How Automation Hero Uses Accurate AI to Process Documents

We’re excited to bring Transform 2022 back in person on July 19 and pretty much July 20-28. Join AI and data leaders for insightful conversations and exciting networking opportunities. Register today!

Before Dr. Alan Turing designed the first computer, people only dreamed of intelligent machines that could read paperwork and do most of their grunge work for them. Science fiction movies show sophisticated software that processes large volumes of documents to find hidden insights that save the day. Today this is available in real life from progressive software vendors.

One of them, located in San Francisco Automation Hero, today launched v6.0 of its Hero Platform, a SaaS service that the company claims represents a quantum leap in the accuracy of OCR (optical character recognition) document processing. It can also read handwriting with 70-80% accuracy.

Yes, this includes doctors’ notoriously bad handwriting, Automation Hero founder and CEO Stefan Groschupf told VentureBeat.

The Hero Platform has shown, both in beta testing and actual production, that it can unlock millions of dollars in return on investment (ROI) for companies such as MarkerStudyturn documents into actionable insights in claims processing, supply chain optimization, fraud detection, and customer interaction automation.

Faster new AI engine

The latest version of the AH platform offers a faster new AI engine for document processing and automation, Groschupf told VentureBeat. The company’s deep learning-based approach, along with its fast-reading OCR process, can instantly convert structured or unstructured documents — such as contracts, invoices, receipts, prescriptions, doctor’s notes and purchase orders — into highly accurate and actionable data, Groschupf said.

Automation Hero’s OCR engine is modeled on cognitive science, turning scans of documents into data similar to how humans read even the most difficult handwriting with contextual cues. The patent-pending technology is combined with an intuitive-to-use natural language understanding engine, all within a single end-to-end platform, Groschupf said.

While this may seem far-fetched, the goal is to deliver the industry’s highest ROIs within weeks without the need for data science or large training data, Groschupf said.

“Our job at Automation Hero is to accelerate healthcare, get insurance claims paid out faster, and find bad actors who overbill or surface contracts that can be renegotiated,” Groschupf told VentureBeat. “Our mission is to equip overwhelmed employees with the AI ​​superpowers to speed through the mountain of documents that keep piling up on their desks or in their inboxes.

“We have AI that goes into a document management tool and processes the data to make it usable to automate certain business processes.”

40% faster than Google’s OCR, claims Automation Hero

Based on new benchmark data, the technology outperformed handwriting OCR alternatives ABBYY and Google Vision by about 280% and 40%, respectively, Groschupf said. It too outperformed ABBYY and Rossum in AI-based invoice processing in a separate benchmark at 60% and 100%, respectively, he said.

Insurance claims processing is Automation Hero’s best activity right now, Groschupf told VentureBeat.

“Eighty percent of all data in companies is contained in documents. This is a treasury that has not been tapped in the past,” Groschupf said. “And if you think about all this business intelligence and ETL, it’s a multi-billion dollar market where we’re all operating on 20% structured data. Historically, people have stored so much unstructured data — emails, contracts, images, invoices, infrastructure data, etc. — that it took days or weeks to get through it.

“We can do things you couldn’t do before, like constantly mining hundreds of thousands of contracts, automating 60,000 claims per day, and so on. We really want to be a bicycle for people’s minds, by mining a lot more documents than before.”

Automation Hero’s unique approach to OCR has reduced time-consuming claims management by hundreds of hours, changing the way we handle customer claims and manage employee satisfaction, said Eoin Grace, deputy head of IT at Markerstudy, in a media briefing. advice.

“We used to decipher doctors’ diagnoses, stamped addresses and handwritten notes with a wide variety of claim forms,” ​​Grace said. “Automation Hero’s intelligent OCR technology delivers superhuman accuracy.”

The mission of VentureBeat is a digital city square for technical decision makers to gain knowledge about transformative business technology and transactions. Learn more about membership.

Shreya Christina
Shreya has been with for 3 years, writing copy for client websites, blog posts, EDMs and other mediums to engage readers and encourage action. By collaborating with clients, our SEO manager and the wider team, Shreya seeks to understand an audience before creating memorable, persuasive copy.

More from author


Please enter your comment!
Please enter your name here

Related posts


Latest posts

3 Ways You Can Support Hispanic Businesses During Hispanic Heritage Month

National Hispanic Heritage Month is a time to celebrate the rich culture and immense contributions of Hispanic and Latino Americans. This year, as we...

The Nostalgia Factor: Why Retro Gaming Continues to Thrive

In the fast-paced world of modern video games with their stunning graphics, lifelike simulations, and complex narratives, there's a distinct charm in returning to...

The Rise of Cross-Platform App Development in Australia

In the ever-evolving landscape of app development, the need for efficiency, cost-effectiveness, and wider reach has given rise to a significant trend: cross-platform app...

Want to stay up to date with the latest news?

We would love to hear from you! Please fill in your details and we will stay in touch. It's that simple!