What is a duplicate document?
A duplicate is the same document received or uploaded more than once. It can be an identical file, or two different files that represent the same item: a scan and a photo of the same invoice, a renamed file, a copy sent by two people. Koncile analyzes the content of each document on upload and flags those that match a document already processed.
Why do duplicates slip through?
The same documents often circulate several times without anyone noticing. Duplicates create double payment risk, extra costs and needless manual checks.
Repeat sends
A vendor resends the same invoice, or several colleagues forward the same file.
Double scanning
A packing slip is scanned twice, or scanned and then photographed.
Automatic copies
A shared inbox gets the same file in copy, or a feed duplicates it.
How does duplicate detection work?
Detection is on from the first upload, with no setup. It combines several analyses to recognize the same document in different forms.
- Step 1
Content
Text, figures and extracted fields are compared.
- Step 2
Layout
Blocks, tables and logos are checked side by side.
- Step 3
Context
Dates, vendors and key identifiers are verified.
- Step 4
Similarity
A score measures the match with existing files.
- Step 5
Alert
Above the threshold, the file goes to duplicates.
What happens when a duplicate is found?
The document is put on hold and is not processed until you decide: no extraction, no push to your ERP or accounting system. It is linked to the original so you can compare both. You confirm the duplicate, or dismiss the alert to run normal processing. A webhook notification can alert your system.
A document that was actually changed, such as an amendment or a corrected invoice, is treated as a new document.
How much does duplicate detection cost?
It is included in every plan, with no extra credits: you pay for page analysis, and the comparison runs at the same time. Plan details are on the pricing page.
An AI OCR built for security
Your documents are never used to train a model. Fully encrypted software, secure storage of extracted data, a SOC 2 certified and GDPR compliant platform.
Duplicate detection FAQ
What is Koncile?
Koncile is document extraction and automation software. It turns invoices, quotes, purchase orders, contracts, IDs or prescriptions into usable data, in Excel, in JSON or straight into your tools by API.
How do I turn on duplicate detection?
It is on by default. Every document uploaded through the app, the API or email is compared with your library, and duplicates show up in the Status column.
Does Koncile catch duplicates when the files differ?
Yes. Koncile compares the content and structure of the document, and spots the same invoice photographed at another angle, scanned in another format or renamed.
Does detection work on handwritten documents?
Yes, thanks to handwriting reading and layout analysis. Results depend on how legible the document is.
What is the difference between a duplicate and a reissued copy?
A duplicate is the same document received more than once, often by mistake. A reissued copy is a deliberate new version. Koncile flags the duplicate and lets you decide.
Can I process a batch of hundreds of documents?
Yes. Each file in the batch is compared individually with your entire document library.
