Research and application of intelligent learning path optimization based on LSTM-Transformer model

In the global wave of digital learning, how to optimize personalized learning paths and improve learning efficiency has become a key issue to be solved urgently in the field of education. Based on this, this study proposes a hypothesis: the intelligent learning path optimization strategy based on the LSTM-Transformer model can achieve accurate prediction and personalized optimization of learners' learning paths with the help of deep learning technology. In the research process, the LSTM model was used to capture the characteristics of the learner's learning behavior sequence, and the self-attention mechanism of the Transformer model was introduced to deepen the understanding of the learner's learning status. Experimental comparison shows that compared with the traditional learning path recommendation algorithm, the optimization strategy based on the LSTM-Transformer model has achieved remarkable results, with the learner's knowledge mastery rate greatly increased from 75% to 95%, the learning time shortened by about 25%, and the learning satisfaction also increased from 70% to 90%, which verifies the research hypothesis and fully proves that the LSTM-Transformer model has high application value in intelligent learning path optimization.