摘要： 如何确定候选频繁序列模式以及如何计算它们的支持数是序列模式挖掘中的两个关键问题。该文提出了一种基于二进制形式的候选频繁序列模式生成和相应的支持数计算方法，该方法只需对挖掘对象进行一些“或”、“与”、“异或”等逻辑运算操作，显著降低了算法的实现难度，将该方法与频繁序列模式挖掘及更新算法相结合，可以进一步提高算法的执行效率。

关键词: 数据挖掘；序列模式；增量式更新

Abstract: How to generate candidate frequent sequential pattern and calculate its support is a key problem in mining frequent sequentialpatterns. An efficient and fast algorithm based on binary format for discovering candidate frequent sequential patterns and calculating its support isproposed, which only executes some logical operation. A performance comparison of this algorithm with GSP algorithm and ISE is given, and theexperiments show that the new methods are more efficient.

Key words: Data mining; Sequential pattern; Incremental update