Skip to main content

​
Introduction

In this tutorial, we will walk through an example of using DocParse to extract structured metadata from a document via the Aryn DocParse UI. We will be working with a sample insurance document that contains a workers compensation reinsurance submission.
To learn how to extract structured metadata using the Aryn SDK, you can follow this tutorial.

​
Prerequisites

  1. Get your free Aryn API key by signing up on the Aryn Console at app.aryn.ai.
  2. Download the sample document or have your own handy.

​
Step 1: Defining a Simple Schema

Once you have logged into the Aryn console, load the document you downloaded into the DocParse Playground. To define properties, click on the “Configure Schema” button on the right-hand side of the page. Property Extraction Options in the DocParse UI This brings up the schema creation wizard where you can define the properties you want to extract. Click the + button to add a property. For each property you can specify the name and type of the property, as well as an optional description, default values, and examples. The schema creation wizard in DocParse Go ahead and add the following two fields: 
Name: Submission Date
Type: Datetime
Description: The submission date of the claim.

Name: Submission Contact Email
Type: String
Description: The submission contact email.

​
Step 2: Extracting Nested Data with Arrays

It’s common to want to extract multiple records from a single document, each of which has a similar schema. For example, in the sample document, the current exposure information is broken out by state in a table on page 2. You can extract all of these entries with DocParse by specifying a field of type Array. Extracting an Array in the DocParse UI Since each record has multiple properties itself, we set the “Item type” of the Array to be Object. Then, scroll down and specify the properties of each Array element. Extracting an Array in the DocParse UI, Part 2 In this case, the nested properties should be 
Name: State, Type: String
Name: Class Code, Type: String
Name: Payroll, Type: Integer
Name: Manual Premium, Type: Integer
Name: Modified Premium, Type: Integer
The schema should look like the following: The final Schema in the DocParse UI Once you have the schema how you like it, click on Save Schema and then Process Document to perform the parsing and extraction.

​
Step 3: Review Results

After DocParse has finished processing, you can review the results. Select the “Properties” tab on the right-hand side to look at the extracted properties. Reviewing a document in the DocParse UI