SlideShare a Scribd company logo
1 of 24
Clever data: Building a
chatbot from your database
Luis Beltrán
April 27th, 2019
Luis Beltrán
• Microsoft MVP in Developer Technologies
• Researcher and PhD student at Tomás Bata University in Zlín,
Czech Republic.
• Professor at Tecnológico Nacional de México in Celaya, Mexico.
@darkicebeam
luis@luisbeltran.mx
• A bot performs an action:
• Typically, bots react/respond to messages (conversational bots).
• Bots might run a background task.
• A bot detects a user’s intent.
• A bot is able to combine millions of data from different sources.
• A bot is available 24/7/365
• Any platform, anywhere.
• A bot uses AI to improve the user experience and keeps human effort
to a minimum.
Handoff to Human
Every company deals with this:
Handoff to Human
First
triage/data
collection
Simple and
repetitive
solutions
If it is simple and repetitive, it can
be coded. Bots can accelerate it
Handoff to Human
Bot to human hand off: Complete or supervised
Thank you for providing all this information. I
have John with me now who will take from here
and help you out
Hello, this is John. I understand your computer
won’t power on. Let’s take a look at some
service options
I’ve tried these steps, my computer still won’t turn on
Sounds lovely, thank you
I suggest us to request a hardware service. We can have one
of our service engineers look at your computer
Note to operator: It sounds like the user will need hardware
replacement, what next step should I take?
Apologize to
user
Suggest
hardware
service
Let me type
What is the Bot Framework?
Goals
• Start Simple. Add Complexity. No dead-ends.
• Bot adapts to the user, based on context
• Composable and intelligent controls to manage complexity
Bot Controls
LUIS
Query over database via
Azure Search
Form
Filling
QnA
C#
Customer’s
Business Logic
& DataBot Connector
Cortana Direct Line
What?
• Tools for building REST Web Sites
• Services to enrich
• Mechanisms for receive events
• Data to debug and analyze
Why?
• Implements standard protocols
• Modeling conversations is hard. Tools help!
• UI across multiple canvases is hard. Cards rock!
• Language Understanding is hard
• Common and well understood patterns
Bot web service
Your bot code
Entity
Extraction
Speech
Vision/Face
Natural
Language
Translation
+ Microsoft Cognitive Services
Search
Emotion
Knowledge
API
…
Message input <> output
State Management
Bot Connector Service
Conversation Canvas/Channels
……
…
Other services, APIs,
Databases, Azure Machine
Learning, Azure Search,
etc…
Bot Builder SDK
Web Chat
Direct Line…
Email
Facebook
GroupMe
Kik
Skype
Slack
Telegram
Twilio (SMS)
An x-ray of a typical bot
Bot Builder SDK
Your bot code goes here
Bot Connector messages
Your bot
{
"type": "Message",
"id": "68YrxgtB53Y",
"conversationId": "DphPaFQrDuZDKyCez4AFGcT4vy5aQDje1lLGIjB8v18MFtb",
"language": "en",
"text": "You can say "/order" to order!",
"attachments": [ ],
"from": {
"name": "+12065551212",
"channelId": "sms",
"address": "+12065551212",
"id": "Ro52hKN287",
"isBot": false
},
"channelData": { SMS data here },
"botUserData": { your data here },
...
}
Bot
Connector
Bot Builder
SDK
Template
Your Bot LUIS
Publish to
Azure
Connect to
users
Add dialog
smarts
Bot Builder SDK Template
Language Understanding Intelligent Service (LUIS)
“I want to find
news about flight
delays”
{
“entities”: [
{
“entity”: “flight delays”,
“type”: “Topic”
}
],
“intents”: [
{
“intent”: “FindNews”,
“score”: 0.99853384
},
{
“intent”: “None”,
“score”: 0.07289317
},
{
“intent”: “ReadNews”,
“score”: 0.0167122427
},
{
“intent”: “ShareNews”,
“score”: 1.0919299E-06
}
]
}
Publish to Azure
Connect to Users
Add Dialog Smarts with Adaptive Cards
Notification Microsoft Teams Skype Android iOS
https://github.com/icebeam7
Bot scenarios
• Q & A
• Helpdesk
• Product selection
• Task automation
• Monitoring
• Expert Systems
Call to action
• Microsoft Bot Framework https://dev.botframework.com/
• Microsoft Cognitive Services https://microsoft.com/cognitive
• Bot Builder http://github.com/Microsoft/botbuilder
• LUIS https://luis.ai
• Docs https://aka.ms/azure/bots/overview/docs
¡Thank you for
your attention!
Luis Beltrán
Tomás Bata University in Zlín
Tecnológico Nacional de México en Celaya
luis@luisbeltran.mx luisbeltran.mx @darkicebeam
GitHub:
https://github.com/icebeam7
LinkedIn:
https://linkedin.com/in/luisantoniobeltran
SlideShare:
https://slideshare.net/icebeam
YouTube:
https://youtube.com/user/darkicebeam
About Me:
https://about.me/luis-beltran

