Outlook: From Capture to Acquire – Why Context is King

As I look back on 2019 at the good, the bad and the in-between, I see a trend forming with our customers and in the markets we serve. Organizations are starting to build broader strategies around their document capture needs, tied to their digital transformation strategies. At a tactical level, companies are evaluating the automation of their core processes. 

However, legacy capture has distracted the enterprise into viewing document capture as a cheap, commoditized method of automation and content data extraction. Essentially, legacy capture sits at the periphery of the enterprise and facilitates the single-use of flat – barely usable – data through a fixed, static predetermined process. The data it uses is really a digital “plastic bottle” to the organization. It’s leveraged once, used, and then no one knows what to do with it. So it is typically purged, thrown away or left in a dark corner of the IT world. It can create major headaches in this era of GDPR and regulation if it floats around the dark data ether. But that data, if properly harvested and enriched can be an immense value and a catalyst for true productivity. 

Think of all the content that flows in and out of your organization today. Most of it has no context, and is usually a trigger for more processes or tasks that need to take place. Take a government immigration/visa form that arrives via the mail. It is opened, scanned, its data extraction takes place and it is typically routed into a workflow or RPA process. This static process combined with flat data is where capture ends and the real work begins, triggering human involvement with questions such as:

  • What is this document?
  • Does the employee still work for the company?
  • Do they have valid ID?
  • Is their visa valid?
  • Who is their manager?
  • Are there other pertinent forms in the system?

It’s this context about the content and the relationships of key data that is the blockade to true automation. If technology can advance to gather the answers to those questions automatically, organizations will see increased productivity and agility in solving tasks.

In 2020, Ephesoft will address those problems and define a concept that looks at content capture through a new lens: Enterprise Acquisition, or more plainly put, “Acquire.” Before I dig in on a quick overview of this concept, let’s define acquire:





  1. buy or obtain (an asset or object) for oneself.
  2. learn or develop (a skill, habit, or quality).

The Acquire mindset requires us to look at incoming content in a new way. It is now an asset we obtain, as well as a new way for the Enterprise can learn. So how does that differ from the way we have treated legacy capture in the past? Does it require new technology? How do they differ?  

The Seven Core Areas 
Core Area From: 




Intent Legacy capture systems have a sole purpose: to capture inbound documents and their data through a static, repetitive automated process and place it in a system of record. With an acquire mindset, that captured data is a stepping stone to the promised land. Acquire focuses not only on the initial content data but provides a pathway to data enrichment and the creation of context. 
Data Captured data is plain, flat and one dimensional. Acquired data is enriched with contextual dimensions and relationships.
Presentation The presentation of captured data is tied to a fixed and static UI, typically for human validation and error handling.  With an acquisition system, the presentation is dynamic and expansive to take advantage of the extended dimensions and provide users with a single view to consume all the information to finish a task.
Technology Capture technology leverages pattern matching and templates to accomplish data extraction. Acquire leverages semantic data extraction and neural networks to accomplish its goal.
Post Process The data within a legacy capture system is purged when its task is done and now resides in an internal system. The Acquire data lives on within an ever-growing Knowledge Graph, providing immense value post process.
Automation Capture automation is task-oriented and human-intensive.  Acquisition is process focused and automation-ready.
Platform Legacy capture applications are thick client-server apps that don’t live well in the cloud. With Acquire, processes have no boundary and can live on-premises, in a hybrid state or in the cloud. This pervasive coverage gives organizations flexibility and fluid infrastructure.

As we venture into the new year, we will be posting more on this topic and how the face of document capture will change. Can’t wait? Contact us here

Expand on the History of Capture: Past, Present and Future

When you look at the history of document capture (now being called Intelligent Document Processing by some), the last few years have been a wild ride. With the advent of advanced supercomputing, machine learning and artificial intelligence have been claimed and touted by all, especially newcomers in the industry. Here is a quick history in the advent of these industry-changing technologies, how the automation tiers are laid out, and the rise of true content understanding.

Old School

Quite a bit of document capture technology has been around for decades and is still the foundation of many legacy capture vendors that have not advanced their platforms.

Manual Classification and Data Entry

Ah, the old standby. You would be amazed how many organizations still manually open documents, manually identify them and manually enter data. It is the lowest on the automation totem pole, but it works (albeit very slowly).


Next up the chain is the use of barcode technology on documents to automate inbound processing and handling. Encode the type of content and the data that lies within, and when read, data is mapped to fields and extracted automated. The arrival on the scene of 2D barcodes like QR Codes, Datamatrix and PDF417 changed the game and allowed huge data sets to be held in a thumbnail patch.

