基于活动理论的AIGC观展交互设计研究——以“趣迹”APP为例
Research on AIGC Exhibition Interaction Design Based on Activity Theory—Taking “Quji” APP as an Example
DOI: 10.12677/sheji.2026.111001, PDF,   
作者: 胡 琪:华东理工大学艺术设计与传媒学院,上海
关键词: AIGC活动理论观展体验多模态交互数字资产AIGC Activity Theory Exhibition Experience Multimodal Interaction Digital Assets
摘要: 青年群体在各类展览的参观过程中,普遍面临“看不懂”“没意思”与“留不住”的体验断层,严重制约了展览内容的传播效能。文章引入活动理论与数字叙事视角,针对观展交互中的主体能力不足与工具效能滞后等矛盾,构建了AIGC赋能下的交互系统模型。在此基础上,设计了“趣迹”App:利用计算机视觉与大语言模型技术,将晦涩的展品信息实时转化为通俗的知识卡片,降低认知门槛;通过语音合成技术赋予展品拟人化角色,以第一人称叙事重塑交互规则,增强情感共鸣;引入视觉隐喻与收藏机制,将碎片化的观展体验整合为可流动的数字记忆。设计方案通过多模态技术的介入,有效优化了从感知到记忆的观展全流程,为展览场景的活态传承提供了新的实践路径。
Abstract: During visits to various exhibitions, young groups generally face experiential disconnects characterized by “incomprehension”, “lack of interest”, and “inability to retain memories”, which severely restrict the dissemination efficiency of exhibition content. This paper introduces the perspectives of Activity Theory and Digital Storytelling to address contradictions such as insufficient subject capabilities and lagging tool efficacy in exhibition interactions, constructing an interaction system model empowered by AIGC. On this basis, the “Quji” App was designed: it utilizes computer vision and large language model technologies to translate obscure exhibit information into accessible knowledge cards in real-time, thereby lowering the cognitive threshold; it endows exhibits with anthropomorphic roles through speech synthesis technology, reshaping interaction rules with first-person narratives to enhance emotional resonance; and it introduces visual metaphors and collection mechanisms to integrate fragmented exhibition experiences into fluid digital memories. By intervening with multimodal technologies, this design scheme effectively optimizes the entire exhibition process from perception to memory, providing a new practical path for the living inheritance of exhibition scenes.
文章引用:胡琪. 基于活动理论的AIGC观展交互设计研究——以“趣迹”APP为例[J]. 设计进展, 2026, 11(1): 1-11. https://doi.org/10.12677/sheji.2026.111001

参考文献

[1] 中国国家博物馆. 2024年中国国家博物馆数据报告[EB/OL].
https://www.chnmuseum.cn/shxg/zlxz/pdfdown/202503/t20250320_271313.shtml, 2025-03-20.
[2] 孙芮英. 首都博物馆AI智慧导览技术的公众服务应用研究[J]. 中国博物馆, 2025(4): 96-103.
[3] 孔雯莉, 郝琳霰, 徐浩, 等. 生成式人工智能在博物馆中的应用实践与思考[J]. 中国信息化, 2025(10): 70-72.
[4] 夏沁宁. 认知负荷下博物馆展示的多感官设计研究[D]: [硕士学位论文]. 南京: 南京航空航天大学, 2023.
[5] Vygotsky, L.S. (1978) Mind and Society. Harvard University Press.
[6] Leontev, A.N. (1978) Activity, Consciousness, and Personality. Prentice Hall.
[7] 王翀, 周龙飞, 张祖耀. 基于活动理论的听障骑手AI语音交互产品设计[J]. 设计, 2023, 36(9): 138-141.
[8] 刘芳. 物质文化遗产数字叙事的理论与应用模式研究[J]. 东南文化, 2025(1): 22-29.
[9] Tamah Al-Shammari, D.E. (2025) My Heritage Companion: An AI-Driven Mobile Experience for Visual Storytelling. Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization, New York, 16-19 June 2025, 442-448. [Google Scholar] [CrossRef
[10] 母峻彰. 数字化背景下博物馆智能情感转译设计方法研究[D]: [硕士学位论文]. 无锡: 江南大学, 2024.
[11] 伍蕾, 王亦禾, 伍蓓. 数字沉浸式场景下游客临场感的形成机理——以扬州中国大运河博物馆为例[J/OL]. 中南林业科技大学学报(社会科学版), 1-12.
https://link.cnki.net/urlid/43.1478.F.20251022.1407.006, 2025-11-30.
[12] Moortheeswari, S.K., Archaeologist, D.S. and George, F.S. (2015) Telling Stories with Museum Objects—Reflection on Interpretation. Fort Museum, Archaeological Survey of India, 1-8.
[13] 王文琪. 智能语音助手的拟人化设计对用户持续使用意愿的影响研究[D]: [硕士学位论文]. 上海: 上海外国语大学, 2024.
[14] 田家荣. 基于博物馆馆藏文物学习的游戏化设计研究[D]: [硕士学位论文]. 北京: 北京服装学院, 2024.
[15] 张宇. AI赋能下用户生成内容如何重塑博物馆文化遗产叙事——基于参与式文化理论的研究[J]. 画廊, 2025(Z2): 51-53.