In the Case Management world, automation is not an unknown word. On the contrary, in Case Management, automation and digitalization have been a hot topic for the last few decades.
From classification to automated workflows, automation has been present in the world of large organizations. But, the one thing that has always been a problem in Case Management, and unfortunately, still seems to bother large organizations is paper-based documents.
In today’s world of Case Management where data access, security, and efficiency are crucial, many large organizations realize the importance of deriving value from data TRAPPED in paper-based documents.
According to a report by Wise, 4 out of 5 organizations say that they are trying to cut down the use of paper. Nearly a third of them place larger orders of paper than they did 5 years ago. And only 18 percent of organizations declare themselves as entirely paperless.
Numbers that won’t put a smile on any faces outside the paper production industry.
Let’s dig a bit deeper into this matter and see why paper-based documents are such a problem in the world of Case Management and how organizations can make things better.
The Case Management Problem With Paper Documents
While paper itself is not that expensive, the costs of managing paper documents could be as much as 31 times the cost of buying it.
In 2015, Corp Magazine reported that in the United States, organizations spend on average 8 billion dollars annually on managing paper. The report explains that organizations spend an average of $20 to file a document, $120 to find a misplaced document and $220 to reproduce a lost document.
CMSWire found out that 47% of employees believe that the strongest thing preventing organizations from becoming entirely paperless is the lack of paper management.
The very nature of paper documents does not allow for large organizations to appropriately manage, access, and search through them. Reports mention a PricewaterhouseCoopers finding, that employees spend up to 50% of their time searching for information amongst piles and piles of paper documents.
This lack of paper management means delays, unsatisfied clients, wasted time, and wasted money.
Let me raise another key question here: What about paper waste? How much do companies even care? Does your company ever think about this issue?
Paper comes at a tremendous cost to our planet and we all know that. But, according to the statistics, it seems that very few cares.
Let’s take a look at some facts I found in The World Counts report:
- Recycling 1 ton of paper saves around 682.5 gallons of oil, 26,500 liters of water and 17 trees.
- It takes an average of 5 liters of water to produce one piece of A4 paper.
- Printing a Sunday edition of the New York Times requires 75,000 trees!
- Paper accounts for 25% of landfill waste and 33% of municipal waste.
- Every tree produces enough oxygen for 3 people to breathe.
- 50% of the waste of businesses is composed of paper.
- S offices use 12.1 trillion sheets of paper a year.
So, the question running through my mind is:
Why waste any more money, time, and effort on managing paper documents when instead, you can rely on the next generation tools that can make Case Management much easier, faster, and much more effective. All of this while saving the planet from destruction.
Let me expand on the answer.
New Generation Tools vs. Paper-Based Documents
The world evolves every day and new technologies emerge on the market as we speak. Thanks to this ‘new generation tools’ large organizations can now enhance productivity, provide greater access to certain types of information trapped in paper documents, and improve their preservation options.
With this ‘new generation tools’, large organizations are now capable of easily turning all paper documents into electronic forms which are easy to access, easy to search through, and easy to classify.
Basically, these tools enable organizations to save themselves from all the troubles of managing paper documents and in the meantime, save the Earth.
I am talking about digitalization.
But, what Exactly does Digitalization mean?
Digitalization, also known as digital image processing is the process of converting information into a computer-readable format. Paper documents are converted into their digital representations called digital images. These digital images can further be used in various ways, including full-text searching or editing.
This process starts by scanning the original paper document. The original paper document is then represented by a series of pixels arranged in a two-dimensional matrix called a bitmap or raster image. This image is then kept either on a network or transferred onto a variety of electronic storage media.
There are 3 ways in which paper documents can be digitalized:
- Optical Character Recognition (OCR) – This method of document image processing makes an electronic conversion of images of typed, handwritten, or printed text into machine-encoded text. These images can either be a scanned document, a photo of a document, or a scene-photo.
- Intelligent Character Recognition (ICR) – This method is an advanced version of the OCR. It allows computers to learn different fonts and styles of handwriting to improve accuracy and recognition.
- Optical Mark Recognition (OMR) – This is the fastest and most advanced technique of document image processing. It allows checkbox regions recognition on scanned images.
Scanning paper documents make them instantly available. These techniques of document image processing produce 2 types of files which have separate uses:
- Master copy. This type of copy is created with the intent of replacing the original document. These copies are files with high quality and follow recommended standards that ensure complete and secure records.
- Access copy. This type of file is a copy of the master file created with an intent to provide regular access to users. This type of copy also follows certain standards. Access copies are generally lower in quality resulting in smaller file sizes which allow for easier access.
Unlike analog data, which in the process of copying and transmitting might suffer a slight loss of quality, digital data can be copied indefinitely with absolutely no degradation.
