Use of Big Data Technology for Network Classroom Teaching Quality Management

Abstract

Quality management of network classroom teaching has always been an urgent problem to be solved. Big data technology handles massive amounts of data and provides new quality management methods and means for network classroom teaching. However, data integration and fusion is a complex task and existing methods may not be able to deal with data fragmentation effectively, because data is often distributed across different systems and platforms in the network teaching environment. Therefore, this research aimed to study the quality management of network classroom teaching based on big data technology. This study provided a framework diagram of teaching quality evaluation criteria and factors affecting the teaching quality in the big data environment, explained complex relationships and effects among the factors, and described teaching quality prediction problems. The dimensionality reduction method of Least Absolute Shrinkage and Selection Operator (LASSO) was used for comprehensive status data integration of factors affecting teaching quality. An unequal-interval grey Riccati-Bernoulli model was constructed to study the internal relationships between various variable factors and network classroom teaching quality. Then the execution process of the prediction model, detailed modeling steps and teaching quality management steps were provided. The experimental results verified that the constructed model was effective.