{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T15:53:57Z","timestamp":1778514837726,"version":"3.51.4"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T00:00:00Z","timestamp":1750982400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T00:00:00Z","timestamp":1750982400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072180"],"award-info":[{"award-number":["62072180"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Sci. Eng."],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Truck-cargo matching is one of the core tasks of online freight platforms, where the primary objective is to optimally assign each cargo task to the most suitable truck. The existing matching strategies seek to maximize total transported weight of cargoes by increasing the number of truck-cargo pairings. However, these strategies fail to ensure global matching pair maximization across all regions due to the heterogeneous spatial distribution of truck supply and cargo transporting demand. This limitation necessitates the incorporation of regional supply\u2013demand gap prediction into the matching process. Two critical challenges emerge in achieving optimal matching: (1) the prediction accuracy of supply\u2013demand gaps is influenced by multiple complex factors, and (2) the multi-objective optimization conflicts within current matching decisions may adversely impact subsequent matching performance. To address these challenges, we propose a hierarchical reinforcement learning framework for multi-objective truck-cargo matching, comprising two key components: a supply\u2013demand gap prediction module and a multi-objective optimization matching module.For accurate supply\u2013demand gap prediction, we develop a hypergraph attention network model incorporating an adaptive confidence interval optimization mechanism to capture complex relationships among various predictive factors. Furthermore, to mitigate negative effects of multi-objective conflicts on long-term matching performance, we design a hierarchical deep Q network model that dynamically adjusts objective weights based on predicted long-term benefits. Extensive experiments conducted on two real-world logistics datasets demonstrate that our proposed method achieves a 10.7% higher competitive ratio compared to state-of-the-art approaches, validating the effectiveness of our supply\u2013demand balance guided matching strategy in practical operational scenarios.\u00a0<\/jats:p>","DOI":"10.1007\/s41019-025-00299-6","type":"journal-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T02:45:29Z","timestamp":1750992329000},"page":"692-710","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Supply\u2013Demand Balance Guided Hierarchical Reinforcement Learning Approach for Truck-Cargo Matching"],"prefix":"10.1007","volume":"10","author":[{"given":"Jiajun","family":"Liao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiali","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aoying","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,27]]},"reference":[{"key":"299_CR1","unstructured":"Avati A, Duan T, Zhou S, Jung K, Shah NH, Ng AY (2020) Countdown regression: sharp and calibrated survival predictions. In: Uncertainty in Artificial Intelligence. PMLR"},{"key":"299_CR2","doi-asserted-by":"crossref","unstructured":"Aveklouris A, DeValve L, Stock M, Ward A (2024) Matching impatient and heterogeneous demand and supply. Operat Res","DOI":"10.1287\/opre.2022.0005"},{"key":"299_CR3","doi-asserted-by":"crossref","unstructured":"Bilal M, Canini M, Fonseca R, Rodrigues R (2023) With great freedom comes great opportunity: rethinking resource allocation for serverless functions. In: EuroSys","DOI":"10.1145\/3552326.3567506"},{"key":"299_CR4","doi-asserted-by":"crossref","unstructured":"Cao S, Lu W, Xu Q (2015) Grarep: learning graph representations with global structural information. In: CIKM","DOI":"10.1145\/2806416.2806512"},{"issue":"2","key":"299_CR5","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1109\/TII.2022.3167380","volume":"19","author":"R Chen","year":"2022","unstructured":"Chen R, Li W, Yang H (2022) A deep reinforcement learning framework based on an attention mechanism and disjunctive graph embedding for the job-shop scheduling problem. Trans Ind Inf 19(2):1322\u20131331","journal-title":"Trans Ind