From PDF invoice to PEPPOL e-invoice in plain English
A regular PDF invoice is a printable document β humans can read it, but a computer cannot reliably tell the supplier name from the buyer address, or the line totals from the grand total. An e-invoice (electronic invoice) solves that by encoding all the same information as structured fields in an XML document. The dominant European format is PEPPOL BIS Billing 3.0, built on the EN 16931 norm and serialised as UBL 2.1 XML.
Converting a PDF to an e-invoice means extracting every field on the page β supplier identity and VAT number, buyer details, invoice number and dates, every line item with its quantity, unit price and VAT rate, payment terms, totals β and rebuilding it as a UBL 2.1 XML document that conforms to PEPPOL BIS 3.0. aiDoks handles both halves automatically: AI OCR for the extraction, a PEPPOL-aware form for review and editing, and an XML export for delivery.
What if the OCR misses something?
OCR is excellent on clean PDFs and high-resolution scans, but no system is perfect. After extraction, the data lands in an editable PEPPOL BIS 3.0 form β you can correct any field, add or remove invoice lines, and tweak VAT categories. The validator runs as you type, flagging missing mandatory fields and rule violations with the exact rule ID (for example BR-CO-15 for tax-total mismatches). When the form is clean, click export.
Output formats and downstream use
Every converted invoice produces two files. The UBL 2.1 XML is the machine-readable e-invoice, ready to upload to a PEPPOL Access Point, send via email to a buyer's e-invoicing inbox, or import into Xero, SAP, Odoo, Standard Books or any PEPPOL-capable accounting system. The PDF rendering is for archive, printing and human review β many businesses send both side by side.
Privacy and data handling
aiDoks does not retain your PDFs or extracted data on its servers after conversion. All processing is done over TLS and the platform is GDPR-compliant. See the security page for details.