Zone OCR 

With structured, repetitive documents or forms that have the same data in the same location consistently, “zoning” or Zone Optical Character Recognition (OCR) allows for automated extraction of data based on location and the conversion of image to text.

Auto-Classification and Text Matching  

Combining OCR with advanced pattern matching allowed large rule sets to be created to search for a certain text string and combinations of anchor values and text to not only classify the document but also to look for key information, regardless of the page position. This also allowed for broad variation in document structure and layout.

The New Kids

As computing power and technology have accelerated, the move towards modern data science and models have spurred organizations in a race for “document intelligence.” Now, it’s much more than just documents that have the need for intelligence – it’s all types of content from images, documents, emails, PDFs and videos. 

Machine Learning 

Training a system to do your document tasks for you seems to be the ultimate. Whether it’s an administrator or a consultant loading sample images, or an end user telling the system where the necessary data lies, machine learning is the technology of the day. Building a model to process documents seems the norm, but many systems fall short and lack granularity of control and operate as a black box.  

Dimensional Deep Learning and NLP

Let’s face it, documents are tough. Think about how humans interpret documents: we use our experience, text-based cues, understanding of business language and interpretation of layout and many other dimensions to classify a document to understand what is of interest. There are very few companies just touching on this space, using a broad range of dimensional analysis. This plus natural language processing (NLP) is the “tech du jour” in the intelligent processing sprint to the finish line.

The Future and What’s Next? 

Where will the industry go next? What’s on the horizon? Is there a game changer waiting in the wings? I am predicting that by year’s end there will be some grand announcements with some groundbreaking technology that goes beyond those in the race today. Keep moving forward with your intelligent digital transformation efforts, but don’t stop there: stay tuned for the latest updates as technology advances.

If you don’t follow us on LinkedIn and Twitter, make sure you do so today to keep track of industry breaking news.

Plugging Smart Capture Into Your Digital Transformation Strategy

Digital Transformation Strategy: 4 Benefits of Smart Capture

Digital transformation is one of the most overused terms in the tech industry today. Just do a search for “digital transformation” on Google, you get over 419,000,000 results, many of them with varying definitions, scopes and opinions. The chatter that revolves around this terminology can be confusing, and so pervasive, it’s hard for IT and business leaders to come to a broad understanding of what it means.

Without a shared, true understanding, driving internal and external initiatives can be difficult at best. In fact, a McKinsey study found that 70% of digital transformation initiatives fail. But what is the problem? Is it the technology that is faulty? It is rarely the technology that fails the organization, but a lack of true understanding of what it means and a broad strategic plan for a “Digital Transformation Journey.”

So, just what is Digital Transformation? Here is one of the best definitions I have found from CIO Magazine:

“Digital Transformation is the application of digital capabilities to processes, products, and assets to improve efficiency, enhance customer value, manage risk, and uncover new monetization opportunities.”

Clean and simple. If you examine the 4 defined areas of focus, they could be natural header topics for strategic initiatives across an organization. Once these broad, overarching themes are in place, tacticians can hunt for areas where intelligent process automation can drive results.

Where does Smart Capture® fit into your digital transformation strategy?

Smart Capture technology is a critical and often overlooked component of any digital transformation initiative. Organizations run on documents, and document processes are a key challenge for all. Documents are also low hanging fruit, and their processes typically translate well to the digital. So, let’s see where the power of Smart Capture fits in our strategic transformation headers:

Improve Efficiency – This is the core advantage of implementing a Smart Capture solution to digitize document-centric processes. Having capture technology classify and separate documents, auto-extract key data and then place it in a system of record, creates great returns on any investment. Typically, we can reduce the time to process by 50-80% (read more in our case studies here: Ephesoft Document Automation Case Studies). These efficiencies can be gleaned through direct use of our application, but can also have a multiplier effect when combined with other technologies like RPA and workflow.

Enhance Customer Value – In this highly competitive digital market, creating customer-centered processes that are fast, accurate and complete is essential to any organization. Imagine if you could turnaround documents 50 times faster than your competition, or have the data you need from document instantly during a customer interaction. Smart Capture combined with the speed and scalability of the cloud can provide unmatched results that provide exceptional customer experiences.

Manage Risk – Documents are a minefield for most organizations. Their unstructured content can remain dark and hidden indefinitely without the right technology. Smart Capture can open up this content, and allow the organization to identify risks around private information, fraud, and many other areas of interest. Having the full picture from a data perspective can give an organization a 360-degree view of their risk factors.

