SlideShare une entreprise Scribd logo
1  sur  44
© 2016, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Alex Smith – Amazon Web Services
Jo-Anne Tan – Gowild.sg
JAWS DAYS 2017
Singapore AWS User Group
Amazon Lex
AWS User Groups
AWS User Groups – ASEAN
ASEAN
10 Member States
• SG, TH, VN, ID, PH, MY,
MM, KH, LA, BN
https://aws.amazon.com/usergroups/
AWS User Groups – ASEAN
Jakarta (Indonesia)
Kuala Lumpur (Malaysia)
Manila (Philippines)
Singapore
Bangkok (Thailand)
Hanoi (Viet Nam)
https://aws.amazon.com/usergroups/
AWS User Group - Singapore
The “Little Red Dot”
5.75 Million
• 3.9m Citizen/PR
• 1.6m Other
!= China
AWS User Group - Singapore
4 Languages (-and more)
Asia Pacific Hub
“Kiasu”
Restarted regular meetings
Restarted regular meetings
Passed 1000 members
(2016-01-08)
Restarted regular meetings
Passed 1000 members
(2016-01-08)
Changed to a better quality pizza
shop
What worked well
Regularity of meetings
Good venue & AV
Engineers.sg
Engineers.sg
• Oct 2013 – PHP UG
• >1200 videos
• 40 Strong Team
• More info:
https://alexjs.co/engineers
http://engineers.sg
What worked well
Regularity of meetings
Good venue & AV
Engineers.sg
What worked well
Regularity of meetings
Good venue & AV
Engineers.sg
Beer
What didn’t work well
AWS driven group
Huge variance in talk quality
Attendance/RSVP discrepancy
What’s next?
AWS User Group SG links:
https://www.facebook.com/groups/awsugsg/
https://www.meetup.com/AWS-SG/
https://engineers.sg
What didn’t work well
AWS driven group
Huge variance in talk quality
Attendance/RSVP discrepancy
Attendance vs RSVP Discrepancy
User intent vs intended usage
The trash can analogy
Reduce the effort to comply
Amazon Lex
Why Did We Build
Amazon Lex?
Advent of Conversational Interactions
1st Gen:
Punch Cards & Memory Registers
2nd Gen:
Pointers & Sliders
3nd Gen:
Conversational Interfaces
Conversational Access
On-Demand
Accessible
Efficient
Natural
Conversational Access
On-Demand
Accessible
Efficient
Natural
Developer Challenges
Speech
Recognition Language
Understanding
Business Logic
Disparate
Systems
Authentication
Messaging
platforms
Scale Testing
Security
Availability
Mobile
Conversational interfaces need to combine a large number of
sophisticated algorithms and technologies
Amazon Lex: New service for building
conversational interfaces using voice and
text
Amazon Lex - Features
Text and Speech language understanding: Powered by the same technology as
Alexa
Enterprise SaaS Connectors: Connect to enterprise systems
Deployment to chat services
Designed for Builders: Efficient and intuitive tools to build
conversations; scales automatically
Versioning and alias support
Text and Speech Language Understanding
Speech
Recognition
Natural Language
Understanding
Powered by the same Deep Learning technology as Alexa
Amazon Lex – Use Cases
Informational Bots
Chatbots for everyday consumer requests
Application Bots
Build powerful interfaces to mobile applications
• News updates
• Weather information
• Game scores ….
• Book tickets
• Order food
• Manage bank accounts ….
Enterprise Productivity Bots
Streamline enterprise work activities and improve efficiencies
• Check sales numbers
• Marketing performance
• Inventory status ….
Internet of Things (IoT) Bots
Enable conversational interfaces for device interactions
• Wearables
• Appliances
• Auto ….
Amazon Lex - Benefits
High quality Text and Speech Language
Understanding
Built-in integration with the AWS platform
Seamlessly deploy and scale
Easy to use
Cost effective
Lex Bot Structure
Utterances
Spoken or typed phrases that invoke
your intent
BookHotel
Intents
An Intent performs an action in
response to natural language user input
Slots
Slots are input data required to fulfill the
intent
Fulfillment
Fulfillment mechanism for your intent
User input Response
Lex Bot Structure: Utterances
