基于知识库分割的多知识库整合方法  

Integration of multiple knowledge bases based on knowledge blocks

作　　者：杨龙[1,2] 张公让[1,2] 王力[1,2] 魏炎炎[1,2] 

机构地区：[1]合肥工业大学管理学院,合肥230009 [2]合肥工业大学过程优化与智能决策教育部重点实验室,合肥230009

出　　处：《计算机工程与应用》2014年第7期129-132,229,共5页Computer Engineering and Applications

基　　金：国家"863"云制造主题项目(No.2011AA040501);国家自然科学基金(No.70871033);安徽省教育厅自然科学重点项目(No.KJ2011A006)

摘　　要：知识库是集团企业云制造平台中知识服务的重要基础,知识库的质量直接决定着知识服务的质量。目前单一分散的知识库不能提供统一的知识资源全局视图,不利于知识资源的共享。多知识库整合技术已经成为该领域的研究热点之一。提出一种基于知识库分割的多知识库整合方法,采用基于蚁群聚类的分割策略,将知识库有效划分为知识块集。在知识块间利用语义概念映射生成知识块间映射图,从而实现多知识库整合。通过对算法的时间复杂度进行分析,表明该方法在时间复杂度方面要优于基于最小概念集的多知识库整合方法;实验结果也表明该方法在运行性能方面明显优于已有的方法。Knowledge base is an important foundation of knowledge services in the Group’s Enterprise Cloud manufac-turing platform.As a result,the quality of the knowledge base directly determines the quality of knowledge services.Sin-gle dispersed knowledge base cannot provide a unified global view of the knowledge resources,which is not conducive to the sharing of knowledge resources.Multiple knowledge bases integration technology has become one of the focuses.An efficient integration of multiple knowledge bases method based on knowledge blocks is proposed,which divides a knowl-edge base into a set of blocks through an improved ant colony clustering algorithm.Then,the mapping between blocks is based on computing semantic similarity of candidate mapping entity pairs are selected from the block mapping result. Through the algorithm’s time complexity analysis,the time complexity is better than the method of integration based on the minimum set of concepts knowledge base.The results also show that the operating performance of the method is obviously superior to existing methods.

关 键 词：云制造 多知识库整合 蚁群聚类 语义概念映射 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]