by Donald Panek

On the Eve of Christmas Eve Santa gave to us a bonus gift…

Managing an annual worldwide list of who’s been naughty or nice has always been a challenge for Santa and the North Pole. In the past, starting each year in January once all the presents have been delivered, Santa and his massive team of BOEs (Behavioral Observation Elves) begin their year-long travels around the world to aggregate data on each individual keeping tabs of good deeds vs. naughty deeds.

As you can imagine collecting, aggregating, scoring, and delivering all this data is quite a chore, but now thanks to Microsoft AI Builder and the solution teams at Hitachi Solutions, Santa and the BOEs are getting some much-needed relief.

North Pole goes High Tech

Let’s have a high level look at how Santa leverages some new technology to deliver faster and better accuracy when managing the Naughty or Nice list. Don’t forget that you most likely do not want to be on the naughty list when you have been good all year. In the past accidents have happened and some folks ended up on the wrong list!

To make the whole process faster and more accurate Santa and the BOEs have employed some great new tech. First off, every new gift delivered by Santa has embedded IoT (Internet of Things) monitoring devices that help report back to the North Pole NLMS (Naughty List Management System) good and bad behaviors detected in or around those devices. Beginning in December, the data is analyzed for each person in the world and based on the outcome, that person gets added to the Naughty or Nice list. BOEs out in the field all around the world also use Augmented Reality goggles when observing folks to quickly and easily spot good deeds and nefarious ones. Once again, this data is quickly tagged and passed to the NLMS.

Detected Behaviors? What?

So, you’re probably asking yourself “How can these devices determine a good behavior from a bad one?”. Well this is where the real magic of Santa and technology come into play. Leveraging the new Microsoft AI (Artificial Intelligence) Builder, a vast historical data model is created that takes all the good and bad deeds from years of history and adds them into the model. This model is then trained to match a currently detected action with historical actions and tag them as Naughty or Nice. Once this tagging is done, which takes milliseconds, the data is then sent to the NLMS. At the end of the yearly observation period in December, the data is analyzed, and the AI Model determines which list each person gets placed on. In case you were not aware, December is a blackout month for being good or bad except in extreme cases of badness. You can’t just run rampant in December without notice! You also can’t be bad all year then have a do-good marathon in December in hopes of swinging your status. The AI model also measures monthly consistency in making its determination. BOEs rejoice!

AI Builder Overview

AI Builder is a new Power Platform capability that allows you to easily automate processes and predict outcomes to help improve business performance. AI Builder is a turnkey solution that brings the power of AI through a point-and-click experience. Using AI Builder, you can add intelligence to your apps even if you have no coding or data science skills. This is the same power that the North Pole and Santa has implemented in the new NLMS!

Using AI Builder is easy, fast and intuitive

Using AI is easy thanks to integration with Power Apps and Microsoft Power Automate. Adding intelligence to your business is as simple as this:

1. Choose AI model type: Use the model type that suits your business need. Choose from a growing set of AI turnkey solutions.
2. Connect data: Select your business-specific data from Common Data Service. AI Builder does the hard work for you thanks to the Common Data Model.
3. Tailor your AI model: Filter your data, set scheduling, and tweak the AI model to optimize how your AI performs.
4. Train your AI model: Training is an automatic process where AI Builder “teaches” your AI model how to resolve your business problem (for example, recognize your products on an image) thanks to your business data and tailoring. When trained, your AI model can generate insights, such as the result of a prediction or the list and number of objects detected in an image.
5. Use your AI model’s insights: Use the results from your AI model across Power Platform to create end-to-end solutions that meet your business needs, even if you have no coding skills. For example, create a flow that automates document processing in Power Automate, or an app created with Power Apps that predicts whether a supplier will be out of compliance. NOTE: AI Builder is currently in public preview. Please consult documentation for General Availability release schedule.

Santa is all about his Models

An AI Builder model is a data model that you train to perform a specific AI task using your data. You select the model type, provide the data, build and train your own unique AI model, and then use or share the model. Build your own custom AI model using these AI model types:

Prediction Model –This model allows you to determine a yes/no, good/bad, true/false, pass/fail type of determination from your data. This is the primary model used in the NLMS. The data aggregated all year gets fed to the model and the person is tagged as Naughty or Nice.

Form Processing –Form processing allows you to create and use models that use machine learning technology to identify and extract key-value pairs and table data from form documents.

Object Detection – This allows you to train a model with various images and then recognize those images with your model and act accordingly. Santa and the NLMS utilize this to identify good and bad acts out in the wild.

Text Classification –Use AI Builder text classification with Power Automate and Power Apps to automate and scale your business processes and free your employees to act on these insights. It can also be used as an input for other AI capabilities such as subscription user churn and predictive analysis. AI Builder can learn from your previously labeled text items and enable you to classify unstructured text data stored in Common Data Service into your own business-specific categories.

Wrapping it up

So, there you have it. Santa and the BOEs are enjoying an easier workflow throughout the year when managing the Naughty or Nice list using Artificial Intelligence and Microsoft AI Builder. You can rest assured that all the hard work you are doing all year long being as good as you can will pay off and get you accurately onto the Nice list. Remember, now more than ever, he knows if you’ve been bad or good so be good for goodness sake! Happy holidays!

To learn more about Artificial Intelligence and how it can streamline your business processes, reach out to the Elves at Hitachi Solutions today!