基于人工智能的医学生个性化指导模式——以“智慧阅读助手”为例
An AI-Based Personalized Guidance Model for Medical Students—A Case Study of the “Smart Reading Assistant”
DOI: 10.12677/ae.2026.16112454, PDF,    科研立项经费支持
作者: 李国琳, 张 琪, 高 昕:长治医学院第一临床学院,山西 长治;太原市中心医院呼吸与危重症医学科,山西 太原;乔可宏*:太原市中心医院呼吸与危重症医学科,山西 太原
关键词: 人工智能;医学教育;个性化学习;认知诊断;Artificial Intelligence; Medical Education; Personalized Learning; Cognitive Diagnosis
摘要: 传统医学教学多以教师讲授为中心,学生的主体性容易被忽视。如何借助人工智能精准识别个体差异,并提供适切的指导支持,已成为教学改革中的重要命题。本文系统介绍了一款自主研发的人工智能医学学习平台。该平台分为教师端与学生端:教师端支持学习资料的智能管理与教学反馈分析,学生端通过智能对话引擎实现个性化学习交互,并自动记录学习者的提问轨迹。平台的核心价值在于,通过对同一知识点下不同学生提问角度、认知层次与表达风格的深度挖掘,揭示学习者在知识建构与掌握上的个体差异,为教师提供精准的教学诊断依据。在学情数据分析的基础上,平台进一步设计了“数据驱动的教学活动建议”模块与“教学策略库”,将诊断结果转化为可操作的教学行动方案,并以《诊断学》课程为例,展示教师如何依据学情报告设计与改进课堂教学。技术层面,平台采用基于BERT预训练模型微调的多标签文本分类方案,实现提问类型的自动识别,在医学教育提问数据集上取得了较好的分类性能,并通过决策阈值校准与低置信度回退机制保障分类可靠性。本文认为,学生在人工智能辅助环境下提出的问题,本质上是其内在认知过程的外化表征;人工智能平台的意义,正在于将这一过程系统化、可视化与可操作化,从而重构医学教育中的师生互动模式与教学决策逻辑。
Abstract: Traditional medical teaching model is often teacher-centered, which tends to neglect students’ agency. How to use artificial intelligence to accurately identify individual differences and provide appropriate guidance and support has become an important issue in teaching reform. This paper systematically introduces a self-developed AI-powered medical learning platform. The platform consists of a teacher portal and a student portal. The teacher portal supports intelligent management of learning materials and analysis of instructional feedback, while the student portal enables personalized learning interactions through an intelligent dialogue engine and automatically records learners’ question-asking trajectories. The core value of the platform lies in uncovering individual differences in learners’ knowledge construction and mastery by deeply mining the questioning perspectives, cognitive levels, and expression styles of different students around the same knowledge point, thereby providing teachers with a precise basis for instructional diagnosis. Building on learning analytics, the platform further incorporates a “data-driven teaching activity recommendation” module and a “teaching strategy library”, translating diagnostic results into actionable teaching plans. Using the Diagnostics course as an example, it demonstrates how teachers can design and improve classroom instruction based on learning reports. Technically, the platform adopts a multi-label text classification approach based on fine-tuning a pre-trained BERT model to automatically identify question types. It achieves strong classification performance on a medical education question dataset and ensures classification reliability through decision threshold calibration and a low-confidence fallback mechanism. This paper argues that the questions students raise in AI-assisted environments are essentially externalized representations of their internal cognitive processes. The significance of AI platforms lies in systematizing, visualizing, and operationalizing this process, thereby reshaping teacher-student interaction patterns and the logic of teaching decisions in medical education.
文章引用:李国琳, 张琪, 高昕, 乔可宏. 基于人工智能的医学生个性化指导模式——以“智慧阅读助手”为例[J]. 教育进展, 2026, 16(11): 878-890. https://doi.org/10.12677/ae.2026.16112454

参考文献

[1] Ali, M. (2025) The Role of AI in Reshaping Medical Education: Opportunities and Challenges. The Clinical Teacher, 22, e70040.
https://doi.org/10.1111/tct.70040
[2] Alsolami, A.S. (2025) The Effectiveness of Using Artificial Intelligence in Improving Academic Skills of School-Aged Students with Mild Intellectual Disabilities in Saudi Arabia. Research in Developmental Disabilities, 156, Article 104884.
https://doi.org/10.1016/j.ridd.2024.104884
[3] Lee, S. and Bang, J. (2025) Personalized Learning through AI: From Rule-Based Systems to AI Mentors. Multimedia-Assisted Language Learning, 28, 95-114.
