ABBYY Vantage Video – Laserfiche® Integration

Discover how to integrate ABBYY Vantage with Laserfiche® for extraction, classification, and storage of metadata.

Hello. Today I’d like to show you our integration with Laserfiche®. And the cool part about this technology is that we have the ability to kind of do a direct integration with them. Not only can we give you the document, but we can pass along its metadata so that you have that for long-term storage within Laserfiche.

So what I’m going to do today is process a lockbox file. It’s kind of a file where we get multiple documents in one, and what you’re going to see is that we have the ability to pass that over to ABBYY Vantage, and then we will pass that over into Laserfiche.

So while that’s getting processed, let me show you that workflow. So in this case, a document is going to come in. We’re going to assemble the document because it’s one PDF with multiple documents in it. We’re going to then classify each document. We’re going to extract critical information from those documents. If we need a human review, we will pass that to human review and then we’ll of course output that over to Laserfiche.

So let’s go check on the status. Our status is we are waiting for review so that we can take a peek at that document. And here you can see what we have. So this is a very standard lockbox example, but we have a table of contents and then we had some scan dividers, and then we may have a denial form. We also have a patient record. We also have an explanation of benefits. And the cool part about our technology is first off, we broke apart the documents. So we were able to classify each individual page or pages. We were able to then from there, extract based on that document type. So for an EOB, for example, we may want header information and claims. And then for a denial, we may want the basic information, like who the patient details are, and is this a denial or what kind of authorization did we receive on that?

So once we’re done completed here, I’m going to hit our complete button. And what you’ll see is that we have our integration over to Laserfiche completed. So if we look at our workflow one more time, we are now here where we’re going to pass that information over to Laserfiche.

So what I’m going to do is go ahead and refresh our Laserfiche system and we’ll go up to our claims process here. When we go up to our claims process and we go into our active accounts, what you’ll start seeing here is that now those documents that we had processed over in ABBYY Vantage are now stored in Laserfiche from a long-term repository perspective. So we have this document, we now have its document type, and we have all of the critical information that we’ve extracted off of that document here for permanent review.

This is a perfect example of where we can use two best-in-class technologies to do the extraction, the classification, and then of course the long-term storage over here into Laserfiche.

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

“ABBYY”, “ABBYY Vantage”, “Vantage”, and the ABBYY Logo are all registered trademarks of ABBYY Software Ltd.

“Blue Cross”, “Blue Shield”, the Blue Cross Word Logo, the Blue Cross Image, the Blue Shield Word Logo, and the Blue Cross Image are all registered trademarks of the Blue Cross Blue Shield Association. All Rights Reserved.

“Humana” and the Humana logo are registered trademarks of Humana Inc. All Rights Reserved.

“Laserfiche” and the Laserfiche logo are registered trademarks of Compulink Management Center, Inc. All Rights Reserved.

“Lincoln Financial Group” and Lincoln Financial logo are registered trademarks of Lincoln National Corporation. All Rights Reserved.]

ABBYY Vantage Video – Processing Lockbox & eLockbox Documents

Learn how to process Lockbox and eLockbox documents in ABBYY Vantage.

Hello. Today I’d like to show you how we process Lockbox documents, and sometimes we refer to these as eLockbox documents. And essentially what you have is a document that contains multiple different types of correspondence that are then kind of combined into one big old PDF document. And we got to process those and extract that information and do something intelligent with it.

So here’s an example of a document where it’s been prepared as a Lockbox. We typically would see some sort of table of contents, which describes what this file includes. There would be some sort of scan divider or divider per document, and then we would actually get into the document. And then that cycle repeats where we have another scan divider, and then we potentially have another document and then we’ll see another scan divider and then lastly, our last document here. So this is very common in healthcare and financial fields where we just see the sort of collaboration of documents into one big old PDF and now we have to parse those.

What you see here is a multitude of different document types. So we may have a discharge summary, which is kind of part of a patient record. We may have a denial letter, which belongs to the patient, needs to be filed appropriately. And then we may have an explanation of benefits document where of course we want to extract the information and from there and support that and extract that to our claiming system downstream. This is very common of a setup for us, and what I’d like to do is show you how we process this with ABBYY Vantage.

