家禽肉品加工業因為法規的要求，必須建置電動屠宰設備且符合衛生法規，故普遍擁有基礎的自動化設備。但是，家禽肉品加工業使用較多的人員經驗進行決策，在數位轉型與智慧化的程度相對落後。雖然政府持續推動台灣農業4.0，但是家禽肉品加工業還多處於3.0，甚至2.0的階段，要在短短幾年內要提升進步，在資金與人力物力上並非易事。
國內白肉雞生產成本約為歐美國家之1.5至2倍，在面對雞肉進口量逐年增加的兢爭壓力下，台灣的家禽肉品加工業除了強調在地生鮮的特色外，更要強化供應鏈管理與生產效率，提升雞肉產品的競爭力。因此，利用產業專家的經驗、企業內外部資料，以及資訊技術和人工智慧技術，以數據為核心串聯供應鏈的上、中、下游，為傳統家禽肉品加工業提供智慧決策輔助且縮短決策流程與時間，對於受到進口雞肉競爭的台灣肉品加工業實屬關鍵，也是建立邁向農業4.0的信心與基礎。
本研究基於紫式決策分析架構，提出數位轉型解決方案，發展白肉雞價量預測方法、供應鏈管理系統與供應鏈需求分切輔助決策系統，作為傳統家禽肉品加工業數位轉型的一個開端。並以實證研究檢驗效度，研究結果證實人工智慧搭配資訊系統可以協助傳統產業之產銷人員，以模型預測結果輔助投放決策，獲取可信賴的供應鏈資訊以協助排程與加工生產決策。相較依賴人工經驗，數位轉型後的供應鏈與生產加工的決策可以更透明無縫的銜接，決策品質與效率提高，企業營收與獲利獲得明顯的改善。

The poultry meat processing industry, regulated to establish electric slaughtering facilities that comply with health standards, widely uses basic automation equipment. However, compared to Taiwan's 3C industry, it relies more personnel experiences for decision-making, lagging in digital transformation. Despite government efforts to promote Agriculture 4.0, the industry remains at stages 3.0 or even 2.0. Achieving improvements in a short timeframe is challenging due to constraints in funding and resources.
Domestic production costs of broiler chickens are approximately 1.5 to 2 times higher than those of imported broiler meat. With increasing competition from imported broiler meat, the industry must enhance supply chain management and production efficiency to improve competitiveness. Leveraging industry expertise, open data, Enterprise owned data, IT, and AI to integrate the supply chain's upstream, midstream, and downstream is crucial. This approach provides intelligent decision support, shortens decision-making processes, and strengthens the industry's position against import competition, laying the foundation for Agriculture 4.0.
This study proposes a digital transformation solution based on UNISON decision framework, including broiler chicken price and quantity forecasting, supply chain management systems, and broiler meat processing and portioning decision support systems. Empirical results demonstrate that AI combined with information systems can assist industry professional in making raising chicks decisions, obtaining reliable supply chain information for scheduling and production. Compared to relying on personnel experiences, post-digital transformation decisions achieve more transparent and seamless integration, improving decision quality and efficiency, significantly enhancing corporate revenue and profitability.

