Team-Oriented Task Planning in Spatial Crowdsourcing

The rapid development of mobile devices has stimulated the popularity of spatial crowdsourcing. Various spatial crowdsourcing platforms, such as Uber, gMission and Gigwalk, are becoming increasingly important in our daily life. A core functionality of spatial crowdsourcing platforms is to allocate tasks or make plans for workers to efficiently finish the published tasks. However, existing studies usually ignore the fact that tasks may impose different skill requirements on workers, which may lead to decreased numbers of accomplished tasks in real-world applications. In this work, we propose a practical problem called TOTP, \({\underline{T}}\)eam-\({\underline{O}}\)riented \({\underline{T}}\)ask \({\underline{P}}\)lanning, which not only makes feasible plans for workers but also satisfies the skill requirements of different tasks on workers. We prove the NP-hardness of TOTP, and propose two greedy-based heuristic algorithms to solve the TOTP problem. Evaluations on both synthetic and real-world datasets verify the effectiveness and the efficiency of the proposed algorithms.