← Back to The European Patent Office accelerates innovation with Mistral

Source proof for The European Patent Office accelerates innovation with Mistral

Source-bound proof

Verified source excerpts for every supported field

Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.

14 fields supported

Title

The European Patent Office accelerates innovation with Mistral

quote · high
…Fs to structured output: automated patent transcription at scale. Public sector The European Patent Office accelerates innovation with Mistral. From PDFs to structured output: automated patent transcription at scale. The Eu…

Description

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.

derived · high
…was adapted to the EPO’s operational reality rather than the other way around.​ The core of the solution included a 1B OCR model, specifically fine-tuned on over 150,000 PDFs, representing 50,000 unique patents. The team developed a sophisticated pipeline that successfully converts complex,…
…nts of patent applications, particularly complex formulas and technical images. Specifically, the system achieved a throughput of 400,000 pages transcribed per day while maintaining a character recognition error rate of less than 1%. This benefit also allows faster processing of patent applications. The success…
…essing. Stats: 400,000 pages/day throughput 1% character recognition error rate Lead time from up to 5 days down to a few minutes "Standard OCR tools often fall short when confronted with the intricacies of pa…

Company

European Patent Office

quote · high
…, Chief Operating Officer and Chief Technology Officer, European Patent Office. The European Patent Office (EPO) is at the forefront of Europe’s innovation ecosystem. It processes millions of pages of patent documents annually, and to maintain qu…

Region

Europe

classification · high
…, Chief Operating Officer and Chief Technology Officer, European Patent Office. The European Patent Office (EPO) is at the forefront of Europe’s innovation ecosystem. It processes millions of pages of patent documents annually, and to maintain qu…

Industry

Government & Public Sector

classification · high
…touch From PDFs to structured output: automated patent transcription at scale. Public sector The European Patent Office accelerates innovation with Mistral. From PDFs to structured output: automated patent transcription at scale. The Eu…

Problem

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.

quote · high
…ary hurdle for the EPO is the extreme technical density of patent applications. Patent documents frequently embed mathematical formulas, chemical structures, detailed images, and intricate tables within text across multiple European languages. These elements are notoriously difficult for standard digital tools to interpret, often leading to incomplete or inaccurate data structuring. For the EPO, the operational reality was clear: they needed a scalable solution…

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.

derived · high
…dard ST36 XML. The EPO partnered with Mistral AI to modernize its capabilities. Over a three-month proof of concept, Mistral AI deployed advanced Optical Character Recognition (OCR) technology, achieving near-zero fault tolerance and unlocking new efficiencies in handling…
…ecifically fine-tuned on over 150,000 PDFs, representing 50,000 unique patents. The team developed a sophisticated pipeline that successfully converts complex, multifaceted patent documents from Markdown, to HTML, and finally into the required ST36 XML format. This specialized pipeline ensures the model can handle the diversity of Europea…
…application built for reliability and full compliance with industry standards, ready for on-premises deployment. Figure: Patent transcription automation with EPO fine-tuned OCR model Driving…

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.

quote · high
…nts of patent applications, particularly complex formulas and technical images. Specifically, the system achieved a throughput of 400,000 pages transcribed per day while maintaining a character recognition error rate of less than 1%. This benefit also allows faster processing of patent applications. The success…
…essing. Stats: 400,000 pages/day throughput 1% character recognition error rate Lead time from up to 5 days down to a few minutes "Standard OCR tools often fall short when confronted with the intricacies of pa…

AI capabilities

Document Intelligence

classification · high
…Mistral AI to modernize its capabilities. Over a three-month proof of concept, Mistral AI deployed advanced Optical Character Recognition (OCR) technology, achieving near-zero fault tolerance and unlocking new efficiencies in handling…

Technology

Mistral AI OCR

classification · high
…Mistral AI to modernize its capabilities. Over a three-month proof of concept, Mistral AI deployed advanced Optical Character Recognition (OCR) technology, achieving near-zero fault tolerance and unlocking new efficiencies in handling…

Headline outcome

derived · high
…ffice leverages Mistral AI to streamline complex application processing. Stats: 400,000 pages/day throughput 1% character recognition error rate Lead time from up to 5 days down to a few m…

Use case type

Document processing

classification · high
…ect Community Partners Help center Login Studio Vibe Vibe for Code Get in touch From PDFs to structured output: automated patent transcription at scale. Public sector The European Patent Office accelerates innovation with Mistral. F…

Deployment model

on-premise

classification · high
…application built for reliability and full compliance with industry standards, ready for on-premises deployment. Figure: Patent transcription automation with EPO fine-tuned OCR model Driving…

Deployment options

On-premise

classification · high
…application built for reliability and full compliance with industry standards, ready for on-premises deployment. Figure: Patent transcription automation with EPO fine-tuned OCR model Driving…
Capture details
Captured
29 Sept 2026, 06:05 UTC
Extractor
fetch-strip@1
Snapshot hash
3a97a2ee7314993c7bf42d2e2a4258419bda29a71b30fc72c26782a46068fe0a