So what I’ve done is I’ve actually uploaded this document into ABBYY Vantage, and you’ll see here we were able to take that one big PDF and separate the individual documents. You can see the first page here is determined as a table of contents.

Our second page, if you remember, is now we start the scan divider in this specific example.

And then of course we get to the actual meat and potatoes, which is our Lockbox. And you’ll see that here. And what we’ve decided is that this is a denial letter. We know the patient, we know all of the metadata on the document, and then of course we know that this is actually in a denial. Here is the final decision on it.

And then in proper format, we saw the scan divider and we were able to extract any information off of that. So sometimes these scan dividers actually give us good transactional information. Oftentimes they’re done by batches and there’s a transaction number.

And then of course, we’ve got our next document, and we’ve been able to classify that. Classification means we determine the document type. So we’ve now determined automatically that the document type for that fifth page is a patient record. So I’m able to find patient record information such as ID number, date of birth. What is the type of document? Is this a discharge summary? Is this medication review? Is this a physical and history document, et cetera.

And then lastly, of course, our last document here was our explanation of benefits. So on an explanation of benefits, we may want the insurer’s name, we may want the patient information, we may want member details, we may want date of birth. And of course we want claim sort of information off the document.

But this is a very common use case. And ABBYY Vantage gives us the ability to quickly, within minutes, set up a process where we automatically take a big PDF, we tell the software how to classify the individual pages, and then of course, based on the document type, we will extract the critical information off of that document. This gives us the ability to pass this information, both the individual document and its metadata downstream to our document management system and potentially claim adjudication system or whatever our process is downstream, so that we have both the document and its metadata that we’ve extracted from it.

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

“ABBYY”, “ABBYY Vantage”, “Vantage”, and the ABBYY Logo are all registered trademarks of ABBYY Software Ltd.

“Adobe”, “Acrobat”, and the Adobe PDF logo are either registered trademarks or trademarks of Adobe in the United States and/or other countries.

“Blue Cross”, “Blue Shield”, the Blue Cross Word Logo, the Blue Cross Image, the Blue Shield Word Logo, and the Blue Cross Image are all registered trademarks of the Blue Cross Blue Shield Association. All Rights Reserved.

“Humana” and the Humana logo are registered trademarks of Humana Inc. All Rights Reserved.

“Lincoln Financial Group” and Lincoln Financial logo are registered trademarks of Lincoln National Corporation. All Rights Reserved.]

ABBYY Vantage Video – Configure Mobile Capture

Discover in our video how to configure a mobile upload in ABBYY Vantage.

Hello. Today I’d like to show you how we configure a mobile upload within ABBYY Vantage. Now this is a pretty cool feature. It gives us the ability to allow an end user to use their phone to provide documents into the solution. And this is going to be a technical video today where we explain how to set up this process.

The one thing that I want to bring your attention to very quickly here is the Vantage Help section where we refer to as “Uploading documents from a mobile device”. There are a lot of features built into this platform to customize this experience and therefore I just want to make sure that you are aware of how to find this. And this is just simply done with Vantage. Under the help section and the documentation.

Within this section, there’s also a link to the Swagger API, where you can find all of the calls that are supported within Vantage. Now, the reason I mention that is because the idea of uploading documents through a mobile device has to be secure. And one of the ways that happens is that Vantage gives us the ability to ask the API call for a token and a mobile experience link. And that’s essentially what we’re doing here as we go into the Vantage API.

So allow me to show you how that works. And the way I’m going to show you is by asking the API to provide us a mobile upload link. And this mobile upload link is secure. Also, it’s a timed mobile upload link. So it lasts for a period of time and then it expires. And that’s obviously for security purposes. So we’re in the Swagger page and we’re under transactions. The way that we initiate this mobile upload link and we ask Vantage to provide that to us is we go to our transactions and we say, “Hey, let’s try it out”.

So let me give you an example of how this is done. Obviously we’re going to have to provide it a skill id. And then of course we want to make sure that this generate mobile input link is set to true. That parameter being set to true is what’s going to ask Vantage to create the transaction and as part of the response, give us the mobile input link. So I’m going to go ahead and execute that. When I do, what you’ll see here is a response where I get a specific transaction Id. Also, I do get a mobile input link.

