摘要： 频繁模式挖掘算法FP-growth算法需递归地生成大量的条件FP-树，且耗费大量存储空间和时间。为此，采用矩阵技术统计约束子树中的频繁项集和频繁项集的支持度，以进行数据挖掘。实验结果表明，该频繁模式挖掘算法是有效的，具有较高的时间效率及空间 效率。

关键词: 频繁模式, FP-growth算法, 矩阵技术, 数据挖掘, 约束子树方法

Abstract: Some problems exists in FP-growth algorithm. It must recursively generate huge number of conditional FP-trees that requires huge volume of memory and costs a lot of time. In this paper. It uses matrix technology constrained sub-tree statistic frequent item sets and frequent item sets for data mining. Experimental result shows constraint sub-tree method with matrix technology is an efficient frequent pattern mining algorithm and it has a better time efficiency and space efficiency.

Key words: frequent pattern, FP-growth algorithm, matrix technology, data mining, constraint sub-tree method

中图分类号: 

• TP311.52