生成式AI在生物分离工程教学中的创新应用探索
Generative AI in Bioseparation Engineering Teaching: An Exploration of Innovative Applications
摘要: 生物分离工程作为生物工程专业的核心课程,知识体系复杂抽象,传统教学长期面临教学效能与学习成效的双重困境。针对学生学习动力不足、课堂参与度低、教学方式单一及评价机制僵化等问题,本研究以“蛋白质层析纯化”典型单元为实践载体,构建生成式人工智能驱动的“教–学–评”一体化教学模式。教:通过AI生成虚拟仿真实验、动态知识图谱、个性化教案与行业案例;学:智能学伴实时答疑、自适应路径规划与前沿资源推送;评:作业智能批阅、学习行为诊断与过程性反馈闭环。教学实践表明,该模式显著提升学生对分离原理的理解深度与技术应用能力,课堂参与度与高阶思维能力同步增强。同时,将课程思政有机融入AI生成内容,结合生物制药“卡脖子”技术攻关、绿色分离工艺等产业热点,引导学生树立科技报国志向与工程伦理意识,实现知识传授、能力培养与价值引领的有机统一。
Abstract: Bioseparation Engineering, a core course in bioengineering programs, features a complex and abstract knowledge system, and traditional pedagogy has long grappled with the dual challenges of limited teaching efficacy and suboptimal learning outcomes. To address persistent issues including low student motivation, minimal classroom engagement, monotonous instructional methods, and inflexible assessment mechanisms, this study adopts “protein chromatographic purification” as a representative teaching module to develop a Generative Artificial Intelligence (Generative AI)-driven integrated “Teaching-Learning-Assessment” instructional framework. Specifically: in the teaching dimension, AI generates virtual simulations, dynamic knowledge graphs, personalized lesson plans, and industry-relevant cases; in the learning dimension, an intelligent learning companion offers real-time, adaptive pathway recommendations, and curated frontier resources; in the assessment dimension, the system enables intelligent homework evaluation, learning behavior analytics, and closed-loop formative feedback. Empirical teaching results demonstrated significant improvements in students’ conceptual mastery of separation principles, technical application competence, classroom participation, and higher-order thinking skills. Furthermore, ideological, and political education was seamlessly embedded within AI-generated content-contextualized through biopharmaceutical “bottleneck” technology breakthroughs and green separation innovations-to foster students’ commitment to serving the nation through science and technology and strengthen engineering ethics awareness. The model realizes the organic integration of knowledge transmission, capability development, and value cultivation.
文章引用:刘晓丽, 井自强, 孙涛. 生成式AI在生物分离工程教学中的创新应用探索[J]. 创新教育研究, 2026, 14(8): 680-687. https://doi.org/10.12677/ces.2026.148650

参考文献

[1] 倪贺, 范瑞芳, 尹亮, 等. “新工科”背景下“生物分离工程”课程创新改革[J]. 生物工程学报, 2022, 38(4): 1612-1618.
[2] 孙星, 唐彤彤, 张微微. 基于OBE教育理念的生物分离工程课程教学改革与探索[J]. 高教学刊, 2023, 9(33): 137-140.
[3] 刘晓丽, 曾化伟, 孙涛. 新工科背景下“生物分离工程”创新教学探索[J]. 淮北师范大学学报(自然科学版), 2025, 46(2): 87-91.
[4] 陈娟丽, 慕军鹏. 基于生成式人工智能的“生态学”课程教学改革与探索[J]. 绵阳师范学院学报, 2026, 45(2): 110-115.
[5] 高佩天, 李璐, 罗桢妮. 高校人工智能教学研究热点与展望——基于CiteSpace的可视化分析[J]. 西部素质教育, 2025, 11(17): 19-23.
[6] 谷飞. 认知增强AI与教育共生: 未来教育新生态[J]. 开放教育研究, 2024, 30(6): 13-20.
[7] 陈盼, 习阳, 金晓锋, 等. “教、学、评、研”四维一体的生成式人工智能辅助生物化学与分子生物学教学的实践探索[J]. 生物化学与生物物理进展, 2026, 53(3): 789-800.
[8] 李松真. AI技术在高等教育智慧教学中的应用研究[J]. 华章, 2025(4): 126-128.
[9] 张金青, 高雪芹, 李淑霞, 等. AI赋能《草坪学》智慧化教学的模式构建与路径探索[J/OL]. 草业科学: 1-12.
https://link.cnki.net/urlid/62.1069.S.20260306.1059.002, 2026-08-19.
[10] 穆学峰, 王文龙, 许建兴. 生成式人工智能赋能SPOC教学模式应用新范式[J]. 计算机教育, 2024(9): 23-27.
[11] 孙科宏, 郑旭东, 杨海燕. 生成式AI支持的人机协同精准教学模式设计与实践研究[J]. 数字教育, 2025, 11(5): 70-77.
[12] 黄星云, 焦建利, 曾君, 等. GenAI重塑课堂活动: 应用路径与实践样态[J]. 现代教育技术, 2025, 35(2): 26-34.