Abstract: Spatial crowdsourcing (SC), as an effective paradigm for accomplishing spatiotemporal tasks, has gradually attracted widespread attention from both industry and academia. With the advancement of mobile technology, the service modes of SC have become more diversified and flexible, aiming to better meet the variable requirements of users. However, most research has focused on homogeneous task allocation problems under a single service model, without considering the individual differences among task requirements and workers. Consequently, many of these studies fail to achieve satisfactory outcomes in real scenarios. Based on real service scenarios, in this study, we investigate a heterogeneous multi-task allocation (HMTA) problem for hybrid scenarios and provide a formal description and definition of the problem. To solve the problem, we propose a role division approach embedded with an individual sorting model (RD-ISM). This approach is implemented based on a batch-based mode (BBM) and consists of two parts. First, an individual sorting model is introduced to determine the sequence of objects based on spatiotemporal attributes, prioritizing tasks and workers. Second, a role division model is designed based on an attraction‍–‍repulsion mechanism to match tasks and workers. Following several iterations over multiple batches, the approach obtains the final matching results. The effectiveness of the approach is verified using real and synthetic datasets and its performance is demonstrated through comparisons with other algorithms. Additionally, the impact of different parameters within the approach is investigated, confirming its scalability.

面向异构多任务混合场景的空间众包任务分配：一种嵌入模型的角色分工方法

[1]Alamri S, 2024. The geospatial crowd: emerging trends and challenges in crowdsourced spatial analytics. ISPRS Int J Geo-Inform, 13(6):168.

[2]Bhatti SS, Fan JH, Wang KR, et al., 2021. An approximation algorithm for bounded task assignment problem in spatial crowdsourcing. IEEE Trans Mob Comput, 20(8):2536-2549.

[3]Cai JH, Jia LS, Hu XQ, 2023. Operation decision model in a platform ecosystem for car-sharing service. Electron Commer Res Appl, 59:101262.

[4]Chen Z, Fu R, Zhao ZY, et al., 2014. gMission: a general spatial crowdsourcing platform. Proc VLDB Endow, 7(13):1629-1632.

[5]Dortheimer J, 2022. Collective intelligence in design crowdsourcing. Mathematics, 10(4):539.

[6]Duan ZJ, Li W, Zheng X, et al., 2019. Mutual-preference driven truthful auction mechanism in mobile crowdsensing. Proc IEEE 39^th Int Conf on Distributed Computing Systems, p.1233-1242.

[7]Dudek G, Pełka P, Smyl S, 2022. A hybrid residual dilated LSTM and exponential smoothing model for midterm electric load forecasting. IEEE Trans Neur Netw Learn Syst, 33(7):2879-2891.

[8]Feng ZH, Xiao RB, 2023. Spatiotemporal distance embedded hybrid ant colony algorithm for a kind of vehicle routing problem with constraints. Front Inform Technol Electron Eng, 24(7):1062-1079.

[9]Feng ZH, Xiao RB, 2024. Three-dimensional task allocation for smart transportation in spatial crowdsourcing: an intelligent role division approach. Adv Eng Inform, 62:102736.

[10]Gong DW, Peng C, Yao XJ, et al., 2020. A model of new workers’ accurate acceptance of tasks using capable sensing. Swarm Evol Comput, 59:100732.

[11]Guo B, Liu Y, Wang LY, et al., 2018. Task allocation in spatial crowdsourcing: current state and future directions. IEEE Int Things J, 5(3):1749-1764.

[12]Hassan UU, Curry E, 2014. A multi-armed bandit approach to online spatial task assignment. Proc IEEE 11^th Int Conf on Ubiquitous Intelligence and Computing and IEEE 11^th Int Conf on Autonomic and Trusted Computing and IEEE 14^th Int Conf on Scalable Computing and Communications and Its Associated Workshops, p.212-219.

[13]Hettiachchi D, Kostakos V, Goncalves J, 2022. A survey on task assignment in crowdsourcing. ACM Comput Surv, 55(3):49.

[14]Li BY, Cheng YR, Wang GR, et al., 2020. 3D-online stable matching problem for new spatial crowdsourcing platforms. J Softw, 31(12):3836-3851 (in Chinese).

