A carregar...
Publicação
Chatbots, para transformar a experiência e interação do utilizador em cenários imersivos 3D
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 6.3 MB | Adobe PDF |
Orientador(es)
Resumo(s)
A crescente adoção de ambientes tridimensionais imersivos em contextos comerciais criou uma necessidade crítica por interfaces conversacionais inteligentes que transcendam as limitações dos chatbots bidimensionais tradicionais. Esta dissertação apresenta o desenvolvimento de um sistema integrado que combina agentes conversacionais baseados em Inteligência Artificial (IA) com ambientes de realidade virtual. O sistema implementa uma arquitetura Retrieval-Augmented Generation (RAG) que garante respostas factuais precisas por meio de um pipeline automatizado para aquisição e processamento de dados da web, combinando modelos de linguagem em grande escala (GPT-4o-mini) com bancos de dados vetoriais (Pinecone), processamento de voz em tempo real (Convai) e ambientes Tridimensional (3D) desenvolvidos no Unity, otimizados para dispositivos Meta Quest. A avaliação empírica em dois cenários comerciais distintos (BNH e Rádio Popular) demonstrou uma taxa de sucesso geral de 94,6%, com tempos médios de resposta de 2,17 segundos, validando a eficácia da arquitetura proposta. O sistema inclui uma plataforma de gestão administrativa que permite monitorização em tempo real, análise de padrões de utilização e controlo dinâmico da base de conhecimento, garantindo a conformidade com o Regulamento Geral de Proteção de Dados (GDPR) através de mecanismos de anonimização automática. Os resultados confirmam a viabilidade técnica e a aplicabilidade comercial de agentes conversacionais em ambientes imersivos, demonstrando generalização em diferentes domínios e abrindo caminho para novas formas de interação humano-computador em contextos de comércio eletrónico e atendimento ao cliente.
The growing adoption of immersive three-dimensional environments in commercial contexts has created a critical need for intelligent conversational interfaces that transcend the limitations of traditional two-dimensional chatbots. This dissertation presents the development of an integrated system that combines artificial intelligence based conversational agents with virtual reality environments. The system implements a RAG architecture that ensures accurate factual responses through an automated pipeline for web data acquisition and processing, combining large-scale language models (GPT-4o-mini) with vector databases (Pinecone), real-time voice processing (Convai), and 3D environments developed in Unity, optimised for Meta Quest devices. Empirical evaluation in two distinct commercial scenarios (BNH and Rádio Popular) demonstrated an overall success rate of 94.6%, with average response times of 2.17 seconds, validating the effectiveness of the proposed architecture. The system includes an administrative management platform that allows real-time monitoring, analysis of usage patterns, and dynamic control of the knowledge base, ensuring compliance with the GDPR through automatic anonymisation mechanisms. The results confirm the technical feasibility and commercial applicability of conversational agents in immersive environments, demonstrating generalisation across different domains and paving the way for new forms of human-computer interaction in e-commerce and customer service contexts.
The growing adoption of immersive three-dimensional environments in commercial contexts has created a critical need for intelligent conversational interfaces that transcend the limitations of traditional two-dimensional chatbots. This dissertation presents the development of an integrated system that combines artificial intelligence based conversational agents with virtual reality environments. The system implements a RAG architecture that ensures accurate factual responses through an automated pipeline for web data acquisition and processing, combining large-scale language models (GPT-4o-mini) with vector databases (Pinecone), real-time voice processing (Convai), and 3D environments developed in Unity, optimised for Meta Quest devices. Empirical evaluation in two distinct commercial scenarios (BNH and Rádio Popular) demonstrated an overall success rate of 94.6%, with average response times of 2.17 seconds, validating the effectiveness of the proposed architecture. The system includes an administrative management platform that allows real-time monitoring, analysis of usage patterns, and dynamic control of the knowledge base, ensuring compliance with the GDPR through automatic anonymisation mechanisms. The results confirm the technical feasibility and commercial applicability of conversational agents in immersive environments, demonstrating generalisation across different domains and paving the way for new forms of human-computer interaction in e-commerce and customer service contexts.
Descrição
Palavras-chave
Chatbots Ambientes 3D Realidade virtual Inteligência artificial