隨著BIM技術在台灣建築產業中的普及，BIM的應用已從單純的設計階段建模逐漸擴展到全面命週期的介入。特別是在維運管理階段，BIM的介入有機會解決高人力成本和傳統管理方法限制的挑戰。本研究動機旨在探索智慧化技術與BIM結合的新策略，以改善複雜環境中的人流管理效率和安全性。
由於在傳統的設施管理（FM）中，管理多採取被動的方式，往往只能在問題出現後進行應對，此種方式在動態變化的人流管理中顯得效率低下，且難以預測和防範潛在問題。為了突破這一窠臼，本研究探索了一個主動式的人流管理新模式，旨在透過建築資訊模型（BIM）和人工智能（AI）技術等多個領域的結合應用下，來提升人員監控管理與環境安全管理的自動性、靈活性和智能性，使管理者能夠主動應對各種場域狀況，提高管理效率和安全性。基於這個主動式BIM的概念，本研究建立了基於人流的建築維運管理情境，透過整合並聚焦於涵構察覺、數位雙生與智能管理三大構面，提出一套主動式場域人流管理系統(以下簡稱本系統)的流程與實踐。
為了驗證本系統的實際具體操作與運作過程的效果，本研究以國立成功大學的數位智造工坊作為提供複雜且動態人流情境的示範場域。這個工坊提供了一個充滿複雜且動態人流情境的環境，適合作為實驗的場域。在實作過程中的涵構察覺方面，本研究成功地將工坊中CCTV監視器所收集的影像紀錄，運用AI影像辨識軟體自動分析人流情境的分布、行為與編號，利用影像校正技術將人流分布位置進行空間座標化。並將這些資訊整合後以平面視圖視覺化呈現，使管理者能夠快速檢測和空間放樣，實現便利且自動化的場域人流涵構資料獲取，展示了人流情境識讀的智能化可能性。
在數位雙生方面，本研究成功地將工坊的BIM場域模型進行空間性的元資料來完成雲端BIM模型的空間放樣，並通過APS雲端平台與前後端程式的應用，實現連續人流涵構資訊的即時更新和同步，整合形成一套人流的實時建築資訊模型。系統以網頁平台形式結合設計好的使用者介面，提升即時性反饋的使用互動體驗，使管理者能夠以空間視覺化的方式隨時掌握場域的即時狀況。
在智能管理方面，本研究成功地運用網頁編程和資料視覺化等技術來投遞多項管理服務功能，不僅凸顯了人的空間比例與行為分類來協助閱讀資訊，還開發了一個能夠即時自定義區域參數設置的區域感知提醒系統。此感知系統能靈活調整且自動化地判釋人流情境，並提供多層次的管理等級，包括禁止、管制與預設區域，來應對工坊內常見的不同狀況作出合適的反饋。更進一步地，此感知系統還提供事件回顧功能，除了幫助管理者分析場域的歷史動態，協助管理決策，還能透過記錄回顧來以不同事件獲得時間錨點，以利管理者查閱CCTV能過濾空白資訊，增進事件追查的管理效率。
綜上所述，本研究的實作成果表現了主動式場域人流管理系統在提升維運管理效率、降低安全風險及減少對人力資源依賴方面的實際應用價值。通過本系統的實踐和應用，不僅確立了涵構察覺、數位雙生和智能管理三大構面的整合與組成，更是成功地展示了一種主動式的人流管理新模式，為智慧化的建築維運揭櫫了一個嶄新的典範轉移。

With the widespread adoption of Building Information Modeling (BIM) technology in Taiwan's construction industry, its application has gradually expanded from simple design-stage modeling to comprehensive lifecycle involvement. Especially during the operations and maintenance (O&M) phase, BIM has the potential to address challenges related to high labor costs and the limitations of traditional management methods. This study aims to explore new strategies combining intelligent technologies with BIM to improve the efficiency and safety of crowd management in complex environments.

