Real Time Adaptive Teaching Digital Human System Based on Large Language Model

Abstract

With the diversification and personalization of educational needs, the traditional teaching model is facing many challenges, especially in meeting students' personalized learning needs and providing real-time feedback. This study proposes a real-time adaptive teaching digital human system based on a large language model, which aims to improve the quality of education and student engagement through intelligent technology. The system obtains students' learning status in real time through a variety of data acquisition devices (such as learning behavior tracking, question-answering records, and speech recognition) and uses the large language model to generate personalized teaching content and feedback. The system calculates a comprehensive learning status score by evaluating students' learning progress, answer accuracy, participation, and learning time, thereby dynamically adjusting the teaching content and learning path. Experimental results show that with the system, students' knowledge mastery rate increases by 15%, understanding depth by 17%, and learning interest by 20%. The system's response time is reduced from 5 seconds (in traditional systems) to 1.5 seconds, and its processing capacity is increased by 2.5 times, supporting more concurrent users. The successful implementation of the system provides a new solution for personalized education and has broad application prospects, especially in online education and distance learning.