Design of MOOC Response System Based on Intelligent Algorithms

With the rapid development of the internet era and online education, large-scale open online course MOOC has successfully achieved a high-end knowledge interconnection and exchange mode. By adopting diversified real-time feedback technology to achieve classroom interaction, the efficiency of classroom teaching has been greatly improved. In the entire response system design, how to optimize the response efficiency of online course systems is a key issue that needs to be studied in online education. This article studies the use of intelligent algorithm technology to design MOOC response systems, aiming to use digital technology to improve classroom efficiency. Through actual research and comparative analysis, this article uses convolutional neural network algorithm based on LSTM (long short term memory), combined with actual research data analysis, and discusses the following conclusions based on the chart results: In the context of the increasing development speed of online education MOOC courses, the MOOC response system designed using convolutional neural networks has a response rate that is about 10% faster than that without convolutional neural network design after model optimization training. At the same time, the average time spent by students mastering knowledge in the same science subjects is about 1 h less on the convolutional neural network response system, and the average time spent understanding and memorizing knowledge in the same humanities subjects is about 10 min less. This indicates that the MOOC response system based on convolutional neural network algorithm has significantly improved its response rate after model optimization training, and its application effect on science subjects has significantly increased.