| 2,632 | 35 | 2599 |
| 下载次数 | 被引频次 | 阅读次数 |
知识图谱愈加成为教育数字化基础设施的重要组成部分，相关应用逐渐增多，但知识图谱作用于教与学的应用逻辑与应用场景仍有待挖掘。基于当前的智能学习面临着碎片化严重、联通性不足、知识库缺失的问题，该研究以经典学习理论为基础，以学习者处理学习任务时的认知活动为状态，从认知心理的角度探究知识图谱驱动下的智能学习机制，为解决三个主要问题提出针对性的解决方案。第一，针对知识碎片化的问题，知识图谱通过将知识串联成网络，促进学习中的认知加工，减少碎片化学习；第二，针对知识点冗余的问题，知识图谱通过合并相同知识点、增加跨学科知识的联系，提高了学习中的智能联结，激发学习者主动探索，并主动形成知识构建活动；第三，针对知识库缺失的问题，知识图谱平台通过集成知识点、学习资源库与学生的学习行为，使学习的个性化推荐有据可依。基于学习者运用知识图谱学习的理论机制，未来知识图谱的教育教学创新方向将聚焦于个性化、自适应、探索性、反馈性的学习平台搭建，为推进教育教学的智能化变革提供理论支撑。
Abstract：Knowledge graphs are increasingly becoming an essential component of digital educational infrastructure, with a growing number of related applications. However, the application logic and scenarios of knowledge graphs in teaching and learning remain to be further explored.Given the current challenges faced by intelligent learning, including severe fragmentation, inadequate connectivity, and a lack of knowledge bases, this study, grounded in classical learning theories, investigates the cognitive activities of learners when tackling learning tasks, and explores the mechanisms of knowledge graph-driven intelligent learning from a cognitive psychology perspective. Targeted solutions are proposed to address three major issues. First, to tackle knowledge fragmentation, knowledge graphs facilitate cognitive processing in learning by connecting knowledge into a network, thereby reducing fragmented learning. Second, to address knowledge redundancy, knowledge graphs enhance intelligent connections in learning by merging identical knowledge points and increasing interdisciplinary linkages, stimulating learners' proactive exploration and knowledge construction. Third, to solve the problem of missing knowledge bases, knowledge graph platforms enable personalized learning recommendations by integrating knowledge points, learning resource libraries, and students' learning behaviors. Based on the theoretical mechanisms of learners' utilization of knowledge graphs, future innovations in educational teaching leveraging knowledge graphs will focus on the development of personalized, adaptive, exploratory, and feedback-driven learning platforms,providing theoretical support for advancing the intelligent transformation of education and teaching.
[1]李振,周东岱等.“人工智能+”视域下的教育知识图谱:内涵、技术框架与应用研究[J].远程教育杂志,2019,37(4):42-53.
[2]戴岭,祝智庭.教育数字化转型的逻辑起点、目标指向和行动路径[J].中国教育学刊,2023,(7):14-20.
[3]邹红军,柳欣源.数字化社会的知识“面相”与教育应对[J].东北师大学报(哲学社会科学版),2024,(3):108-119.
[4]方莉,谭莹.知识和信息碎片化对高校思政课课程体系的影响探析[J].学校党建与思想教育,2019,(22):50-52.
[5]汪建基,马永强等.碎片化知识处理与网络化人工智能[J].中国科学:信息科学,2017,47(2):171-192.
[6]Adiredja,A.P.Students’struggles with temporal order in the limit definition:uncovering resources using knowledge in pieces[J].International Journal of Mathematical Education in Science and Technology,2020,52(9),1295-1321.
[7]Peet M R.Transforming students’beliefs:Developing employability skills and generative identities through the Integrative Knowledge Portfolio Process[J].Journal of Transformative Learning,2015,3(2):15-36.
[8]Chen Y,Cheng HK,et al.Knowledge-sharing ties and equivalence in corporate online com-munities:A novel source to understand voluntary turnover[J].Production and Operations Management,2022,31(10):3896-3913.
[9]刘峤,李杨等.知识图谱构建技术综述[J].计算机研究与发展,2016,53(3):582-600.
[10][19][25][法]斯坦尼斯拉斯·迪昂.周加仙译.精准学习[M].杭州:浙江教育出版社,2023.