So what I’m going to do here is I’m going to copy that link into my clipboard. And there’s a couple of things. I’m going to open up a new notepad here. What I’d like to show you is a couple of things that we get when we get this link. Let me get rid of some of the noise here real quick. There are several different pieces of this URL. First off, we have some query strings that are very, very important. We have a query string called md. This is the mode of the mobile capture experience, and I’ll explain more about that in a second. We have the token of the mobile capture experience and specifically the token of how we’re going to provide this to the end user. And then of course we have a version. So there’s several different pieces of this URL. As you’ll read in the documentation, we can customize the mobile experience. And the way that we do that is we modify this MD query string. And there are a couple of ways we can do it.

In short, we can provide it some JSON and I have some example JSON here that shows us how we could do this. So in this sample JSON, we’re asking for a passport and we’re asking for a proof of residency where we’re asking the user to make a choice of what kind of document. Is it a rental agreement or a utility bill? So what I’m going to do is I’m going to copy that. Now, if I go back over into our query string, this is actually going to get overwritten with the JSON. However, before we do that, we must URL encode this JSON. I’m going to go ahead and do that here on my other screen. And you can use any third party URL encoder for JSON.

So once you do that and you copy it, you take your JSON, you get that URL encoded right here is where you would paste it. What we have here is our transaction information. That’s our transaction id. This is the mode which explains the JSON, which once again changes the user interface that we’re going to prompt Vantage for. The token and the version here. So what I’m going to do is simply correct my URL now that I have it all separated and I will show you here the mobile experience.

So now I have the mobile experience in front of me. Essentially what I’ve done is that URL that we just built, I’ve provided to my mobile device. And what we’re going to do here is simply open that from here.

Now once we load this experience, you can see here I have what we’re asking for as a passport and a proof of residence. This is customized from that JSON that we URL encoded. So that’s where the software realizes what I need to ask for here. So I’m going to simply capture a couple of documents and show you this awesome user experience.

This gives us the ability to ask for a document without having to have an app on our phone. The user does not have to download an app or have an app pre-installed on their phone. We’re simply just asking them to open this experience.

Here’s an example where I just did a passport, and when we come to the proof of residency, we have the ability to ask for a utility bill or a rental agreement. So today I’m going to go ahead and select a utility bill. And you can see here I have a utility bill in front of me so we can auto capture that. And this experience actually, I’m asking for two utility bills, so I’m going to use the same exact document here. You can see as I hover over the document, the software will look for the borders here and capture that document for us. A pretty cool experience here. And then of course when we’re done, we can click the upload button. And what that does is it gives us the ability to pass that information to the specific transaction in Vantage securely and confidently. So that’s the experience here of how we make this mobile upload process happen technically. From the end user perspective, you can see it’s simple. They just get a link that we would provide and then of course we open up this beautiful photo capture experience for them.

So let me summarize because this is pretty technical and I want to make sure that we’re very clear on how this is done. So the first thing we do is we ask Vantage to create a transaction and provide us a mobile link that we’re going to provide the end user. We have the ability to customize that mobile link with different parameters in the JSON. So if you remember, we have a transaction, we have a mode, we have a token, and we have a version. So those were our different query strings that we have the ability to modify. We have JSON, and this is all very well documented in the documentation. We have JSON that we provide to the experience that must be URL encoded. And that’s how the app, when the user sees it, knows what to ask for. So am I asking for a passport or a proof of residency or a driver’s license? And how many of those documents do we really need? That’s where the intelligence of the application comes from. And of course, we have our token here on how we’re going to access our software and give it to the ability to make sure we’re already authorized to use it.

So a very cool experience, very customizable, very configurable to make sure that your end users and your customer experience is top notch.

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

ABBYY, ABBYY Vantage, Vantage, and the ABBYY Logo are all registered trademarks of ABBYY Software Ltd.

Google Chrome and the Google Chrome browser are trademarks of Google LLC. Use of this trademark is subject to Google Permissions.

Notepad++ is a registered trademark of Don Ho. All rights reserved.

Swagger, Swagger API, and the Swagger Image (SN: 88160148) are registered trademarks of Smartbear Software Inc. All rights reserved.]

