Governance di una Conversational AI
Download as PPTX, PDF1 like116 views
The document discusses governance in conversational AI, focusing on the management of conversational agents and their integration into business processes. It outlines tools and frameworks provided by Microsoft, such as Azure Bot Service and Cognitive Services, to create and manage conversational experiences. Additionally, it addresses the technical architecture and functionalities of conversational applications, including user interaction via various channels and natural language processing capabilities.
![BotChannel
Registration
App
Service WPF+Unity Player
VIRTUAL ASSISTANT ARCHITECTURE ON BOT FRAMEWORK
Microsoft Azure Virtual Assistant (on premises)
Management
Web App
AI
[Bot Framework
V4]
Config
Cognitive
Services
Text-To-
Speech
Speech-To-
Text
NLP (LUIS)NLP
Design
Text/Audi
o
Camera
Micropho
ne
Speakers
Video
Audio
Audio
Testo
Testo
Intent
Audio
input
output
Avatar
Channel
Touch(x,y)
Proiezion
e
3D
Audio
DirectLine
Windows PC](https://image.slidesharecdn.com/2019-191209191054/85/Governance-di-una-Conversational-AI-31-320.jpg)
Governance di una Conversational AI
- 1. GOVERNANCE DI UNA AI CONVERSAZIONALE Marco Parenzan
- 2. WHO AM I? Marco Parenzan Solution Sales Specialist @ Insight Microsoft Azure MVP 1nn0va Community Lead Marco Parenzan marco.parenzan@1nn0va.it marco.parenzan@insight.com Twitter: @marco_parenzan
- 3. CONVERSATIONAL AGENTS ARE ARTIFICIAL INTELLIGENCE COMPUTER PROGRAMS THAT COMMUNICATE WITH PEOPLE WHO USE NATURAL LANGUAGE.
- 4. CONVERSATIONAL AI “Conversational AI refers to the use of messaging apps, speech-based assistants and chatbots to automate communication and create personalized customer experiences at scale” “A chatbot is a computer software program designed to simulate human conversation via text, audio messages, or images”
- 5. NEED FOR GOVERNANCE Rationalise management to avoid abandonment Governance - Highlight and optimize the asset value of a CA Conversational Agents are another resource that IT needs to manage So you need to identify where the costs and points of attention are Apply some "devops" style discipline
- 6. User Input Channels Business ProcessBot Intelligence CONVERSATIONAL AI: AZURE BOT SERVICE + COGNITIVE SERVICES
- 7. CREATE A CONVERSATION WITH BOT SERVICE Comprehensive framework for the lifecycle of your project Author Dialogs Design Cards Visualize Bot Framework SDK Cognitive Services Getting Started Templates Emulator Application Insights DevOps Tools Azure BYO Web Host WebChat Cortana Skype, FB + Custom (DirectLine) Application Insights LUIS Suggestions
- 8. INTRO ON HOW THE BOT FRAMEWORK WORKS • Every interaction creates an activity • Bot Framework interacts with the user via channel • ConversationalUpdate and Message • Requests arrive to the bot via HTTP POST • Status responses are an HTTP 200 • Conversation in managed via TurnContext
- 9. INTRO ON HOW THE BOT FRAMEWORK WORKS • Activity is executed via JSON • JSON is deserialized and sent to the Adapter, using the ProcessActivity method • Adapter creates the TurnContext and calls the middleware • Activities are managed by the ActivityHandler
- 10. GITHUB https://github.com/microsoft/botframework https://github.com/microsoft/BotBuilder-Samples https://github.com/microsoft/botframework-solutions https://github.com/microsoft/BotFramework-Samples old
- 11. GITHUB https://github.com/microsoft/BotFramework-Composer Bot Framework Composer is an integrated development tool for developers and multi-disciplinary teams to build bots and conversational experiences with the Microsoft Bot Framework. Within this tool, you'll find everything you need to build a sophisticated conversational experience. https://github.com/microsoft/BotFramework-Emulator The Bot Framework Emulator is a desktop application that allows bot developers to test and debug bots built using the Bot Framework SDK. You can use the Bot Framework Emulator to test bots running either locally on your machine or connect to bots running remotely through a tunnel. https://github.com/microsoft/BotFramework-WebChat This repository contains code for the Bot Framework Web Chat component. The Bot Framework Web Chat component is a highly- customizable web-based client for the Bot Framework V4 SDK. The Bot Framework SDK v4 enables developers to model conversation and build sophisticated bot applications. https://github.com/microsoft/botframework-cli The new BF Command Line Interface (CLI) tool replaces the collection of standalone tools used to manage Bot Framework bots and related services. We have ported most tools and are in process of porting the rest. The new BF CLI aggregates the collection of cross- platform tools into one cohesive and consistent interface.
