在对Web应用挖掘的基本步骤作系统性研究的基础上,设计了一个Web应用挖掘可视化系统.该系统能够对用户访问Web时服务器方留下的访问记录进行挖掘,从中得出用户的访问模式和访问兴趣,并对所得出的结果进行可视化的处理.为了识别用户浏览模式利用Apriori算法对Web应用挖掘过程中预处理阶段所产生的用户会话文件进行了挖掘.采用Web图可视化了Web站点的拓扑结构以及各节点访问计数和登录计数信息.Web图的新颖之处在于两点:首先,为了将Web拓扑结构映射到Web图上,利用了站点拓扑结构数据和站点应用数据；其次,在绘制表示用户登录计数的信息层时允许通过使用动态布局的方法,以及为每一层的节点重新分配360度周长的方法来解决节点之间的冲突问题.文中较详细地阐述了该系统对Web应用数据挖掘可视化界面布局的具体措施.%Underlying the systematic studies on the basic steps of Web usage mining,implemented a visual Web usage mining system, which is a system mainly used to mine the Web log access file that acquired from the Web Server, get the user visiting patterns and visiting interests and then visualize the mining results. In order to identify the navigational patterns of Web site visitors, Apriori algorithm is used on the mining of the user session file that has been generated after the data pie-processing process on the Web log file. In order to effectively visualize the topology of a Web site and the visiting numbers and login numbers of per page, the Web image is used. The novelty of the system is two: Firstly .adopt a new strategy for collapsing the Web topology into a tree structure exploiting Web usage data, in addition to the structure of the site. Secondly, deal with the problem of occlusion by using a dynamic layout that redistributes the nodes of each level along the 360 degree perimeter when visualized information layer that represents the user login numbers. It illustrates in detail concrete measures mat have applied on visual Web usage mining interface layout.
展开▼