In traditional facility management (FM), management often adopts a passive approach, responding to problems only after they arise. This approach is inefficient in dynamically changing crowd management scenarios and fails to predict and prevent potential issues. To overcome this limitation, this study explores a proactive crowd management model, aiming to enhance the automation, flexibility, and intelligence of personnel monitoring and environmental safety management through the combined application of BIM and artificial intelligence (AI) technologies. Based on the concept of proactive BIM, this study establishes a crowd-based building O&M management scenario by integrating and focusing on three major components: awareness, digital twin, and intelligent management, proposing a set of processes and practices for a proactive field crowd management system (hereinafter referred to as the system).

To verify the practical operation and effectiveness of this system, this study uses the Digital Manufacturing Workshop at National Cheng Kung University as a demonstration site providing complex and dynamic crowd scenarios. This workshop offers an environment filled with complex and dynamic crowd interactions, making it suitable for experimental purposes. In the implementation process, regarding context awareness, the study successfully uses AI image recognition software to automatically analyze the distribution, behavior, and identification of crowd scenarios based on the continuous CCTV footage collected over a week. These analyses are spatially calibrated and visualized in a planar view, enabling managers to quickly detect and map spaces, achieving convenient and automated acquisition of crowd awareness data, demonstrating the potential for intelligent interpretation of crowd scenarios.

In terms of digital twin, the study successfully completes the spatial sampling of the workshop's BIM field model by integrating spatial metadata and utilizing the APS cloud platform and frontend/backend applications to achieve real-time updates and synchronization of continuous crowd awareness information. This integration forms a real-time building information model (BIM) of crowd data, which, through a web platform with a well-designed user interface, enhances real-time interactive feedback, allowing managers to visualize and grasp the real-time status of the field.

For intelligent management, the study utilizes web programming and data visualization techniques to deliver multiple management service functions. These functions not only highlight the spatial proportions and behavior classifications of people to assist in information reading but also develop an area awareness alert system with real-time customizable area parameters. This awareness system can flexibly and automatically interpret crowd scenarios and provide multi-level management services, including prohibited, controlled, and preset areas, to respond appropriately to different situations commonly found in the workshop. Furthermore, this system offers an event review function that helps managers analyze historical dynamics of the field, assist in management decisions, and filter out irrelevant information during CCTV review, improving the efficiency of event traceability.

In summary, the practical results of this study demonstrate the actual application value of the proactive field crowd management system in enhancing O&M management efficiency, reducing safety risks, and decreasing reliance on human resources. Through the implementation and application of this system, the integration and composition of the three major components—awareness, digital twin, and intelligent management—are established, successfully showcasing a new proactive crowd management model and setting a new paradigm for intelligent building O&M.

