一种Web日志序列模式挖掘的改进方法  

Improved method on Web log sequential pattern mining

作　　者：汪琳[1] 庄卫华[1] 

机构地区：[1]河海大学计算机及信息工程学院,南京210098

出　　处：《计算机工程与应用》2010年第7期136-138,共3页Computer Engineering and Applications

摘　　要：Web序列模式挖掘是Web数据挖掘重要研究内容之一。在WAP算法的基础上提出了一种改进算法,该算法在Web序列模式挖掘过程中不需要反复生成条件树,从而提高了算法的运行效率。实验表明,该算法在运行时间上相对于WAP算法具有明显的优势。Web sequential pattern mining has become an important research branch of Web data mining.Based on WAP algorithm,an improved algorithm is proposed.The improved algorithm makes no needs of producing conditional tree repeatedly during the process of mining to become more efficient.The experiment shows that the improved algorithm gains an advantage over WAP algorithm with respect to running time.

关 键 词：WEB数据挖掘 Web序列模式 WAP-tree 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]