SlideShare une entreprise Scribd logo
1  sur  18
P U B L I C S E C T O R
S U M M I T
C anb er r a, AC T
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Let a ChatBot do the Heavy Lifting
of the Simple Stuff
Kurt Heiz
Senior Solutions Architect
ANZ Public Sector, AWS
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Agenda
What is a ChatBot?
Amazon Lex
Demo
Sample use cases and architecture
Code
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
ChatBot definition
Wikipedia defines a ChatBot as:
“A chatbot is a computer program which conducts a conversation via
auditory or textual methods. Such programs are often designed to
convincingly simulate how a human would behave as a conversational
partner, although as of 2019, they are far short of being able to pass the
Turing test”
“A Turing test is a method of inquiry in artificial intelligence (AI) for
determining whether or not a computer is capable of thinking like a
human being.” Developed by Alan Turing in 1950, who cracked the Nazi
Enigma code
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Amazon Lex
• Service to build conversational interfaces
• Integrates tightly with other AWS services
• Fulfilment using AWS Lambda at two stages
• Authentication with IAM or Amazon Cognito
• Built in channel support for
• Kik
• Slack
• Twilio
• Facebook
• Amazon Connect integration
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Structure of a ChatBot example
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Sample use case (anonymous user)
• Support desk: internal or external
• ‘Low hanging fruit’ questions
• How do I reset my password for [system]?
• What are the term dates?
• Where can I find [something] ?
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Sample use case (authenticated user)
• Support desk: internal or external
• ‘Low hanging fruit’ questions
• Book an appointment with [person] for [date] at [time]
• How many days [leaveType] do I have?
• Spin up a new [environmentType] for [solutionName]
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Our sample use case scenario
• External support desk (anonymous user)
• Business problem
• Customers are currently waiting up to one hour to have simple questions answered
• Estimates that offloading the simple questions could save call wait times by up to 66%
• Channels in use:
• Telephone
• Facebook Messenger
• Proposal
• Create a ChatBot to answer simple questions as defined by the business, using existing call
logs to define those questions
• Introduce a new interface, web, and integrate with FB
• Leave telephone integration to future phase once ChatBot has proven itself in two to three
months
• Where do we start?
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Where do we start?
• Define a goal
• “Assist new students with basic tasks and finding their way around campus”
• Define intents from top simple requests, aim for between 5-10
• Action or Assistance based – be sure to make use of slots
• Sample utterances for training
• Where can answers and responses be found?
• Technical architecture
• Operational support
• Continuous training and updating of ChatBot
• Set expectations for users upfront about limits of ChatBot capability
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Test – train – test (ensure it understands correctly)
• Create an automated
testing regime
• Ensure expected intent is
matched and correct answer
is given
• Create list of non-trained
utterances with expected
positive and negative
matches
• Learn about the confusion
matrix
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Confusion matrix
• A confusion matrix is a
table that is often used to
describe the performance
of a classification model
(or "classifier") on a set of
test data for which the
true values are known.
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
Technical serverless architecture option
AWS Cloud
Customer
desktop
client
Amazon API Gateway
AWS Lambda Amazon Lex AWS Lambda
AWS Lambda Amazon DynamoDB
Amazon Elasticsearch
Service
Customer
mobile
client
Amazon Kinesis
Data Firehose
Support
desktop
client
Amazon Cognito
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
What more can the interceptor do for you?
AWS Cloud
Desktop
client
Amazon API Gateway
AWS Lambda Amazon Lex AWS Lambda
AWS Lambda Amazon DynamoDB
Amazon Elasticsearch
Service
Mobile
client
Amazon Kinesis
Data Firehose
Desktop
client
Amazon Cognito
Amazon Translate
Amazon Comprehend
Third Party web chat systems
e.g. LiveChat
© 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R
S U M M I T
DynamoDB sample table structure
• Table can be generic to handle any intent and slot values

Contenu connexe

Tendances

Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...
Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...
Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...Amazon Web Services
 