英文參考文獻
[1] Alirezaie, M., Renoux, J., Köckemann, U., Kristoffersson, A., Karlsson, L., Blomqvist, E., ... & Loutfi, A. (2017). An ontology-based context-aware system for smart homes: E-care@ home. Sensors, 17(7), 1586.
[2] Bardram, J. E., & Hansen, T. R. (2004, November). The AWARE architecture: supporting context-mediated social awareness in mobile cooperation. In Proceedings of the 2004 ACM conference on Computer supported cooperative work (pp. 192-201).
[3] Bellavista, P., Corradi, A., Fanelli, M., & Foschini, L. (2012). A survey of context data distribution for mobile ubiquitous systems. ACM computing surveys (CSUR), 44(4), 1-45.
[4] Bolchini, C., Curino, C. A., Quintarelli, E., Schreiber, F. A., & Tanca, L. (2007). A data-oriented survey of context models. ACM Sigmod Record, 36(4), 19-26.
[5] Buchanan, B. G., & Smith, R. G. (1988). Fundamentals of expert systems. Annual review of computer science, 3(1), 23-58.
[6] Childe, S. J., Maull, R. S., & Bennett, J. (1994). Frameworks for understanding business process re‐engineering. International Journal of operations & production management, 14(12), 22-34.
[7] Clarkson, B. B. P. (1999). Environmental audio-visual context awareness (Doctoral dissertation, Massachusetts Institute of Technology).
[8] Dey, A. K. (2001). Understanding and using context. Personal and ubiquitous computing, 5, 4-7.
[9] Dey, A. K., Salber, D., Abowd, G. D., & Futakawa, M. (1999, October). The conference assistant: Combining context-awareness with wearable computing. In Digest of Papers. Third International Symposium on Wearable Computers (pp. 21-28). IEEE.
[10] Främling, K., Holmström, J., Ala-Risku, T., & Kärkkäinen, M. (2003). Product agents for handling information about physical objects. Report of Laboratory of information processing science series B, TKO-B, 153(03).
[11] Gorry, G. A., & Scott Morton, M. S. (1971). A framework for management information systems.
[12] Grieves, M. (2006). Product lifecycle management: driving the next generation of lean thinking. (No Title).
[13] Grifoni, P., D’Ulizia, A., & Ferri, F. (2018). Context-awareness in location based services in the big data era. Mobile Big Data: A Roadmap from Models to Technologies, 85-127.
[14] Guerra-Zubiaga, D., Kuts, V., Mahmood, K., Bondar, A., Nasajpour-Esfahani, N., & Otto, T. (2021). An approach to develop a digital twin for industry 4.0 systems: manufacturing automation case studies. International Journal of Computer Integrated Manufacturing, 34(9), 933-949.
[15] Hinze, A., & Buchanan, G. (2005). Context-awareness in mobile tourist information systems: challenges for user interaction. In International Workshop on Context in Mobile HCI at the Seventh International Conference on Human Computer Interaction with Mobile Devices and Services.
[16] Iqbal, F., Altaf, A., Waris, Z., Aray, D. G., Flores, M. A. L., Díez, I. D. L. T., & Ashraf, I. (2023). Blockchain-Modeled Edge-Computing-Based Smart Home Monitoring System with Energy Usage Prediction. Sensors, 23(11), 5263.
[17] Kaltz, J. W., Ziegler, J., & Lohmann, S. (2005). Context-aware web engineering: Modeling and applications. Revue d'Intelligence Artificielle: RIA, 19(3), 439-458.
[18] Keen, P. G. (1980). Decision support systems: a research perspective. Decision Support Systems: Issues and Challenges, International Institute for Applied Systems Analysis (IIASA) Proceedings Series, 11, 23-27.
[19] Khajavi, S. H., Motlagh, N. H., Jaribion, A., Werner, L. C., & Holmström, J. (2019). Digital twin: vision, benefits, boundaries, and creation for buildings. IEEE access, 7, 147406-147419.
[20] Kortuem, G., Kawsar, F., Sundramoorthy, V., & Fitton, D. (2009). Smart objects as building blocks for the internet of things. IEEE internet computing, 14(1), 44-51.
[21] Lee, J., Lapira, E., Bagheri, B., & Kao, H. A. (2013). Recent advances and trends in predictive manufacturing systems in big data environment. Manufacturing letters, 1(1), 38-41.
[22] Liu, H., & Wang, L. (2021). Collision-free human-robot collaboration based on context awareness. Robotics and Computer-Integrated Manufacturing, 67, 101997.
[23] Ljungstrand, P. (2001). Context awareness and mobile phones. Personal and ubiquitous computing, 5, 58-61.
[24] Long, S., Kooper, R., Abowd, G. D., & Atkeson, C. G. (1996, November). Rapid prototyping of mobile context-aware applications: The cyberguide case study. In Proceedings of the 2nd annual international conference on Mobile computing and networking (pp. 97-107).
[25] Lu, Q., Parlikad, A. K., Woodall, P., Don Ranasinghe, G., Xie, X., Liang, Z., ... & Schooling, J. (2020). Developing a digital twin at building and city levels: Case study of West Cambridge campus. Journal of Management in Engineering, 36(3), 05020004.
[26] Mayer-Schönberger, V., & Cukier, K. (2013). Big data: A revolution that will transform how we live, work, and think. Houghton Mifflin Harcourt.
[27] Mettouris, C., & Papadopoulos, G. A. (2010, June). Exploiting context in location-based information systems. In 2010 10th IEEE International Conference on Computer and Information Technology (pp. 1593-1598). IEEE.
[28] Musumba, G. W., & Nyongesa, H. O. (2013). Context awareness in mobile computing: A review.
[29] Naya, F., Noma, H., Ohmura, R., & Kogure, K. (2005, October). Bluetooth-based indoor proximity sensing for nursing context awareness. In Ninth IEEE International Symposium on Wearable Computers (ISWC'05) (pp. 212-213). IEEE.
[30] Pantsar-Syväniemi, S., Simula, K., & Ovaska, E. (2010, June). Context-awareness in smart spaces. In The IEEE symposium on Computers and Communications (pp. 1023-1028). IEEE.
[31] Perera, C., Zaslavsky, A., Christen, P., & Georgakopoulos, D. (2013). Context aware computing for the internet of things: A survey. IEEE communications surveys & tutorials, 16(1), 414-454.
[32] Rafsanjani, H. N., & Nabizadeh, A. H. (2023). Towards digital architecture, engineering, and construction (AEC) industry through virtual design and construction (VDC) and digital twin. Energy and Built Environment, 4(2), 169-178.
[33] Rosenberger, P., & Gerhard, D. (2018). Context-awareness in industrial applications: definition, classification and use case. Procedia CIRP, 72, 1172-1177.
[34] Sahoo, K. C., & Pati, U. C. (2017, May). IoT based intrusion detection system using PIR sensor. In 2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT) (pp. 1641-1645). IEEE.
[35] Schilit, B., Adams, N., & Want, R. (1994, December). Context-aware computing applications. In 1994 first workshop on mobile computing systems and applications (pp. 85-90). IEEE.
[36] Schmidt, A. (2003). Ubiquitous computing-computing in context. Lancaster University (United Kingdom).
[37] Shafto, M., Conroy, M., Doyle, R., Glaessgen, E., Kemp, C., LeMoigne, J., & Wang, L. (2010). Draft modeling, simulation, information technology & processing roadmap. Technology area, 11, 1-32.
[38] Singh, M., Fuenmayor, E., Hinchy, E. P., Qiao, Y., Murray, N., & Devine, D. (2021). Digital twin: Origin to future. Applied System Innovation, 4(2), 36.

