SlideShare uma empresa Scribd logo
1 de 38
Baixar para ler offline
© 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Rebeker Choi, Solutions Architect
15-Sep, 2017
Building an AI-based service
with Rekognition, Polly, and Lex
The Challenge for Artificial Intelligence: SCALE
Tons of GPUs and CPUs
Prediction
Tons of GPUs
TrainingData
PBs of existing data
AWS is the Center of Gravity for
Artificial Intelligence
Amazon AI
Intelligent Services Powered by Deep Learning
DIY Deep Learning
for Custom Models
AI Enabled
Managed API
Services
Amazon AI: New Deep Learning Services
Polly LexRekognition
Deep Learning
Frameworks
MXNet, TensorFlow, Theano, Caffe, Torch
CONTROL
USABILITY&
SIMPLICITY
Running AI in Production on AWS Today
Recommendation & Ranking at Netflix
Personalized
ranking, page
generation, search,
similarity, ratings
In 140 new
countries
simultaneously
Autonomous Driving System
Pinterest Visual Search Pinterest Lens
Amazon AI: New Deep Learning Services
Life-like Speech
Polly Lex
Conversational
Engine
Rekognition
Image Analysis
Amazon Lex
Conversational interfaces for your applications, powered
by the same Natural Language Understanding (NLU) &
Automatic Speech Recognition (ASR) models as Alexa
Lex: Build Natural, Conversational Interactions
Trigger AWS
Lambda functions
Continually improving
ASR & NLU models
Enterprise
connectors
Salesforce
Microsoft Dynamics
Marketo
Zendesk
Fully
Managed
Voice & Text
“Chatbots”
Text interaction
with Slack & Messenger
Improving human interactions…
• Contact, service, and support center interfaces (text + voice)
• Employee productivity and collaboration (minutes into seconds)
Intents
A particular goal that the
user wants to achieve
Utterances
Spoken or typed phrases
that invoke your intent
Slots
Data the user must provide to fulfill the
intent
Prompts
Questions that ask the user to input
data
Fulfillment
The business logic required to fulfill the
user’s intent
BookHotel
Origin
Destination
Departure Date
Flight Booking
“Book a flight
to London from Seattle”
Automatic
Speech Recognition
Natural Language
Understanding
Book Flight
London
Utterances
Flight booking
London Heathrow
Intent /
Slot model
London Heathrow
Seattle
Seattle
Seattle
Origin
Destination
Departure Date
Flight Booking
“Book a flight
to London from Seattle”
Automatic
Speech Recognition
Natural Language
Understanding
Book Flight
London
Utterances
Flight booking
Intent /
Slot model
London Heathrow
Seattle
Prompt
“When would you like to fly?”
“When would you
like to fly?”
Polly
Seattle
London Heathrow
Seattle
Origin
Destination
Departure Date
Flight Booking
London Heathrow
Seattle
Prompt
“When would you like to fly?”
“When would you
like to fly?”
Polly
“Next Friday”
Origin
Destination
Departure Date
Flight Booking
“Next Friday”
Automatic
Speech Recognition
Next Friday
Utterances
Natural Language
Understanding
Flight booking
02 / 24 / 2017
Intent /
Slot model
London Heathrow
Seattle
02/24/2017
Origin
Destination
Departure Date
Flight Booking
“Next Friday”
Automatic
Speech Recognition
Next Friday
Utterances
Natural Language
Understanding
Flight booking
02 / 24 / 2017
Intent /
Slot model
London Heathrow
Seattle
02/24/2017
Confirmation
“Your flight is booked for next Friday”
“Your flight is booked
for next Friday”
Polly
Origin
Destination
Departure Date
Flight Booking
“Next Friday”
Automatic
Speech Recognition
Next Friday
Utterances
Natural Language
Understanding
Flight booking
02 / 24 / 2017
Intent /
Slot model
London Heathrow
Seattle
02/24/2017
Hotel Booking
Amazon Polly
Turn Text into lifelike speech using deep learning
technologies to synthesize speech that sounds like a
human voice
Amazon Polly
“The temperature
in WA is 75°F”
“The temperature
in Washington is 75 degrees
Fahrenheit”
Amazon Polly: Text In, Life-like Speech Out
Converts text
to life-like speech
47 voices 24 languages Low latency,
real time
Fully managed
Polly: Life-like Speech Service
What is supported?
• Supports all programming language included in AWS SDK
(Java, Python, Node.js, etc) as well as HTTP API
• Audio stream formats: MP3, Vorbis, raw PCM
• Choose your sampling rate to optimize bandwidth & quality
• Customized Pronunciation
Articles and Blogs
Training Material
Chatbots (Lex)
Public Announcements
Polly: SSML and Lexicons
• Using version 1.1 SSML tags to adjust the speech rate, pitch, or volume. e.g.
• <break time="1s"/> pause 1 second between the initial two sentences
• <sub alias="World Wide Web Consortium">W3C</sub> substitute "World Wide Web Consortium" for the
acronym "W3C"
• <amazon:effect name="whispered">Score</amazon:effect> say the second "Score" in a whispered voice
<speak>He was caught up in the game.<break time="1s"/> In the middle of the 10/3/2014 <sub
alias="World Wide Web Consortium">W3C</sub> meeting he shouted, "Score!" quite loudly. When
his boss stared at him, he repeated <amazon:effect name="whispered">"Score"</amazon:effect> in
a whisper.</speak>
• Pronounciation lexicons enable you to customize the pronunciation of words
