| 270 | 0 | 71 |
| 下载次数 | 被引频次 | 阅读次数 |
有效诊断VR学习过程中学习者的认知状态是衡量VR学习效果的关键，也是实现个性化VR学习的基础。针对当前VR环境中学习者认知状态诊断忽视认知状态动态性、多模态数据缺失的现实困境，研究首先明确VR环境中学习者的认知状态，分析学习者认知状态表征的内涵，并基于此构建VR环境中学习者认知状态表征框架，包括多模态数据采集、认知图谱构建、交互特征构建、认知追踪模型构建与教育智能体构建等。接着对VR环境中学习者认知状态表征框架进行实践应用，以大学物理实验“用惠斯通电桥测电阻”为具体学习内容进行VR学习环境设计与开发，采集VR实验过程中的多模态数据，并利用DKVMN模型实现学习者认知状态追踪。模型效果分析表明其具有较好的性能与准确性；认知追踪结果分析表明其能够有效建模VR学习过程中的动态认知状态；结果解释与学习干预智能体能够对认知追踪结果进行分析解释并基于此提供VR学习干预。
Abstract：Accurately diagnosing the cognitive state of learners during VR learning is crucial for evaluating the effectiveness and is also the foundation for personalized VR learning. In light of the current challenges in diagnosing learners' cognitive states in VR environments, such as the neglect of the dynamic changes in cognitive states and the lack of multi-modal data, this study first clarifies the cognitive states of learners in VR environments, analyzes the connotation of learners' cognitive state representation. Based on this, constructs a framework for representing learners' cognitive states in VR environments, including the collection of multi-modal data, the construction of cognitive graph, the construction of interaction features, the construction of learners' cognitive tracing model, and the construction of educational AI agents. Subsequently, the framework for representing learners' cognitive states in VR environments is applied in practice. The specific learning content of college physics experiment “Measuring Resistance with a Wheatstone Bridge” is selected for the design and development of a VR learning environment, collected multi-modal data during the VR experiment process, and used the DKVMN model to trace the cognitive states of learners. The analysis of the cognitive tracing model's performance shows that it has good performance and accuracy. The analysis of the cognitive tracing results indicates that it can effectively model the dynamic cognitive states during VR learning. The result interpretation and learning intervention AI agent could analyze and explain the cognitive tracing results and provide VR learning intervention.
[1]Wan B,Wang Q,Su K,et al.Measuring the impacts of virtual reality games on cognitive ability using EEG signals and game performance data[J].IEEE Access,2021,9:18326-18344.
[2]刘妍，胡碧皓，尹欢欢，等.虚拟现实(VR)沉浸式环境如何实现深度取向的学习投入?——复杂任务情境中的学习效果研究[J].远程教育杂志，2021(4):72-82.
[3]张琪，杨玲玉.e-Learning环境学习测量研究进展与趋势——基于眼动应用视角[J].中国电化教育，2016(11):68-73.
[4]Manzoor S R,Mohd-Isa W N,Dollmat K S.Post-pandemic e-learning:a pre-protocol to assess the impact of mobile VR on learner motivation and engagement for VARK learning styles[J].F1000Research,2022,10:1-16.
[5]Dubovi I.Cognitive and emotional engagement while learning with VR:The perspective of multimodal methodology[J].Computers & Education,2022,183:104495.
[6][美]洛林·W.安德森，等.布卢姆教育目标分类学分类学视野下的学与教及其测评[M].蒋小平，张琴美，罗晶晶，译.北京：外语教学与研究出版社，2009:4,21,51-52.
[7][美]罗伯特·J.马扎诺，[美]约翰·S.肯德尔.教育目标新分类学(第2版)[M].高凌飚，吴有昌，苏峻，译.北京：教育科学出版社.2012:56.
[8][澳大利亚]约翰·彼格斯，[新西兰]凯文·科利斯.学习质量评价：SOLO分类理论(可观察的学习成果结构)[M].高凌飚，张洪岩，译.北京：人民教育出版社，2010:27-28.
