SlideShare a Scribd company logo
1 of 47
State-of-the-art Search
with Azure Cognitive
Search
Brian McKeiver
About Me • Co-Owner, BizStream, Grand Rapids, MI
• .NET developer since Classic ASP and
Visual InterDev
• Azure developer since Windows Azure
was powered by Silverlight
• Focus is on enterprise websites powered
by CMS
• Kentico Xperience MVP (Traditional CMS)
• Kentico Kontent MVP (Headless CMS)
@mcbeev
Expectation
is the root of all heartache
Isn’t it just like Google?
Search is Hard
 It’s Complex
 Requires constant rebuilding / tuning / Love and Care
 Needs to be industry / site / context Specific
 Difficult to predict load
 If it doesn’t work, you’ll know Really Fast
 Anyone have anything else?
“ Hey Someone mentioned
Search is being ‘weird’ ”
…Ok, I’ll bite. Hold my beer…
Funny Meme here
It’s gonna be a long night …
Search Result Accuracy / Lack of
• 31% of all searches end in vain, returning useless, non-
relevant results or (even worse) returning no results at all.
• People who use search are twice more likely to convert,
compared to people who browse through the menus.
• 60% of the time, it works every time.
Presenting a Solution
Enter the next generation of Search
https://azure.microsoft.com/en-us/services/search/
New to it?
• PaaS solution offering
in Azure
• Allows you to add
sophisticated search
into your Apps and
Sites
• Quickly ingest, enrich,
and explore structured
and unstructured
content
The Basics
• API / SDK based
• Relevance (Scoring Profiles)
• Location Based Search (Geo Proximity)
• Dynamic Facets (Filters to narrow results by)
• Autocomplete (Predicative type ahead)
• Search Suggestions (actual results in the index, not just other terms)
• Synonyms (associate equivalent terms)
• Highlights (yellow highlighter via markup)
• Automatic UI
• Sorting/Paging
Enter Azure Search
Ingest Data
Structured Data Unstructured Data
Characteristics • Defined Content Models
• Usually, text only
• Easy to Search
• No defined data model
• Maybe text, images, sound, others
• Difficult to Search
Lives in • Relational databases
• Data warehouses
• XML, JSON
• Applications
• NoSQL databases
• Data warehouses
• Physical format
Typical Applications • CMS, CRM, ERP
• Business Apps
• Word processing
• Email
• Tools for editing media
Examples • Dates
• Phone Numbers
• Customer Names
• Addresses
• Product info
• Transactions
• Text files
• Reports
• Email messages
• Video files
• Images
Demo: Import Data
AI Enrichment Image Analysis
Entity Recognition
Keyword Extraction
DEMO: Enrich Data
By the Way Kentico Xperience…
Kentico Xperience is the award-winning digital
experience platform that combines content
management, digital marketing, and commerce,
on-premises or in the cloud.
Demo: Mcbeev.com
But why am I here?
Not just a software demos right?
Have you heard about it?
Lexical vs. Semantic
Lexical is “keyword
density”, break apart
content by white space and
see how many times it
appears.
Semantic is relating to
meaning in language or logic
or context.
Heart stress test results
Performance test
Regression testing
Test data
Tested positive for drugs
And many more…
Test
Explain Semantic 1
Practice test
Certification test
What is a unit test
UI Testing
Font-end test framework
A/B Tests
Isolated Integration Test
Pass final exam test
Explain Semantic 2
Pop Quiz
Hotshot
Transaxle
ASM
Mcbeevcom
Semantic Relevance
• Most Search engines have a default Similarity ranking for relevance
• Semantic ranking for relevance:
• Re-ranks the top matches of an initial result set
• backed by large transformer-based networks, trained for
capturing the semantic meaning of query terms (powered by
Bing)
• uses the context and meaning of words
Pre-processing
• Content
reduction
begins with the
initial results
based on
similarity
(~ top 50 results)
• String
reduction
(~ 128 words)
Extraction
• Pass the
reduced inputs
to Machine
Learning
• Long strings
summarized
into Captions
• Answers to
questions
Semantic Ranking
• Captions are
evaluated for
conceptual
and
semantic
relevance
How?
Semantic Captions
• The semantic subsystem determines what part of your content
has the characteristics of a caption or answer.
Search Answers
•What is …?
•How does …?
•Restaurants near me …
Search: What isKentico?
Spelling Correction
Demo: Semantic Search
Try it yourself
• Get Started with Azure Cognitive Search
• aka.ms/SemanticPreview
• aka.ms/SemanticGetStarted
• Azure Maps
• xperience.io
Pricing
Pricing page
• Azure Cognitive Search:
• Free, Basic, Standard,…
• Starts at about $73.00 / mn
• Real World Recommendation
• Standard 1
Search is Still Hard, but…
 Offloading of indexing Saves compute resources
 Search as a Service is Fast and reusable
 More and more AI is going into Search Results
 Semantic Search can help answer questions, gain
better accuracy of results
 Dynamic Facets are easier than ever to achieve
 Federated search is now possible (multiple datasets,
not just content on the website)
Questions?
Thank you
@mcbeev
www.mcbeev.com
mcbeev@gmail.com
THAT Conference 2021 - State-of-the-art Search with Azure Cognitive Search

