在全球供應鏈高度不確定與航運市場快速變動之環境下，紡織業出口物流航運商之評選已無法僅以單一成本作為決策依據。企業除需考量運費價格外，亦須同時評估運輸時效、艙位保障、服務品質及風險控管能力等因素，使航運商選擇逐漸演變為多準則決策問題。然而，實務上決策資料常分散於不同系統與文件中，導致資訊整合困難、流程冗長與決策效率不佳。
因此，本研究以紡織業出口物流航運商評選為研究情境，結合低程式碼/無程式碼(Low-Code/No-Code, LCNC)技術、多準則決策方法(Multi-Criteria Decision Making, MCDM)與大型語言模型(Large Language Model, LLM)，建構一套具數位化管理與智慧決策能力之雲端決策支援架構。研究透過資訊價值流圖(Information Stream Mapping, iSM)分析案例公司現行資訊流程，並以Ragic雲端資料庫與Power BI建置數位化報價管理系統與決策儀表板，以改善資訊分散與人工彙整問題。
在決策模型方面，本研究採用最佳最差法(Best-Worst Method, BWM)建立準則權重，並結合理想解相似度法(Technique for Order Preference by Similarity to Ideal Solution, TOPSIS)進行航運商排序，以建構具一致性與可解釋性之決策模型。此外，本研究進一步透過情境模擬與敏感度分析，驗證模型於不同市場波動情境下之穩健性，並導入大型語言模型進行決策推理與風險辨識，比較其與MCDM模型之決策結果。
實證結果顯示，LCNC平台有效整合分散資訊，成功將報價至決策產出之流程前置時間縮減50%，並提升資訊即時性與決策透明度。BWM-TOPSIS模型展現良好之一致性與穩定性，即使於權重波動情境下，整體排序結果仍維持高度穩健。此外，LLM於多期模擬中展現良好的語義推理與風險辨識能力，能有效辨識低價高風險方案，並與MCDM基準結果呈現高度一致性。
本研究證實，透過LCNC平台、多準則決策模型與LLM之整合，能有效提升物流評選之資訊整合效率、決策品質與風險辨識能力。研究成果除可作為紡織業推動數位轉型之參考外，亦提供生成式AI應用於物流決策支援之實務驗證。

Under global supply chain uncertainty and rapidly changing logistics markets, textile export logistics provider selection has evolved into a complex multi-criteria decision-making problem. Enterprises must evaluate not only freight costs, but also transportation lead time, cargo space availability, service quality, and risk management capabilities. However, decision-related information is often dispersed across multiple systems and documents, resulting in inefficient information integration, lengthy operational processes, and low decision-making efficiency.
Therefore, this study proposes a cloud-based decision support framework integrating Low-Code/No-Code (LCNC) technologies, Multi-Criteria Decision-Making (MCDM) models, and a Large Language Model (Harris et al.) for export logistics provider selection in the textile industry. Information Stream Mapping (iSM) was adopted to analyze the existing information flow of the case company, while the Ragic platform and Microsoft Power BI were utilized to establish a digitalized quotation management and decision support system.
For the decision-making process, the Best-Worst Method (BWM) was applied to determine criteria weights, and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) was used to rank logistics providers. Scenario simulations and sensitivity analyses were further conducted to validate the robustness of the proposed model under different market fluctuation conditions. In addition, an LLM was introduced for semantic reasoning and risk identification, and its results were compared with the benchmark MCDM model outcomes.
The empirical results demonstrated that the LCNC platform reduced the lead time from quotation collection to decision-making by 50% while improving information transparency, operational efficiency, and decision timeliness. The BWM-TOPSIS model exhibited strong consistency and robustness under fluctuating weight conditions. Moreover, the LLM demonstrated promising semantic reasoning and risk identification capabilities, successfully identifying low-cost but high-risk alternatives and maintaining high consistency with the benchmark MCDM ranking results.
This study confirms that integrating LCNC platforms, MCDM models, and an LLM can effectively improve information integration, decision quality, and risk identification in logistics provider selection. The proposed framework provides practical guidance for digital transformation and generative AI-based logistics decision support in the textile industry.