<lexeme>
<grapheme>Bob</grapheme>
<alias>Robert</alias>
</lexeme>
aws polly synthesize-speech 
--lexicon-names LexA LexB 
--output-format mp3 
--text 'Hello, my name is Bob' 
--voice-id Justin 
bobAB.mp3
“Hello, my name is Robert”
"Our Mapbox Navigation SDK offers a complete
turn-by-turn navigation solution that you can easily
add to your iOS or Android application, and having
clear, well-understood voice guidance is critical to
the user experience. Therefore, we’re excited to
offer natural-sounding pronunciation with highly
intelligible and pleasant voices in our users’ most
widely used languages with Amazon Polly’s Text-to-
Speech service."
– Paul Veugen, VP of Mobile, Mapbox.
Amazon Rekognition
Image Recognitions and Analysis powered by Deep
Learning which allows to search, verify and organize
millions of images
Amazon Rekognition
Deep learning-based image recognition service
Search, verify, and organize millions of images
Object and Scene
Detection
Facial
Analysis
Face
Comparison
Facial
Recognition
Integrated with S3, Lambda, Polly, Lex
Object and Scene Detection
• Search, filter, and
curate image
libraries
• Smart searches for
user generated
content
• Photo, travel, real
estate, vacation
rental applications
Maple
Plant
Villa
Garden
Water
Swimming Pool
Tree
Potted Plant
Backyard
Request
Response
Object and Scene Detection – DetectLabels API
{
"Image": {
"Bytes": blob,
"S3Object": {
"Bucket": "string",
"Name": "string",
"Version": "string"
}
},
"MaxLabels": number,
"MinConfidence": number
}
Maple
Plant
Villa
Garden
Water
Swimming Pool
Tree
Potted Plant
Backyard
{
"Labels": [
{
"Confidence": 95.78783416748047,
"Name": "Villa"
},
{
"Confidence": 68.914794921875,
"Name": "Swimming Pool"
},
{
"Confidence": 59.24593734741211,
"Name": "Backyard"
},
{
"Confidence": 59.24593734741211,
"Name": "Yard"
},
],
"OrientationCorrection": "ROTATE_0"
}
Generate labels for thousands of objects, scenes, and concepts, each with a
confidence score
S3 bucket
Facial Analysis
Demographic Data
Facial Landmarks
Sentiment Expressed
• Smart searches for
user generated
content
• Photo, travel, real
estate, vacation
rental applications
• Targeted marketing
• Dynamic,
personalized ads
• Improve online dating
match
recommendations
Facial Analysis
"AgeRange": {"High": 38, "Low": 23},
"BoundingBox": {
"Height": 0.42500001192092896,
"Left": 0.1433333307504654,
"Top": 0.11666666716337204,
"Width": 0.2822222113609314
},
"Confidence": 99.8899917602539,
"Emotions": [
{"Confidence": 93.29251861572266,
"Type": "HAPPY"},
{"Confidence": 28.57428741455078,
"Type": "CALM" },
{"Confidence": 1.4989674091339111,
"Type": "ANGRY" }
],
"Eyeglasses": { "Confidence": 99.99998474121094,
"Value": true },
"Gender": { "Confidence": 100,
"Value": "Female" },
"Smile": { "Confidence": 99.47274780273438,
"Value": true },
"Sunglasses": { "Confidence": 97.63555145263672,
"Value": true }
DetectFaces
smart cropping
& ad overlays
sentiment
capture
demographic
analysis
face editing
& pixelation
Face Comparison
Measure the likelihood that faces in two images are of the same
person
• Add face verification to
applications and devices
• Extend physical security
controls
• Provide guest access to
VIP-only facilities
• Verify users for online
exams and polls
CompareFaces
"FaceMatches": [
{"Face": {"BoundingBox": {
"Height": 0.4601006507873535,
"Left": 0.32827046513557434,
"Top": 0.18212316930294037,
"Width": 0.3135717809200287},
"Confidence": 99.99964141845703},
"Similarity": 93
},
{"Face": {"BoundingBox": {
"Height": 0.2383333295583725,
"Left": 0.6233333349227905,
"Top": 0.3016666769981384,
"Width": 0.15888889133930206},
"Confidence": 99.71249389648438},
"Similarity": 0
}
],
"SourceImageFace": {"BoundingBox": {
"Height": 0.23983436822891235,
"Left": 0.28333333134651184,
"Top": 0.351423978805542,
"Width": 0.1599999964237213},
"Confidence": 99.99344635009766}
}
Similarity 93%
Similarity 0%
Celebrity Recognition
More Rekognition Capabilities
Image Moderation
Facial Recognition
Identify people in images by finding the closest match for an input face
image against a collection of stored face vectors
• Add friend tagging to
social and messaging apps
• Assist public safety officers
find missing persons
• Identify employees as they
access sensitive locations
• Identify celebrities in
historical media archives
Media Case Study
Identify who is on camera at what time for
each of 8 networks so that recorded video
streams can be indexed and searched
Video frame-sampling facial recognition
solution using Amazon Rekognition:
• Indexed 97,000 people into a face collection in
1 day
• Sample frames every 6 secs and test for image
variance
• Upload images to S3 and call Rekognition to
find best facial match
• Store time stamp and faceID metadata
Demo
Amazon AI Services
• Leveraging Amazon internal experiences with AI / ML
• Managed API services with embedded AI for maximum
accessibility and simplicity
• Full stack of platforms and engines for specialized deep
learning applications
Thank you!