[15]Liang L, Fu JD, Zhu HB, et al., 2023. Solving the team allocation problem in crowdsourcing via group multirole assignment. IEEE Trans Comput Soc Syst, 10(3):843-854.

[16]Lin XC, Wei KM, Li ZT, et al., 2024. Aggregation-based dual heterogeneous task allocation in spatial crowdsourcing. Front Comput Sci, 18(6):186605.

[17]Liu Z, Li KL, Zhou X, et al., 2022. Multi-stage complex task assignment in spatial crowdsourcing. Inform Sci, 586:‍119-139.

[18]Mazzetto S, 2024. A review of urban digital twins integration, challenges, and future directions in smart city development. Sustainability, 16(19):8337.

[19]Ray A, Chowdhury C, Bhattacharya S, et al., 2023. A survey of mobile crowdsensing and crowdsourcing strategies for smart mobile device users. CCF Trans Pervas Comput Interact, 5(1):98-123.

[20]Song TS, Tong YX, Wang LB, et al., 2017a. Online task assignment for three types of objects under spatial crowdsourcing environment. J Softw, 28(3):611-630 (in Chinese).

[21]Song TS, Tong YX, Wang LB, et al., 2017b. Trichromatic online matching in real-time spatial crowdsourcing. Proc IEEE 33^rd Int Conf on Data Engineering, p.1009-1020.

[22]Tong YX, Yuan Y, Cheng YR, et al., 2017. Survey on spatiotemporal crowdsourced data management techniques. J Softw, 28(1):35-58 (in Chinese).

[23]Tong YX, Zhou ZM, Zeng YX, et al., 2020. Spatial crowdsourcing: a survey. VLDB J, 29(1):217-250.

[24]Tong YX, Zeng YX, Ding BL, et al., 2021. Two-sided online micro-task assignment in spatial crowdsourcing. IEEE Trans Knowl Data Eng, 33(5):2295-2309.

[25]Wang L, Yu ZW, Han Q, et al., 2018. Multi-objective optimization based allocation of heterogeneous spatial crowdsourcing tasks. IEEE Trans Mob Comput, 17(7):1637-1650.

[26]Wang MZ, Wang YJ, Sai AMVV, et al., 2022. Task assignment for hybrid scenarios in spatial crowdsourcing: a Q-Learning-based approach. Appl Soft Comput, 131:109749.

[27]Wang YJ, Cai ZP, Zhan ZH, et al., 2019. An optimization and auction-based incentive mechanism to maximize social welfare for mobile crowdsourcing. IEEE Trans Comput Soc Syst, 6(3):414-429.

[28]Wu HS, Li H, Xiao RB, et al., 2018. Modeling and simulation of dynamic ant colony’s labor division for task allocation of UAV swarm. Phys A Stat Mech Appl, 491:127-141.

[29]Xiao RB, 2024. Four development stages of collective intelligence. Front Inform Technol Electron Eng, 25(7):903-916.

[30]Xiao RB, Feng ZH, Wu BW, 2023. Research on emergence mechanism of collective intelligence from the complexity perspective. Int J Bio-Inspir Comput, 22(1):28-39.

[31]You JP, Jiang HW, Chen ZY, et al., 2023. Order allocation strategy for online car-hailing platform in the context of multi-party interests. Adv Eng Inform, 57:102110.

[32]Zhang Q, Wang YJ, Cai ZP, et al., 2022. Multi-stage online task assignment driven by offline data under spatio-temporal crowdsourcing. Dig Commun Netw, 8(4):516-530.

[33]Zhang Q, Wang YJ, Yin GS, et al., 2023. Two-stage bilateral online priority assignment in spatio-temporal crowdsourcing. IEEE Trans Serv Comput, 16(3):2267-2282.

[34]Zhao BM, Xu P, Shi YX, et al., 2019. Preference-aware task assignment in on-demand taxi dispatching: an online stable matching approach. Proc 33^rd AAAI Conf on Artificial Intelligence, p.2245-2252.

[35]Zhao H, Pan QK, Gao KZ, 2023. A cooperative population-based iterated greedy algorithm for distributed permutation flowshop group scheduling problem. Eng Appl Artif Intell, 125:106750.

[36]Zhou JJ, Gao L, Lu C, 2023. Solving multi-task manufacturing cloud service allocation problems via bee colony optimizer with transfer learning. Adv Eng Inform, 56:101984.