A Design of Academic Diagnosis and Early Warning System Based on Big Data Mining Technology

In order to achieve effective academic situation analysis, based on big data mining technology, an academic situation diagnosis and early warning system containing six modules, namely, student information management, performance analysis module, attendance analysis module, class portrait construction, real-time monitoring of academic situation and system configuration, is designed. The progressive framework technology VUE is used to build the basic Web framework. Hive uses its distributed file system HDFS to store and manage massive academic data. MapReduce, a distributed computing framework, is used to process the data in parallel and then send the analysis results to the server. Through the ServLet interface, the system responds to requests and sends data to the front-end to generate academic diagnostic reports. This system plays an important and positive role in personalized teaching, scientific evaluation and the promotion of educational equity.