ABBYY Vantage Video – ACORD® Document Processing

Learn how to process ACORD® forms in ABBYY® Vantage.

Hello. Today I’d like to share with you how we process ACORD® forms within ABBYY® Vantage. Now what you see in front of us is an ACORD® 25 form. This is the form that is our certificate of liability insurance. So a very common form in business. And what you’ll see as I show you kind of behind the scenes of what’s cool with how ABBYY Vantage works with these forms is that we support a number of ACORD forms that are already prebuilt within the software for you to process. So what that means is that you don’t have to teach the software about these documents. All you simply have to do is upload them and start processing your documents automatically.

This is really cool because this gives you the ability to kind of instantly hit the ground running with the software. And of course, on an ACORD form, we’re looking for the header information. So, who’s the producer? Who’s the insured? Who the contact information is. And then of course, we get into our nitty gritties of the policy information that we have. What are the limits? What are the types of policies? Et cetera. And then of course any sort of certificate holder or signing details that we need off of that document.

So this is already prebuilt for us. Here’s an example of us diving into the commercial general liability, where we’re obviously seeing everything that the software extracted here and of course, we’re also able to extract all of the general limits and those sorts of things as well that will come off of these sort of ACORD forms. So it’s a very common implementation of what the software’s able to do for us. Once again, already prebuilt out of the box and ready for you to consume without ever having to even worry about setting up your own model because we already have those in play for us. Now, let me show you how we kind of get started very quickly within ABBYY to make this happen.

The first thing we do is we set up a process skill. And I already have one that is preestablished for us, but essentially this is how easy it is. I dragged an input, an extract, a manual review and an output. The extract activity should point to our prebuilt ACORD 25 document skill. Document skills, if you remember, are the ones that tell the software what model to use for extraction. And then this is an optional queue, but we have the ability to stop a document for a human review upon certain criteria, whether it’s a business rule, so we didn’t find certain fields or they weren’t the certain math that we wanted, or we can force every document to come in. So this would be an optional step. And then of course, when we output this, you have a ton of configuration options in how you get that data back to you.

But the cool part is that we’ve already had that prebuilt model, so I don’t have to set up an extraction skill. I’ve already done that. The software’s actually already done that for us. It comes prebuilt within Vantage. So all we got to do is set up a very basic process skill in a matter of a few seconds, and we are processing these ACORD forms as if we’ve been able to do this a million times.

Looking forward to learning how your experience goes with this technology. If you need any help or you have interest in using ABBYY Vantage, please contact us.

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

ABBYY, ABBYY Vantage, Vantage, and the ABBYY Logo are all registered trademarks of ABBYY Software Ltd.

ACORD, “Association for Cooperative Operations Research and Development”, and the ACORD Logo are all registered trademarks of the ACORD Corporation. All rights reserved.]

ABBYY Vantage Video – Logistics Document Processing

Discover in our video how to process logistics documents in ABBYY® Vantage.

Hello. Today I’d like to share with you how we process logistics documents. And typically when we get these sort of use cases, really what we see is that there’s a packet of information that’s been delivered to you that has logistic information and bill of lading documents, commercial invoices, packing slips, et cetera and our software has the ability to take that packet, split it, determine the document types, and then extract information from those documents. This is a very popular scenario in the logistics world.

Now, what we see in front of us here is a packet that I’ve received and it contained multiple documents. So this was one PDF with multiple documents in it. And our software was able to split it, and we were able to determine that in this case, the first series of pages is a bill of lading, and then I had a certificate of origin, there’s a commercial invoice on the document, and then lastly, a scale ticket. So in our case, what we have here is the ability to what we call assemble. So split up the packet, determine the document type, we call that classification, and then of course, based on that document type extract the information. So we’ve been able to determine that the first page, for example, is a bill of lading, and then the model that we call for this bill of lading is referred to here on the right. So this is the information that we’ve extracted on the software.

The cool part about this technology, especially in transportation, is that we have the ability to machine learn different document types. So as we see different bill of ladings or as we see different commercial invoices, the software can learn those documents and also it can learn what to extract off of those documents. So not only does it know that a new document is present and how to classify it, but it also can determine what to extract on that document, even though it’s never seen it before. So machine learning in logistics is a very, very important aspect of automating these sort of processes.

