“ I have checked the documents of AWS to explore the amazon augmented ai with human review workflows, amazon textract form extraction task and amazon cognito user pool.. Amazon augmented ai makes it easy and secure to have human review workflows for amazon textract. In terms of cost, the solution is cheaper and secure.”
Amazon Augmented AI(Amazon A2I) is designed to allow you to integrate your workflow with Amazon Textract for document processing and Amazon Rekognition for content moderation, so you can implement human review workflows in just a few clicks. The Amazon A2I API is also designed to allow you to integrate your workflows into custom models that you have built with Amazon Sagemaker or other machine learning tools.
Amazon A2I supports multiple choices for human reviewers. You can use your private team of reviewers for in-house review jobs, especially when handling sensitive data that needs to stay within your organization.
In this post, you will experience explore the amazon augmented ai with human review workflows, amazon textract form extraction task and amazon cognito user pool. Here I have explored the human reviews workflows feature and amazon textract extraction task with user authentication with cognito user pool.
Architecture Overview
The architecture diagram shows the overall deployment architecture with data flow, amazon augmented ai, s3 bucket, amazon cognito and amazon textract.
Solution overview
The blog post consists of the following phases:
- Create of Private Workforce in Amazon SageMaker AI
- Create of Human Review Workflow in Amazon Augmented AI with Amazon Textract
- Output of Labeling Project for Human Review
Phase 1: Create of Private Workforce in Amazon SageMaker AI
- Open the Amazon SageMaker AI console, choose the labeling workforces parameter under ground truth. Create the private team with select of private team creation "create a private team with aws cognito”, specify the team name, choose worker as “invite new workers by email” with specify of email addresses, organization name and contact email. Optionally we can set sns notification also in amazon sagemaker ai. Once complete, we can create the private team as a private workforce. Also we have an s3 bucket with text file screenshot uploaded in the bucket.
Phase 2: Create of Human Review Workflow in Amazon Augmented AI with Amazon Textract
- Under the Amazon Augmented AI parameter, choose the human review workflows parameter option and create it with specifying the s3 bucket created, workflow settings as specifying name, s3 bucket, iam role, choose task type “textract” and set value for amazon textract from extraction, specify the worker task template name and task description. Also select private teams created and create the human review workflow.
Phase 3: Output of Labeling Project for Human Review
Clean-up
Amazon sagemaker ai : private team, workers, private workforce and human review workflows, s3 bucket and amazon cognito : domain and user pool.
Pricing
I review the pricing and estimated cost of this example.
Cost of Amazon SageMaker AI = $0.00
Cost of Amazon Cognito = $0.00
Cost of Simple Storage Service = $0.01
Total Cost = $0.01
Summary
In this post, I showed “explore the amazon augmented ai with human review workflows, amazon textract form extraction task and amazon cognito user pool”.
For more details on Amazon Augmented AI, Checkout Get started Amazon Augmented AI, open the Amazon Augmented AI console. To learn more, read the Amazon Augmented AI documentation.
Thanks for reading!
Connect with me: Linkedin
Top comments (0)