in the case of the same database and support.

Key words: association rules, Fast Update(FUP) algorithm, Pruning and Fast Updating(PFUP) algorithm, Update With Early Pruning(UWEP) algorithm

中图分类号: 

• TP301.6