1. Machine Learning and Office 365 Collaboration
6/20/2018 2:02 AM
THR1021
Machine Learning and Office 365 Collaboration
Liam Cleary
Associate Director / MVP
© Microsoft Corporation. All rights reserved. MICROSOFT MAKES NO WARRANTIES, EXPRESS, IMPLIED OR STATUTORY, AS TO THE INFORMATION IN THIS PRESENTATION.

2. Liam Cleary
@helloitsliam |

3. Agenda Machine Learning Microsoft Cognitive Services
Developing using Microsoft Cognitive Services
SharePoint and Microsoft Cognitive Services

4. Machine Learning

5. What is Machine Learning?
Data science technique that allows computers to use existing data to forecast future behaviors, outcomes, and trends
Allows computers to learn without being explicitly programmed
Ability to perform actions using specific rulesets
Automatically identify content, patterns, languages and classifications

6. What is Machine Learning?
Artificial Intelligence
Statistical Analysis
Neuroscience Processing
Signal Processing
Information Theory

7. Machine Learning Algorithms
Clustering & Dimensionality Reduction
Linear Regression
Decision Trees
Random Forests
Classification
Hidden Markov Model
Association Analysis

8. Microsoft Cognitive Services

9. Microsoft Cognitive Services are a set of APIs, SDKs and services available to developers to make their applications more intelligent, engaging and discoverable.
Microsoft Cognitive Services enable you to easily add intelligent features – such as emotion and video detection; facial, speech and vision recognition; speech and language understanding – into your applications.

10. What are Microsoft Cognitive Services?
Vision
From faces to feelings, allow your apps to understand images and video
Speech
Hear and speak to your users by filtering noise, identifying speakers, and understanding intent
Language
Process text and learn how to recognize what users want
Knowledge
Tap into rich knowledge amassed from the web, academia, or your own data
Search
Access billions of web pages, images, videos, and news with the power of Bing APIs

11. Vision Computer Vision API Content Moderator API Video API
Video Indexer API
Face API
Emotion API

12. Language Language Understanding Intelligent Service
Text Analytics API
Translator Text API
Linguistic Analysis API
Bing Spell Check API
Web Language Model API

13. Speaker Recognition API
Speech
Speaker Recognition API
Translator Speech API
Bing Speech API

14. Search Bing Autosuggest API Bing News Search API Bing Web Search API
Bing Entity Search API
Bing Image Search API
Bing Video Search API

15. Knowledge Recommendations API Decision Service API
Knowledge Exploration API
QnA Maker API
Entity Linking Intelligence Service API
Academic Knowledge API

16. Developing with Microsoft Cognitive Services

17. Developing with Microsoft Cognitive Services

18. Developing using Microsoft Cognitive Services
Generated for Tenant (PaaS Instance)
Each request needs to be in JSON format
API Endpoint
Access Key (Private)
JSON Request
JSON Response
Unique Endpoint for each API
Responses are Sync and Async
Standard HTML status codes

19. Microsoft Cognitive Services Endpoints
Register Endpoints
Generate Access Keys

20. Microsoft Cognitive Services Endpoints
Emotion API:
Face API:
Content API:
Recommendation API:
Text API:
Translation API:

21. Example: Text Analytics – Async vs Sync
/sentiment
Sync
/keyPhrases
/text/analytics/v2.0
/languages
ASync
/topics

22. SharePoint and Microsoft Cognitive Services

23. SharePoint / Microsoft Cognitive Services Usage
User Uploads Content
Event Fires
Event Receivers
Remote Event Receivers
Azure Functions

24. SharePoint / Microsoft Cognitive Services Usage
User Uploads Content
Sentiment - Is text positive or negative?
Key Phrases - What are people discussing in a single article?
Topics - What are people discussing across many articles?
Language - What language is text written in?
Event Fires
Open files using OpenXml
Content Text Analysis

25. SharePoint / Microsoft Cognitive Services Usage
User Uploads Content
Translation – Copy existing content and translate to language. Create new file/content for specific language and save in SharePoint
Event Fires
Open files using OpenXml
Translation

26. SharePoint / Microsoft Cognitive Services Usage
User Uploads Content
Content Properties Updated
Event Fires
JSON Values returned
Content Type fields updated
Results Returned
Content Text Analysis

27. Sample Data for Text Analytics
KeyPhraseBatchResult languageResults = client.KeyPhrases(
new MultiLanguageBatchInput( new List<MultiLanguageInput>() { new MultiLanguageInput("ja", "1", "発火は素晴らしいです"), new MultiLanguageInput("cs", "2", "Zapal je úžasné"), new MultiLanguageInput("en", "3", "Ignite is Awesome" new MultiLanguageInput("es", "4", "Ignite es impresionante") } ) );

28. Sample Code for Text Analytics
using Microsoft.Azure.CognitiveServices.Language.TextAnalytics; using Microsoft.Azure.CognitiveServices.Language.TextAnalytics.Models;
ITextAnalyticsAPI client = new TextAnalyticsAPI(); client.AzureRegion = AzureRegions.Westus; client.SubscriptionKey = "ENTER TENANT KEY";
foreach (var document in languageResults.Documents) { Console.WriteLine("Document ID: {0} ", document.Id); Console.WriteLine("\t Key phrases:"); foreach (string keyphrase in document.KeyPhrases) { Console.WriteLine("\t\t" + keyphrase); } }

29. Review Cognitive Services Cloud Enablement Build Applications
Commoditized
Simple
Cloud Enablement
Pay-as-you-go
Consumption
Build Applications
Human
Natural
Chat
Bots

30. To Learn More Machine Learning Cheat Sheet
Machine Learning Studio
Machine Learning Basics
Preview Documentation and Examples
Azure Cognitive Services

31. Please evaluate this session
Tech Ready 15
6/20/2018
Please evaluate this session
From your
Please expand notes window at bottom of slide and read. Then Delete this text box.
PC or tablet: visit MyIgnite
Phone: download and use the Microsoft Ignite mobile app
Your input is important!
© 2012 Microsoft Corporation. All rights reserved. Microsoft, Windows, Windows Vista and other product names are or may be registered trademarks and/or trademarks in the U.S. and/or other countries.
The information herein is for informational purposes only and represents the current view of Microsoft Corporation as of the date of this presentation. Because Microsoft must respond to changing market conditions, it should not be interpreted to be a commitment on the part of Microsoft, and Microsoft cannot guarantee the accuracy of any information provided after the date of this presentation. MICROSOFT MAKES NO WARRANTIES, EXPRESS, IMPLIED OR STATUTORY, AS TO THE INFORMATION IN THIS PRESENTATION.