Extract data from certificates of origin

A certificate of origin certifies where goods were manufactured, and it is the document that decides whether a shipment qualifies for a preferential tariff or clears at the standard rate. Customs brokers and trade-compliance teams handle two broad kinds: a generic certificate, often stamped by a chamber of commerce, and a preferential certificate tied to a trade agreement such as the USMCA, which secures a reduced duty. Fields are consistent: the exporter and producer, the consignee, the country of origin, a description of the goods with their Harmonized System classification, and the certifying party with a signature and date. Difficulty concentrates in the origin determination and the agreement-specific structure. Country of origin is not always the country the goods shipped from, and for a preferential claim it depends on origin criteria (such as a tariff-shift rule or a regional value content threshold) that the certificate references by code. A USMCA certification carries specific data elements and a blanket-period date range that can cover a year of shipments, while a generic chamber-stamped certificate covers a single consignment. HS codes on the certificate have to match the code on the commercial invoice and the customs declaration, and a mismatch holds the shipment. Goods descriptions are free text that has to be tied to the right HS line. Talonic reads the certificate of origin and returns the exporter, producer, consignee, country of origin, the goods with their HS codes, the origin criteria, and any blanket period. A broker reconciles origin against the invoice and the customs declaration from structured data rather than re-keying each certificate. A certificate issued 2026-04-12 for a shipment from Shenzhen to Long Beach, valued in USD, lets a US broker reconcile the HS code against the commercial invoice and the customs declaration before the goods clear.

What gets extracted from certificates of origin

How extraction works for certificates of origin

Certificates of origin arrive as chamber-stamped scans, exporter PDFs, and trade-agreement certifications, so a generic certificate and a USMCA certification carry different data elements. Talonic classifies the certificate and maps it to the trade-document schema in the Field Registry, which captures the exporter, producer, consignee, country of origin, and the goods with their Harmonized System codes. For a preferential claim, the origin criterion (a tariff-shift rule or a regional value content threshold) and any blanket-period date range are captured, since a USMCA certification can cover a year of shipments while a chamber certificate covers one consignment. HS codes are captured so a broker can reconcile them against the commercial invoice and the customs declaration. Every value returns with a confidence score and pixel-region provenance under DIN SPEC 91491 conformity, so a trade-compliance team can verify origin against the source certificate.

Sample extraction

A chamber-stamped certificate of origin for an ocean shipment

{
  "certificate_type": "generic",
  "exporter_name": "Shenzhen Anchor Electronics Co.",
  "producer_name": "Shenzhen Anchor Electronics Co.",
  "consignee_name": "Acme Imports LLC",
  "country_of_origin": "China",
  "goods": [
    {
      "description": "Bluetooth speaker modules",
      "hs_code": "8518.22",
      "quantity": 288
    }
  ],
  "origin_criterion": "wholly_obtained",
  "blanket_period": null,
  "issue_date": "2026-04-12"
}

Frequently asked