Empower your business use cases
summary
A working Document Understanding Solution assembles Amazon Textract for OCR and table-to-CSV extraction, Amazon Comprehend Medical for medical-entity detection and PHI redaction, and Amazon Kendra for semantic search compared against Elasticsearch keyword results. The demo shows redaction, table export, and a human-review loop via Amazon Augmented AI with a configurable confidence threshold (example: send <90% to review). The stack deploys via CloudFormation/CDK, uses S3, Lambda, DynamoDB, Cognito and CloudFront, is open source, and targets hundreds of thousands of documents.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 1:36Document processing challenges
- 3:05AWS AI services for documents
- 5:29Amazon Textract and Comprehend deep dive
- 8:25Amazon Comprehend Medical
- 9:31Amazon Kendra for search
- 10:34Human review with Augmented AI
- 15:05Document Understanding architecture
- 16:07Live demo of solution
- 21:58Key features and deployment
- 24:28How to get started with the solution
related talks
35mAutomate your document pipeline with intelligent document processing
30mIntelligent document processing: Extract data & insights from documents
18mUsing AI to automate clinical workflows
41mInsights into patient health with
42mExtract information accurately from documents using computer vision
29mSolve common business problems with AI and ML
30mIntelligent document processing for the insurance industry
32mAutomate data extraction & analysis with intelligent document processing