生成式AI数字媒体创作中的具身交互设计研究
高洁

北京交通大学，北京市，100044；

摘要：生成式人工智能正在改变数字媒体内容的生成方式，也改变创作者与工具之间的关系。现有系统大多以文本提示、候选生成和结果筛选为主要交互路径，能够显著提高生产效率，却较难承载姿态、空间、节奏、力度和情绪等连续、隐性的创作意图。本文采用整合式文献综述方法，综合生成式AI、人机共创、具身认知、临场感与多模态交互等研究，并结合近年数字媒体与设计领域的实证进展，讨论生成式AI创作中“具身交互”究竟改变了什么。综述认为，具身性不应被等同于手势、头显或多模态设备，而应被理解为身体行动、系统表征与生成反馈之间可感知、可修正的耦合关系。在此基础上，本文提出“具身线索—心理机制—共创行为—创作结果”的循环框架：动作自然性、多模态互补性、时空一致性与情境可供性首先影响感知控制、认知负荷、任务沉浸和共创认同，继而改变创意外化、方案探索、反馈修正与作者性判断，并最终作用于效率、质量、新颖性、内容多样性和持续使用。已有证据对效率和局部质量提升较为一致，但对新颖性、群体多样性与长期作者性的影响仍存在分歧。文章据此提出身体意图可计算化、反馈状态可见化、生成过程分层可控、共创贡献可追溯、具身强度适应化与数据伦理过程化六项设计策略，并给出后续实验和长期研究需要优先检验的问题。本文的价值不在于证明“具身化必然优于提示词”，而在于说明何种身体参与能够转化为真实的创作控制，以及这种控制何时可能成为新的负担。

关键词：生成式人工智能；数字媒体创作；具身交互；人机共创；创作能动性；整合式文献综述

参考文献

[1] NOY S, ZHANG W. Experimental evidence on the productivity effects of generative artificial intelligence[J]. Science, 2023, 381(6654): 187-192. DOI: 10.1126/science.adh2586.

[2] ZHOU E, LEE D. Generative artificial intelligence, human creativity, and art[J]. PNAS Nexus, 2024, 3(3): pgae052. DOI: 10.1093/pnasnexus/pgae052.

[3] DOSHI A R, HAUSER O P. Generative AI enhances individual creativity but reduces the collective diversity of novel content[J]. Science Advances, 2024, 10(28): eadn5290. DOI: 10.1126/sciadv.adn5290.

[4] EPSTEIN Z, HERTZMANN A, HERMAN L, et al. Art and the science of generative AI[J]. Science, 2023, 380(6650): 1110-1111. DOI: 10.1126/science.adh4451.

[5] DWIVEDI Y K, KSHETRI N, HUGHES L, et al. “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI[J]. International Journal of Information Management, 2023, 71: 102642. DOI: 10.1016/j.ijinfomgt.2023.102642.

[6] SHNEIDERMAN B. Human-centered artificial intelligence: Reliable, safe & trustworthy[J]. International Journal of Human-Computer Interaction, 2020, 36(6): 495-504. DOI: 10.1080/10447318.2020.1741118.

[7] DOURISH P. Where the Action Is: The Foundations of Embodied Interaction[M]. Cambridge, MA: MIT Press, 2001.

[8] WILSON M. Six views of embodied cognition[J]. Psychonomic Bulletin & Review, 2002, 9(4): 625-636. DOI: 10.3758/BF03196322.

[9] BARSALOU L W. Grounded cognition[J]. Annual Review of Psychology, 2008, 59: 617-645. DOI: 10.1146/annurev.psych.59.103006.093639.

[10] KILTENI K, GROTEN R, SLATER M. The sense of embodiment in virtual reality[J]. Presence: Teleoperators and Virtual Environments, 2012, 21(4): 373-387. DOI: 10.1162/PRES_a_00124.

[11] STEUER J. Defining virtual reality: Dimensions determining telepresence[J]. Journal of Communication, 1992, 42(4): 73-93. DOI: 10.1111/j.1460-2466.1992.tb00812.x.

[12] SLATER M. Place illusion and plausibility can lead to realistic behaviour in immersive virtual environments[J]. Philosophical Transactions of the Royal Society B, 2009, 364(1535): 3549-3557. DOI: 10.1098/rstb.2009.0138.