Mais conteúdo relacionado

Mais procurados

Building Reliable Data Lakes at Scale with Delta Lake
Building Reliable Data Lakes at Scale with Delta LakeBuilding Reliable Data Lakes at Scale with Delta Lake
Building Reliable Data Lakes at Scale with Delta Lake
Databricks
 

Mais procurados (20)

Financial Services Cloud - Blueprint Webinar (March 20, 2016)
Financial Services Cloud - Blueprint Webinar (March 20, 2016)Financial Services Cloud - Blueprint Webinar (March 20, 2016)
Financial Services Cloud - Blueprint Webinar (March 20, 2016)
 
Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2
 
DAS Slides: Building a Data Strategy – Practical Steps for Aligning with Busi...
DAS Slides: Building a Data Strategy – Practical Steps for Aligning with Busi...DAS Slides: Building a Data Strategy – Practical Steps for Aligning with Busi...
DAS Slides: Building a Data Strategy – Practical Steps for Aligning with Busi...
 
Retail fulfillment—thinking local, acting local | Accenture
Retail fulfillment—thinking local, acting local | AccentureRetail fulfillment—thinking local, acting local | Accenture
Retail fulfillment—thinking local, acting local | Accenture
 
Gartner Overview
Gartner OverviewGartner Overview
Gartner Overview
 
Integration Of Digital Technology PowerPoint Presentation Slides
Integration Of Digital Technology PowerPoint Presentation SlidesIntegration Of Digital Technology PowerPoint Presentation Slides
Integration Of Digital Technology PowerPoint Presentation Slides
 
Transform Data to Insight
Transform Data to InsightTransform Data to Insight
Transform Data to Insight
 
Slides: Data Monetization — Demonstrating Quantifiable Financial Benefits fro...
Slides: Data Monetization — Demonstrating Quantifiable Financial Benefits fro...Slides: Data Monetization — Demonstrating Quantifiable Financial Benefits fro...
Slides: Data Monetization — Demonstrating Quantifiable Financial Benefits fro...
 
