算力网络时代的网络工程动态课程知识图谱构建研究
Research on the Construction of a Dynamic Curriculum Knowledge Graph for Network Engineering in the Era of Computing Power Networks
DOI: 10.12677/ae.2026.16112401, PDF,    科研立项经费支持
作者: 李 刚, 王晓梅, 谢晓燕:西安邮电大学计算机学院,陕西 西安
关键词: 算力网络;网络工程;动态课程知识图谱;Computing Power Network; Network Engineering; Dynamic Curriculum Knowledge Graph
摘要: 生成式人工智能及其核心技术大语言模型的不断突破,推动网络工程领域向智能化、算网融合方向演进,而培养方案中的传统课程体系与实践评价体系呈现结构性滞后。文章依托西安邮电大学网络工程专业,融合工程教育专业认证理念与新工科建设要求,构建了以“大模型赋能网络工程”为核心的四层递进式知识本体架构,提出了面向算力网络时代的动态课程知识图谱构建方法,实现了算力网络等前沿知识的动态关联,并设计了大模型赋能的语义多维度评价闭环模型。初步实践表明,该图谱能有效支撑人机协同项目制学习,提升学生解决复杂工程问题的综合能力。
Abstract: The continuous breakthroughs in generative artificial intelligence and its core technology, large language models, are driving the field of network engineering toward intelligence and the integration of computing and networking, while the traditional curriculum system and practical evaluation system in training programs exhibit structural lag. Grounded in the Network Engineering program of Xi’an University of Posts and Telecommunications and integrating the philosophy of engineering education professional accreditation with the requirements of emerging engineering education, this paper constructs a four-layer progressive knowledge ontology architecture centered on “large-model-empowered network engineering”, proposes a dynamic curriculum knowledge graph construction method oriented to the era of computing power networks, realizes the dynamic association of frontier knowledge such as computing power networks, and designs a semantic multi-dimensional closed-loop evaluation model empowered by large models. Preliminary practice indicates that this knowledge graph can effectively support human-machine collaborative project-based learning and enhance students’ comprehensive ability to solve complex engineering problems.
文章引用:李刚, 王晓梅, 谢晓燕. 算力网络时代的网络工程动态课程知识图谱构建研究[J]. 教育进展, 2026, 16(11): 418-425. https://doi.org/10.12677/ae.2026.16112401

参考文献

[1] 林健. 面向未来的中国新工科建设[J]. 清华大学教育研究, 2017, 38(2): 26-35.
[2] 钟登华. 新工科建设的内涵与行动[J]. 高等工程教育研究, 2017(3): 1-6.
[3] 施晓秋. 遵循专业认证OBE理念的课程教学设计与实施[J]. 高等工程教育研究, 2018(5): 154-160.
[4] 周春月, 刘颖, 张洪婷, 等. 基于产出导向OBE的阶梯式实践教学研究[J]. 实验室研究与探索, 2016, 35(11): 206-208+220.
[5] 施晓秋, 蒋宗礼, 沈谦, 等. 网络工程新工科人才培养与专业建设的挑战、机遇与对策[J]. 高等工程教育研究, 2020(5): 11-17.
[6] 徐巧枝. 新工科背景下网络工程专业建设的思考与探索——以内蒙古师范大学为例[J]. 内蒙古师范大学学报(教育科学版), 2018, 31(11): 84-87+91.
[7] 钟秉林, 尚俊杰, 王建华, 等. ChatGPT对教育的挑战(笔谈) [J]. 重庆高教研究, 2023, 11(3): 3-25.
[8] 何珊云, 沈演. 学会提问: 大学生与生成式人工智能协同学习模式的研究[J]. 华东师范大学学报(教育科学版), 2025, 43(2): 34-48.
[9] 钟卓, 唐烨伟, 钟绍春, 等. 人工智能支持下教育知识图谱模型构建研究[J]. 电化教育研究, 2020, 41(4): 62-70.
[10] 杨文霞, 王卫华, 何朗, 等. 知识图谱赋能智慧教育的研究与实践——以武汉理工大学“线性代数”课程为例[J]. 高等工程教育研究, 2023(6): 111-117.
[11] 穆肃, 谭梓淇, 骆珏秀, 等. 面向精准教研的立体知识图谱构建方法研究[J]. 电化教育研究, 2023, 44(5): 74-81.
[12] 周东岱, 董晓晓, 顾恒年. 教育领域知识图谱研究新趋向: 学科教学图谱[J]. 电化教育研究, 2024, 45(2): 91-97+120.
[13] 董晓晓, 周东岱, 顾恒年. 面向学科核心素养发展的学生学科认知图谱构建研究[J]. 电化教育研究, 2023, 44(6): 90-96+103.
[14] Wang, G.X., Zhan, Z.H. and Qin, S.Y. (2025) Synergizing Knowledge Graphs and LLMs: An Intelligent Tutoring Model for Self-Directed Learning. Education Sciences, 15, Article 1102.
https://doi.org/10.3390/educsci15091102
[15] 叶俊民, 尹兴翰, 于爽, 等. 生成式人工智能赋能学习分析: 价值内涵、实践框架及发展路向[J]. 电化教育研究, 2025, 46(1): 86-92.
[16] Jauhiainen, J.S. and Garagorry Guerra, A. (2024) Generative AI in Education: ChatGPT-4 in Evaluating Students’ Written Responses. Innovations in Education and Teaching International, 62, 1377-1394.
https://doi.org/10.1080/14703297.2024.2422337
[17] Grévisse, C. (2024) LLM-Based Automatic Short Answer Grading in Undergraduate Medical Education. BMC Medical Education, 24, Article No. 1060.
https://doi.org/10.1186/s12909-024-06026-5