臺灣博碩士論文加值系統

本研究旨在開發基於對話式之建築資訊傳遞系統。如今，設施管理平台已廣泛用於建築物生命週期的設施維護階段。然而，存儲於設施管理平台中的BIM模型資訊量是複雜而且龐大的，並且使用者每次開啟設施管理平台時，通常需要花費大量的時間來等待模型載入。這些因素可能會影響設施管理員在設施管理平台上檢索特定模型資訊的效率和使用者體驗。為了解決這些問題，本研究提出了一個基於對話式之建築資訊傳遞系統，該系統包含五個模組：決策機制，設備數據集模組，意圖分析，數據收集和知識庫。首先，基於TF-IDF和餘弦相似度的決策機制、設備數據集和意圖分析，主要用於分析使用者之查詢意圖。其次，數據收集和知識庫主要用於處理建築模型資訊（BIM）數據。知識庫包括一個自行開發的汲取器，用於結構化數據以進行後續分析。我們使用Line來作為平台，並通過BIM軟體Revit來收集模型資料。我們透過可行性測試來驗證該系統的可行性，並與位於臺灣新北市樹林藝文行政中心合作，進行現場測試來分析該系統與舊有操作方法的效率比較。結果表明，該方法改變了使用者與設施管理平台之間的傳統互動方式，新的互動模式不僅為設施管理員提供了完善的用戶體驗，而且使檢索效率提高了近兩倍。

The aim of this study is to develop a conversation-based building information delivery system for facility management. Facility management platforms are widely used in the facility maintenance phase of the building life cycle. However, a large amount of complex building information is stored in the facility management platform, and it often takes a significant amount of time to load the model when the facility management platform is activated. These factors may affect the efficiency and user experience of facility managers in retrieving specific model information on the facility management platform. Also, the heavy platform makes the related personnel hard to retrieve the data during conducting the investigation on-site since the platform can only be run on a PC or laptop. To tackle such problems, a conversation-based delivery system was proposed with five modules: decision mechanism, equipment dataset module, intent analysis, data collection, and knowledge base. First, the decision mechanism, equipment dataset, and intent analysis were established based on Term Frequency–Inverse Document Frequency (TF-IDF) and cosine similarity, which is mainly used to analyze the user's query intent. Second, the data collection and knowledgebase were built to primarily process building information modeling (BIM) data. The knowledge base includes a self-devel-oped extractor to structure the data for subsequent analysis. For implementation, LINE, a communication software with the largest market share in Taiwan, was used as a platform, and data was collected through Revit, a BIM software. This system was validated through a feasibility test and field test at the Shulin Arts Comprehensive Administration Building of the New Taipei City Government in Taiwan. The results showed that the proposed method changes the traditional interaction mode between the user and the facility management platform. The new interactive mode not only provides a friendly user experience for facility managers but also decreases time spent on retrieval by 45.7%.

