How smart data extraction makes for smart AP automation

Spend Matters welcomes this guest post from Laurent Charpentier, COO and chief innovation officer of Yooz Inc., an AP automation solution provider.

When it comes to invoice and payment processing in AP automation, there is a lot of reference to optical character recognition (OCR) — the technology that turns typed, printed or handwritten text into machine-encoded text. The initial text can come from a scanned document, a photo of a document, a scene-photo (for example the text on signs and billboards in a landscape photo), or from subtitle text superimposed on an image (like from a television broadcast).

Simply put, the technology is looking at an image or file and is able to identify what is on it — turning a picture into words.

Smart data extraction, the next layer, is used to understand and process the text from the OCR to transform it into relevant data. This is critical to know because OCR by itself does not know what to do with the information it reads. This is where the “smart” in smart data extraction comes in. And it’s important to differentiate the two.

Some AP automation solution providers might claim OCR technology. Be careful and dig deeper to find more information. Many apply manual extraction by a person or outsourcing for third-party verification. OCR extraction that layers human verification uses people to put data read by the OCR into predefined fields. In this scenario data entry is done by an outsourced firm and takes time as the data is being populated by people, typically 24 to 72 business hours. It kind of defeats the purpose of moving from a manual AP process to an automated process to save time, right?

What you really want to know when investigating AP automation solution providers is whether the solution has a complete technology, combining OCR (converting images to text), smart data extraction (transforming the text into relevant data) — and machine learning (remembering the data and populating it into the applicable data fields each time the data is recognized).

You are looking for a system that gets smarter the more you use it!

Putting smart data to use

But what does all of this mean, exactly, to finance leaders and their AP teams? Mark Brousseau, consultant, Institute of Finance Management (IOFM) spokesperson, and AP automation subject matter expert, puts it in perspective in a recent interview with The Knowledge Group. “Businesses today are expecting more from their AP function. They realize that if they can get at the information and data housed in their AP department, they can use it to support better management of their working capital, mitigate potential risk and make more strategic decisions,” Brousseau said.

This allows companies to transform data into knowledge that can better inform their business decisions and streamline their business processes. And it’s made possible with smart data extraction, the most important feature of advanced AP automation solutions.

With advanced solutions, this functionality powers the next steps in the invoice and payment processing workflow. Once data is extracted from unstructured content and then validated, the system uses that data to automate other tasks like routing and approval.

And it includes comparing the data against existing records within legacy finance systems/ERPs. This results in fewer errors and eliminates duplicate documents and transactions.

Making it ‘smart’

Data extraction using machine learning powered by artificial intelligence (AI) is able to “understand” what information on a document needs to be used and, more importantly, what should be done with that information to make it relevant data.

As it pertains to advanced AP automation solutions, smart data extraction technology leverages OCR to read information from scanned/photos of paper invoices or PDFs received via email. It then interprets the information, extracts the relevant data, then applies it to the appropriate field in the application to be reviewed and sent for approval. Finally, the data is exported to an ERP. If there are pieces of data that cannot be interpreted or read, the system learns over time how to extract those missing pieces.

With constant enhancements, no end user is ever involved to teach the software. The staff transitions from manual data entry and third-party verification to simply reviewing data extraction for accuracy. If there is a miss, the reviewer can click inside the application to quickly correct it and flag the miss.

Utilizing machine learning optimizations, the system will become more intelligent — smarter — over time, reducing the number of mistakes and increasing overall efficiencies. That will earn your AP department an A+!

Share on Procurious

Discuss this:

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.