Organisations heavily dependent on paper documents still spend a significant amount of time managing a large volume of documents. An intelligent document management system (DMS) is presented to automate the processing of tax and administrative documents. The proposed system fills a gap in the landscape of practical tools in the field of DMS and advances the state of the art. This system represents a complex process of integrated AI-powered technologies that creates an ontology, extracts information from documents, defines profiles, maps the extracted data in RDF format, and applies inference through a reasoning engine. The DMS was designed to help all those companies that manage their clients’ tax and administrative documents daily. Automation speeds up the management process so that companies can focus more on value-added services. The system was tested in a case study that focused on the preparation of tax returns. The results demonstrated the efficacy of the system in providing document management service.

Writing study regulations for academic study programs and automatically implementing those regulations is a difficult task that involves a variety of actors and requires at each step careful compliance to the constraints defined in the regulations. This paper describes: (1) the innovation process, taking place through a hands-on experiment, that lead the R&D Unit of the University of Geneva to provide a proposal for a digital service targeting the above purpose; (2) the actual design of such a digital service, providing various functionalities: (a) the elaboration of study regulations; (b) the elaboration of the corresponding study plan; (c) the actual implementation of the study plan through the information system. The digital service relies on two main ideas: (1) all study regulations and study plans are built from common atomic elements, that we call building blocks; (2) ensuring compliance to various constraints is achieved through a reasoning engine capturing the constraints defined over an ontology of the study regulations domain. Each year, for a given University, several study regulations, with various constraints and structure are defined or updated. They all need to be carefully crafted and implemented. The work presented in this paper has the potential to alleviate and improve this task for the various actors involved (students, program directors, lawyers, scientific committee members, study advisor, information systems managers, students’ office).

Collective behaviour in nature provides a source of inspiration to engineer artificial collective adaptive systems, due to their mechanisms favouring adaptation to environmental changes and enabling complex emergent behaviour to arise from a relatively simple behaviour of individual entities. As part of our ongoing research, we study the social amoeba Dictyostelium discoideum to derive agent-based models and mechanisms that we can then exploit in artificial systems, in particular in swarm robotics. In this paper, we present a selection of agent-based models of the aggregation phase of D. discoideum, their corresponding biological illustrations and how we used them as an inspiration for transposing this behaviour into swarms of Kilobots. We focus on the stream-breaking phenomenon occurring during the aggregation phase of the life cycle of D. discoideum. Results show that the breakup of aggregation streams depends on cell density, motility, motive force and the concentration of cAMP and CF. The breakup also comes with the appearance of late centres. Our computational results show similar behaviour to our biological experiments, using Ax2(ka) strain. For swarm robotics experiments, we focus on signalling and aggregation towards a centre.

By studying and modelling the behaviour of Dictyostelium discoideum, we aim at deriving mechanisms useful for engineering collective artificial intelligence systems. This paper discusses a selection of agent-based models reproducing second-order behaviour of Dictyostelium discoideum, occurring during the migration phase; their corresponding biological illustrations; and how we used them as an inspiration for transposing this behaviour into swarms of Kilobots. For the models, we focus on: (1) the transition phase from first- to second-order emergent behaviour; (2) slugs’ uniform distribution around a light source; and (3) the relationship between slugs’ speed and length occurring during the migration phase of the life cycle of D. discoideum. Results show the impact of the length of the slug on its speed and the effect of ammonia on the distribution of slugs. Our computational results show similar behaviour to our biological experiments, using Ax2(ka) strain. For swarm robotics experiments, we focus on the transition phase, slugs’ chaining, merging and moving away from each other.