머신러닝으로 유창해지는 AWS의 언어실력 - 트랙1, Community Day 2018 re:Invent 특집
머신러닝으로 유창해지는 AWS의 언어실력 - 트랙1, Community Day 2018 re:Invent 특집머신러닝으로 유창해지는 AWS의 언어실력 - 트랙1, Community Day 2018 re:Invent 특집
머신러닝으로 유창해지는 AWS의 언어실력 - 트랙1, Community Day 2018 re:Invent 특집AWSKRUG - AWS한국사용자모임
 
re:Invent re:Cap - An overview of Artificial Intelligence and Machine Learnin...
re:Invent re:Cap - An overview of Artificial Intelligence and Machine Learnin...re:Invent re:Cap - An overview of Artificial Intelligence and Machine Learnin...
re:Invent re:Cap - An overview of Artificial Intelligence and Machine Learnin...Adrian Hornsby
 
Add Intelligence to Applications with AWS AI Services
Add Intelligence to Applications with AWS AI ServicesAdd Intelligence to Applications with AWS AI Services
Add Intelligence to Applications with AWS AI ServicesNicholas Walsh
 
Artificial Intelligence for Developers - OOP Munich
Artificial Intelligence for Developers - OOP MunichArtificial Intelligence for Developers - OOP Munich
Artificial Intelligence for Developers - OOP MunichBoaz Ziniman
 
Tips and Tricks to Stay Out of the Spam Folder
Tips and Tricks to Stay Out of the Spam FolderTips and Tricks to Stay Out of the Spam Folder
Tips and Tricks to Stay Out of the Spam FolderSendGrid
 
Building AI-powered Serverless Applications on AWS
Building AI-powered Serverless Applications on AWSBuilding AI-powered Serverless Applications on AWS
Building AI-powered Serverless Applications on AWSAdrian Hornsby
 
Image Segmentation: Approaches and Challenges
Image Segmentation: Approaches and ChallengesImage Segmentation: Approaches and Challenges
Image Segmentation: Approaches and ChallengesApache MXNet
 

Tendances (9)

Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...
Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...
Workshop Build an Image-Based Automatic Alert System with Amazon Rekognition:...
 
머신러닝으로 유창해지는 AWS의 언어실력 - 트랙1, Community Day 2018 re:Invent 특집
머신러닝으로 유창해지는 AWS의 언어실력 - 트랙1, Community Day 2018 re:Invent 특집머신러닝으로 유창해지는 AWS의 언어실력 - 트랙1, Community Day 2018 re:Invent 특집
머신러닝으로 유창해지는 AWS의 언어실력 - 트랙1, Community Day 2018 re:Invent 특집
 
re:Invent re:Cap - An overview of Artificial Intelligence and Machine Learnin...
re:Invent re:Cap - An overview of Artificial Intelligence and Machine Learnin...re:Invent re:Cap - An overview of Artificial Intelligence and Machine Learnin...
re:Invent re:Cap - An overview of Artificial Intelligence and Machine Learnin...
 
Add Intelligence to Applications with AWS AI Services
Add Intelligence to Applications with AWS AI ServicesAdd Intelligence to Applications with AWS AI Services
Add Intelligence to Applications with AWS AI Services
 
Email etiquettes_110
Email  etiquettes_110Email  etiquettes_110
Email etiquettes_110
 
Artificial Intelligence for Developers - OOP Munich
Artificial Intelligence for Developers - OOP MunichArtificial Intelligence for Developers - OOP Munich
Artificial Intelligence for Developers - OOP Munich
 
Tips and Tricks to Stay Out of the Spam Folder
Tips and Tricks to Stay Out of the Spam FolderTips and Tricks to Stay Out of the Spam Folder
Tips and Tricks to Stay Out of the Spam Folder
 
Building AI-powered Serverless Applications on AWS
Building AI-powered Serverless Applications on AWSBuilding AI-powered Serverless Applications on AWS
Building AI-powered Serverless Applications on AWS
 
Image Segmentation: Approaches and Challenges
Image Segmentation: Approaches and ChallengesImage Segmentation: Approaches and Challenges
Image Segmentation: Approaches and Challenges
 

