Abstract
Emergency response of natural disaster is a complex process involving multiple response levels and cross-organization collaboration. Traditionally, cross-organization collaborative process models of emergency response are constructed based on the common experiences of domain experts and business process modelers. Textual emergency plans are not conducive to emergency performers quickly understanding response tasks and managers analyzing and evaluating the quality of emergency plans of natural disaster. In this paper, a novel approach is proposed to automatically extract cross-organization collaborative process models from emergency plans for supporting emergency response process modeling and the automation analysis of emergency plans. First, an attention mechanism is introduced into the Bi-directional Long Short-Term Memory network combined with a Conditional Random Field (BiLSTM-Attention-CRF), which is trained to identify process elements from sentences. Second, inter-organization relationships are extracted to generate a cross-organization collaborative network of emergency response. Then, response tasks and task relationships are extracted to generate emergency response sub-process models for all organizations. Finally, inter-organization relationships integrate all sub-process models into a global cross-organization collaborative process model of emergency response. A real-world dataset is collected for experimental evaluation and the results illustrate that the proposed approach is capable of extracting automatically cross-organization collaborative process models from emergency plans of natural disaster, and the automatically extracted models are highly consistent with the manually extracted models.