一种基于本体的个性化模式库建模方法  

A Modeling Method of User Profile Based on Ontology

作　　者：陈俊杰[1] 刘炜[1] 

机构地区：[1]太原理工大学计算机与软件学院,太原030024

出　　处：《计算机研究与发展》2007年第7期1151-1159,共9页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60472093);教育部科学技术研究重点项目(03020);山西省自然科学基金项目(20031038)

摘　　要：搜索引擎的"千人一面"为人们信息检索时带来了很大的烦恼,个性化模式库技术的引入解决了这个问题,使得搜索引擎能够很好地满足人们的个性化、智能化需求.提出一种基于本体的个性化模式库建模方法,通过树图和空间图相结合的方法来建模,在空间图中建立本体节点,并引入区间值模糊集理论,同时给出相关定义和公式,在对该方法进行理论分析的基础上,设计了一个实现算法.这种建模方法对改进传统树形建模的不足有一定益处,更利于建立、使用和完善用户个性化模式.理论分析证明,该算法具有正确性、有效性并且复杂性低的特点.The machine-made trait of search engines brings great trouble to people when they retrieve information. Therefore, the technology of user profile is introduced to solve the problem which makes search engine fit for people＇ demands of individuation and intelligence better. A modeling method of user profile based on ontology is advanced. And the innovation of this paper is to do modeling with a method of combining tree graphics and spatial graphics together, to set up ontology nodes in spatial graphics and to introduce the theory of interval valued fuzzy sets. In addition, the paper explains the method in theory, brings forward some correlative definitions and formulae, and designs an algorithm of founding and updating nodes based on ontology （LW-FUNO） . The modeling method is helpful in overcoming the deficiencies of traditional modeling methods and is in favor of user profile＇s foundation, use and perfection. Finally, a well-ordered implement is used to prove correctness of the algorithm strictly, and then, time complexity of the algorithm, which is T （n） = o （n^2）, is analyzed. It is proved theoretically that the algorithm has the traits of correctness, validity and low time complexity. It is considered that the work in this paper is a useful attempt at the research of user profile.

关 键 词：信息检索 搜索引擎 本体论 个性化模式库 空间图 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]