Technical Case Study · Logistics & Customs

Reconciling Bills of Lading before data enters customs

Traditional OCR fails in logistics by forcing Bills of Lading into financial schemas. Here is how deterministic extraction isolates containers, seals, and weights.

The challenge

Customs brokers face critical bottlenecks when matching Bills of Lading against Commercial Invoices. Standard OCR systems attempt to parse these logistics documents as if they were standard invoices, inevitably missing critical relational data like container numbers tied to specific seal IDs or net/gross weight discrepancies.

The SunnyExtract pipeline

SunnyExtract routes logistics documents through a dedicated extraction schema. It isolates the Bill of Lading, extracts the complex tables of container and seal data, and cross-checks the total weights against the accompanying Commercial Invoice. Exceptions are flagged before any payload hits the customs declaration software.

system_payload.json
{
  "document_type": "bill_of_lading",
  "port_of_loading": "Rotterdam",
  "containers": [
    {
      "container_id": "MSKU1234567",
      "seal_id": "SL-998877",
      "gross_weight_kg": 24500.00
    }
  ],
  "validation": {
    "weight_match_invoice": true,
    "status": "cleared_for_export"
  }
}

Operational impact

Zero manual entry

No data entry for container and seal numbers.

Automatic weight cross-checks

Weights are cross-checked between the BL and the Commercial Invoice.

Dedicated exception queue

Mismatched freight documents are queued for review, not silently passed through.

Request a private workflow review

Tell us how your document workflow works today. We review every request manually and prepare demos around real operational needs.

Request private workflow review

We use analytics cookies (Google Analytics) to understand how the site is used and improve it. They only run if you accept. Cookie policy