Machine Learning Predictions: 60% Of Companies Bring AI Into Everyday Business By 2022 Posted on : Mar 14 - 2019

AI and machine learning are breathing new life and business opportunities into that tired old phrase, “automating paper-based processes.” Consider this trio of forecasts that IDC predicted to happen by 2022:

Sixty percent of G2000 enterprises will be AI-enabled

AI will help over 50 percent of enterprise application workflows to better use legacy data, real-time operational data, and third-party data feeds

Businesses will use 50 percent more automation over the next three years as AI and machine learning workflows start consuming more business data

I saw an example of how software developers can inject intelligence into business processes in this VIDEO interview at SAP TechEd with Dr. Matthias Sessler, technical enablement lead, SAP Leonardo Machine Learning Foundation.

The demo showed image object detection combined with scene text recognition and optical character recognition (OCR), three of the 23 ready-to-use services on offer from the SAP Leonardo Machine Learning Foundation. Image object detection automatically identifies objects from images like a bus, and often tag teams with scene text recognition, which reads the fine print, such as the station name and line number.

“With smartphones, it’s so much easier for people to take a picture of something. However, developers need a toolbox so they can quickly build machine learning capabilities to make sense of these images and text,” said Sessler. “We’ve grouped our intelligent services into three deep learning model areas.  Image-based services understand what someone is seeing and can extract text from images. Text-based services understand written text. Speech-based services convert speech to text, and text to speech. All of this software semantically comprehends data and extracts relevant information.”

Deep learning neural networks

While AI’s proposed benefits sound suspiciously like last century’s ‒ automating repetitive transactions and manual tasks ‒ nothing could be further from the reality. That’s because despite ongoing digitalization, there’s still far too much paper-based stuff taking place in business. Like other AI and machine learning advances, the promise of OCR and scene text recognition is to automatically feed data from all kinds of places, anywhere and anytime, into a neural network.

“OCR is good for many business processes that have paper-based elements, like hotel bills for travel and expenses,” said Sessler. “Machine learning can read text and the two-dimensional position information on paper and within images, and automatically feed it into a neural network. When it’s connected to a company’s processes in finance, HR and other departments, the benefits can be exponential.” View More