# Public sector use case: Benefit application

## Introduction

Do you struggle with extracting valuable insights from documents? Manual data entry and manual processes can be costly, time-consuming, and error-prone. Get ready to revolutionize your document processing and unlock valuable information with automation. In this workshop, learn how to build an intelligent document processing pipeline that extracts, enriches, and analyzes text from documents. This session provides you with example code and architectures to help you build an intelligent document processing solution at scale. You must bring your laptop to participate.

The goal of this workshop is to introduce you to AWS machine learning services and techniques that will help accelerate your document processing tasks. We will work through two labs to accomplish this objective:

- [Lab 1: Intelligent document processing using Amazon Textract](./lab1-textract.ipynb)
- [Lab 2: Training and deploying an Amazon Comprehend Custom Classification model](./lab2-comprehend.ipynb)

## Getting started

You can run this workshop in all commercial AWS regions where Amazon SageMaker is available.

## Datasets

The dataset used for this lab was created using random sample data.
    
## License

The contents of this workshop are licensed under the [Apache 2.0 License](./LICENSE).

## Authors
[Sherry Ding](https://www.linkedin.com/): Sr. AI/ML Solutions Architect
<br />
[Srinath Godavarthi](https://www.linkedin.com/): Principal SA, SLG HHS
<br />
[Bill Screen](https://www.linkedin.com/): Sr. Solutions Architect
<br />
[Richard Tang](https://www.linkedin.com/): Solutions Architect II