Every year, you have to do more with less.
More documents, more sources of data, more complicated business needs. You’ve got to improve automation to keep up with evolving requirements, but every technology you review claims their solution works like magic.
Which makes you feel like you’re swimming in the middle of an ocean of paper with no life vest.
Does This Sound Like You?
We believe you deserve a better way. It just shouldn’t be so hard to find technology that can bring order to the chaos.
The Benefits of Grooper Software are Real and Significant
Do more with less without missing a beat, and become the go-to person for new technologies.
Document Processing Can Be Tough.
That’s Why We Made a Much Better Way.
We understand how hard it can be to find an automation solution that works for your documents, your systems, and your people.
After processing over 100 million pages in our own data migration center with outdated technologies that caused more problems than they solved, we decided that enough is enough. That’s why we created Grooper, our AI-powered solution that reads your documents and makes intelligent decisions about OCR, classification, indexing, and more.
Thousands of users have trusted Grooper to process millions of pages containing billions of data fields every day. We’ve provided solutions for the toughest document data problems for over 35 years, helping departmental managers get their paper under control and move into the corner office.
But don’t just take our word for it:
“Grooper has saved OSU hundreds of thousands of dollars and the ROI was seen in less than six months after going live.
“This product has taken data processing, document scanning, and import automation to a whole new level. It’s now in virtually every department including our President’s office.
oklahoma state university
“The Grooper data processing platform has been invaluable to our organization through our transition to a paperless environment.
“Instead of manually scanning / batching hundreds of contract documents each week, we email PDF sets of documents to a designated e-mail box. The system identifies, separates, and indexes the various documents with incredible speed, security, and, most importantly, increased accuracy. The automation and OCR technology is state of the art and has saved us hours of labor.
“Grooper is saving time and labor, and increasing accuracy. The results are invaluable.“
food and beverages industry
3 Easy Steps to Document Automation
This is how we do it:
We consult with your departmental leadership and subject matter experts to understand your processes and your opportunities for automation.
We follow an agreed-upon, clearly-defined roadmap to strategically automate your processes in order of business value.
You’ll stop thinking, “how am I going to deal with all these documents”, and start thinking “what am I going to do with all this extra time?”
Automation with Intelligent Document Processing
Deliver a proven solution for digital transformation and business process automation.
Develop a practical working relationship with unstructured data.
Achieve efficiency and innovation to drive revenue growth and competitive advantage.
Solve tough problems and automate workflows.
Empower human workers.
What is Grooper Document Processing?
Build human logic and reasoning into documents and other unstructured data, embedding value and meaning without adding layers of complexity. All with Grooper®.
Powerful Document Processing – What Does Grooper Do?
Conquer Paper Documents
You probably have a mix of digital and physical documents. Intelligent document processing puts you in control of all document processing workflows. Starting with paper or microform? Connect directly to scanner hardware to maximize efficiency and speed. Process all documents from any source without separate modules or add-ons. Enjoy seamless access to all tools and features.
Powerful Image Processing
OCR accuracy depends on good image processing. You’ll have access to over 70 image processing commands. Apply them at any time, and multiple times – not just when documents are first added.
Image processing software achieves three critical goals:
Intelligent Classification & Extraction
While once thought of as “advanced capture,” zonal OCR and template-based data extraction are a thing of the past. Layered AI is at the heart of intelligent document processing.
Enjoy near-perfect OCR through advanced and patented layered OCR technology and by using multiple OCR engines.
Grooper gets the most accurate OCR on the most challenging documents by pairing computer vision, imaging processing, and lexicon-based data look-ups.
Fuzzy Data Handling
Finally achieve true machine reading by understanding the organic meaning of data – on both business data and common dictionary words.
Now, instead of relying on exact matches for expected data, fuzzy match your results with weighted accuracy. Familiar with Regular Expressions? This is RegEx on steroids.
Connect to any CMIS-compliant document repository and to both cloud and local file systems. Integrate external data sources as needed during processing for validation.
With enterprise-ready data integration you won’t pay extra for to connect your systems. Export data in the format of your choice.
Manual data entry is expensive, error-prone, and slow.
Let’s do something about it.
Nobody wants to waste money and time, or miss out on better outcomes.
