近年來，建築、工程與營造(AEC)行業經歷前所未有的數位化轉型，特別是生成式人工智慧(GAI)和建築資訊模型(BIM)技術的廣泛應用，為行業帶來巨大的變革。本研究深入探討GAI在建築設計領域的應用及其與BIM技術的整合，旨在揭示這些先進技術如何推動設計流程的創新和最佳化。
本論文探討GAI技術、文生圖像、文本轉換、以及網路爬蟲技術在室內設計的應用，從概念到實現的過程，聚焦在GAI如何提高設計效率、促進創新思維、以及強化設計方案溝通中的潛力和挑戰。
研究實驗顯示，GAI與BIM的結合不僅提升設計過程的效率，還增加設計方案的多樣性和創新性。例如，使用GAI工具如Stable Diffusion在網頁端整合，使得設計師和業主能夠以更直觀的方式進行溝通，並快速反覆修改設計方案。同時，整合GAI工具使設計師能夠迅速將創意轉化為詳盡的3D模型。
本研究探討從“湧現到實現”的設計過程，基於BIM與GAI應用的設計協作。以室內設計流程為例，展示GAI在設計階段的關鍵作用，並驗證這一過程的加速效果。研究成果顯示，GAI加BIM資訊重組通過網路爬蟲和標籤對齊的技術，提高計劃資訊的收集和管理效率。GAI在提升設計效率和創意表現的潛力，結合BIM技術的平台在數據管理和透明化方面提供效益，然而，技術的應用仍面臨諸多問題和人工協作的不可替代性等挑戰，工作流程也需隨之調整，以適應新技術的導入。

In recent years, the Architecture, Engineering, and Construction (AEC) industry has experienced significant digital transformation through the adoption of Generative Artificial Intelligence (GAI) and Building Information Modeling (BIM). This study explores the integration of GAI in architectural design with BIM, focusing on how these technologies drive innovation and optimize design processes. It examines how GAI technologies, such as text-to-image and web crawling, accelerate the transition from concept to realization in interior design. The study also addresses the potential and challenges of GAI in enhancing design efficiency, promoting innovation, and improving communication.
The results indicate that combining GAI and BIM improves design efficiency and increases the diversity and innovation of proposals. For example, tools like Stable Diffusion and ComfyUI facilitate intuitive communication and quick iteration between designers and clients. Additionally, GAI enables rapid transformation of ideas into detailed 3D models. However, there are limitations, such as inconsistent data quality and a disconnect between generated content and the real world. Moreover, GAI cannot fully replace human resources and traditional design processes involving collaboration and site management. Challenges in technology integration include the need for interdisciplinary knowledge, compatibility issues, and privacy and legal considerations.
This study underscores the importance of human-centered design in the digital transformation of the AEC field. By integrating GAI and BIM, future architectural design processes can become more efficient, sustainable, and aligned with user needs and market dynamics. Future research will explore overcoming current technological limitations and better integrating AI into design and construction processes to achieve comprehensive industry innovation.

Abd Hamid, A. B., & Embi, M. R. (2016). Review on application of Building Information Modelling in interior design industry. MATEC Web of Conferences,
AbouHamad, M., & Abu-Hamd, M. (2019). Framework for construction system selection based on life cycle cost and sustainability assessment. Journal of Cleaner Production, 241, 118397.
Bengesi, S., El-Sayed, H., Sarker, M. K., Houkpati, Y., Irungu, J., & Oladunni, T. (2024). Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers. IEEE Access.
Caixeta, M. C. B. F., Tzortzopoulos, P., & Fabricio, M. M. (2019). User involvement in building design–a state-of-the-art review. PosFAUUSP, 26(48), e151752-e151752.
Chen, X., Chang-Richards, A., Ling, F. Y. Y., Yiu, T. W., Pelosi, A., & Yang, N. (2024). Digital technologies in the AEC sector: a comparative study of digital competence among industry practitioners. International Journal of Construction Management, 1-14.
comfyanonymous. (2023). ComfyUI. https://github.com/comfyanonymous/ComfyUI
Documents, B. A. C. (2022). Introducing AIA Contract Documents’ 2022 BIM Documents.
Eastman, C., & Computing, D. (2001). New directions in design cognition: studies of representation and recall. In Design knowing and learning: Cognition in design education (pp. 147-198). Elsevier.
EN, C. (2011). 15978—Sustainability of Construction Works—Assessment of Environmental Performance of Buildings—Calculation Method. European Standards: Brussels, Belgium.
Esfahani, M. E., Rausch, C., Sharif, M. M., Chen, Q., Haas, C., & Adey, B. T. (2021). Quantitative investigation on the accuracy and precision of Scan-to-BIM under different modelling scenarios. Automation in Construction, 126, 103686.
Gero, J. S. (1990). Design prototypes: a knowledge representation schema for design. AI magazine, 11(4), 26-26.
Gero, J. S. (2000). Computational models of innovative and creative design processes. Technological forecasting and social change, 64(2-3), 183-196.
