Web挖掘的体系研究  

Research on the structure of Web mining

作　　者：李亚飞[1] 刘业政[1] 

机构地区：[1]合肥工业大学管理学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2004年第3期305-309,共5页Journal of Hefei University of Technology：Natural Science

摘　　要：互联网的出现极大地丰富了人们的信息,但也困扰人们从中获取有用的知识。Web挖掘的应用为解决此问题指明了方向。该文从Web内容挖掘、Web结构挖掘和使用记录挖掘3个方面论述了Web挖掘的内容及相关技术的研究现状和发展方向。Web内容挖掘包括信息提取和信息检索,Web信息提取的主要过程包括向量表示、特征提取、特征缩减和文本挖掘;对于信息检索,文章从搜索引擎的原理、分类以及最新的发展技术方面对其进行了论述;而对于结构挖掘和使用记录挖掘,文章主要论述了其算法和过程。People are puzzled about how to get the knowledge that they need in the huge amount of information from Internet nowadays. The application of Web mining technology is a way to solve this problem. In this paper,the Web Content Mining(WCM), the Web Structure Mining(WSM) and the Web Usage Mining(WUM) are discussed from their contents, research status and development direction. The WCM consists of Web Information Extraction(Web IE) and Web Information Retrieval(Web IR). The process of Web IE includes vector expressing, character extracting, character reducing and text mining. As to Web IR, it is described from the principle, classification and latest achievement of the search engine. The algorithms and processes of WSM and WUM are also introduced in the paper.

关 键 词：WEB内容挖掘 WEB结构挖掘 WEB使用记录挖掘 

分 类 号：TP393.4[自动化与计算机技术—计算机应用技术]