At UpdateAI, our mission is simple: to make meetings better so you can do better things.
We leverage our revolutionary artificial intelligence technology to detect action items for you – allowing you to keep your focus on the customer during meetings and not on taking notes. The data doesn’t lie, either. UpdateAI outperforms competitors in action item detection by up to 180% in overall accuracy, based on a testing set of dozens of meetings with over 1,000 combined minutes of speech.
As UpdateAI, we wanted to avoid a generic, unimaginative approach. We didn’t want to be a “CTRL+F” solution, as in, just locating keywords in the transcript (e.g. “send email”). That’s not enough.
From there, the objective was to refine our definitions and determine which types of action item patterns were the most prevalent, and then focus on nailing those pattern types.
According to our research, self-assigned action items are the most common. This was very useful to know; training for this type of action item gave us a “simple” groundwork on which to build our model, and also gave us a basis for evaluating more precise language patterns. We named these “sub-patterns.” For example, the simplest self-assigned sub-pattern we discovered was “1st person pronoun + will + [action verb]” (e.g. I will send the emails.).
But we also discovered the simplest sub-pattern isn’t always correct. There are times when the pattern is used but does not indicate an action item – these cases are what we call “anti-patterns.” An example of an anti-pattern in this instance would be if the speaker is describing a quality of state of being (e.g., “I will be fine.”).
Ultimately, the collection of these patterns, sub patterns, and anti-patterns formed our proprietary action item taxonomy.