Similaire à Let a ChatBot do the Heavy Lifting of the Simple Stuff

Making Cloud Procurement Easy with AWS Marketplace, Automation, and Governance
Making Cloud Procurement Easy with AWS Marketplace, Automation, and GovernanceMaking Cloud Procurement Easy with AWS Marketplace, Automation, and Governance
Making Cloud Procurement Easy with AWS Marketplace, Automation, and GovernanceAmazon Web Services
 
A Tale of Two Pizzas: Accelerating Software Delivery with AWS Developer Tools
A Tale of Two Pizzas: Accelerating Software Delivery with AWS Developer ToolsA Tale of Two Pizzas: Accelerating Software Delivery with AWS Developer Tools
A Tale of Two Pizzas: Accelerating Software Delivery with AWS Developer ToolsAmazon Web Services
 
AWS Secret Region – Lessons Learned Around DevSecOps
AWS Secret Region – Lessons Learned Around DevSecOpsAWS Secret Region – Lessons Learned Around DevSecOps
AWS Secret Region – Lessons Learned Around DevSecOpsAmazon Web Services
 
AWS Sydney Summit 2019 Re:Cap
AWS Sydney Summit 2019 Re:CapAWS Sydney Summit 2019 Re:Cap
AWS Sydney Summit 2019 Re:CapInjae Kwak
 
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisions
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisionsai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisions
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better DecisionsAmazon Web Services
 
Building Intelligent Applications Using AI Services
Building Intelligent Applications Using AI ServicesBuilding Intelligent Applications Using AI Services
Building Intelligent Applications Using AI ServicesAmazon Web Services
 
DevOps: The Amazon Way
DevOps: The Amazon WayDevOps: The Amazon Way
DevOps: The Amazon WayAWS Summits
 
Building Like Amazon
Building Like AmazonBuilding Like Amazon
Building Like AmazonAggregage
 
Breaking Up the Monolith with Containers
Breaking Up the Monolith with ContainersBreaking Up the Monolith with Containers
Breaking Up the Monolith with ContainersAmazon Web Services
 
Enabling Cloud Smart, Zero-Trust, and TIC
Enabling Cloud Smart, Zero-Trust, and TICEnabling Cloud Smart, Zero-Trust, and TIC
Enabling Cloud Smart, Zero-Trust, and TICAmazon Web Services
 
Boost your AWS Infrastructure with CDK
Boost your AWS Infrastructure with CDKBoost your AWS Infrastructure with CDK
Boost your AWS Infrastructure with CDKphilippgarbe
 
Build Intelligent Apps Using AI Services.pdf
Build Intelligent Apps Using AI Services.pdfBuild Intelligent Apps Using AI Services.pdf
Build Intelligent Apps Using AI Services.pdfAmazon Web Services
 
Continuous Integration and Continuous Delivery Best Practices for Building Mo...
Continuous Integration and Continuous Delivery Best Practices for Building Mo...Continuous Integration and Continuous Delivery Best Practices for Building Mo...
Continuous Integration and Continuous Delivery Best Practices for Building Mo...Amazon Web Services
 
Getting Started with Serverless Architectures
Getting Started with Serverless ArchitecturesGetting Started with Serverless Architectures
Getting Started with Serverless ArchitecturesAmazon Web Services
 
AI Powered Conversational Interfaces
AI Powered Conversational InterfacesAI Powered Conversational Interfaces
AI Powered Conversational InterfacesAmazon Web Services
 
An Amazonian approach to enterprise transformation
An Amazonian approach to enterprise transformationAn Amazonian approach to enterprise transformation
An Amazonian approach to enterprise transformationAmazon Web Services
 
Getting Started with Serverless Architectures
Getting Started with Serverless ArchitecturesGetting Started with Serverless Architectures
Getting Started with Serverless ArchitecturesAmazon Web Services
 

Similaire à Let a ChatBot do the Heavy Lifting of the Simple Stuff (20)

Making Cloud Procurement Easy with AWS Marketplace, Automation, and Governance
Making Cloud Procurement Easy with AWS Marketplace, Automation, and GovernanceMaking Cloud Procurement Easy with AWS Marketplace, Automation, and Governance
Making Cloud Procurement Easy with AWS Marketplace, Automation, and Governance
 