Building Reliable Data Lakes at Scale with Delta Lake
Building Reliable Data Lakes at Scale with Delta LakeBuilding Reliable Data Lakes at Scale with Delta Lake
Building Reliable Data Lakes at Scale with Delta Lake
 
Transforming the industry that transformed the world
Transforming the industry that transformed the worldTransforming the industry that transformed the world
Transforming the industry that transformed the world
 
Monetization - The Right Business Model for Your Digital Assets
Monetization - The Right Business Model for Your Digital AssetsMonetization - The Right Business Model for Your Digital Assets
Monetization - The Right Business Model for Your Digital Assets
 
Data Monetization Framework
Data Monetization FrameworkData Monetization Framework
Data Monetization Framework
 
CRM@Oracle: CRM Analytics
CRM@Oracle: CRM AnalyticsCRM@Oracle: CRM Analytics
CRM@Oracle: CRM Analytics
 
Modernizing to a Cloud Data Architecture
Modernizing to a Cloud Data ArchitectureModernizing to a Cloud Data Architecture
Modernizing to a Cloud Data Architecture
 
Introduction to Artificial Intelligence on AWS
Introduction to Artificial Intelligence on AWSIntroduction to Artificial Intelligence on AWS
Introduction to Artificial Intelligence on AWS
 
Guide to Data Monetization
Guide to Data MonetizationGuide to Data Monetization
Guide to Data Monetization
 
Customer-Centric Data Management for Better Customer Experiences
Customer-Centric Data Management for Better Customer ExperiencesCustomer-Centric Data Management for Better Customer Experiences
Customer-Centric Data Management for Better Customer Experiences
 
[DSC Europe 22] Lakehouse architecture with Delta Lake and Databricks - Draga...
[DSC Europe 22] Lakehouse architecture with Delta Lake and Databricks - Draga...[DSC Europe 22] Lakehouse architecture with Delta Lake and Databricks - Draga...
[DSC Europe 22] Lakehouse architecture with Delta Lake and Databricks - Draga...
 
Customer Experience in a SaaS business
Customer Experience in a SaaS businessCustomer Experience in a SaaS business
Customer Experience in a SaaS business
 
Forging an Analytics Center of Excellence
Forging an Analytics Center of ExcellenceForging an Analytics Center of Excellence
Forging an Analytics Center of Excellence
 

Destaque

Destaque (20)

把您的 Amazon Lex Chatbot 與訊息服務集成
把您的 Amazon Lex Chatbot 與訊息服務集成把您的 Amazon Lex Chatbot 與訊息服務集成
把您的 Amazon Lex Chatbot 與訊息服務集成
 
網路安全自動化 - 縮短應用維安的作業時間
網路安全自動化 - 縮短應用維安的作業時間網路安全自動化 - 縮短應用維安的作業時間
網路安全自動化 - 縮短應用維安的作業時間
 
遷移過程中建置混和雲架構的最佳實踐分享
遷移過程中建置混和雲架構的最佳實踐分享遷移過程中建置混和雲架構的最佳實踐分享
遷移過程中建置混和雲架構的最佳實踐分享
 
AWS 機器學習 II ─ 深度學習 Deep Learning & MXNet
AWS 機器學習 II ─ 深度學習 Deep Learning & MXNetAWS 機器學習 II ─ 深度學習 Deep Learning & MXNet
AWS 機器學習 II ─ 深度學習 Deep Learning & MXNet
 
Building IoT Backends
Building IoT BackendsBuilding IoT Backends
Building IoT Backends
 
Chief Data Officer: Customer Analytics Innovation
Chief Data Officer: Customer Analytics InnovationChief Data Officer: Customer Analytics Innovation
Chief Data Officer: Customer Analytics Innovation
 
AI as a service
AI as a serviceAI as a service
AI as a service
 
Process Mining based on the Internet of Events
Process Mining based on the Internet of EventsProcess Mining based on the Internet of Events
Process Mining based on the Internet of Events
 
Office of the Chief Data Officer. How is your office organized?
Office of the Chief Data Officer. How is your office organized?Office of the Chief Data Officer. How is your office organized?
Office of the Chief Data Officer. How is your office organized?
 
