DGTAL, a Software-as-a-Service (SaaS) platform providing artificial intelligence (AI) powered audit and tools for insurance portfolios, has launched a new Intelligent Document Processing tool, GRABBER.
The new tool excels at understanding, extracting and validating data from sources such as invoices, bank statements, utility bills, quotes, order forms etc, DGTAL stated.
This eliminates the need for manual intervention in repetitive, error-prone tasks, such as invoice validations, price comparisons, and cost estimations while enhancing automation, reducing leakage, and combating fraud.
GRABBER builds upon the DGTAL’s DRILLER technology, by using the most innovative approaches in optical character recognition (OCR), natural language processing (NLP), computer vision, machine learning (ML) and artificial intelligence (AI), the firm explained.
GRABBER manages to deal with a huge number of documents across entire claims portfolios, something that it is able to do similarly to DRILLER.
But unlike DRILLER, its AI approaches also go much deeper by looking for specific information in specific documents. For instance, in the health insurance domain, GRABBER can automatically calculate private vs. social security contributions, validate invoice charges against price catalogues, cross-check ICD codes with medical examination protocols, and identify financial discrepancies with precision.
Arndt Gossmann, DGTAL’s CEO, said: “GRABBER has been spawned by our first DRILLER clients. Amazed by how AI supports proactive management of claims portfolios, our clients want to go deeper. If it is possible to flag 132 critical cases from 500’000 claims files within milliseconds, claims experts obviously ask how AI can allow a deeper dive.”
GRABBER delivers 95%+ accuracy in data extraction and Straight Through Processing (STP) and reduces processing time by 80%, DGITAL highlighted; and stated that both GRABBER and DRILLER demonstrate the immense potential of AI in harnessing insights from the vast pool of unstructured data available to insurance companies.
Additionally, GRABBER offers multi-language support and high universality, which allows the software to classify and extract data in any type of document despite format, style of text, and complexity. The tool is to be offered as a standalone product or as an add-on to DRILLER.
“Today, I am proud to present our value proposition to address this need. GRABBER answers specific questions on specific documents after DRILLER answered the questions across entire portfolios. Both products deliver unprecedented insights from unstructured data and can be used independently. As to GRABBER, we even predict interest from other industries. I am confident that GRABBER will hit €1M revenues within the next 12 to 18 months,” Gossmann continued.
