Percorrer por autor "Sousa, Paulo Gandra de"
A mostrar 1 - 5 de 5
Resultados por página
Opções de ordenação
- Automated extraction of insurance product characteristicsPublication . Oliveira, Francisco; Sousa, Paulo Gandra de; Faria, Luiz; Faria, Luiz; Cardoso, Duarte; Teixeira, JoãoThe increasing complexity and diversity of insurance products have highlighted the need for efficient methods to interpret and manage the detailed information present in regulatory documents. This project explores the application of Natural Language Processing (NLP) and Large Language Models (LLMs) in the automatic extraction of relevant characteristics of these products, addressing challenges such as structuring technical texts and accurately identifying rules, conditions, and variations. The research focuses on analyzing the state of the art in technologies such as vector databases, LLMs, knowledge graphs, and agentic workflows, as well as evaluating NLP tools and methodologies. The text goes on to explore the primary challenges encountered during the interpretation of insurance documentation, as well as the transformation of unstructured data into organized formats that are compatible with modelling systems. The solution developed responded satisfactorily to the objectives established, enabling the structured and consistent extraction of product characteristics from regulatory documents. To this end, AI agent-based workflows were used, supported by LLMs and validation schemes, ensuring the quality and consistency of the results.
- Elements of scalable data processingPublication . Andersson, Björn; Sousa, Paulo Gandra de; Pacheco, Filipe; Andreou, Panayiotis; Marrón, Pedro; Iqbal, UmerCooperating objects (COs) is a recently coined term used to signify the convergence of classical embedded computer systems, wireless sensor networks and robotics and control. We present essential elements of a reference architecture for scalable data processing for the CO paradigm.
- Operational modal monitoring of ancient structures using wireless technologyPublication . Aguilar, Rafael; Ramos, Luis; Lourenço, Paulo; Severino, Ricardo; Gomes, Ricardo; Sousa, Paulo Gandra de; Alves, Mário; Tovar, EduardoOperational Modal Analysis is currently applied in structural dynamic monitoring studies using conventional wired based sensors and data acquisition platforms. This approach, however, becomes inadequate in cases where the tests are performed in ancient structures with esthetic concerns or in others, where the use of wires greatly impacts the monitoring system cost and creates difficulties in the maintenance and deployment of data acquisition platforms. In these cases, the use of sensor platforms based on wireless and MEMS would clearly benefit these applications. This work presents a first attempt to apply this wireless technology to the structural monitoring of historical masonry constructions in the context of operational modal analysis. Commercial WSN platforms were used to study one laboratory specimen and one of the structural elements of a XV century building in Portugal. Results showed that in comparison to the conventional wired sensors, wireless platforms have poor performance in respect to the acceleration time series recorded and the detection of modal shapes. However, for frequency detection issues, reliable results were obtained, especially when random excitation was used as noise source.
- Quality-of-service in wireless sensor networks: state-of-the-art and future directionsPublication . Alves, Mário; Baccour, Nouha; Koubâa, Anis; Severino, Ricardo; Dini, Gianluca; Pereira, Nuno; Sá, Rui; Savino, Ida; Sousa, Paulo Gandra deWireless sensor networks (WSNs) are one of today’s most prominent instantiations of the ubiquituous computing paradigm. In order to achieve high levels of integration, WSNs need to be conceived considering requirements beyond the mere system’s functionality. While Quality-of-Service (QoS) is traditionally associated with bit/data rate, network throughput, message delay and bit/packet error rate, we believe that this concept is too strict, in the sense that these properties alone do not reflect the overall quality-ofservice provided to the user/application. Other non-functional properties such as scalability, security or energy sustainability must also be considered in the system design. This paper identifies the most important non-functional properties that affect the overall quality of the service provided to the users, outlining their relevance, state-of-the-art and future research directions.
- Simplifying complex insurance product management with AIPublication . Teixeira, João; Sousa, Paulo Gandra de; Cardoso, Duarte; Faria, Luiz; Oliveira, FranciscoThe digital transformation of the insurance sector presents significant challenges in internal processes, particularly in the management of product information. These challenges arise from the high complexity and variability of insurance product models, which are frequently updated, and from the technical demands of existing tools that require extensive user expertise to operate effectively. Recent advances in Generative Artificial Intelligence (GenAI) and the growing use of Large Language Models (LLMs) and intelligent agents are opening up new opportunities to automate and streamline processes, enabling organizations to adapt to a rapidly evolving technological landscape. The Product Machine Explorer leverages Generative AI, Large Language Models (LLMs), and AI agents to make exploring insurance product models easier. Integrated with msg Life Iberia’s Product Machine platform, it allows users to interact with complex product data using natural language. By leveraging structured data and advanced query techniques, it can understand user requests and deliver accurate, context-aware responses, improving both efficiency and usability in product model exploration. Built using the Evaluation-Driven Development (EDD) methodology and supported by software, prompt, and context engineering, the tool was assessed using defined metrics and expert feedback. The results demonstrate significant efficiency improvements, with professionals spending considerably less time on repetitive tasks. Overall, the Product Machine Explorer demonstrates how LLM-powered agents can simplify complex information management and support better decision-making in the insurance sector.