06.04.2019
#
2019
#
Conversational AI applications in
Microsoft Teams
06.04.2019
#
Sponsors and Partners
ABOUT US
THOMAS GÖLLES
MICROSOFT MVP (O365)
SOLVION
https://thomy.tech
@thomyg
Head of Modern Workplace Solutions
Graz, Austria
STEPHAN BISSER
MICROSOFT MVP (AI)
SOLVION
https://www.cloudguy.pro
@cloudguy_pro
Technical Lead
Graz, Austria
DEFINITION
Source: http://www.boredpanda.com/fast-food-ads-vs-reality/
ARTIFICIAL INTELLIGENCE
I’ll be back
0 ≤ 𝑥 ≤ 1
EVERYTHING YOU SEE TODAY ...
“Do I need an
umbrella today?”
“… At the moment computers have an advantage of speed, but they show no
sign of intelligence.
But computers roughly obey a version of Moore’s Law, which says that their
speed and complexity double every eighteen months. …”
This is not surprising because our present computers are less complex than
the brain of an earthworm, a species not noted for its intellectual powers.
MICROSOFT
AI PLATFORM
Conversational AI
WHAT IS CONVERSATIONAL AI?
2000s: Mobile
• Social
• User download apps
from App Stores
The future: Conversations
• Natural language between people
and technology
• Conversational canvas
• Bots and agents
• Conversational AI
1990s: Internet
• Search
• User “visits” websites
1980s: PC
• Desktop
The evolution of computers and IT
• A new user interface paradigm
• Exposes software services through
conversational interface
• In apps, browser and on IoT devices
• Pro-active capabilities
(Virtual Assistant etc.)
• Bots
CONVERSATIONAL AI
Conversational AI is a subfield of artificial intelligence focused on producing natural and seamless
conversations between humans and computers
BOTS 101
“a computer program designed to have a
conversation with a human being, especially over
the internet” *
* https://dictionary.cambridge.org/dictionary/english/chatbot
• It’s one thing: it’s an app that performs an automated task
• It solves the user’s needs in the quickest/easiest way compared to any
other option... like an app, or a website
BOTS 101
• Automate routine work
• Faster transactions
• Introduce AI in a friendly way
THE BUSINESS CASE FOR BOTS
…
MODERNIZING THE COMPANY FAQ
Company info
Departmental knowledge
Troubleshooting/support
+ ++
QNA MAKER
• Data - Aggregate and extract
knowledge from non structured
data
• Architecture. The data and
runtime hosted in your Azure
subscription.
• Data privacy and compliance.
QnA data is hosted within your
Azure compliance boundary.
• Seamless chit-chat integration
with personalities like:
Profesional; Friend; Comic.
• Azure Application Insights
integration.
QNAMAKER
BOTS 101
{ Your Code }
REST Endpoint
MICROSOFT BOT FRAMEWORK
Users
Direct Line
Mail
Bing
kik
Facebook
Messenger
Web Chat
3rd Party
3rd
Slack GroupMe
CortanaMicrosoft Teams
Telegram
Twilio (SMS)
SkypeOffice 365
Channels Conversational AI Platform
Functions BotWeb App Bot Bot Channels Registration Bot Service Types
Bot Builder SDKs
C#
.NET SDK Java SDK*JavaScript SDK Python SDK*
Cognitive ServicesVision Speech Search Language Knowledge
Patterns & ConceptsRecognizers CardsMiddlewareState Dialogs
HostingMicrosoft Azure On-premises Other Cloud Service Providers
* still in preview
HOW BOTS WORK
ACTIVITY PROCESSING STACK
MIDDLEWARE
• 1st middleware object’s turn handler
executes code before calling next.
• 2nd middleware object’s turn handler
executes code before calling next.
• The bot’s turn handler executes and
returns.
• 2nd middleware object’s turn handler
executes any remaining code before
returning.
• 1st middleware object’s turn handler
executes any remaining code before
returning.
next()
next()
1st
middleware
2nd
middleware
Bot logic
STATE MANAGEMENT
.BOT FILE
With a .bot file, you can register services like:
• Localhost local debugger endpoints
• Azure Bot Service registrations.
• LUIS.AI gives your bot the ability to communicate with people using natural language..
• QnA Maker Build, train and publish a simple question and answer bot based on FAQ
URLs, structured documents or editorial content in minutes.
• Dispatch models for dispatching across multiple services.
• Azure Application Insights for insights and bot analytics.
• Azure Blob Storage for bot state persistence.
• Azure Cosmos DB - globally distributed, multi-model database service to persist bot
state.
