A Novel Dispatch Mode of Online Car-hailing Platform Based on Batch-delay Matching Model

Abstract

With the popularization of information technology and the acceleration of modern life, the online ride-hailing industry has been flourishing in China. This paper first explores the traditional order dispatch mode, identifies its contradictions, and analyzes their underlying causes. Next, a novel dispatch mode is proposed based on a batch-delay matching model. The PLTS-Hungarian algorithm is employed to match orders clustered by a clustering algorithm. Subsequently, evaluation criteria for dispatch modes are established. Finally, order allocation results are obtained using both the traditional and proposed modes. Comparative analysis demonstrates the validity and practicality of the proposed mode. Compared with the objective function values before and after optimization, the new mode improves overall platform efficiency, reflected by increased average pick-up time and higher average order efficiency coefficient. Meanwhile, computational complexity is significantly reduced. In addition, the applicability of the proposed model is verified through sensitivity analysis, and its performance under both high and low demand scenarios is examined. This approach provides valuable guidance for similar scheduling and matching problems.

Keywords

Dispatch mode / online car-hailing platform / batch-delay / probabilistic linguistic term sets / Hungarian algorithm

References

[1] Blumenthal D B, Bougleux S, Dignös A, Gamper J. Enumerating dissimilar minimum cost perfect and error-correcting bipartite matchings for robust data matching. Information Sciences, 2022, 596: 202-221.

[2] Chen R, Shi Y, Shen L, Zhou X, Qian G. Scheduling algorithm for online car-hailing considering both benefit and fairness. International Conference on Computer Engineering and Networks (CENet), 2020October 16–18,2020

[3] Chopra S, Notarstefano G, Rice M, Egerstedt M. A distributed version of the Hungarian method for multirobot assignment. IEEE Transactions on Robotics, 2017, 33(4): 932-947.

[4] Du W J, Li Y Z, Zhang J G. Stability analysis of a car-following model with effect of driver’s memory delay in connected vehicle environment. Journal of the Operations Research Society of China, 2025, 13: 1181-1204.

[5] Ding H, Li J, Zheng N, Zheng X, Huang W, Bai H. Dynamic dispatch of connected taxis for large-scale urban road networks with stochastic demands: An MFD-enabled hierarchical and cooperative approach. Transportation Research Part C: Emerging Technologies, 2022, 142: 103792.

[6] Gad-Elrab A A, Noaman A Y. A two-tier bipartite graph task allocation approach based on fuzzy clustering in cloud-fog environment. Future Generation Computer Systems, 2020, 103: 79-90.

[7] Guo Y, Zhang Y, Boulaksil Y, Tian N. Multidimensional spatiotemporal demand forecasting and service vehicle dispatching for online car-hailing platforms. International Journal of Production Research, 2022, 60(6): 1832-1853.

[8] Gou X, Xu Z. Novel basic operational laws for linguistic terms, hesitant fuzzy linguistic term sets and probabilistic linguistic term sets. Information Sciences, 2016, 372: 407-427.

[9] Jiang Y, Xia Y, Cheng X, Xu Y. A mutual selection mechanism of ride-hailing based on hidden points. Wireless Communications and Mobile Computing, 2020, 2020(1): 9520384

[10] Lan S, Yang C, Chen C H. Online car-hailing system performance analysis based on Bayesian network. IEEE Access, 2019, 7: 101195-101212.

[11] Liu X, Yang H, Xiao F. Equilibrium in taxi and ride-sourcing service considering the use of e-hailing application. Transportmetrica A: Transport Science, 2022, 18(3): 659-675.

[12] Li Q, Zhang Q, Li Y, Liu Y. The image of China’s car-hailing policy in the eyes of the public: A social media analytics perspective. Case Studies on Transport Policy, 2022, 10(3): 1651-1660.

[13] Li X, Zhang S, Liu D, Cheng T, Zhang Z. Policy evaluation and policy style analysis of ride-hailing in China from the perspective of policy instruments: The introduction of a TOE three-dimensional framework. Processes, 2022, 10(10): 2035.

[14] Li Y, Fang J, Zeng Y, Maag B, Tong Y, Zhang L. Two-sided online bipartite matching in spatial data: Experiments and analysis. GeoInformatica, 2020, 24: 175-198.

