Design And Implementation Of Online Education Recommendation System Based On Container Cloud

With the rapid development of the Internet,people ’s lives have undergone tremendous changes.Especially in the field of education,more and more people begin to learn online.However,with the explosive growth of learning resources on the Internet,it is difficult for people to find the information they want from the massive information.The online education recommendation system that provides users with personalized recommendations has emerged as the times require,which has greatly improved the learning efficiency of learners.Based on the background of chess online education platform,the thesis provides users with personalized recommendations for teaching videos.The main content of the thesis is to design and implement a recommendation system for chess teaching platform.Based on the chess teaching platform,a recommendation system including a variety of recommendation methods is designed.The main contents of this study are as follows :1)Design a recommendation system including offline recommendation,real-time recommendation,statistical recommendation and similar recommendation.In offline recommendation,the collaborative filtering recommendation algorithm based on ALS is periodically called,and the offline recommendation module is implemented by Spark core and Spark MLlib.In real-time recommendation,the model-based recommendation algorithm is adopted.The implementation of the real-time recommendation core algorithm uses the Spark Streaming component.The statistical recommendation is based on the statistical recommendation algorithm.2)Build offline warehouse,provide data source for the offline recommendation module,and provide the calculation results of statistical indicators for the statistical recommendation module.This can eliminate the need to read business data and perform the same logical data analysis each time in the statistical recommendation calculation process.At the same time,the data set cleaned by ETL is prepared for the offline recommendation,and the increase in the amount of data caused by the increase in the number of users in the later stage of the system and the good scalability of the system are taken into account.3)in order to realize the scalability of system resources and the reliability of the system,the Kubernetes container cloud platform is used as the deployment environment of the system.The construction of offline warehouse,the deployment of recommendation module and web system are carried out on the Kubernetes platform,and the separation of storage and calculation is realized by using PVC combined with PV.4)In order to provide users with a good way to interact,the thesis designs and implements a web system,using Angular JS as the front-end development framework and Spring series components as the back-end development framework.After rigorous testing,it is found that all the functions of the online education recommendation system have reached the expected standard,which proves its feasibility and practical application value.