Uncover New Monetization Ideas – Let’s face it, if you have all the data, that full picture can open your eyes to new opportunities, as well as poor performing areas. Tapping into all the information in unstructured content can provide deep insight and benchmarks that were previously unavailable. In addition, relieving your staff burdened with mundane data entry tasks, and allowing them to focus on new areas and on new projects can change your organization.

Interested in learning how Ephesoft can improve efficiency, speed up processes, help you manage risk and give you the data you need to run your business optimally? Want to multiply the effect of automation technologies like RPA and workflow with document intelligence? Contact us today for more information on your digital transformation strategy and next steps.

6 Trends in the Transformation of Document Capture

The past few years have shown a remarkable transformation in the document capture and data extraction market. With the rise of Robotic Process Automation (RPA), and the desire to automate labor-heavy, document-centric workflows, document capture and data extraction applications have had to morph to meet a broad variety of needs. Here are a few observations from my daily interactions with partners and customers, and a few trends that are transforming the market:

Expanded Market – It’s as if the robots found new and hidden uses for intelligent classification and data extraction on unstructured document data (using AI, of course). A market that was estimated a few years ago at $1-1.5 billion is now estimated at upwards of $20 billion. How can that much dormant market be hidden? I believe it is an awakening within organizations; a true, deep examination of document processes and their inefficiencies, with every process, no matter the size, are being considered a target for improvement.

No Longer Paper-Centric – The initial rise of document capture was during the rush to digitization and the conversion of paper files to digital assets. Scanning high volumes of paper is a painful, extensive process, and automation is required to shorten the task duration. Today, most documents being processed are “born digital,” already exist digitally or arrive in a digital state for ingestion and processing.

Humans and Bots – The rise of RPA requires the document capture platform to provide processing power that is available to both human and digital workers. The human worker accesses capture power through an app interface, while the digital worker leverages an API infrastructure for a digital processing stream.

App Enablement – The expectation is now for all native apps to have access to capture functionality (workflow, BPM, ERP, content services). The power and efficiency of behind the scenes, “transparent” capture, is now realized, recognized and available for all apps is desired.

Movement Up the Business Value Stack – Data extraction and classification started out as a way to speed up a low-level business process – scanning. Today, the information gleaned out of a document is a critical component of how that document is processed, and its value to the business. By becoming a core part of business operations, the value of this functionality has risen, and content capture has moved to the top of the food chain.

No Process Too Small – In the past, the costs and complexities of a capture project were barriers that reserved the technology only for large batch focused projects. Friendly and open APIs, and the rise of “Citizen Developer” applications that allow connecting to web services without code, have made the power of intelligent document processing available to all (you can read more on this incremental automation phenomena here: Incremental Automation with APIs).

All these factors have driven a need for modern, flexible platforms that can adapt quickly to customer needs and expanded requirements. For help in how Smart Capture® can change the way you do business, contact Ephesoft today.

Overcome the 5 Top Challenges in AP

Accounting departments have struggled with age-old invoice problems of too much paper, too many errors and high touch manual processes, which all can be costly. Invoices flow inbound in a constant stream, from all types of sources: email, paper, portal uploads, fax, etc. Manual sorting and management of these streams result in inefficiency and several additional challenges faced by accounts payable teams.

Below are the 5 Top Challenges (outlined in Ardent Partners 2018 State of ePay Survey):

  1. High Percentage of Exceptions – Exceptions processing can be painful and ensuring all invoice data is present and correct can be an arduous task. This forces AP personnel to spend hours or days tracking down missing or additional information.
  2. Invoice/Payment Approvals Take Too Long – Delays in ingesting and analyzing invoice data can delay approval routing and extend processing time.
  3. Too Much Paper – Over 40% of organizations still struggle with paper invoices, and typically have separate workflows for digital and physical invoices. This can result in further delays and inconsistent processing.
  4. High Invoice Processing Costs – Organizations that don’t leverage best in class solutions have a cost of $14.38 per invoice and it takes them up to 11 days to process 1.
  5. Lack of Invoice Data Visibility – Visibility into the process from start to finish is often lacking. Knowing volumes, exception rates and where to look for bottlenecks is prerequisite to process improvement.

Overcome the 5 Top Challenges in AP

Jumping Over the Hurdles

Where do you start? How can you tackle these challenges? The good news is, that organizations that leverage best in class solutions can reduce their overall processing cost per invoice from $14.38 down to $2.52. Simply stated, it starts with Smart Capture®.

Smart Capture becomes the moat and drawbridge around your organization that forces a single point of entry for all invoices, regardless of the source. It minimizes and/or eliminates the core challenges through the following:

A Single, Standardized Process – Regardless of source, all invoices get routed through the same entry process. Scans, email attachments and other sourced documents are all pulled into the same workflow. This provides an audit trail, and allows for analysis and transparency of invoice batches in process.

