| 1,116 | 0 | 261 |
| 下载次数 | 被引频次 | 阅读次数 |
在教育数字化转型与人工智能深度融合的背景下,教育智能体正成为重构教育生态的核心载体,但当前研究多局限于认知层面的知识传递,存在离身性与情感缺失的痛点。该文基于具身认知理论,构建了面向在线教育场景的“生理—具身—情感共鸣”(PEER)框架。该框架包含生理、具身行为、情感与共鸣四个层级:在生理层,利用生理夹带机制实现呼吸与节律的无意识协同;在行为层,通过视线跟随与空间索引构建共享认知空间;在情感层,基于Russell情感环状模型识别学习者状态,并提供动态情感支架;最终在共鸣层实现人机在节律、意图与情感上的深度对齐。研究进一步探讨了该框架在创设身心协同情境、构建多模态协作空间及优化深层伴学体验中的应用路径,旨在推动教育智能体从单向干预向双向身心共鸣的范式转变。
Abstract：In the context of the digital transformation of education and its deep integration with artificial intelligence, educational agents are becoming the core carriers for reconstructing the educational ecosystem. However, current research is mostly limited to knowledge transfer at the cognitive level, suffering from the critical issues of disembodiment and a lack of emotional engagement. Grounded in embodied cognition theory, cognition is the result of the dynamic coupling of the body, the environment, and the mind, which emphasizes the core role of the body in meaning generation and emotion regulation. Building upon this foundation, this paper constructs a “Physiological-Embodied-Emotional Resonance”(PEER) framework tailored for online education scenarios. The framework consists of four levels: physiological, embodied behavioral, emotional, and resonance. At the physiological level, physiological entrainment mechanisms are utilized to achieve an unconscious synergy of respiration and rhythm. At the behavioral level, a shared cognitive space is constructed through gaze following and spatial indexing. At the emotional level, learners' states are identified utilizing Russell's circumplex model of affect to provide dynamic emotional scaffolding. Ultimately, at the resonance level, a deep human-machine alignment in rhythm, intention, and emotion is achieved. The study further explores the application paths of this framework in creating mind-body synergistic contexts, constructing multimodal collaborative spaces, and optimizing deep companion learning experiences. This research aims to promote a paradigm shift in educational agents from unidirectional intervention to bidirectional mind-body resonance.
[1]中共中央,国务院.教育强国建设规划纲要(2024—2035年)[EB/OL].https://www.gov.cn/gongbao/2025/issue＿11846/202502/content＿7002799.html,2025-01-13.
[2]教办[2025]3号,教育部等九部门关于加快推进教育数字化的意见[Z].
[3]中华人民共和国教育部.中国智慧教育白皮书[R].北京:中华人民共和国教育部,2025.
[4]京教办[2025]2号.北京市教育委员会关于印发《北京市推进中小学人工智能教育工作方案(2025—2027年)》的通知[Z].
[5]浙教技[2025]24号,浙江省教育厅浙江省发展和改革委员会浙江省科学技术厅浙江省数据局关于印发《浙江省推进“人工智能+教育”行动方案(2025—2029年)》的通知[Z].
[6][德]海德格尔.陈嘉映,王庆节译.存在与时间[M].北京:生活·读书·新知三联书店,2006.
[7][法]梅洛-庞蒂.姜志辉译.知觉现象学[M].北京:商务印书馆,2001.
[8]Williams L E,Bargh J A.Experiencing physical warmth promotes interpersonal warmth[J].Science,2008,322(5901):606-607.
[9]Varela F J, Thompson E, et al. The Embodied Mind:Cognitive Science and Human Experience[M].Cambridge,MA:MIT Press,1991.
[10]De Jaegher H,Di Paolo E.Participatory sense-making:An enactive approach to social cognition[J].Phenomenology and the Cognitive Sciences,2007,6(4):485-507.
[11]Rizzolatti G,Craighero L.The mirror-neuron system[J].Annual Review of Neuroscience,2004,27(1):169-192.
[12]Gallese V.Embodied simulation:From neurons to phenomenal experience[J].Phenomenology and the Cognitive Sciences,2005,4(1):23-48.
[13]卢宇,余京蕾等.生成式人工智能的教育应用与展望——以Chat GPT系统为例[J].中国远程教育,2023,43(4):24-31+51.
[14]李海峰,王炜.面向人机智慧共生的大语言模型智能体反馈研究[J].中国电化教育,2025,(11):42-51.
[15]Wang H,Wang C,et al.Impact of AI-agent-supported collaborative learning on the learning outcomes of University programming courses[J].Education and Information Technologies,2025,30(12):17717-17749.
[16]Schlimbach R,Lange T,et al.A Longitudinal Study on Boosting Students’Performance with a Learning Companion[A]. Proceedings of the 44th International Conference on Information Systems(ICIS 2023)[C].Hyderabad:Association for Information Systems,2023.1-17.
[17]Moribe S,Ushiama T.Imitating Mistakes in a Learning Companion AI Agent for Online Peer Learning[C].Bangkok:IEEE,2025.1-8.