Attend the user group
Come to the meet up
User inputs:
I want to come to the next
meetup
Could I attend the next user
group please
Maps to RegisterUserForEvent intent
RegisterUserForEvent intent
UTTERANCES
Lex Bot Structure: Utterances
Attend the user group on
{eventDate}
Come to the meet up on
{eventDate}
User inputs:
I want to come to the next
meetup on 12 March 2017
Could I attend the user group
tomorrow please
Maps to RegisterUserForEvent intent;
eventDate=2017-12-03
RegisterUserForEvent intent
UTTERANCES
SLOTS
eventDate AMAZON.DATE
SLOT NAME SLOT TYPE
Lex Bot Structure: Fulfilment
RegisterUserForEvent
eventDate=2017-03-12
SLOT
INTENT
AWS Lambda Integration
Intents and slots
passed to AWS
Lambda function for
business logic
implementation.
Return to Client
Lambda input event
{
...,
"invocationSource": "FulfillmentCodeHook or DialogCodeHook",
"userId": "user-id",
"bot": {...},
"outputDialogMode": "Text or Voice”,
"currentIntent": {
"name": "intent-name",
"slots": {
"slot-name": "value",
"slot-name": "value",
"slot-name": "value"
},
"confirmationStatus": "None, Confirmed, or Denied"
}
}
Lambda response object
{
...,
"dialogAction": {
"type": "ElicitIntent, ElicitSlot, ConfirmIntent, Delegate, or Close",
"fulfillmentState": "Fulfilled or Failed",
"message": {
"contentType": "PlainText or SSML",
"content": "message to convey to the user"
},
"intentName": "intent-name",
"slots": {
"slot-name": "value",
"slot-name": "value",
"slot-name": "value"
},
"slotToElicit" : "slot-name",
}
Response card
{
...,
responseCard: {
"version": 1,
"contentType":
"application/vnd.amazonaws.card.generic",
"genericAttachments": [
{
"title": "Flowers",
"subTitle": “Pick a flower”,
"imageUrl: "…",
"buttons": [
{"text": "tulips","value": "tulips"},
{"text": "lilies","value": "lilies"},
{"text": "roses","value": "roses"}
]
}
]
}
Pick a flower
“Attend an Event”
Attend event
12 March
“Attend the event on
12 March”
Automatic Speech
Recognition
Natural Language
Understanding
Intent/Slot
Model
Utterances
“You are now confirmed for the
next event on 12th March”
Polly
the
on RegisterUserForEvent
eventDate
SLOT
INTENT
Validate
eventDate
slot value
“You are now confirmed for the
event on 12th March”
Update DB
“Attend an Event”
Attend event
12 March
“Attend the event on
12 March”
Automatic Speech
Recognition
Natural Language
Understanding
Intent/Slot
Model
Utterances
“You are now confirmed for the
next event on 12th March”
Polly
the
on RegisterUserForEvent
eventDate
SLOT
INTENT
Validate
eventDate
slot value
“You are now confirmed for the
event on 12th March”
Update DB
“Attend an Event”
Attend event
12 March
“Attend the event on
12 March”
Automatic Speech
Recognition
Natural Language
Understanding
Intent/Slot
Model
Utterances
“You are now confirmed for the
next event on 12th March”
Polly
the
on RegisterUserForEvent
eventDate
SLOT
INTENT
Validate
eventDate
slot value
“You are now confirmed for the
event on 12th March”
Update DB
“Attend an Event”
Attend event
12 March
“Attend the event on
12 March”
Automatic Speech
Recognition
Natural Language
Understanding
Intent/Slot
Model
Utterances
“You are now confirmed for the
next event on 12th March”
Polly
the
on RegisterUserForEvent
eventDate
SLOT
INTENT
Validate
eventDate
slot value
“You are now confirmed for the
event on 12th March”
Update DB
Event Manager Bot: Flow of Information
GetUpcomingEvent
INTENT
GetUpcomingEventAgenda
eventDate
SLOT
INTENT
RegisterUserForEvent
eventDate
SLOT
INTENTList summary of all events
Show details for event on
{eventDate}
Register user for event on
eventDate}
Event Manager Bot: Flow of Information
GetUpcomingEvent
INTENT
GetUpcomingEventAgenda
eventDate
SLOT
INTENT
RegisterUserForEvent
eventDate
SLOT
INTENT
Do you want to hear
more?
YES
NO
“Okay. Bye!”
?
Thank You!
http://aws.amazon.com/lex