期刊論文
吳祥雲 and 紀學斌 (2002), “進口與國產冷凍豬肉品質差異之探討,” 畜產研究, Vol. 35, No. 4, pp. 331～337.
阮有山 (2022). 農業 4.0 之紫式決策架構與肉雞重量預測提升聰明生產之實證研究. 工業工程與工程管理學系, 國立清華大學.
周汶蔚 (2022). 紫式決策架構建立最佳化廢水幫浦作業與半導體綠色生產之實證研究. 工業工程與工程管理學系, 國立清華大學.
洪建中 (2021). 紫式決策架構以評估工業 3.5 智慧工廠解決方案. 智慧製造跨院高階主管碩士在職學位學程, 國立清華大學.
財團法人獸醫畜產發展基金會 (2023), 2022 台灣家禽統計手冊. 財團法人獸醫畜產發展基金會,台北.
劉玹君 and 鍾秋悅 (2022), “日本六次產業化影響因素之探討,” 台灣農學會報, Vol. 22, No. 1, pp. 1-26.
蔡本原 (2014), “農業六級產業化策略發展之探討,” 臺中區農業改良場特刊, Vol., No. 122號, pp. 255-260.
簡禎富 (2015), 決策分析與管理：紫式決策分析以全面提升決策品質(第二版). 雙葉書廊,台北.
簡禎富 and 許嘉裕 (2018), 大數據分析與資料挖礦(第二版). 前程文化, 台北.
Arikan, M. S., Çevrimli, M., Polat, M., Mat, B., Akin, A., Özel, Z., and Tekindal, M. (2022), “Analyzing the factors affecting the price of broiler chicken in Turkey using the boosting regression method,” Brazilian Journal of Poultry Science, Vol. 24, No., pp. eRBCA-2021-1618.
Chien, C.-F., Lin, Y.-S., and Lin, S.-K. (2020), “Deep reinforcement learning for selecting demand forecast models to empower Industry 3.5 and an empirical study for a semiconductor component distributor,” International Journal of Production Research, Vol. 58, No. 9, pp. 2784-2804.
Clemen, R. T. (1996), Making Hard Decisions: An Introduction to Decision Analysis (2nd edition). Duxbury Press, Belmont, CA.
Deepa, S., Alli, A., and Gokila, S. (2023), “Machine learning regression model for material synthesis prices prediction in agriculture,” Materials Today: Proceedings, Vol. 81, No., pp. 989-993.
Huang, B.-W., Shih, M.-L., Chiu, N.-H., Hu, W., and Chiu, C. (2009), “Price information evaluation and prediction for broiler using adapted case-based reasoning approach,” Expert Systems with Applications, Vol. 36, No. 2, pp. 1014-1019.
Johansen, S. V., Bendtsen, J. D., Martin, R., and Mogensen, J. (2017), “Data driven broiler weight forecasting using dynamic neural network models,” IFAC-PapersOnLine, Vol. 50, No. 1, pp. 5398-5403.
Keeney, R. and Raiffa, H. (1993), Decisions with multiple objectives: preferences and value trade-offs. Cambridge University Press.
Li, F. and Chen, L. (2022), “Research on the Correlation Between China's Meat Non-staple Food Prices Based on Univariate Regression,” Proceedings of Proceedings of the International Conference on Information Economy, Data Modeling and Cloud Computing, ICIDC 2022, 17-19 June 2022, Qingdao, China.
Lyu, P., Jeongik, M., and Song, J. (2023), “Application of Machine Learning Algorithms for On-Farm Monitoring and Prediction of Broilers’ Live Weight: A Quantitative Study Based on Body Weight Data,” Agriculture, Vol. 13, No. 12, pp. 2193.
Ma, Z., Chen, Z., Chen, T., and Du, M. (2019), “Application of Machine Learning Methods in Pork Price Forecast,” Proceedings of International Conference on Machine Learning and Computing.
Wang, C.-Y., Chen, Y.-J., and Chien, C.-F. (2021), “Industry 3.5 to empower smart production for poultry farming and an empirical study for broiler live weight prediction,” Computers & Industrial Engineering, Vol. 151, No., pp. 106931.
Wang, L., Feng, J., Sui, X., Chu, X., and Mu, W. (2020), “Agricultural product price forecasting methods: research advances and trend,” British Food Journal, Vol. 122, No. 7, pp. 2121-2138.
Zielinska-Sitkiewicz, M. and Chrzanowska, M. (2018), “Forecasting prices of broiler chickens using the creeping trend,” ECONOMIC SCIENCE FOR RURAL DEVELOPMENT 2018, Vol., No., pp. 537.

網路資料
中央氣象署. (2024). “氣象資料開放平台.”, from https://opendata.cwa.gov.tw/index.
日本農林水產省. (2010). “食料・農業・農村白書 平成21年度.” ,from https://warp.ndl.go.jp/info:ndljp/pid/12232574/www.maff.go.jp/j/wpaper/w_maff/h21_h/index.html.
財團法人中央畜產會. (2024). “家禽資訊.”, from https://www.naif.org.tw/infoFowlsListAll.aspx?frontTitleMenuID=37&frontMenuID=114.
鉅亨網. (2024). “麥、黃豆、玉米期貨與現貨價格.”, from https://www.cnyes.com/futures/History.aspx?mydate=%2020200512&code=WCON.
農業部. (2001). “加入ＷＴＯ家禽產業因應對策.”, from https://www.moa.gov.tw/ws.php?id=952.
農業部. (2017). “2017年年報.”, from https://www.moa.gov.tw/ws.php?id=2508389.
農業部. (2018). “107年度施政計畫.”, from https://www.moa.gov.tw/ws.php?id=2508349.
農業部. (2019). “108年度施政計畫.”, from https://www.moa.gov.tw/ws.php?id=2509291.
農業部. (2024). “農業部畜產行情資訊網.” From https://ppg.naif.org.tw/naif/MarketInformation/Pig/TranStatistics.aspx.
INSEAD. (2024). “Decision Sciences.” , from https://www.insead.edu/faculty-research/academic-areas/decision-sciences.
National Chicken Council. (2024). “Broiler Chicken Industry Key Facts 2023.” , from https://www.nationalchickencouncil.org/statistic/broiler-industry-key-facts/.