Research on the Application of an AI-Tutor-Driven Human-Computer Collaborative Learning Model in Vocational College Website Front-End Teaching
Year: 2025
Type: conference-paper
Study design: Clinical Trial
Abstract: This paper addresses the common challenges faced by vocational college students in website front-end courses, such as weak foundational knowledge, fragmented understanding, and the disconnect between theory and practice, which leads to low learning efficiency. We propose an Artificial Intelligence (AI) Tutor-driven human-computer collaborative learning model that integrates knowledge graphs, reinforcement learning, and Transformer-based natural language processing. By constructing a structured front-end knowledge system and using reinforcement learning to dynamically optimize personalized learning paths, the model establishes a closed-loop learning mechanism characterized by “AI guidance, collaborative practice, and real-time feedback.” To validate the model's effectiveness, an eight-week controlled teaching experiment was conducted with computer application majors at a vocational college. The experimental group used the proposed model, while the control group followed a traditional online-offline blended approach. Results show that the experimental group significantly outperformed the control group in theoretical test scores, excellence rates for practical projects, and core task completion efficiency. Further analysis using a competency radar chart indicates more balanced and comprehensive development across core competencies for the experimental group. This study demonstrates the model's effectiveness in adapting to vocational students' cognitive characteristics and learning needs, offering a replicable solution for the intelligent reform of technical course teaching.
Authors: Dongxing Wang, Kunquan Ye, Meiman Li, Weixing Wang
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W7154331752