Contenu connexe

Tendances

Building speech enabled products with Amazon Polly & Amazon Lex
Building speech enabled products with Amazon Polly & Amazon LexBuilding speech enabled products with Amazon Polly & Amazon Lex
Building speech enabled products with Amazon Polly & Amazon Lex
Amazon Web Services
 
Building Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon LexBuilding Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon Lex
Amazon Web Services
 
AWS re:Invent 2016: Alexa in the Enterprise: How JPL Leverages Alexa to Furth...
AWS re:Invent 2016: Alexa in the Enterprise: How JPL Leverages Alexa to Furth...AWS re:Invent 2016: Alexa in the Enterprise: How JPL Leverages Alexa to Furth...
AWS re:Invent 2016: Alexa in the Enterprise: How JPL Leverages Alexa to Furth...
Amazon Web Services
 

Tendances (20)

Building a Better Chatbot with Amazon Lex and Polly
Building a Better Chatbot with Amazon Lex and PollyBuilding a Better Chatbot with Amazon Lex and Polly
Building a Better Chatbot with Amazon Lex and Polly
 
AWS re:Invent 2016: NEW LAUNCH! Introducing Amazon Lex (MAC304)
AWS re:Invent 2016: NEW LAUNCH! Introducing Amazon Lex (MAC304)AWS re:Invent 2016: NEW LAUNCH! Introducing Amazon Lex (MAC304)
AWS re:Invent 2016: NEW LAUNCH! Introducing Amazon Lex (MAC304)
 
Building Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon LexBuilding Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon Lex
 
Building a Better Chatbot with Amazon Lex & Amazon Polly
Building a Better Chatbot with Amazon Lex & Amazon PollyBuilding a Better Chatbot with Amazon Lex & Amazon Polly
Building a Better Chatbot with Amazon Lex & Amazon Polly
 
Integrate Your Amazon Lex Chatbot with Any Messaging Service
Integrate Your Amazon Lex Chatbot with Any Messaging ServiceIntegrate Your Amazon Lex Chatbot with Any Messaging Service
Integrate Your Amazon Lex Chatbot with Any Messaging Service
 
Building a Chatbot with Amazon Lex and AWS Lambda Workshop
Building a Chatbot with Amazon Lex and AWS Lambda WorkshopBuilding a Chatbot with Amazon Lex and AWS Lambda Workshop
Building a Chatbot with Amazon Lex and AWS Lambda Workshop
 
AWS re:Invent 2016: Workshop: Building Serverless Bots on AWS - Botathon (DCS...
AWS re:Invent 2016: Workshop: Building Serverless Bots on AWS - Botathon (DCS...AWS re:Invent 2016: Workshop: Building Serverless Bots on AWS - Botathon (DCS...
AWS re:Invent 2016: Workshop: Building Serverless Bots on AWS - Botathon (DCS...
 
Learn How to Build a Bot for Voice and Text with Amazon Lex and Amazon Polly
Learn How to Build a Bot for Voice and Text with Amazon Lex and Amazon PollyLearn How to Build a Bot for Voice and Text with Amazon Lex and Amazon Polly
Learn How to Build a Bot for Voice and Text with Amazon Lex and Amazon Polly
 
Building Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon LexBuilding Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon Lex
 
Deep Dive: Amazon Lex
Deep Dive: Amazon LexDeep Dive: Amazon Lex
Deep Dive: Amazon Lex
 
Building speech enabled products with Amazon Polly & Amazon Lex
Building speech enabled products with Amazon Polly & Amazon LexBuilding speech enabled products with Amazon Polly & Amazon Lex
Building speech enabled products with Amazon Polly & Amazon Lex
 
Building Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon LexBuilding Speech Enabled Products with Amazon Polly & Amazon Lex
Building Speech Enabled Products with Amazon Polly & Amazon Lex
 
Integrate Your Amazon Lex Chatbot with Any Messaging Service - AWS Online Tec...
Integrate Your Amazon Lex Chatbot with Any Messaging Service - AWS Online Tec...Integrate Your Amazon Lex Chatbot with Any Messaging Service - AWS Online Tec...
Integrate Your Amazon Lex Chatbot with Any Messaging Service - AWS Online Tec...
 
Chatbot
ChatbotChatbot
Chatbot
 
Building ChatBots with Amazon Lex - AWS Summit Tel Aviv 2017
Building ChatBots with Amazon Lex - AWS Summit Tel Aviv 2017Building ChatBots with Amazon Lex - AWS Summit Tel Aviv 2017
Building ChatBots with Amazon Lex - AWS Summit Tel Aviv 2017
 
Introduzione ad Amazon Lex
Introduzione ad Amazon LexIntroduzione ad Amazon Lex
Introduzione ad Amazon Lex
 
Amazon Rekognition & Amazon Polly
Amazon Rekognition & Amazon PollyAmazon Rekognition & Amazon Polly
Amazon Rekognition & Amazon Polly
 
AWS re:Invent 2016: Workshop: Build an Alexa-Enabled Product with Raspberry P...
AWS re:Invent 2016: Workshop: Build an Alexa-Enabled Product with Raspberry P...AWS re:Invent 2016: Workshop: Build an Alexa-Enabled Product with Raspberry P...
AWS re:Invent 2016: Workshop: Build an Alexa-Enabled Product with Raspberry P...
 
