SlideShare ist ein Scribd-Unternehmen logo
1 von 35
CLOUD
CONFERENCE
ITALIA
2019
SPONSOR
GOVERNANCE DI UNA AI CONVERSAZIONALE
Marco Parenzan
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
CONVERSATIONAL AGENTS ARE ARTIFICIAL INTELLIGENCE
COMPUTER PROGRAMS THAT COMMUNICATE WITH
PEOPLE WHO USE NATURAL LANGUAGE.
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”
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
User Input Channels Business ProcessBot Intelligence
CONVERSATIONAL AI: AZURE BOT SERVICE + COGNITIVE SERVICES
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
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
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
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
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.
Open Framework Multiple Canvases
ADAPTIVE CARDS
Notification Microsoft Teams Skype Android iOS
Bot Service Lifecycle: Plan | Build | Test | Publish | Connect | Evaluate
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
TRAIN YOUR INTELLIGENCE
 You will not lower people in your company
 You will use them to more valuable tasks
THE TWO STEPS OF A COMPANY BOT STRATEGY
UNAUTHENTICATED
EXPERIENCE
AUTHENTICATED
EXPERIENCE
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
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
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
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.
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
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
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

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
ENCOURAGING THE ROLE OF CONVERSATIONAL DESIGNER
 independence
 autonomy
 Skill IT
 Channel independence
 form text

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
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
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
FUTURESReti Neurali (verticali, taylor made, efficaci, ma costosi)
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)
FONIA
 Full cloud solution. Twilio
 Integration with existing Call Center
 Feasibility verification
 Human Hand-off
ESEMPI DI SCENARI
 interactive voice response (IVR)
 First level
 Massive call schedule for data retrieval
 Compliance compliance
 Artifact Development Appliances
 Hands-free interaction
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
GRAZIE!
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

Weitere ähnliche Inhalte

Was ist angesagt?

Ratan_cv_pdf
Ratan_cv_pdfRatan_cv_pdf
Ratan_cv_pdf
Ratan Lal
 

Was ist angesagt? (20)

SAP Conversational AI as a Service managed by Skybuffer (SAP chatbot)
SAP Conversational AI as a Service managed by Skybuffer (SAP chatbot)SAP Conversational AI as a Service managed by Skybuffer (SAP chatbot)
SAP Conversational AI as a Service managed by Skybuffer (SAP chatbot)
 
AI Machine vs Human
AI Machine vs HumanAI Machine vs Human
AI Machine vs Human
 
SharePoint Saturday Warsaw - Conversational AI applications in Microsoft Teams
SharePoint Saturday Warsaw - Conversational AI applications in Microsoft TeamsSharePoint Saturday Warsaw - Conversational AI applications in Microsoft Teams
SharePoint Saturday Warsaw - Conversational AI applications in Microsoft Teams
 
Why is flutter considered the best cross platform framework
Why is flutter considered the best cross platform frameworkWhy is flutter considered the best cross platform framework
Why is flutter considered the best cross platform framework
 
AppliFire - Low Code Rapid Application Development Platform
AppliFire - Low Code Rapid Application Development PlatformAppliFire - Low Code Rapid Application Development Platform
AppliFire - Low Code Rapid Application Development Platform
 
Watson bluemix 17112014
Watson bluemix 17112014Watson bluemix 17112014
Watson bluemix 17112014
 
How ring central sdk changing the game
How ring central sdk changing the gameHow ring central sdk changing the game
How ring central sdk changing the game
 
Google MLkit
Google MLkitGoogle MLkit
Google MLkit
 
Ratan_cv_pdf
Ratan_cv_pdfRatan_cv_pdf
Ratan_cv_pdf
 
RakeshKushwaha
RakeshKushwahaRakeshKushwaha
RakeshKushwaha
 
DEEPTI REVANKAR_RESUME
DEEPTI REVANKAR_RESUMEDEEPTI REVANKAR_RESUME
DEEPTI REVANKAR_RESUME
 
E031202024029
E031202024029E031202024029
E031202024029
 
Chats & Messengers Development | Powercode
Chats & Messengers Development | PowercodeChats & Messengers Development | Powercode
Chats & Messengers Development | Powercode
 
Top 10 mobile app development programming languages in 2022
Top 10 mobile app development programming languages in 2022Top 10 mobile app development programming languages in 2022
Top 10 mobile app development programming languages in 2022
 
