Classification & splitting
Send one big file. Sigixtract works out what is inside it, separates each document and routes it to the right workflow.
What it handles
- Bundles of mixed documents in one PDF
- Multi-page scans from shared scanners
- Email attachments of different types
- Files with missing or duplicate pages
What you get
- Each document separated with page ranges
- A type label on every document
- Routing to the correct extraction flow
- Early warnings for unreadable or incomplete files
Built for real-world documents
Automatic splitting
A 60-page upload becomes the invoices, statements and IDs inside it.
Type recognition
Documents are labelled so each follows the right rules and queues.
Quality checks at the door
Blurred pages and missing pages are flagged before they cause problems later.
What comes back, and what gets checked
Each document returns structured fields with confidence scores, plus the results of your validation rules. Anything uncertain goes to review.
From document to data in four steps
Collect
Documents arrive by email, upload, SFTP or API.
Read
Sigixtract classifies, splits and extracts the fields and tables.
Check
Your rules and cross-checks run on every document.
Deliver
Clean data goes to your systems. Exceptions go to review.
Common questions
Can it handle a document type it has not seen?
Yes. Tell us the new type and we configure it. You do not need to supply training data to begin.
What happens to files it cannot classify?
They go to a review queue where a person assigns the type once, and the system learns from it.
Related
Document extraction
Capture every field and table row from any business document, with a confidence score on each value.
ProductWorkflow automation
Move every document from inbox to decision. Collect, classify, extract, check and deliver without manual hand-offs.
DocumentBill of lading data extraction
Capture shipper, consignee, vessel, ports, containers and cargo details from bills of lading.
See Sigixtract on your own documents
Send us a real invoice, statement or form. We will show you every field extracted and checked.