Enhancing User Experience of Task Assignment in Spatial Crowdsourcing: A Self-Adaptive Batching Approach

摘要: Faced with the explosive demand of real-world applications, spatial crowdsourcing has attracted much attention, in which task assignment algorithms take dominant role past few years. On one hand, most recent studies concentrate on maximizing overall benefits platform, ignoring fact that user experience also plays an essential allocation. other they focus matching, is, how to assign tasks, rather than batching, when make assignment. In fact, depends but this is largely overlooked by current studies. paper, we propose a self-adaptive batching mechanism enhance crowdsourcing. With appropriate start-up timestamps, previous matching methods can perform better. Multi-armed bandit algorithm reinforcement learning adopted split batch dynamically according historical states. Extensive experimental results both real and synthetic datasets demonstrate effectiveness efficiency proposed approach.