基于Web日志挖掘的自适应网站构建方法研究  

Approach of Adaptive Web Site Construction Based on Web Logs Mining

作　　者：母俐丽[1] 

机构地区：[1]兰州交通大学电子与信息工程学院,甘肃兰州730070

出　　处：《计算机与现代化》2010年第3期144-147,150,共5页Computer and Modernization

摘　　要：自适应网站能够提高网站对用户的服务质量。本文首先给出自适应网站的总体框架,对框架中主要模块做详细的分析,包括数据预处理、数据挖掘、页面推荐和站点调整。在数据挖掘模块给出一种有效的识别用户访问模式的算法,该算法利用数据库查询简化频繁最大前向访问路径集的查找,并在此基础上形成频繁访问路径图,为页面推荐和站点调整做好准备。最后给出自适应网站的设计原则。Adaptive Web site construction based on Web mining could improve the semite quality for users. The adaptive Web site general framework is proposed. A detailed analysis is made for main modules of the framework, including data pre-processing, data mining, page recommendation and site adjustment. An effective algorithm of user access patterns identification is proposed in data mining module. The algorithm utilizes database query to simplify the find of the most frequent access paths set, and then forms a frequency access patterns map preparing for page recommendation and site adjusunent. Finally, the adaptive Web site design prineiples are proposed.

关 键 词：自适应网站 频繁访问路径图 页面推荐 站点调整 数据挖掘 WEB日志 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]