[18]Höök K.Affective loop experiences:What are they?[C].Berlin,Heidelberg:Springer,2008.1-12.
[19]Vinciarelli A,Pantic M,et al.Social signal processing:Survey of an emerging domain[J].Image and Vision Computing,2009,27(12):1743-1759.
[20]Russell J A.A circumplex model of affect[J].Journal of Personality and Social Psychology,1980,39(6):1161-1178.
[21]Pekrun R. The control-value theory of achievement emotions:Assumptions,corollaries, and implications for educational research and practice[J].Educational Psychology Review,2006,18(4):315-341.
[22]张惠敏,梁为等.生成式人工智能时代教育空间的具身化重构[J].中国电化教育,2026,(2):23-29.
[23]Barbaresi M, Nardo D, et al.Physiological Entrainment:A Key Mind-Body Mechanism for Cognitive,Motor and Affective Functioning,and Well-Being[J].Brain Sciences,2025,15(1):3.
[24]Phillips-Silver J,Aktipis CA,et al.The ecology of entrainment:Foundations of coordinated rhythmic movement[J].Music Perception,2010,28(1):3-14.
[25]Vasta N, Jajo N, et al. Evaluating a Camera-Based Approach to Assess Cognitive Load During Manufacturing Computer Tasks[J].Electronics,2025,14(3):467.
[26]Gupta A,Ghanekar B,et al.CogPhys:Assessing Cognitive Load via Multimodal Remote and Contact-based Physiological Sensing[A].Advances in Neural Information Processing Systems 36(NeurIPS 2023)[C]. La Jolla:Neural Information Processing Systems Foundation,2024.1-14.
[27]Varni G,Bove C,et al.When agents become partners:a review of the role the implicit plays in the interaction with artificial social agents[J].Multimodal Technologies and Interaction,2020,4(4):81.
[28]Yang X, Zhan Y, et al. From Tool to Partner:Exploring the Roles of Embodiment on AI Agent in Pair Programming[C]. Los Alamitos:IEEE Computer Society,2025.234-240.
[29]Pejsa T, Andrist S, et al. Gaze and attention management for embodied conversational agents[J]. ACM Transactions on Interactive Intelligent Systems(Tii S),2015,5(1):4.
[30]Wen J, Gheisari M. Influence of pedagogical agent deictic gestures on construction management students learning within a 360-degree virtual field trip[A].Proceedings of the 38th International Symposium on Automation and Robotics in Construction(ISARC)[C].Dubai:IAARC,2021:707-715.
[31]Ashwin T S, Caitlin S, et al. Combining multimodal analyses of students’emotional and cognitive states to understand their learning behaviors[A].Proceedings of the 32nd International Conference on Computers in Education(ICCE 2024)[C]. Quezon City:Asia-Pacific Society for Computers in Education,2024.306-316.
[32]Kumar M J D,Rao M S,et al.Multimodal emotion recognition:A comprehensive survey of datasets,methods,and applications[J].IEEE Access,2025,13:201067-201097.
[33]Bailenson J N,Yee N.Digital chameleons:automatic assimilation of nonverbal gestures in immersive virtual environments[J].Psychological Science,2005,16(10):814-819.
[34]Andrist S,Mutlu B,et al.Conversational gaze aversion for virtual agents[A].Aylett R,Krenn B,et al.International Workshop on Intelligent Virtual Agents[C].Berlin:Springer,2013.249-262.
[35]Li W,Wang F,et al.Getting the point:which kinds of gestures by pedagogical agents improve multimedia learning?[J].Journal of Educational Psychology,2019,111(8):1382-1395.
[36]Lawson A P,Mayer R E,et al.The positivity principle:do positive instructors improve learning from video lectures?[J].Educational Technology Research and Development,2021,69(6):3101-3129.
[37]Choi S,Kang S,et al.The effect of an agent tutor’s integration of cognitive and emotional gestures on cognitive load, motivation, and achievement[J].Contemporary Educational Technology,2024,16(1):ep491.
[38]Mayer R E,Fiorella L.Principles based on social cues in multimedia learning:personalization,voice,image,and embodiment principles[A].Mayer R E.The Cambridge Handbook of Multimedia Learning[M]. Cambridge:Cambridge University Press,2021.279-288.
[39]Pekrun R, Goetz T, et al. Measuring emotions in students’ learning and performance:The Achievement Emotions Questionnaire(AEQ)[J].Contemporary Educational Psychology,2011,36(1):36-48.
[40]Biocca F,Harms C,et al.Toward a more robust theory and measure of social presence:Review and suggested criteria[J]. Presence:Teleoperators and Virtual Environments,2003,12(5):456-480.
基本信息:
中图分类号:TP18;G434
引用信息:
[1]薛耀锋,张佳佳,许宏鑫.具身认知视域下学伴智能体的多模态框架构建研究[J].中国电化教育,2026,No.476(09):56-65.
基金信息:
国家自然科学基金项目“基于跨模态通用语言大模型的专业领域人机对话交互方法”（项目编号：92370206）研究成果
2026-09-07
2026-09-07