delNoteTT
Machine Learning, Deep Learning, Data Science, Delivery Notes
![](../../../Binaries/Binary39101/Unbenannt-1.png)
Course of studies
Computer Science (BSc)Project description
As globalization and digitalization continue to shape the business landscape, companies are faced with increasingly complex challenges. The rising tide of data and information necessitates extensive adaptation across all levels of corporate structure. It's essential to bolster established frameworks with digital technologies from the present era and expand upon them.
A significant portion of the production flow relies on the intake and output of goods. Complications in this process can have repercussions for all subsequent steps and demand important resources such as personnel, time, and money. With the growing volume of invoices, delivery notes, and notes, employees at the receiving end are faced with the daunting task of digitizing these documents. This involves capturing data, managing customers, reconciling deliveries, and updating databases for further processing steps. All of this must happen in real-time, as every subsequent production step depends on it. Any delays or errors thus slow down the subsequent process.
Thanks to advancements in machine learning technologies, it's possible to organize large amounts of data in a short time and automate the process at goods reception. Delivery notes, which carry information about which goods were delivered by which supplier at what time, can be categorized, read, and captured thanks to Optical Character Recognition (OCR) and other machine learning approaches. This approach can be seamlessly integrated into existing structures. Documents are scanned, identified as delivery notes, and automatically captured in the database with the necessary data, allowing resources that were previously needed for this task to be allocated elsewhere. As a result, processes within the company can be completed more efficiently and reliably.
Involved persons
Supervisor:
Prof. Dr. rer. nat. Claudia Reuter
Dennis Rockstein
Students:
Yun Cheng
Louis Tschan
Jonas Winkler
Roland Zimmermann
Fatih Karakuzu
Korbinian Böhm