EGU General Assembly 2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Intelligent Extraction and Generation Technology of Emergency Plan

haiyang liu
haiyang liu
  • tsinghua university, Engineering physics, China (

Natural disasters will bring a huge threat to the safety of human life and property. When disasters happen, leaders at all levels need to respond in time. Emergency plans can be regarded as the effective guidance of natural disaster emergency responses, and they include the textual descriptions of emergency response processes in terms of natural language. In this paper, we propose an approach to automatically extract emergency response process models from Chinese emergency plans, and can automatically generate appropriate emergency plans. First, the emergency plan is represented as a text tree according to its layout markups and sentence-sequential relations. Then, process model elements, including four-level response condition formulas, executive roles, response tasks, and flow relations, are identified by rule-based approaches. An emergency response process tree is generated from both the text tree and extracted process model elements, and is transformed to an emergency response process that is modeled as business process modeling notation. Finally, when different disasters occur, a new plan is generated according to the training of historical plan database. A large number of experiments in the actual emergency plan show that this method can extract the emergency response process model, and can generate a suitable new plan.

How to cite: liu, H.: Intelligent Extraction and Generation Technology of Emergency Plan, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-12439,, 2020