Table of Contents
Abstract....................................................................... I
Acknowledgements .............................................................................. II
Table of Contents ............................................................................. III
List of Figures .............................................................................. VI
List of Tables ............................................................................. VII
1. Introduction ............................................................... 1
1.1 Development of traditional facility management platform ................... 1
1.2 Inefficient information retrieval from BIM models ......................... 1
1.3 New solutions for the facility management platform ........................ 2
2. Literature Review .......................................................... 2
2.1 BIM in facility management ................................................ 3
2.2 Challenges in retrieving BIM information .................................. 4
2.3 Applications of ontology in BIM ........................................... 5
2.4 Dialogue-based information delivery system in various fields .............. 6
3. Objective .................................................................. 8
4. Proposed Approach for Information Delivery System .......................... 9
4.1. System architecture ...................................................... 9
4.2. Decision mechanism ...................................................... 10
Rule-based approach .......................................................... 10
Retrieval-based approach ..................................................... 11
4.3. Equipment dataset module ................................................ 12
Dataset definition ........................................................... 12
User interview for defining the search scope of the system ................... 13
4.4. Intent analysis module .................................................. 14
Keyword extraction ........................................................... 14
Intent corpus ................................................................ 15
TF-IDF method for similarity calculations .................................... 16
Ranking and matching ......................................................... 17
4.5. Data collection module................................................... 19
4.6. Knowledge base .......................................................... 19
5. Implementation ............................................................ 20
5.1 Overview of the conversation-based delivery system ....................... 21
5.2 Decision mechanism ....................................................... 21
5.3 Equipment dataset ........................................................ 23
5.4 Intention analysis........................................................ 24
5.5 Data collection........................................................... 27
5.6 Knowledge base ........................................................... 27
Data preprocessor ............................................................ 28
Data extractor ............................................................... 28
Ontology builder ............................................................. 29
6. Validation ................................................................ 31
6.1 Feasibility test ......................................................... 31
Design of the feasibility test ............................................... 32
Results of the feasibility test .............................................. 33
6.2 Field test ............................................................... 34
Design of the field test ..................................................... 34
Result of field test ......................................................... 35
7. Discussion ................................................................ 40
7.1. Contributions ........................................................... 41
Simple interface and easy-to-use conversation-based delivery system .......... 41
Personal assistant for providing retrieval of BIM information ................ 41
Search engine based on ontological techniques................................. 41
Customized features and suitability for any BIM model ........................ 42
7.2. Limitations ............................................................. 42
Lack of machine learning algorithms .......................................... 42
High labor demand to maintain the corpus ..................................... 42
Mobile device size affects user experience ................................... 42
7.3. Potential Applications of the System .................................... 43
8. Conclusions ............................................................... 43
References ................................................................... 45

List of Figures
Figure 1. Conversation-based system architecture. ............................ 10
Figure 2. Clickable menu. .................................................... 11
Figure 3. User input panel. .................................................. 12
Figure 4. The architecture of the equipment dataset. ......................... 13
Figure 5. The content of the user interview questionnaire..................... 14
Figure 6. The keyword extraction process. .................................... 15
Figure 7. The ranking and matching process. .................................. 18
Figure 8. Schematic diagram of the ranking and matching process. ............. 18
Figure 9. The process of structuring BIM data. ............................... 20
Figure 10. Overview of the conversation-based delivery system. ............... 21
Figure 11. The main interface of the chatbot: (A) the message input bar and (B) the rich menu. ............................................................... 22
Figure 12. The three chatbot menus: (A) confirm template, (B) imagemap message, and (C) carousel template. ................................................... 23
Figure 13. Schematic diagram of automatically sending rule-based sentences.... 25
Figure 14. The intent analysis implementation. ............................... 27
Figure 15. The implementation of the knowledge base. ......................... 28
Figure 16. Implementation of the ontology framework. ......................... 30
Figure 17. Implementation of the individuals in the ontology framework. ...... 30
Figure 18. Implementation of the data reasoning. ............................. 31
Figure 19. Statistical results of the three methods. ......................... 40

List of Tables
Table 1. Equipment dataset for facility manager. ............................. 24
Table 2. Designed tasks for the feasibility test. ............................ 33
Table 3. Result of the feasibility test. ..................................... 34
Table 4. Designed tasks for the field test. .................................. 35
Table 5. Field test results for Method 1. .................................... 36
Table 6. Field test results for Method 2. .................................... 37
Table 7. Field test results for Method 3. .................................... 38

[1] W.L. Lee, M.H. Tsai, C.H. Yang, J.R. Juang, J.Y. Su, V3DM+: BIM interactive collaboration system for facility management, Vis. Eng. 4 (2016) 5. https://doi.org/10.1186/s40327-016-0035-9.
[2] L. Chen, P. Shi, Q. Tang, W. Liu, Q. Wu, Development and application of a specification-compliant highway tunnel facility management system based on BIM, Tunn. Undergr. Sp. Technol. 97 (2020) 103262. https://doi.org/10.1016/j.tust.2019.103262.
[3] Y.C. Lin, Y.C. Su, Y.P. Chen, Developing mobile BIM/2D barcode-based auto-mated facility management system, Sci. World J. (2014). https://doi.org/10.1155/2014/374735.
