Abstract: Concerning the problem that some results are easily leaked while the component testing ontology is retrieved using the existed calculation method of ontology semantic similarity, a similarity calculation method based on concept and attribute was proposed to improve the retrieval efficiency of component testing information. Firstly, the structure, hierarchy, the number of offspring nodes and ancestor nodes of concept were used to calculate the concept similarity. Then, the attribute similarity was calculated based on the concept similarity of the attributes and its data type similarity. Finally, the concept similarity and attribute similarity were combined to calculate the comprehensive ontology semantic similarity. The experimental results indicate that the similarity calculation method can be applied in component testing and other domains effectively.

Key words: ontology, component testing ontology, semantic similarity, concept similarity, attribute similarity

摘要： 为了提高构件测试信息的检索效率，针对现有本体语义相似度计算方法作用于构件测试本体时容易出现漏检的问题，提出一种结合本体概念和属性的综合语义相似度计算方法。该方法首先结合概念的结构、层次、子代节点个数和祖先节点个数等因素计算概念相似度；然后，结合属性的概念相似度和数据类型相似度计算属性相似度；最后，综合概念相似度和属性相似度计算本体的语义相似度。实验表明该方法可以有效应用于构件测试领域及其他领域的信息检索。

关键词: 本体, 构件测试本体, 语义相似度, 概念相似度, 属性相似度