Exceptions and Rules Enforcement – Issues and exceptions can now be quickly identified at the earliest point in the process (at capture). This prevents data errors from entering the system of record or downstream processes, which can lead to extended processing time. Are you familiar with the 1-10-100 rule? Catching an error prior to a process will cost $1. After it enters a process, it will cost you $10 to fix. Once the process is complete, it will run you $100 to resolve.

Speedy Approvals – With an automated process, all invoice data available and manual steps removed, straight through processing can speed up approvals by getting the invoice in the right hands at the earliest possible moment.

Simple Conversion of Paper – Whether you are using a scanning copier or a dedicated scanner, being able to insert a stack of invoices into the feeder and have an application do the sorting, classification and extraction, is an immense time saver.

Integration with RPA and Workflow Tools – Content capture may be the initial part of the process, but many organizations are leveraging different tool sets to further automation, and Smart Capture® can seamlessly integrate with existing or new process applications.

With the challenges removed, the result is a lower cost per invoice, on-time and accurate payments and more productive employees who can spend their valuable time on higher value work.

Smart Content Capture and Hybrid Cloud: Taking Advantage of Cloud Power

Rush to the Cloud

The past decade has been a wild ride when you look at the advances in cloud computing. Although adoption was slow during its formative years, a recent survey by RightScale showed that 96% of respondents are leveraging the cloud in some way, shape or form, and approximately 60% of enterprise workloads will be running on some form of hosted cloud service.

The core drivers for cloud adoption have been outlined extensively, but a key feature has been the ability to slowly and methodically migrate via a hybrid cloud strategy. Hybrid cloud means different things to different people, so here is a quick definition:

hybrid cloud


  1. A computing environment that uses a mix of on-premise, private cloud and public cloud services with orchestration between environments.

“Orchestration” is the key word in this definition and will be a theme and focus for the rest of this post.

Why are some apps and services being left behind?

There some applications that just can’t go to the cloud. Many legacy software vendors have not invested in the “cloudification” of their applications, and these limitations have left many organizations with on-premise anchors that have become a persistent headache from a management perspective. Content capture is one of these areas of pain, with most vendors lacking cloud-ready feature sets, including web browser interfaces, comprehensive  APIs and Single Sign-On (SSO) capabilities.

In addition, many legacy capture vendors have taken an “all or nothing” approach to initial cloud offerings, with no way to leverage initial on-premise investments or ease into cloud capture with a hybrid scenario: you are either on-premise or in the cloud. They just don’t have the orchestration technology to coordinate a hybrid of on-premise and cloud infrastructures.

The Hybrid Challenge

What is necessary to enable the hybrid smart capture bridge, allowing organizations to leverage on-premise investments and the power of the cloud? Creating the software conduit between environments requires some key attributes:

Flexible Configuration – The application used for processing must allow the user to pick and choose what workloads to send to the cloud. This should be the minimum requirement along with being completely automated.

Transparency – It should be completely transparent to users whether the cloud or on-premise resources are being utilized. The application should control and orchestrate document workflows automatically.

Security – Creating a secure conduit and ensuring cloud data is protected is paramount. At a minimum, there should be secure API keys, and HTTPS endpoint, encrypted data at rest and a timed purge of documents and data.

Native Cloud To harness the true power of the cloud, especially in CPU intensive document capture processes, native cloud applications are key. Serverless architectures can provide scaling beyond any on-premise system capability to deliver “horsepower on demand.”

The Ephesoft Solution

Ephesoft recently launched its new groundbreaking hybrid cloud offering as an add-on with the release of Ephesoft Transact 2019.1, called the Cloud HyperExtender. This hybrid cloud solution allows existing high and variable volume customers the opportunity for “pay as you go” cloud access to speed and scalability that cannot be achieved with on-premise or single instance solutions.

In addition, it provides legacy capture customers the opportunity to bridge their move to the cloud and take the next steps necessary towards offloading all capture workloads to a more affordable and scalable solution.

Enhancing RPA Document Vision

Watch the on-demand webinar


Download The Slide Deck

Hello all, my name is Steve Boals and I manage our RPA technology partners here at Ephesoft. In this webinar, I will discuss how you can enhance your digital workforce’s document vision through 4 essential keys. By using the right document intelligence platform, I will show how you can improve robot automation and efficiency.

Before we get started, a quick overview on Ephesoft. If you aren’t familiar with us, we help you create actionable information from unstructured document content chaos. It is through this that we provide structured order, and finally data to enlighten your organization.

