DocuOCR reads your bills of lading and pulls the shipper, consignee, carrier, BOL and PRO numbers, commodity, freight class, weight, and freight terms into structured fields you can export to Excel, CSV, or JSON, or push straight into your TMS. It reads native PDFs, scanned paper, carrier-stamped copies, and photographed pages, so inbound freight paperwork becomes clean, searchable data. No template required, for any carrier.
The OCR and extraction layer that turns a pile of BOLs into TMS-ready shipment records.
Last updated July 2026
Upload a document to extract
Drop files here or click to upload
Up to 50 files
Uploading...
Drop in a bill of lading to see the shipper, consignee, carrier, weight, and freight terms DocuOCR pulls out, ready to export.
// In short
Bill of lading OCR software uses AI optical character recognition to read a BOL and extract the shipper, consignee, carrier and SCAC, BOL and PRO numbers, commodity, NMFC freight class, weight, piece count, and freight terms into structured data. DocuOCR handles the OCR and extraction on native PDFs, scanned paper, carrier-stamped copies, and photographed pages at 95 to 99 percent field-level accuracy, links every field to its source line, and exports to Excel, CSV, JSON, or a TMS. It is the extraction layer that feeds transportation and freight-audit systems, not a TMS itself.
Upload, read, review, export. No retyping BOL data into a spreadsheet, no scanned freight document left as a flat image, no weight or freight class miskeyed into a freight-bill audit.
Drop in a BOL as a PDF, image, or scan. Process one shipment or an entire batch of inbound freight documents at once, from any carrier.
DocuOCR runs OCR on scanned, stamped, or photographed pages, reads the full document, and returns the shipper, consignee, carrier, BOL and PRO numbers, weight, class, and freight terms as structured fields.
Every field carries a confidence score and a link to its source line, so a doubtful weight, piece count, or handwritten note is checked before you trust it.
Send the structured shipment data to Excel, CSV, or JSON, or push it into your TMS, WMS, ERP, or freight-audit tool through one REST API.
# bill of lading -> clean shipment fields { "bol_number": "BOL-4471902", "pro_number": "078-6642180", "ship_date": "2026-06-18", "shipper": "Acme Mfg, Toledo OH", "consignee": "Northwind Dist, Dallas TX", "carrier": "Old Dominion", "scac": "ODFL", "pieces": "6 pallets", "weight_lbs": 4820, "nmfc_class": "70", "freight_terms": "Prepaid", "confidence": 0.98 } # export -> .xlsx | .csv | .json | TMS / WMS / ERP
DocuOCR returns the shipment data your team has to key into a TMS or a freight-bill audit, plus the line-level detail behind it, so nothing has to be read off the BOL and retyped by hand.
Handling the whole freight document set, not just BOLs? See the logistics document processing software platform. Matching received goods against orders? Pair it with purchase order OCR.
DocuOCR is the OCR and extraction layer, not a transportation management system. It reads and structures the BOLs; your TMS rates, tenders, tracks, and bills the shipments. Here is how the two divide the work.
| Task | DocuOCR (OCR + extraction) | Your TMS / freight system |
|---|---|---|
| Read scanned, stamped, photographed BOLs | Yes, OCR on any page | No, needs digital records |
| Extract shipper, consignee, carrier, weight, class | Yes, as structured fields | No, entered by hand or by staff |
| Read BOLs from any carrier with no template | Yes, by meaning not layout | No, out of scope |
| Link each field to its source line | Yes, with confidence scores | No |
| Rate, tender, and track shipments | No, feeds your system | Yes |
| Generate invoices and settle freight bills | No | Yes |
| Store shipment history and reporting | No | Yes |
| Export to Excel, CSV, JSON, or API | Yes | Varies by platform |
Most freight teams already run a TMS but still have inbound BOLs arriving as email PDFs, scans, and dock photos with no structured data behind them. DocuOCR fills that gap: it reads those documents, extracts the fields, and pushes clean records into the system you already use, so freight-bill audit and data entry stop depending on someone keying every weight and class by hand.
If BOL data is trapped in PDFs, scans, and dock photos and someone has to key it into a system before it is useful, this is for you.
Turn every inbound BOL into a structured shipment record without a coordinator retyping shipper, consignee, weight, and class into the TMS.
Capture piece count, weight, and carrier off the BOL at the dock and match it against the inbound order in minutes, not by hand.
Pull the carrier, weight, class, and freight terms off the BOL so invoice amounts can be audited against what was actually shipped.
Digitize a high volume of BOLs and delivery documents into clean data for billing, settlement, and reporting.
Extract outbound and inbound BOL data into the ERP so shipment records are complete without manual keying.
Add bill of lading OCR and extraction to your product through one REST API instead of building document AI in-house.