Brochure of luxoft automotive software by luxoft software development
Brochure of luxoft automotive software by luxoft software developmentBrochure of luxoft automotive software by luxoft software development
Brochure of luxoft automotive software by luxoft software development
 
API:World 2016 - Applying Domain Driven Design to APIs and Microservices
API:World 2016 - Applying Domain Driven Design to APIs and MicroservicesAPI:World 2016 - Applying Domain Driven Design to APIs and Microservices
API:World 2016 - Applying Domain Driven Design to APIs and Microservices
 
New NeXt for Advanced Developers
New NeXt for Advanced DevelopersNew NeXt for Advanced Developers
New NeXt for Advanced Developers
 
Priyotosh_resume
Priyotosh_resumePriyotosh_resume
Priyotosh_resume
 
Tomer kimhi mobmodcon-nov2015-integrating new camera hardware
Tomer kimhi mobmodcon-nov2015-integrating new camera hardwareTomer kimhi mobmodcon-nov2015-integrating new camera hardware
Tomer kimhi mobmodcon-nov2015-integrating new camera hardware
 
ManpraX Software LLP corporate overview with technology list
ManpraX Software LLP corporate overview with technology listManpraX Software LLP corporate overview with technology list
ManpraX Software LLP corporate overview with technology list
 

Ähnlich wie CCI2019 - Governance di una Conversational AI

Ähnlich wie CCI2019 - Governance di una Conversational AI (20)

Realizzare un Virtual Assistant con Bot Framework Azure e Unity
Realizzare un Virtual Assistant con Bot Framework Azure e UnityRealizzare un Virtual Assistant con Bot Framework Azure e Unity
Realizzare un Virtual Assistant con Bot Framework Azure e Unity
 
Da 0 all'AI conversazionale usando Microsoft Azure
Da 0 all'AI conversazionale usando Microsoft AzureDa 0 all'AI conversazionale usando Microsoft Azure
Da 0 all'AI conversazionale usando Microsoft Azure
 
Want to integrate your business phone system or contact center with your CRM?
Want to integrate your business phone system or contact center with your CRM?Want to integrate your business phone system or contact center with your CRM?
Want to integrate your business phone system or contact center with your CRM?
 
Conversational Document Processing AI with Rui Costa
Conversational Document Processing AI with Rui CostaConversational Document Processing AI with Rui Costa
Conversational Document Processing AI with Rui Costa
 
Global ai bootcamp_codrina
Global ai bootcamp_codrinaGlobal ai bootcamp_codrina
Global ai bootcamp_codrina
 
PDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptx
PDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptxPDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptx
PDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptx
 
運用對話機器人提供線上客服服務
運用對話機器人提供線上客服服務運用對話機器人提供線上客服服務
運用對話機器人提供線上客服服務
 
Bots are the New Apps: Building Bots with ASP.NET WebAPI & Language Understan...
Bots are the New Apps: Building Bots with ASP.NET WebAPI & Language Understan...Bots are the New Apps: Building Bots with ASP.NET WebAPI & Language Understan...
Bots are the New Apps: Building Bots with ASP.NET WebAPI & Language Understan...
 
Microsoft Teams Development - Conversational AI
Microsoft Teams Development - Conversational AIMicrosoft Teams Development - Conversational AI
Microsoft Teams Development - Conversational AI
 
Chatbots and automation in the digital workplace
Chatbots and automation in the digital workplaceChatbots and automation in the digital workplace
Chatbots and automation in the digital workplace
 
Ai tools every developer should know
Ai tools every developer should knowAi tools every developer should know
Ai tools every developer should know
 
Arya.ai artificial intelligence platform vinay kumar
Arya.ai   artificial intelligence platform  vinay kumarArya.ai   artificial intelligence platform  vinay kumar
Arya.ai artificial intelligence platform vinay kumar
 
AI at Microsoft for HEC
AI at Microsoft for HECAI at Microsoft for HEC
AI at Microsoft for HEC
 
Create Conversational Applications to Transform the Digital Enterprise
Create Conversational Applications to Transform the Digital EnterpriseCreate Conversational Applications to Transform the Digital Enterprise
Create Conversational Applications to Transform the Digital Enterprise
 
api.ai presentation
api.ai presentationapi.ai presentation
api.ai presentation
 
Conversational AI and Chatbot Integrations
Conversational AI and Chatbot IntegrationsConversational AI and Chatbot Integrations
Conversational AI and Chatbot Integrations
 
Microsoft power platform
Microsoft power platformMicrosoft power platform
Microsoft power platform
 
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
 
Artificial Intelligence Solutions
Artificial Intelligence SolutionsArtificial Intelligence Solutions
Artificial Intelligence Solutions
 
Why Is Flutter A Great Platform Amidst All Cross-Platform Apps?
Why Is Flutter A Great Platform Amidst All Cross-Platform Apps?Why Is Flutter A Great Platform Amidst All Cross-Platform Apps?
Why Is Flutter A Great Platform Amidst All Cross-Platform Apps?
 

