| 基于最长前缀频繁子路径树的Web日志挖掘算法 |
| |
| 引用本文： | 翁伟,林开标,朱顺痣,王震岳.基于最长前缀频繁子路径树的Web日志挖掘算法[J].成都大学学报(自然科学版),2013,32(3):285-288. |
| |
| 作者姓名： | 翁伟 林开标 朱顺痣 王震岳 |
| |
| 作者单位： | 厦门理工学院计算机与信息工程学院,福建厦门,361024;厦门理工学院计算机与信息工程学院,福建厦门,361024;厦门理工学院计算机与信息工程学院,福建厦门,361024;厦门理工学院计算机与信息工程学院,福建厦门,361024 |
| |
| 基金项目： | 厦门市科技计划高校创新课题，福建省教育厅B类课题 |
| |
| 摘 要： | 现有的Web日志频繁访问路径挖掘算法往往不能在追求时间效率的同时准确挖掘出符合用户浏览顺序的频繁路径.提出了有效挖掘Web日志中频繁访问路径的算法,将事务数据库转换为Web访问路径树,根据支持度进行剪枝构造最长前缀频繁子路径树,然后进行频繁路径挖掘,实验证实了此方法的有效性,并分析了支持度设置对频繁路径生成的影响.
|
| 关 键 词： | Web日志挖掘 频繁访问路径 访问路径树 |
Web Logs Mining Algorithm Based on Longest Prefix Frequent Sub-path Tree |
| |
| WENG Wei
,
LIN Kaibiao
,
ZHU Shunzhi
,
WANG Zhenyue.Web Logs Mining Algorithm Based on Longest Prefix Frequent Sub-path Tree[J].Journal of Chengdu University (Natural Science),2013,32(3):285-288. |
| |
| Authors: | WENG Wei LIN Kaibiao ZHU Shunzhi WANG Zhenyue |
| |
| Institution: | (College of Computer and Information Engineering, Xiamen University of Technology, Xiame 361024, China) |
| |
| Abstract: | The existing web logs mining algorithm for frequent access path often can not accurately meet the users＇ accessing order in pursuit of time effciency. An efficient web logs mining algorithm for frequent ac- cess path is proposed, which converts the transaction database to web access path tree and prunes the tree branches to create the longest prefrx frequent sub-path tree according to support degree, and then the min- ing process is implemented. The experiment confirms the effectiveness of this method, and analyzes the im- pact of the settings of frequent support degree on frequent paths generation. |
| |
| Keywords: | web logs mining frequent access path WAP-tree |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