Inbound freight paperwork arrives in every format: emailed PDFs, faxed scans, carrier-stamped copies, and photos snapped at the dock. Someone reads each one and keys the shipper, consignee, weight, and class into the TMS, and a miskeyed weight or freight class does not surface until the freight bill is already wrong.
DocuOCR reads the whole BOL, extracts the fields that matter, keeps each one tied to its source line, and exports clean data, so the slow, error-prone read becomes a few minutes of checking flagged fields.
See the full logistics document processing softwareDocuOCR is the extraction layer, not a replacement for your TMS. It turns bills of lading into structured data; your TMS rates, tenders, tracks, and bills the freight. Accuracy runs 95 to 99 percent on clean BOLs, with a confidence score and a source-line link on every field, so uncertain reads are reviewed rather than trusted blindly.
Bill of lading OCR is one job inside the logistics workflow. DocuOCR is the platform that reads the rest of the freight file too.
The category platform: classify a mixed freight file and extract BOLs, delivery receipts, customs forms, and rate confirmations.
Read purchase orders and match received freight against what was ordered, line by line.
The full platform behind this page, with a dashboard for teams who want BOL data without code.
Extract structured data from any fixed or semi-structured form, from freight documents to compliance paperwork.
The end-to-end pipeline that classifies, reads, extracts, and validates documents before records are built.
Add bill of lading OCR and extraction to your own TMS or logistics product through one REST call.
New to automating this? Read how to extract data from a bill of lading for the step-by-step on which fields to capture, how AI reads scanned and handwritten BOLs, and how to feed clean data into your TMS.
Bills of lading carry customer names, addresses, and commercial terms, so they are handled under enterprise-grade controls, with encryption in transit and at rest, role-based access, audit logs, and optional automatic purge after extraction. The controls support your SOC 2 program and your own contractual obligations; ask about deployment options for your environment.
The questions people ask most about reading and extracting data from bills of lading with OCR.
Bill of lading OCR is the use of AI-powered optical character recognition to read a BOL, whether a native PDF, a scanned paper copy, or a carrier-stamped photo, and turn it into structured shipment data. Instead of a clerk keying the shipper, consignee, carrier, weight, and freight terms by hand, OCR pulls each field automatically so it can flow into a TMS, WMS, or spreadsheet.
AI OCR extracts the shipper and consignee names and addresses, the bill-to party, the carrier and its SCAC code, the BOL number and PRO number, the ship date, origin and destination, commodity descriptions, NMFC freight class, piece count and package type, weight and dimensions, freight terms (prepaid, collect, or third party), FOB terms, hazmat details, declared value, and reference or PO numbers. Every field is tagged, source-linked, and exportable.
Modern AI OCR reads clean bills of lading at roughly 95 to 99 percent field-level accuracy on standard fields like the BOL number, carrier, weight, and piece count. Accuracy matters because a wrong weight or freight class flows straight into a freight-bill audit or an invoice. A confidence score on every field and a link back to the source line let a reviewer confirm the doubtful reads quickly rather than trusting the output blindly.
Yes. DocuOCR reads native digital PDFs, scanned paper BOLs, carrier-stamped copies, and photographed pages, and it handles the handwritten notes, weights, and piece counts that show up on real freight documents. When the text is not selectable it runs OCR first, then extracts the shipment fields from the recognized text, which suits the mixed-quality documents a dock or mailroom actually receives.
Yes. Every carrier and broker uses a different BOL layout, so DocuOCR reads the fields by meaning rather than by fixed template. It pulls the shipper, consignee, carrier, weight, and freight terms whether the document is a VICS BOL, a straight BOL, an LTL carrier form, or a broker-generated PDF, so you do not have to build and maintain a template for every carrier you receive freight from.
DocuOCR is the extraction layer that feeds your transportation system, not a replacement for it. Extracted BOL data exports to Excel, Google Sheets, CSV, or JSON, and a REST API pushes the structured fields into a TMS, WMS, ERP, or freight-audit tool so shipments and invoices are populated without manual keying. It fits between the inbound document and the system your team already runs.
DocuOCR is priced per page, so you pay for the BOLs you actually process rather than a fixed seat license or an annual platform fee. You can test it on your own documents for free before committing, and pricing scales with volume, which suits a small brokerage processing a few hundred BOLs a month and a large 3PL processing tens of thousands equally.
The BOL number is assigned by the shipper and identifies the shipment on the bill of lading itself, used to reference the load internally. The PRO number is assigned by the carrier and is what you use to track the freight in transit. A bill of lading usually carries both, and DocuOCR extracts each into its own field so your TMS and freight-audit records stay clean.
Upload a bill of lading, watch the shipper, consignee, carrier, weight, and freight terms come back as clean, source-linked fields, then scale per page across every inbound BOL.
From the same family of tools
