作　　者： ; ; ;

机构地区： 吉林大学

出　　处： 《现代情报》 2012年第6期72-74,共3页

摘　　要： 数据挖掘技术可以帮助人们在海量的信息资源中提取隐含的、潜在的、有价值的信息,因此已经被引入到了处理爆炸式增长的档案信息资源中。而待挖掘的信息是否完整、规范直接关系到之后的挖掘质量。本文根据档案信息资源的现状以及档案数据的特性,在给出执行具体挖掘操作前的数据采集和数据预处理各个环节的概念描述的基础上,探讨各个环节的注意事项及具体实现方法。 Data mining technology can help people extract implicit,potential and valuable information from massive information resources,so it has been introduced to deal with the explosive growth of archival information resources.Whether the source data for mining is complete and standardized is directly related to the quality of mining.According to the situations,based on the concept description of all aspects of data collection and preparation,combining the status of archival information resources,as well as the characteristics of the data,this paper illustrates the points for attention and the specific method of each aspect before mining,aiming at ameliorating the quality of the information and the mining.This makes a good foundation for consequent research.

关 键 词： 数字档案馆 数据挖掘 数据采集 数据预处理

领　　域： [文化科学]