SlideShare une entreprise Scribd logo
1  sur  38
Scalable Chatbot
Architecture with
eBay ShopBot
Robert Enyedi
InfoQ.com: News & Community Site
• 750,000 unique visitors/month
• Published in 4 languages (English, Chinese, Japanese and Brazilian
Portuguese)
• Post content from our QCon conferences
• News 15-20 / week
• Articles 3-4 / week
• Presentations (videos) 12-15 / week
• Interviews 2-3 / week
• Books 1 / month
Watch the video with slide
synchronization on InfoQ.com!
https://www.infoq.com/presentations/
ebay-shopbot
Presented at QCon New York
www.qconnewyork.com
Purpose of QCon
- to empower software development by facilitating the spread of
knowledge and innovation
Strategy
- practitioner-driven conference designed for YOU: influencers of
change and innovation in your teams
- speakers and topics driving the evolution and innovation
- connecting and catalyzing the influencers and innovators
Highlights
- attended by more than 12,000 delegates since 2007
- held in 9 cities worldwide
eBay Marketplace
at a Glance
2
One of the world’s largest and
most vibrant marketplaces
Data as of Q1 2017
12M
New listings
added via
mobile per week
$20B
GMV
1.1B
Live listings
67%
Transactions
that ship for
free (US, UK, DE)
60%
Platform GMV
touched by
mobile
80%
Items sold as new
2017 Fun Facts: Velocity Stats by Region Frequency of product purchases via
desktop and mobile
US
11 sec
5 sec
4 sec
UK
1 sec
3 sec
8 sec
DE AU
16 sec
3 sec
18 sec
14 sec
26 sec
4 sec
The Major Trends in Commerce
4
AI is having a profound
impact on commerce
Users expect simple
and personalized
interactions
What is ShopBot?
eBay ShopBot
•Personal shopping assistant
•Powered by AI and eBay data
•Launched in late 2016
on Facebook Messenger
ShopBot AI System
System Architecture
7
Bot Memory
ShopBot
Fabric
Dialog Manager
Input Processors
Facebook
Messenger
Knowledge
Graph
User Experience
•A shopping assistant
•Multi-turn and multi-modal
•Try it out yourself:
https://shopbot.ebay.com/
8
Challenges
•Relevancy
•Shopping conversations
•Informal conversations
•Conversation not search
•Environment
•Building a deep memory
9
Goals
•Optimize:
–For mobile
–For chat
–For upcoming platforms and hardware
•Flexibility of integrations
•Rich interactions
10
Under the Hood
Multi-Modal System Input
“looking for shoes size 10”
“shop for sleeping bags”
“shoes for my baby”
12
Text
Image
Speech
Click & Tap
System Output
13
Text
Product Listings
Selectors
Multi-Turn Conversation
•Dialog around a topic
•More productive than traditional
search
14
System Design Constraints
• User input:
– Minimal
– Fragmented through multiple interactions
– Limited forms
• Needs large amounts of data to accurately understand the input
• System output:
– Has to be user-friendly
– Limited mechanisms
15
Features of Third-Party Bot Frameworks
•Natural Language Understanding and Processing
–Tuned for general purpose bots
–Intent detection: (e.g. weather, flight scheduling, shopping)
–Entity extraction: (e.g. number, temperature)
•Limited non-linear conversation support
•Coarse grained bot memory
•In various states of availability and maturity of API, tools and
implementation
16
Why Implement Our Own Bot Back-end?
•Commerce-aware input analysis tuned with
eBay-scale data
•Fine-grained bot memory with long-term
secure storage
•Support for non-linear multi-turn dialog
•Full data from input analysis
17
ShopBot AI System
System Architecture
18
Bot Memory
ShopBot
Fabric
Dialog Manager
Input Processors
Facebook
Messenger
Knowledge
Graph
ShopBot Fabric layer with Facebook Messenger Integration
19
ShopBot Fabric
Facebook
Messenger
Webhook
Callback
Web View
Webhook
Send API
Bot Memory
20
Missions
Turns
Product
Product Attributes User Attributes
Input Processors
• Common outputs:
– Intent (ShopBot focus is… shopping)
– Product attributes; ranked
21
Natural
Language
Understanding
Image Recognition
Speech
Recognition
Natural Language Understanding
22
My husband needs some new black leather dress shoes but I want to
spend less than $80, what do you have?
Relationship: Husband
Gender: Male
Dominant Object: Dress shoes
Product Category: Men's Dress Shoes
Color: Black
Material: Leather
Max price: $80
Natural
Language
Understanding
Image Analysis
23
Product Category: Men's Casual Shoes
Color: Black
Pattern: Solid
Image
Recognition
Dialog Manager
24
Dialog Manager
Input Handler
NLG
Input
Analysis
Output
Utterances
Bot Memory
Answer Generator
Mission Manager
Product Retriever
Dialog Manager – Search
25
Product Retriever
Text Search
Visual Search
Curation Search
Dialog Manager
Input Handler
NLG
Answer Generator
Mission Manager
Product Retriever
Dialog Manager in Action
26
Bot Memory Knowledge Graph
Dialog Manager in Action – search results
27
Dialog Manager
Input Handler
NLG
Answer Generator
Mission Manager
Product Retriever
Bot Memory Knowledge Graph
Dialog Manager
Input Handler
NLG
Answer Generator
Mission Manager
Product Retriever
Dialog Manager in Action: Mission Change
28
Bot Memory Knowledge Graph
Implementation Choices
•Runtime: mostly JVM languages, some Python
•ML Model Training: Python, Spark
•Micro-services architecture
29
Cloud Deployment
30
Architectural Benefits
•Extensibility and Flexibility
–Integrations
–Search providers
–Knowledge sources
•Improved scalability
–Auto-scalable chat bot system
–Horizontal and vertical
•Depth of understanding
–Leverages the richness of eBay data
31
ShopBot AI System
Bot Memory
ShopBot
Fabric
Dialog Manager
Input Processors
Facebook
Messenger
Knowledge
Graph
Learnings
•Many users see ShopBot as a search engine: “shoes size 12”
•Handling unrestricted user input is challenging when specialized on
shopping:
–Users greet the bot
–Some expect it to know the weather
–Others use free text such as ”I don’t like those”
•Accurate response tops a fast response
•Ask the user for disambiguation
32
Status
•Work started in Jan 2016
•Released as public beta in Oct 2016
•A platform for collecting data and learning
•Full eBay inventory in the cloud
•Continuing innovation into non-linear dialog interactions
•Researching how to leverage AI in conversational commerce
to make shopping easier/faster/delightful
33
We Are Hiring
https://careers.ebayinc.com/
34
Q&A
Robert Enyedi
Software Engineer
renyedi@ebay.com
Watch the video with slide synchronization on
InfoQ.com!
https://www.infoq.com/presentations/ebay-
shopbot