Chief Data Officer: 6 Ideas for Data Innovation
Chief Data Officer: 6 Ideas for Data Innovation Chief Data Officer: 6 Ideas for Data Innovation
Chief Data Officer: 6 Ideas for Data Innovation
 
AI and the Financial Service Segment
AI and the Financial Service SegmentAI and the Financial Service Segment
AI and the Financial Service Segment
 
Chief Data Officer: Top Ten Learnings...
Chief Data Officer: Top Ten Learnings...Chief Data Officer: Top Ten Learnings...
Chief Data Officer: Top Ten Learnings...
 
Software strategy for startups
Software strategy for startupsSoftware strategy for startups
Software strategy for startups
 
How does semantic technology work?
How does semantic technology work? How does semantic technology work?
How does semantic technology work?
 
Strategy toolbox for startsups
Strategy toolbox for startsupsStrategy toolbox for startsups
Strategy toolbox for startsups
 
Predictive Analytics World for Business Deutschland 2017
Predictive Analytics World for Business Deutschland 2017Predictive Analytics World for Business Deutschland 2017
Predictive Analytics World for Business Deutschland 2017
 
Data strategy in a Big Data world
Data strategy in a Big Data worldData strategy in a Big Data world
Data strategy in a Big Data world
 
Overview of IBM Watson Services via Blue Mix
Overview of IBM Watson Services via Blue Mix Overview of IBM Watson Services via Blue Mix
Overview of IBM Watson Services via Blue Mix
 
Compared: IBM Watson Services / Microsoft Azure Services
Compared: IBM Watson Services / Microsoft Azure ServicesCompared: IBM Watson Services / Microsoft Azure Services
Compared: IBM Watson Services / Microsoft Azure Services
 
IoT and AI Services in Healthcare | AWS Public Sector Summit 2017
 IoT and AI Services in Healthcare | AWS Public Sector Summit 2017 IoT and AI Services in Healthcare | AWS Public Sector Summit 2017
IoT and AI Services in Healthcare | AWS Public Sector Summit 2017
 

Semelhante a Building an AI-based service with Rekognition, Polly and Lex

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
 
An Overview of AI on the AWS Platform - February 2017 Online Tech Talks
An Overview of AI on the AWS Platform - February 2017 Online Tech TalksAn Overview of AI on the AWS Platform - February 2017 Online Tech Talks
An Overview of AI on the AWS Platform - February 2017 Online Tech Talks
Amazon Web Services
 

Semelhante a Building an AI-based service with Rekognition, Polly and Lex (20)

Building Serverless AI-powered Apps on AWS
Building Serverless AI-powered Apps on AWSBuilding Serverless AI-powered Apps on AWS
Building Serverless AI-powered Apps on AWS
 
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...
 
AWS FSI Symposium 2017 NYC - Amazon AI for FS
AWS FSI Symposium 2017 NYC - Amazon AI for FSAWS FSI Symposium 2017 NYC - Amazon AI for FS
AWS FSI Symposium 2017 NYC - Amazon AI for FS
 
Hands-on with Rekognition, Polly & Lex - Pop-up Loft TLV 2017
Hands-on with Rekognition, Polly & Lex - Pop-up Loft TLV 2017Hands-on with Rekognition, Polly & Lex - Pop-up Loft TLV 2017
Hands-on with Rekognition, Polly & Lex - Pop-up Loft TLV 2017
 
Amazon AI (March 2017)
Amazon AI (March 2017)Amazon AI (March 2017)
Amazon AI (March 2017)
 
An Overview of AI on the AWS Platform - June 2017 AWS Online Tech Talks
An Overview of AI on the AWS Platform - June 2017 AWS Online Tech TalksAn Overview of AI on the AWS Platform - June 2017 AWS Online Tech Talks
An Overview of AI on the AWS Platform - June 2017 AWS Online Tech Talks
 
An Overview to Artificial Intelligence Services at AWS
An Overview to Artificial Intelligence Services at AWSAn Overview to Artificial Intelligence Services at AWS
An Overview to Artificial Intelligence Services at AWS
 
Amazon AI (October 2017)
Amazon AI (October 2017)Amazon AI (October 2017)
Amazon AI (October 2017)
 
Harnessing Artificial Intelligence_Alastair Cousins
Harnessing Artificial Intelligence_Alastair CousinsHarnessing Artificial Intelligence_Alastair Cousins
Harnessing Artificial Intelligence_Alastair Cousins
 
