摘要: 介绍了网络日志挖掘的基本概念,提出了一个网络日志挖掘通用系统的结构,分析了本地缓存和代理服务器对日志挖掘的影响,并给出了一种近似解决方案。这种方案通过网络拓扑结构和日志文件记录的结合,将杂乱无章的日志记录组合成具有语义信息的事务记录,从而使挖掘结果更有意义。
关键词:
网络日志,
数据挖掘,
本地缓存,
代理服务器
Abstract: This paper introduces the conception of Web usage mining, and gives an architecture of generic Web usage mining system, also analyzes the influence of local caching and proxy server to the mining procedure, and gives an approximate solution. Using the topology of the Web site, this solution transforms the disorder Web access logs into semantical transactions and makes the mining result more meaningful.
中图分类号:
李毅,李石君. 本地缓存和代理服务器环境下的网络日志挖掘[J]. , 2003, 29(05): 54-56.
LI Yi, LI Shijun. Web Usage Mining Under Local Caching and Proxy Server Environment[J]. , 2003, 29(05): 54-56.