Construction of Learner Profiles and Precision Resource Recommendation Strategies for Learners Driven by Academic Credit Bank Label Management System

As an emerging educational technology, the academic credit bank offers learners a flexible learning path by certifying, accumulating, and transforming various learning achievements. It quantifies, visualizes, and makes these achievements comparable through standardized labels, supporting data governance and lifelong learning. With the diversity of learning resources growing, learners face numerous choices. To address this, the Academic Credit Bank's data label management system analyzes learners' history, performance, and preferences. It creates personalized profiles and designs recommendation algorithms to offer tailored resource services. Taking the Shanghai Lifelong Education Academic Credit Bank (SHCB) as an example, this study constructed profiles and designed algorithms through system analysis, empirical research, case analysis, and technology implementation, verifying their effectiveness in practice. SHCB's label management platform comprises data, label, and application layers, generating various labels via an automated algorithm and multidimensional annotation. The profile framework based on these labels accurately describes learners' characteristics, preferences, and growth, providing personalized resources and path planning. SHCB has also developed recommendation algorithms that consider factors like gender, age, background, and preferences. The results show that learner profiles accurately depict characteristics and learning modes, promoting personalized education, precise resource recommendations, and enhanced learning effects. The data-driven recommendation algorithm meets learners' personal needs, improving satisfaction and reducing information overload.