DATA-WA: Demand-based Adaptive Task Assignment with Dynamic Worker Availability Windows
Jinwen Chen, Jiannan Guo, Dazhuo Qiu, Yawen Li, Guanhua Ye, Yan Zhao, Kai Zheng
TL;DR
This paper tackles the Adaptive Task Assignment (ATA) problem in spatial crowdsourcing by incorporating future demand dynamics and dynamic worker availability windows. It introduces DATA-WA, a two-phase framework that first predicts spatio-temporal task demands using a Dynamic Dependency-based Graph Neural Network (DDGNN) with a learned demand graph, and then assigns tasks through a Worker Dependency Separation (WDS) scheme and a reinforcement learning–driven Task Value Function (TVF) to guide adaptive sequences. Key contributions include the Dynamic Dependency Learning module for end-to-end adjacency learning, a tree-structured, partitioned search to prune the assignment space, and an online adaptive algorithm that updates plans in real time, validated on real Yueche and DiDi datasets. The approach demonstrates improved task coverage and practical efficiency, offering a scalable solution for real-time, demand-aware spatial crowdsourcing systems.
Abstract
With the rapid advancement of mobile networks and the widespread use of mobile devices, spatial crowdsourcing, which involves assigning location-based tasks to mobile workers, has gained significant attention. However, most existing research focuses on task assignment at the current moment, overlooking the fluctuating demand and supply between tasks and workers over time. To address this issue, we introduce an adaptive task assignment problem, which aims to maximize the number of assigned tasks by dynamically adjusting task assignments in response to changing demand and supply. We develop a spatial crowdsourcing framework, namely demand-based adaptive task assignment with dynamic worker availability windows, which consists of two components including task demand prediction and task assignment. In the first component, we construct a graph adjacency matrix representing the demand dependency relationships in different regions and employ a multivariate time series learning approach to predict future task demands. In the task assignment component, we adjust tasks to workers based on these predictions, worker availability windows, and the current task assignments, where each worker has an availability window that indicates the time periods they are available for task assignments. To reduce the search space of task assignments and be efficient, we propose a worker dependency separation approach based on graph partition and a task value function with reinforcement learning. Experiments on real data demonstrate that our proposals are both effective and efficient.