[13] REZWANA J, MAHER M L. Designing creative AI partners with COFI: A framework for modeling interaction in human-AI co-creative systems[J]. ACM Transactions on Computer-Human Interaction, 2023, 30(5): Article 67. DOI: 10.1145/3519026.

[14] SINGH S, HINDRIKS K, HEYLEN D, BARAKA K. A systematic review of human-AI co-creativity[EB/OL]. arXiv:2506.21333, 2025[2026-09-02]. https://arxiv.org/abs/2506.21333.

[15] AMERSHI S, WELD D, VORVOREANU M, et al. Guidelines for human-AI interaction[C]//Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2019: 1-13. DOI: 10.1145/3290605.3300233.

[16] SHNEIDERMAN B. Human-Centered AI[M]. New York: Oxford University Press, 2022.

[17] YANG Q, STEINFELD A, ROSÉ C, ZIMMERMAN J. Re-examining whether, why, and how human-AI interaction is uniquely difficult to design[C]//Proceedings of CHI 2020. New York: ACM, 2020: 1-13. DOI: 10.1145/3313831.3376301.

[18] BAUDOUX G, GUO C, GOUCHER-LAMBERT K. Multimodal generative AI for conceptual design: Enabling text-based and sketch-based human-AI conversations[J]. Proceedings of the Design Society, 2025, 5: 2501-2510. DOI: 10.1017/pds.2025.10264.

[19] OPPENLAENDER J, JOHNSTON H, SILVENNOINEN J M, BARRANHA H. Artworks reimagined: Exploring human-AI co-creation through body prompting[J]. Proceedings of the ACM on Human-Computer Interaction, 2025, 9(4): Article EICS012. DOI: 10.1145/3734189.

[20] CSIKSZENTMIHALYI M. Flow: The Psychology of Optimal Experience[M]. New York: Harper & Row, 1990.

[21] SCHUBERT T, FRIEDMANN F, REGENBRECHT H. The experience of presence: Factor analytic insights[J]. Presence, 2001, 10(3): 266-281. DOI: 10.1162/105474601300343603.

[22] GONZALEZ-FRANCO M, PECK T C. Avatar embodiment: Towards a standardized questionnaire[J]. Frontiers in Robotics and AI, 2018, 5: 74. DOI: 10.3389/frobt.2018.00074.

[23] LONG D, MAGERKO B. What is AI literacy? Competencies and design considerations[C]//Proceedings of CHI 2020. New York: ACM, 2020: 1-16. DOI: 10.1145/3313831.3376727.

[24] HASSENZAHL M. Experience Design: Technology for All the Right Reasons[M]. Cham: Springer, 2010.

[25] NORMAN D A. The Design of Everyday Things[M]. Revised and Expanded Edition. New York: Basic Books, 2013.

[26] 辛向阳. 交互设计：从物理逻辑到行为逻辑[J]. 装饰, 2015(1): 58-62.

[27] 王文娟, 卢兆麟, 郝佳, 等. 基于神经生理测量探究具身交互对创意思维的影响[J]. 机械工程学报, 2025, 61(19): 237-248. DOI: 10.3901/JME.2025.19.237.

[28] 李旭, 刘彦杰, 黄桂红. AIGC多模态叙事视角下的非遗数字创意产品人机共创设计研究[J]. 包装工程, 2025, 46(14): 313-327. DOI: 10.19554/j.cnki.1001-3563.2025.14.032.

[29] 田少煦, 夏文英. 计算创造与意义创建——AIGC语境下数字艺术的人机共创研究[J]. 山东社会科学, 2025(5): 82-91.

[30] 刘宏宇, 巩淼森, 梁峭. 具身认知视角下的人—智能体交互的意向立场[J]. 包装工程, 2022, 43(2): 145-151.

[31] 汤晓颖, 唐艺英. 具身认知视阈下粤剧非遗数字化设计研究[J]. 包装工程, 2023, 44(6): 311-319. DOI: 10.19554/j.cnki.1001-3563.2023.06.034.

[32] 赵宜. 人机共创、数据融合与多模态模型：生成式AI的电影艺术与文化工业批判[J]. 当代电影, 2023(8): 15-21.

[33] HEIGL R. Generative artificial intelligence in creative contexts: A systematic review and future research agenda[J]. Management Review Quarterly, 2026, 76: 955-992. DOI: 10.1007/s11301-025-00494-9.