Use intelligent document processing for data entry automation and achieve a new level of efficiency and profitability.
Support legacy capture processes with straight-through exception processing.
Disrupt, or be Disrupted
Competition and changing economical climates bring disruption. Be the disruptor – gain market share, and increase business outcomes through new data sources.
Act now to create data you trust.
Powerful and Secure Document Processing
- Champion AI Initiatives – No-code / low-code machine learning, natural language processing, and computer vision
- Diverse Data Extraction – Extract data from any physical or electronic data source
- Protect Data Ownership – Safeguard data and intellectual property
- Enhance Processes – Stream intelligence into existing tools and applications
While not open source, Grooper is an open system. All machine learning training is transparent – no black-box algorithms or dark APIs here.
Grooper’s transparent AI enables fine-tune control over settings and an industry first – built-in unit testing.
As a result, you get quick optimization from rapid machine learning model training.
Grooper document processing converges modern data science tools and techniques – a new era of data integration.
Grooper core technologies include:
Learn How Grooper Understands Your Data
How does Grooper understand and identify data in order to integrate it? How does this compare to how humans understand data? Check out this intelligent document processing infographic!
Grooper Frequently Asked Questions
Why was Grooper Created?
Frustrations in existing document capture software lead to the development of Grooper. We’re a 30+ year veteran in enterprise capture.
Because our customers needed results that legacy platforms struggled to deliver, we decided to stop building custom-coded add-ons and build the industry’s first intelligent document processing platform.
Is Grooper just OCR?
Grooper is not an OCR engine. While the platform contains multiple OCR products, the benefit is that Grooper makes OCR perform as promised.
For instance, users mostly use Transym, Tesseract, and ABBYY. Grooper then adds in image processing, lexicons, trainable OCR, and other patented tools to achieve very high accuracy on any kind of document.
What is Grooper?
Grooper was built from the ground up by BIS, a company with 35 years of continuous experience developing and delivering new technology. Grooper is an intelligent document processing and digital data integration solution that empowers organizations to extract meaningful information from paper/electronic documents and other forms of unstructured data.
The platform combines patented and sophisticated image processing, capture technology, machine learning, natural language processing, and optical character recognition to enrich and embed human comprehension into data. By tackling tough challenges that other systems cannot resolve, Grooper has become the foundation for many industry-first solutions in healthcare, financial services, oil and gas, education, and government.
- Single platform
- Patented OCR
- Image processing
- Machine learning
- Natural language processing
- Zero code
- Zero templates
- Open architecture
“Elegance and simplicity are valuable principles in the production of creative, efficient, and sincere work.”-CEO Dan Rotelli
Why should I choose Grooper?
You get 30+ years experience in the evolution of document capture, patented technology and a deep understanding of the complexity and true potential of unstructured data
Grooper was built to succeed where others have failed, taking on tough challenges. This platform processes and integrates massive amounts of difficult data from complex documents and architecture. If we say our system can solve a problem, it can. And we’ll show you how.
“People are the most important part of our business. We value long-term relationships with employees and with clients. We have spent over three decades cultivating trust.”-CEO Dan Rotelli
How do I win with Grooper?
- Make data more useful by embedding comprehension into it
- Innovate by automating workflows and streamlining operations
- Make faster decisions by creating meaningful data
- Faster time to value from digital transformation with less risk of failure
- Increase revenue, customer experience, and strategic partnerships by making I.T. simpler
- Become more agile by transferring knowledge more easily
- Improve compliance and safeguard private information
“The outcome is the most important part of the journey.”-CEO Dan Rotelli
How complicated is the pricing?
Because Grooper is a unified platform, pricing is based on volume of use. The lowest tier is $18,000. Successful solutions require a level of services to get the system installed and the data models designed. The time and cost for that varies. There are no “per-seat” licensing fees for Grooper Enterprise, so you get unlimited users.
Pricing for basic data integration is straight forward. Pricing for more complex integration is based on a POC to reveal core requirements and potential partner / professional services needed.
Grooper Desktop OCR is priced at $2,500 per user. You can find more information about that here.
Is Grooper a cloud product?
Grooper will run on any cloud infrastructure that supports Windows VMs. Grooper is not currently fully offered as a cloud-hosted system, and is not cloud-native, although we do support some cloud-native technologies, such as AWS autoscaling.
