| 本文已被：浏览 10930次 下载 20693次 |
码上扫一扫！ |
|
|
| 数据质量和数据清洗研究综述 |
|
郭志懋1,2, 周傲英1,2
|
|
1.复旦大学,智能信息处理开放实验室,上海,200433;2.复旦大学,计算机科学与工程系,上海,200433
|
|
| 摘要: |
| 对数据质量,尤其是数据清洗的研究进行了综述.首先说明数据质量的重要性和衡量指标,定义了数据清洗问题.然后对数据清洗问题进行分类,并分析了解决这些问题的途径.最后说明数据清洗研究与其他技术的结合情况,分析了几种数据清洗框架.最后对将来数据清洗领域的研究问题作了展望. |
| 关键词: 数据质量 数据清洗 数据集成 相似重复记录 数据清洗框架 |
| DOI： |
| 分类号: |
| 基金项目:国家自然科学基金资助项目(60003016);霍英东教育基金青年教师基金资助项目;教育部跨世纪优秀人才培养计划资助项目 |
|
| Research on Data Quality and Data Cleaning:a Survey |
|
GUO Zhi-mao,ZHOU Ao-ying
|
| Abstract: |
| Data quality, especially data cleaning, is surveyed in this paper. The importance of data quality, and its measurement metrics are described. The data cleaning problems are defined and classified. The approaches to solving data quality problems are detailed. How to combine the techniques in other research areas with data cleaning is overviewed, and several data cleaning frameworks proposed previously by others are introduced. The future research topics related to data cleaning problems are also discussed. |
| Key words: data quality data cleaning data integration duplicate record data cleaning framework |