Empowering Customer Service with Cloud Telephony & AI
Empowering Customer Service with Cloud Telephony & AIEmpowering Customer Service with Cloud Telephony & AI
Empowering Customer Service with Cloud Telephony & AI
 
AWS re:Invent 2016: Alexa in the Enterprise: How JPL Leverages Alexa to Furth...
AWS re:Invent 2016: Alexa in the Enterprise: How JPL Leverages Alexa to Furth...AWS re:Invent 2016: Alexa in the Enterprise: How JPL Leverages Alexa to Furth...
AWS re:Invent 2016: Alexa in the Enterprise: How JPL Leverages Alexa to Furth...
 

En vedette

APIを叩くだけでない、Deep Learning on AWS で自分だけの学習モデルを作ろう! by JAWS-UG AI支部
APIを叩くだけでない、Deep Learning on AWS で自分だけの学習モデルを作ろう! by JAWS-UG AI支部APIを叩くだけでない、Deep Learning on AWS で自分だけの学習モデルを作ろう! by JAWS-UG AI支部
APIを叩くだけでない、Deep Learning on AWS で自分だけの学習モデルを作ろう! by JAWS-UG AI支部
Daisuke Nagao
 
AWSを学ぶための取り組み
AWSを学ぶための取り組みAWSを学ぶための取り組み
AWSを学ぶための取り組み
hideaki yanase
 

En vedette (20)

APIを叩くだけでない、Deep Learning on AWS で自分だけの学習モデルを作ろう! by JAWS-UG AI支部
APIを叩くだけでない、Deep Learning on AWS で自分だけの学習モデルを作ろう! by JAWS-UG AI支部APIを叩くだけでない、Deep Learning on AWS で自分だけの学習モデルを作ろう! by JAWS-UG AI支部
APIを叩くだけでない、Deep Learning on AWS で自分だけの学習モデルを作ろう! by JAWS-UG AI支部
 
Jawsdays2017 slide share
Jawsdays2017 slide shareJawsdays2017 slide share
Jawsdays2017 slide share
 
mizuderuからnekoderuへ
mizuderuからnekoderuへmizuderuからnekoderuへ
mizuderuからnekoderuへ
 
Awsで温暖化予想?!
Awsで温暖化予想?!Awsで温暖化予想?!
Awsで温暖化予想?!
 
AWSでアプリ開発するなら 知っておくべこと
AWSでアプリ開発するなら 知っておくべことAWSでアプリ開発するなら 知っておくべこと
AWSでアプリ開発するなら 知っておくべこと
 
JAWS DAYS 2017 / SORACOM UGで発表されたLTやブログを紹介しちゃうよ!!
JAWS DAYS 2017 / SORACOM UGで発表されたLTやブログを紹介しちゃうよ!!JAWS DAYS 2017 / SORACOM UGで発表されたLTやブログを紹介しちゃうよ!!
JAWS DAYS 2017 / SORACOM UGで発表されたLTやブログを紹介しちゃうよ!!
 
子ども向けプログラミング道場を運営してみたお話し〜CoderDojo長岡京と、時々、EC2〜
子ども向けプログラミング道場を運営してみたお話し〜CoderDojo長岡京と、時々、EC2〜子ども向けプログラミング道場を運営してみたお話し〜CoderDojo長岡京と、時々、EC2〜
子ども向けプログラミング道場を運営してみたお話し〜CoderDojo長岡京と、時々、EC2〜
 
サーバーレスの今とこれから
サーバーレスの今とこれからサーバーレスの今とこれから
サーバーレスの今とこれから
 
JAWSDAYS2017 新訳 とあるアーキテクトのクラウドデザインパターン目録 AMI Maintenance Environment
JAWSDAYS2017 新訳 とあるアーキテクトのクラウドデザインパターン目録 AMI Maintenance EnvironmentJAWSDAYS2017 新訳 とあるアーキテクトのクラウドデザインパターン目録 AMI Maintenance Environment
JAWSDAYS2017 新訳 とあるアーキテクトのクラウドデザインパターン目録 AMI Maintenance Environment
 
SlideShare 101
SlideShare 101SlideShare 101
SlideShare 101
 
20170311 jawsdays 新訳 とあるアーキテクトのクラウドデザインパターン目録
20170311 jawsdays 新訳 とあるアーキテクトのクラウドデザインパターン目録20170311 jawsdays 新訳 とあるアーキテクトのクラウドデザインパターン目録
20170311 jawsdays 新訳 とあるアーキテクトのクラウドデザインパターン目録
 
jawsdays 2017 新訳-とある設計士の雲設計定石目録_3
jawsdays 2017 新訳-とある設計士の雲設計定石目録_3jawsdays 2017 新訳-とある設計士の雲設計定石目録_3
jawsdays 2017 新訳-とある設計士の雲設計定石目録_3
 