Contenu connexe

Plus de C4Media

Shifting Left with Cloud Native CI/CD
Shifting Left with Cloud Native CI/CDShifting Left with Cloud Native CI/CD
Shifting Left with Cloud Native CI/CDC4Media
 
CI/CD for Machine Learning
CI/CD for Machine LearningCI/CD for Machine Learning
CI/CD for Machine LearningC4Media
 
Fault Tolerance at Speed
Fault Tolerance at SpeedFault Tolerance at Speed
Fault Tolerance at SpeedC4Media
 
Architectures That Scale Deep - Regaining Control in Deep Systems
Architectures That Scale Deep - Regaining Control in Deep SystemsArchitectures That Scale Deep - Regaining Control in Deep Systems
Architectures That Scale Deep - Regaining Control in Deep SystemsC4Media
 
ML in the Browser: Interactive Experiences with Tensorflow.js
ML in the Browser: Interactive Experiences with Tensorflow.jsML in the Browser: Interactive Experiences with Tensorflow.js
ML in the Browser: Interactive Experiences with Tensorflow.jsC4Media
 
Build Your Own WebAssembly Compiler
Build Your Own WebAssembly CompilerBuild Your Own WebAssembly Compiler
Build Your Own WebAssembly CompilerC4Media
 
User & Device Identity for Microservices @ Netflix Scale
User & Device Identity for Microservices @ Netflix ScaleUser & Device Identity for Microservices @ Netflix Scale
User & Device Identity for Microservices @ Netflix ScaleC4Media
 
Scaling Patterns for Netflix's Edge
Scaling Patterns for Netflix's EdgeScaling Patterns for Netflix's Edge
Scaling Patterns for Netflix's EdgeC4Media
 
Make Your Electron App Feel at Home Everywhere
Make Your Electron App Feel at Home EverywhereMake Your Electron App Feel at Home Everywhere
Make Your Electron App Feel at Home EverywhereC4Media
 