More Related Content

What's hot

What's hot (6)

The SEO Workshop (session 2)
The SEO Workshop (session 2)The SEO Workshop (session 2)
The SEO Workshop (session 2)
 
The SEO Magic of Structured Data
The SEO Magic of Structured DataThe SEO Magic of Structured Data
The SEO Magic of Structured Data
 
Design Recommender systems from scratch
Design Recommender systems from scratchDesign Recommender systems from scratch
Design Recommender systems from scratch
 
Smx Ad Tech Seo Tactics
Smx Ad Tech Seo TacticsSmx Ad Tech Seo Tactics
Smx Ad Tech Seo Tactics
 
Recommendations with Elastic Search
Recommendations with Elastic SearchRecommendations with Elastic Search
Recommendations with Elastic Search
 
Generating docs from APIs
Generating docs from APIsGenerating docs from APIs
Generating docs from APIs
 

Similar to THAT Conference 2021 - State-of-the-art Search with Azure Cognitive Search

RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
Joaquin Delgado PhD.
 
RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
 RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning... RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
S. Diana Hu
 

Similar to THAT Conference 2021 - State-of-the-art Search with Azure Cognitive Search (20)

RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
RecSys 2015 Tutorial - Scalable Recommender Systems: Where Machine Learning m...
 
RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
 RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning... RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
RecSys 2015 Tutorial – Scalable Recommender Systems: Where Machine Learning...
 
How to SEO a Terrific - and Profitable - User Experience
How to SEO a Terrific - and Profitable - User ExperienceHow to SEO a Terrific - and Profitable - User Experience
How to SEO a Terrific - and Profitable - User Experience
 
SEO Introduction
SEO IntroductionSEO Introduction
SEO Introduction
 
Natural language processing and search
Natural language processing and searchNatural language processing and search
Natural language processing and search
 
Search Engine Optimization (Seo) for Developers
Search Engine Optimization (Seo) for DevelopersSearch Engine Optimization (Seo) for Developers
Search Engine Optimization (Seo) for Developers
 
Building Search Systems for the Enterprise
Building Search Systems for the EnterpriseBuilding Search Systems for the Enterprise
Building Search Systems for the Enterprise
 
State of Search 2017 - Semantics and Science - Upasna Gautam
State of Search 2017 - Semantics and Science - Upasna GautamState of Search 2017 - Semantics and Science - Upasna Gautam
State of Search 2017 - Semantics and Science - Upasna Gautam
 
Digital marketing
Digital marketingDigital marketing
Digital marketing
 
Semantic Search: Fast Results from Large, Non-Native Language Corpora with Ro...
Semantic Search: Fast Results from Large, Non-Native Language Corpora with Ro...Semantic Search: Fast Results from Large, Non-Native Language Corpora with Ro...
Semantic Search: Fast Results from Large, Non-Native Language Corpora with Ro...
 
SEO in the Age of Artificial Intelligence | How AI influences Search
SEO in the Age of Artificial Intelligence | How AI influences SearchSEO in the Age of Artificial Intelligence | How AI influences Search
SEO in the Age of Artificial Intelligence | How AI influences Search
 
Análisis del roadmap del Elastic Stack
Análisis del roadmap del Elastic StackAnálisis del roadmap del Elastic Stack
Análisis del roadmap del Elastic Stack
 
SharePoint Fest Chicago Presentation
SharePoint Fest Chicago PresentationSharePoint Fest Chicago Presentation
SharePoint Fest Chicago Presentation
 
SEO Training Course Online, Learn SEO, SEO for Beginners, Complete SEO Tutorial
SEO Training Course Online, Learn SEO, SEO for Beginners, Complete SEO TutorialSEO Training Course Online, Learn SEO, SEO for Beginners, Complete SEO Tutorial
SEO Training Course Online, Learn SEO, SEO for Beginners, Complete SEO Tutorial
 
Análisis de las novedades del Elastic Stack
Análisis de las novedades del Elastic StackAnálisis de las novedades del Elastic Stack
Análisis de las novedades del Elastic Stack
 