Now that you understand the concept, let me show you a little bit behind the scenes on a typical setup for a ABBYY Vantage Process Skill. What you’ll see here is that we have always an input and an output. Every single process skill will always have that, but right here in the middle is really where the critical part of this process skill comes into play. You see, I have an assemble step. The assemble step gives me the ability to classify and break apart that packet. So although I may have one PDF with all of these details in it, or one email with all these details in it, we can determine when to split it. Now that we know how to split it, we will classify it. So we’ll determine the different document types within the packet, and then of course, based on those document types, we will extract it. Then lastly, if and only if needed, we would send that to a review queue. So this is a very common flow, especially in more complicated scenarios where we just need a ton of document types in one given packet.

Now, before I wrap this up, I wanted to kind of share also the different document types that we support. We support a tremendous amount of document types in the transportation and logistics world. You’ll see some of those listed here. If you don’t see some of the documents that you have, it is very likely that we have models already created for them. Also, our machine learning technology gives us the ability to adapt to new documents that we’ve never even seen before, very, very rapidly, and without the need to do templating or without the need to have consultants or highly technical staff to do that for you.

Definitely continue looking into your logistics use cases here with ABBYY Vantage. I think we’ve got a really cool piece of technology that can automate this for you.

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

ABBYY, ABBYY Vantage, Vantage, and the ABBYY Logo are all registered trademarks of ABBYY Software Ltd.]

ABBYY Vantage Video – Property Tax Bills

View how you can extract key information from Property Tax Statements via ABBYY Vantage.

Hello. Today I’d like to give you a quick overview of what our property tax bill can extract for us on either residential or commercial property tax statement.

It’s a very clean, what we call skill. This is a document skill that we’ve developed to extract information from these bills. You can see that the model that we’re using is referencing things like header details on the tax statement. So things that are found one time such as the owner or the parcel information, et cetera. And then of course we got our repeating information, or taxing unit details down at the bottom, which of course can sometimes be one item. It can sometimes be pages of items. So our software is definitely built to process a variety of these tax bills. But that’s what I wanted to show you real quick is kind of just a summary that we’re able to extract this information on these property tax bills no matter what they look like. Obviously, different municipalities or counties or different locations have control of their formats, of their tax bills. However, our machine learning models do have the ability to learn those different formats, therefore taken away the requirement of human template development and things like that.

Now, let me kind of explain to you quickly the workflow through our solution is very simple and it is configurable, but this is a very common way to do it where we’ll bring a document into the solution, which is ABBYY Vantage. We will extract the information from the bill. We will then review it if necessary, and then of course, we can provide that output to you in the proper format that your business looks to consume. This is very, very common flow and a very great use case and model for property tax bills.

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

ABBYY, ABBYY Vantage, Vantage, and the ABBYY Logo are all registered trademarks of ABBYY Software Ltd.]

ABBYY Vantage Video – Integration with MuleSoft®

Learn how to integrate MuleSoft® with ABBYY Vantage® to retrieve document information from a source application.

Hello. Today I’m going to show you a really cool integration between MuleSoft® and ABBYY® Vantage®. Now, this is a very simple flow and very simple to develop in these mature applications.

So what you see in front of us is our Anypoint Studio so that we can develop the flow. And this flow is pretty simple. We have our listener, which is the way to invoke this process. That can happen through a multitude of other options, but today it’s just that we have an API listener that we’re going to invoke this process. Once that process is invoked, you can see here we’re just going to kind of make sure that as part of the post to MuleSoft, we get some file details and those sorts of things. So we’re going to store those in variables. Then we’re going to go to ABBYY Vantage® and say, Hey, give me a token, and then we’re going to store that token in a variable, and we will use that token then in this next activity to upload the file to Vantage.