The Talk You've Been Await-ing For
The Talk You've Been Await-ing ForThe Talk You've Been Await-ing For
The Talk You've Been Await-ing ForC4Media
 
Future of Data Engineering
Future of Data EngineeringFuture of Data Engineering
Future of Data EngineeringC4Media
 
Automated Testing for Terraform, Docker, Packer, Kubernetes, and More
Automated Testing for Terraform, Docker, Packer, Kubernetes, and MoreAutomated Testing for Terraform, Docker, Packer, Kubernetes, and More
Automated Testing for Terraform, Docker, Packer, Kubernetes, and MoreC4Media
 
Navigating Complexity: High-performance Delivery and Discovery Teams
Navigating Complexity: High-performance Delivery and Discovery TeamsNavigating Complexity: High-performance Delivery and Discovery Teams
Navigating Complexity: High-performance Delivery and Discovery TeamsC4Media
 
High Performance Cooperative Distributed Systems in Adtech
High Performance Cooperative Distributed Systems in AdtechHigh Performance Cooperative Distributed Systems in Adtech
High Performance Cooperative Distributed Systems in AdtechC4Media
 
Rust's Journey to Async/await
Rust's Journey to Async/awaitRust's Journey to Async/await
Rust's Journey to Async/awaitC4Media
 
Opportunities and Pitfalls of Event-Driven Utopia
Opportunities and Pitfalls of Event-Driven UtopiaOpportunities and Pitfalls of Event-Driven Utopia
Opportunities and Pitfalls of Event-Driven UtopiaC4Media
 
Datadog: a Real-Time Metrics Database for One Quadrillion Points/Day
Datadog: a Real-Time Metrics Database for One Quadrillion Points/DayDatadog: a Real-Time Metrics Database for One Quadrillion Points/Day
Datadog: a Real-Time Metrics Database for One Quadrillion Points/DayC4Media
 
Are We Really Cloud-Native?
Are We Really Cloud-Native?Are We Really Cloud-Native?
Are We Really Cloud-Native?C4Media
 
CockroachDB: Architecture of a Geo-Distributed SQL Database
CockroachDB: Architecture of a Geo-Distributed SQL DatabaseCockroachDB: Architecture of a Geo-Distributed SQL Database
CockroachDB: Architecture of a Geo-Distributed SQL DatabaseC4Media
 
A Dive into Streams @LinkedIn with Brooklin
A Dive into Streams @LinkedIn with BrooklinA Dive into Streams @LinkedIn with Brooklin
A Dive into Streams @LinkedIn with BrooklinC4Media
 

Plus de C4Media (20)

Shifting Left with Cloud Native CI/CD
Shifting Left with Cloud Native CI/CDShifting Left with Cloud Native CI/CD
Shifting Left with Cloud Native CI/CD
 
CI/CD for Machine Learning
CI/CD for Machine LearningCI/CD for Machine Learning
CI/CD for Machine Learning
 
Fault Tolerance at Speed
Fault Tolerance at SpeedFault Tolerance at Speed
Fault Tolerance at Speed
 
Architectures That Scale Deep - Regaining Control in Deep Systems
Architectures That Scale Deep - Regaining Control in Deep SystemsArchitectures That Scale Deep - Regaining Control in Deep Systems
Architectures That Scale Deep - Regaining Control in Deep Systems
 
ML in the Browser: Interactive Experiences with Tensorflow.js
ML in the Browser: Interactive Experiences with Tensorflow.jsML in the Browser: Interactive Experiences with Tensorflow.js
ML in the Browser: Interactive Experiences with Tensorflow.js
 
Build Your Own WebAssembly Compiler
Build Your Own WebAssembly CompilerBuild Your Own WebAssembly Compiler
Build Your Own WebAssembly Compiler
 
User & Device Identity for Microservices @ Netflix Scale
User & Device Identity for Microservices @ Netflix ScaleUser & Device Identity for Microservices @ Netflix Scale
User & Device Identity for Microservices @ Netflix Scale
 
Scaling Patterns for Netflix's Edge
Scaling Patterns for Netflix's EdgeScaling Patterns for Netflix's Edge
Scaling Patterns for Netflix's Edge
 
Make Your Electron App Feel at Home Everywhere
Make Your Electron App Feel at Home EverywhereMake Your Electron App Feel at Home Everywhere
Make Your Electron App Feel at Home Everywhere
 
