A novel data–intelligence–driven three–stage dynamic model for resilience assessment in an emergency material support system

Abstract

Resilience is a crucial benchmark in characterizing the comprehensive capability of the emergency material support system (EMSS) to respond to major risk events. Given the involvement of multiple stakeholders, multiple stages and dynamic evolution, EMSS resilience assessment remains a challenge. Therefore, we attempt to develop a novel data–intelligence–driven three–stage dynamic model based on multi–source text data and multi–expert knowledge. In Stage 1, a large language models–enhanced named entity recognition model is proposed to extract and analyze EMSS risk events, providing a foundational dataset for scenario construction. In Stage 2, an ontology–based scenario construction model is proposed to abstract risk events into ontological concepts, providing a feature reference for the hierarchical system of assessment criteria. In Stage 3, a feature–matching assessment model is proposed to quantify the profile of EMSS resilience, where the uncertainty and variability in experts’ perceptions of resilience feature are addressed. Subsequently, the model effectiveness is demonstrated in a case study, in which the key criteria and improvement paths for EMSS resilience are identified. This study provides a holistic solution and efficient methodology for EMSS resilience assessment, offering significant insights into a multifaceted recognition of EMSS resilience to risk scenarios.