Studies on the New Deep Learning Models-Based Higher Education System

The main goal of this study is to enhance the attractiveness of university classroom teaching and students’ learning efficiency. A prediction module is constructed through deep learning techniques using Gesture Recognition Algorithm (GRA) and Long Short-Term Memory (LSTM) network, thus shaping a novel human–computer interaction system. Deep learning techniques, the core of this study, provide the system with highly intelligent capabilities, especially in GRA, which successfully improves the gesture recognition accuracy of previous image segmentation and pattern matching methods. Specifically, the accuracies of the gestures “hold”, “pinch”, and “point” reached an impressive 98.66%, 99.52%, and 99.46%, respectively. In addition, the LSTM network model also performs well with a small amount of data, and its prediction accuracy can reach about 70% stably. This stability provides a reliable performance guarantee for the practical application of the system. The constructed human–computer interaction system is not only a technological innovation, but also a highly intelligent educational tool. The system effectively optimises the interactive teaching method between the teacher and the computer by more accurately interpreting the teacher’s gesture intentions and implementing the corresponding commands. It also inherently has the qualities of gamified teaching, which increases students’ interest and participation in the educational process, and at the same time has an important practical value in improving the teaching efficiency of general higher education.