An Overview of the AI on the AWS Platform
An Overview of the AI on the AWS PlatformAn Overview of the AI on the AWS Platform
An Overview of the AI on the AWS Platform
 
AWS 機器學習 I ─ 人工智慧 AI
AWS 機器學習 I ─ 人工智慧 AIAWS 機器學習 I ─ 人工智慧 AI
AWS 機器學習 I ─ 人工智慧 AI
 
An Overview of AI at AWS: Amazon Lex, Amazon Polly, Amazon Rekognition, Apach...
An Overview of AI at AWS: Amazon Lex, Amazon Polly, Amazon Rekognition, Apach...An Overview of AI at AWS: Amazon Lex, Amazon Polly, Amazon Rekognition, Apach...
An Overview of AI at AWS: Amazon Lex, Amazon Polly, Amazon Rekognition, Apach...
 
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...
 
An Introduction to Amazon AI
An Introduction to Amazon AIAn Introduction to Amazon AI
An Introduction to Amazon AI
 
AI State of the Union
AI State of the UnionAI State of the Union
AI State of the Union
 
Enhancing Your Startup w/ Amazon AI
Enhancing Your Startup w/ Amazon AIEnhancing Your Startup w/ Amazon AI
Enhancing Your Startup w/ Amazon AI
 
Raleigh DevDay 2017: Distributed Deep Learning on AWS with Apache MXNet
Raleigh DevDay 2017: Distributed Deep Learning on AWS with Apache MXNetRaleigh DevDay 2017: Distributed Deep Learning on AWS with Apache MXNet
Raleigh DevDay 2017: Distributed Deep Learning on AWS with Apache MXNet
 
An Overview of AI on the AWS Platform - February 2017 Online Tech Talks
An Overview of AI on the AWS Platform - February 2017 Online Tech TalksAn Overview of AI on the AWS Platform - February 2017 Online Tech Talks
An Overview of AI on the AWS Platform - February 2017 Online Tech Talks
 
AI Overview
AI OverviewAI Overview
AI Overview
 
Introduction to Artificial Intelligence on AWS
Introduction to Artificial Intelligence on AWSIntroduction to Artificial Intelligence on AWS
Introduction to Artificial Intelligence on AWS
 

Mais de Amazon 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 AWS
Amazon 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 Deck
Amazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
Amazon Web Services
 

Mais 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
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
 
Come costruire un'architettura Serverless nel Cloud AWS
Come costruire un'architettura Serverless nel Cloud AWSCome costruire un'architettura Serverless nel Cloud AWS
Come costruire un'architettura Serverless nel Cloud AWS
 

