Creative design of emergency management scenarios driven by semantics: An application to smart cities.

We present a framework to support creative design of emergency management scenarios. By creative design of scenarios we mean the process of imagining situations and describing them through models and stories. The framework supports the tasks of gathering and organizing knowledge about emergency management situations by automatically generating conceptual models, related to fragments of emergency scenarios. It leverages semantics-based techniques to enable a computational creativity approach. A software application was defined to support the activities of modeling scenarios by permitting to generate, organize, and query sets of these conceptual models, which we name mini-stories, and that can be adopted to inspire the activity of creative design. Selected mini-stories are blueprints for more detailed user scenario descriptions and models that can be used, for instance, for analysis or simulation. As a case study, we consider emergency management in smart cities. This is a challenging domain because smart cities are characterized by interconnected physical and virtual services forming complex ecosystems, which provide sophisticated services to the population and to institutions, manage public resources in a optimal way, and involve citizens in decisional processes. As a consequence, smart city ecosystems can be threatened by several hazards spanning from natural disasters, as tsunami and earthquakes, to anthropic events, as terrorist attacks. Ability of service providers and institutional operators to face and manage emergency situations is therefore a relevant issue. Simulation and analysis of both crisis events and executions of management plans are a promising approach to deal with these articulated problems. However, manual definition of models to base the analysis is a demanding activity due to the huge number of different situations to consider. It requires knowledge related to the crisis and emergency domains, to the context (e.g., a specific city and its current regulations) and ability in modeling tasks. All these aspects demand for tools to support modeling activities, and our proposal aims at fulfilling this need. In particular, the discussed framework uses in a integrated way three types of knowledge: structural knowledge, to support the construction of models based on design patterns; domain knowledge, here related to smart cities and emergency management and represented by means of ontologies; and contextual knowledge, related to specific aspects (e.g., localization) of the considered scenario and represented as rules. We validated the presented approach by means of experiments performed by real city planners.