中文參考文獻
[1] 內政部建築研究所研究報告，王榮進，沈揚庭（2020）。應用人工智慧科技提升建築物維運管理效益之研究。內政部建築研究所協同研究
[2] 王宓琦, 蔡珵宜, 林瑞浤, & 沈揚庭. (2022). 基於數位雙生適地性服務的擴增實境空間數據可視化維運管理. 物業管理學會論文集, 61-66.
[3] 沈揚庭, 楊佳恩, & 廖士豪. (2020). 整合建築資訊模型與涵構察覺技術發展可調適性維運管理系統. 建築學報, (113), 47-66.
[4] 楊佳恩. (2018). 建築資訊模型雲端視覺化系統應用於智慧維運之研究. 逢甲大學建築碩士在職學位學程學位論文, 2018, 1-87.
[5] 廖士豪, 沈揚庭, & 楊佳恩. (2021). 智慧維運:涵構察覺導向主動調適建築維運管理 .物業管理學報,(秋季號十二卷第二期),1-12
[6] 廖士豪. (2020). 整合 AI 電腦視覺與 BIM 電子圍籬發展智慧維運平台. 逢甲大學建築碩士學位學程學位論文, 2020, 1-92.

圖片來源
[1] AwarePhone和AwareMedia : https://www.bardram.net/awaremedia/
[2] Corify Care S.L. : https://www.itaca.upv.es/corify-care-sl/

網路文獻
[1] AwarePhone和AwareMedia 網路文獻: https://www.bardram.net/awaremedia/
[2] Corify Care S.L. 網路文獻: https://www.itaca.upv.es/corify-care-sl/
[3] 應用人工智慧科技提升建築物維運管理效益之研究https://www.abri.gov.tw/News_Content_Table.aspx?n=807&s=214284