Research on Adaptive Teaching Strategy of Smart Aesthetic Education Teaching Platform Based on Reinforcement Learning

Existing smart aesthetic education platforms organize resources in terms of courses with coarse granularity, and teachers need to spend a lot of time to find teaching resources. This paper proposes a user-centered design framework for the smart aesthetic education teaching platform in response to the needs of aesthetic education. Connecting the DDQN recommendation model with knowledge representation learning through feature combination sharing unit, the KERL4Rec model is proposed for learning resource recommendation. The application effect of the smart aesthetic education teaching platform based on reinforcement learning is evaluated and analyzed from three dimensions, namely, model performance, feasibility and practical application effect. The results show that the accuracy of KERL4Rec model on MOOCCube dataset is 3.41% higher than the best performing other models, and the recall is 3.49% higher. The percentage of user satisfaction in practicality, applicability, and accuracy evaluations that received 5 points were 71.25%, 82.00%, and 84.75%, respectively. Teachers’ performance of low and middle level students was significantly improved after adopting the results of resource recommendation.