全球先進國家都積極規劃並發展與智慧城市建設相關科技，而智慧停車系統是其中非常重要的基礎設施建設。有別於路外停車場在封閉場域的閘道口，設置感應裝置(eTag)或車牌辨識攝影機(CCTV)識別車輛計算資費。近年因人工智慧(AI)相關軟硬體技術成熟，尤其是AI運算能力快速進化，使人工巡場搭配PDA開單的路邊停車開單作業有了新變革。改以路側攝影機辨識車牌，記錄車子進入、離開停車格位的時間，計算停車資費。
台灣的AI政策以「打造人工智慧島」為願景，從人才、法規、技術、產業、基礎設施等多面向推動AI政策，目標是2030年達成創新、包容、永續的智慧國家。高雄市政府近年積極推動城市主權AI，目標是提升城市治理自主性及效率。而高雄市交通局為落實智慧城市交通治理及淨零永續政策，於112年12月完成「高雄市北區路邊停車人工智慧開單案」發包作業，至114年2月共建置3344格的人工智慧開單路邊停車格。本文透過蒐集該政策實施前後，人工智慧開單(實驗組)與純人工開單(對照組)的各項停車數據，分類統計分析，檢視該政策實施後的各項停車績效指標如停車收益、停車格佔有率、週轉率、每車的平均停車延時是否符合政策規劃預期。
本文採用「差異中的差異」（difference-in-differences）法，期望透由此研究方法了解上述各種停車績效指標的變化，來檢驗該政策對整體停車績效是否具有正面影響。進一步對停車格用地屬性加以分類，藉以探討路邊人工智慧開單政策的實施，在不同土地使用分區(住宅區、商業區、行政機關用地、文教用地、特定用地、公園廣場用地)停車格，各項停車績效指標變化，以檢驗政策效果。
研究結果獲知在政策實施後，停車收益成長，停車格的週轉率變高，佔有率、停車延時也增加。不同土地使用分區停車格在不同時段的數據顯示，政策實施後各類分區停車績效指標皆呈現正向趨勢，另不同土地使用分區則會因為平、假日及不同時段而有不同的停車供需變化，這也表示民眾日常生活、休憩、經濟活動習慣，明顯影響停車供需。未來大型半導體產業鏈即將進駐高雄的科學園區，因應即將移入的大量就業人口，政府規劃須未雨綢繆。本研究結果，或可作為未來楠梓、橋頭區及其他城市停車管理政策的擘劃參考。

This study evaluates the effectiveness of the AI-based roadside parking enforcement policy implemented in the northern district of Kaohsiung City, Taiwan. As artificial intelligence (AI), automatic license plate recognition (ALPR), and cloud computing technologies have matured, local governments have gradually introduced AI-assisted parking management systems to replace conventional manual patrol operations. Although these technologies have been widely adopted in recent years, empirical evidence regarding their policy effectiveness remains limited. Using large-scale operational parking data, this study applies the Difference-in-Differences (DID) approach to evaluate whether AI-assisted roadside parking management improves parking performance. Four key performance indicators—parking revenue, occupancy rate, turnover rate, and average parking duration—are examined. In addition, land-use zoning analysis is incorporated to investigate whether policy impacts vary across different urban environments. The findings provide empirical evidence supporting AI-assisted parking management and offer practical implications for future smart parking policies and urban transportation planning.

Anderson, C. (2010). Free: The future of a radical price. Hyperion. https://books.google.com.tw/books/about/Free.html?id=LhR44BB6KY8C
Anderson, C. K., & Carroll, B. (2007). Demand management: Beyond revenue management. Journal of Revenue and Pricing Management, 6(4), 260–263. https://link.springer.com/article/10.1057/palgrave.rpm.5160092
Bertrand, M., Duflo, E., & Mullainathan, S. (2004). How much should we trust differences-in-differences estimates? The Quarterly Journal of Economics,119(1),249–275.https://academic.oup.com/qje/article/119/1/249/1876068
Chatman, D. G., & Manville, M. (2014). Theory versus implementation in congestion-priced parking: An evaluation of SFpark, 2011–2012. Research in Transportation Economics,44,52–60.https://doi.org/10.1016/j.retrec.2014.04.002
Fujita, M., & Okada, M. (2007). Parking in a city with scarce land. Journal of Urban Economics, 61(2), 295–311. https://publications.slu.se/?file=publ/show&id=104376
Geng, Y., & Cassandras, C. G. (2013). A new “smart parking” system based on optimal resource allocation and reservations. IEEE Transactions on Intelligent Transportation Systems, 14(3),1129–1139.https://ieeexplore.ieee.org/document/6515171
Goodman-Bacon, A. (2021). Difference-in-differences with variation in treatment timing. Journal of Econometrics, 225(2), 254–277.https://www.sciencedirect.com/science/article/pii/S0304407621001445
Kelly, J. A., & Clinch, J. P. (2009). Temporal variance of revealed preference on-street parking price elasticity. Transport Policy, 16(4), 193–199. https://doi.org/10.1016/j.tranpol.2009.06.001 82
Krishnamurthy, C. K. B., & Ngo, N. S. (2020). The effects of smart-parking on transit and traffic: Evidence from SFpark. Journal of Environmental Economics and Management,99,102273.https://doi.org/10.1016/j.jeem.2019.102273
Ojeda-Cabral, M., & Stead, A. D. (2025). Estimating the impact of new rail station openings on through-passenger demand: A difference-in-differences approach.Transportation.https://doi.org/10.1007/s11116-025-10684-9
Shoup, D. (2005). The high cost of free parking. Routledge. https://www.shoupdogg.com/publications/
Spiliopoulou, C., & Antoniou, C. (2012). Analysis of illegal parking behavior in Greece. Procedia – Social and Behavioral Sciences, 48, 1622–1631. https://doi.org/10.1016/j.sbspro.2012.06.1137
Wang, H., & He, W. (2011). A reservation-based smart parking system. In Proceedings of the 2011 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) (pp. 690–695).IEEE.https://digitalcommons.unl.edu/cgi/viewcontent.cgi?article=1225&context=cseconfwork
Yang, W., & Kang, B. (2026). Slower roads, cleaner skies? Causal effects of speed limit reduction on urban air quality using propensity score matching and spatial difference-in-differences regression. Transport Policy, 178, 103969. https://doi.org/10.1016/j.tranpol.2025.103969