Glossary
What is the confidence indicator
How sure the system is about each value it read, and what to do with that.
Confidence indicator
A measure of how sure the system is that it read a particular value correctly, based on the clarity of the original and on what is plausible for that field.
It is what makes automatic reading usable. Without it you would review everything just in case; with it you review what asks to be reviewed.
How to read it
| Level | What it means | What to do |
|---|---|---|
| High | The value was read clearly | Use it |
| Medium | It was read, but something does not quite fit | A glance |
| Low | The original did not allow a clean read | Check it against the document |
Important
A low-confidence value must not be used for anything with consequences — a payment, an official registration, an access decision — without being checked. Automatic reading saves time; responsibility stays with whoever decides.
Worth knowing
If one document type always comes back low, the problem is how it arrives: ask for a better-quality original rather than reviewing each one by hand.
›Does confidence say whether the value is correct?
It says whether it was read correctly, not whether the paper tells the truth.
›Can I filter by low confidence?
Yes, and it is the efficient way to review a large batch.
›Does it rise if I correct it?
Correcting improves reading of subsequent documents of the same type.
A real case
The situation
A batch of two hundred certificates arrives for review.
What you do
- Filters by low confidence
- Reviews the eighteen that come up
What you get
Review goes from a full day to half an hour, without giving up on checking what is doubtful.
The situation
Everything is reviewed equally even though almost all of it read well.
What you do
- Sorts by confidence and starts at the bottom
What you get
Review time concentrates where the risk is.
The situation
A high-confidence figure turns out to be wrong.
What you do
- Corrects the figure and records the correction
What you get
The indicator guides, but the last word stays human.
The situation
Nobody knows what threshold to review at.
What you do
- Tries a real batch and adjusts
What you get
The threshold is set from your own data rather than a default.
The situation
One document type always comes out with low confidence.
What you do
- Checks whether the extraction model fits that format
What you get
The problem is tackled at source rather than at every review.
The situation
Two hundred figures are approved in bulk without looking.
What you do
- Sets the uncertain ones aside before approving the rest
What you get
Bulk approval stops dragging along what was failing.
This article answers
- what does confidence on an extracted value mean
- low confidence on a document
- when to review extracted data
- ocr confidence percentage