数据管理技术的新格局  

New Landscape of Data Management Technologies

作　　者：覃雄派[1,2,3] 王会举[1,2,3] 李芙蓉[1,2,3] 李翠平[1,2,3] 陈红[1,2,3] 周烜[1,2,3] 杜小勇[1,2,3] 王珊[1,2,3] 

机构地区：[1]教育部数据工程与知识工程重点实验室(中国人民大学),北京100872 [2]萨师烜大数据管理与分析研究中心(中澳),北京100872 [3]中国人民大学信息学院,北京100872

出　　处：《软件学报》2013年第2期175-197,共23页Journal of Software

基　　金：国家自然科学基金(61070054;60873017;61170013);"核高基"国家科技重大专项(2010ZX01042-001-002;2010ZX01042-002-002-03);EMC中国研究院"EMC全球CTO办公室"资金

摘　　要：数据获取技术的革命性进步、存储器价格的显著下降以及人们希望从数据中获得知识的客观需要等,催生了大数据.数据管理技术迎来了大数据时代.关系数据库技术经历了20世纪70年代以来40年的发展,目前遇到了系统扩展性不足、支持数据类型单一等困难.近年来,noSQL技术异军突起,对多种类型的数据进行有效的管理、处理和分析;通过并行处理技术获得良好的系统性能;并以其高度的扩展性,满足不断增长的数据量的处理要求.试图沿着数据库技术进步的历史脉络,从应用维度(操作型与分析型应用)入手,为读者展开当今数据管理技术的新格局,讨论具有挑战性的重要问题,并介绍作者自己的研究工作.The revolutionary progress of data collecting techniques, dramatic decrease of the price of storage devices, as well as the desirability of people to extract information from the data have given birth to the so-called big data and data management technologies usher in the age of big data. RDBMS （relational database management system） undergoes a development of 40 years since the 1970s and now encounters some dift3culties such as limited system scalability and limited data variety support. In recent years, noSQL technologies has risen suddenly as a new force. The technologies can manage, process, and analyze various types of data, achieve rather high performance with the help of parallel computing, can handle even bigger volume of data with the nice property of highly scalability. The paper follows the path of database technology progress and unfolds the new landscape of data management technologies from the angle ofapplications （operational as well as analytic applications）. The paper also identifies some chanllenging and important issues that deserve further investigation, with the authors＇ recent research work introduced at the end.

关 键 词：关系数据库 NOSQL 大数据 操作型 分析型 新格局 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]