摘要
在资源描述框架(RDF)图的语义相似性度量过程中,结构相似性和语义相似性计算不精确。针对该问题,提出结构语义(SAS)方法。结合改进的基于网络距离模型的语义距离公式、基于信息量模型的权重度量机制,计算概念节点的语义相似度,完善RDF图语义相似度算法,分析结构、深度和密度对RDF图语义相似性度量的影响。设计并实现原型系统,实验结果表明,该方法可有效保证RDF图的语义相似度与实际相符。
Aiming at the inaccuracy of structural similarity and semantic similarity in the process of measuring semantic similarity between objects represented by Resource Description Framework（RDF） graph, a method named Structure and Semantics（SAS） is proposed, which calculates semantic similarity of concept nodes by combining improved semantic distance formulas based on the network model and weight measure mechanism based on the information quantity model, and perfects the algorithm of semantic similarity of RDF graphs. SAS reflects the influence of structure, depth, density in semantic similarity of RDF graphs. Prototype system is designed and realized. Results show that the method can effectively guarantee the RDF graph is consistent with the reality.
出处
《计算机工程》
CAS
CSCD
2013年第3期223-228,235,共7页
Computer Engineering
基金
国家自然科学基金资助项目"关系数据库对象级别信息检索关键技术研究"(61073057)
中央高校基本科研业务费专项基金资助项目(2011JC007)
关键词
语义匹配
语义距离
权重度量
结构相似性
语义相似度
概念节点
资源描述框架图
semantic match
semantic distance
weight measure
structure similarity
semantic similarity
concept nodes
Resource Description Framework（RDF） graph
