Building a document processing solution with Amazon Textract, database, data lakes, and analytics on AWS (Level 200)
Organizations have many traditional documents and forms that hold critical business data. These documents, such as medical forms, insurance claims and loan applications, have structured and unstructured data that are either extracted by humans or by rule-based systems which are not easily scalable, have high costs, and could produce low-accuracy extraction results. In this session, learn how to use Amazon Textract to extract structured data to more accessible file types or to a queryable database, integrate a data lake and analytics solution, visualize the extraction results and deploy your automated document processing workflow into production, at scale.
Ryan Hendriks, Principal Solution Architect – Data Modernization, AWS