带限制的动态数据库中大项目集增量式挖掘

Incremental Mining Large Itemsets with Constraints in Dynamic Databases

提出了一种带限制的动态数据库中大项目集的增量式挖掘算法 ,基于限制条件它有 4种优化策略 ,并对候选项目集进行修剪 ,减少了候选项目集的数量 .同时 ,利用已挖掘的大项目集计算本次挖掘中大项目集的记数 ,减少了I/O的次数 .该算法允许用户不断改变限制条件 ,实现交互式挖掘 ,而且可将挖掘的目标仅仅聚焦到其感兴趣的模式上 ,这不仅适用于对数据库进行插入操作 ,还适用于删除、修改操作 .

An incremental mining technique is developed for large itemsets with constraints in dynamic databases, where four optimization strategies are proposed to prune candidate itemsets. The previously mined large itemsets are employed to compute currently large itemset counts and the I/O number can be reduced. The method allows users to change constraints to implement interactive mining, and also facilitates the users to focus the mining on their interesting patterns. It is indicated that the method is suitable for the cases of insertion deletion and modification of operation in the database.