Case Study: Boehringer Ingelheim achieves a full-text searchable archive and faster information retrieval with ABBYY Recognition Server

Detailed Document Capture Serving Public Health

Boehringer Ingelheim, a global research-driven pharmaceutical company, faced a massive document challenge: an archive of up to 50-year-old product licensing records—about 30 million pages—with no full-text search capability and roughly 10,000 new pages scanned daily. Finding specific information was time-consuming and costly, so the company needed a precise, stable OCR solution that could be integrated into existing systems and handle large, continuous volumes.

They implemented ABBYY Recognition Server, a scalable server-based OCR platform with a flexible API, central management console and automatic job distribution (installed with four processing stations). The system converts scans into searchable PDFs and indexable text, attaches results to original records, and prioritizes new documents. Deployed on time and within budget, the solution enabled full-text search across the archive, continuous processing of new documents, and significantly faster, more efficient information retrieval.

Boehringer Ingelheim

Dirk Ehrhard

Boehringer Ingelheim