More Related Content

What's hot

How do Chatbots Work? A Guide to Chatbot Architecture
How do Chatbots Work? A Guide to Chatbot ArchitectureHow do Chatbots Work? A Guide to Chatbot Architecture
How do Chatbots Work? A Guide to Chatbot Architecture
Maruti Techlabs
 

What's hot (12)

How do Chatbots Work? A Guide to Chatbot Architecture
How do Chatbots Work? A Guide to Chatbot ArchitectureHow do Chatbots Work? A Guide to Chatbot Architecture
How do Chatbots Work? A Guide to Chatbot Architecture
 
Student information chatbot final report
Student information chatbot  final report Student information chatbot  final report
Student information chatbot final report
 
Spam Bot & internet Bots
Spam Bot & internet BotsSpam Bot & internet Bots
Spam Bot & internet Bots
 
Scalable state of-the-art conversational AI
Scalable state of-the-art conversational AIScalable state of-the-art conversational AI
Scalable state of-the-art conversational AI
 
Chatbots
ChatbotsChatbots
Chatbots
 
Whats a Chat bot
Whats a Chat botWhats a Chat bot
Whats a Chat bot
 
AI Machine vs Human
AI Machine vs HumanAI Machine vs Human
AI Machine vs Human
 
Introduction to chat bot
Introduction to chat botIntroduction to chat bot
Introduction to chat bot
 
Chatbot and AI Design Principles
Chatbot and AI Design PrinciplesChatbot and AI Design Principles
Chatbot and AI Design Principles
 
Deprecating the state machine: building conversational AI with the Rasa stack
Deprecating the state machine: building conversational AI with the Rasa stackDeprecating the state machine: building conversational AI with the Rasa stack
Deprecating the state machine: building conversational AI with the Rasa stack
 
How AI can help you build better customer relationships?
How AI can help you build better customer relationships?How AI can help you build better customer relationships?
How AI can help you build better customer relationships?
 
Chatbot
ChatbotChatbot
Chatbot
 

Similar to Clever data building a chatbot from your database

Similar to Clever data building a chatbot from your database (20)

Clever data: building a chatbot from your database
Clever data: building a chatbot from your databaseClever data: building a chatbot from your database
Clever data: building a chatbot from your database
 
Clever data building a chatbot from your database
Clever data building a chatbot from your databaseClever data building a chatbot from your database
Clever data building a chatbot from your database
 
Everything you need to know about chatbots
Everything you need to know about chatbotsEverything you need to know about chatbots
Everything you need to know about chatbots
 
Bot design AIsatPN 2018
Bot design AIsatPN 2018Bot design AIsatPN 2018
Bot design AIsatPN 2018
 
virtual-2021-data.sql_.saturday.la-Building database interactions with users ...
virtual-2021-data.sql_.saturday.la-Building database interactions with users ...virtual-2021-data.sql_.saturday.la-Building database interactions with users ...
virtual-2021-data.sql_.saturday.la-Building database interactions with users ...
 
Mat Velloso - Bots in the real world
Mat Velloso - Bots in the real worldMat Velloso - Bots in the real world
Mat Velloso - Bots in the real world
 
Chatbotmeetup15062017
Chatbotmeetup15062017Chatbotmeetup15062017
Chatbotmeetup15062017
 
Azure as a Chatbot Service: From Purpose To Production With A Cloud Bot Archi...
Azure as a Chatbot Service: From Purpose To Production With A Cloud Bot Archi...Azure as a Chatbot Service: From Purpose To Production With A Cloud Bot Archi...
Azure as a Chatbot Service: From Purpose To Production With A Cloud Bot Archi...
 
SharePoint Fest DC 2019 - Bot Framework and Microsoft Graph - Join The Revolu...
SharePoint Fest DC 2019 - Bot Framework and Microsoft Graph - Join The Revolu...SharePoint Fest DC 2019 - Bot Framework and Microsoft Graph - Join The Revolu...
SharePoint Fest DC 2019 - Bot Framework and Microsoft Graph - Join The Revolu...
 
