Automatically processing incoming orders at Van Marcke

Every day, hundreds of order confirmations arrive in Van Marcke's mailbox. Usually, this information is embedded in a pdf which has to be processed manually.

This project was realized by

Challenge

Van Marcke's mailbox receives a multitude of order confirmations everyday. Typically, these confirmations are enclosed within PDF files, necessitating the manual extraction of data into Van Marcke's mainframe. This process was done manually, that is why Van Marcke sought the assistance of RoboRana, for its expertise in hyper automation and Robotic Process Automation (RPA). However, despite implementing RPA, the challenge persisted. That is why Klassif.ai stepped in.

Approach

In collaboration with RoboRana, they combined AI and RPA into a single solution. Our AI tool seamlessly integrates with a Blue Prism RPA bot, enabling the extraction of data from PDFs. During the next step, the tool uses optical character recognition (OCR) technology to convert the unstructured data, such as product names, quantities, and amounts, into structured data. To train the AI tool to recognize unstructured data, an initial manual intervention was required from employees. They provided guidance to the tool, indicating the location of relevant information like amounts and distinguishing between invoice and delivery data. Through this kind of training, the system became smarter and gains insight into how the orders are usually structured. As a result, the tool can now classify Van Marcke's order confirmation without help. As the final step, one of RoboRana's virtual workers enters the extracted structured data into the mainframe. This automated process eliminates the need for manual intervention, resulting in a fully automated order confirmation process for Van Marcke.

"In the first month, almost 7.000 PDFs were processed. If you know that an employee usually needs 1 to 2 minutes per document, this results in 10 hours saved per day on average. This is an immense amount of time that can be used for more value-adding tasks." - Stijn Hoegaerts, IT manager, Van Marcke

Result

The implementation of this intelligent process automation solution has resulted in significant time and efficiency gains. Several hours per day are now saved as a direct outcome of this streamlined approach.

Furthermore, the error margin associated with manual processing has been dramatically reduced. Klassif.ai's accurate interpretation of data, coupled with error-free entry by the RPA bots, ensures a high level of precision. Consequently, employees' satisfaction has increased as they can now devote more time to engaging and stimulating tasks instead of repetitive ones.