The European Patent Office accelerates innovation with Mistral
European Patent OfficeMistral AI OCRThe European Patent Office partnered with Mistral AI on a three-month proof of concept to automate patent document transcription. A 1B-parameter OCR model was fine-tuned on over 150,000 PDFs (50,000 unique patents) and built into a pipeline converting complex patent documents (with formulas, chemical structures, tables, and figures across multiple European languages) from Markdown to HTML to ST36-compliant XML, deployed on-premises. The system achieves 400,000 pages/day throughput with a character recognition error rate below 1%, cutting lead time from up to 5 days down to a few minutes.
Overview
The European Patent Office partnered with Mistral AI on a three-month proof of concept to automate patent document transcription. A 1B-parameter OCR model was fine-tuned on over 150,000 PDFs (50,000 unique patents) and built into a pipeline converting complex patent documents (with formulas, chemical structures, tables, and figures across multiple European languages) from Markdown to HTML to ST36-compliant XML, deployed on-premises. The system achieves 400,000 pages/day throughput with a character recognition error rate below 1%, cutting lead time from up to 5 days down to a few minutes.
This entry has 14 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Patent documents frequently embed mathematical formulas, chemical structures, detailed images, and intricate tables within text across multiple European languages, elements that are notoriously difficult for standard digital tools to interpret, often leading to incomplete or inaccurate data structuring.
The solution
The EPO partnered with Mistral AI on a three-month proof of concept, deploying a 1B OCR model fine-tuned on over 150,000 PDFs representing 50,000 unique patents, built into a pipeline that converts complex patent documents from Markdown to HTML and finally into the required ST36 XML format, ready for on-premises deployment.
Reported business value
The system achieved a throughput of 400,000 pages transcribed per day while maintaining a character recognition error rate of less than 1%, cutting lead time from up to 5 days down to a few minutes.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other government & public sector entries in the register.
GovTech unlocks data insights to improve nationwide services with Databricks
Singapore's Government Technology Agency (GovTech) migrated from an on-premises dashboarding system to the Databricks Data + AI Platform on AWS with Unity Catalog and Delta Lake, cutting dashboard creation time from 90 to 30 days, democratizing data across 50% of corporate divisions in the first year, and saving 8,000 labor hours annually.
GovTech· SingaporeDelta Lake · Lakeflow Connect · Lakeflow Jobs +1Estonia rolls out Bürokratt, an AI-guided virtual assistant network for public services
Bürokratt is a network of chatbots deployed on Estonian public sector institutions' websites, letting people obtain information from institutions and use public and information services via virtual assistants. It is a state-created, AI-based digital assistant that helps institutions deliver modern, efficient, around-the-clock customer service using large language models.
VA Advances Healthcare Insights With AI
The U.S. Department of Veterans Affairs leverages Databricks Data Intelligence to modernize healthcare analytics for millions of veterans, unifying massive distributed datasets into a single secure environment and streaming petabytes of health data in real time, reducing processes that once took hours to seconds. Databricks enables AI and large language models to detect risk early and enhance governance.
U.S. Department of Veterans AffairsDatabricks
Austrian Academy of Sciences unlocks Ancient Greek with Mistral
The Austrian Academy of Sciences (OeAW), together with its Austrian Archaeological Institute, partnered with Mistral and services partner Reply to build Apollo, described as the first advanced large language model for Ancient Greek. Apollo is trained on a specialized corpus of 600 million words of historical Greek text plus tens of thousands of published inscriptions and papyri, helping researchers reconstruct damaged texts and identify thematic connections across collections. The OeAW reports Apollo turns work that once took years into hours, addressing over one million unread Greek papyri worldwide, with future phases planned for semantic search and handwritten inscription decipherment.
Austrian Academy of Sciences· AustriaMistralWas this helpful?
Your feedback helps us improve our use case database