Search Engine Optimization
Search Engine OptimizationSearch Engine Optimization
Search Engine Optimization
 
Latest trends in AI and information Retrieval
Latest trends in AI and information Retrieval Latest trends in AI and information Retrieval
Latest trends in AI and information Retrieval
 
AI, Search, and the Disruption of Knowledge Management
AI, Search, and the Disruption of Knowledge ManagementAI, Search, and the Disruption of Knowledge Management
AI, Search, and the Disruption of Knowledge Management
 
Search Analytics - Comperio
Search Analytics - ComperioSearch Analytics - Comperio
Search Analytics - Comperio
 
How Google works
How Google worksHow Google works
How Google works
 

More from Brian McKeiver

More from Brian McKeiver (15)

Delivering on the Promise or AI for content.pptx
Delivering on the Promise or AI for content.pptxDelivering on the Promise or AI for content.pptx
Delivering on the Promise or AI for content.pptx
 
Great Lakes Area .Net UG: Optimize .Net Azure App Services
Great Lakes Area .Net UG: Optimize .Net Azure App ServicesGreat Lakes Area .Net UG: Optimize .Net Azure App Services
Great Lakes Area .Net UG: Optimize .Net Azure App Services
 
Prairie Code 2019: How to Win Friends and Influence Better Developer Estimates
Prairie Code 2019: How to Win Friends and Influence Better Developer EstimatesPrairie Code 2019: How to Win Friends and Influence Better Developer Estimates
Prairie Code 2019: How to Win Friends and Influence Better Developer Estimates
 
Code on the Beach 2019 - Let's Take a Tour of .Net Core: CLI
Code on the Beach 2019 - Let's Take a Tour of .Net Core: CLICode on the Beach 2019 - Let's Take a Tour of .Net Core: CLI
Code on the Beach 2019 - Let's Take a Tour of .Net Core: CLI
 
Code on the Beach 2018: Build an E-Commerce Chatbot on Azure Bot Framework v4
Code on the Beach 2018: Build an E-Commerce Chatbot on Azure Bot Framework v4Code on the Beach 2018: Build an E-Commerce Chatbot on Azure Bot Framework v4
Code on the Beach 2018: Build an E-Commerce Chatbot on Azure Bot Framework v4
 
GLSEC 2017 Build an Open Data .Net MVC site in 30 mins
GLSEC 2017 Build an Open Data .Net MVC site in 30 minsGLSEC 2017 Build an Open Data .Net MVC site in 30 mins
GLSEC 2017 Build an Open Data .Net MVC site in 30 mins
 
Kentico Cloud - Our First Impressions
Kentico Cloud - Our First Impressions Kentico Cloud - Our First Impressions
Kentico Cloud - Our First Impressions
 
Content Last: A Strategy for Success or Failure?
Content Last: A Strategy for Success or Failure?Content Last: A Strategy for Success or Failure?
Content Last: A Strategy for Success or Failure?
 
Amp up your Site with Accelerated Mobile Pages
Amp up your Site with Accelerated Mobile PagesAmp up your Site with Accelerated Mobile Pages
Amp up your Site with Accelerated Mobile Pages
 
How to Wield Kentico 9 in the Real World
How to Wield Kentico 9 in the Real WorldHow to Wield Kentico 9 in the Real World
How to Wield Kentico 9 in the Real World
 
Growth Hacking with Kentico
Growth Hacking with KenticoGrowth Hacking with Kentico
Growth Hacking with Kentico
 
Dog Food Con 2015 Integrate & Automate CMS Deployments
Dog Food Con 2015 Integrate & Automate CMS DeploymentsDog Food Con 2015 Integrate & Automate CMS Deployments
Dog Food Con 2015 Integrate & Automate CMS Deployments
 
Convert More With Marketing Automation
Convert More With Marketing AutomationConvert More With Marketing Automation
Convert More With Marketing Automation
 
Kentico 8 EMS API Deep Dive
Kentico 8 EMS API Deep DiveKentico 8 EMS API Deep Dive
Kentico 8 EMS API Deep Dive
 
Kentico Connection 2014 Boston Upgrade Like a Pro
Kentico Connection 2014 Boston Upgrade Like a ProKentico Connection 2014 Boston Upgrade Like a Pro
Kentico Connection 2014 Boston Upgrade Like a Pro
 

Recently uploaded

Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 

Recently uploaded (20)

Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
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
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Navi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Navi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot ModelNavi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Navi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
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...
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu SubbuApidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
 