Jawsdays2017(配布用)
Jawsdays2017(配布用)Jawsdays2017(配布用)
Jawsdays2017(配布用)
 
AWSKRUGの現状 (Sanguk Park) - JAWS Days 2017
AWSKRUGの現状 (Sanguk Park) - JAWS Days 2017AWSKRUGの現状 (Sanguk Park) - JAWS Days 2017
AWSKRUGの現状 (Sanguk Park) - JAWS Days 2017
 
Cross-regional Application Deplolyment on AWS - Channy Yun (JAWS Days 2017)
Cross-regional Application Deplolyment on AWS - Channy Yun (JAWS Days 2017)Cross-regional Application Deplolyment on AWS - Channy Yun (JAWS Days 2017)
Cross-regional Application Deplolyment on AWS - Channy Yun (JAWS Days 2017)
 
Jaws days2017-ops jaws-2
Jaws days2017-ops jaws-2Jaws days2017-ops jaws-2
Jaws days2017-ops jaws-2
 
20170328-jaws days linked us to the super power
20170328-jaws days linked us to the super power20170328-jaws days linked us to the super power
20170328-jaws days linked us to the super power
 
EBS-1 Grand Prix
EBS-1 Grand PrixEBS-1 Grand Prix
EBS-1 Grand Prix
 
激震!これが本当のクラウドだ!
激震!これが本当のクラウドだ!激震!これが本当のクラウドだ!
激震!これが本当のクラウドだ!
 
AWSを学ぶための取り組み
AWSを学ぶための取り組みAWSを学ぶための取り組み
AWSを学ぶための取り組み
 

Similaire à AWS User Group Singapore / Amazon Lex -- JAWSDAYS 2017

Similaire à AWS User Group Singapore / Amazon Lex -- JAWSDAYS 2017 (20)

Introducing Amazon Lex
Introducing Amazon Lex Introducing Amazon Lex
Introducing Amazon Lex
 
使用 Amazon Lex 在應用程式中建立對話式機器人
使用 Amazon Lex 在應用程式中建立對話式機器人 使用 Amazon Lex 在應用程式中建立對話式機器人
使用 Amazon Lex 在應用程式中建立對話式機器人
 
AWS re:Invent 2016: bots + serverless = ❤ (SVR304)
AWS re:Invent 2016: bots + serverless = ❤ (SVR304)AWS re:Invent 2016: bots + serverless = ❤ (SVR304)
AWS re:Invent 2016: bots + serverless = ❤ (SVR304)
 
BDA310 An Introduction to the AI services at AWS
BDA310 An Introduction to the AI services at AWSBDA310 An Introduction to the AI services at AWS
BDA310 An Introduction to the AI services at AWS
 
WIN205-Building a Better .NET Bot with AWS Services
WIN205-Building a Better .NET Bot with AWS ServicesWIN205-Building a Better .NET Bot with AWS Services
WIN205-Building a Better .NET Bot with AWS Services
 
Building a Better .NET Bot with AWS Services - WIN205 - re:Invent 2017
Building a Better .NET Bot with AWS Services - WIN205 - re:Invent 2017Building a Better .NET Bot with AWS Services - WIN205 - re:Invent 2017
Building a Better .NET Bot with AWS Services - WIN205 - re:Invent 2017
 
BDA306 An Introduction to Amazon Lex, your Service for Building Voice and Tex...
BDA306 An Introduction to Amazon Lex, your Service for Building Voice and Tex...BDA306 An Introduction to Amazon Lex, your Service for Building Voice and Tex...
BDA306 An Introduction to Amazon Lex, your Service for Building Voice and Tex...
 
Serve Your Customers with AI from the Cloud: AWS Developer Workshop - Web Sum...
Serve Your Customers with AI from the Cloud: AWS Developer Workshop - Web Sum...Serve Your Customers with AI from the Cloud: AWS Developer Workshop - Web Sum...
Serve Your Customers with AI from the Cloud: AWS Developer Workshop - Web Sum...
 