Enhancing Robot Vision

It is interesting that one of today’s most advanced process automation technologies, software robots, are broadly using decades-old technology in its simplest form to drive document automation. Smart Capture platforms can go beyond basic OCR, augmenting your RPA efforts, and enhancing robot vision. Before we see the solution, let’s examine the current state and the problem.

Every organization has document pain, either with physical documents, digital documents or most probably both. In the world of RPA, document-centric processes can be a key target. But to process documents, and the unstructured content within, bots need clear, unobstructed vision to analyze document streams, make intelligent decisions based on the data, and request help from humans, if required.

Factors Driving Smart RPA Adoption

The Everest Group put out a great report on RPA, called the “Smart RPA Enterprise Playbook.” By enhancing robot document vision, there can be a multiplier effect when you examine difficult enterprise document workflows where just a minor enhancement or improvement can dramatically impact a wide variety of the factors on this list.

The Process of Documents for Humans

If we look at a typical organization, they receive documents from a wide variety of sources on a daily basis. This typically creates a multi-channel problem, and organizations struggle creating a streamlined flow for physical and digital documents, let alone one from fax, scanners, copiers, mobile, email or other sources. In processing, humans typically have a variety of workflows, both manual and automated to go through inbound documents. Some may augment and automate a piece of this with technology, but the core steps remain:

  • Documents are received, added, separated, sorted and routed
  • Important data is identified
  • Data is extracted and entered
  • And then data and documents may be validated, although this step is missing in quite a bit of organizations, causing additional problems

Hopefully, in the end, both the data and documents land in the correct system.

The Process of Documents for Robots

If we just swap out people with robots without enhancing vision, and relying on legacy OCR, we essentially create digital confusion, as bots have no way to accomplish all these document processing steps and just don’t have the intelligence to handle the flow. Outfitting our robots with dirty glasses can be an inhibitor to maximizing efficiency and achieving peak automation. What are the roadblocks?

OCR Challenges

The majority of the OCR engines on the market are 10-12 year old technologies and are quite good at what they were designed to do: convert images to text. But it is important to understand that the OCR text results are the baseline or foundation for document processing methods. There is no context, no identification of type and no data of interest out of the box. Many products take that text layer and provide basic pattern matching, use templates or zoning to extract data. These technologies are ineffective with semi-structured and unstructured content, can cause high error rates when trying to classify, and require really high levels of human involvement in exceptions processing….added intelligence is just necessary to aid in full automation. With the complex workflows that take RPA implementations to the next level, to avoid digital workforce confusion and high exception rates, we need a smarter platform.

Smart RPA Platform

If you take a peek again at Everest’s playbook, Smart RPA is reliant on the intermingling of a wide variety of augmenting technologies that make the digital workforce smarter, faster, more accurate and less prone to human involvement.

Now we have an understanding of the issue and what we need to get optimum results, what are some keys to improving robot document awareness? I’ll touch on 4 key essential areas that must be part of your clear robot vision strategy:

Go Beyond Legacy OCR and adopt a smart capture platform to enhance our vision.1. Beyond Legacy OCR: The first key is that we just have to go beyond basic, legacy OCR and adopt a smart capture platform to enhance our vision.

Modern smart capture platforms don’t look at documents as pure text but as a series of dimensions. Looking at documents in this manner enhances our accuracy, and leads to desired results. It also allows for advanced methods of extraction that go beyond pure text matching. These enhanced extraction rules allow us to move away from rigid processing templates and provide for variations in documents, and rules that can apply across the entire document. Advanced platforms extend our processing reach to more complicated document types as well.

2. Machine Learning: ML provides simplified setup through the use of sample documents. Upload your different doc types, and the system builds a model for identification/classification. Along with simplified setup for admins, ML also provides a training mechanism for operators (digital and human), where items that are not recognized can be added to aid the next time that type is processed.

Documents are difficult and cannot be treated like any other image. In my experience, there can be document form types that look exactly the same, except for a difference in formatting or text. ML models that work well in identifying a lion from a dog usually don’t pick up subtle dimensional details. Therefore, doing a combination of text analysis and a possible layered approach is required for our goals.

Analyzing beyond the image or text is a strong requirement, and the document intelligence leveraged by the digital workforce needs to focus on document dimensions, beyond plain words.