Building an AI-based service with Rekognition, Polly and Lex

  • 1. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Rebeker Choi, Solutions Architect 15-Sep, 2017 Building an AI-based service with Rekognition, Polly, and Lex
  • 2. The Challenge for Artificial Intelligence: SCALE Tons of GPUs and CPUs Prediction Tons of GPUs TrainingData PBs of existing data
  • 3. AWS is the Center of Gravity for Artificial Intelligence
  • 4. Amazon AI Intelligent Services Powered by Deep Learning
  • 5. DIY Deep Learning for Custom Models AI Enabled Managed API Services Amazon AI: New Deep Learning Services Polly LexRekognition Deep Learning Frameworks MXNet, TensorFlow, Theano, Caffe, Torch CONTROL USABILITY& SIMPLICITY
  • 6. Running AI in Production on AWS Today
  • 7. Recommendation & Ranking at Netflix Personalized ranking, page generation, search, similarity, ratings In 140 new countries simultaneously
  • 9. Pinterest Visual Search Pinterest Lens
  • 10. Amazon AI: New Deep Learning Services Life-like Speech Polly Lex Conversational Engine Rekognition Image Analysis
  • 11. Amazon Lex Conversational interfaces for your applications, powered by the same Natural Language Understanding (NLU) & Automatic Speech Recognition (ASR) models as Alexa
  • 12. Lex: Build Natural, Conversational Interactions Trigger AWS Lambda functions Continually improving ASR & NLU models Enterprise connectors Salesforce Microsoft Dynamics Marketo Zendesk Fully Managed Voice & Text “Chatbots” Text interaction with Slack & Messenger Improving human interactions… • Contact, service, and support center interfaces (text + voice) • Employee productivity and collaboration (minutes into seconds)
  • 13. Intents A particular goal that the user wants to achieve Utterances Spoken or typed phrases that invoke your intent Slots Data the user must provide to fulfill the intent Prompts Questions that ask the user to input data Fulfillment The business logic required to fulfill the user’s intent BookHotel
  • 14. Origin Destination Departure Date Flight Booking “Book a flight to London from Seattle” Automatic Speech Recognition Natural Language Understanding Book Flight London Utterances Flight booking London Heathrow Intent / Slot model London Heathrow Seattle Seattle Seattle
  • 15. Origin Destination Departure Date Flight Booking “Book a flight to London from Seattle” Automatic Speech Recognition Natural Language Understanding Book Flight London Utterances Flight booking Intent / Slot model London Heathrow Seattle Prompt “When would you like to fly?” “When would you like to fly?” Polly Seattle London Heathrow Seattle
  • 16. Origin Destination Departure Date Flight Booking London Heathrow Seattle Prompt “When would you like to fly?” “When would you like to fly?” Polly “Next Friday”
  • 17. Origin Destination Departure Date Flight Booking “Next Friday” Automatic Speech Recognition Next Friday Utterances Natural Language Understanding Flight booking 02 / 24 / 2017 Intent / Slot model London Heathrow Seattle 02/24/2017
  • 18. Origin Destination Departure Date Flight Booking “Next Friday” Automatic Speech Recognition Next Friday Utterances Natural Language Understanding Flight booking 02 / 24 / 2017 Intent / Slot model London Heathrow Seattle 02/24/2017 Confirmation “Your flight is booked for next Friday” “Your flight is booked for next Friday” Polly
  • 19. Origin Destination Departure Date Flight Booking “Next Friday” Automatic Speech Recognition Next Friday Utterances Natural Language Understanding Flight booking 02 / 24 / 2017 Intent / Slot model London Heathrow Seattle 02/24/2017 Hotel Booking
  • 20. Amazon Polly Turn Text into lifelike speech using deep learning technologies to synthesize speech that sounds like a human voice
  • 21. Amazon Polly “The temperature in WA is 75°F” “The temperature in Washington is 75 degrees Fahrenheit” Amazon Polly: Text In, Life-like Speech Out
  • 22. Converts text to life-like speech 47 voices 24 languages Low latency, real time Fully managed Polly: Life-like Speech Service What is supported? • Supports all programming language included in AWS SDK (Java, Python, Node.js, etc) as well as HTTP API • Audio stream formats: MP3, Vorbis, raw PCM • Choose your sampling rate to optimize bandwidth & quality • Customized Pronunciation Articles and Blogs Training Material Chatbots (Lex) Public Announcements
  • 23. Polly: SSML and Lexicons • Using version 1.1 SSML tags to adjust the speech rate, pitch, or volume. e.g. • <break time="1s"/> pause 1 second between the initial two sentences • <sub alias="World Wide Web Consortium">W3C</sub> substitute "World Wide Web Consortium" for the acronym "W3C" • <amazon:effect name="whispered">Score</amazon:effect> say the second "Score" in a whispered voice <speak>He was caught up in the game.<break time="1s"/> In the middle of the 10/3/2014 <sub alias="World Wide Web Consortium">W3C</sub> meeting he shouted, "Score!" quite loudly. When his boss stared at him, he repeated <amazon:effect name="whispered">"Score"</amazon:effect> in a whisper.</speak> • Pronounciation lexicons enable you to customize the pronunciation of words <lexeme> <grapheme>Bob</grapheme> <alias>Robert</alias> </lexeme> aws polly synthesize-speech --lexicon-names LexA LexB --output-format mp3 --text 'Hello, my name is Bob' --voice-id Justin bobAB.mp3 “Hello, my name is Robert”
