多信息源下本体自动抽取的实现  

Implementation of automatic ontology extraction based on multiple information sources

作　　者：刘勇军[1] 聂规划[1] 

机构地区：[1]武汉理工大学信息管理与信息系统系,武汉430070

出　　处：《计算机应用研究》2007年第11期183-184,187,共3页Application Research of Computers

基　　金：国家自然科学基金资助项目(70572079)

摘　　要：以关系型数据库、XML文件、HTML文件、一般文档为信息源,运用不同的方法分别将多信息源映射为概念图,并按照拟定的概念逻辑结构进行统一存储,最后运用抽取算法实现本体的自动抽取。Multiple information sources, for example, relational database,XML file, HTML file and document, were mapped as concept map respectively. Subsequently, they were executed unified storage according to the logical structure of concepts constucted beforehand. Finally, extraction algorithm was applied to automatically extracting ontology.

关 键 词：本体抽取 语义网 本体映射 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]