3. Three Pillars of Document Capture:

  1. The first and most important pillar is classification. Just as a human knowledge worker would examine documents, the system applies its learned model to figure out when one document ends and another begins. It auto-classifies, or identifies the document type and all the pages contained within. This function allows documents to be captured in bulk bundles, such as large PDFs or paper stacks, and does all the heavy lifting in short order that would take a human worker extensive time and effort.
  2. Once the system has identified all the documents in the train of pages it receives, it then rips them into individual sets. This process is similar to the task a human would perform on a stack of documents that need to be split. It is called separation. Separation provides the ability to output individual documents as the end result of the process. When you combine classification and separation in this automated form, using your machine-learned model, you create massive time savings and efficiency, especially when dealing with large multi-document PDFs or large volumes of paper files. This combined process also preps the documents for the next automated step.
  3. Manual data entry is the next human process we can tackle. Through the use of rule sets tied to our classification, we can now auto-extract data of interest from the document. These rules can differ and vary per document, and the technology eliminates the need for a worker to manually enter data, manually name a document, or manually create folders. This data is now available to the digital worker for further processing.

4. Exceptions Processing: The last key is that robots need a “phone a friend” option. But when human intervention is required for an exception, it needs to be a controlled and seamless evolution. To validate and process exceptions, humans and robots need as much information as possible. With Smart Capture, rules can be built to catch documents missing pages, data that is low quality and also data that doesn’t match what the machine expects. This process of validation and exceptions processing can eliminate errant data, format information and ensure high quality. This is the only step that requires human intervention, and these queues can be used to train the system further through an easy-to-use machine learning interface.

The Robot Sandwich

With the right technology, we can create what I call a “Robot Sandwich.” This method essentially has a software robot as the source of documents, feeding the document process, with the ability to engage human knowledge workers for quality assurance, and or exception processing. At the end of the process, is another robot, waiting for the results. Once again, a simple, seamless method and interface to get input.

The “Robot Sandwich”What’s the Solution?

Where can we find those 4 key elements? Ephesoft provides those and more to give your digital workforce clear document vision. To further simplify and in the context of robotic workflow, Ephesoft opens up robot vision to unstructured content in documents, providing classification of document types, separation of bundled PDFs and images, and the extraction of data of interest.

How is Ephesoft different? We provide that intelligence layer that sits on top of the basic foundation of OCR and pattern matching. Think of these features and functions as an upgrade to your robot OS, providing enhanced visions and document processing capabilities.


Watch the demo


Learn more:

Solution: RPA Document Intelligence

UiPath: Ephesoft Activity Set

Blue Prism: Ephesoft VBO Integration

Contact Us

Document-Aware Robots Are Here

Clear Document Vision for the Digital Workforce

In this day of Artificial Intelligence (AI) and Machine Learning, most software robots are still using decades-old, legacy Optical Character Recognition (OCR) technology to provide robot document vision. Basic pattern matching, hard-coded rule sets and fixed templates are the seeing-eye dog for cutting edge, robotic technology. Essentially, organizations are outfitting their digital workers with smudged, dirty digital glasses, and only getting part of a much larger, more valuable document story.

Introducing Smart Capture®

With Smart Capture® technology, OCR is the foundation of the technology stack. Raw text and basic document dimension information can be leveraged, along with fueling an intelligence layer that sits on top of this basic foundation. It’s this layer that provides the means to process difficult, unstructured content, allows for wide variations within documents and supplies robots with information for complex data extraction.

Ephesoft adds document intelligence to RPA
Intelligence Layer on Top of OCR

In addition, building document processing configurations are facilitated through sample documents using both supervised machine learning and point-and-click methods. This provides clear and undistorted vision for the robotic or digital worker when it comes to documents.

Robotic Value of Smart Capture

Smart Capture provides three core functions to the RPA digital workforce: classification, separation and extraction. Below is a quick overview of each:

Document Classification – With classification, robots can now immediately identify the type of document within a digital workflow. Quick identification allows for intelligent decision making and custom document handling. Classification not only applies to individual documents, but it extends to batches or sets of documents. For example, software robots can now understand when a PDF contains multiple documents within one file.

Document Separation – With classification, robots are now “aware” of not only the type of document, but also where documents start and end. This awareness allows for sets of documents to be split or separated into individual elements for processing. In the PDF example above, the PDF can now be split into individual documents.

Document Data Extraction – Smart Capture’s data extraction capabilities allow software robots in an RPA process to extract data from all types of documents and create structured data. This data can be individual elements, paragraphs or data tables. Without the need for fixed templates, robot document vision is now more accurate and can span a variety of document types.

APIs Are the Clear Glasses

To give robots the comprehensive and clear document “glasses” they require, simplified, tight access to Smart Capture services are necessary to onramp data. This is accomplished through OpenAPIs, which can provide both synchronous and asynchronous methods for processing individual documents or large batches. OpenAPIs allow RPA design interface integration and drag-and-drop capabilities for “Citizen Developers”. These OpenAPIs can provide an open feedback loop for software robots, providing real-time document vision and improved automation.

