Streamlining and Integrating Incident Data for Improved Accuracy and Consistency

Start year: 2024

Summary: Due to the multiplicity of sources, incidents are often recorded redundantly, with variations in descriptions, event types, locations, and timelines. This project aims to develop a robust, automated approach by leveraging three advanced AI methods: Large Language Models (LLMs), Fuzzy Machine Learning (Fuzzy-ML), and Bayesian Deep Learning (BDL). By utilising advanced natural language processing, data analysis and machine learning techniques, and uncertainty estimation, the approach will reconcile disparate information sources, resolve conflicts, extract key incident information, and produce accurate, consistent incident documentation. The outcome of this project is expected to yield accurate and consistent incident records, providing better insights for enhanced decision-making.