[34] TSAO J, LIANG C X, NOGUES C, WONG A. Perceptions and integration of generative artificial intelligence in creative practices and industries: A scoping review and conceptual model[J]. AI & Society, 2026, 41(3): 2259-2278. DOI: 10.1007/s00146-025-02667-2.

[35] YOU Y Q, GUAN S S, FENG Y L. Expressive activation enhances user satisfaction in AIGC co-creation through perceived control and meaning-making[J]. Scientific Reports, 2026, 16: 20991. DOI: 10.1038/s41598-026-53744-5.

[36] BOMBA F, DE ANGELI A. Agency and authorship in AI art: Transformational practices for epistemic troubles[J]. International Journal of Human-Computer Studies, 2025, 205: 103652. DOI: 10.1016/j.ijhcs.2025.103652.

[37] DREYER S, MCTEAGUE C, THORING K. AI as creative partner: Exploring perceived roles in human-AI co-creation[J]. Proceedings of the Design Society, 2026, 6: 1011-1020. DOI: 10.1017/pds.2026.10459.

[38] KIM B. TRACE: An embodied paper-based human-AI co-doodling ecosystem with authorship traces[J]. Design and Artificial Intelligence, 2026: 100099. DOI: 10.1016/j.daai.2026.100099.

[39] MONTEFIORE T, FORMOSA P, BANKINS S, et al. The impacts of generative AI on the meaningfulness of creative work[J]. Journal of Business Ethics, 2026. DOI: 10.1007/s10551-026-06342-4.

[40] BRADE S, WANG B, SOUSA M, et al. Promptify: Text-to-image generation through interactive prompt exploration with large language models[C]//Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. New York: Association for Computing Machinery, 2023: 1-14. DOI: 10.1145/3586183.3606725.

[41] WANG Z, HUANG Y, SONG D, et al. PromptCharm: Text-to-image generation through multi-modal prompting and refinement[C]//Proceedings of the CHI Conference on Human Factors in Computing Systems. New York: Association for Computing Machinery, 2024: 1-21. DOI: 10.1145/3613904.3642803.

[42] WHITTEMORE R, KNAFL K. The integrative review: Updated methodology[J]. Journal of Advanced Nursing, 2005, 52(5): 546-553. DOI: 10.1111/j.1365-2648.2005.03621.x.

[43] TORRACO R J. Writing integrative literature reviews: Guidelines and examples[J]. Human Resource Development Review, 2005, 4(3): 356-367. DOI: 10.1177/1534484305278283.

[44] WEN W, YAMASHITA A, ASAMA H. The sense of agency during continuous action: Performance is more important than action-feedback association[J]. PLOS ONE, 2015, 10(4): e0125226. DOI: 10.1371/journal.pone.0125226.

[45] WEN W, YAMASHITA A, ASAMA H. The sense of agency during continuous action: Performance is more important than action-feedback association[J]. PLOS ONE, 2015, 10(4): e0125226. DOI: 10.1371/journal.pone.0125226.

[46] ZAMFIRESCU-PEREIRA J D, WONG R Y, HARTMANN B, et al. Why Johnny can’t prompt: How non-AI experts try (and fail) to design LLM prompts[C]//Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. New York: Association for Computing Machinery, 2023: 1-21. DOI: 10.1145/3544548.3581388.

[47] DIETVORST B J, SIMMONS J P, MASSEY C. Algorithm aversion: People erroneously avoid algorithms after seeing them err[J]. Journal of Experimental Psychology: General, 2015, 144(1): 114-126. DOI: 10.1037/xge0000033.

[48] JAHANI E, MANNING B S, ZHANG J, et al. Prompt adaptation as a dynamic complement in generative AI systems[J/OL]. Information Systems Research, 2026[2026-09-04]. DOI: 10.1287/isre.2025.2029.

[49] OVIATT S. Human-centered design meets cognitive load theory: Designing interfaces that help people think[C]//Proceedings of the 14th ACM International Conference on Multimedia. New York: Association for Computing Machinery, 2006: 871-880. DOI: 10.1145/1180639.1180831.

[50] WEN W. Does delay in feedback diminish sense of agency? A review[J]. Consciousness and Cognition, 2019, 73: 102759. DOI: 10.1016/j.concog.2019.05.007.