关联规则模式维护算法

Algorithm for Association Rules Pattern Maintenance

大部分关联规则更新算法只考虑最小支持度这一因素,没有考虑最小置信度阈值,而在数据库更新时只考虑数据的添加,不考虑数据的删除。为此,提出一种可同时考虑上述问题的动态数据库更新算法,该算法可有效挖掘出人们感兴趣的知识,并能节省大量挖掘时间。实验结果表明,该算法是切实可行的。

As the majority updating algorithms for association rules have the same shortcomings which only take account of the minimum support and data increase, without the minimum confidence and data decrease. This paper proposes a new updating algorithm for dynamic database which can avoid some shortcomings of the above. It can effectively mine some interested knowledge and save a large amount of mining time. Experimental result shows that the proposed approach is feasible.