Multi-Worker-Aware Task Planning in Real-Time Spatial Crowdsourcing

Spatial crowdsourcing emerges as a new computing paradigm with the development of mobile Internet and the ubiquity of mobile devices. The core of many real-world spatial crowdsourcing applications is to assign suitable tasks to proper workers in real time. Many works only assign a set of tasks to each worker without making the plan how to perform the assigned tasks. Others either make task plans only for a single worker or are unable to operate in real time. In this paper, we propose a new problem called the Multi-Worker-Aware Task Planning (MWATP) problem in the online scenario, in which we not only assign tasks to workers but also make plans for them, such that the total utility (revenue) is maximized. We prove that the offline version of MWATP problem is NP-hard, and no online algorithm has a constant competitive ratio on the MWATP problem. Two heuristic algorithms, called Delay-Planning and Fast-Planning, are proposed to solve the problem. Extensive experiments on synthetic and real datasets verify the effectiveness and efficiency of the two proposed algorithms.