论文部分内容阅读
大数据分析中如何有效安排并行任务使得大数据处理更高效十分关键。尽管已开展了对不同类型数据的处理技术研究,但是尚未对并行查询的效率进行深入的优化。特别是针对信息分散较广的在线用户端信息分析难度更大。本文提出一种在线用户端算法,通过在线用户端输入的数据进行后台挖掘。该算法通过如K-最近邻居算法等机器学习算法验证其并行效率有明显提升。
How to efficiently schedule big data in big data analytics makes big data processing more efficient. Although research has been conducted on the processing techniques for different types of data, the efficiency of parallel queries has not been further optimized. Especially for the information dispersed widely online client information analysis more difficult. This paper presents an online client-side algorithm that uses the data entered by the online client for background mining. The algorithm improves the parallel efficiency through machine learning algorithms such as K-nearest neighbor algorithm.