Point of
Interest
Mail
Automotive
Custom
Hospitality
Conversation Skills
(Customisable)
APIs
Productivity
1st/3rd Party
Directory
Tasks
Calendar
AI
Capabilities
Language
Understanding
Speech
Vision
QnA
Knowledge
Sources
Manuals
(PDF)
Data Sources
General
Knowledge
3rd Party
Assistants
IoT Edge
Devices
Type Speak
Tap
User
Input
Adaptive
Cards
Channels
Azure Bot
Services
Virtual Assistant
Your Brand
Your Personality
Dialogs
Language Model
Virtual Assistant
Your brand, your assistant
• Text, with optional media attachments
• Traditional chat, can contain media attachments
(e.g., image, video, audio, file)
• Input prompts
• Suggested actions: Buttons, numbered items in a list, etc.
• Rich cards, rendered as a list or carousel
• Images, buttons, audio, animations, video, user sign-in,
etc.
• Hero | Audio | Animation | Thumbnail | Receipt | Sign In
|
Video | Adaptive | Purchase
• Speech
• Text-based chat using Speech Recognition & Synthesis
(TTS)
CONVERSATIONAL MECHANISMS
https://ai.jumpto365.com
LANGUAGE & KNOWLEDGE
COGNITIVE SERVICES
• Machine learning-based service
to build natural language into
apps, bots, and IoT devices.
Quickly create enterprise-ready,
custom models that
continuously improve.
• New People and Geography
entity recognizers
• CLI tools and v4 SDK
integration
• CSA STAR, ISO 27001, ISO
27018, HIPAA and PCI DSS
Compliance
LANGUAGE UNDERSTANDING (LUIS)
Always learning &
improving
Enterprise Grade,
available worldwide
LANGUAGE UNDERSTANDING EXAMPLE
Book a hotel in Warsaw.
Intent = BookHotel Entity = Warsaw
LANGUAGE UNDERSTANDING EXAMPLE
{
"query": "Book a hotel in Warsaw.",
"topScoringIntent": {
"intent": "BookHotel",
"score": 0.921233
},
"entities": [
{
"entity":“Warsaw",
"type": "Location",
"startIndex": 10,
"endIndex": 13,
"score": 0.7615982
}
]
}
THE LIFECYCLE OF YOUR PROJECT
Comprehensive framework for the lifecycle of your project
Plan Build Test Publish Connect Evaluate
Author Dialogs
Design Cards
Visualize
Bot Builder SDK
Cognitive Services
Getting Started
Templates
Emulator​
Application
Insights
Conversation
Transcripts
DevOps Tools
Azure
BYO Web Host
WebChat
Cortana
Skype, FB
+
Custom
(DirectLine)
Application
Insights
LUIS
Suggestions
DEMOS TILL THE END ;)
FREE BOT WEBINAR –
PLEASE GIVE
FEEDBACK
http://bit.ly/bot_webinar_feedback
06.04.2019
#
06.04.2019
#

SharePoint Saturday Warsaw - Conversational AI applications in Microsoft Teams

  • 1.
  • 2.
  • 3.
    ABOUT US THOMAS GÖLLES MICROSOFTMVP (O365) SOLVION https://thomy.tech @thomyg Head of Modern Workplace Solutions Graz, Austria STEPHAN BISSER MICROSOFT MVP (AI) SOLVION https://www.cloudguy.pro @cloudguy_pro Technical Lead Graz, Austria
  • 5.
  • 6.
  • 7.
  • 9.
    0 ≤ 𝑥≤ 1 EVERYTHING YOU SEE TODAY ... “Do I need an umbrella today?”
  • 11.
    “… At themoment computers have an advantage of speed, but they show no sign of intelligence. But computers roughly obey a version of Moore’s Law, which says that their speed and complexity double every eighteen months. …” This is not surprising because our present computers are less complex than the brain of an earthworm, a species not noted for its intellectual powers.
  • 12.
  • 13.
  • 14.
  • 15.
    2000s: Mobile • Social •User download apps from App Stores The future: Conversations • Natural language between people and technology • Conversational canvas • Bots and agents • Conversational AI 1990s: Internet • Search • User “visits” websites 1980s: PC • Desktop The evolution of computers and IT
  • 16.
    • A newuser interface paradigm • Exposes software services through conversational interface • In apps, browser and on IoT devices • Pro-active capabilities (Virtual Assistant etc.) • Bots CONVERSATIONAL AI Conversational AI is a subfield of artificial intelligence focused on producing natural and seamless conversations between humans and computers
  • 17.
    BOTS 101 “a computerprogram designed to have a conversation with a human being, especially over the internet” * * https://dictionary.cambridge.org/dictionary/english/chatbot
  • 18.
    • It’s onething: it’s an app that performs an automated task • It solves the user’s needs in the quickest/easiest way compared to any other option... like an app, or a website BOTS 101
  • 19.
    • Automate routinework • Faster transactions • Introduce AI in a friendly way THE BUSINESS CASE FOR BOTS …
  • 20.
