Student Daily Life Management System Based On Big Data Design And Implementation

At present,the research on big data has become a hot spot.All industries rely on big data and cloud computing related technologies to provide reliable data basis for the development of various industries.However,the current analysis of behavioral data for students is relatively small and inefficient.The focus of this paper is based on cloud computing,using the daily behavior data of students,to develop and design a student life manage ment system based on big data.The system can analyze and judge the daily behavior data of students during school,provide reliable data support for the school's management work,and promote students' development in many aspects.Clustering algorithm is the key to data analysis.This paper proposes a parallel K-Means clustering algorithm based on cloud computing platform environment by using traditional clustering algorithm and paralle l framework under cloud platform.The algorithm parallelizes the cluster center selection,data sample and cluster center distance calculation and data object clustering through the Map/Reduce parallel framework,and improves the paralle lization of the traditional K-Means clustering algorithm.More intelligent,efficient and so on.Improve the efficiency of the algorithm and the ability to analyze and judge the various data of students' daily life.The system includes three parts: data storage management,server side and client side,which form the overall architecture of the system.The distributed storage and processing of data has been completed,and the deep mining and analysis of various types of data of students has been realized.The system has many functions such as student behavior collection,analysis,query and early warning,which helps schools to analyze,judge and alert students' behaviors and strengthen students' effective management.After testing and application,it shows that there are still some problems in the system.As the amount of data continues to increase,the accuracy and efficiency of data acquisition and preprocessing have yet to be further improved.Secondly,the behavioral early warning mechanism still depends on the threshold setting.How to accurately predict the automatic warning threshold also needs further research.In the future work,in the process of education and teaching,the continuous analysis and summary of student behavior,optimize the student's daily life data analysis algorithm to improve the performance of the system,and provide accurate data support for the students' learning and life management.It also provides guidance for students' physical and mental health during their school days.