Inf"},{"key":"299_CR6","doi-asserted-by":"crossref","unstructured":"Cheng P, Lian X, Chen L, Shahabi C (2017) Prediction-based task assignment in spatial crowdsourcing. In: ICDE","DOI":"10.1109\/ICDE.2017.146"},{"key":"299_CR7","doi-asserted-by":"crossref","unstructured":"Feng C, Liao J, Mao J, Liu J, Guo Y, Qian W (2022) Dynamic vehicle-cargo matching based on adaptive time windows. In: APWeb","DOI":"10.1007\/978-3-031-25158-0_23"},{"key":"299_CR8","doi-asserted-by":"crossref","unstructured":"Gao G, Wu J, Xiao M, Chen G (2020) Combinatorial multi-armed bandit based unknown worker recruitment in heterogeneous crowdsensing. In: INFOCOM","DOI":"10.1109\/INFOCOM41043.2020.9155518"},{"key":"299_CR9","unstructured":"Georg\u00a0Balke LA (2023) Dataset of trucks\u2019 anonymized recorded driving and operation, https:\/\/github.com\/TUMFTM\/dt-cargo"},{"issue":"1","key":"299_CR10","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.ejor.2022.07.017","volume":"306","author":"K Gkiotsalitis","year":"2023","unstructured":"Gkiotsalitis K, Iliopoulou C, Kepaptsoglou K (2023) An exact approach for the multi-depot electric bus scheduling problem with time windows. Eur J Oper Res 306(1):189\u2013206","journal-title":"Eur J Oper Res"},{"key":"299_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2023.103688","volume":"173","author":"J Hatzenb\u00fchler","year":"2023","unstructured":"Hatzenb\u00fchler J, Jenelius E, Gid\u00f3falvi G, Cats O (2023) Modular vehicle routing for combined passenger and freight transport. Trans Res Part A Policy Pract 173:103688","journal-title":"Trans Res Part A Policy Pract"},{"issue":"3","key":"299_CR12","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/S0951-8320(02)00056-X","volume":"77","author":"E Hofer","year":"2002","unstructured":"Hofer E, Kloos M, Krzykacz-Hausmann B, Peschke J, Woltereck M (2002) An approximate epistemic uncertainty analysis approach in the presence of epistemic and aleatory uncertainties. Reliab Eng Syst Safety 77(3):229\u2013238","journal-title":"Reliab Eng Syst Safety"},{"issue":"4","key":"299_CR13","doi-asserted-by":"publisher","first-page":"2476","DOI":"10.1109\/TII.2021.3094527","volume":"18","author":"Y Huang","year":"2021","unstructured":"Huang Y, Chen H, Ma G, Lin K, Ni Z, Yan N, Wang Z (2021) Opat: optimized allocation of time-dependent tasks for mobile crowdsensing. IEEE Trans Industr Inf 18(4):2476\u20132485","journal-title":"IEEE Trans Industr Inf"},{"key":"299_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103289","volume":"130","author":"Y Jiao","year":"2021","unstructured":"Jiao Y, Tang X, Qin ZT, Li S, Zhang F, Zhu H, Ye J (2021) Real-world ride-hailing vehicle repositioning using deep reinforcement learning. Trans Res Part C Emerg Technol 130:103289","journal-title":"Trans Res Part C Emerg Technol"},{"key":"299_CR15","doi-asserted-by":"crossref","unstructured":"Jin J, Zhou M, Zhang W, Li M, Guo Z, Qin Z, Jiao Y, Tang X, Wang C, Wang J, et\u00a0al (2019) Coride: joint order dispatching and fleet management for multi-scale ride-hailing platforms. In: CIKM","DOI":"10.1145\/3357384.3357978"},{"issue":"4","key":"299_CR16","doi-asserted-by":"publisher","first-page":"10216","DOI":"10.1109\/LRA.2022.3190100","volume":"7","author":"J Li","year":"2022","unstructured":"Li J, Tang C, Tomizuka M, Zhan W (2022) Hierarchical planning through goal-conditioned offline reinforcement learning. Robot Automat Lett 7(4):10216\u201310223","journal-title":"Robot Automat Lett"},{"key":"299_CR17","doi-asserted-by":"crossref","unstructured":"Li M, Qin Z, Jiao Y, Yang Y, Wang J, Wang C, Wu G, Ye J (2019) Efficient ridesharing order dispatching with mean field multi-agent reinforcement learning. In: WWW","DOI":"10.1145\/3308558.3313433"},{"issue":"5","key":"299_CR18","doi-asserted-by":"publisher","first-page":"5282","DOI":"10.1109\/TITS.2023.3237387","volume":"24","author":"YL Li","year":"2023","unstructured":"Li YL, Chai ZY, Tan F, Liu X (2023) Temporal data scheduling in internet of vehicles using an improved decomposition-based multi-objective evolutionary algorithm. Trans Intell Transp Syst 24(5):5282\u20135295","journal-title":"Trans Intell Transp Syst"},{"key":"299_CR19","first-page":"685","volume":"12114","author":"J Liu","year":"2020","unstructured":"Liu J, Mao J, Liao J, Ma Y, Guo Y, Hu H, Zhou A, Jin C (2020) Adaptive loading plan decision based upon limited transport capacity. DASFAA 12114:685\u2013697","journal-title":"DASFAA"},{"issue":"2","key":"299_CR20","doi-asserted-by":"publisher","first-page":"351","DOI":"10.2507\/IJSIMM20-2-564","volume":"20","author":"M Liu","year":"2021","unstructured":"Liu M, Zhang C, Wu Q, Meng B (2021) Vehicle routing problem with soft time windows of cargo transport o2o platforms. Int J Simul Model 20(2):351\u2013362","journal-title":"Int J Simul Model"},{"issue":"11","key":"299_CR21","doi-asserted-by":"publisher","first-page":"3319","DOI":"10.1080\/00207543.2021.1919780","volume":"60","author":"J Long","year":"2022","unstructured":"Long J, Pardalos PM, Li C (2022) Level-based multi-objective particle swarm optimizer for integrated production scheduling and vehicle routing decision with inventory holding, delivery, and tardiness costs. Int J Prod Res 60(11):3319\u20133338","journal-title":"Int J Prod Res"},{"issue":"1","key":"299_CR22","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1109\/TII.2021.3076811","volume":"19","author":"Z Lu","year":"2021","unstructured":"Lu Z, Wang Y, Tong X, Mu C, Chen Y, Li Y (2021) Data-driven many-objective crowd worker selection for mobile crowdsourcing in industrial IoT. IEEE Trans Industr Inf 19(1):531\u2013540","journal-title":"IEEE Trans Industr Inf"},{"key":"299_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106208","volume":"91","author":"S Luo","year":"2020","unstructured":"Luo S (2020) Dynamic scheduling for flexible job shop with new job insertions by deep reinforcement learning. Appl Soft Comput 91:106208","journal-title":"Appl Soft Comput"},{"key":"299_CR24","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602"},{"key":"299_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2021.108251","volume":"240","author":"W Qin","year":"2021","unstructured":"Qin W, Sun YN, Zhuang ZL, Lu ZY, Zhou YM (2021) Multi-agent reinforcement learning-based dynamic task assignment for vehicles in urban transportation system. Int J Prod Econ 240:108251","journal-title":"Int J Prod Econ"},{"key":"299_CR26","doi-asserted-by":"crossref","unstructured":"Song C, Chang R, Zhang Z, Liu A, Li R, Zhou S (2022) A short-term traffic supply-demand gap prediction model with integrated GCN-LSTM method for online car-hailing services. In: DSIT","DOI":"10.1109\/DSIT55514.2022.9943914"},{"issue":"1","key":"299_CR27","first-page":"25","volume":"9","author":"Y Sun","year":"2019","unstructured":"Sun Y, Tan W (2019) A trust-aware task allocation method using deep q-learning for uncertain mobile crowdsourcing. HCIS 9(1):25","journal-title":"HCIS"},{"key":"299_CR28","doi-asserted-by":"crossref","unstructured":"Sun Y, Zhang J, Tang Q, Yan Y (2020) Research on benefit-risk of vehicle-cargo matching platform based on matching degree. In: ICITE","DOI":"10.1109\/ICITE50838.2020.9231375"},{"key":"299_CR29","doi-asserted-by":"crossref","unstructured":"Tang X, Qin Z, Zhang F, Wang Z, Xu Z, Ma Y, Zhu H, Ye J (2019) A deep value-network based approach for multi-driver order dispatching. In: SIGKDD","DOI":"10.1145\/3292500.3330724"},{"issue":"4","key":"299_CR30","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1109\/JSTSP.2015.2402646","volume":"9","author":"C Tekin","year":"2015","unstructured":"Tekin C, Van Der Schaar M (2015) Releaf: an algorithm for learning and exploiting relevance. J Select Topics Signal Process 9(4):716\u2013727","journal-title":"J Select Topics Signal Process"},{"key":"299_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2022.108039","volume":"168","author":"R Tian","year":"2022","unstructured":"Tian R, Wang C, Ma Z, Liu Y, Gao S (2022) Research on vehicle-cargo matching algorithm based on improved dynamic Bayesian network. Comput Ind Eng 168:108039","journal-title":"Comput Ind Eng"},{"issue":"12","key":"299_CR32","first-page":"1053","volume":"9","author":"Y Tong","year":"2016","unstructured":"Tong Y, She J, Ding B, Wo T, Xu K (2016) Online minimum matching in real-time spatial data: experiments and analysis. VLDB 9(12):1053\u20131064","journal-title":"VLDB"},{"key":"299_CR33","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: AAAI","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"299_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2024.110221","volume":"192","author":"Y