[4] M.H. Tsai, H.Y. Chan, L.Y. Liu, Conversation-based school building inspection support system, Appl. Sci. 10 (2020). https://doi.org/10.3390/app10113739.
[5] E.H.K. Wu, C.H. Lin, Y.Y. Ou, C.Z. Liu, W.K. Wang, C.Y. Chao, Advantages and constraints of a hybrid model K-12 E-Learning assistant chatbot, IEEE Ac-cess. 8 (2020) 77788–77801. https://doi.org/10.1109/ACCESS.2020.2988252.
[6] A. Akcamete, X. Liu, B. Akinci, J.H. Garrett, Integrating and Visualizing Maintenance and Repair Work Orders In BIM: Lessons Learned From A Proto-type, 11th International Conference On Construction Applications of Virtual Re-ality (CONVR, 2011), Weimar, Germany. November 3 - 4, 2011.
[7] B. Becerik-Gerber, F. Jazizadeh, N. Li, G. Calis, Application areas and data re-quirements for BIM-enabled facilities management, J. Constr. Eng. Manag. 138 (2012) 431–442. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000433.
[8] G. Kelly, M. Serginson, S. Lockley, N. Dawood, M. Kassem, BIM for facility management: a review and a case study investigating the value and challenges, in: Proceedings of the 13th International Conference on Construction Applica-tions of Virtual Reality (CONVR, 2013), London, United Kingdom. October 30 –31, 2013.
46
[9] S.K. Lee, H.K. An, J.H. Yu, An Extension of the Technology Acceptance Model for BIM-based FM, in: Proceedings of Construction Research Congress 2012: Construction Challenges in a Flat World, West Lafayette, Indiana. May 21-23, 2012.
[10] A. Akcamete, B. Akinci, J.H. Garrett, Potential utilization of building infor-mation models for planning maintenance activities, in: Proceedings of the Inter-national Conference on Computing in Civil and Building Engineering (ICCCBE, 2010), Nottingham, United Kingdom. June 30 - July 2, 2010.
[11] R. Edirisinghe, K.A. London, P. Kalutara, G. Aranda-Mena, Building infor-mation modelling for facility management: Are we there yet?, Eng. Constr. Ar-chit. Manag. 24 (2017) 1119–1154. https://doi.org/10.1108/ECAM-06-2016-0139.
[12] C.M. Eastman, P. Teicholz, R. Sacks, K. Liston, BIM Handbook: a Guide to Building Information Modeling for Owners, Managers, Architects, Engineers, Contractors, and Fabricators, 2nd ed. John Wiley and Sons, Hoboken, NJ, 2011.
[13] M. Yalcinkaya, V. Singh, Building information modeling (BIM) for facilities management-literature review and future needs, IFIP Adv. Inf. Commun. Tech-nol. 442 (2014) 1–10. https://doi.org/10.13140/RG.2.1.3052.5525.
[14] M. Kassem, G. Kelly, N. Dawood, M. Serginson, S. Lockley, BIM in facilities management applications: A case study of a large university complex, Built En-viron. Proj. Asset Manag. 5 (2015) 261–277. https://doi.org/10.1108/BEPAM-02-2014-0011.
[15] J.R. Lin, Z.Z.Hu, J.P. Zhang, F.Q. Yu, A Natural-Language-Based Approach to Intelligent Data Retrieval and Representation for Cloud BIM, Comput. Civ. In-frastruct. Eng. 31 (2016) 18–33. https://doi.org/10.1111/mice.12151.
[16] M.P. Nepal, S. Staub-French, R. Pottinger, J. Zhang, Ontology-based feature modeling for construction information extraction from a building information model, J. Comput. Civ. Eng. 27 (2013) 555–569. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000230.
47
[17] L. Zhang, R.R.A. Issa, Ontology-based partial building information model ex-traction, J. Comput. Civ. Eng. 27 (2013) 576–584. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000277.
