3. We need smarter apps
but the processing power of our smartphones is not enough for
everything
4. We need smarter services
that can be easily integrated with our apps
5. What are Cognitive Services?
The Cognitive Services are a collection of complimentary
‘services’ (29 and counting) to assist developers with the
processing of natural input sources such as speech, images and
emotion.
The Cognitive Services are organized into five pillars: Speech,
Language, Vision, Knowledge and Search.
By combining different Cognitive Services developers can build
intelligent apps with powerful algorithms using just a few lines of
code.
6. Cognitive Services
Vision SpeechLanguage KnowledgeSearch
Computer Vision
Content Moderator
Emotion
Face
Video Indexer
LUIS
Spell Check
Linguistic Analysis
Text Analytics
Translator
Web Language Model
Speech
Speaker Recognition
Translator
Custom
Academic
Entity Linking
Exploration
QnA Maker
Recommendations
Autosuggest
Image
News
Video
Web
Entity
Custom
Vision Service
Custom
Language
Understanding
Custom
Speech
Custom
Search
Custom
Decision Service
7. Language
Language Understanding Intelligent Service PREVIEW
Teach your apps to understand commands from
your users
Bing Spell Check API
Detecting and correcting spelling mistakes in your
app
Web Language Model API PREVIEW
Use the power of predictive language models
trained on web-scale data
Translator Speech API
Easily conduct real-time speech translation with a
simple REST API call
Text Analytics API PREVIEW
Easily evaluate sentiment and topics to
understand what users want
Translator Text API
Easily conduct machine translation with a
simple REST API call
Linguistic Analysis API PREVIEW
Simplify complex language concepts and
parse text with the Linguistic Analysis API.
8. Computer Vision APIs
Computer Vision API
Distil actionable information from images
Content moderator
Automated image, text and video moderation
Video Indexer PREVIEW
Unlock video insights
Face API
Detect, analyse, organise and tag faces
in photos
Emotion API PREVIEW
Personalise user experiences with emotion
recognition
Custom Vision Service PREVIEW
Easily customise your own state-of-the-art
computer vision models for your unique use case.
9. Speech APIs
Custom Speech Service PREVIEW
Overcome speech recognition barriers like speaking
style, background noise and vocabulary
Bing Speech API
Convert speech to text and back again to understand
user intent
Speaker Recognition API PREVIEW
Use speech to identify and authenticate
individual speakers
10. Search APIs
Bing Autosuggest API
Give your app intelligent autosuggest options for
searches
Bing News Search API
Search for news and get comprehensive results
Bing Web Search API
Get enhanced search details from billions of web
documents
Bing Entity Search API
Enrich your app by infusing knowledge search into
existing content
Bing Image Search API
Search for images and get comprehensive results
Bing Video Search API
Search for videos and get comprehensive results
Bing Custom Search PREVIEW
An easy-to-use, advert-free, commercial-grade
search tool that lets you deliver the results you
want.
11. Knowledge APIs
Recommendations API PREVIEW
Predict and recommend items that your customers
want
Knowledge Exploration Service PREVIEW
Enable interactive search experiences over structured
data via natural language inputs
Entity Linking Intelligence Service API PREVIEW
Power your app’s data links with named entity
recognition and disambiguation.
Academic Knowledge API PREVIEW
Tap into the wealth of academic content in the
Microsoft Academic Graph
QnA Maker API PREVIEW
Distil information into conversational, easy-to-
navigate answers.
Custom Decision Service PREVIEW
A cloud-based, contextual decision-making API
that sharpens with experience
13. Linguistic Analysis
Programmatically analyze text and get:
• Language
• Key phrase extraction
• Sentiment analysis
• Topic detection
examples:
I had a wonderful experience! The rooms
were wonderful and the staff was helpful.
I had a terrible time at the hotel. The staff
was rude and the food was awful.
15. Language Understanding
Intelligent Service - LUIS
Build custom language models:
LUIS provides simple tools that enable you to build your own
language models (intents/entities) which allow any application/bot
to understand your commands and act accordingly
Define Concepts
(intents and
entities)
Provide Examples
(uterances)
Deploy Active Learning
16. Language Understanding
Intelligent Service - LUIS
Example:
“News about flight delays”
{
"entities":[{"entity":flight_delays", "type":"Topic"}],
"intents":[
{"intent":"FindNews", “score":0.99853384},
{"intent":"None", "score":0.07289317},
{"intent":"ReadNews", "score":0.0167122427},
{"intent":"ShareNews", "score":1.0919299E-06}
]
}
17. Language Understanding
Intelligent Service - LUIS
Powering bots:
• Microsoft bot framework
• Bots built with Node.js or C#
• Dialogs to model a conversation
• Many types of dialogs
18. Roll your own with REST APIs
Simple to add: just a few lines of
code required
Integrate into the language and
platform of your choice
Breadth of offerings helps you find the
right API for your app
Built by experts in their field from
Microsoft Research, Bing, and Azure
Machine Learning
Quality documentation, sample
code, and community support
Easy Flexible Tested
GET A
KEY
Cognitive Services
25. The IoT
Customer
Journey
Objective
Increase efficiency by reducing costs and
eliminating bottlenecks
Organizational readiness
This is a great place to start if you have:
• An identified business process you
want to gain visibility into
• An understanding of the kind of data
you need in order to support your
business objective
• Devices capable of providing the
type of data required
26. Objective
Drive innovation and increase revenue
using your existing assets
Organizational readiness
This is a great place to start if you have :
• The ability to interpret incoming data
from devices
• An understanding of the impacted
business groups and processes
• A plan for using data to drive business
process improvements
The IoT
Customer
Journey
27. The IoT
Customer
Journey
Objective
Create new lines of business and new
business models
Organizational readiness
This is a great place to start if you have :
• A strong baseline of historical device data
(e.g. usage trends, repair records)
• Visibility into real-time operational
status
• Predictive capability from advanced
analytics
• Stakeholder commitment to support
change efforts
28. IoT projects are complex
Time-consuming to
stand up
Hard to scaleIncompatible with current
infrastructure
Difficult to maintain
cohesive security