As organisations embark on process automation strategies as part of their digital transformation journey, they hit one major roadblock – how to digitise unstructured data. Around 80% of the data in an organisation – including images, web pages, hand-written documents, signatures, and mobile content – is completely unstructured. With conventional Optical Character Recognition (OCR) technology, digitising documents that contain signatures, handwritten text (both block and cursive) or images is almost impossible because of OCR’s zone-based or template dependent data extraction methods.
Cognitive Machine Reading (CMR) combines the power of AI technologies such as Natural Language Processing (NLP), Machine Vision, Natural Language Modeling (NLM) and Machine Learning (ML) to automatically pre-process, classify, extract, and validate all types of data.