Ephesoft Activity in UiPath Design Studio
Ephesoft Activities in UiPath Design Studio

Learn More

Want to add to your RPA capabilities through Smart Capture? Want clear glasses for your robot vision? You can learn more through the links below or contact us today.

Solution: RPA Document Intelligence

UiPath: Ephesoft Activity Set

Blue Prism: Ephesoft VBO Integration

Achieving Incremental Automation with APIs

Watch the on-demand webinar


Download The Slide Deck

Hello all, and welcome to this Ephesoft Webinar. My name is Steve Boals and today I will talk about how organizations can leverage modern smart capture to capture enable just about any device, application or process through the use of modern, standardized APIs. The expansion of capture and its pervasive nature can lead to extensive efficiency through what I call incremental automation.

Document = Pain

Documents have always been an essential part of business, both in paper and digital form, and present unique challenges for all types of organizations. Whether it’s a law firm that just received 1,000 boxes of paper documents from opposing counsel, and accounting department that processes invoice email attachments or a legal department processing visa applications, the impact on productivity can be massive if they are manually processed.

As technology companies began addressing the document problem, solutions began arriving on the market in the late 1980s and early 1990s with the advent of big ECM systems like FileNet and Documentum. And capture quickly arrived on the scene to help process documents and make them accessible digitally. While capture started with a paper focus, it transformed over time to take on all documents, physical and digital. Over the next few slides, I’ll talk about the types of capture that developed over the years.

In the early days, companies built centralized processing centers to digitize large volumes of paper documents. Documents were shipped and mailed to the centralized capture location, and expensive “big iron” scanning hardware was utilized. As the documents were scanned, some basic metadata was added, mostly for search purposes. In most cases, this was all performed to create a digital file room for speed of access and records management. These images were stored on optical media, and accessible to a select few centralized users.

As the price of capture hardware and software was reduced and networking technology improved, organizations could decentralize their capture efforts and move operations out to field locations. This eliminated mail and shipping costs and reduced the time for digital access. Still paper focused, the emphasis started to narrow in on automated extraction and indexing. The metadata was not only used for search, but was also entered in systems of record to reduce manual data entry.

With the rise of the scanning copier, the need arose for solutions that could leverage a single device that served many constituents. Organizations still leveraged centralized and distributed capture, but now the technology was pushed further out, to the individual end user. Automation and workflow were key, and the standardized, repeatable processes that capture could provide became necessary on a grand scale. Around this time, as more and more documents arrived digitally, email, fax and other multichannel capture features were added allowing efficiencies spread throughout the enterprise.

If you look at capture over the years, advancements were made in several technology areas:

  • Infrastructure and networking gave the ability to move documents fast and efficiently between locations
  • Applications like document management and content management systems provided an end resting place
  • Scanning hardware got faster, smaller and cheaper
  • Storage systems moved from optical to storage area networks to cloud

Along this journey, capture began to spread in an outward ring, becoming available to more and more users, and more and more applications. So just what does “pervasive” mean with regards to capture? What technology is driving it?

First, let’s start with a common definition and foundation of what pervasive means when it comes to technology. It can be defined as a technology that spreads and is available widely throughout the enterprise to everyone and everything.

Technology Enablers

As with each era of Capture defined in the timeline, there are core technologies that have made pervasive a capture a reality:

  • The Cloud – providing smart capture services anywhere anytime, on-premises or in the field
  • Content Services – the advent of cloud content service providers like Box and SharePoint Online make content available once captured
  • Web Services – with OpenAPI standards, APIs are now easily accessible from any application through standardized formatting
  • Applications like RPA and IPA have revolutionized process automation but have a need for document intelligence

The evolution of our technology has led to a diverse enterprise landscape which includes human and digital users, and physical devices plus digital applications. These exist both on premise and in the cloud, creating a complex, hybrid operating environment that requires flexible and modular capture services.

If you overlay today’s applications onto this landscape, you see a diverse enterprise ecosystem contains a wide variety of applications that are hungry for document intelligence, down at the transaction level. The only way to service them is with simple, easy to consume services.

Tying all of this back to our historical transition to today, we arrive at an environment that provides an application interface for both desktop and mobile users to process and interact with documents and supports all the types of capture previously mentioned. But in the background, there are also OpenAPI/Swagger enabled Web Services that can support software robots, devices, workflow and all other applications that require document intelligence. This hidden layer, transparent to end users, is a critical component for pervasive capture. Of particular note is the trend towards Citizen Developer friendly apps that provide an opportunity for incremental automation.

