对分布式数据挖掘解决方案的思考  

Reflection on Solution of Distributed Data Mining

作　　者：周蕾[1] 

机构地区：[1]江苏联合职业技术学院泰州机电分院,江苏泰州225300

出　　处：《常州信息职业技术学院学报》2016年第5期22-24,共3页Journal of Changzhou College of Information Technology

摘　　要：传统数据挖掘解决方案计算能力有限,对数据挖掘算法迭代复杂性,难以发现数据中存在的关系和规则,不能根据现有数据预测未来发展趋势。分布式数据挖掘工具的出现则是解决非关系型数据库或者非结构化模式的数据库系统最佳选择。通过对传统数据挖掘解决方案和分布式数据挖掘解决方案的综述和功能分析,对数据挖掘解决方案进行了思考:注重数据挖掘平台,避免误入大数据的陷阱,同时分析大数据出现的新问题,希望借此引起人们的重视。The traditional data mining is limited in computing power, such as the data mining algorithm iteration complexity, the difficulty in finding relationship between data and rules, and the disability in predicting the future development trend based on existing data. Distr-0uted data rnk-g tools appear to be the best choice for the database system which can solve the non relational database or the non structural model. The review and functional analysis on the traditional data mining solution and distributed data mining lead to the use of data mining solution using, the focus on data mining platform, and avoiding straying into the trap of big data, and facing new problems emerged in large data, which is to draw people＇s attention.

关 键 词：数据挖掘 大数据 平台 系统工具 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]