So a very simple flow, but our goal here is to get a document from a source application through MuleSoft to ABBYY Vantage. The way that we’re going to invoke this listener today is through Postman®. So pretty simple way that we want to call it and invoke it. But this would obviously be a multitude of options. But what I’m going to click is our send button. When I click the send button, you will see that part of my MuleSoft flow was to return the transaction ID. This transaction ID is the ABBYY Vantage transaction ID. So then we can store that and we can save that in our flow here in other variables. So we have a lot of options here on what we do with that data, but that’s our goal, is we’re going to upload that file to a Vantage. And as part of that response, we’re going to provide the transaction ID to the caller.

If we look on the ABBYY Vantage side, what we’ll see here is that we now have a document that is available for our review, and of course we can open it, we can work it in manual review. Ideally, documents don’t even go to manual review. So the part of this flow would obviously be not just passing the document and getting the transaction ID, but also parsing the details of the documents so that either in JSON or other standard formats that our consumer application requires, we then have all of the details, all the field level details off of that document that we can use to kind of transform and transpose over to the caller application.

So a very cool way to use mature technology to pass information through, in this case, Vantage APIs, and get that information and parse that and make sure the calling application is updated. And the cool part is here is that it’s just a very simple series of steps where we’re asking ABBYY Vantage for the token, and of course we’re uploading files. And then eventually we may even read the results from Vantage here as part of this flow. So just want to give you a glimpse of how we set up this integration. Hope you enjoy this video.

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

ABBYY, ABBYY Vantage, Vantage, and the ABBYY Logo are all registered trademarks of ABBYY Software Ltd.

MuleSoft is a registered trademark of MuleSoft, Inc., a Salesforce company. All other marks are those of respective owners.

Postman logos, name, and related product names are registered trademarks of Postman, Inc.]

ABBYY Vantage Video – ChatGPT(TM) Sentiment Analysis

Discover in our video how to utilize ABBYY Vantage to perform a sentiment analysis with large language models like ChatGPT(TM).

Hello. Today I’d like to show you how we can integrate ABBYY Vantage with large language models in this case ChatGPT(TM). So what you have in front of us is a very basic restaurant survey, and that’s really the kind of the concept of today’s demo is that we have the ability to get things like a large comments field and be able to grade that based on what we refer to as sentiment or what is the intent of that comment in this case. Is it positive, negative, or neutral? So that we have some generic grading of incoming documents and the feedback we have on those documents.

This is a very basic example of some surveys that we had from a restaurant. Really what we’re grading here is the comments field. That’s really what we’re trying to capture off the surveys. And then what we’re gonna do is we’re gonna pass that over to ChatGPT for sentiment analysis so we can understand whether it’s a positive, negative or neutral response.

And the workflow will look like this. A document comes into ABBYY and we’ll extract that comments field. We will then send that comments field to ChatGPT, and then of course we’ll review it.

I’ve already set that up for you and kind of show you some of these examples here. So in front of us is an example of a survey that we got and you can read the comment is quite positive. And so what we’re doing is we’re passing that comments to ChatGPT and ChatGPT is looking at the sentiment of that comments field and telling us this is a positive statement. We’ll look at another one here where potentially it was just, okay, the comment said my experience was just, okay. So that’s what we refer to as a neutral sentiment. And then of course we have the negative sentiment where we are looking at a comment that obviously says we’re not coming back to eat anymore here. And that is of course a negative sentiment. And then last, just for fun, we have a book <laugh> of a comment where, look, we’re just getting a substantial amount of detail here that tells us this person had a very negative experience. They’re telling us why. Said they’ll never come back again and try other restaurants. And of course we are looking for a negative grading on that statement.

So sentiment analysis is one of these ways that we can take and have ABBYY Vantage extract that data for us and pass that to a large language model where we can grade it for either summarization or sentiment. And in today’s demo, this was sentiment, a very basic example, but really in real life we would use this in some sort of digital mailroom experience where documents may be coming in and we’re looking for whether or not a letter was a complaint letter or a compliment letter and those sorts of things. So hope you enjoyed this very basic review of how we can integrate ChatGPT into ABBYY Vantage.

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

ChatGPT is a pending trademark of OPENAI OPCO, LLC. All rights will be reserved.]

ABBYY Vantage Video – Manual Cropping and Splitting Within a Review Queue

Learn in our demo how to manually crop and split documents within a review queue in ABBYY Vantage.

