Document data capture
An OCR-ready document data model stores the status, extracted fields and raw results of document reading alongside each case. Officers see the results read-only next to the original file, and the reading engine can be added or replaced later without changing the case workflow.
What it does
Structured document records
Each document carries its status, extracted fields and results.
Read-only review
Officers compare extracted data with the original file.
Engine independent
The reading engine can be connected or changed later.
Common questions
What is an OCR-ready document data model?
It is a case data structure with fields for document reading status, extracted data and raw results, ready for an OCR engine to fill.
Which documents does it cover?
Any document attached to a case, such as payslips or supporting letters. The fields are defined per document type.
Does it include the reading engine?
The data model and review screens are ready. The reading engine is chosen and connected per project.
Have a process you want to automate?
Tell us how the work runs today. We will reply with the next step and a quote in RM.