A Method for Automatically Extracting Emergency Response Process Model from Emergency Plan

Abstract

The invention discloses a method for automatically extracting an emergency response process model from an emergency plan, which belongs to the field of process mining, and adopts an emergency plan text paragraph structure tree construction module, a four-level response start condition expression extraction module, and a process model entity element The extraction module, the process model relationship element extraction module, the emergency response process tree generation module and the emergency response process directed graph model generation module; specifically include the following steps: construct the text paragraph structure tree of the emergency plan; extract the emergency response process model elements; generate the emergency response process model. The invention firstly generates an emergency response process tree according to the extracted process model elements and text paragraph structure tree, and then transforms it into a directed graph model of the emergency response process. The invention can not only assist modeling experts to complete the construction and analysis of the emergency response process model, but also can be used for checking and revising the text of the emergency plan for emergencies.

Description

technical field [0001] The invention belongs to the field of flow mining, and in particular relates to a method for automatically extracting an emergency response flow model from an emergency plan. Background technique [0002] There are three main solutions for current process modeling: one is to manually create process models by domain modeling experts based on experience; the other is to generate process models from log files through process mining algorithms; the third is to use natural language processing technology to extract process models from text Model. [0003] Emergency response to emergencies is a complex process of multi-department and multi-organization linkage coordination, and the emergency response process has important guiding significance for the effective implementation of the entire response process. The emergency response process model for emergencies should not only clearly show the corresponding relationship between emergency response tasks and exec...

AI Technical Summary

Problems solved by technology

The extraction of relational elements first needs to analyze the corpus data to construct a dictionary of process relational words, and then use character matching to complete the extraction of relational elements. This method lacks universal applicability, and it takes a lot of time and effort to analyze the text

Therefore, the extraction of process model entity elements in this scheme is easy, but the extraction of relational elements is not only difficult but also poor in portability

[0006] Comprehensive analysis of the above three methods, the process model generated by the first expert modeling scheme is correct and usable, but it is too difficult to find a process modeling expert in this emergency field

The second method mines the process model from the event log. The existing process mining algorithm is very mature, but for the emergency response process of the lack of information system, the relevant event log data cannot be obtained.

The third method has a large difference between the extraction object and the text of the emergency plan, and is not suitable for the extraction process of the text of the emergency plan

Images