AWS Artificial Intelligence Day - Toronto
AWS Artificial Intelligence Day - TorontoAWS Artificial Intelligence Day - Toronto
AWS Artificial Intelligence Day - Toronto
 
Amazon Web Services - Strategy and Current Offering
Amazon Web Services - Strategy and Current OfferingAmazon Web Services - Strategy and Current Offering
Amazon Web Services - Strategy and Current Offering
 
Integrate Your Amazon Lex Chatbot with Any Messaging Service - AWS Online Tec...
Integrate Your Amazon Lex Chatbot with Any Messaging Service - AWS Online Tec...Integrate Your Amazon Lex Chatbot with Any Messaging Service - AWS Online Tec...
Integrate Your Amazon Lex Chatbot with Any Messaging Service - AWS Online Tec...
 
Building Chatbots with Amazon Lex I AWS Dev Day 2018
Building Chatbots with Amazon Lex I AWS Dev Day 2018Building Chatbots with Amazon Lex I AWS Dev Day 2018
Building Chatbots with Amazon Lex I AWS Dev Day 2018
 
BDA306 NEW LAUNCH! An Introduction to Amazon Lex, your service for building v...
BDA306 NEW LAUNCH! An Introduction to Amazon Lex, your service for building v...BDA306 NEW LAUNCH! An Introduction to Amazon Lex, your service for building v...
BDA306 NEW LAUNCH! An Introduction to Amazon Lex, your service for building v...
 
Building voice enabled Apps with Alexa voice service and Amazon Lex.
Building voice enabled Apps with Alexa voice service and Amazon Lex.     Building voice enabled Apps with Alexa voice service and Amazon Lex.
Building voice enabled Apps with Alexa voice service and Amazon Lex.
 
New Artificial Intelligence and IoT Services (Lex, Polly, Rekognition, Greeng...
New Artificial Intelligence and IoT Services (Lex, Polly, Rekognition, Greeng...New Artificial Intelligence and IoT Services (Lex, Polly, Rekognition, Greeng...
New Artificial Intelligence and IoT Services (Lex, Polly, Rekognition, Greeng...
 
re:Invent Recap keynote - An introduction to the latest AWS services
re:Invent Recap keynote  - An introduction to the latest AWS servicesre:Invent Recap keynote  - An introduction to the latest AWS services
re:Invent Recap keynote - An introduction to the latest AWS services
 
Build Your Own Search Engine
Build Your Own Search EngineBuild Your Own Search Engine
Build Your Own Search Engine
 
AWS re:Invent 2016: All Your Chats are Belong to Bots: Building a Serverless ...
AWS re:Invent 2016: All Your Chats are Belong to Bots: Building a Serverless ...AWS re:Invent 2016: All Your Chats are Belong to Bots: Building a Serverless ...
AWS re:Invent 2016: All Your Chats are Belong to Bots: Building a Serverless ...
 
Build a Voice-based Chatbot for Your Amazon Connect Contact Center - SRV326 -...
Build a Voice-based Chatbot for Your Amazon Connect Contact Center - SRV326 -...Build a Voice-based Chatbot for Your Amazon Connect Contact Center - SRV326 -...
Build a Voice-based Chatbot for Your Amazon Connect Contact Center - SRV326 -...
 
Everything You Need to Develop Apps Faster and Scale to Millions of Users
Everything You Need to Develop Apps Faster and Scale to Millions of UsersEverything You Need to Develop Apps Faster and Scale to Millions of Users
Everything You Need to Develop Apps Faster and Scale to Millions of Users
 

Dernier

CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
mohitmore19
 

Dernier (20)

Chinsurah Escorts ☎️8617697112 Starting From 5K to 15K High Profile Escorts ...
Chinsurah Escorts ☎️8617697112  Starting From 5K to 15K High Profile Escorts ...Chinsurah Escorts ☎️8617697112  Starting From 5K to 15K High Profile Escorts ...
Chinsurah Escorts ☎️8617697112 Starting From 5K to 15K High Profile Escorts ...
 
BUS PASS MANGEMENT SYSTEM USING PHP.pptx
BUS PASS MANGEMENT SYSTEM USING PHP.pptxBUS PASS MANGEMENT SYSTEM USING PHP.pptx
BUS PASS MANGEMENT SYSTEM USING PHP.pptx
 
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfLearn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
 
ManageIQ - Sprint 236 Review - Slide Deck
ManageIQ - Sprint 236 Review - Slide DeckManageIQ - Sprint 236 Review - Slide Deck
ManageIQ - Sprint 236 Review - Slide Deck
 
Exploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdfExploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdf
 
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfThe Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTV
 
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdfAzure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
 
10 Trends Likely to Shape Enterprise Technology in 2024
10 Trends Likely to Shape Enterprise Technology in 202410 Trends Likely to Shape Enterprise Technology in 2024
10 Trends Likely to Shape Enterprise Technology in 2024
 
