利用XML的一种因果模式Web挖掘模型  

A Causal Pattern Web Mining Model Based on XML

作　　者：李孝忠[1] 赵国桦[1] 

机构地区：[1]天津科技大学计算机科学与信息工程学院,天津300222

出　　处：《天津科技大学学报》2010年第2期65-67,共3页Journal of Tianjin University of Science & Technology

基　　金：国家自然科学基金资助项目(70571056)

摘　　要：定义了一种因果关系模式,包括因集、果集和各种因果关系,以及影响度、分类权值等参数.再结合统计分析等各种数据挖掘算法和XML的优势组成了一种Web挖掘模型,该模型可用来发现Web上事物之间的内在联系以及发生规律,以便为任务的执行提供有力的预测和决策依据.应用实例表明,该模型是有效的,能够在预测和决策中发挥作用.A causal pattern was defined, including resulting set, factor set, a variety of causal relations and kinds of parameters such as impact degree, category weight. Then combined with statistical analysis of various data mining algorithms and the advantages ofXML, a Web mining model was formed to find the intrinsic link and the occurrence between things on the Web. The model could be used to provide a strong basis of the forecasting and decision-making for the future implementation of the mandate. Application example shows that the model is effective and benefits the forecasting and decisionmaking.

关 键 词：WEB挖掘 因果模式 因集 果集 影响度 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]