Invoices and receipts digitization can help companies automate processes, organizations become more transparent and get vendor payments done efficiently and with fewer errors. Traditionally for an insurance company dealing with invoices and receipts needs to involve multiple manual reviewers going through each invoice to reduce the chances of error. With deep learning and OCR techniques, the company can read medical invoices and automatically review the receipts, extract important fields out of them, check whether the invoices are legitimate and process claims accordingly. All this data can be stored and retrieved anytime for the company as well as the client's benefit.

Manual Inspection

Having to manually review each receipt for each client is a time-consuming process that also costs the company a lot. This process involves each invoice to go through three manual reviewers to make sure the error rate is minimal. This approach leads to a 99.9% accuracy but involves the same task being done by several people several times. Manual reviewing of invoices also means that the company has to bear the costs of several reviewers who will process images of invoices, read through each image and manually enter the data into the designated software for the claim processing to go further.

Inspection with Nanonets

The process of verifying if the invoices are real, reading text from each invoice image, extracting important details, entering the text into tables and fields or return json responses, all of this can be automated with the Nanonets. Automating claims processing means the company saves a lot of time by processing several invoices a minute, unlike humans. OCR technology can aid the manual reviewers in doing the inspections a lot faster and with greater convenience, while the company can reduce costs and time taken for the processing. Now an invoice that would pass through the hands of 3 reviewers and finally entered manually into a software, one reviewer can automatically structure the invoice data, make a few corrections like spellings, hyphenations, etc and move on to the next document.

The Nanonets API

Our API provides high speeds and great accuracy, enables fraud detection and drives automation for insurance companies. The Nanonets API can help the insurance companies automate the process of

Finding out if the image adheres to specifications like the high resolution, full receipt visible, the upright orientation of the receipt, etc. and providing instant feedback to customers.

Inspecting images and detecting:

• The table structure of an invoice and the titles and fields in it.
• All the entries and fields present in the invoice like name, product, price, total sum, discounts, etc.
• These fields can be extracted as json outputs so you can build your own apps, platforms.

The Nanonets Impact

We were able to reduce the time taken to process claims by 90% by automating invoice digitization. Though the accuracy was lower compared to humans, the number of manual reviewers was reduced along with the number of passes required for each invoice to make sure there’s no error. This meant that the company reduced it’s cost by 50% while also providing it’s customers more convenience in their services and it’s employees less repetitive and more engaging work.