A Tale of Two Pizzas: Accelerating Software Delivery with AWS Developer Tools
A Tale of Two Pizzas: Accelerating Software Delivery with AWS Developer ToolsA Tale of Two Pizzas: Accelerating Software Delivery with AWS Developer Tools
A Tale of Two Pizzas: Accelerating Software Delivery with AWS Developer Tools
 
AWS Secret Region – Lessons Learned Around DevSecOps
AWS Secret Region – Lessons Learned Around DevSecOpsAWS Secret Region – Lessons Learned Around DevSecOps
AWS Secret Region – Lessons Learned Around DevSecOps
 
AWS Sydney Summit 2019 Re:Cap
AWS Sydney Summit 2019 Re:CapAWS Sydney Summit 2019 Re:Cap
AWS Sydney Summit 2019 Re:Cap
 
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisions
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisionsai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisions
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisions
 
Building Intelligent Applications Using AI Services
Building Intelligent Applications Using AI ServicesBuilding Intelligent Applications Using AI Services
Building Intelligent Applications Using AI Services
 
DevOps: The Amazon Way
DevOps: The Amazon WayDevOps: The Amazon Way
DevOps: The Amazon Way
 
Building Like Amazon
Building Like AmazonBuilding Like Amazon
Building Like Amazon
 
Breaking Up the Monolith with Containers
Breaking Up the Monolith with ContainersBreaking Up the Monolith with Containers
Breaking Up the Monolith with Containers
 
Moving to DevOps the Amazon Way
Moving to DevOps the Amazon WayMoving to DevOps the Amazon Way
Moving to DevOps the Amazon Way
 
Enabling Cloud Smart, Zero-Trust, and TIC
Enabling Cloud Smart, Zero-Trust, and TICEnabling Cloud Smart, Zero-Trust, and TIC
Enabling Cloud Smart, Zero-Trust, and TIC
 
Boost your AWS Infrastructure with CDK
Boost your AWS Infrastructure with CDKBoost your AWS Infrastructure with CDK
Boost your AWS Infrastructure with CDK
 
Build Intelligent Apps Using AI Services.pdf
Build Intelligent Apps Using AI Services.pdfBuild Intelligent Apps Using AI Services.pdf
Build Intelligent Apps Using AI Services.pdf
 
Continuous Integration and Continuous Delivery Best Practices for Building Mo...
Continuous Integration and Continuous Delivery Best Practices for Building Mo...Continuous Integration and Continuous Delivery Best Practices for Building Mo...
Continuous Integration and Continuous Delivery Best Practices for Building Mo...
 
Getting Started with Serverless Architectures
Getting Started with Serverless ArchitecturesGetting Started with Serverless Architectures
Getting Started with Serverless Architectures
 
From Monolith to Microservices
From Monolith to MicroservicesFrom Monolith to Microservices
From Monolith to Microservices
 
AI Powered Conversational Interfaces
AI Powered Conversational InterfacesAI Powered Conversational Interfaces
AI Powered Conversational Interfaces
 
An Amazonian approach to enterprise transformation
An Amazonian approach to enterprise transformationAn Amazonian approach to enterprise transformation
An Amazonian approach to enterprise transformation
 
Getting Started with Serverless Architectures
Getting Started with Serverless ArchitecturesGetting Started with Serverless Architectures
Getting Started with Serverless Architectures
 
Lex and connect
Lex and connectLex and connect
Lex and connect
 

Plus de Amazon Web Services

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Amazon Web Services
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Amazon Web Services
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateAmazon Web Services
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSAmazon Web Services
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Amazon Web Services
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Amazon Web Services
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...Amazon Web Services
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsAmazon Web Services
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareAmazon Web Services
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSAmazon Web Services
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAmazon Web Services
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareAmazon Web Services
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWSAmazon Web Services
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckAmazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without serversAmazon Web Services
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...Amazon Web Services
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceAmazon Web Services
 

