August 19, 2026
Answer: Air waybill OCR and sea waybill OCR use AI document extraction to read shipping documents and turn them into structured data for freight, customs, accounting, and logistics workflows. Lido is the best fit when you need to process air waybills, MAWBs, HAWBs, sea waybills, ocean waybills, and other carrier-specific layouts without templates or model training. It extracts fields like AWB number, shipper, consignee, carrier, routing, vessel, voyage, container number, seal number, cargo description, weight, charges, and customs values, then exports the results to Excel, CSV, Google Sheets, JSON, API, or downstream workflow systems.
Waybills look standardized until you process them at volume. One airline uses one air waybill layout, a freight forwarder sends a house air waybill in a different format, an ocean carrier uses its own sea waybill template, and the supporting documents arrive as PDFs, scans, photos, and email attachments.
If your team is manually keying those documents into a freight management system, TMS, customs platform, spreadsheet, or accounting workflow, the problem is not just OCR. You need reliable shipping document data extraction: the document has to be classified, the right fields have to be pulled from the right place, and the output has to be consistent enough to import downstream.
Basic OCR turns an image into text. That is not enough for air waybill data extraction or sea waybill data extraction. This is also why generic PDF-to-Excel converters fail on trade documents once layouts, attachments, and field definitions vary.
A production workflow needs to understand the document, not just read it. The software has to know that an AWB number is different from a booking number, that a carrier prefix is not a flight number, that a port of discharge is different from a place of delivery, and that a container number, seal number, and package count should not be mixed together.
The workflow usually looks like this:
That is the difference between OCR that gives you text and waybill OCR software that removes manual data entry.
Air waybills and sea waybills are document families, not single fixed templates. That is why template-based OCR often breaks in logistics operations.
Common problems include:
For low-volume work, a person can open the PDF and key the data manually. At scale, that becomes a bottleneck. The goal is not to remove every human from the process. The goal is to stop making people retype every field and only have them review the fields that need judgment.
An air waybill, or AWB, is the core document for air freight. It is also called an air consignment note. It is typically a non-negotiable document that functions as a receipt, contract of carriage, tracking document, and source of shipment details for billing, insurance, and customs workflows.
Air waybill OCR software should handle both clean digital PDFs and scanned or photographed AWBs. It should also support the common spelling variations people use in search and operations: air waybill OCR, airway bill OCR, AWB OCR, AWB data extraction, MAWB OCR, and HAWB OCR. For a focused workflow example, see air waybill OCR software powered by Lido.
Typical air waybill fields include:
| Field group | Examples to extract |
|---|---|
| Shipment identifiers | AWB number, MAWB number, HAWB number, carrier prefix, shipment reference, tracking number |
| Parties | Shipper, consignor, consignee, account numbers, notify party, agent, freight forwarder |
| Air routing | Origin airport, destination airport, routing, airline carrier, flight number, departure date, destination codes |
| Cargo details | Number of pieces, package type, commodity description, HS code, dimensions, gross weight, chargeable weight |
| Value and charges | Declared value, customs value, prepaid charges, collect charges, rate class, currency, insurance details |
| Instructions and compliance | Handling instructions, dangerous goods notes, temperature requirements, special service codes, issue date, place of execution |
The AWB number is especially important. A standard AWB number is usually an 11-digit identifier made up of a carrier prefix, a serial number, and a check digit. If that number is wrong, shipment tracking, billing, and exception handling can fail downstream.
A sea waybill is used for ocean freight. Like an air waybill, it is generally non-negotiable. It serves as evidence of the contract of carriage and receipt of goods, but it is not a document of title. That is one of the key differences between a sea waybill and a negotiable ocean bill of lading.
Sea waybill OCR is also searched as sea way bill OCR, seawaybill OCR, SWB OCR, ocean waybill OCR, sea waybill data extraction, and shipping document OCR. The underlying need is the same: extract structured shipment data from ocean transport documents without manually building a template for every carrier or NVOCC. For a focused workflow example, see sea waybill OCR software powered by Lido.
Typical sea waybill fields include:
| Field group | Examples to extract |
|---|---|
| Shipment identifiers | Sea waybill number, booking number, carrier reference, customer reference, bill of lading reference |
| Parties | Shipper, consignee, notify party, carrier, freight forwarder, NVOCC |
| Ocean routing | Vessel, voyage, port of loading, port of discharge, place of receipt, place of delivery, final destination |
| Container details | Container number, seal number, container type, number of packages, marks and numbers |
| Cargo details | Commodity description, HS code, gross weight, net weight, measurement, CBM, package type |
| Charges and instructions | Freight charges, prepaid or collect terms, special instructions, issue date, place of issue |
The risky fields are usually the ones that drive release, matching, billing, or customs workflows: container numbers, seal numbers, ports, weights, package counts, consignee names, and shipment references. Those are the fields where automated extraction should be paired with validation rules and exception review.