    MODERNIZING THE COMPANYFAQ Company info Departmental knowledge Troubleshooting/support + ++
  • 21.
  • 22.
    • Data -Aggregate and extract knowledge from non structured data • Architecture. The data and runtime hosted in your Azure subscription. • Data privacy and compliance. QnA data is hosted within your Azure compliance boundary. • Seamless chit-chat integration with personalities like: Profesional; Friend; Comic. • Azure Application Insights integration. QNAMAKER
  • 24.
    BOTS 101 { YourCode } REST Endpoint
  • 25.
    MICROSOFT BOT FRAMEWORK Users DirectLine Mail Bing kik Facebook Messenger Web Chat 3rd Party 3rd Slack GroupMe CortanaMicrosoft Teams Telegram Twilio (SMS) SkypeOffice 365 Channels Conversational AI Platform Functions BotWeb App Bot Bot Channels Registration Bot Service Types Bot Builder SDKs C# .NET SDK Java SDK*JavaScript SDK Python SDK* Cognitive ServicesVision Speech Search Language Knowledge Patterns & ConceptsRecognizers CardsMiddlewareState Dialogs HostingMicrosoft Azure On-premises Other Cloud Service Providers * still in preview
  • 26.
  • 27.
  • 28.
    MIDDLEWARE • 1st middlewareobject’s turn handler executes code before calling next. • 2nd middleware object’s turn handler executes code before calling next. • The bot’s turn handler executes and returns. • 2nd middleware object’s turn handler executes any remaining code before returning. • 1st middleware object’s turn handler executes any remaining code before returning. next() next() 1st middleware 2nd middleware Bot logic
  • 29.
  • 30.
    .BOT FILE With a.bot file, you can register services like: • Localhost local debugger endpoints • Azure Bot Service registrations. • LUIS.AI gives your bot the ability to communicate with people using natural language.. • QnA Maker Build, train and publish a simple question and answer bot based on FAQ URLs, structured documents or editorial content in minutes. • Dispatch models for dispatching across multiple services. • Azure Application Insights for insights and bot analytics. • Azure Blob Storage for bot state persistence. • Azure Cosmos DB - globally distributed, multi-model database service to persist bot state.
  • 31.
    Point of Interest Mail Automotive Custom Hospitality Conversation Skills (Customisable) APIs Productivity 1st/3rdParty Directory Tasks Calendar AI Capabilities Language Understanding Speech Vision QnA Knowledge Sources Manuals (PDF) Data Sources General Knowledge 3rd Party Assistants IoT Edge Devices Type Speak Tap User Input Adaptive Cards Channels Azure Bot Services Virtual Assistant Your Brand Your Personality Dialogs Language Model Virtual Assistant Your brand, your assistant
  • 32.
    • Text, withoptional media attachments • Traditional chat, can contain media attachments (e.g., image, video, audio, file) • Input prompts • Suggested actions: Buttons, numbered items in a list, etc. • Rich cards, rendered as a list or carousel • Images, buttons, audio, animations, video, user sign-in, etc. • Hero | Audio | Animation | Thumbnail | Receipt | Sign In | Video | Adaptive | Purchase • Speech • Text-based chat using Speech Recognition & Synthesis (TTS) CONVERSATIONAL MECHANISMS
  • 33.
  • 34.
  • 35.
    • Machine learning-basedservice to build natural language into apps, bots, and IoT devices. Quickly create enterprise-ready, custom models that continuously improve. • New People and Geography entity recognizers • CLI tools and v4 SDK integration • CSA STAR, ISO 27001, ISO 27018, HIPAA and PCI DSS Compliance LANGUAGE UNDERSTANDING (LUIS) Always learning & improving Enterprise Grade, available worldwide
  • 36.
    LANGUAGE UNDERSTANDING EXAMPLE Booka hotel in Warsaw. Intent = BookHotel Entity = Warsaw
  • 37.
    LANGUAGE UNDERSTANDING EXAMPLE { "query":"Book a hotel in Warsaw.", "topScoringIntent": { "intent": "BookHotel", "score": 0.921233 }, "entities": [ { "entity":“Warsaw", "type": "Location", "startIndex": 10, "endIndex": 13, "score": 0.7615982 } ] }
  • 39.
    THE LIFECYCLE OFYOUR PROJECT Comprehensive framework for the lifecycle of your project Plan Build Test Publish Connect Evaluate Author Dialogs Design Cards Visualize Bot Builder SDK Cognitive Services Getting Started Templates Emulator​ Application Insights Conversation Transcripts DevOps Tools Azure BYO Web Host WebChat Cortana Skype, FB + Custom (DirectLine) Application Insights LUIS Suggestions
  • 40.
  • 41.
    FREE BOT WEBINAR– PLEASE GIVE FEEDBACK http://bit.ly/bot_webinar_feedback
  • 42.