[4] Zheng, K., Shen, Z., Chen, Z., Che, C. and Zhu, H. (2024) Application of AI-Empowered Scenario-Based Simulation Teaching Mode in Cardiovascular Disease Education. BMC Medical Education, 24, Article No. 1003.
https://doi.org/10.1186/s12909-024-05977-z
[5] Chin, C. and Brown, D.E. (2002) Student-Generated Questions: A Meaningful Aspect of Learning in Science. International Journal of Science Education, 24, 521-549.
https://doi.org/10.1080/09500690110095249
[6] Sailer, M., Ninaus, M., Huber, S.E., Bauer, E. and Greiff, S. (2024) The End Is the Beginning Is the End: The Closed-Loop Learning Analytics Framework. Computers in Human Behavior, 158, Article 108305.
https://doi.org/10.1016/j.chb.2024.108305
[7] Han, Y., Hong, S., Li, Z. and Lim, C. (2025) Defining and Classifying the Roles of Intelligent Learning Companion Systems: A Scoping Review of the Literature. Tech Trends, 69, 567-581.
https://doi.org/10.1007/s11528-025-01058-0
[8] Bergey, B.W., Cromley, J.G., Kaplan, A. and Bloxton, J.D. (2022) Do Students’ Questions during Chemistry Lectures Predict Perceived Comprehension and Exam Performance? The Journal of Experimental Education, 91, 411-430.
https://doi.org/10.1080/00220973.2021.2021843
[9] Wong, A.H.P., Wong, L.W., Hooi, S.C. and Lee, S.S. (2026) From Inquiry to Insight: Unlocking the Potential of Students’ Questions in Medical Education in Singapore. Teaching and Learning in Medicine, 38, 186-195.
https://doi.org/10.1080/10401334.2025.2481400
[10] Hao, Z., Jiang, J.X., Yu, J.F., et al. (2025) Student-AI Interaction in an LLM-Empowered Learning Environment: A Cluster Analysis of Engagement Profiles. arXiv: 2503.01694.
[11] Anderson, L.W. and Krathwohl, D.R. (2001) A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom’s Taxonomy of Educational Objectives. Longman.
[12] Lee, H., Atif, A. and Kang, K. (2026) Analysing AI Utilisation in Education through Learner Question Types: A Constructivist Approach. Australasian Journal of Educational Technology, 42, 79-96.
https://doi.org/10.14742/ajet.10657
[13] Devlin, J., Chang, M., Lee, K. and Toutanova, K. (2019) BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, 2-7 June 2019, 4171-4186.
https://doi.org/10.18653/v1/n19-1423
[14] Cui, Y., Che, W., Liu, T., Qin, B. and Yang, Z. (2021) Pre-Training with Whole Word Masking for Chinese BERT. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 3504-3514.
https://doi.org/10.1109/taslp.2021.3124365
[15] Wang, Z.Y., Yang, H.W., Li, X.G., et al. (2025) Leveraging AI Technology for Coding the Classroom Observation Record Form of Flanders Interaction Analysis. IEEE Access, 13, 66094-66108.
[16] Ouassilet, M.A., Jebbari, M., Rachidi, R., et al. (2026) A Voting Classifier Approach to Bloom’s Taxonomy: Integrating BERT and Large Language Models for Questions Automatic Classification. 2026 6th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), FEZ, 14-15 May 2026, 1-7.
[17] Almatrafi, O. and Johri, A. (2025) Leveraging Generative AI for Course Learning Outcome Categorization Using Bloom’s Taxonomy. Computers and Education: Artificial Intelligence, 8, Article 100404.
https://doi.org/10.1016/j.caeai.2025.100404
[18] Lee, K.W., Ang, Y.S. and Lai, J.W. (2025) Learning Analytics with Scalable Bloom’s Taxonomy Labeling of Socratic Chatbot Dialogues. Computers, 14, Article 555.
https://doi.org/10.3390/computers14120555
[19] Balubaid, A., Shahbal, L., Talib, M., Shahbal, A., Barajeh, L., Al-Hababi, K., et al. (2025) From Interrogative Detection to Difficulty Classification: A Two-Stage BERT-Based Approach for Educational Questions (Version v2). Zenodo.
[20] 王征海, 杨昌尧. 面向认知层级识别与知识诊断的智能学习系统设计[J]. 科技与创新, 2025(24): 8-11.
[21] Punyatoya, S., Vidya, N., Pradhan, C., Thejaswini, S., et al. (2025) VTU Question Classification System Based on BERT and Bloom’s Taxonomy Ring. 2025 International Conference on Emerging Systems and Intelligent Computing (ESIC), Bhubaneswar, 8-9 February 2025, 774-777.
[22] Al Faraby, S., Adiwijaya, Romadhony, A., et al. (2022) Educational Question Classification with Pre-Trained Language Models. 2022 7th International Conference on Informatics and Computing (ICIC), Denpasar, 8-9 December 2022, 1-6.
[23] 杨艳, 邱佳宁, 罗静, 谢满云. 人工智能赋能眼科课程设计教学改革[J]. 科学咨询, 2024(10): 101-105.
[24] 郝一双. OBE理念下使用微助教改进课堂教学的探索——以教师教育类理论课程为例[J]. 高等工程教育研究, 2021(S1): 24-25+46.
[25] Chen, P.H., Zeng, Y.X. and Lee, L.H. (2021) Incorporating Domain Knowledge into Language Transformers for Multi-Label Classification of Chinese Medical Questions. In: Lee, L.H., Chang, C.H. and Chen, K.Y., Eds., Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021), The Association for Computational Linguistics and Chinese Language Processing (ACLCLP), 265-270.