摘要
文章主要论述了在Web使用挖掘数据预处理中如何构造用户与网站之间的会话。首先,根据对Web服务器日志数据格式的分析,对会话概念进行了形式化描述;然后在分析目前会话构造方法的基础上,利用基于时间和引用的启发式方法来构造会话;最后依据评估会话构造方法的标准,通过实验对给出的新会话构造方法与其他方法进行了分析比较。
This paper mainly discusses the methods how to construct the sessions between sites and users in the data preprocessing of web usage mining.First of all,by the analysis of web server log format,we have given the formal descriptions of the concept of session,Secondly,on the basis of analyzing the current session construction methods,the paper proposes the time-referrer-based heuristic method that can be used to construct sessions.Finally according to measures for session construction methods,the paper compares the performance of the time-referrer-based method to other session construction methods by means of experimental data.
出处
《计算机工程与应用》
CSCD
北大核心
2005年第25期148-151,共4页
Computer Engineering and Applications
基金
合肥工业大学科研发展基金项目资助(编号:030503F)