THAT Conference 2021 - State-of-the-art Search with Azure Cognitive Search

  • 1. State-of-the-art Search with Azure Cognitive Search Brian McKeiver
  • 2.
  • 3.
  • 4. About Me • Co-Owner, BizStream, Grand Rapids, MI • .NET developer since Classic ASP and Visual InterDev • Azure developer since Windows Azure was powered by Silverlight • Focus is on enterprise websites powered by CMS • Kentico Xperience MVP (Traditional CMS) • Kentico Kontent MVP (Headless CMS) @mcbeev
  • 5. Expectation is the root of all heartache Isn’t it just like Google?
  • 6. Search is Hard  It’s Complex  Requires constant rebuilding / tuning / Love and Care  Needs to be industry / site / context Specific  Difficult to predict load  If it doesn’t work, you’ll know Really Fast  Anyone have anything else?
  • 7. “ Hey Someone mentioned Search is being ‘weird’ ” …Ok, I’ll bite. Hold my beer…
  • 8.
  • 10. It’s gonna be a long night …
  • 11. Search Result Accuracy / Lack of • 31% of all searches end in vain, returning useless, non- relevant results or (even worse) returning no results at all. • People who use search are twice more likely to convert, compared to people who browse through the menus. • 60% of the time, it works every time.
  • 12. Presenting a Solution Enter the next generation of Search
  • 14. New to it? • PaaS solution offering in Azure • Allows you to add sophisticated search into your Apps and Sites • Quickly ingest, enrich, and explore structured and unstructured content
  • 15. The Basics • API / SDK based • Relevance (Scoring Profiles) • Location Based Search (Geo Proximity) • Dynamic Facets (Filters to narrow results by) • Autocomplete (Predicative type ahead) • Search Suggestions (actual results in the index, not just other terms) • Synonyms (associate equivalent terms) • Highlights (yellow highlighter via markup) • Automatic UI • Sorting/Paging
  • 17. Ingest Data Structured Data Unstructured Data Characteristics • Defined Content Models • Usually, text only • Easy to Search • No defined data model • Maybe text, images, sound, others • Difficult to Search Lives in • Relational databases • Data warehouses • XML, JSON • Applications • NoSQL databases • Data warehouses • Physical format Typical Applications • CMS, CRM, ERP • Business Apps • Word processing • Email • Tools for editing media Examples • Dates • Phone Numbers • Customer Names • Addresses • Product info • Transactions • Text files • Reports • Email messages • Video files • Images
  • 23.
  • 24. By the Way Kentico Xperience… Kentico Xperience is the award-winning digital experience platform that combines content management, digital marketing, and commerce, on-premises or in the cloud.
  • 26. But why am I here? Not just a software demos right?
  • 27. Have you heard about it?
  • 28.
  • 29. Lexical vs. Semantic Lexical is “keyword density”, break apart content by white space and see how many times it appears. Semantic is relating to meaning in language or logic or context.
  • 30. Heart stress test results Performance test Regression testing Test data Tested positive for drugs And many more… Test Explain Semantic 1 Practice test Certification test What is a unit test UI Testing Font-end test framework A/B Tests Isolated Integration Test Pass final exam test
  • 34. ASM
  • 36. Semantic Relevance • Most Search engines have a default Similarity ranking for relevance • Semantic ranking for relevance: • Re-ranks the top matches of an initial result set • backed by large transformer-based networks, trained for capturing the semantic meaning of query terms (powered by Bing) • uses the context and meaning of words
  • 37. Pre-processing • Content reduction begins with the initial results based on similarity (~ top 50 results) • String reduction (~ 128 words) Extraction • Pass the reduced inputs to Machine Learning • Long strings summarized into Captions • Answers to questions Semantic Ranking • Captions are evaluated for conceptual and semantic relevance How?
  • 38. Semantic Captions • The semantic subsystem determines what part of your content has the characteristics of a caption or answer.
  • 39. Search Answers •What is …? •How does …? •Restaurants near me … Search: What isKentico?
  • 42. Try it yourself • Get Started with Azure Cognitive Search • aka.ms/SemanticPreview • aka.ms/SemanticGetStarted • Azure Maps • xperience.io
  • 43. Pricing Pricing page • Azure Cognitive Search: • Free, Basic, Standard,… • Starts at about $73.00 / mn • Real World Recommendation • Standard 1
  • 44. Search is Still Hard, but…  Offloading of indexing Saves compute resources  Search as a Service is Fast and reusable  More and more AI is going into Search Results  Semantic Search can help answer questions, gain better accuracy of results  Dynamic Facets are easier than ever to achieve  Federated search is now possible (multiple datasets, not just content on the website)