We’re called inverbis because during the research phase that our company’s founders carried out on process mining, they decided to combine that technology with Natural Language Processing (NLP).
“Say it with words” was the slogan on the first documents we created to frame the project. That was quite a few years ago now.
What did we use NLP for? To automatically describe the results of the analysis. Something like this (very generic):
“The process has an average duration of two hours and twenty-two minutes, with a minimum of two hours and one minute, and a maximum of six hours and fourteen minutes. The most frequent variant is number 22, occurring in 42% of cases.”
The value of this type of description is that it can summarize data—naturally including critical variables to monitor—and provide an explanatory text when a process monitoring alert is triggered. Or, for example, in organizations with very large process maps where non-critical processes don’t require intensive monitoring, it’s useful to receive automatic performance descriptions periodically (quarterly, for example).
Additionally, in other areas of research, NLP is being explored to describe a process and convert it into a BPMN model.
After the first versions of our product, feedback from reviewers and clients showed us that automatic text descriptions drew far less attention than other forms of visualization. We believe this was partly due to the immaturity of the process mining field itself: building compelling reports required deep knowledge of real processes—and obtaining such data was extremely difficult.
The result? We withdrew the NLP algorithms and stored them away.
We still kept the name inverbis though—the team felt it was already part of our identity.
But now, perhaps the time is coming to bring it back. What do you think?
If you have an opinion on this, we’d love to hear (or read) it.
We’ve also prepared a very short survey you might want to participate in (we’ll share the results with you if you’re interested).
If you’d like to know more, contact us.
Check some of our videos:
- New ➽ ICU discharges: where time slips away
- Fast Track vs Standard Path: Which is Better for Diagnosing Colorectal Cancer
- What causes discards in parenteral nutrition preparation? Key factors revealed!
- How Process Mining Uncovers Medication Administration Issues
The Prompter.io is our open project to share our experience—and that of others—in integrating language models and data-to-text techniques into process intelligence. Don’t miss it!
