摘要
数据挖掘已成为情报学的研究热点,而传统的数据挖掘过程是在数据仓库的基础上,面向结构化的数据进行分析,这在很大程度上限制了数据挖掘的作用范围和效果。在充分分析数据挖掘和领域本体等相关理论后,提出了一个面向领域本体,应用语义相似度匹配的数据挖掘模型。该模型在理论上解决了用户的目标发现和挖掘对象选择的问题,同时也在数据挖掘算法上引入了本体概念,使得系统能快速识别用户需求,高效的选择相应算法,在很大程度上提高了数据挖掘处理异构、分布式数据的能力。
Data mining has become the focus of research in information science,while the traditional data mining process is based on the data warehouse,facing structured data and analyzing,which largely limits the scope and effectiveness of data mining.In this paper,after the full analysis of data mining and other related theory such as domain ontology,it proposes a data mining model.The model solves the problem of the user＇s target discovery and the choice of the mining object in theory,while incorporates the concept of ontology in the data mining algorithms,making the system quickly identifies the user needs and selects the appropriate algorithm efficiently.It improves the capacity of the dealing with heterogeneous,distributed data.
出处
《情报科学》
CSSCI
北大核心
2011年第2期275-278,共4页
Information Science
基金
教育部人文社会科学重点研究基地重大项目(2009JJD870002)
教育部人文社会科学研究项目(2008JA870013)
关键词
领域本体
语义相似
数据挖掘
domain ontology
semantic similarity
data mining