Mehr von walk2talk srl

Mehr von walk2talk srl (20)

CCI 2019 - SQL Injection - Black Hat Vs White Hat
CCI 2019 - SQL Injection - Black Hat Vs White HatCCI 2019 - SQL Injection - Black Hat Vs White Hat
CCI 2019 - SQL Injection - Black Hat Vs White Hat
 
CCI 2019 - Exploiting Custom Vision SDK in Python to create an efficient imag...
CCI 2019 - Exploiting Custom Vision SDK in Python to create an efficient imag...CCI 2019 - Exploiting Custom Vision SDK in Python to create an efficient imag...
CCI 2019 - Exploiting Custom Vision SDK in Python to create an efficient imag...
 
CCI 2019 - Come ottimizzare i propri workload su Azure
CCI 2019 - Come ottimizzare i propri workload su AzureCCI 2019 - Come ottimizzare i propri workload su Azure
CCI 2019 - Come ottimizzare i propri workload su Azure
 
CCI 2019 - Exchange 2019 da 0 ad HA in 1 ora
CCI 2019 - Exchange 2019 da 0 ad HA in 1 oraCCI 2019 - Exchange 2019 da 0 ad HA in 1 ora
CCI 2019 - Exchange 2019 da 0 ad HA in 1 ora
 
CCI 2019 - PowerApps for Enterprise Developers
CCI 2019 - PowerApps for Enterprise DevelopersCCI 2019 - PowerApps for Enterprise Developers
CCI 2019 - PowerApps for Enterprise Developers
 
CCI 2019 - Architettare componenti in SPFx, esperienze sul campo
CCI 2019 - Architettare componenti in SPFx, esperienze sul campoCCI 2019 - Architettare componenti in SPFx, esperienze sul campo
CCI 2019 - Architettare componenti in SPFx, esperienze sul campo
 
CCI 2019 - Step by step come attivare un servizio voce in MS Teams
CCI 2019 - Step by step come attivare un servizio voce in MS TeamsCCI 2019 - Step by step come attivare un servizio voce in MS Teams
CCI 2019 - Step by step come attivare un servizio voce in MS Teams
 
CCI 2019 - Strumenti Azure per l'Anomaly Detection in ambito Industria 4.0
CCI 2019 - Strumenti Azure per l'Anomaly Detection in ambito Industria 4.0CCI 2019 - Strumenti Azure per l'Anomaly Detection in ambito Industria 4.0
CCI 2019 - Strumenti Azure per l'Anomaly Detection in ambito Industria 4.0
 
CCI2019 - I've got the Power! I've got the Shell!
CCI2019 - I've got the Power! I've got the Shell!CCI2019 - I've got the Power! I've got the Shell!
CCI2019 - I've got the Power! I've got the Shell!
 
CCI2019 - Sistema di controllo del traffico con architettura Big Data
CCI2019 - Sistema di controllo del traffico con architettura Big DataCCI2019 - Sistema di controllo del traffico con architettura Big Data
CCI2019 - Sistema di controllo del traffico con architettura Big Data
 
CCI2019 - SQL Server ed Azure: Disaster Recovery per tutti
CCI2019 - SQL Server ed Azure: Disaster Recovery per tuttiCCI2019 - SQL Server ed Azure: Disaster Recovery per tutti
CCI2019 - SQL Server ed Azure: Disaster Recovery per tutti
 
CCI2019 - Reagire agli eventi generati dalla propria infrastruttura con Azure...
CCI2019 - Reagire agli eventi generati dalla propria infrastruttura con Azure...CCI2019 - Reagire agli eventi generati dalla propria infrastruttura con Azure...
CCI2019 - Reagire agli eventi generati dalla propria infrastruttura con Azure...
 