Hello. Today I’m gonna walk you through how we set up manual review cropping on a document. And this happens in places where we actually get three separate documents on a given page or even within a given file. But this is an example of what you see on the screen. I have one page with three separate IDs on them, and really what we would need is those to be three separate documents. So in ABBYY Vantage, we have the ability to allow a human to tell us where on this page the documents start and stop so they can crop them. And then from there we can set up the rest of the extraction and classification processes automatically.

So this is very common, like what you’re gonna see in business. Somebody just gives us three documents, three in this case IDs on a given page. But we actually need those to be three separate documents for storage and automation downstream.

So what we’re gonna have here is what we refer to as a process skill. And today’s process is gonna be what you see here on the screen. We’re gonna bring a document in, we’re gonna send that to a cropping review screen. So that’s the very first thing that’s gonna happen is we’re gonna ask the human to crop this image to make sure that we’ve auto separated it. Now what that does is it will create one document with three separate IDs. So if you remember here, when we crop, what’s gonna happen is we’ll have three separate IDs, but all within a single document. So that actually creates three pages. That’s not quite what we need, but good enough for the user. So we don’t wanna burden the user with having to assemble the document manually. So we will do that automatically. We will assemble that through what we call our assemble activity, using our classification step. We will then extract the information from those IDs and then of course we’ll review the results together. But the idea is, is that a human’s gonna come into Vantage, crop that document for us, so we know where those IDs start and stop, and then we’ll automatically assemble them here.

So let me show you kind of this process. So we’re gonna go ahead and upload this ID PDF, and that’s going to go to our process skill.

Now this should happen pretty quick. What it’s gonna do is it’s gonna send us right into that cropping activity that you saw there on the workflow. So we would just hit our review button here. And what we’re gonna ask the end user is to look at this document and tell us where these IDs stop and start. So no big deal. We’re gonna crop this image here using our cropping tool. And all we need the end user to do is just tell us where these documents start and stop. So this looks like a good ID. This looks like a good ID. And lastly, this looks like a good ID as well. And we’re just gonna go ahead and apply the crop.

So this is what the software’s done now. So we have a document that came in and this document has three pages. Like I said, that’s not necessarily always ideal. Typically in downstream processes, we would actually want these to be three separate documents, not a document with three separate pages.

What we’re gonna do is once again, carry down the workflow. So we’re right here at the review and crop. Now we’re gonna tell the software to go ahead and assemble that for us, and then we’ll go ahead and extract. So let’s just kind of release this from our queue. We’ll save and close this. We don’t need to extract any data yet. And then we’ll go ahead and complete it.

Now this task will be completed. So what we’re gonna do is we’re gonna kind of see that here. The software’s gonna continue processing that image. And then what we will do is we will have a queue that shows three separate documents.

So this is now what we have. So we’ve cropped it. And now you can see here I have three separate documents, each of those that we’ve manually cropped here, but now we’ve classified them correctly as identity documents and we’ve extracted the data from them correctly. So we can kind of see here on these documents here. Not only do we know the document type, but obviously now that we know the document, we can use our intelligent document processing extraction technology to extract the critical details off of those documents. So then what happens from here on is really up to you as the citizen developer to take these documents over to data and perform interactions downstream.

But the critical part, once again, is knowing the workflow. Is we have this cropping mechanism that allows the end user to intervene and tell us where documents start and stop. And that’s all we’re asking that end user to do. And then the rest here, we will handle ourselves through our activities in the ABBYY Vantage Suite.

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

Adobe, Acrobat, and the Adobe PDF logo are either registered trademarks or trademarks of Adobe in the United States and/or other countries.]

ABBYY Vantage Video – Address Parsing

Discover in this video how to perform Address Parsing in ABBYY Vantage.

Hello. Today I’d like to show you how we perform Address Parsing within ABBYY Vantage. So what I have here is obviously a very simplified version of a document that it has an address. And on this address we wanna extract the name, the street, the city, state, and zip.

What we’re gonna do is we’re gonna go ahead and create a brand new document skill in our Advanced Designer within Vantage. We’ll call this our Address Parsing Skill. And when we do that, the first thing we’re gonna do is we’re gonna go ahead and upload a document, just kind of as our reference document.