One reason logistics OCR projects get messy is that teams use “waybill,” “bill of lading,” “AWB,” and “shipping document” loosely. Your software needs to separate them because the extracted fields and downstream workflows are different.
| Document | Mode | What it usually represents | OCR implications |
|---|---|---|---|
| Air waybill | Air | Non-negotiable air freight document used as receipt, contract, tracking, and shipment detail record | Extract AWB number, airline, airport routing, pieces, weights, charges, shipper, consignee, and handling instructions |
| Master air waybill | Air | Carrier-issued air waybill for a consolidated shipment | Useful for forwarder and consolidation workflows; may need matching to one or more HAWBs |
| House air waybill | Air | Forwarder-issued document for an individual shipment inside a consolidation | Extract individual shipper, consignee, and cargo details; often matched to a MAWB |
| Sea waybill | Ocean | Non-negotiable ocean transport document and receipt of goods | Extract carrier, vessel, voyage, ports, containers, seals, cargo, weights, and references |
| Ocean bill of lading | Ocean | May be negotiable and can function as a document of title depending on type | Often needs additional title, release, endorsement, and compliance handling beyond simple OCR |
If your team processes all of these documents, do not choose a tool that only works on one fixed form. Choose a logistics document OCR system that can classify the file first, then apply the right extraction schema for each document type. If bills of lading are a major part of the workflow, see our guide to the best bill of lading OCR software.
Lido uses a custom blend of AI vision models, OCR, and LLMs to extract data from documents in any format. You describe the fields you want in plain English, upload sample documents, and Lido returns structured data without requiring a template for every airline, forwarder, ocean carrier, or NVOCC.
For waybill processing, that means you can ask Lido to extract fields like:
Lido can export the extracted results to Excel, CSV, Google Sheets, JSON, or API. That matters because logistics teams rarely want another isolated OCR dashboard. They want the data to move into the system they already use: a freight management platform, TMS, customs brokerage workflow, shared spreadsheet, ERP, accounting system, or internal database.
The same approach also works across related documents. If a shipment packet includes a commercial invoice, packing list, bill of lading, delivery order, carrier invoice, or proof of delivery, Lido can extract the relevant fields from each document type instead of forcing your team to process every file manually. For customs-heavy workflows, see our comparison of the best customs document processing software.
When you compare air waybill OCR software or sea waybill OCR tools, the feature list can sound similar. Most vendors will say they use AI, machine learning, OCR, or document AI. The practical test is whether the tool works on your actual shipping documents.
Use this checklist:
If you only have one perfectly consistent document format, a template tool might be enough. If you process many carriers, forwarders, and document types, a layout-agnostic approach like Lido is usually the better fit.
Waybill OCR only creates value when the extracted data moves somewhere useful. Before choosing a tool, decide what the end state should be.
Common outputs include:
A good implementation starts small. Pick a representative set of air waybills and sea waybills from different carriers. Define the fields you need. Decide which fields can flow straight through and which require review. Then connect the output to one downstream workflow before expanding to more document types.
That first workflow might be simple: upload AWBs and sea waybills, extract fields into a spreadsheet, review exceptions, and export CSV. Once the schema is stable, you can connect the same structured output to an API or internal system.
Lido is a good fit if your team processes shipping documents at enough volume that manual data entry is slowing down operations, but your document formats are too variable for rigid templates. That pattern shows up across logistics teams, including trucking companies processing handwritten BOLs, PODs, driver tickets, and carrier paperwork at scale.
It is especially useful when:
The documents do not need to become cleaner or more standardized for automation to work. The extraction layer needs to be flexible enough to handle the documents your team already receives.
Lido is the best software for teams that need to extract structured data from air waybills, MAWBs, HAWBs, sea waybills, and related shipping documents without building templates for every carrier or forwarder. It handles variable layouts, scanned PDFs, and custom fields, then exports results to Excel, CSV, Google Sheets, JSON, or API.
Air waybill OCR can extract AWB number, MAWB number, HAWB number, carrier, shipper, consignee, origin airport, destination airport, routing, flight number, pieces, gross weight, chargeable weight, commodity description, HS code, declared value, handling instructions, charges, insurance details, and shipment references.
Sea waybill OCR can extract sea waybill number, booking number, carrier reference, shipper, consignee, notify party, vessel, voyage, port of loading, port of discharge, place of receipt, place of delivery, container number, seal number, package count, cargo description, gross weight, measurement, charges, and special instructions.
Yes. Lido can extract data from both master air waybills and house air waybills. It can pull fields from each document type and structure them separately, which is useful when a freight forwarder needs to match a MAWB for a consolidated shipment with one or more HAWBs for individual consignments.
No. A sea waybill is generally a non-negotiable ocean freight document and is not a document of title. A bill of lading can be negotiable depending on the type and may function as a document of title. OCR software should classify these documents separately because the fields, release workflow, and compliance handling can differ.
Yes. Lido can export extracted waybill data to Excel, CSV, Google Sheets, JSON, or API. Teams can use those outputs to update spreadsheets, feed a freight management system, support customs brokerage workflows, push data into a TMS, or connect with internal operations and accounting systems.
Basic OCR is usually not enough for shipping document processing because it only converts the page into text. Waybill automation needs document classification, field extraction, normalization, validation, and structured output. Lido handles those steps so teams can work with clean rows of data instead of unstructured OCR text.
%20(1).svg)
.png){kind=small}