Digitalization also increases the possibilities for using the information contained within the documents. Scanning paper documents only make them instantly available in master copies and access copies, but it also allows their further processing, managing, and maintaining.
With over a decade of digitalization experience, we at Armedia learned to rely on Ephesoft as the leading innovator in this field.
For some that are not familiar with Ephesoft, allow me a bit of time to explain who Ephesoft really is.
Why Go Digital With Ephesoft?
Ephesoft offers advanced capture solutions that help organizations run more efficiently, increase information accessibility and searchability. It allows all this by automatically classifying, separating, sorting and extracting data from scanned documents.
Here’s why Ephesoft is a safe, reliable digitalization choice:
- Ephesoft makes business-critical information available to processes and customers faster and more accurately than legacy systems.
- It’s the only document capture and extraction system to employ RESTful APIs, which makes it easy to integrate with third-party systems.
- It’s open architecture and open-source, freeing up customers from proprietary black-box technology.
- It has faster deployments when integrating with CMIS-enabled systems, including Alfresco.
- It offers classification and separation without barcodes or separator sheets.
- It has free-form Extraction – barcodes, key values, regular expressions.
- It supports TIFFs, PNGs, PDFs, DOCs, XLSs, GIFs, and JPEGs.
- It provides a platform streamlined for ease-of-use and high performance.
- It’s browser-based so you don’t have to download it to a client system.
- It provides significant data entry savings through less manual keying.
- Ephesoft has Automated Learning for documents, emails, and faxes.
- It’s Internationalized and Localized – easy to brand.
- It provides LDAP and Active Directory Integration.
This September Ephesoft released Ephesoft Transact 188.8.131.52. Besides the benefits I’ve listed above, this new and improved version takes document image processing and data classification to a whole new level.
Let’s see why.
Ephesoft Transact 184.108.40.206
“Our goal is to make enterprise content capture and data discovery from unstructured data easily accessible and meaningful for decision-makers worldwide” Ike Kavas, Founder and CEO at Ephesoft.
For this particular reason, Ephesoft released their new and improved version of Ephesoft Transact.
As you can see from the image below, Ephesoft Transact 220.127.116.11 includes 6 stages. Each of them very important and inclusive to the process.
Now let’s take a glimpse at each stage separately and see how Ephesoft Transact 18.104.22.168 work.
- Capture. The first stage of the process is data capture. Ephesoft Transact 22.214.171.124 allows multiple ways of capturing data. From scanners, content services, mobile devices, etc., to UNC folders (network folders) and so on.
- Image processing. Once the capture stage is done, the process continues with image processing. At this point in the process, documents and images are prepared for classification. This phase includes: cleaning up, rotating, improving image quality, etc.
All of this allows the resulting document to be easily identified in the third stage.
- Classification. The third stage is where the system determines the type of document. This step determines if a document is, for instance, an invoice, customer record, or any other type of file specific to the industry involved.
As an advanced document capture system, Ephesoft Transact 126.96.36.199 needs only one or two samples to learn to classify the document.
For this purpose, Ephesoft uses Machine Learning algorithms, a variety of techniques for data classification like search content, images, barcodes, and one document merging.
If the system shows low confidence in any document classification it calls upon a human operator for confirmation.
- Extraction. At this point of the process, Ephesoft Transact 188.8.131.52 identifies the metadata within documents. The reason for the existence of this stage is because metadata is very useful in organizing, finding, and feeding documents into another type of business system.
- Validation. This is a stage where Ephesoft Transact 184.108.40.206 validates the documents, in terms of a human assistance. In cases where there are some smudges, spills, blurry characters, or possibly missing fields in the document, the system alerts for manual verification and correction.
- Export & Deliver. Once all the documents are validated, they are moved to a repository or other line of business system. These documents and data can be stored either on a local server or cloud-based storage, like Alfresco, Box or SAP.
As such, the entire process of Ephesoft Transact 220.127.116.11 improves productivity, increases transactional velocity, enhances data viability, and reduces processing costs.
This new version of Ephesoft Transact includes multiple new features and improvements build on Ephesoft Transact 18.104.22.168’s functionality and flexibility.
Let’s take a look at some of them.
New Features And Improvements Of Ephesoft Transact
Ike Kavas, Founder and CEO at Ephesoft talks about these new features and improvements stating:
“Pioneering advantageous features that improve our customers’ business processes is what we do, and our latest version of Ephesoft Transact 22.214.171.124 helps achieve that customer success.”