GhaffarianHoseini, A., Zhang, T., Nwadigo, O., GhaffarianHoseini, A., Naismith, N., Tookey, J., & Raahemifar, K. (2017). Application of nD BIM Integrated Knowledge-based Building Management System (BIM-IKBMS) for inspecting post-construction energy efficiency. Renewable and Sustainable Energy Reviews, 72, 935-949.
Grauman, K., Westbury, A., Torresani, L., Kitani, K., Malik, J., Afouras, T., Ashutosh, K., Baiyya, V., Bansal, S., & Boote, B. (2024). Ego-exo4d: Understanding skilled human activity from first-and third-person perspectives. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,
Hettithanthri, U., Hansen, P., & Munasinghe, H. (2023). Exploring the architectural design process assisted in conventional design studio: a systematic literature review. International Journal of Technology and Design Education, 33(5), 1835-1859.
Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. arXiv:2006.11239. Retrieved June 01, 2020, from https://ui.adsabs.harvard.edu/abs/2020arXiv200611239H
Hong, S.-H., Lee, S.-K., & Yu, J.-H. (2019). Automated management of green building material information using web crawling and ontology. Automation in Construction, 102, 230-244.
Huang, Y. (2024). Latent Auto-recursive Composition Engine.
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020). Scaling Laws for Neural Language Models. arXiv:2001.08361. Retrieved January 01, 2020, from https://ui.adsabs.harvard.edu/abs/2020arXiv200108361K
Keita, M., Hamidouche, W., Eutamene, H. B., Hadid, A., & Taleb-Ahmed, A. (2024). Bi-LORA: A Vision-Language Approach for Synthetic Image Detection. arXiv preprint arXiv:2404.01959.
Li, X., Shen, G. Q., Wu, P., & Yue, T. (2019). Integrating building information modeling and prefabrication housing production. Automation in Construction, 100, 46-60.
Li, Z., Müller, T., Evans, A., Taylor, R. H., Unberath, M., Liu, M.-Y., & Lin, C.-H. (2023). Neuralangelo: High-fidelity neural surface reconstruction. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,
Liu, J., Xu, D., Hyyppä, J., & Liang, Y. (2021). A survey of applications with combined BIM and 3D laser scanning in the life cycle of buildings. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 5627-5637.
Lu, K., Jiang, X., Yu, J., Tam, V. W. Y., & Skitmore, M. (2021). Integration of life cycle assessment and life cycle cost using building information modeling: A critical review. Journal of Cleaner Production, 285, 125438. https://doi.org/10.1016/j.jclepro.2020.125438
Nwodo, M. N., & Anumba, C. J. (2019). A review of life cycle assessment of buildings using a systematic approach. Building and Environment, 162, 106290.
Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2023). Robust speech recognition via large-scale weak supervision. International conference on machine learning,
Segara, S., Li, Q. J., Gallotta, A., Wang, Y., Gosling, J., & Rezgui, Y. (2024). A taxonomy of circularity indicators for the built environment: Integrating circularity through the Royal Institute of British architects (RIBA) plan of work. Journal of Cleaner Production, 141429.
Suwa, M., Gero, J., & Purcell, T. (2000). Unexpected discoveries and S-invention of design requirements: important vehicles for a design process. Design studies, 21(6), 539-567.
Talib, M., Al-Noori, A. H., & Suad, J. (2024). YOLOv8-CAB: Improved YOLOv8 for Real-time object detection. Karbala International Journal of Modern Science, 10(1), 5.
Wang, J., Wang, X., Shou, W., & Xu, B. (2014). Integrating BIM and augmented reality for interactive architectural visualisation. Construction Innovation, 14(4), 453-476.
Wang, K., Guo, F., Zhang, C., Hao, J., & Schaefer, D. (2022). Digital technology in architecture, engineering, and construction (AEC) industry: Research trends and practical status toward construction 4.0. Construction Research Congress 2022,
Wang, Q., Guo, J., & Kim, M.-K. (2019). An application oriented scan-to-BIM framework. Remote Sensing, 11(3), 365.
Wang, T., & Chen, H.-M. (2023). Integration of building information modeling and project management in construction project life cycle. Automation in Construction, 150, 104832.
Watts, R. D. (1966). The elements of design. The design method, 85-95.
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., & Metzler, D. (2022). Emergent abilities of large language models. arXiv preprint arXiv:2206.07682.
Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., Chi, E. H., Hashimoto, T., Vinyals, O., Liang, P., Dean, J., & Fedus, W. (2022). Emergent Abilities of Large Language Models. arXiv:2206.07682. Retrieved June 01, 2022, from https://ui.adsabs.harvard.edu/abs/2022arXiv220607682W
Yi, H., & Wang, W. (2016). The Application of Building Information Modeling in Interior Design. 2016 International Conference on Sensor Network and Computer Engineering,
吳典育. (2018). BIM整合操作運用之設計流程研究 國立成功大學]. 臺灣博碩士論文知識加值系統. 台南市. https://hdl.handle.net/11296/3vur7f
鄭泰昇. (2016). BIM雲端作業之先導應用與AEC產業4.0升級策略規劃研究.
鄭泰昇. (2020). AI 人工智慧輔助 BIM 衍生設計之研究.