Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

AI Builder Deep Dive Power BI User Group Washington DC

86 views

Published on

Slide deck of the online session I presented at Power BI User Group Washington DC

Published in: Software
  • Be the first to comment

  • Be the first to like this

AI Builder Deep Dive Power BI User Group Washington DC

  1. 1. AI Builder Deep Dive Power BI User Group | Washington, DC
  2. 2. 🦄 Technology consultant @ 🦄 Co-organizer 🦄 MSFT BizApps MVP 🦄 Dutchy 🦄 Book nerd 🦄 Lover of all things Unicorn 🦄 2 cats – 1 husband Rebekka Aalbers #PowerAddict #LessCodeMorePower
  3. 3. Target audience You want to know more about AI Builder You have (some) experience with the tools in the Power Platform (CDS, Apps, Automation)
  4. 4. Goal Understand How, Why, and When to use AI Builder
  5. 5. Agenda
  6. 6. Why & What AI Builder
  7. 7. But first! Let’s generate some demo data! • Tweet something using #AIBuilder • Use a language you like (Latin script)
  8. 8. Why do I like the Power Platform tools – including AI Builder? Evolved to become a Consultant at a Microsoft Partner Landed by accident in the IT-department of an end customer Started out as business user
  9. 9. Guided point-and-click AI applications AI for every skill level Embedded within the Microsoft Power Platform and Dynamics 365
  10. 10. 2 Model types Custom models Prebuilt models
  11. 11. Select the model
  12. 12. Step by Step Guidance in the UI ADD YOUR DATA TRAIN THE MODEL CHECK THE PERFORMANCE PUBLISH & USE
  13. 13. Prediction - GA Determine the likelihood of specific business outcomes – Boolean (Yes/No – True/False) Input: Data in 1 CDS entity Output: prediction written back into prediction field in CDS Use automatic schedule in CDS and in Power Automate Specifics: Uses CDS Entity Only 2 outcome possibilities (Yet!) Data requirements: Minimum of 50 records in total and 10 records historical outcome for each class. Best result with at least 1000 records.
  14. 14. Object detection - Preview Build an AI model that recognizes and counts visual objects.​ Output: Name and count of detected objects Use in Power Apps Canvas & Power Automate Specifics: JPG, png or BMP – max 6 MB Data requirements: minimum of 15 images per object – preferably 50 or more.
  15. 15. Lighting Object size Camera angle Background Use diverse images
  16. 16. Text classification- Preview Build an application that reviews, tags, and classifies large volumes of text to track sentiment, improve customer experiences, and mine valuable insights.​ Output: List of tags with certainty score in separate entity Auto generated on schedule in CDS & used in Power Automate Specifics: Uses CDS Entity Languages: English, French, German, Dutch, Italian, Spanish, Portuguese Data requirements: Text and tags in text fields in same entity – All tags in one field using a delimeter Max 5000 characters per text item - Minimum of 50 text items per tag.
  17. 17. Form processing - Preview Read, extract, and process data from scans, emails, PDFs, and images.​ Output: Extracted key-value pairs and table data. Use in Power Apps Canvas & Power Automate Specifics: JPG, png or PDF – max 4 MB – Latin alphabet High quality images – between 530 x 100 and 4200 x 4200 pixels Data requirements: 5 – 10 sample documents with the same layout. Must contain keys above or to the left of the value.
  18. 18. Éric Sauvé @ZePowerDiver http://bit.ly/AIBuilderWW
  19. 19. Recent updates
  20. 20. Recent updates Manually enter objects for Object detection New fields recognized with Business Card Reader Updates to AI Builder in the Power Apps canvas studio AI Builder flow templates https://powerapps.microsoft.com/en-us/blog/category/ai-builder/
  21. 21. On the roadmap New AI Models • Prebuilt Text classification model • Anomaly detection • Image moderation • Receipt scanning Usability • AI Builder connector • Guided learning Form processor • Entity extraction model • New Power Apps controls • New prebuilt Flow templates • ‘Try’ feature for the keyword extraction model. AND MORE…
  22. 22. Availability, Administration & Licensing
  23. 23. Availability per region
  24. 24. Custom model maintenance & deployment
  25. 25. Update custom model Create new version • From published version • Or • From last trained version Change settings or training data Publish or • Only for: • Prediction model • Text classification model Retrain model
  26. 26. Deployment through solutions* PROD Production environment Managed solution • Use model TEST /QA Sandbox environment Managed solution • Test model DEV Sandbox environment Unmanaged solution • Create model • Train model • Improve model
  27. 27. Using the model PUBLISH THE MODEL SET RUN SCHEDULE* SHARE MODEL
  28. 28. Roles & security  CDS security roles ENVIRONMENT MAKERS CREATE AI MODELS CDS USERS USE MODELS SYTEM ADMINS & CUSTOMIZERS ACCESS ALL MODELS
  29. 29. AI Builder License AI Builder Capacity Add-on $ 500 / subscription 1 million service credits Tenant level Credit consumption Training models Using models Credit calculation ???? – Calculator not available yet Credit allocation Allocate capacity to environments in Power Platform admin center
  30. 30. Q & A

×