Workflow Management Systems + Swarm Intelligence = Dynamic Task Assignment for Emergency Management Applications

The assignment of tasks to human performers is a critical componentin people-centric business process management systems. Workflowmanagement systems typically assign work items using strategies that onlyconsider qualified resources. There are, however, situations, where thisapproach falls short. For instance, in emergency response situations, tasks needto be carried out by resources that are available immediately, even if they do notmatch all skill requirements. This paper compares the performance of a set ofsix task assignment mechanisms for workflow applications using a scenariofrom the emergency management domain. In particular, we develop andsimulate assignment strategies inspired by stimulus/response models derivedfrom swarm intelligence, and benchmark these strategies against conventionaltask assignment strategies. Our findings show that swarm intelligence-based approaches outperform the traditional assignment of tasks in ad-hoc organizations, and that workflow-based emergency management systems couldbenefit significantly from these novel task assignment strategies.