WWW缓冲挖掘中基于粗糙集的用户模糊兴趣建模  

Rough set-based user's fuzzy interest model in mining WWW cache

作　　者：张卫丰[1] 徐宝文[2,3] 

机构地区：[1]南京邮电学院计算机科学与技术系 [2]东南大学计算机科学与工程系 [3]江苏省软件质量研究所江苏南京210096

出　　处：《计算机应用》2005年第9期1992-1994,1998,共4页journal of Computer Applications

基　　金：国家杰出青年科学基金资助项目(60303024);国家自然科学基金资助项目(90412003);国家973规划资助项目(2002CB312000);教育部跨世纪优秀人才基金;教育部博士点基金;江苏高校自然科学研究计划(04kjb520096)

摘　　要：如何有效充分地利用WWW缓冲中的信息,其关键是建立一个合适的用户兴趣模型和构造合适的兴趣挖掘算法。用户的兴趣是一个相对模糊的概念,简单兴趣模型通过(词条,权重)来刻画兴趣,但是它的表示粒度太小,不能贴切地描述用户的兴趣。文中在充分分析WWW缓冲模型的基础上提出了基于粗糙集的用户模糊兴趣概念。利用该方法可以对WWW缓冲中的网页文档和文档集合进行统一建模,这为利用用户历史兴趣信息和进行兴趣匹配提供了便利。The popular WWW pages are stored in users＇ places. By this WWW Cache technology, the browsers can speed up fetching these pages. The information in the WWW Cache shows the users＇ recent interest, which can be widely used, for example, to customize the WWW pages, filter the information, pre-fetch the information and so on. How to use the information in the WWW Cache effectively lies in how to build an adaptive user interest model and how to construct an adaptive algorithm for interest mining. The interest is a fuzzy concept, but the granularity is too little in simple interest model to describe users＇ interest appropriately. Based on analyzing the WWW Cache model, a rough set-based describing method for users＇ fuzzy interest was brought forward. By this method, the web page and the set of web pages in the WWW cache can be modeled conformably, by which the history interest and matching the interest can be easily used.

关 键 词：WWW缓冲 兴趣模型 模糊集 粗糙集 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]