Process Mining and Natural Language​

  • Sponsored by: Celonis SE
  • Project Lead: Dr. Ricardo Acevedo Cabra
  • Scientific Lead: David Becher
  • Term: Summer semester 2019

Results of this project are explained in detail in the final documentation and presentation.

Accompanied by a lot of media coverage, the world has seen major progress in the field of natural language processing, manifesting most prominently in Amazon Alexa and Apple Siri.​

Another field which had great breakthroughs recently is Process Mining. Major companies are using this technology to improve their processes by making them transparent.​

Our vision at Celonis as the Process Mining market leader is to combine both technologies to provide Process Mining insights without any entrance barrier.​

Currently, mining is mostly done by trained analysts. The gained insights are aggregated and then presented to the decision makers, often even the executive board. Despite modern web interfaces provided by systems like Celonis, the training period is still too long for decision makers.

Providing these mining insights through a natural language interface, in ways that even the busiest decision maker feels comfortable with, is the key challenge of this project.

The benefit, apart from providing the decision makers with correct and up to date numbers, is that the analyst can focus more on digging deeper into the data and spend less times in answering standard questions.​

To fulfill this vision, it is not sufficient to simply replicate the existing interface in Alexa or others. Instead, the whole Process Mining interaction has to be rethought and tailored to provide comprehensive and meaningful insights.