Clever data: building a chatbot from your database
1 like2,892 views
The document provides an overview of building chatbots using the Microsoft Bot Framework, emphasizing the integration of AI to enhance conversational capabilities. It covers key components such as entity extraction, user intent recognition, and various scenarios for chatbot applications including Q&A, helpdesk, and automation tasks. Additionally, it offers resources and tools to facilitate the development and implementation of chatbots connected to databases and utilizing Azure services.
![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](https://image.slidesharecdn.com/cleverdatabuildingachatbotfromyourdatabase-190922123432/85/Clever-data-building-a-chatbot-from-your-database-15-320.jpg)
![“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
}
]
}](https://image.slidesharecdn.com/cleverdatabuildingachatbotfromyourdatabase-190922123432/85/Clever-data-building-a-chatbot-from-your-database-19-320.jpg)
Clever data: building a chatbot from your database
- 2. Clever data: Building a chatbot from your database Luis Beltrán
- 3. Luis Beltrán • Microsoft MVP in AI & Developer Technologies • Researcher at Tomás Bata University in Zlín, Czech Republic. • Professor at Tecnológico Nacional de México in Celaya, Mexico. @darkicebeam luis@luisbeltran.mx
- 4. Agenda • Chatbots Introduction • Microsoft Bot Framework • Adding your data into your bot • Demo
- 7. Chatbots: • Conversational bots. • Background tasks. • Availability 24/7/365. • AI-powered. A bot detects users’ intentions and is capable of combining millions of data from different sources.
- 8. Pattern: Knowledge Base Bots Fuzzy Searching Filtering to guide a conversation Generating search queries from natural language
- 9. Pattern: Handoff to Human Every company deals with this:
- 10. First triage/data collection Simple and repetitive solutions If it is simple and repetitive, it can be coded. Bots can accelerate it
- 11. 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 Bot to human hand-off: Complete or supervised
- 13. 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 What is Microsoft Bot Framework?
- 14. An x-ray of a typical bot 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) Bot Builder SDK Your bot code goes here
- 15. 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
- 16. Bot Builder SDK Template Your Bot LUIS Publish to Azure Connect to users Add dialog smarts
- 17. Bot Builder SDK Template
- 18. LUIS (Language Understanding Intelligent Service) Trains utterances (examples) into a REST API Maps utterances to intents (verbs) and extracts entities
- 19. “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. Publish to Azure
- 21. Connect to users
- 22. Add Dialog Smarts with Adaptive Cards Notification Microsoft Teams Skype Android iOS
- 23. Adding your data into your bot
- 24. Database (SQL Server, Azure SQL, Oracle, …)
- 25. Access to your database (REST API, GraphQL, …)
- 26. Bot project – Understand user messages (1)
- 27. LUIS – Intents, Entities and Utterances
- 28. LUIS – Intents, Entities and Utterances
- 29. Bot project – Send user messages to LUIS (2)
- 30. Bot project - Translate user messages into API calls (3)
- 31. Bot project - Translate user messages into API calls (4)
- 32. Profit!
- 33. Demo
- 35. Bot Scenarios • Q & A • Helpdesk • Product selection • Task automation • Monitoring • Expert Systems
- 36. Call to Action • Microsoft Bot Framework https://dev.botframework.com/ • Azure 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
- 38. Luis Beltrán Tomás Bata University in Zlín Tecnológico Nacional de México en Celaya luis@luisbeltran.mx luisbeltran.mx @darkicebeam Thank you for your attention! Let’s connect! ☺ icebeam darkicebeam luisantoniobeltran icebeam7 about.me/luis-beltran