The Talk You've Been Await-ing For
The Talk You've Been Await-ing ForThe Talk You've Been Await-ing For
The Talk You've Been Await-ing For
 
Future of Data Engineering
Future of Data EngineeringFuture of Data Engineering
Future of Data Engineering
 
Automated Testing for Terraform, Docker, Packer, Kubernetes, and More
Automated Testing for Terraform, Docker, Packer, Kubernetes, and MoreAutomated Testing for Terraform, Docker, Packer, Kubernetes, and More
Automated Testing for Terraform, Docker, Packer, Kubernetes, and More
 
Navigating Complexity: High-performance Delivery and Discovery Teams
Navigating Complexity: High-performance Delivery and Discovery TeamsNavigating Complexity: High-performance Delivery and Discovery Teams
Navigating Complexity: High-performance Delivery and Discovery Teams
 
High Performance Cooperative Distributed Systems in Adtech
High Performance Cooperative Distributed Systems in AdtechHigh Performance Cooperative Distributed Systems in Adtech
High Performance Cooperative Distributed Systems in Adtech
 
Rust's Journey to Async/await
Rust's Journey to Async/awaitRust's Journey to Async/await
Rust's Journey to Async/await
 
Opportunities and Pitfalls of Event-Driven Utopia
Opportunities and Pitfalls of Event-Driven UtopiaOpportunities and Pitfalls of Event-Driven Utopia
Opportunities and Pitfalls of Event-Driven Utopia
 
Datadog: a Real-Time Metrics Database for One Quadrillion Points/Day
Datadog: a Real-Time Metrics Database for One Quadrillion Points/DayDatadog: a Real-Time Metrics Database for One Quadrillion Points/Day
Datadog: a Real-Time Metrics Database for One Quadrillion Points/Day
 
Are We Really Cloud-Native?
Are We Really Cloud-Native?Are We Really Cloud-Native?
Are We Really Cloud-Native?
 
CockroachDB: Architecture of a Geo-Distributed SQL Database
CockroachDB: Architecture of a Geo-Distributed SQL DatabaseCockroachDB: Architecture of a Geo-Distributed SQL Database
CockroachDB: Architecture of a Geo-Distributed SQL Database
 
A Dive into Streams @LinkedIn with Brooklin
A Dive into Streams @LinkedIn with BrooklinA Dive into Streams @LinkedIn with Brooklin
A Dive into Streams @LinkedIn with Brooklin
 

Dernier

ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxRemote DBA Services
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyKhushali Kathiriya
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024The Digital Insurer
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...apidays
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Bhuvaneswari Subramani
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Zilliz
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Orbitshub
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWERMadyBayot
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsNanddeep Nachan
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelDeepika Singh
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 

Dernier (20)

ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptx
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 