Asadabadi, M. R., Ahmadi, H. B., Gupta, H., & Liou, J. J. (2023). Supplier selection to support environmental sustainability: the stratified BWM TOPSIS method. Annals of Operations Research, 322(1), 321–344.
Bal, T., & Güner, R. (2025). Sepsis as Seen through the Eyes of AI: A Comparative evaluation of ChatGPT and Gemini. Infectious Diseases Now, 105228.
Behzadian, M., Otaghsara, S. K., Yazdani, M., & Ignatius, J. (2012). A state-of the-art survey of TOPSIS applications. Expert Systems with applications, 39(17), 13051–13069.
Cao, N. (2006). Supply chain performance measurement in textile and apparel industries.
Dang, T.-T., Nguyen, N.-A.-T., Nguyen, V.-T.-T., & Dang, L.-T.-H. (2022). A two-stage multi-criteria supplier selection model for sustainable automotive supply chain under uncertainty. Axioms, 11(5), 228.
Frank, A. G., Dalenogare, L. S., & Ayala, N. F. (2019). Industry 4.0 technologies: Implementation patterns in manufacturing companies. International journal of production economics, 210, 15–26.
Gebre, S. L., Cattrysse, D., Alemayehu, E., & Van Orshoven, J. (2021). Multi-criteria decision making methods to address rural land allocation problems: A systematic review. International Soil and Water Conservation Research, 9(4), 490–501.
Geng, R., Mansouri, S. A., & Aktas, E. (2017). The relationship between green supply chain management and performance: A meta-analysis of empirical evidences in Asian emerging economies. International journal of production economics, 183, 245–258.
Gereffi, G. (1999). International trade and industrial upgrading in the apparel commodity chain. Journal of international economics, 48(1), 37–70.
Goncalves, S., Coelho, C., Pretre, L., Roussillon, C., Jarlot, M., Ducloux, C., Penfornis, A., & Amadou, C. (2025). Chat, Gemini and Claude at the dinner table: assessing general-purpose AI tools for carbohydrate counting in the context of type 1 diabetes. Diabetes Research and Clinical Practice, 113031.
Harris, C. R., Millman, K. J., Van Der Walt, S. J., Gommers, R., Virtanen, P., Cournapeau, D., Wieser, E., Taylor, J., Berg, S., & Smith, N. J. (2020). Array programming with NumPy. nature, 585(7825), 357–362.
Hosseini, J., Shakeryari, M., Nazari Nejad, A., Mastalizadeh, H., Maleki, M., Wang, J., Rustum, R., Rahmati, M., Doostvandi, F., & Mostafavi, M. A. (2024). Comparison of the analytic network process and the best–worst method in ranking urban resilience and regeneration prioritization by applying geographic information systems. Land, 13(7), 1008.
Hosseini, S. H., & Pourzangbar, A. (2025). How well do DeepSeek, ChatGPT, and Gemini respond to water science questions? Environmental Modelling & Software, 106772.
Hwang, C.-L., & Yoon, K. (2012). Multiple attribute decision making: methods and applications a state-of-the-art survey. Springer Science & Business Media.
Koohathongsumrit, N., Chankham, W., & Meethom, W. (2024). Multimodal transport route selection: An integrated fuzzy hierarchy risk assessment and multiple criteria decision-making approach. Transportation Research Interdisciplinary Perspectives, 28, 101252.
Koprov, P., & Starly, B. (2025). Industrial metaverse meets IIoT: Low-code platforms for machine-to-machine and human-to-machine integration. Manufacturing Letters, 44, 1254–1265.
Likert, R. (1932). A technique for the measurement of attitudes. Archives of psychology.
McGinnis, M. A. (1989). A comparative evaluation of freight transportation choice models. Transportation Journal, 36–46.
Microsoft. Microsoft Power Platform. Retrieved 2026/05/18 from https://www.microsoft.com/zh-tw/power-platform/products/power-bi
Ragic. Ragic. Retrieved 2026/05/18 from https://www.ragic.com/intl/zh-TW/home
Raisch, S., & Krakowski, S. (2021). Artificial intelligence and management: The automation–augmentation paradox. Academy of management review, 46(1), 192–210.
