OWL中的概念相似度计算和应用  

Concept Similarity Calculation and Application in OWL

作　　者：智东杰[1] 智慧来[2] 刘宗田[2] 

机构地区：[1]河南理工大学计算机科学与技术学院,焦作454150 [2]上海大学计算机工程与科学学院,上海200072

出　　处：《计算机科学》2008年第12期200-202,共3页Computer Science

基　　金：国家自然科学基金(项目批准号60575035)

摘　　要：为了提高信息检索的查全率和查准率,经常要处理相似的概念,因此计算概念间的相似度是必要的。OWL中的概念有如下两个特点:概念按照继承关系形成了一个层次结构的分类树,子概念继承父概念的属性;概念的属性由断言条件定义。概念相似度计算分为两步:首先,递归计算相同属性的数量;然后,根据相同属性的数量计算概念相似度。计算模型利用了OWL的较为完整的信息,计算结果与人为判断基本吻合。In order to improve the recall and precision, similar concepts are often processed during the information retrieval. With this regard, the possibility of evaluating concept similarity is acquiring an increasing relevance, since it allows the identification of different concepts that are semantically close. Concepts in owl have two features. Firstly, as son concepts inherit their father concepts＇ attributes, so all concepts form a hierarchical taxonomy tree. Secondly, concept＇s attributes are defined by asserted conditions including the ones inherit their father concept＇s. The computing model also has two parts. First part is using reeursive algorithm to compare concepts＇ attribute similarity. The second part is to calculate concept similarity by using the amount of same attributes.

关 键 词：本体 概念相似度 属性 深度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP311[自动化与计算机技术—计算机科学与技术]