[18] E. Ergen, B. Akinci, R. Sacks, Life-cycle data management of engineered-to-or-der components using radio frequency identification, Adv. Eng. Informatics. 21 (2007) 356–366. https://doi.org/10.1016/j.aei.2006.09.004.
[19] G. Chen, Y. Luo, A BIM and ontology-based intelligent application framework, in: Proceedings of 2016 IEEE Advanced Information Management, Communi-cates, Electronic and Automation Control Conference (IMCEC, 2016), Xi'an, China. October 3-5, 2016. https://doi.org/10.1109/IMCEC.2016.7867261.
[20] H. Liu, M. Lu, M. Al-Hussein, Ontology-based semantic approach for construc-tion-oriented quantity take-off from BIM models in the light-frame building in-dustry, Adv. Eng. Informatics. 30 (2016) 190–207. https://doi.org/10.1016/j.aei.2016.03.001.
[21] C. Zhang, J. Beetz, B. DeVries, BimSPARQL: Domain-specific functional SPARQL extensions for querying RDF building data, Semant. Web. 9 (2018) 829–855. https://doi.org/10.3233/SW-180297.
[22] E.A. Pärn, D.J. Edwards, Conceptualising the FinDD API plug-in: A study of BIM-FM integration, Autom. Constr. 80 (2017) 11–21. https://doi.org/10.1016/j.autcon.2017.03.015.
[23] A. Kiviniemi, R. Codinhoto, Challenges in the implementation of BIM for FM — case Manchester town hall complex, in: Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering (ICCCBE, 2014), Orlando, Florida. June 23-25, 2014.
[24] P. Katranuschkov, A. Gehre, R.J. Scherer, An ontology framework to access IFC model data, Electron. J. Inf. Technol. Constr. 8 (2003) 413–437.
[25] M. Niknam, S. Karshenas, A shared ontology approach to semantic representa-tion of BIM data, Autom. Constr. 80 (2017) 22–36. https://doi.org/10.1016/j.autcon.2017.03.013.
48
[26] S.K. Lee, K.R. Kim, J.H. Yu, BIM and ontology-based approach for building cost estimation, Autom. Constr. 41 (2014) 96–105. https://doi.org/10.1016/j.autcon.2013.10.020.
[27] W. Chen, K. Chen, J.C. Cheng, Towards an Ontology-based Approach for Infor-mation Interoperability Between BIM and Facility Management, in: Workshop of the European Group for Intelligent Computing in Engineering, 447-469. 2018. Springer. 10.1007/978-3-319-91638-5_25.
[28] H.H. Wang, F. Boukamp, T. Elghamrawy, Ontology-based approach to context representation and reasoning for managing context-sensitive construction infor-mation, J. Comput. Civ. Eng. 25 (2011) 331–346. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000094.
[29] S. Karshenas, M. Niknam, Ontology-based building information modeling, in: Processing of the 2013 ASCE International Workshop on Computing in Civil Engineering (IWCC, 2013), Los Angeles, California. June 23-25, 2013.
[30] L. Zhang, R.R.A. Issa, Development of IFC-based construction industry ontol-ogy for information retrieval from IFC models, EG-ICE 2011, Eur. Gr. Intell. Comput. Eng. (2014).
[31] Y.C. Lee, C.M. Eastman, W. Solihin, An ontology-based approach for develop-ing data exchange requirements and model views of building information model-ing, Adv. Eng. Informatics. 30 (2016) 354–367. https://doi.org/10.1016/j.aei.2016.04.008.
[32] S. Jiang, J. Zhang, Development of an ontology-based semantic retrieval method for construction project risk management, in: Proceedings of the 2013 Interna-tional Conference on Construction and Real Estate Management (ICCREM, 2013). Karlsruhe, Germany. October 10-11, 2013. https://doi.org/10.1061/9780784413135.070.
[33] M. Nuruzzaman, O.K. Hussain, IntelliBot: A Dialogue-based chatbot for the in-surance industry, Knowledge-Based Syst. 196 (2020) 105810. https://doi.org/10.1016/j.knosys.2020.105810.
