One of the key results of the Teaming.AI project are new methods to extract industrial data at scale and transform them into integrated knowledge graphs at production time. The constructed graphs are dynamically populated to provide contextual information to human and AI agents and enable low-latency decision support.
The methods are grounded in standard representations (e.g., RDF) and integrate data based on several well-established industrial methods and standards (e.g., FMEA, PPR models, etc.), but a key innovation is that the methods tackle scalability challenges and enable semantic data integration in industrial settings. The resulting industrial knowledge graphs provide a shared knowledge space to enable collaborative problem solving and a flexible foundation for AI/ML applications.
| Web resources: | https://www.teamingai-project.eu/exploitable-results |
The method provides a modular approach for knowledge graph population and curation from complex and heterogeneous industrial/manufacturing domains. It helps different stakeholders to represent and share their mental models in a uniform standard representation that can be interpreted by both humans and AI agents.