AWS Certified AI PractitionerAWS Services for AI/ML and Generative AIMedium
A company is migrating its on-premises document processing workflow to AWS. They frequently deal with scanned invoices and receipts, needing to extract structured data such as vendor names, invoice numbers, and line items, even from poorly formatted documents. Which AWS service is purpose-built for this task?
- AAmazon Textract
- BAWS Glue
- CAmazon Comprehend
- DAmazon Rekognition
Show answer & explanationAnswer & explanation
Correct answer: A. Amazon Textract
Amazon Textract is a machine learning service that automatically extracts text, handwriting, and data from scanned documents. It goes beyond simple optical character recognition (OCR) to identify fields, tables, and key-value pairs from virtually any document, including invoices and receipts.
Why the other options are wrong
- B. AWS Glue is an ETL service for data integration, not for extracting data from scanned documents.
- C. Amazon Comprehend is for natural language processing of text, not for extracting structured data from document images.
- D. Amazon Rekognition is for image and video analysis, not for extracting text and structured data from documents.
Amazon Textract
An AWS machine learning service that automatically extracts text, handwriting, and data from scanned documents.
- Goes beyond OCR to identify fields, tables, and key-value pairs.
- Ideal for processing forms, invoices, receipts, and other documents.
- Extracts data in a structured format for easy use.
Memory trick: Textract extracts text and data from documents.