We are currently developing support for cloud-native deployments using docker containers.
Does Grooper have a web client / thin client?
Yes! The Grooper Web Client allows end users to process documents using an internet connection alone. With the Grooper Web Client, there is no reason for document review users to install Grooper on their workstations.
Instead, Grooper is installed on a web server, and users simply access that server’s Grooper Repository (or Repositories) using a web browser. Here is more information about the Grooper web client.
The Grooper web client also supports scanning with the installation of a small helper application, and beginning in Grooper 2023, users can design and administer Grooper processes using a fully-featured Web Design client.
What are the system requirements for a Grooper system?
End User PC
- Windows Windows 10 or later is required
- The end user PC would include Grooper Thick Clients and installations on premises
- Network latency should be (ideally) less than 50ms
- Network throughput should be (ideally) greater than 50MB
- The end user PC would not have Grooper Thick Client installation
- Connects to Grooper via web browser
- May be on or off prem
- A Windows 10 or later PC is required for Grooper Scan
- Logs in using Windows Account on Server PC (Domain or Local)
Grooper Processing Server
- A Grooper processing environment can have as many servers as is necessary to meet business requirements
- Windows Server 2016 or later is required
- Server RAM should be 16GB or more
- The CPU should consist of 4 or more cores
- The port for licensing is 13900 by default
Grooper SQL Server
- Windows Server 2016 or later is required
- SQL Server 2012 or later is required
- The Grooper Database should allow for a size of 20GB or more
- The scaling of the Grooper Database should be set to percentage, ideally, not the default of a few MB. This will reduce frequent scaling that hinders performance
- The SQL Port is 1433
Grooper FileStore Share
- Windows Server 2016 or later is required
- This can be local to the Grooper SQL Server or managed on a separate server
- The ideal file size would accommodate for roughly 150GB for small to medium installs
- The authentication requires CIFS or SMB
Grooper Web Server
- Windows Server 2016 or later is required
- This can be local to the Grooper SQL Server and or the Grooper FileStore Share or managed on a separate server
- Internet Information Services, or IIS, should be installed and properly configured
- Requires a SSL Certificate for encrypted connections
- IIS Impersonation Account with access to Grooper Filestore and Database is needed for proper configuration
For more information, visit our wiki page on Grooper requirements.
Does Grooper come with pre-trained models?
With a few exceptions, your solution will be custom-configured. We provide data fulfillment as a “done-for-you” service or collaborate on a “done-with-you” approach to teach you our tech.
The reason the promise of 100% “out-of-the-box” solutions is not a reality is that your documents, workflows, and data are unique to your organization. Grooper is designed to rapidly learn your documents and a Grooper architect will help configure the platform to extract the data that’s important to you in the format your systems expect.
Is Grooper easy to learn?
We have successfully trained hundreds of Grooper architects. Learning the platform typically takes around 90 days. Our training and curriculum team provides ongoing training, and rich documentation on all new features and capabilities.
Check out the Grooper Wiki to get an idea of what our documentation looks like.
Learn more about Grooper ACE certifications and training.
How is Grooper implemented?
There are 2 unique paths for your Grooper implementation!
If we are deploying a “done-for-you” solution, we will provide an estimate of what we believe the project will cost. There are many factors that affect overall project complexity and cost (and we can’t know them all upfront):
- How well you understand your own data (data literacy) and the desired outcomes
- How available your subject matter experts are to dedicate their time
- How “the rest of your documents / data” compare to the samples we were given
Because there are many factors that affect the timeline and amount of work that goes into the project, it is just an estimate.
Our most successful customers become experts with the platform, and we offer training to help facilitate that learning. We’ve discovered the “Statement of Work” approach is limiting and counter-productive for you to achieve the results you need for quick return on investment.
If we are deploying a “done-with-you” solution, we will start a paid services engagement in which you will receive a dedicated expert Grooper resource to ensure your staff is properly trained on how to setup and deploy your solution.
“Transparency from all parties is essential to be effective. We work in a way that makes it safe for everyone to understand and tell the truth. When we say we can do something, we make it easy to see how.”-CEO Dan Rotelli
How will Grooper help me?
