The rapid growth of smart home technologies, driven by the expansion of the Internet of Things (IoT), has introduced both opportunities and challenges in automating daily routines and orchestrating device interactions. Traditional rule-based automation systems often fall short in adapting to dynamic conditions, integrating heterogeneous devices, and responding to evolving user needs. To address these limitations, this study introduces a novel smart home orchestration framework that combines generative Artificial Intelligence (AI), Retrieval-Augmented Generation (RAG), and the modular OSGi framework. The proposed system allows users to express requirements in natural language, which are then interpreted and transformed into executable service bundles by large language models (LLMs) enhanced with contextual knowledge retrieved from vector databases. These AI-generated service bundles are dynamically deployed via OSGi, enabling real-time service adaptation without system downtime. Manufacturer-provided device capabilities are seamlessly integrated into the orchestration pipeline, ensuring compatibility and extensibility. The framework was validated through multiple use-case scenarios involving dynamic device discovery, on-demand code generation, and adaptive orchestration based on user preferences. Results highlight the system’s ability to enhance automation efficiency, personalization, and resilience. This work demonstrates the feasibility and advantages of AI-driven orchestration in realising intelligent, flexible, and scalable smart home environments.
In the last years, there has been an increasing amount of data published in different sources, formats, and structures that could be useful for various purposes: learning about a topic, discovering trends, and monitoring public opinion, among others. To facilitate access to this data and, more importantly, to identify the most interesting information in the set, in this poster, we present an interactive tool aimed at extracting and processing collections of unstructured text data to create a knowledge graph that users can explore and edit. The tool has been designed in three modules: gathering information, processing texts, building relations, and visualizing the knowledge base. The user can interact with these steps, particularly by exploring the visualization and changing the concepts and the relations using either a graphical or textual view.