<p>In music education, traditional piano teaching methods often fail to meet students’ individualized learning needs, especially in distance teaching, where the interaction between students and teachers is restricted. The emergence of digital network technology has provided new ideas and methods for solving this problem. The research is based on a digital network platform. It uses flexible sensors to monitor in real time the finger strength, position and posture of students during piano playing, and utilizes speech recognition technology to convert students’ playing sounds into text for analysis. Based on the collected data, the system combines big data analysis and artificial intelligence algorithms to generate personalized learning paths for students and provide targeted guidance and feedback. The experimental part verified the effectiveness of the system by simulating the teaching environment. The experimental results show that the system can accurately record and analyze students’ playing skills, and generate appropriate personalized learning paths based on students’ individual needs. After using this system for learning, students’ playing skills and learning outcomes have significantly improved. The application of digital network technology not only enhances the efficiency of data processing but also provides students with a more convenient and personalized learning experience. This study successfully designed and implemented a remote personalized piano learning path by integrating digital network technology, flexible sensors and speech recognition technology. The system can provide students with real-time feedback and personalized learning suggestions, significantly improving the effect and efficiency of piano learning.</p>