System for automatically processing phyto-pharmaceutical data
For our foreign client we have developed a system that extracts relevant data from pdf documents that contain a variety of information on pharmaceutical and phyto-pharmaceutical products and transforms them into tabular form.
When developing the system we have stumbled upon many challenges – from converting pdf files to reasonable structure of textual data (arranged in tables for example).
The system is currently processing ten thousand documents. For every document input the subscriber spends approximately one tenth of the time that he needed for carrying out the same tasks before the introduction of the system.
We are developing the system even more with adding the intelligence of data identification and filters for enabling imports of other types of documents as well.