Speaker
Description
Model based approaches have proved to be efficient in supporting engineering activities, with models replacing traditional document based approaches. Nevertheless even in the most advanced deployments, a lot of engineering artifacts are textual either because the return on investment of introducing models is too low or because the information is more efficiently expressed in natural language even if consistency and correctness issues appear. On the other hand, huge progress has been made with AI-based Natural Language Processing (NLP), mainly driven by chatbots and vocal home assistant usages. The activity presented here consisted in assessing how to spin in NLP technologies into the space engineering process, to support engineers in their daily activities. Multiple use cases were captured and ranked according to the user interest and technical feasibility. Eventually 5 use cases were selected to be demonstrated in the study including, for instance, semantic search through model and textual artefacts, or traceability between two set of artefacts (e.g., between two specification for satisfaction links or between functions and related requirements). For each use case, an investigation phase was done where multiple implementation options were studied and the retained principle was integrated into a micro-service single search architecture (with an unified web interface) capable to support almost all use cases and sourcing its data (the engineering artefacts) into a knowledge graph structured by an ontology very similar to OSMoSE's.
