Imagine having a giant digital warehouse full of messy notes, photos, and spreadsheets from different sources that don't speak the same language. This tool acts like a super-smart librarian that automatically organizes, labels, and connects all that clutter. It turns a chaotic pile of data into a clean, searchable map that AI can actually understand and use.
Companies struggle to use AI because their data is messy, fragmented, and lacks proper labels. Manually cleaning this data is too expensive and slow to keep up with the volume of information generated.
A Knowledge Lake Management System (KLMS) that includes a data catalog, a knowledge graph, and tools for automated data linking and annotation.
If you are an agri-tech software provider dealing with mismatched satellite images and ground sensor data — this project developed a Knowledge Lake Management System that automatically aligns different data resolutions to make them AI-ready.
If you are a food safety regulator dealing with incident reports in different languages and formats — this project developed data linking tools that connect fragmented information about the same entity across diverse sources.
If you are an agricultural data broker dealing with low-quality metadata that prevents data sharing — this project developed a system to automatically enhance metadata and create a knowledge graph for easier data discovery.
Based on available project data, specific pricing or implementation costs are not provided.
Yes, the system is designed to handle large amounts of data in Data Lakes and is being pilot tested in real-world agrifood data space use cases.
Based on available project data, the specific IP and licensing terms are not mentioned.
The system adds a knowledge layer to raw data lakes, using a data catalog and knowledge graphs to make existing assets findable and interoperable.
The project period runs from 2022-09-01 to 2025-08-31, indicating the development and testing phase is currently active.
The consortium shows a strong commercial orientation with a 44% industry ratio, comprising 4 industry partners (including 3 SMEs) and 3 universities. This balance suggests the technology is being developed with a clear eye toward market viability and practical application across 5 different countries.
Contact ATHINA-EREVNITIKO KENTRO KAINOTOMIAS for technical specifications
Contact SciTransfer to connect with the STELAR consortium for pilot opportunities.
