Author(s)

Xinxin Jia ^1,2, Xiaofeng Li ^1,2, Lei Kou ^1,2, Jingya Wen ^1,2, Yongjie Ma ^1,2, Huibin Yu ^1,2

Affiliation(s)

¹ Institute of Oceanographic Instrumentation, Qilu University of Technology (Shandong Academy of Sciences), Qingdao, Shandong, China
² State Key Laboratory of Physical Oceanography, Qingdao, 250353, Shandong, China

Corresponding Author

Huibin Yu

ABSTRACT

The Equations of Mathematical Physics course frequently engenders student anxiety and diminished motivation due to its highly abstract content and complex solution structures. Traditional teaching methods—characterized by knowledge spoon-feeding, delayed feedback, and disconnection from practical applications—further constrain learning efficacy. To address these challenges, this study implemented the Intelligent Tutoring System (ITS) "Xuetang-Cloud" as an intervention tool. The system constructs a structured knowledge graph for precise learning diagnostics and dynamically generates adaptive learning pathways based on real-time student performance data. Through continuous progress tracking and management, it enables dynamic personalized instruction. Empirical results demonstrate that the ITS's personalized incentive mechanisms—including real-time progress visualization and targeted resource recommendations—significantly enhance student motivation and self-directed learning. Research has shown that intelligent transportation system interventions that address learning anxiety in a timely manner can enhance students' confidence; Through case studies of embedded engineering, we aim to bridge the gap between theoretical application and ultimately achieve a synergistic improvement in students' knowledge internalization efficiency and STEM literacy.

KEYWORDS

Equations of Mathematical Physics, Intelligent Tutoring System, Learning Motivation, Educational Reform

CITE THIS PAPER

Xinxin Jia, Xiaofeng Li, Lei Kou, Jingya Wen, Yongjie Ma, Huibin Yu, The Impact of AI-Based Intelligent Assistance Systems on Student Learning: A Case Study of the Equations of Mathematical Physics Course. Curriculum and Teaching Methodology (2025) Vol. 8: 157-162. DOI: http://dx.doi.org/10.23977/curtm.2025.080522.

REFERENCES

[1] Shapiro J A. An algebra subsystem for diagnosing students' input in a physics tutoring system[J]. International Journal of Artificial Intelligence in Education, 2005, 15(3): 205-228.
[2] Liu X. Application and Challenges of Artificial Intelligence in Education: Current Status, Issues, and Future Directions[J]. International Journal of Social Science and Education Research, 2025, 8(6): 150-159.
[3] Song X. Physical education teaching mode assisted by artificial intelligence assistant under the guidance of high-order complex network[J]. Scientific Reports, 2024, 14(1): 4104.
[4] Xavier C, Rodrigues L, Costa N, et al. Empowering Instructors With AI: Evaluating the Impact of an AI-Driven Feedback Tool in Learning Analytics[J]. IEEE Transactions on Learning Technologies, 2025.
[5] Wang H, Wang C, Chen Z, et al. Impact of AI-agent-supported collaborative learning on the learning outcomes of University programming courses[J]. Education and Information Technologies, 2025: 1-33.
[6] Ley T, Tammets K, Pishtari G, et al. Towards a partnership of teachers and intelligent learning technology: A systematic literature review of model‐based learning analytics[J]. Journal of Computer Assisted Learning, 2023, 39(5): 1397-1417. 

Sponsors, Associates, and Links

---

• Advances in Educational Technology and Psychology
  
  
• Transactions on Comparative Education
  
  
• Applied & Educational Psychology
  
  
• Advances in Vocational and Technical Education
  
  
• Adult and Higher Education