ArcelorMittal, the world's leading steel and mining company, has selected Iris.ai, a platform that leverages AI to make the world’s research accessible, to automate some of its R&D processes. The steelmaker is using Iris.ai’s platform to significantly reduce the time required to undertake patent research by extracting experiment data and presenting it in a machine-readable format to researchers. Being able to review and process the latest patents is important for ArcelorMittal to define its competitive strategy.
ArcelorMittal is a Fortune Global 500 company, the leader in all major global steel markets, with a presence in more than 60 countries and an industrial footprint in 18 countries. It relies on its R&D function to advance products, improve manufacturing processes, deliver on its sustainability commitments, and transform itself into an AI-driven enterprise. Sitting within R&D, the patent team carries out ongoing competitive analysis to identify market gaps and patentable solutions as well as monitoring for potential patent infringements. The team searches and then extracts detailed obfuscated experiment data and uses this information to help it develop products, processes, and new formulations of compounds. Monitoring research ensures its manufacturing processes and digital factories are taking advantage of the latest scientific knowledge.
Patent research and data extraction work are integrated into the R&D process at large organisations like ArcelorMittal and are crucial to keeping abreast of the world’s latest cutting-edge research. However, the process of searching and extracting experiment data from documents is unskilled manual work that takes a significant amount of time away from skilled employees.
At ArcelorMittal, it was estimated to take the equivalent of one person-month of effort to extract data from 60 patents - or around two and a half hours per patent. This information can now be extracted and reviewed with high confidence in a matter of minutes. Iris.ai’s Extract tool has 94% precision, which compares favourably with human extraction precision. The accuracy is estimated through a self-assessment module, meaning it assesses its own extraction results and gives researchers a confidence level and requirement for additional verification.
Iris.ai’s Extract tool uses Natural Language Processing and Machine Learning to identify all appropriate domain-specific entities in the research. The tool locates and extracts data from both tables and text in a machine-readable format. This data is then inserted in an excel sheet, an integrated lab tool, a database, or anywhere else researchers require.
Sophie Plaisant, Head of the Intellectual Property for ArcelorMittal, said, “At ArcelorMittal, we are constantly looking for ways to optimise our R&D processes and this is what brought us to Iris.ai. Integrating the Extract tool into our process has made the ingestion and processing of external data significantly easier. It has cut weeks and, in some cases, months out of our research and development timelines and gives us the capacity to review more patents. Iris.ai proves there is enormous potential when research and development meets artificial intelligence, and we are only witnessing the beginning of that journey.”
Anita Schjøll Brede, CEO and co-founder of Iris.ai, said, “We live in a world where more scientific research is publicly available to us than ever before and millions of new research papers are published every year. However, to take advantage of all this research requires a significant amount of manual work.
“Countless hours are being invested in corporate R&D functions around the world manually extracting data from tables. With our Extract tool, it’s possible to automate this manual work to free up time so researchers can focus on carrying out valuable research.
“Through our platform, ArcelorMittal is saving a significant amount of time on manual extraction which means it can focus on its R&D goals of improving manufacturing processes, developing new products, reaching its sustainability goals, and transforming itself into an AI-driven enterprise.
“Our vision is to help the world’s scientists and engineers work more closely together and use each other’s research more efficiently.”