Document Classification

Document Category updates!

New in 11.12 categories for financial reports, government tenders, legal documents, manuals, patents, scientific journals, and technical drawings have been added

Requirements

These packages are required to use these features in production. Trial keys have unlimited access to all features

Package: Smart Data ExtractionModule: Data ExtractionLive demo

Document Classification is an AI-trained SDK API that identifies each file on upload, based on a predefined set of 24 categories, so you can:

• Validate intake.
• Route to the right workflow.
• Add metadata for processing later.

The output includes the predicted label with a confidence score in structured JSON for easy integration into your solution.

The benefits of using this feature include:

• Automatically identify document types from a predefined set of 24 categories such as invoices, receipts, IDs, budgets, contracts, and more.
• You decide the thresholds for automated routing or manual reviews.
• Provides easy integration into downstream workflows.

The 24 categories include:

• "advertisement"
• "budget"
• "email"
• "financial_reports"
• "form"
• "government_tenders"
• "id"
• "invoice"
• "legal_documents"
• "letter"
• "manuals"
• "memo"
• "news_article"
• "passport"
• "patents"
• "presentation"
• "questionnaire"
• "receipt"
• "resume"
• "scientific_journals"
• "scientific_publication"
• "scientific_report"
• "specification"
• "technical_drawing"

JSON Output Specification

Refer to the following specifications to learn more about the output JSON format:

• JSON Specification for Document Classification

Extract document classes as JSON file

Specify the name of the input PDF file and the name of the output JSON file, then select the Doc Classification engine:

C#

DataExtractionModule.ExtractData("Invoice.pdf", "Invoice_Classified.json", DataExtractionModule.DataExtractionEngine.e_doc_classification);

C++

DataExtractionModule::ExtractData("Invoice.pdf", "Invoice_Classified.json", DataExtractionModule::e_DocClassification);

Go

DataExtractionModuleExtractData("Invoice.pdf", "Invoice_Classified.json", DataExtractionModuleE_DocClassification)

Java

DataExtractionModule.extractData("Invoice.pdf", "Invoice_Classified.json", DataExtractionModule.DataExtractionEngine.e_doc_classification);

JavaScript

await PDFNet.DataExtractionModule.extractData("Invoice.pdf", "Invoice_Classified.json", PDFNet.DataExtractionModule.DataExtractionEngine.e_DocClassification);

PHP

DataExtractionModule::ExtractData("Invoice.pdf", "Invoice_Classified.json", DataExtractionModule::e_DocClassification);

Python

DataExtractionModule.ExtractData("Invoice.pdf", "Invoice_Classified.json", DataExtractionModule.e_DocClassification)

Ruby

DataExtractionModule.ExtractData("Invoice.pdf", "Invoice_Classified.json", DataExtractionModule::E_DocClassification)

VB

DataExtractionModule.ExtractData("Invoice.pdf", "Invoice_Classified.json", DataExtractionModule.DataExtractionEngine.e_doc_classification)

Extract document classes as JSON string

Specify the name of the input PDF file, then select the Doc Classification engine:

C#

string json = DataExtractionModule.ExtractData("Scientific_Publication.pdf", DataExtractionModule.DataExtractionEngine.e_doc_classification);

C++

UString json = DataExtractionModule::ExtractData("Scientific_Publication.pdf", DataExtractionModule::e_DocClassification);

Go

json := DataExtractionModuleExtractData("Scientific_Publication.pdf", DataExtractionModuleE_DocClassification).(string)

Java

String json = DataExtractionModule.extractData("Scientific_Publication.pdf", DataExtractionModule.DataExtractionEngine.e_doc_classification);

JavaScript

const json = await PDFNet.DataExtractionModule.extractDataAsString('Scientific_Publication.pdf', PDFNet.DataExtractionModule.DataExtractionEngine.e_DocClassification);

PHP

$json = DataExtractionModule::ExtractData("Scientific_Publication.pdf", DataExtractionModule::e_DocClassification);

Python

json = DataExtractionModule.ExtractData("Scientific_Publication.pdf", DataExtractionModule.e_DocClassification)

Ruby

json = DataExtractionModule.ExtractData("Scientific_Publication.pdf", DataExtractionModule::E_DocClassification)

VB

Dim json As String = DataExtractionModule.ExtractData("Scientific_Publication.pdf", DataExtractionModule.DataExtractionEngine.e_doc_classification)

Optional Configurations

Select OCR Language

Password-Protected PDFs

Page Range

Minimum Confidence Threshold