Design And Implementation Of Learning Early Warning System Based On Teaching Data Analysis

With the rapid development of Internet technology,online learning has gradually integrated into people's daily life by virtue of the advantages that can be learned at anytime and anywhere.It will provide a convenient and quick way of learning for the construction of the whole people learning and lifelong learning society.In the background of the development of Internet plus education,online learning has been more and more university identity.However,due to the dual nature of online learning,it also brings a series of negative effects.For example,the use of online learning to distract the attention of some learners,resulting in the quality of learning is not guaranteed,the learners' behavior is difficult to control,so the teachers can not accurately understand the situation of the students,can not make accurate learning programs,teaching evaluation is not objective.In order to solve these problems effectively,learning warning emerges as the times require.Building a learning early warning system based on teaching data analysis is an important key to online teaching.The purpose of this paper is to make effective analysis and data mining of the teaching data in order to achieve early warning learners' academic performance and improve the students' learning quality and efficiency.With the help of data mining methods and tools,this paper takes the mass student learning log produced by the network teaching platform of Shandong Normal University as the research object,carries out the data preprocessing and processing,and designs the optimal learning early warning model.The educational decision-makers can make a personalized teaching plan according to the students' situation.In view of the data mining needs of different teachers,a learning early warning platform is designed to accurately predict students' learning performance,to interfere with students' learning behavior,to improve learning efficiency,to optimize the purpose of individualized learning in educational decision-making,and to make learners' learning behavior more reasonable and effective.The main innovation points of this paper are as follows:1.Technical aspects: Unlike traditional education,which uses a single questionnaire to analyze the questionnaires,this study makes full use of the advantages of professional technology,through various data mining methods for data processing and analysis,and enhances academic rigor.2.Model design: A learning early-warning model was established that canpreprocess the data and use correlation analysis to screen out the key factors affecting students' academic performance.Utilize the log generated by students' online learning activities to predict students' offline learning performance,combine online and offline,provide strong support for teachers to make scientific decisions,help optimize the teaching process,and promote students' effective learning.3.Platform design: adopting the MVC model and designing an early warning platform for students' academic performance.Teachers and students can log in to the platform,import students' grades through a registered account,and provide students with an early warning through a visual interface to help teachers accurately.Master the learner's progress and help students complete their studies smoothly.Using data analysis technology to discover the information contained in educational big data,and discover the influencing factors that truly affect students' learning performance,so that teachers can objectively analyze students' learning ability and learning behavior,so as to achieve intervention in student learning behavior,optimize teacher decision-making,and improve teaching.The purpose of the goal is to achieve true instruction in accordance with your aptitude.