CCI2019 - What's new in Remote Desktop Services on Windows Server 2019 and Azure
CCI2019 - What's new in Remote Desktop Services on Windows Server 2019 and AzureCCI2019 - What's new in Remote Desktop Services on Windows Server 2019 and Azure
CCI2019 - What's new in Remote Desktop Services on Windows Server 2019 and Azure
 
CCI2019 - Teams Direct Routing e servizi fonia avanzati
CCI2019 - Teams Direct Routing e servizi fonia avanzatiCCI2019 - Teams Direct Routing e servizi fonia avanzati
CCI2019 - Teams Direct Routing e servizi fonia avanzati
 
CCI2019 - Microservizi: Idee per un'architettura con al centro l'utente
CCI2019 - Microservizi: Idee per un'architettura con al centro l'utenteCCI2019 - Microservizi: Idee per un'architettura con al centro l'utente
CCI2019 - Microservizi: Idee per un'architettura con al centro l'utente
 
CCI2019i - Implementare Azure Multi-Factor Authentication Lettere dal Fronte
CCI2019i - Implementare Azure Multi-Factor Authentication Lettere dal FronteCCI2019i - Implementare Azure Multi-Factor Authentication Lettere dal Fronte
CCI2019i - Implementare Azure Multi-Factor Authentication Lettere dal Fronte
 
CCI2019 - Monitorare SQL Server Senza Andare in Bancarotta
CCI2019 - Monitorare SQL Server Senza Andare in BancarottaCCI2019 - Monitorare SQL Server Senza Andare in Bancarotta
CCI2019 - Monitorare SQL Server Senza Andare in Bancarotta
 
CCI2019 - Architecting and Implementing Azure Networking
CCI2019 - Architecting and Implementing Azure NetworkingCCI2019 - Architecting and Implementing Azure Networking
CCI2019 - Architecting and Implementing Azure Networking
 
CCI2019 - Teams e lo Shadow IT
CCI2019 - Teams e lo Shadow ITCCI2019 - Teams e lo Shadow IT
CCI2019 - Teams e lo Shadow IT
 
CCI2018 - La "moderna" Sicurezza informatica & Microsoft
CCI2018 - La "moderna" Sicurezza informatica & MicrosoftCCI2018 - La "moderna" Sicurezza informatica & Microsoft
CCI2018 - La "moderna" Sicurezza informatica & Microsoft
 

Kürzlich hochgeladen

Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 
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
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 

Kürzlich hochgeladen (20)

presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
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
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
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
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024
 
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
 
"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 - 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 ...
 
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...
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
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
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 

CCI2019 - Governance di una Conversational AI

  • 3. GOVERNANCE DI UNA AI CONVERSAZIONALE Marco Parenzan
  • 4. 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
  • 5. CONVERSATIONAL AGENTS ARE ARTIFICIAL INTELLIGENCE COMPUTER PROGRAMS THAT COMMUNICATE WITH PEOPLE WHO USE NATURAL LANGUAGE.
  • 6. 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”
  • 7. 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
  • 8. User Input Channels Business ProcessBot Intelligence CONVERSATIONAL AI: AZURE BOT SERVICE + COGNITIVE SERVICES
  • 9. 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
  • 10. 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
  • 11. 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
  • 12. 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
  • 13. 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.
  • 14. Open Framework Multiple Canvases ADAPTIVE CARDS Notification Microsoft Teams Skype Android iOS Bot Service Lifecycle: Plan | Build | Test | Publish | Connect | Evaluate
  • 15. 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
  • 16. TRAIN YOUR INTELLIGENCE  You will not lower people in your company  You will use them to more valuable tasks
  • 17. THE TWO STEPS OF A COMPANY BOT STRATEGY UNAUTHENTICATED EXPERIENCE AUTHENTICATED EXPERIENCE
  • 18. 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
  • 19. 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
  • 20. 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
  • 21. 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.
  • 22. 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
  • 23. 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
  • 24. 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 
  • 25. 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
  • 26. ENCOURAGING THE ROLE OF CONVERSATIONAL DESIGNER  independence  autonomy  Skill IT  Channel independence  form text 
  • 27. 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
  • 28. 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
  • 29. 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 FUTURESReti Neurali (verticali, taylor made, efficaci, ma costosi)
  • 30. 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)
  • 31. FONIA  Full cloud solution. Twilio  Integration with existing Call Center  Feasibility verification  Human Hand-off
  • 32. ESEMPI DI SCENARI  interactive voice response (IVR)  First level  Massive call schedule for data retrieval  Compliance compliance  Artifact Development Appliances  Hands-free interaction
  • 33. 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
  • 35. 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