面向人工智能的“数智融合”教学模式的探索与实践路径研究——以《数控加工与编程》课程为例
Research on Exploration and Implementation Pathways for an AI-Oriented “Digital-Intelligence Integration” Teaching Model—Taking the Course “CNC Machining and Programming” as an Example
摘要: 人工智能推动教育变革,高职工科实践教学面临教学内容与产业脱节、标准化教学与个性化发展矛盾、技能训练评价效率低等挑战。以《数控加工与编程》课程为例,探索构建面向人工智能的“数智融合”教学模式。通过数据驱动、人机协同的教学目标动态校准机制,实现与产业需求、学生差异的双向适配;依托知识图谱与智能引擎,构建模块化、可进化的教学内容供给体系,推动资源从“标准套餐”向“个性定制”转变;设计以人机协同为核心的沉浸式教学活动范式,融合数字孪生、VR/AR等智能场景;基于多模态数据建立“采集无感、分析有据、反馈及时”的智能评价体系。教学效果分析表明,实验组学生在知识掌握、技能达标、问题解决能力及个性化学习体验等方面均显著优于对照组。该模式为高职工科核心实践教学改革提供了理论创新与实践推广价值的解决方案。
Abstract: Artificial intelligence is driving educational transformation, yet vocational science and engineering practical teaching faces challenges such as a disconnect between curriculum and industry demands, conflicts between standardized instruction and personalized development, and inefficient skill assessment. Taking the course “CNC Machining and Programming” as an example, this study explores constructing an AI-oriented “digital-intelligent integration” teaching model. Through a data-driven, human-machine collaborative mechanism for dynamic calibration of teaching objectives, it achieves bidirectional adaptation to both industry needs and student diversity. Leveraging knowledge graphs and intelligent engines, a modular, evolvable instructional content delivery system is established, shifting resources from “standard packages” to “personalized customization.” An immersive teaching activity paradigm centered on human-machine collaboration is designed, integrating intelligent scenarios like digital twins and VR/AR. A smart evaluation system based on multimodal data is built, ensuring “seamless data collection, evidence-based analysis, and timely feedback.” Teaching effectiveness analysis indicates that experimental group students significantly outperformed the control group in knowledge mastery, skill attainment, problem-solving abilities, and personalized learning experiences. This model provides a solution with both theoretical innovation and practical application value for reforming core practical teaching in vocational science and engineering education.
参考文献
|
[1]
|
毕树沙, 张琳琳. 职业教育智能体: AI赋能职业教育新图景[J]. 中国职业技术教育, 2025(20): 5-11+20.
|
|
[2]
|
徐晓飞, 张策. 生成式人工智能赋能工程教育及学生能力的培养、测评与认证体系[J]. 高等工程教育研究, 2025(4): 1-9.
|
|
[3]
|
林健, 杨冬. 工程教育智能化: 内涵、特征与挑战[J]. 清华大学教育研究, 2023, 44(6): 1-11.
|
|
[4]
|
葛福鸿, 刘清堂. 人工智能赋能高校教学支持服务: 内涵、困境、模型与路径[J]. 中国电化教育, 2025(10): 46-54.
|
|
[5]
|
李建龙, 牛振东. “技术-教育”互构下人工智能赋能高校教学评价研究[J]. 中国高教研究, 2025(11): 15-23.
|
|
[6]
|
徐晶晶, 胡卫平. 智能时代思维型教学引领技术赋能学习: 现实反思、运行机制与实践路径[J]. 电化教育研究, 2021, 42(12): 93-99.
|
|
[7]
|
黄丽婕, 黄崇杏, 段青山, 等. 新人工智能背景下包装工程研究生课程教学新模式探索[J]. 包装工, 2024, 45(S2): 23-27.
|
|
[8]
|
管佳, 韩婷芷, 徐国兴. 人工智能技术赋能我国高等教育拔尖人才培养[J]. 中国电化教育, 2022(10): 97-101.
|
|
[9]
|
孙众, 吕恺悦, 骆力明, 等. 基于人工智能的课堂教学分析[J]. 中国电化教育, 2022(10): 15-23.
|
|
[10]
|
吴立宝, 曹雅楠, 曹一鸣. 人工智能赋能课堂教学评价改革与技术实现的框架构建[J]. 中国电化教育, 2021(5): 94-101.
|
|
[11]
|
李小平, 董银银, 姜丽萍, 等. 基于知识图谱设计的VR教学资源建构问题研究[J]. 中国教育信息化, 2022(10): 15-23.
|
|
[12]
|
张国梁, 黄秋娴, 邢义虎. “数控编程与加工”课程教学改革探索与实践[J]. 实验技术与管理, 2021, 38(12): 192-196.
|