摘要
描述网络教学的数据仓库中包含了从各种数据源导入的大量数据,数据的质量问题会直接影响教学评价的效果。针对学生重复信息的处理,文中提出了基于数据类型进行分词的策略,结合编辑距离算法可有效检测出重复的学生基本信息,实验结果表明该方法能有效提高算法的执行效率及检测精度。
Data warehouse for network teaching includes a variety of data which are from different data sources,Data quality problem will di- rectly influence the effect of teaching evaluation.Aiming at the processing of students duplicate information,an segment strategy based on data type is proposed.The similarity computation algorithm of edit distance is presented：The experiment results indicate that this method can detect approximately duplicated records effectually,the algorithm running efficiency and detect precision can be improved.
出处
《网络与信息》
2011年第8期40-41,共2页
Network & Information
基金
辽宁省十一五规划项目
课题编号:JG 10DB192
关键词
相似重复记录
分词
编辑距离算法
Approximately duplicated records
Segment
algorithm of edit distance