Tech talk - Microsoft A.I.
Tech talk - Microsoft A.I.Tech talk - Microsoft A.I.
Tech talk - Microsoft A.I.
 
Building a bot with an intent
Building a bot with an intentBuilding a bot with an intent
Building a bot with an intent
 
Lessons learned from building a commercial bot development platform
Lessons learned from building a commercial bot development platformLessons learned from building a commercial bot development platform
Lessons learned from building a commercial bot development platform
 
Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...
Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...
Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...
 
Chatbot Technology
Chatbot TechnologyChatbot Technology
Chatbot Technology
 
The implementation of Big Data and AI on Digital Marketing
The implementation of Big Data and AI on Digital MarketingThe implementation of Big Data and AI on Digital Marketing
The implementation of Big Data and AI on Digital Marketing
 
Microsoft teams & bot framework - A developer's perspective
Microsoft teams & bot framework - A developer's perspectiveMicrosoft teams & bot framework - A developer's perspective
Microsoft teams & bot framework - A developer's perspective
 
The Software Challenges of Building Smart Chatbots - ICSE'21
The Software Challenges of Building Smart Chatbots - ICSE'21The Software Challenges of Building Smart Chatbots - ICSE'21
The Software Challenges of Building Smart Chatbots - ICSE'21
 
CHATBOT PPT-2.pptx
CHATBOT PPT-2.pptxCHATBOT PPT-2.pptx
CHATBOT PPT-2.pptx
 
Azure Bot Services - Malaysia
Azure Bot Services - MalaysiaAzure Bot Services - Malaysia
Azure Bot Services - Malaysia
 
LUIS and Bots
LUIS and BotsLUIS and Bots
LUIS and Bots
 

More from Luis Beltran

More from Luis Beltran (20)

AI for Accessibility.pptx
AI for Accessibility.pptxAI for Accessibility.pptx
AI for Accessibility.pptx
 
NET Conf Bhubaneswar - Migrating your Xamarin.Forms app to .NET MAUI.pptx
NET Conf Bhubaneswar - Migrating your Xamarin.Forms app to .NET MAUI.pptxNET Conf Bhubaneswar - Migrating your Xamarin.Forms app to .NET MAUI.pptx
NET Conf Bhubaneswar - Migrating your Xamarin.Forms app to .NET MAUI.pptx
 
03 GlobalAIBootcamp2020Lisboa-Rock, Paper, Scissors.pptx
03 GlobalAIBootcamp2020Lisboa-Rock, Paper, Scissors.pptx03 GlobalAIBootcamp2020Lisboa-Rock, Paper, Scissors.pptx
03 GlobalAIBootcamp2020Lisboa-Rock, Paper, Scissors.pptx
 
BI LATAM Summit 2022 - Creación de soluciones de automatización serverless-...
BI LATAM Summit 2022 - Creación de soluciones de automatización serverless-...BI LATAM Summit 2022 - Creación de soluciones de automatización serverless-...
BI LATAM Summit 2022 - Creación de soluciones de automatización serverless-...
 
CEIAAIT - Fundamentos y Aplicaciones de Deep Learning.pdf
CEIAAIT - Fundamentos y Aplicaciones de Deep Learning.pdfCEIAAIT - Fundamentos y Aplicaciones de Deep Learning.pdf
CEIAAIT - Fundamentos y Aplicaciones de Deep Learning.pdf
 
Computo en la Nube con Azure - AI Gaming Panama.pptx
Computo en la Nube con Azure - AI Gaming Panama.pptxComputo en la Nube con Azure - AI Gaming Panama.pptx
Computo en la Nube con Azure - AI Gaming Panama.pptx
 
5StarsConf - Serverless Machine Learning con Azure Functions y ML.NET .pptx
5StarsConf - Serverless Machine Learning con Azure Functions y ML.NET .pptx5StarsConf - Serverless Machine Learning con Azure Functions y ML.NET .pptx
5StarsConf - Serverless Machine Learning con Azure Functions y ML.NET .pptx
 
ACW - Azure Speaker Recognition Biometria de Voz.pptx
ACW - Azure Speaker Recognition Biometria de Voz.pptxACW - Azure Speaker Recognition Biometria de Voz.pptx
ACW - Azure Speaker Recognition Biometria de Voz.pptx
 
UNICABA - Azure Machine Learning.pptx
UNICABA - Azure Machine Learning.pptxUNICABA - Azure Machine Learning.pptx
UNICABA - Azure Machine Learning.pptx
 
Azure Talks Bolivia - Aumente la confiabilidad de su negocio con Azure Anomal...
Azure Talks Bolivia - Aumente la confiabilidad de su negocio con Azure Anomal...Azure Talks Bolivia - Aumente la confiabilidad de su negocio con Azure Anomal...
Azure Talks Bolivia - Aumente la confiabilidad de su negocio con Azure Anomal...
 
