Generating relevant scenarios for intelligent transportation service

TL;DR

This paper presents an NLP-based approach to generate relevant scenarios for intelligent transportation services, aiming to improve system requirements understanding and stakeholder decision-making.

Contribution

It introduces a novel NLP-driven method for scenario generation in transportation, enhancing consistency and completeness of system requirements.

Findings

Approach improves scenario relevance and stakeholder understanding.

Experimental results show increased consistency in system requirements.

Feedback indicates better decision support for project stakeholders.

Abstract

This paper addresses risk assessment issues while conceiving complex systems. Indeed, project stakeholders have to share the same problems understanding allowing to undertake rational and optimal decisions. We propose an approach based on Natural Language Processing (NLP) techniques to improve systems quality requirements such as consistency and completeness. We assess the relevancy of our approaches through experimentations and highlighted feedbacks from project stakeholders and players.