Invoice Recognition: Frequently asked questions (FAQ)

Invoice Recognition is a feature that uses advanced technologies like machine learning to extract invoice information from 1-page documents in your Inbox. The information we will attempt to extract is:

• Invoice #
• Invoice date
• Due date
• Vendor name
• Amount
• Payment terms
• Purchase Order (PO) #

The information will be pre-filled on the review bill screen and the bill will only be created after you review and accept the information.

Jump to:

• How does Invoice Recognition work?
• What is Click and Capture?
• What else should I know about this feature?
• Will I be charged for this?
• Why did Invoice Recognition not read all fields of the bill?
• Can this feature create multiple bills from a multi-page document?
• Is there a limit to how many pages a multi-page document can have for this feature?

How does Invoice Recognition work?

Once documents come into the Inbox, documents that can be processed by IVA will have a Review & Save option instead of the Enter bill option. Note: Invoice Recognition currently only works on PDF, png, jpg, or jpeg type documents. We will be expanding to other file types in the future.

There will be some pieces of information highlighted on the document card - like vendor name, due date and amount.

Once the button Review & Save is selected, you will be taken to the bill entry screen with fields populated.

• Create a new vendor for your records by selecting Add new vendor
• Use an existing vendor by selecting it from the Vendor Name drop-down

Once you have reviewed or edited the populated fields and entered any information that is missing, select Save to create the bill.

You can verify on the Create Bill page if the Invoice Recognition predictions are correct by locating the colored boxes. If you correct a field, the colored box is removed.

You can also upload or drag/drop a new document onto the Create Bill page. The bill details will be autofilled/prefilled for review. Fields already touched by the user are excluded from the Invoice Recognition results.

The Invoice Recognition results will be available within 5-10 seconds of uploading or dragging and dropping a document in.

Note: Invoice Recognition will not process ebills, bills sent to you by a connected customer, since we already have all the information for the required fields via the network connection.

What is Click and Capture?

For those documents or fields we are not able to process or copy to the bill via Invoice Recognition, we have Click and Capture, a feature enabling clickable copy and paste from the document image to the Bill Summary or Expense Details windows to easily complete the bill's basic details from the document!

Simply select text to copy from the bill's document image, then click the field in the Bill Summary or Expense Details window where you'd like to paste the text. If you select Split this amount, you can click and capture in those fields as well.

Ways to select text:

• Move your cursor around a block of text;
  • hover near a single word until the single word is highlighted to click and copy a single word
  • hover above a sentence until the full sentence is highlighted to click and copy a full sentence
  • hover above a paragraph until the full paragraph is highlighted to click and copy a full paragraph
  • To manually copy multiple text regions at once, hold down the Command key (for Mac) or the Ctrl key (for PC), then click in the Bill Summary window
  • To clear copied text without pasting, right-click or hit escape

Click and Capture also works when quick adding a vendor from the Bill Summary window.

You can also click to capture an address from the document and paste into the vendor record as the new vendor's address.

Note: this feature won't be available for screen sizes less than 768px width.

What else should I know about this feature?

Machine learning gets better over time. If we are not confident with the accuracy of a document, we will not show you any results. Hence, you will see some 1-page documents processed and some that are not. For documents that are not processed by Invoice Recognition, they will need to be coded manually.

Will I be charged for this?

You will not be charged for this feature.

Why did Invoice Recognition not read all fields of the bill?

Machine learning algorithms will try to predict all five (5) required fields for creating the bill. If it can only predict less than five (5) with high confidence, we will show you those to give you some help with data entry.

Invoice Recognition currently works on PDF, png, jpg, and jpeg type documents.

Invoice Recognition does not currently recognize foreign currency, the amount field will be blank for foreign currency bills processed via Invoice Recognition.

Can this feature create multiple bills from a multi-page document?

No, Invoice Recognition will not create separate bills from a multi-page document.

Invoice Recognition will read the first page of the multi-page document, then you can save a bill with that page, and any additional pages as needed. Those pages will be removed from the document in the inbox and the rest of the pages remain. You can then use Click and Capture to create bills from the remaining pages.

Is there a limit to how many pages a multi-page document can have for this feature?

Yes, Invoice Recognition will trigger on a multi-page document up to 50 pages.