Reform and Practical Study of Teaching Mode in Physical Chemistry Empowered by Artificial Intelligence

DOI: https://doi.org/10.62517/jnse.202517306

Author(s)

Liu Huijin

Affiliation(s)

School of Chemistry and Chemical Engineering, Yulin University, Shaanxi, Yulin, China

Abstract

In the context of "New Engineering" construction and the digital transformation of education, this study focuses on the theoretical framework and practical pathways for reforming physical chemistry teaching modes empowered by artificial intelligence (AI). It aims to overcome bottlenecks in traditional teaching, such as insufficient personalized guidance and a lack of data-driven decision-making. The research integrates educational technology theories, learning science principles, and intelligent algorithm tools to construct a three-dimensional empowerment model of "AI + Physical Chemistry Teaching," encompassing intelligent teaching environment development, adaptive learning support, and teaching process optimization mechanisms. By analyzing relevant studies domestically and internationally, and considering the knowledge system characteristics of physical chemistry, a reform plan was designed, including intelligent learning diagnostics, dynamic resource allocation, virtual simulation experiments, intelligent Q&A systems, and formative assessment, implemented across multiple universities in comparative experiments. The findings reveal that AI-integrated teaching modes significantly enhance students' knowledge mastery, problem-solving skills, and learning autonomy, particularly in complex topics such as molecular simulation experiments and thermodynamic data modeling, with AI interventions improving learning efficiency by 32%. Additionally, the study identifies key factors for the deep integration of AI technology with course content, including accuracy in knowledge graph construction, design of human-machine collaborative teaching strategies, and alignment with teachers' digital literacy. The conclusions provide a replicable theoretical model and practical paradigm for intelligent teaching reform in foundational courses in higher education.

Keywords

Artificial Intelligence; Physical Chemistry Course; Teaching Mode Reform; Deep Learning; Educational Technology Empowerment

References

[1] Course Team of Physical Chemistry, Central South University for Nationalities. "Teaching Reform Practice of AI + Knowledge Graph in 'Physical Chemistry' Course" [J]. Chinese University Teaching, 2025, (5): 43-48. [2] Course Group of Physical Chemistry, Zhejiang University of Technology. "Construction and Teaching Application of Knowledge Graph in Physical Chemistry Empowered by Artificial Intelligence" [J]. Research in Higher Engineering Education, 2023, (6): 189-195. [3] Liu, Z. "Symbolic Regression Machine Learning for Simple Catalytic Descriptor Discovery" [J]. Journal of Physical Chemistry, 2021, 37 (3): 2007055. DOI: 10.3866/PKU.WHXB202007055. [4] Higher Education Press. "Theoretical Simulation and Virtual Simulation Experiments for Chemical Engineering Majors" [M]. Beijing: Higher Education Press, 2023. [5] Li, H., Chen, Y., Liu, Z. "Research on a Deep Learning-Based Diagnostic Model for Physical Chemistry Learning" [J]. Computer Education, 2021, 168: 104213. [6] Wang, Y., Zhao, J., Sun, W. "Application of Virtual Simulation Technology in Physical Chemistry Laboratory Teaching" [J]. Research and Practice in Chemical Education, 2022, 23: 789-802. [7] Zhang, Y., Li, X., Wang, L. "Development of Physical Chemistry Teaching Resource Database Driven by Knowledge Graph" [J]. Journal of Educational Technology, 2020, 12 (3): 45-58. [8] Teaching Guidance Committee for Chemistry Majors, Ministry of Education. "White Paper on Teaching Reform of Physical Chemistry Course" (2024) [R]. Beijing: Higher Education Press, 2024. [9] Liu, H., Wang, M., Zhang, W. "Research on Human-Machine Collaborative Decision-Making Model in Physical Chemistry Classroom Teaching" [J]. Research in Educational Technology, 2024, 45 (8): 105-112. [10] Chen, T., Yang, L., Zhou, M. "Construction of Formative Evaluation System for Physical Chemistry Based on Learning Analytics" [J]. China Educational Technology, 2023, 421: 78-85. [11] Expert Group on National Education Digital Strategy Action. "Ethical Norms for AI Education Applications (Trial)" [S]. Beijing: Ministry of Education, 2024. [12] Li, N., Wang, G., Liu, Y. "Research on Data Security and Privacy Protection in Intelligent Teaching Systems" [J]. China Distance Education, 2024, 40 (6): 62-68.