Research On Key Technologies Of College Entrance Examination Volunteer Data Analysis Based On Big Data

With the popularity of online college entrance voluntary system,a large number of voluntary data have been obtained by enrollment management departments.Due to the absence of efficiently analysis platform,the voluntary data are not used effectively.The emergence of big data solved this problem.A deep study on Hadoop distribute system is conducted in this paper,and a series of research work has been carried out around the data analysis of college entrance examination.The main content and innovation in this paper are as follows.(1)The architecture of the distributed processing platform and the principle is studied,and the Hadoop distributed processing platform is expounded.The thinking of Hadoop File System and Map Reduce computing model are analyzed.(2)A kind of distributed data processing system model is built,which include core control node,data preprocessing node,task node,computing nodes and monitor node.On the basis of big data process,the model is combined with the characteristics of voluntary data to meet the needs of the college entrance examination data analysis.(3)A kind of task scheduling mechanism based on genetic algorithm is proposed,which reduce time consumption and cost.Compared with FIFO strategy on Hadoop platform,the mechanism can reduce the time consumption and cost effectively.(4)A kind of voluntary recommendation algorithm based on collaborative filtering algorithm is proposed,which can provide voluntary recommendation correctly.The efficiency of the algorithm is proved under different number of nodes.