Latino NET - Integrando WhatsApp en nuestras apps .NET con Twilio.pptx
Latino NET - Integrando WhatsApp en nuestras apps .NET con Twilio.pptxLatino NET - Integrando WhatsApp en nuestras apps .NET con Twilio.pptx
Latino NET - Integrando WhatsApp en nuestras apps .NET con Twilio.pptx
 
NOVA - Enriquecimiento de IA con Azure Cognitive Search.pptx
NOVA - Enriquecimiento de IA con Azure Cognitive Search.pptxNOVA - Enriquecimiento de IA con Azure Cognitive Search.pptx
NOVA - Enriquecimiento de IA con Azure Cognitive Search.pptx
 
Netcoreconf 2021 Realidad mixta en apps móviles con Azure Spatial Anchors y ...
Netcoreconf 2021 Realidad mixta en apps móviles con Azure Spatial Anchors y ...Netcoreconf 2021 Realidad mixta en apps móviles con Azure Spatial Anchors y ...
Netcoreconf 2021 Realidad mixta en apps móviles con Azure Spatial Anchors y ...
 
ATG Puebla - El cementerio de Microsoft.pptx
ATG Puebla - El cementerio de Microsoft.pptxATG Puebla - El cementerio de Microsoft.pptx
ATG Puebla - El cementerio de Microsoft.pptx
 
Data-Saturday-10-Sofia-2021 Azure Video Indexer- Advanced data extraction fro...
Data-Saturday-10-Sofia-2021 Azure Video Indexer- Advanced data extraction fro...Data-Saturday-10-Sofia-2021 Azure Video Indexer- Advanced data extraction fro...
Data-Saturday-10-Sofia-2021 Azure Video Indexer- Advanced data extraction fro...
 
Azure Community Conference - Image Recognition in WhatsApp chatbot with Azure...
Azure Community Conference - Image Recognition in WhatsApp chatbot with Azure...Azure Community Conference - Image Recognition in WhatsApp chatbot with Azure...
Azure Community Conference - Image Recognition in WhatsApp chatbot with Azure...
 
Real NET Docs Show - Serverless Machine Learning v3.pptx
Real NET Docs Show - Serverless Machine Learning v3.pptxReal NET Docs Show - Serverless Machine Learning v3.pptx
Real NET Docs Show - Serverless Machine Learning v3.pptx
 
Sesion 5 - Eficiencia del Rendimiento - Well Architected Backstage Tour.pptx
Sesion 5 - Eficiencia del Rendimiento - Well Architected Backstage Tour.pptxSesion 5 - Eficiencia del Rendimiento - Well Architected Backstage Tour.pptx
Sesion 5 - Eficiencia del Rendimiento - Well Architected Backstage Tour.pptx
 
XamarinExpertDay - Creating PDF files in mobile apps with PdfSharpCore and Mi...
XamarinExpertDay - Creating PDF files in mobile apps with PdfSharpCore and Mi...XamarinExpertDay - Creating PDF files in mobile apps with PdfSharpCore and Mi...
XamarinExpertDay - Creating PDF files in mobile apps with PdfSharpCore and Mi...
 
Latam Space Week - Clasificación de rocas espaciales por medio de IA.pptx
Latam Space Week - Clasificación de rocas espaciales por medio de IA.pptxLatam Space Week - Clasificación de rocas espaciales por medio de IA.pptx
Latam Space Week - Clasificación de rocas espaciales por medio de IA.pptx
 

Recently uploaded

+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Victor Rentea
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 

Recently uploaded (20)

Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Cyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfCyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdf
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024
 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdf
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 

