分析了实例多重继承和实例属性层次关系对实例相似性的影响,针对原有的实例语义相似度计算方法的不足,提出了一种语义相似度计算方法SSCM,该方法综合考虑了实例多重继承关系和属性及属性值的层次关系,并利用继承关系的树状结构特点对计算过程进行了优化。实验表明,该方法在本体知识库的多种组成情况下,均能有效提高语义相似度计算的准确率。在实例多重继承关系相对复杂的情况下,准确率提高更加明显。
The effects of multi-inheritance of entities and hierarchical structure of the properties on semantic similarity were analyzed. Aiming at the problems in the traditional semantic similarity calculation methods, a scheme called SSCM was presented. The method took multi-inheritance of entities, hierarchical structure of the properties and property values into consideration, and then optimized the process of calculating the semantic similarity by using the tree structure of inheritance relationship. The experimental results show that the scheme can calculate semantic similarity more precisely in several cases, and the more multi-inheritance of entities exist in the knowledge base, the more increase of precision.