基于Ontology的文档过滤研究  

Research on Document Filtering Based on Ontology

作　　者：房艳焱[1] 余锦凤[1] 

机构地区：[1]北京大学信息管理系,北京100871

出　　处：《图书情报工作》2006年第1期76-79,共4页Library and Information Service

基　　金：本文系国家自然科学基金资助项目"数字图书馆自学习知识管理系统的研究与实现"(项目编号:70473002)研究成果之一

摘　　要：区分文档过滤、信息过滤和文本过滤并介绍文档过滤技术的研究现状;提出基于Ontology的文档过滤的设想,认为其优势在于灵活、共享性好、有利于进行个性化服务等;讨论基于Ontology的文档过滤的实施过程,包括构建准备、本体构建、本体调用,重点阐述公共本体、用户本体和文档本体的构建方法以及实施过程中涉及的技术体系;最后指出今后的努力方向。This paper introduces the document filtering and its cmrrent research status and makes a clear distinction among document filtering, text filtering and information filtering. Then it proposes a hypothesis of document filtering based on ontology and discusses its advantages such as flexibility, sharability, and the convenience for characteristic service. The application process, from establishing preparation to ontology establishment and ontology application, is extensively discussed in this hypothesis. A special focus is put on the design method and technology system of public ontology, user ontology and document ontology.

关 键 词：文档过滤 电子文档过滤 ONTOLOGY 本体构建 个性化服务 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]