Wang","year":"2024","unstructured":"Wang Y, Sun H, Lv Y, Chang X, Wu J (2024) Reinforcement learning-based order-dispatching optimization in the ride-sourcing service. Comput Ind Eng 192:110221","journal-title":"Comput Ind Eng"},{"issue":"10","key":"299_CR35","doi-asserted-by":"publisher","first-page":"10923","DOI":"10.1109\/TITS.2023.3274636","volume":"24","author":"Y Wang","year":"2023","unstructured":"Wang Y, Wu J, Sun H, Lv Y, Xu G (2023) Reassignment algorithm of the ride-sourcing market based on reinforcement learning. IEEE Trans Intell Transp Syst 24(10):10923\u201310936","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"299_CR36","doi-asserted-by":"crossref","unstructured":"Yang Z, Yang D, Dyer C, He X, Smola A, Hovy E (2016) Hierarchical attention networks for document classification. In: NAACL","DOI":"10.18653\/v1\/N16-1174"},{"issue":"3","key":"299_CR37","first-page":"362","volume":"4","author":"D Zhang","year":"2018","unstructured":"Zhang D, Han X, Deng C (2018) Review on the research and practice of deep learning and reinforcement learning in smart grids. J Power Energy Syst 4(3):362\u2013370","journal-title":"J Power Energy Syst"},{"issue":"5","key":"299_CR38","first-page":"7635","volume":"6","author":"K Zhang","year":"2019","unstructured":"Zhang K, Zhu Y, Leng S, He Y, Maharjan S, Zhang Y (2019) Deep learning empowered task offloading for mobile edge computing in urban informatics. Internet Things J 6(5):7635\u20137647","journal-title":"Internet Things J"},{"issue":"3","key":"299_CR39","first-page":"2267","volume":"16","author":"Q Zhang","year":"2022","unstructured":"Zhang Q, Wang Y, Yin G, Tong X, Sai AMVV, Cai Z (2022) Two-stage bilateral online priority assignment in spatio-temporal crowdsourcing. IEEE Trans Serv Comput 16(3):2267\u20132282","journal-title":"IEEE Trans Serv Comput"},{"issue":"11","key":"299_CR40","doi-asserted-by":"publisher","first-page":"13452","DOI":"10.1007\/s10489-022-04151-6","volume":"53","author":"B Zhao","year":"2023","unstructured":"Zhao B, Dong H, Wang Y, Pan T (2023) A task allocation algorithm based on reinforcement learning in spatio-temporal crowdsourcing. Appl Intell 53(11):13452\u201313469","journal-title":"Appl Intell"},{"key":"299_CR41","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1016\/j.ast.2019.06.024","volume":"92","author":"X Zhao","year":"2019","unstructured":"Zhao X, Zong Q, Tian B, Zhang B, You M (2019) Fast task allocation for heterogeneous unmanned aerial vehicles through reinforcement learning. Aerosp Sci Technol 92:588\u2013594","journal-title":"Aerosp Sci Technol"},{"key":"299_CR42","doi-asserted-by":"crossref","unstructured":"Zhao Y, Li Y, Wang Y, Su H, Zheng K (2017) Destination-aware task assignment in spatial crowdsourcing. In: CIKM","DOI":"10.1145\/3132847.3132894"},{"key":"299_CR43","doi-asserted-by":"crossref","unstructured":"Zhao Y, Zheng K, Cui Y, Su H, Zhu F, Zhou X (2020) Predictive task assignment in spatial crowdsourcing: a data-driven approach. In: ICDE","DOI":"10.1109\/ICDE48307.2020.00009"},{"key":"299_CR44","doi-asserted-by":"crossref","unstructured":"Zhou F, Lu C, Tang X, Zhang F, Qin Z, Ye J, Zhu H (2021) Multi-objective distributional reinforcement learning for large-scale order dispatching. In: ICDM. IEEE","DOI":"10.1109\/ICDM51629.2021.00202"}],"container-title":["Data Science and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41019-025-00299-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41019-025-00299-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41019-025-00299-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T08:42:06Z","timestamp":1765528926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41019-025-00299-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,27]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["299"],"URL":"https:\/\/doi.org\/10.1007\/s41019-025-00299-6","relation":{},"ISSN":["2364-1185","2364-1541"],"issn-type":[{"value":"2364-1185","type":"print"},{"value":"2364-1541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,27]]},"assertion":[{"value":"26 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"One co-author, Aoying Zhou, is the managing editor of Data Science and Engineering and was not involved in the peer review of, and decision related to, this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}