document-understanding
latest
false
- Overview
- Building models
- Consuming models
- ML packages
- 1040 - ML package
- 1040 Schedule C - ML package
- 1040 Schedule D - ML package
- 1040 Schedule E - ML package
- 1040x - ML package
- 3949a - ML package
- 4506T - ML package
- 709 - ML package
- 941x - ML package
- 9465 - ML package
- ACORD131 - ML package
- ACORD140 - ML package
- ACORD25 - ML package
- Bank Statements - ML package
- Bills Of Lading - ML package
- Certificate of Incorporation - ML package
- Certificate of Origin - ML package
- Checks - ML package
- Children Product Certificate - ML package
- CMS 1500 - ML package
- EU Declaration of Conformity - ML package
- Financial Statements - ML package
- FM1003 - ML package
- I9 - ML package
- ID Cards - ML package
- Invoices - ML package
- Invoices Australia - ML package
- Invoices China - ML package
- Invoices Hebrew - ML package
- Invoices India - ML package
- Invoices Japan - ML package
- Invoices Shipping - ML package
- Packing Lists - ML package
- Payslips - ML package
- Passports - ML package
- Purchase Orders - ML package
- Receipts - ML Package
- Remittance Advices - ML package
- UB04 - ML package
- Utility Bills - ML package
- Vehicle Titles - ML package
- W2 - ML package
- W9 - ML package
- Public endpoints
- Supported languages
- Data and security
- Licensing and Charging Logic
- How to
- Classify documents automatically
- Train a classifier
Classify documents automatically
Document Understanding User Guide
Classify documents automatically
The objective of classification is to analyze a document, then decide which document type it belongs to.
With Document UnderstandingTM modern projects, your uploaded documents are classified automatically. If you're looking to classify your documents manually, or find that certain uploaded documents are not automatically classified, follow the steps from this page for guidance.
Note: To train a document classification model, you need to have at
least two document types.
Use this procedure if you want to upload your documents
and have them classified automatically.
Note: For an optimal
dataset size, make sure you upload at least 150 documents for each document
type.
After moving the documents to the correct type, wait for
them to be processed. During processing, documents are annotated automatically.
Use this procedure if you want to upload your documents to
a custom document type.
Tip: Before you create a custom
document type, make sure that the document type you need is not already
pre-existing. You can view the pre-existing document types if you select Add
document type and then check the Type drop-down list.
Note: For an optimal dataset size, make sure you upload at least 150
documents for each document type.