Search

Semi-structured decisions, which fall between highly structured and unstructured decision types, rely on human intuition and experience for the final choice, while using data and analytical models to generate tentative solutions. These processes are traditionally iterative and time-consuming, requiring cycles of data gathering, analysis, and option evaluation. In this study, we propose a novel framework that integrates Large Language Models (LLMs) with optimization techniques to streamline such decision-making processes. In our approach, LLMs leverage their capabilities in data interpretation, common-sense reasoning, and mathematical modeling to assist decision makers by reducing cognitive load. They achieve this by automating aspects of information processing and option evaluation, while preserving human oversight as a crucial component of the final decision-making process. Another significant strength of our framework lies in its potential to drive the evolution of a new generation of decision support systems (DSSs). Unlike traditional systems that rely on rigid and inflexible interfaces, our approach enables users to express their preferences in a more natural, intuitive, and adaptable manner, substantially enhancing both usability and accessibility. A case study on last-mile delivery system design in a smart city demonstrates the practical application of this framework. The results suggest that our approach has the potential to simplify the decision-making process and improve efficiency by reducing cognitive load, enhancing user experience, and facilitating more intuitive interactions. [ABSTRACT FROM AUTHOR]

The hospital is essential for managing the health of citizens with a high degree of complexity. The hospital system is very energy-intensive, presents rapid technological obsolescence and often requires specific and multidisciplinary skills to also manage new clinical-health organizational models for the dynamic change of functional needs and the management of emergencies (e.g. Covid 19 pandemic). The proposed methodology en-visages the pervasive use of renewable energy and the modeling of the digital twin of the building with system solutions specifically designed to increase the comfort of the users of the structure and optimize the maintainability of the systems. These systems, thanks to artificial intelligence software, after an initial period of “learning” the behavior of the building, are able to dynamically simulate different ways of operating the systems in order to pursue the model capable of maximizing the energy saving of the building. The advanced energy monitoring system (BEMS - Building Energy Management System) allows to guarantee the monitoring of the pre-established performance indicators with undoubted advantages from the point of view of the reduction of the primary energy necessary for the functioning of the structure, the study of consumption for cost, air quality and resource consumption.