  • 24. "Our Mapbox Navigation SDK offers a complete turn-by-turn navigation solution that you can easily add to your iOS or Android application, and having clear, well-understood voice guidance is critical to the user experience. Therefore, we’re excited to offer natural-sounding pronunciation with highly intelligible and pleasant voices in our users’ most widely used languages with Amazon Polly’s Text-to- Speech service." – Paul Veugen, VP of Mobile, Mapbox.
  • 25. Amazon Rekognition Image Recognitions and Analysis powered by Deep Learning which allows to search, verify and organize millions of images
  • 26. Amazon Rekognition Deep learning-based image recognition service Search, verify, and organize millions of images Object and Scene Detection Facial Analysis Face Comparison Facial Recognition Integrated with S3, Lambda, Polly, Lex
  • 27. Object and Scene Detection • Search, filter, and curate image libraries • Smart searches for user generated content • Photo, travel, real estate, vacation rental applications Maple Plant Villa Garden Water Swimming Pool Tree Potted Plant Backyard
  • 28. Request Response Object and Scene Detection – DetectLabels API { "Image": { "Bytes": blob, "S3Object": { "Bucket": "string", "Name": "string", "Version": "string" } }, "MaxLabels": number, "MinConfidence": number } Maple Plant Villa Garden Water Swimming Pool Tree Potted Plant Backyard { "Labels": [ { "Confidence": 95.78783416748047, "Name": "Villa" }, { "Confidence": 68.914794921875, "Name": "Swimming Pool" }, { "Confidence": 59.24593734741211, "Name": "Backyard" }, { "Confidence": 59.24593734741211, "Name": "Yard" }, ], "OrientationCorrection": "ROTATE_0" } Generate labels for thousands of objects, scenes, and concepts, each with a confidence score S3 bucket
  • 29. Facial Analysis Demographic Data Facial Landmarks Sentiment Expressed • Smart searches for user generated content • Photo, travel, real estate, vacation rental applications • Targeted marketing • Dynamic, personalized ads • Improve online dating match recommendations
  • 30. Facial Analysis "AgeRange": {"High": 38, "Low": 23}, "BoundingBox": { "Height": 0.42500001192092896, "Left": 0.1433333307504654, "Top": 0.11666666716337204, "Width": 0.2822222113609314 }, "Confidence": 99.8899917602539, "Emotions": [ {"Confidence": 93.29251861572266, "Type": "HAPPY"}, {"Confidence": 28.57428741455078, "Type": "CALM" }, {"Confidence": 1.4989674091339111, "Type": "ANGRY" } ], "Eyeglasses": { "Confidence": 99.99998474121094, "Value": true }, "Gender": { "Confidence": 100, "Value": "Female" }, "Smile": { "Confidence": 99.47274780273438, "Value": true }, "Sunglasses": { "Confidence": 97.63555145263672, "Value": true } DetectFaces smart cropping & ad overlays sentiment capture demographic analysis face editing & pixelation
  • 31. Face Comparison Measure the likelihood that faces in two images are of the same person • Add face verification to applications and devices • Extend physical security controls • Provide guest access to VIP-only facilities • Verify users for online exams and polls
  • 32. CompareFaces "FaceMatches": [ {"Face": {"BoundingBox": { "Height": 0.4601006507873535, "Left": 0.32827046513557434, "Top": 0.18212316930294037, "Width": 0.3135717809200287}, "Confidence": 99.99964141845703}, "Similarity": 93 }, {"Face": {"BoundingBox": { "Height": 0.2383333295583725, "Left": 0.6233333349227905, "Top": 0.3016666769981384, "Width": 0.15888889133930206}, "Confidence": 99.71249389648438}, "Similarity": 0 } ], "SourceImageFace": {"BoundingBox": { "Height": 0.23983436822891235, "Left": 0.28333333134651184, "Top": 0.351423978805542, "Width": 0.1599999964237213}, "Confidence": 99.99344635009766} } Similarity 93% Similarity 0%
  • 33. Celebrity Recognition More Rekognition Capabilities Image Moderation
  • 34. Facial Recognition Identify people in images by finding the closest match for an input face image against a collection of stored face vectors • Add friend tagging to social and messaging apps • Assist public safety officers find missing persons • Identify employees as they access sensitive locations • Identify celebrities in historical media archives
  • 35. Media Case Study Identify who is on camera at what time for each of 8 networks so that recorded video streams can be indexed and searched Video frame-sampling facial recognition solution using Amazon Rekognition: • Indexed 97,000 people into a face collection in 1 day • Sample frames every 6 secs and test for image variance • Upload images to S3 and call Rekognition to find best facial match • Store time stamp and faceID metadata
  • 36. Demo
  • 37. Amazon AI Services • Leveraging Amazon internal experiences with AI / ML • Managed API services with embedded AI for maximum accessibility and simplicity • Full stack of platforms and engines for specialized deep learning applications