[15] Manasero P B. Binary operations for the lattice structure in a many-to-many matching model. Journal of the Operations Research Society of China, 2021, 9(1): 207-228.

[16] Martins L D C, de la Torre R, Corlu C G, Juan A A, Masmoudi M A. Optimizing ride-sharing operations in smart sustainable cities: Challenges and the need for agile algorithms. Computers & Industrial Engineering, 2021, 153: 107080.

[17] Pang Q, Wang H, Xu Z. Probabilistic linguistic term sets in multi-attribute group decision making. Information Sciences, 2016, 369: 128-143.

[18] Qiao S, Han N, Huang J, Peng Y, Cai H, Qin X, Lei Z. An three-in-one on-demand ride-hailing prediction model based on multi-agent reinforcement learning. Applied Soft Computing, 2023, 149: 110965.

[19] Rodriguez R M, Martinez L, Herrera F. Hesitant fuzzy linguistic term sets for decision making. IEEE Transactions on Fuzzy Systems, 2011, 20(1): 109-119.

[20] Teng F, Teng J, Qiao L, Du S, Li T. A multi-step forecasting model of online car-hailing demand. Information Sciences, 2022, 587: 572-586.

[21] Wang X, Xu Z, Gou X. Nested probabilistic-numerical linguistic term sets in two-stage multiattribute group decision making. Applied Intelligence, 2019, 49: 2582-2602.

[22] Wang Y Q, Wu J J, Sun H J, Zhang Y F, Lyu Y. Order dispatching optimization in ride-sourcing market by considering cross service modes. Journal of Central South University, 2023, 30(2): 642-653.

[23] Wang Z, Wang Y, Muhammad K. Network car hailing pricing model optimization in edge computing-based intelligent transportation system. IEEE Transactions on Intelligent Transportation Systems, 2022, 24(11): 13286-13295.

[24] Wikihow. How to use the Hungarian algorithm, 2022

[25] Xu K, Sun L, Liu J, Wang H. An empirical investigation of taxi driver response behavior to ride-hailing requests: A spatio-temporal perspective. PloS One, 2018, 13(6): e0198605.

[26] Yan J, Daobo W, Tingting B, Zongyuan Y. Multi-UAV objective assignment using Hungarian fusion genetic algorithm. IEEE Access, 2022, 10: 43013-43021.

[27] Yang M, Yuan Y, Zhan F B. Explore urban interactions based on floating car data - A case study of Chengdu, China. Annals of GIS, 2023, 29(1): 37-53.

[28] Yang X, Zhao N, Yu S. Combined internal trucks allocation of multiple container terminals with Hungarian algorithm. Journal of Coastal Research, 2020, 103(SI): 923-927.

[29] Ye X, Ye Q, Yan X, Wang T, Chen J, Li S. Demandfore-casting of online car-hailing with combining LSTM+ attention approaches. Electronics, 2021, 10(20): 2480.

[30] You J, Jiang H, Chen Z, Ming X, Sun P Z. Order allocation strategy for online car-hailing platform in the context of multi-party interests. Advanced Engineering Informatics, 2023, 57: 102110.

[31] Yu W, Wang W, Hua X, Wei X. Exploring taxi demand distribution of comprehensive land-use patterns using online car-hailing data and points of interest in Chengdu, China. Transportation Research Record, 2021, 2675(10): 1268-1286.

[32] Zhou M, Jin J, Zhang W, Qin Z, Jiao Y, Wang C, Ye J. Multi-agent reinforcement learning for order-dispatching via order-vehicle distribution matching. Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM’ 19), 2019November 3–7, 2019

[33] Zhu B, Xu Z. Consistency measures for hesitant fuzzy linguistic preference relations. IEEE Transactions on Fuzzy Systems, 2013, 22(1): 35-45.

[34] Zukhruf F, Baliepalli C, Frazila R B, Nugroho T S, Kurnia I S. Algorithms for restoring disaster-struck seaport operations considering interdependencies between infrastructure availability and repair team assignments. Computers & Industrial Engineering, 2023, 175: 108894.

RIGHTS & PERMISSIONS

Systems Engineering Society of China and Springer-Verlag GmbH Germany

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.