[9][美]B.S.布卢姆等.教育目标分类学第一分册认知领域[M].罗黎辉，丁证霖，等，译.上海：华东师范大学出版社.1986:14,20.
[10]Paxinou E,Georgiou M,Kakkos V,et al.Achieving educational goals in microscopy education by adopting virtual reality labs on top of face-to-face tutorials[J].Research in Science & Technological Education,2022(3):320-339.
[11]Mutian N,Hung L C,Zhiyuan Y.Embedding virtual reality technology in teaching 3d design for secondary education[J].Frontiers in Virtual Reality,2021,2:661920.
[12]Gagné R M.The conditions of learning and theory of instruction (4th ed) [M].New York:Hol,Rinehart and Winston,1985:125-126.
[13]Black J B,Segal A,Vitale J,et al.Embodied cognition and learning environment design[M]//Theoretical foundations of learning environments.Routledge,2012:198-223.
[14]张慕华，李策，祁彬斌，等.沉浸式虚拟现实环境中认知投入的自动测评研究[J].远程教育杂志，2023(5):76-85.
[15]Suzuki Y,Wild F,Scanlon E.Measuring cognitive load in augmented reality with physiological methods:A systematic review[J].Journal of Computer Assisted Learning,2024(2):375-393.
[16]Shadiev R,Li D.A review study on eye-tracking technology usage in immersive virtual reality learning environments[J].Computers & education,2023,196:104681.
[17]胡翰林，刘革平.从多态表征到置身参与：虚拟现实技术助力学科教学的价值路径[J].电化教育研究，2022(1):79-85.
[18]Li Y F,Guan J Q,Wang X F,et al.Examining students’ self-regulated learning processes and performance in an immersive virtual environment[J].Journal of Computer Assisted Learning,2024(6):2948-2963.
[19]Sobocinski M,Dever D,Wiedbusch M,et al.Capturing self-regulated learning processes in virtual reality:Causal sequencing of multimodal data[J].British Journal of Educational Technology,2024(4):1486-1506.
[20]Ji Z,Hu C,Luo Z,et al.The important thing neglected:integrating bloom’s taxonomy into VR safety training model development[J].Virtual Reality,2025(4):1-21.
[21]Wang W S,Lin C J,Lee H Y,et al.Enhancing self-regulated learning and higher-order thinking skills in virtual reality:the impact of ChatGPT-integrated feedback aids[J].Education and Information Technologies,2025(14):19419-19445.
[22]Zhang J,Shi X,King I,et al.Dynamic key-value memory networks for knowledge tracing[C]//Proceedings of the 26th international conference on World Wide Web.2017:765-774.
[23]周涛，李艳婷，杨月婷，等.学习者学习行为建模：一种基于预训练模型的可解释性知识追踪模型[J].大数据，2025(5):86-100+2.
[24]孙新杰，刘淇，张凯，等.2T-Agent:生成式智能体驱动的类教师思维认知诊断框架 [J/OL].计算机学报，1-16[2025-11-26].https://link.cnki.net/urlid/11.1826.tp.20251119.1112.010.
[25]万海鹏，王琦，余胜泉.基于学习认知图谱的适应性学习框架构建与应用[J].现代远距离教育，2022 (4):73-82.
[26]Kursa M B,Rudnicki W R.Feature selection with the Boruta package[J].Journal of statistical software,2010,36:1-13.
基本信息:
DOI：10.13927/j.cnki.yuan.20260430.005
中图分类号:O4-4;G434;G642;TP391.9
引用信息:
[1]胡翰林,刘革平.VR环境中学习者认知状态的表征与应用研究[J].现代远距离教育,2026,No.223(01):47-56.DOI:10.13927/j.cnki.yuan.20260430.005.
基金信息:
国家自然科学基金面上项目“VR环境下深度认知追踪关键技术及学习干预模型研究”(编号：62277044); 西华师范大学科研启动项目“VR环境中学习者建模研究”(编号：493232)
2026-04-30
2026-04-30
2026-04-30