Scalable Chatbot Architecture with eBay ShopBot

  • 2. InfoQ.com: News & Community Site • 750,000 unique visitors/month • Published in 4 languages (English, Chinese, Japanese and Brazilian Portuguese) • Post content from our QCon conferences • News 15-20 / week • Articles 3-4 / week • Presentations (videos) 12-15 / week • Interviews 2-3 / week • Books 1 / month Watch the video with slide synchronization on InfoQ.com! https://www.infoq.com/presentations/ ebay-shopbot
  • 3. Presented at QCon New York www.qconnewyork.com Purpose of QCon - to empower software development by facilitating the spread of knowledge and innovation Strategy - practitioner-driven conference designed for YOU: influencers of change and innovation in your teams - speakers and topics driving the evolution and innovation - connecting and catalyzing the influencers and innovators Highlights - attended by more than 12,000 delegates since 2007 - held in 9 cities worldwide
  • 4. eBay Marketplace at a Glance 2 One of the world’s largest and most vibrant marketplaces Data as of Q1 2017 12M New listings added via mobile per week $20B GMV 1.1B Live listings 67% Transactions that ship for free (US, UK, DE) 60% Platform GMV touched by mobile 80% Items sold as new
  • 5. 2017 Fun Facts: Velocity Stats by Region Frequency of product purchases via desktop and mobile US 11 sec 5 sec 4 sec UK 1 sec 3 sec 8 sec DE AU 16 sec 3 sec 18 sec 14 sec 26 sec 4 sec
  • 6. The Major Trends in Commerce 4 AI is having a profound impact on commerce Users expect simple and personalized interactions
  • 8. eBay ShopBot •Personal shopping assistant •Powered by AI and eBay data •Launched in late 2016 on Facebook Messenger
  • 9. ShopBot AI System System Architecture 7 Bot Memory ShopBot Fabric Dialog Manager Input Processors Facebook Messenger Knowledge Graph
  • 10. User Experience •A shopping assistant •Multi-turn and multi-modal •Try it out yourself: https://shopbot.ebay.com/ 8
  • 12. Goals •Optimize: –For mobile –For chat –For upcoming platforms and hardware •Flexibility of integrations •Rich interactions 10
  • 14. Multi-Modal System Input “looking for shoes size 10” “shop for sleeping bags” “shoes for my baby” 12 Text Image Speech Click & Tap
  • 16. Multi-Turn Conversation •Dialog around a topic •More productive than traditional search 14
  • 17. System Design Constraints • User input: – Minimal – Fragmented through multiple interactions – Limited forms • Needs large amounts of data to accurately understand the input • System output: – Has to be user-friendly – Limited mechanisms 15
  • 18. Features of Third-Party Bot Frameworks •Natural Language Understanding and Processing –Tuned for general purpose bots –Intent detection: (e.g. weather, flight scheduling, shopping) –Entity extraction: (e.g. number, temperature) •Limited non-linear conversation support •Coarse grained bot memory •In various states of availability and maturity of API, tools and implementation 16
  • 19. Why Implement Our Own Bot Back-end? •Commerce-aware input analysis tuned with eBay-scale data •Fine-grained bot memory with long-term secure storage •Support for non-linear multi-turn dialog •Full data from input analysis 17
  • 20. ShopBot AI System System Architecture 18 Bot Memory ShopBot Fabric Dialog Manager Input Processors Facebook Messenger Knowledge Graph
  • 21. ShopBot Fabric layer with Facebook Messenger Integration 19 ShopBot Fabric Facebook Messenger Webhook Callback Web View Webhook Send API
  • 23. Input Processors • Common outputs: – Intent (ShopBot focus is… shopping) – Product attributes; ranked 21 Natural Language Understanding Image Recognition Speech Recognition
  • 24. Natural Language Understanding 22 My husband needs some new black leather dress shoes but I want to spend less than $80, what do you have? Relationship: Husband Gender: Male Dominant Object: Dress shoes Product Category: Men's Dress Shoes Color: Black Material: Leather Max price: $80 Natural Language Understanding
  • 25. Image Analysis 23 Product Category: Men's Casual Shoes Color: Black Pattern: Solid Image Recognition
  • 26. Dialog Manager 24 Dialog Manager Input Handler NLG Input Analysis Output Utterances Bot Memory Answer Generator Mission Manager Product Retriever
  • 27. Dialog Manager – Search 25 Product Retriever Text Search Visual Search Curation Search
  • 28. Dialog Manager Input Handler NLG Answer Generator Mission Manager Product Retriever Dialog Manager in Action 26 Bot Memory Knowledge Graph
  • 29. Dialog Manager in Action – search results 27 Dialog Manager Input Handler NLG Answer Generator Mission Manager Product Retriever Bot Memory Knowledge Graph
  • 30. Dialog Manager Input Handler NLG Answer Generator Mission Manager Product Retriever Dialog Manager in Action: Mission Change 28 Bot Memory Knowledge Graph
  • 31. Implementation Choices •Runtime: mostly JVM languages, some Python •ML Model Training: Python, Spark •Micro-services architecture 29
  • 33. Architectural Benefits •Extensibility and Flexibility –Integrations –Search providers –Knowledge sources •Improved scalability –Auto-scalable chat bot system –Horizontal and vertical •Depth of understanding –Leverages the richness of eBay data 31 ShopBot AI System Bot Memory ShopBot Fabric Dialog Manager Input Processors Facebook Messenger Knowledge Graph
  • 34. Learnings •Many users see ShopBot as a search engine: “shoes size 12” •Handling unrestricted user input is challenging when specialized on shopping: –Users greet the bot –Some expect it to know the weather –Others use free text such as ”I don’t like those” •Accurate response tops a fast response •Ask the user for disambiguation 32
  • 35. Status •Work started in Jan 2016 •Released as public beta in Oct 2016 •A platform for collecting data and learning •Full eBay inventory in the cloud •Continuing innovation into non-linear dialog interactions •Researching how to leverage AI in conversational commerce to make shopping easier/faster/delightful 33
  • 38. Watch the video with slide synchronization on InfoQ.com! https://www.infoq.com/presentations/ebay- shopbot