| 非页面日志信息在改进会话识别中的应用研究 |
| |
| 引用本文： | 姜宏飞,范纯龙,徐蕾.非页面日志信息在改进会话识别中的应用研究[J].沈阳航空工业学院学报,2010,27(1):60-64. |
| |
| 作者姓名： | 姜宏飞 范纯龙 徐蕾 |
| |
| 作者单位： | 沈阳航空工业学院计算机学院,辽宁沈阳,110136 |
| |
| 摘 要： | 会话识别是web日志挖掘数据预处理的关键步骤，其质量对日志挖掘结果有重要影响。文章介绍了现有的会话识别方法，提出了利用数据清洗中废弃的图片等日志数据和web图结构，改进会话识别中的页面分组规则和路径补全算法，并通过实验证实方法对改善会话识别质量是有效的。
|
| 关 键 词： | 会话识别 数据预处理 web图结构 |
The application research of non——page log information in improving session identification |
| |
| JIANG Hong-fei,FAN Chun-long,XU Lei.The application research of non——page log information in improving session identification[J].Journal of Shenyang Institute of Aeronautical Engineering,2010,27(1):60-64. |
| |
| Authors: | JIANG Hong-fei FAN Chun-long XU Lei |
| |
| Institution: | JIANG Hong- fei FAN Chun- long XU Lei (Dept. of Computer Science, Shenyang Institue of Aeronautical Engineering ,Liaoning Shenyang 110136) |
| |
| Abstract: | Session identification is a key step for web log mining data pre - processing, and its quality has significant impacts on the log mining results. This paper introduces the current session identification methods, proposes a method which uses the web graph structure and log data including abandoned pictures in data cleaning to improve page grouping rules and path completion rules algorithm in the session identification. Finally the method is experimentally proved to be effective to improve the session identification of quality. |
| |
| Keywords: | session identification data pre - processing web graph structure |
| 本文献已被 维普 万方数据 等数据库收录！ |
