Online Spatial Crowdsourcing Matching Algorithm for Disaster Relief
After disasters,people often post information about volunteer rescue efforts and requests for help from the affected on social media platforms.Extracting the information of help task and rescue personnel from these data and making a reasonable match between them can provide effective support for rescue.In this paper,spatial crowdsourcing technology is introduced into the field of disaster relief,and online spatial crowdsourcing matching problem for disaster relief is proposed.The disaster event information extraction model is constructed by using deep learning classification method and large-scale language model to realize the accurate extraction of rescue and help information.The task rating method and dynamic loss measurement are designed to reflect the urgency of the task and the dynamic change of the loss.A greedy algorithm combining preempt and delay strategies is proposed based on dynamic loss measurement.Through detailed experimental analysis of real data sets and synthetic data sets,the total loss of the greedy algorithm combining preempt and delay strategies is reduced by at least 35%compared with the existing algorithm,and the effectiveness of the proposed algorithm is verified.
spatial crowdsourcingdisaster relieftask matchingtask levelminimum loss
万方数据
维普
