Getting Started with Document Information Extraction UI Application

Introduction

The previous beta version of Document Information Extraction (DOX) UI and its components are now GA. Both Document Information Extraction (DOX) and Document Information Extraction UI are now available on EU10, EU11, JP10, and US10, while Trial is currently available on EU10 and US10 only.

This Document Information Extraction UI is a very handy tool for visualizing machine learning extracted header fields and line items of your uploaded pdf documents.
The good thing here there is NO additional pricing – if you already have an active Document Information Extraction (API) service instance, you can get this Document Information Extraction UI application for FREE!

If you are new to Document Information Extraction, you can check out my previous DOX service intro blog post here; I would also recommend you to check out the official help documentation here.

Setting up Document Information Extraction Trial UI Application

Step 1: Login to SAP Cloud Platform Trial Cockpit

SAP Cloud Platform trial cockpit here.
Skip this step if you have already logged-in.

Step 2: Access Cloud Foundry Trial Sub-Account

Click Access Cloud Foundry Trial link. You will find the link when you scroll down the page.

Step 3: Access Subscriptions sub-menu, and search for Document Information Extraction

Click Document Information Extraction Trial UI tile.

Step 4: Subscribe to Document Information Extraction Trial UI

Click Subscribe button.

Note: you should be able to subscribe to this service successfully, otherwise if there’s any error encountered, most likely you didn’t create any Document Information Extraction Service (API)Instance before. If so, you can use booster to create the DOX instance and its service key quickly just in few steps.

Step 5: Assign Document Information Extraction UI role to your account

Go back to Cloud Foundry cockpit homepage again, and click on Trust Configuration link.

You should see a Trust Configuration page, and proceed by clicking sap.default link.

Enter your email address, and click on Show Assignments button first then followed by click on Assign Role Collection button.

At Assign Role Collection pop-up, select Document_Information_Extraction_UI_End_User_trial role collection, and finally click Assign Role Collection button to close the pop-up.

You email address should have the correct roles assignment as shown below.

Note: you can also add other email address of your team-mate(s) to let them access the DOX Trial UI too.

Step 6: Access DOX Trial UI application

Go back to Subscriptions sub-menu again, and click on Document Information Extraction Trial UI subscription tile.

Click on Go to Application. This will open up the link in new browser tab. Login with your SCP email address and password as per usual.

Getting started with Document Information Extraction Trial UI application

Using DOX Trial UI application is pretty straightforward just under 3 steps:
1. Upload PDF document (make sure the selected document type is tally with the document you want to upload).
2. Select the Header Fields you want to extract from the document. You need to select at least one header field.
3. Select the Line Items Columns you want to extract from in the document (optional).

Check out my video below on using DOX Trial UI application:

What I liked about this DOX UI application is that you can perform correction on the extraction results, be it on header fields and on line item columns fields by editing and selecting words on PDF preview.

Resources / References

• Document Information Extraction Help Page
• Developer Tutorial on Document Information Extraction Service

**Special thanks to Tomasz Janasz for his feedback on DOX regions availability and dedicated booster link.**