With the rapid development of artificial intelligence and robotics technology, educational robots are increasingly widely used in the fields of personalized teaching and intelligent interaction. As an important factor affecting the effect of human-robot interaction, how to accurately identify and effectively utilize user psychological preference has become the key to improve the interaction experience of educational robots. In this paper, we systematically study the recognition method of user psychological preference in educational robots, focusing on the psychological preference recognition algorithm based on multimodal data acquisition and deep learning model, combining feature extraction and model optimization strategies to achieve a high recognition accuracy. On this basis, an interaction optimization algorithm based on the results of psychological preference recognition is proposed, which enhances the user's sense of participation and learning effect by dynamically adjusting the teaching content and interaction mode. Experimental validation shows that the algorithm significantly improves the quality of interaction between the educational robot and the user and the ability of personalized adaptation. The article summarizes the research results and looks forward to the future development trend of psychological preference recognition and interaction optimization, providing theoretical support and technical reference for the design and application of intelligent educational robots.
Jia et al. (Sun,) studied this question.