Become Highly Effective at Using Unstructured Data
Knowing and trusting data is essential for meaningful digital transformation. Gain a practical working relationship with your unstructured data.
Achieve Simplification by Humanizing Unstructured Data
Intelligent documents enable instant knowledge transfer, saving thousands of hours of work. Build human logic and reasoning into documents and other unstructured data, embed value and meaning without layers of complexity.
“Coming to grips with the complexities of data is hard. Being willing to have fun while getting things done makes the process more enjoyable and sustainable.”-CEO Dan Rotelli
What industry was Grooper built for?
Grooper was made to extract data from physical media and electronic data sources for any industry.
Because Grooper is a configurable document and data processing platform, it is used in a wide range of industries like healthcare, oil and gas, education, financial services, and government.
Can Grooper handle Asian languages, such as Japanese?
Grooper, like other IDP solutions, does a number of different things, but the “core” functionality is generally reliant on OCR and Extraction.
We’ve got integrations with both Azure and Tesseract, so we can OCR Japanese-language documents. This includes things like diagrams, images, etc. We are also Unicode-compliant, so we should be able to extract from Japanese language documents, as well.
But the big question is whether our extraction system – and regular expressions, generally, which are a foundational technology for us – is designed to target languages that have an alphabet and a morphology like English.
Japanese has both logographic characters (Kanji) and two different syllabaries (Hiragana and Katakana); English is generally categorized as an analytic language and Japanese is an agglutinative language.
Because of these substantial differences, doing any of the more advanced things – classification, separation, etc. – that depend on extraction is going to be an unknown quantity. Not because the system can’t handle Japanese, but because the core technologies that we use are predicated on processing Western European languages and, as such, make some assumptions about what to expect.
As for other East Asian languages: it depends on if they use logographs (Mandarin Chinese), an alphabet (Vietnamese – which might be challenging because of the diacritics used to indicate tone), or a Syllabary (Korean).
It also depends on how similar their grammatical structures – morphology specifically – are to English and other Western European languages.
“A project should only be pursued if it’s supported by a well-reasoned business case.”– BIS CEO Dan Rotelli
Grooper Document Processing Training
Speed up learning and make your data integration project even more successful by taking advantage of our training classes.
Also, we are adding new training all the time. So check out our training page and contact us to sign up for a course! Learn More
Join fellow Groopers, developers, and engineers in the Grooper xChange community.
In this area you can share ideas, learn new types of data integration, and check out our many resources. Learn more
“All of the information in some file some place is very hard to retrieve. We ought to be able to get it with the click of a button, and now we can. Using the system that Grooper provides to scan the documents and mine the data eliminates many manual processes. My belief is that in the long-term it doesn’t really cost us anything because it’s going to pay us dividends over and over again. I would be surprised if anybody has a system that’s any better than this.”Gary Ridley, former Oklahoma Secretary of Transportation, former Director of Oklahoma Dept of Transportation and former Director of Oklahoma Transportation Authority
“Grooper allows my staff to process ten times more volume than we could with our previous image capture solution; our office thinks Grooper is worth its weight in gold.”Marie Ramsey-Hirst, Court Clerk, Canadian County
“I absolutely think Grooper is the most powerful product at the most pertinent time, that I’ve had to offer in my 30 years in the industry. So excited to work with you.”Amber S., Grooper Partner
“It is a rarity that I find an application that the product can actually do all they claim it can do. I can speak to support, sales or their development team about any challenge I am encountering and they will go above and beyond to help me accomplish my goal! ”Sr Data Architect
“Grooper has saved OSU hundreds of thousands of dollars and the ROI was seen in less than six months after going live. This product has taken data processing, document scanning, and import automation to a whole new level. It’s now in virtually every department including our president’s office.”Erin Girton, Database Administrator/Content Management & Capture Administrator, Oklahoma State University
“Practically every unit here within our agency uses Grooper on some level. Grooper has cut down on our indexing time by 70 percent.”Ryan Freeman-Smith, Manager, Oklahoma Health Care Authority
“Grooper will give us the access to more contract data than ever before by quickly extracting the data across thousands of lengthy contracts, allowing employees to spend time on value-adding data analysis rather than extraction.”Glena Brauer, Supervisor – Marketing Contracts and Compliance, Chesapeake Energy