And the next thing we’ll do is we’ll go ahead and walk through the setup. We’ll go ahead and map some fields. When we map our fields here, we’re gonna have a few things. So we know that we’re gonna have a field that describes the address. So let’s just go ahead and start mapping some things here. We’re gonna call this the full address because it’s the whole thing. And then we know that we’re gonna want fields for each of these independent parts of the address. So let’s just go ahead and add some fields here for the name, the street, the city, state, and zip.

All right. Now that we have our fields set up, the one thing I like to do at this point is I like to make sure that we have our reference details completed as well. This gives the software the ability to compare what it extracts versus what we told it is really the truth. We call that our reference spot. And so what I’m gonna do is I’m gonna go ahead and find each of these fields just so the software when we do it automatically has something to compare itself against for the truth. So we know for the name, the name is gonna be located here. We know for the street. For the full street, we’re here. For the city, we are located here. For the state, we’re here. And of course for our zip, we are here. So we have the full address. But then of course we told the software what the truth is for the other fields that we wanted to automatically extract.

Now that we have that set up, let’s talk about the activities that we’re going to need. So we have within our software, the ability to extract based on rules. Then we will perform Address Parsing. Now the last part of the video will be to actually get the name on the address, which the Address Parsing Module does not give us, so we will use our Named Entity Recognition to get the name of the address.

So let’s go one by one here. Let’s go ahead and tell the software how to do the extraction. We want the full address. We want the software to know where to find the full address. So we’re gonna go ahead and just make sure we only map the full address here. And when we do that, we’re gonna go ahead and go to our search elements and we’re going to tell the software that we’re gonna draw this on the image.

So we’re telling the software, “Hey software, this is where we want you to pull the full address from.” Just because I know what’s gonna have to happen here. This is gonna be a full paragraph. So not just a single line of text, but we want the software to grab that whole region here. Now we have what’s called a paragraph of text, which is on that specific region on the document.

So at this point we’re gonna go ahead and test the activity. This should be a pretty obvious one for the software here. We’re just telling it where to pull that paragraph of text. We have a hundred percent results and that’s because the software now compares against the truth. If you remember back in one of the previous steps just a minute ago, we told the software where to find it. Now it’s telling us where it found it automatically and it’s gonna go ahead and tell us if there’s any difference, which in this case there is not.

So now we told the software where to find the full address. Now we want to teach it how to parse the address. So we’ll go ahead and add our Address Parsing option here. And the software’s gonna say, “Okay. Hey, where do I find the full address?” And we’re gonna say, “Hey, you find it from this field.” And of course we’re going to tell it the things that we know it will find. Now just out of experience, we won’t be able to find the name as part of the Address Parsing. We’re gonna come back and do that. So we’re gonna find street, city, state, and zip. And we’ll go ahead and set up our mapping here.

And what we will do here is we will go ahead and test the skill. So the software automatically comes with intelligence that can take that full address field and give us the result here. And now we have our results. We can see where the software was able to extract that data for us. And as you can see it found street, city, state, and zip. Of course it did not find names. So let’s go ahead and now that we know the software can find and parse the address, let’s go back and say let’s teach the software, how we can extract that name.

What we’re gonna do here is go ahead and use our Named Entity Recognition. This gives us the ability to reference the full address here, but in this case what we’re going to do is just grab the name from the documents. So we’ll call this the organization and the software is gonna use the full address and give us the organization here and put that into our name column. Let’s go ahead and test the skill now.

And now at this point we have a hundred percent accuracy. So the software’s using what we told it as the truth and now it’s going to extract the information on that name for us.

So at this point we have taught the software where to locate the full address. And then using our Address Parsing Activity, we were able to get the street, the city, state, zip, we could even get things like country. And then to actually get the entity on the address, we used our Named Entity Recognition. So we have just full complete control of how this Address Parsing takes place. Now what we could do is we could obviously deploy this skill like we do in other situations with the Advanced Designer and use this technique to get the address details and the entity on that address.

Hope you enjoyed this video. If you have any questions, please reach out to us.

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

Adobe, Acrobat, and the Adobe PDF logo are either registered trademarks or trademarks of Adobe in the United States and/or other countries.]