One note here: the legacy capture platforms that grew up from the early timeline weren’t built to accommodate pervasive capture. Their technology foundation was built in the days of centralized capture, a client server architecture without native browser support or modern Web Services.

Aren’t APIs for Developers?

There’s probably a few of you saying: APIs and Web Services…those are for developers. If I can’t code, I can’t use them. Today that is just not true.


There is a relatively new standard in web services called the OpenAPI specification, previously known as Swagger. It provides a standard on how REST APIs are described and documented.  This format is easy to learn and readable to both humans and machines. The API definition can be imported into applications, which can easily understand, render and integrate with apps that publish OpenAPI endpoints.

Why does this matter?

Many software companies saw this as an opportunity to allow users to transform code, and use these APIs through a visual interface. With many of the applications seen here, you can import an Open API compatible definition and immediately have the API as a visual toolset that any user with a bit of technical background can leverage, aka Citizen Developers.

Plugin Document Intelligence

Now capture can be added to any application through simple configuration versus custom code. In this example, a document’s information can be captured and used to automatically make the workflow process more intelligent. This takes away the requirement for manual intervention or human data entry steps.

The result is something called incremental automation. With capture available to everything, document automation is possible, even in small instances. Front line users can now begin to eliminate all manual document interactions, making every process a target. RPA and IPA can now have an added layer of intelligence that makes them document aware, which is much more efficient.

Documents are so widespread throughout business today, any human touchpoint can be an opportunity for incremental automation. Processes where info is entered manually or where humans have to interact to choose how to route documents can be great candidates. Also, points where documents need to be validated and processed if incorrect, perhaps where signatures or data must be checked. All of these are great places to start in the incremental automation journey.

Incremental automation can provide immense value, and leads to broad reaching automation and efficiency, reducing the time to process and required personnel, ensuring accurate extraction and valid, clean data, while continuously getting smarter through operator interaction and learning.

Pervasive Capture: The New Age of Efficiency

Incremental Automation for the Masses

The document capture industry has gone through a number of transformations over the years, typically tied to technology innovation and market demand. The new frontier we are experiencing, which I refer to as Pervasive Capture, is a challenging one for legacy vendors with dated technology that is bound to the server and desktop. Let’s explore the evolution of document capture and how we now arrive at the age of Pervasive Capture.

Centralized Capture

When capture first made its debut, the focus was purely digitization. You could say this was the Stone Age of Digital Transformation. Organizations centralized scanning rooms with extremely expensive hardware and software to digitize their paper documents. Documents from remote locations were transferred via mail or truck and fed into high-speed scanners. They were processed in large batches and ended up in a digital records repository. Once again, licenses to access digitized documents were extremely expensive and access was limited to a select set of users in the organization.

Decentralized Capture

As hardware and software costs dropped, organizations could justify the cost of numerous “scanning centers” at branches and decentralized locations. Mail and trucking costs were eliminated, while paper was still the focus, with large document batches processed on location.  This led to less lag time in processing, and a faster return on investment and improved access to newly created digital documents.

Distributed Capture

The rise of the scanning copier and low-cost desktop scanners in the office created a market for distributing the efficiencies of capture. Pushing capture technology to the front lines created almost instant access to digital documents, as workers could process small batches, and even single documents. It is during this time that capture software began to expand its reach into digital documents as well. Digital fax, email attachments and other “born digital” documents were now a target of automation as well.

Pervasive Capture

Here we are in 2018, the age of Pervasive Capture. In this world of Robotic Process Automation (RPA) and Intelligent Process Automation (IPA), Smart Capture® is now available via Web Services APIs to create document automation in any process and at any scale.  Applications can now call a document intelligence service to immediately gain information mid-process, creating micro-efficiencies at the individual document level. (See an example here: OCR and Data Extraction with Nintex)

So, what does this mean? Organizations can now examine their existing workflows and robotic processes and use that data to look for incremental automation opportunities. For example, a financial services company can implement an onboarding workflow that allows a prospect customer to upload identification and the most recent W2. The workflow uses Smart Capture® to classify the uploaded document types and extract pertinent data. The ID’s state of issue and the expiration data can be verified to ensure it is a current ID. The W2 year can be extracted and confirmed to be last year’s earnings. The whole process removes humans from the loop and prevents errors from flowing downstream, creating micro-efficiencies at the document level, and allowing additional, incremental automation at the process level. Using this process and deploying this strategy enterprise-wide and the sum of the added efficiencies can be massive.