摘要
为了更好地从数据类型复杂、冗余空缺值多的海量图书数据中挖掘出切实有用的信息,就必须对数据源进行预处理。基于此目的,文章详细介绍了图书数据的预处理方法,并通过安徽省图书馆图书数据实例验证其有效性和可行性,从而为读者服务提供可靠保障。
In order to search for the most practical and useful information from the sea of complex, redundant and inadequate information resources, it is highly necessary to pre-process the data obtained. Starting from this goal, the article makes an introduction to the concrete methods of information pre-processing, and provides a reliable guarantee for the reader service in libraries through verifying the effectiveness and feasibility of the library data in Anhui.
出处
《大学图书情报学刊》
2008年第2期31-33,共3页
Journal of Academic Library and Information Science
关键词
数据预处理
数据挖掘
图书数据
关联规则
data preprocessing
data mining
book data
interrelation rules