Plus de Amazon Web Services (20)

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
 
Fundraising Essentials
Fundraising EssentialsFundraising Essentials
Fundraising Essentials
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
 

Let a ChatBot do the Heavy Lifting of the Simple Stuff

  • 1. P U B L I C S E C T O R S U M M I T C anb er r a, AC T
  • 2. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Let a ChatBot do the Heavy Lifting of the Simple Stuff Kurt Heiz Senior Solutions Architect ANZ Public Sector, AWS
  • 3. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Agenda What is a ChatBot? Amazon Lex Demo Sample use cases and architecture Code
  • 4. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T
  • 5. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T ChatBot definition Wikipedia defines a ChatBot as: “A chatbot is a computer program which conducts a conversation via auditory or textual methods. Such programs are often designed to convincingly simulate how a human would behave as a conversational partner, although as of 2019, they are far short of being able to pass the Turing test” “A Turing test is a method of inquiry in artificial intelligence (AI) for determining whether or not a computer is capable of thinking like a human being.” Developed by Alan Turing in 1950, who cracked the Nazi Enigma code
  • 6. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Amazon Lex • Service to build conversational interfaces • Integrates tightly with other AWS services • Fulfilment using AWS Lambda at two stages • Authentication with IAM or Amazon Cognito • Built in channel support for • Kik • Slack • Twilio • Facebook • Amazon Connect integration
  • 7. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Structure of a ChatBot example
  • 8. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T
  • 9. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T
  • 10. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Sample use case (anonymous user) • Support desk: internal or external • ‘Low hanging fruit’ questions • How do I reset my password for [system]? • What are the term dates? • Where can I find [something] ?
  • 11. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Sample use case (authenticated user) • Support desk: internal or external • ‘Low hanging fruit’ questions • Book an appointment with [person] for [date] at [time] • How many days [leaveType] do I have? • Spin up a new [environmentType] for [solutionName]
  • 12. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Our sample use case scenario • External support desk (anonymous user) • Business problem • Customers are currently waiting up to one hour to have simple questions answered • Estimates that offloading the simple questions could save call wait times by up to 66% • Channels in use: • Telephone • Facebook Messenger • Proposal • Create a ChatBot to answer simple questions as defined by the business, using existing call logs to define those questions • Introduce a new interface, web, and integrate with FB • Leave telephone integration to future phase once ChatBot has proven itself in two to three months • Where do we start?
  • 13. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Where do we start? • Define a goal • “Assist new students with basic tasks and finding their way around campus” • Define intents from top simple requests, aim for between 5-10 • Action or Assistance based – be sure to make use of slots • Sample utterances for training • Where can answers and responses be found? • Technical architecture • Operational support • Continuous training and updating of ChatBot • Set expectations for users upfront about limits of ChatBot capability
  • 14. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Test – train – test (ensure it understands correctly) • Create an automated testing regime • Ensure expected intent is matched and correct answer is given • Create list of non-trained utterances with expected positive and negative matches • Learn about the confusion matrix
  • 15. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Confusion matrix • A confusion matrix is a table that is often used to describe the performance of a classification model (or "classifier") on a set of test data for which the true values are known.
  • 16. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T Technical serverless architecture option AWS Cloud Customer desktop client Amazon API Gateway AWS Lambda Amazon Lex AWS Lambda AWS Lambda Amazon DynamoDB Amazon Elasticsearch Service Customer mobile client Amazon Kinesis Data Firehose Support desktop client Amazon Cognito
  • 17. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T What more can the interceptor do for you? AWS Cloud Desktop client Amazon API Gateway AWS Lambda Amazon Lex AWS Lambda AWS Lambda Amazon DynamoDB Amazon Elasticsearch Service Mobile client Amazon Kinesis Data Firehose Desktop client Amazon Cognito Amazon Translate Amazon Comprehend Third Party web chat systems e.g. LiveChat
  • 18. © 2019, Amazon Web Services, Inc. or its affiliates. All rights reserved.P U B L I C S E C T O R S U M M I T DynamoDB sample table structure • Table can be generic to handle any intent and slot values