- 12. Open Framework Multiple Canvases ADAPTIVE CARDS Notification Microsoft Teams Skype Android iOS Bot Service Lifecycle: Plan | Build | Test | Publish | Connect | Evaluate
- 13. Bing Speech API Convert speech to text and back again, and understand its intent Speaker Recognition API Give your app the ability to know who's talking Custom Speech Service Fine-tune speech recognition for anyone, anywhere QnA Maker Distill information into conversational, easy-to-navigate answers Language Understanding Intelligent Service Teach your apps to understand commands from your users Easily perform speech and text translation Translator Azure Search Integrate search into a conversational experience ADDING INTELLIGENCE
- 14. TRAIN YOUR INTELLIGENCE You will not lower people in your company You will use them to more valuable tasks
- 15. THE TWO STEPS OF A COMPANY BOT STRATEGY UNAUTHENTICATED EXPERIENCE AUTHENTICATED EXPERIENCE
- 16. UNAUTHENTICATED EXPERIENCE Answer to simple questions «How to do this...» «How to do that...» Objective of the company Engaging experience Lower pressure on customer care
- 17. Result Intent INTEGRATION GW (GATEWAY) The GW integration implements the Business Logic for intents 1 intent1 API Enables microservices governance to be implemented Direct call to internal business applications Or indirect if you implement MS on corporate data lakes Infrastructure setup Integration Gateway API Setup Azure VNET Configuration On-premises infrastructure configuration support (Firewall, Host involved you CA Utterance Intent Intent Utterance Channel Entities Result IntentAPI
- 18. HTTPS HTTPS App Service Help Desk Commerciale API Doc Commerciale API Doc interna API TECHNICAL ARCHITECTURE OF A COMPANY INTEGRATION BOT FW Channel Teams Helpdesk API HTTPS Skype for Business Channel Azure AD Active Directory GWIntegrazione AD Connect SAP Sharepoint 2010 FirewallDMZ/PrivateLAN Win10 Mac iOS Android LUIS NLP 1 x Contesto x Lingua Contesto Risposte 1 x Contesto x Lingua Sharepoint 2019
- 19. QNA MAKER Based on Azure. The data and runtime hosted in your Azure subscription. Data privacy and compliance. QnA data is hosted within your Azure compliance boundary. Azure Application Insights integration. Helpful to get insights on how the services is being utilized.
- 20. LANGUAGE UNDERSTANDING (LUIS) Machine learning-based service to build natural language into apps, bots, and IoT devices. Quickly create enterprise-ready, custom models that continuously improve. Quickly build a custom language solution Alays learning & improving Enterprise-ready, available worldwide Add natural language to your apps Bot Service Lifecycle: Plan | Build | Test | Publish | Connect | Evaluate
- 21. LUIS – TERMINOLOGY • Intent – the action/task the user wants to perform • Utterance – the sentence where the user expresses the goal • Entity – words or phrases inside an entity • Domain –Intents related to a specific type of actions (e.g. Calendar intents) – prebuilt domains
- 22. WHAT IT MEANS “TRAINING” It means adding examples (utterance) so that statistically the tool recognizes and classifies the similarities, meaningful words, excludes the least important ones It is not always true (e.g. personalization, sentiment, ...) Beware of ambiguity
- 23. DIFFERENT "CHANNELS" Text Voce Virtual Reality We are meeting different needs Text/form Desktop/Mobile experience Voice Mobility/Hand-free experience Virtual reality Human simulation experience Integration with non-chat-based facilities
- 24. ENCOURAGING THE ROLE OF CONVERSATIONAL DESIGNER independence autonomy Skill IT Channel independence form text
- 25. WHAT IS INTENT The intent is an NLP concept... ... but intents are everywhere The user's intention The idea behind the user's action Every time you interact with an application, you express an intention
- 26. TECHNICALLY SPEAKING, AN INTENT IS... ... a universally recognized text key • Probably a key classified in a domain .. characterized by a set of parameters (called entities) that argue the intention
- 27. NATURAL LANGUAGE PROCESSING (NLP) Cost Effective Based on statistical algorithms (pattern matching on utterance) Identifying the correct set of utterance is the work of the conversational designer Pervasive (coverage) Unambiguous (to avoid false positive) Anyway, a big piece of engineering Out-of-the-box solutions for major players Offline support Adapt Set expectations correctly FUTURESReti Neurali (verticali, taylor made, efficaci, ma costosi)
- 28. SPEECH TO TEXT In NLP terms, it is used to transcribe a "multimedia" utterance We're talking about S2T... ... but even an OCR could have its role... .. or a custom vision using the camera... Cost Effective Pre-established entries Success will involve the availability of variants... ... and the increase in quality You can do the custom training For noise reduction, domain verticalization Expensive (hours of recordings and pages of transcripts)
- 29. FONIA Full cloud solution. Twilio Integration with existing Call Center Feasibility verification Human Hand-off
- 30. ESEMPI DI SCENARI interactive voice response (IVR) First level Massive call schedule for data retrieval Compliance compliance Artifact Development Appliances Hands-free interaction
- 31. BotChannel Registration App Service WPF+Unity Player VIRTUAL ASSISTANT ARCHITECTURE ON BOT FRAMEWORK Microsoft Azure Virtual Assistant (on premises) Management Web App AI [Bot Framework V4] Config Cognitive Services Text-To- Speech Speech-To- Text NLP (LUIS)NLP Design Text/Audi o Camera Micropho ne Speakers Video Audio Audio Testo Testo Intent Audio input output Avatar Channel Touch(x,y) Proiezion e 3D Audio DirectLine Windows PC
- 32. GRAZIE!
- 33. GRAZIE Marco Parenzan Solution Sales Specialist @ Insight Microsoft Azure MVP 1nn0va Community Lead Marco Parenzan marco.parenzan@1nn0va.it marco.parenzan@insight.com Twitter: @marco_parenzan