Let’s dig deeper into each new feature:
1. (Add-on) Transact 4 Mortgage
Transact 4 Mortgage is an extension of Transact and this add-on provides 2 possible solutions:
- Standard Solution. The standard solution of Transact 4 Mortgage is capable of processing 400 loan origination document types that are already trained and configured for classification with Ephesoft Transact.
- Premium Solution. The premium solution includes over 600 loan origination document types, also, previously trained and configured for classification.
This allows the customers to save up to 2,000 hours of implementation time or approximately an 80% reduction in configuration and deployment times for an entire enterprise. Shortening the time from several months to several weeks. Customers of this add-on will enjoy improved accuracy and efficiency for much shorter time.
This add-on is also capable of grouping documents of the same document type which can be of an enormous use and save additional time.
2. (Beta) Hybrid Cloud Plugin To Ephesoft Transact 126.96.36.199
For customers that need high performance that even cluster configuration of services cannot provide, Ephesoft introduces the hybrid cloud plugin.
This hybrid plugin for Ephesoft Transact enables organizations to offload the heaviest image processing or OCR demands to the AWS cloud. Thanks to AWS and parallel cloud processing, Ephesoft Transact offers users higher scalability for high performance and peak demands.
As you can see from the image above, only the image processing/OCR happens in the cloud, while the classification and extraction happen on the Transact server.
With the beta hybrid cloud for Ephesoft Transact, you only pay for what you use. This plugin can also save you money by sparing you from adding servers, maintenance, and workers to support higher processing loads. The beta version is limited to 10,000 free images monthly in a trial capacity.
3. Swagger UI
Ephesoft believes that the best way to connect and share data is through Open APIs. For that reason, they’ve decided to make documenting APIs possible with Ephesoft Transact 188.8.131.52.
Swagger UI support allows modern, easier, self-documented Web Services for developers.
The Swagger UI support comes bundled with Transact for developers looking for standardized documentation. This integration feature provides standardized documentation of Ehpesoft’s existing traditional web service APIs.
Ephesoft uses this technology to create two advanced workflow Web Services Open APIs for both Nintex and Microsoft Flow.
These features are beneficial for both developers and non-developers by allowing them to classify documents and extract information via a simple Web Services interface.
“Users can now quickly add document capture functions to applications, removing the need for manual data entry or human intervention and increasing efficiency, accuracy and time savings.” says on the official site of Ephesoft.
4. Microsoft Exchange Header Support (Enhancement)
In Ephesoft Transact 184.108.40.206, MS Exchange was introduced only for MS Exchange on the cloud. Now, with Ephesoft Transact 220.127.116.11, MS Exchange includes header support and ingestion of documents for an on-premise environment. This makes the Microsoft Exchange Header Support feature available for support on both on-premise and cloud platforms.
Users can now configure the email headers (Subject, From, To and Date) to be included in the batch.xml file when processing batches via AWS.
Adding on-premise support provides extra availability to customers and expedites processing through the system.
5. PDF/A-1b Compliance For Export
Transact has typically supported single and multi-page PDFs within the export module. From Release 18.104.22.168 to 22.214.171.124, Transact has supported PDF/A compliant PDF’s for export, but not PDF/A-1b.
Now, Ephesoft Transact 126.96.36.199 offers PDF/A-1b Compliance and supports searchable single and multi-page PDFs in both black and white as well as color.
The enhancement helps customers put in place more advanced archiving and long-term preservation of electronic documents into their repositories.
6. Fixed Form Extraction Performance Improvements
Ephesoft Transact 188.8.131.52 came out with significant performance improvements to the Fixed Form Extraction process for Windows, used for data extraction from checkboxes and signature detection.
Customers using 16 core system will see up to 70% to 80% performance improvement, and 32 core system users will see impressive improvements up to 250% to 300% performance gains.
Impressive, isn’t it?
The faster processing of pages per minute allows organizations to quickly access their data, make more informed decisions, and improve customer satisfaction.
These new features and improvements of Ephesoft Transact are changing the world of document image processing and Case Management.
Let’s Wrap Things Up
With all of the features and improvements done by Ephesoft in their newest version of Ephesoft Transact, they’ve made the existence of paper offices outdated.
All of this features contribute to creating the following benefits in the Case Management world:
- Entirely automated workflows which save time and increase productivity.
- Easy access to documents which in their paper form were difficult to locate not even search through,
- Integration with other applications which make ERP, CRM, ECM, and back-office programs document-capture-enabled,
- Cost Savings which comes with the removal of paper document management.
Protecting our customers’ best interest and always aiming towards achieving the best, our team decided that a document image processing solution like Ephesoft Transact is a must for our customers.
If you want to find out more about our collaboration with Ephesoft or about our Solutions, don’t hesitate to contact us.
What are your thoughts about digitalization? Please share them in the comments section below.