序列模式增量式更新的研究

Study of incremental updating for mining sequential patterns

序列模式挖掘是数据挖掘领域中十分重要的研究课题。目前已有许多算法用于序列模式的挖掘,但在序列模式增量式更新方面的研究还比较少,针对这种情况提出了序列模式增量式更新的挖掘算法SPIU。SPIU算法充分利用了原有的挖掘结果,并对产生的候选频繁序列进行剪枝,有效地减小了候选频繁序列的大小,从而很好地改善了挖掘效率。测试结果表明SPIU算法是正确和高效的,另外算法还具有很好的扩放性。

Sequential pattern mining is an important research topic in data mining. There are many algorithms for efficient discovery of sequential patterns. However, very little work is done on maintenance of discovered patterns. A new algorithm named SPIU is proposed, which make use of the previous mining results and prune to the candidate frequent sequence. The size of candidate frequent sequence is reduced and the mining efficiency is improved effectively. Synthetic data shows that it is efficient, and it has very good scale-up properties.