Clever data building a chatbot from your database

  • 1. Clever data: Building a chatbot from your database Luis Beltrán April 27th, 2019
  • 2. Luis Beltrán • Microsoft MVP in Developer Technologies • Researcher and PhD student at Tomás Bata University in Zlín, Czech Republic. • Professor at Tecnológico Nacional de México in Celaya, Mexico. @darkicebeam luis@luisbeltran.mx
  • 3.
  • 4. • A bot performs an action: • Typically, bots react/respond to messages (conversational bots). • Bots might run a background task. • A bot detects a user’s intent. • A bot is able to combine millions of data from different sources. • A bot is available 24/7/365 • Any platform, anywhere. • A bot uses AI to improve the user experience and keeps human effort to a minimum.
  • 5.
  • 6. Handoff to Human Every company deals with this:
  • 7. Handoff to Human First triage/data collection Simple and repetitive solutions If it is simple and repetitive, it can be coded. Bots can accelerate it
  • 8.
  • 9. Handoff to Human Bot to human hand off: Complete or supervised
  • 10. Thank you for providing all this information. I have John with me now who will take from here and help you out Hello, this is John. I understand your computer won’t power on. Let’s take a look at some service options I’ve tried these steps, my computer still won’t turn on Sounds lovely, thank you I suggest us to request a hardware service. We can have one of our service engineers look at your computer Note to operator: It sounds like the user will need hardware replacement, what next step should I take? Apologize to user Suggest hardware service Let me type
  • 11. What is the Bot Framework? Goals • Start Simple. Add Complexity. No dead-ends. • Bot adapts to the user, based on context • Composable and intelligent controls to manage complexity Bot Controls LUIS Query over database via Azure Search Form Filling QnA C# Customer’s Business Logic & DataBot Connector Cortana Direct Line What? • Tools for building REST Web Sites • Services to enrich • Mechanisms for receive events • Data to debug and analyze Why? • Implements standard protocols • Modeling conversations is hard. Tools help! • UI across multiple canvases is hard. Cards rock! • Language Understanding is hard • Common and well understood patterns
  • 12. Bot web service Your bot code Entity Extraction Speech Vision/Face Natural Language Translation + Microsoft Cognitive Services Search Emotion Knowledge API … Message input <> output State Management Bot Connector Service Conversation Canvas/Channels …… … Other services, APIs, Databases, Azure Machine Learning, Azure Search, etc… Bot Builder SDK Web Chat Direct Line… Email Facebook GroupMe Kik Skype Slack Telegram Twilio (SMS) An x-ray of a typical bot Bot Builder SDK Your bot code goes here
  • 13. Bot Connector messages Your bot { "type": "Message", "id": "68YrxgtB53Y", "conversationId": "DphPaFQrDuZDKyCez4AFGcT4vy5aQDje1lLGIjB8v18MFtb", "language": "en", "text": "You can say "/order" to order!", "attachments": [ ], "from": { "name": "+12065551212", "channelId": "sms", "address": "+12065551212", "id": "Ro52hKN287", "isBot": false }, "channelData": { SMS data here }, "botUserData": { your data here }, ... } Bot Connector
  • 14. Bot Builder SDK Template Your Bot LUIS Publish to Azure Connect to users Add dialog smarts
  • 15. Bot Builder SDK Template
  • 16.
  • 17. Language Understanding Intelligent Service (LUIS) “I want to find news about flight delays” { “entities”: [ { “entity”: “flight delays”, “type”: “Topic” } ], “intents”: [ { “intent”: “FindNews”, “score”: 0.99853384 }, { “intent”: “None”, “score”: 0.07289317 }, { “intent”: “ReadNews”, “score”: 0.0167122427 }, { “intent”: “ShareNews”, “score”: 1.0919299E-06 } ] }
  • 20. Add Dialog Smarts with Adaptive Cards Notification Microsoft Teams Skype Android iOS
  • 22. Bot scenarios • Q & A • Helpdesk • Product selection • Task automation • Monitoring • Expert Systems
  • 23. Call to action • Microsoft Bot Framework https://dev.botframework.com/ • Microsoft Cognitive Services https://microsoft.com/cognitive • Bot Builder http://github.com/Microsoft/botbuilder • LUIS https://luis.ai • Docs https://aka.ms/azure/bots/overview/docs
  • 24. ¡Thank you for your attention! Luis Beltrán Tomás Bata University in Zlín Tecnológico Nacional de México en Celaya luis@luisbeltran.mx luisbeltran.mx @darkicebeam GitHub: https://github.com/icebeam7 LinkedIn: https://linkedin.com/in/luisantoniobeltran SlideShare: https://slideshare.net/icebeam YouTube: https://youtube.com/user/darkicebeam About Me: https://about.me/luis-beltran