[11][14][美]菲利普·津巴多,[美]罗伯特·约翰逊等.傅小兰译.津巴多普通心理学(第8版)[M].北京:人民邮电出版社,2022.230+277.
[12]Sweller J.Cognitive load during problem solving:Effects on learning[J].Cognitive science,1988,12(2):257-285.
[13]Liu R,Wang L,Koszalka T A,et al.Effects of immersive virtual reality classrooms on students’academic achievement,motivation and cognitive load in science lessons[J].Journal of Computer Assisted Learning,2022,38(5):1422-1433.
[15]Bada S O,Olusegun S.Constructivism learning theory:A paradigm for teaching and learning[J].Journal of Research&Method in Education,2015,5(6):66-70.
[16]赵国庆,孙兴艳等.显性直接教学的概念演进、核心内涵与实践启示[J].远程教育杂志,2023,41(5):28-37.
[17]何克抗.教学支架的含义、类型、设计及其在教学中的应用--美国《教育传播与技术研究手册(第四版)》让我们深受启发的亮点之一[J].中国电化教育,2017,(4):1-9.
[18]Kop R,Hill A.Connectivism:Learning theory of the future or vestige of the past?[J].International Review of Research in Open and Distributed Learning,2008,9(3):1-13.
[20]Zhu A.Knowledge graph visualization for understanding ideas[J].International Journal for Cross-Disciplinary Subjects in Education(IJCDSE),2013,3(1):1392-1396.
[21]王国华,聂胜欣等.多媒体学习中的认知负荷:测量方法与技术纵览[J].电化教育研究,2022,43(4):19-25+54.
[22]辛自强,林崇德.认知负荷与认知技能和图式获得的关系及其教学意义[J].华东师范大学学报(教育科学版),2002,(4):55-60+77.
[23]周东岱,董晓晓等.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.
[24]Seo S,Oh B,Jo E,et al.Active learning for knowledge graph schema expansion[J].IEEE Transactions on Knowledge and Data Engineering,2021,34(12):5610-5620.
[26]Siemens G.Connectivism:Learning and knowledge today[J].The International Review of Research in Open and Distance Learning,2006,9(3):1-13.
[27]Wei Y W Y,Wei Q Q Y,et al.Research on the Construction and Application of Knowledge Graph of Digital Resources in Vocational Colleges[J].Journal of Computers,2023,34(4):195-201.
[28]Huang M,Xu G,Li H.Construction of personalized learning service system based on deep learning and knowledge graph[J].Applied Mathematics and Nonlinear Sciences,2023,9(1):1-14.
[29]王竹立,吴彦茹.数智时代的知识管理:知识不确定性的挑战及应对策略[J].现代远程教育研究,2024,36(1):21-28.
[30]申睿,郭福春等.人工智能赋能高职教学资源建设路径研究--基于联通主义的视角[J].教育学术月刊,2022,(7):52-59.
[31]Zheng L,Niu J,Long M,et al.An automatic knowledge graph construction approach to promoting collaborative knowledge building,group performance,social interaction and socially shared regulation in CSCL[J].British Journal of Educational Technology,2023,54(3):686-711.
[32]Zhang S,Wang X,et al.An Adaptive Learning Method Based on Knowledge Graph[J].Frontiers in Educational Research,2023,6(6):112-115.
[33]Nguyen H D,Truong D,et al.Knowledge management for information querying system in education via the combination of rela-ops model and knowledge graph[J].Journal of Cases on Information Technology(JCIT),2023,25(1):1-17.
[34]Lv P,Wang X,et al.Intelligent personalised exercise recommendation:Aweighted knowledge graph‐based approach[J].Computer Applications in Engineering Education,2021,29(5):1403-1419.
基本信息:
中图分类号:G434
引用信息:
[1]吴杨,吕钰琪,杜钧,等.知识图谱驱动智能学习的内生逻辑[J].中国电化教育,2025,No.457(02):122-130.
基金信息:
北京市教育科学“十四五”规划优先关注课题“生成式人工智能在基础教育的应用现状与优化策略研究”(项目编号：AEGA24012)研究成果
2025-02-10
2025-02-10