Esker Earns Machine Learning Document Data Extraction Patent
Meet the Authors
Key Takeaways
⇨ Esker earned a new patent for a technology that uses machine learning to extract data from physical documents.
⇨ The patented technology can identify data fields, make routing decisions and suggest next actions.
⇨ The solution aims to reduce repetitive tasks within the source-to-pay (S2P) and order-to-cash (O2C) cycles.
Process automation solutions firm Esker recently announced that it earned a new patent related to machine learning. The solution aims to reduce repetitive tasks within the source-to-pay (S2P) and order-to-cash (O2C) cycles. Esker first filed for the patent over a decade ago.
In a press release, Esker said the technology “uses traditional and machine learning algorithms to identify data fields, make routing decisions and suggest next actions with the goal of reducing the number of touches during processing as much as possible.”
Users can also apply input to improve the accuracy of the process over time while also creating rules that define which data it should retrieve, as well as the format it should be in. This new technology aims to not only reduce time-consuming and frustrating manual tasks, but also reduce the number of errors that come with that process.
Meeting the Market
This new technology from Esker comes at the right time for many SAP users. According to survey data in SAPinsider’s SAP S/4HANA Finance and Central Finance: State of the Market 2023 Research Report, payment processing solutions are crucial. The survey found that 33% of respondents are adopting payment processing solutions, a higher percentage of adoption than any other technology solution listed.
This functionality allows companies to align their finance and operations with new digital business models. Organizations continue to prioritize AI, automation, and machine learning technologies for their proven abilities to minimize manual work, cut down on errors, and make processes more efficient overall.
Functionality
Esker highlighted the impact this technology can have on the order management process. Even though customers typically use differing purchase order templates and layouts, this new solution will be able to retrieve relevant information with increasing recognition rates the more times it is used and receives user corrections.
“When we started on the AI journey at Esker, we focused our efforts on data extraction in order to decrease manual data entry for incoming invoices and orders. This project has expanded to enriching the extracted data with predictive and prescriptive functionalities such as detecting anomalies in orders, predicting the invoice analytical axis, or proposing an answer to a customer request. This combination of human and artificial intelligence allows for making the work more engaging and efficient,” said Jean-Jacques Bérard, Vice President of Research and Development at Esker.