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Sector 18, Noida Call girls :8448380779 Model Escorts | 100% verified
Sector 18, Noida Call girls :8448380779 Model Escorts | 100% verifiedSector 18, Noida Call girls :8448380779 Model Escorts | 100% verified
Sector 18, Noida Call girls :8448380779 Model Escorts | 100% verified
 
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
 
MarTech Trend 2024 Book : Marketing Technology Trends (2024 Edition) How Data...
MarTech Trend 2024 Book : Marketing Technology Trends (2024 Edition) How Data...MarTech Trend 2024 Book : Marketing Technology Trends (2024 Edition) How Data...
MarTech Trend 2024 Book : Marketing Technology Trends (2024 Edition) How Data...
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview Questions
 
Right Money Management App For Your Financial Goals
Right Money Management App For Your Financial GoalsRight Money Management App For Your Financial Goals
Right Money Management App For Your Financial Goals
 
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
 
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
Direct Style Effect Systems -The Print[A] Example- A Comprehension AidDirect Style Effect Systems -The Print[A] Example- A Comprehension Aid
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
 
VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learn
 
Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time ApplicationsUnveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
 

AWS User Group Singapore / Amazon Lex -- JAWSDAYS 2017

  • 1. © 2016, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Alex Smith – Amazon Web Services Jo-Anne Tan – Gowild.sg JAWS DAYS 2017 Singapore AWS User Group Amazon Lex
  • 3. AWS User Groups – ASEAN ASEAN 10 Member States • SG, TH, VN, ID, PH, MY, MM, KH, LA, BN https://aws.amazon.com/usergroups/
  • 4. AWS User Groups – ASEAN Jakarta (Indonesia) Kuala Lumpur (Malaysia) Manila (Philippines) Singapore Bangkok (Thailand) Hanoi (Viet Nam) https://aws.amazon.com/usergroups/
  • 5. AWS User Group - Singapore The “Little Red Dot” 5.75 Million • 3.9m Citizen/PR • 1.6m Other != China
  • 6. AWS User Group - Singapore 4 Languages (-and more) Asia Pacific Hub “Kiasu”
  • 7.
  • 9. Restarted regular meetings Passed 1000 members (2016-01-08)
  • 10. Restarted regular meetings Passed 1000 members (2016-01-08) Changed to a better quality pizza shop
  • 11. What worked well Regularity of meetings Good venue & AV Engineers.sg
  • 12. Engineers.sg • Oct 2013 – PHP UG • >1200 videos • 40 Strong Team • More info: https://alexjs.co/engineers http://engineers.sg
  • 13. What worked well Regularity of meetings Good venue & AV Engineers.sg
  • 14. What worked well Regularity of meetings Good venue & AV Engineers.sg Beer
  • 15. What didn’t work well AWS driven group Huge variance in talk quality Attendance/RSVP discrepancy
  • 17. AWS User Group SG links: https://www.facebook.com/groups/awsugsg/ https://www.meetup.com/AWS-SG/ https://engineers.sg
  • 18. What didn’t work well AWS driven group Huge variance in talk quality Attendance/RSVP discrepancy
  • 19. Attendance vs RSVP Discrepancy User intent vs intended usage The trash can analogy Reduce the effort to comply
  • 21. Why Did We Build Amazon Lex?
  • 22. Advent of Conversational Interactions 1st Gen: Punch Cards & Memory Registers 2nd Gen: Pointers & Sliders 3nd Gen: Conversational Interfaces
  • 25. Developer Challenges Speech Recognition Language Understanding Business Logic Disparate Systems Authentication Messaging platforms Scale Testing Security Availability Mobile Conversational interfaces need to combine a large number of sophisticated algorithms and technologies
  • 26. Amazon Lex: New service for building conversational interfaces using voice and text
  • 27. Amazon Lex - Features Text and Speech language understanding: Powered by the same technology as Alexa Enterprise SaaS Connectors: Connect to enterprise systems Deployment to chat services Designed for Builders: Efficient and intuitive tools to build conversations; scales automatically Versioning and alias support
  • 28. Text and Speech Language Understanding Speech Recognition Natural Language Understanding Powered by the same Deep Learning technology as Alexa
  • 29. Amazon Lex – Use Cases Informational Bots Chatbots for everyday consumer requests Application Bots Build powerful interfaces to mobile applications • News updates • Weather information • Game scores …. • Book tickets • Order food • Manage bank accounts …. Enterprise Productivity Bots Streamline enterprise work activities and improve efficiencies • Check sales numbers • Marketing performance • Inventory status …. Internet of Things (IoT) Bots Enable conversational interfaces for device interactions • Wearables • Appliances • Auto ….
