ABBYY Vantage – Assemble Activity Video

Watch our video to learn how to use the ABBYY Vantage – Assemble Activity to intelligently separate multi-page documents into individual documents and/or transactions.

Hello. Today I’d like to show you how we utilize the Assemble Activity within ABBYY Vantage. Now, the Assemble Activity gives us the ability to control and manage how we deal with multiple page transactions or even documents with multiple pages in it, or a document that has multiple documents in it, like what we see on the screen here. So what I have is a sample that shows six pages, but every page here is actually an independent document. So these are just some sample direct deposit forms. And you can see here every single page, even though there’s a couple different types, is its own independent document.

So what we’re gonna do is use the Assemble Activity to break apart this document the way that we expect it to be broken so that instead of six pages, I actually have six different transactions.

All right. So what you’ll see here is we of course have a process skill. And in our process skill we have our standard activities like input and outputs. For today’s demo, we’re gonna drop that sample into an FTP folder. So it’s pretty simple. We will then call the Assemble Activity. Within the Assemble Activity, we have settings here. Specifically in today’s, we’re gonna use classifications. So we want the software to look page by page and determine what the documents’ is, and we’re gonna tell the software, Hey, if you find one of these given direct deposit forms or document types, we want you to consider that the first page until you find another one.

So the reason why that’s important is because some documents aren’t always as simple as having single pages for every single document. So we wanna tell the software when to split the document by using this first page checkbox. So once a software does that, we’re gonna go ahead and classify the document, and then based on that classification, we will extract from the given document type. So of course we have our action pane here that determines the classification skill that we’re pointing to. And then here I have actually extraction for two different documents. If you remember in my sample, I actually have one called ACME and one called Custom Kitchens of Bayshore. So that’s what you see here is the extraction skills that we’ve set up here for each of those given direct deposit forms. And then of course, we will export that to the FTP folder.

But the critical steps are right here in the middle. Assembling the document. Now that we have it assembled, we wanna classify of course, and then extract that information from the given document type. So let’s go ahead and run a sample. What I’m gonna do is bring up our FTP client. I’m gonna navigate to our input folder, and I’m going to drag that sample that you saw into the input folder. Now, what the software’s gonna do, of course, is monitor the input folder here, and when it’s ready and it’s come to its next polling cycle, it will grab that document.

All right, You can see the software now has pulled that document. It is now an actual transaction. If we wanted to, behind the scenes, we would see that transaction in our skills monitor. But what we’re gonna do next is we’re gonna just monitor our output. And what we would expect in this output is for the software to find each of those individual files. And we’re gonna have it export a PDF and a JSON of that file extraction that we have for each of those given document types.

All right, so here is our transaction. If I go into our transaction, you’ll see I have the PDF of each of those and a correlating JSON. So the software did me two favors. It split up the document, and then based on the document type, it extracted the given fields for us here. So this is a perfect way and a perfect example of how we utilize the assemble methodology here on a process skill. I hope you enjoyed this video.

[Music- “‘Engineered to Perfection’ performed by Peter Nickalls, used under license from Shutterstock”.]

Leave a Comment