Welcome to AI. Let me introduce myself: My name is Rick, and I’m the new VP of Artificial Intelligence or AI here at CallMiner. Now that is out of the way, what the heck is AI.
Actually, I’m not sure I can accurately answer that question, basically because in its current form it’s been around since the 1950’s, but lately it has really taken off. Because it is super cool, the term is used liberally to define a whole host of things, many of which are to sell someone a thing. So let’s create a basic definition together.
The basics of AI
At the beginning there was data, we can all agree with that, whether that is 1’s and 0’s or any other integer, we all know data. But what about lots of data? Here is an example:
- How old are you?
How old is everyone right now?
- That’s a piece of datum
- That’s a lot of data
If we get that there is data, then we are faced with a big data problem. Here is the data set that exists in the CallMiner Eureka platform: The total words transcribed by all of our clients is more than a trillion a year. Which is about 200 billion more words than is posted on Twitter in a year. No matter your political affiliation that’s a lot of tweets. With all this data, what can you do with it?
Training data for smarter customer interactions
The first step is training, or what many of you in the contact center do every day, if you work in speech analytics, you create categories, (in mathematics we might call these clusters, or kernels). Your training of your data is the analytics used to train the words of your interactions. In the course of a year CallMiner customers’ generate just shy of 40 billion category hits, and it is growing. This is what we can call training data — our Eureka Analytics users are training the data in the system every day.
NLP, the beginning of the good stuff
Even with all those relevant trained categories we believe we have mapped less than 30% of an interaction, today – meaning, for any given interaction that occurs in a contact center we have created a blueprint for what happens in 30% of each conversation on average. Our goal is to rapidly map the remainder using a semantic network, and natural language processing (NLP). This project is we are calling “auto-categorization”. If we map the genome of a call, we can then begin to predict all sorts of outcomes and even relevant inputs. Those of you who work with speech analytics, let your inner geek out on this one.
All that’s left is AI…
CallMiner has been in the AI business for a while, a good long while, it has just not been transparent to our clients. The basis of speech recognition is a neural network acoustic and language model. Tools used by our customers’ analyst every day to analyze their customer interaction leverage AI techniques. These include Search QA, which leverages machine learning based statistical phrase pattern engine and TopicMiner® for auto topic discovery which leverages NLP vector clustering to identify trends. On this foundation of AI, we are poised to do what humans struggle to do. Complex pattern recognition. In this amazing 1 trillion word set, are all the patterns in each interaction, across every interaction, are the optimal interaction paths for industries such as healthcare, to ensure accurate resolution. Why do consumers call back or cancel a product? The answer is based on every interaction they have had. Or more complex question: who are our customers? What if you could predict who is the perfect person to interact with a customer, the list goes on. The patterns to identify these questions and answers are so close to impossible to see by humans, that it takes artificial intelligence to recognize them.
This is what we are doing, building the complex mathematics and models to find those patterns, no matter how small, to predict the things that are relevant to every interaction, including yours.
I hope you are as excited about AI as I am. Recently I spoke on the webinar, How Artificial Intelligence and Interaction Analytics Drive Better Customer Experiences. I encourage you to listen to it! Hear from contact center industry consultant Sheraz Shere and Shawn Feaser, Sr. Manager Data Analytics at Encore as we discuss how machine learning and AI are changing the customer experience landscape and how it can make a real impact in your business.