  • 30. Amazon Lex - Benefits High quality Text and Speech Language Understanding Built-in integration with the AWS platform Seamlessly deploy and scale Easy to use Cost effective
  • 31. Lex Bot Structure Utterances Spoken or typed phrases that invoke your intent BookHotel Intents An Intent performs an action in response to natural language user input Slots Slots are input data required to fulfill the intent Fulfillment Fulfillment mechanism for your intent User input Response
  • 32. Lex Bot Structure: Utterances Attend the user group Come to the meet up User inputs: I want to come to the next meetup Could I attend the next user group please Maps to RegisterUserForEvent intent RegisterUserForEvent intent UTTERANCES
  • 33. Lex Bot Structure: Utterances Attend the user group on {eventDate} Come to the meet up on {eventDate} User inputs: I want to come to the next meetup on 12 March 2017 Could I attend the user group tomorrow please Maps to RegisterUserForEvent intent; eventDate=2017-12-03 RegisterUserForEvent intent UTTERANCES SLOTS eventDate AMAZON.DATE SLOT NAME SLOT TYPE
  • 34. Lex Bot Structure: Fulfilment RegisterUserForEvent eventDate=2017-03-12 SLOT INTENT AWS Lambda Integration Intents and slots passed to AWS Lambda function for business logic implementation. Return to Client
  • 35. Lambda input event { ..., "invocationSource": "FulfillmentCodeHook or DialogCodeHook", "userId": "user-id", "bot": {...}, "outputDialogMode": "Text or Voice”, "currentIntent": { "name": "intent-name", "slots": { "slot-name": "value", "slot-name": "value", "slot-name": "value" }, "confirmationStatus": "None, Confirmed, or Denied" } }
  • 36. Lambda response object { ..., "dialogAction": { "type": "ElicitIntent, ElicitSlot, ConfirmIntent, Delegate, or Close", "fulfillmentState": "Fulfilled or Failed", "message": { "contentType": "PlainText or SSML", "content": "message to convey to the user" }, "intentName": "intent-name", "slots": { "slot-name": "value", "slot-name": "value", "slot-name": "value" }, "slotToElicit" : "slot-name", }
  • 37. Response card { ..., responseCard: { "version": 1, "contentType": "application/vnd.amazonaws.card.generic", "genericAttachments": [ { "title": "Flowers", "subTitle": “Pick a flower”, "imageUrl: "…", "buttons": [ {"text": "tulips","value": "tulips"}, {"text": "lilies","value": "lilies"}, {"text": "roses","value": "roses"} ] } ] } Pick a flower
  • 38. “Attend an Event” Attend event 12 March “Attend the event on 12 March” Automatic Speech Recognition Natural Language Understanding Intent/Slot Model Utterances “You are now confirmed for the next event on 12th March” Polly the on RegisterUserForEvent eventDate SLOT INTENT Validate eventDate slot value “You are now confirmed for the event on 12th March” Update DB
  • 39. “Attend an Event” Attend event 12 March “Attend the event on 12 March” Automatic Speech Recognition Natural Language Understanding Intent/Slot Model Utterances “You are now confirmed for the next event on 12th March” Polly the on RegisterUserForEvent eventDate SLOT INTENT Validate eventDate slot value “You are now confirmed for the event on 12th March” Update DB
  • 40. “Attend an Event” Attend event 12 March “Attend the event on 12 March” Automatic Speech Recognition Natural Language Understanding Intent/Slot Model Utterances “You are now confirmed for the next event on 12th March” Polly the on RegisterUserForEvent eventDate SLOT INTENT Validate eventDate slot value “You are now confirmed for the event on 12th March” Update DB
  • 41. “Attend an Event” Attend event 12 March “Attend the event on 12 March” Automatic Speech Recognition Natural Language Understanding Intent/Slot Model Utterances “You are now confirmed for the next event on 12th March” Polly the on RegisterUserForEvent eventDate SLOT INTENT Validate eventDate slot value “You are now confirmed for the event on 12th March” Update DB
  • 42. Event Manager Bot: Flow of Information GetUpcomingEvent INTENT GetUpcomingEventAgenda eventDate SLOT INTENT RegisterUserForEvent eventDate SLOT INTENTList summary of all events Show details for event on {eventDate} Register user for event on eventDate}
  • 43. Event Manager Bot: Flow of Information GetUpcomingEvent INTENT GetUpcomingEventAgenda eventDate SLOT INTENT RegisterUserForEvent eventDate SLOT INTENT Do you want to hear more? YES NO “Okay. Bye!” ?