SPDTM: A shapley-value based preference discovery and task matching to maximize satisfaction in mobile crowd sensing

Zhongxin Huang, Zanbo Sun, Wei Tan, Houbing Herbert Song, Tian Wang, Shaobo Zhang, Anfeng Liu

Abstract: Mobile Crowd Sensing (MCS) is a widely adopted paradigm for task-centered data collection. Researchers have noticed that assigning workers to their preferred tasks can improve the task completion rate and satisfaction of MCS. However, there are still some key issues in current research that have not been addressed. First, MCS heavily rely on the impractical assumption that worker-task preferences are prior known for optimal matching. In actual MCS, such preferences are difficult to obtain, and dishonest workers may report false preferences to gain illegal rewards. Second, there are numerous eligible workers for each task in MCS, which makes task difficult to match with highest preference worker. To tackle these challenge issues, a Shapley-value based Preference Discovery and Task Matching (SPDTM) scheme is proposed to maximize task-worker satisfaction. The SPDTM scheme primarily includes three components. First, a Shapley-value based task to workers preference discovery is designed to obtain the true preferences of task to workers based on the contribution of workers. Then, we propose an optimized strategy for selecting workers by trade-off exploration and exploitation. Finally, based on worker preferences discovery and satisfaction improvement, we propose a matching algorithm for task-worker assignment. The outcomes of our experiments indicate that the SPDTM scheme improves task-worker matching satisfaction by 26.01 %, and the detection rate of workers’ true preferences has reached 94.79 %.

External IDs:dblp:journals/cn/HuangSTSWZL25