Rezaei, J. (2015). Best-worst multi-criteria decision-making method. Omega, 53, 49–57.
Roh, P., Kunz, A., & Wegener, K. (2019). Information stream mapping: Mapping, analysing and improving the efficiency of information streams in manufacturing value streams. CIRP Journal of Manufacturing Science and Technology, 25, 1–13.
Ross, S. M. (2022). Simulation. academic press.
Sahay, A., Indamutsa, A., Di Ruscio, D., & Pierantonio, A. (2020). Supporting the understanding and comparison of low-code development platforms. 2020 46th Euromicro Conference on Software Engineering and Advanced Applications (SEAA),
Salminen, J., Jung, S.-G., Kaate, I., Xuan, T. T. T., Azem, J. Y., Aldous, K. K., Amin, D., & Jansen, B. J. (2026). AI representing personas representing user groups: Applying the agency theory to examine interaction challenges of conversational personas as decision-making tools. Decision Support Systems, 114633.
Sarkis, J. (2024). The Palgrave handbook of supply chain management. Springer.
Srdjevic, B., Srdjevic, Z., Reynolds, K. M., Lakicevic, M., & Zdero, S. (2022). Using analytic hierarchy process and best–worst method in group evaluation of urban park quality. Forests, 13(2), 290.
Sufi, F. (2023). Algorithms in low-code-no-code for research applications: a practical review. Algorithms, 16(2), 108.
Sumers, T., Yao, S., Narasimhan, K. R., & Griffiths, T. L. (2023). Cognitive architectures for language agents. Transactions on Machine Learning Research.
Taherdoost, H., & Madanchian, M. (2023). Multi-criteria decision making (MCDM) methods and concepts. Encyclopedia, 3(1), 77–87.
Vial, G. (2021). Understanding digital transformation: A review and a research agenda. Managing digital transformation, 13–66.
Webber, W., Moffat, A., & Zobel, J. (2010). A similarity measure for indefinite rankings. ACM Transactions on Information Systems (TOIS), 28(4), 1–38.
Wong, P. C., Yan, H., & Bamford, C. (2008). Evaluation of factors for carrier selection in the China Pearl River delta. Maritime Policy & Management, 35(1), 27–52.
Xie, H., Li, Y., Pu, Y., Zhang, C., & Huang, J. (2024). Evaluating airline service quality through a comprehensive text-mining and multi-criteria decision-making analysis. Journal of air transport management, 120, 102655.
Xiong, L., Zhong, S., Liu, S., Zhang, X., & Li, Y. (2020). An approach for resilient‐green supplier selection based on WASPAS, BWM, and TOPSIS under intuitionistic fuzzy sets. Mathematical Problems in Engineering, 2020(1), 1761893.
Xu, W., Cui, X., & Peng, H. (2025). Product Design Decision-Making for Uncertain Environments: An Integrated Framework. Mathematics, 13(20), 3257.
Yalcin, A. S., Kilic, H. S., & Delen, D. (2022). The use of multi-criteria decision-making methods in business analytics: A comprehensive literature review. Technological forecasting and social change, 174, 121193.
Yang, S., Liao, H., & Wu, X. (2025). Prescriptive analytics for dynamic multi-criterion decision making considering learned knowledge of alternatives. Expert Systems with applications, 268, 126350.
Yang, T., & Fujimoto, T. (2026). Jidoka just-in-time cycle–from genba kaizen to the introduction of artificial intelligence. International Journal of Production Research, 1–19.
Yang, T., & Hung, C.-C. (2007). Multiple-attribute decision making methods for plant layout design problem. Robotics and computer-integrated manufacturing, 23(1), 126–137.
Yarbrough, A. C., Harris, G. A., & Purdy, G. T. (2022). Improving the flow of data and information in manufacturing. Manufacturing Letters, 32, 1–4.
Zayat, W., Kilic, H. S., Yalcin, A. S., Zaim, S., & Delen, D. (2023). Application of MADM methods in Industry 4.0: A literature review. Computers & Industrial Engineering, 177, 109075.