Document Information Extraction uses a globally pre-trained machine learning model that currently obtains better accuracy results with invoices and payment advices in the languages listed in Supported Languages and Countries. The team is working to support additional document types and languages in the near future.
Upload to the service any document file in PDF or single-page PNG and JPEG format that has content in headers and tables, such as an invoice.
As an alternative to uploading your own documents to the service, you can use the following sample invoice files (right click on the link, then click Save link as to download the files locally):
-
Open the Document Information Extraction Trial UI, as described in the tutorial: Set Up Account for Document Information Extraction and Go to Application.
-
In the top right, click + (Upload a new document).
-
In the Select Document screen, drop files directly or click + to upload one or more document files.
-
Select the Document Type. Click Step 2.
-
In Step 2, select the header fields you want to extract from the documents you’ve uploaded. Click Step 3.
-
In Step 3, select the line items you want to extract from the documents you’ve uploaded. Click Review.
-
Review your selection. Click Edit if you want to change anything. Click Confirm.
You see the Document Name, Upload Date and Status of the documents you have just uploaded.
Status changes from PENDING to READY. This means the selected header fields and line items have been extracted, and the extraction results are ready to be validated and changed if necessary. If status changes from PENDING to FAILED, this means it was not possible to get the extraction results, and you need to upload the document once again.
CAUTION:
Be aware of the following Document Information Extraction Trial UI trial account limitation:
- Maximum 40 uploaded document pages per week (the documents can have more than 1 page)