49
[34] K.C. Lan, K.S. Ho, R.W. Pong Luk, D.S. Yeung, FNDS: A dialogue-based sys-tem for accessing digested financial news, J. Syst. Softw. 78 (2005) 180–193. https://doi.org/10.1016/j.jss.2004.12.020.
[35] K.J. Oh, D. Lee, B. Ko, H.J. Choi, A chatbot for psychiatric counseling in mental healthcare service based on emotional dialogue analysis and sentence generation, in: Proceedings of 18th IEEE International Conference on Mobile Data Manage-ment, (MDM, 2017). Daejeon, Korea. May 29 - June 1, 2017. https://doi.org/10.1109/MDM.2017.64.
[36] H. Al-Zubaide, A.A. Issa, OntBot: Ontology based ChatBot. 4th International Symposium on Innovation in Information and Communication Technology (ISI-ICT, 2011), Amman, Jordan. November 29 – December 01, 2011.
[37] A. Vegesna, P. Jain, D. Porwal, Ontology based Chatbot (For E-commerce Web-site), Int. J. Comput. Appl. 179 (2018) 51–55. https://doi.org/10.5120/ijca2018916215.
[38] A. Xu, Z. Liu, Y. Guo, V. Sinha, R. Akkiraju, A new chatbot for customer ser-vice on social media, in: Proceedings of conference on Human Factors in Com-puting Systems (CHI, 2017), Denver, USA. May 6–11,2017. https://doi.org/10.1145/3025453.3025496.
[39] J. Cho, G. Lee, A chatbot system for construction daily report information man-agement, in: Proceedings of the 36th International Symposium on Automation and Robotics in Construction (ISARC, 2019), Banff, Canada. May 21 – 24, 2019.
[40] M.H. Tsai, J.Y. Chen, S.C. Kang, Ask Diana: A keyword-based chatbot system for water-related disaster management, Water (Switzerland). 11 (2019) 1–19. https://doi.org/10.3390/w11020234.
[41] D. Manning, P. Raghavan, H. Schtze, Introduction to Information Retrieval, Cambridge University Press, Cambridge University Press, 2008.
50
[42] S. Tata, J.M. Patel, Estimating the selectivity of tf-idf based cosine similarity predicates, SIGMOD Rec. 36 (2007) 75–80. https://doi.org/10.1145/1361348.1361351.
[43] Taiwan Network Information Center, 2018 Taiwan Internet Report. Available online: https://www.twnic.net.tw/doc/twrp/201812e.pdf (accessed on 16 August 2020).
[44] Python Software Foundation, Project description. Available online: https://www.python.org/psf/ (accessed on 16 August 2020).
[45] Autodesk Inc, Revit. Available: https://www.autodesk.com/products/revit/over-view (accessed on 16 August 2020).
[46] The Board of Trustees of the Leland Stanford Junior University, Protégé. Availa-ble: https://protege.stanford.edu/ (accessed on 16 August 2020).
[47] S. Alatrish, Comparison of Ontology Editors, E-RAF J. Comput. 4 (2012) 23–38.
[48] Python Software Foundation, Project description - jieba package. Available online: https://pypi.org/project/jieba/ (accessed on 16 August 2020).
[49] Python Software Foundation, Project description - gensim package. Available online: https://pypi.org/project/gensim/ (accessed on 16 August 2020).
[50] The PostgreSQL Global Development Group, PostgreSQL. Available: https://www.postgresql.org/ (accessed on 16 August 2020).
[51] Microsoft, C# documentation. Available online: https://docs.microsoft.com/en-gb/dotnet/csharp/ (accessed on 16 August 2020).
[52] Autodesk Inc, Online Documentation for the Revit API. Available: https://www.revitapidocs.com/ (accessed on 16 August 2020).
[53] Autodesk Inc, Dynamo. Available: https://dynamobim.org/ (accessed on 16 Au-gust 2020).
51
[54] The Knowledge Representation and Reasoning Group, The Knowledge Repre-sentation and Reasoning Group. Available online: http://www.hermit-rea-soner.com/. (accessed on 28 June 2020).