This document summarizes several Microsoft Cognitive Services including Language Understanding (LUIS), Speaker Recognition, Computer Vision, and Bing Search. LUIS allows developers to build models that understand natural language and add conversational capabilities to applications. Speaker Recognition recognizes who is speaking. Computer Vision analyzes images to extract objects and information. Bing Search enables intelligent search over data or the web. These services leverage AI technologies from Microsoft to add human-like capabilities to applications.

2. Trustandsecurity

6. www.botframework.com

7. Your Bot Framework Bot
Bot Connector Bot DirectoryBot Builder SDKs
Connect your bot(s) to
Skype, text/sms, Office 365
mail, Slack, and other
services.
Build great dialogs within
your Node.js- or C#-based
bot
Try, use, and add published
bots to the world’s top
conversation experiences
• Register, connect, publish and
manage your bot through
the bot dashboard
• Message routing and schema
mapping
• User and state management
• Embeddable web chat
control
• Open source SDK on Github
• From simple built-in prompts
and command dialogs to
simple to use yet
sophisticated ‘FormFlow’
dialogs
• Libraries, samples and tools
to make a great
conversationalist
• Chat emulator
• Leverage related services
available in Cognitive
Services
• Public directory of bots
registered and approved with
Bot Framework
• Users can try your bot from
the directory via the web chat
control
• Users can discover and add
your bot to the channels on
which it is configured

8. Your bot’s web
service
(e.g. built using
builder SDK)
Bot registration
Bot directory
Message routing &
mapping
Bot state storage
APIs

11. Microsoft
Cognitive
Services
Give your apps
a human side

12. Call a cab now
from Union
Square
NLP
Intent: CallCabRide
Address: Union Square
DateTime.date: now
Build dialogs and engage
with users in a natural way
Understand and process natural language,
determine users’ intent, and respond with
actions

13. The problem
Language understanding in human-computer interaction is:
Technically
challenging
It’s exceedingly difficult to enable a
computer to understand what a
person wants and to find the pieces
of information that are relevant to
their intent.
Costly
to implement
Building and maintaining machine
learning systems requires a large
investment of time, money and
engineering resources
Often
domain specific
In the past, building your own
machine learned models often
required assistance of a team of
data scientists that would customize
the models to the specific domain.

14. A Microsoft Cognitive Service that provides developers
with an easy way to create language models to allow
applications to understand user commands.
Create your
own LU model
Train by providing
examples
Deploy to an HTTP
endpoint and
activate on any
device
Maintain model
with ease
Introducing
Language
Understanding
Intelligence
Service (LUIS)

15. LUIS Common Usage Scenarios
LUIS offers integration with Microsoft
Bot Framework and Slack, which
enables developers to build and
connect intelligent bots to interact
with users no matter which device
they are on or which technology they
are using
Chat bots
LUIS uses pre-built models from Bing
and Cortana which enable developers
to easily add personal assistant
functionalities to their apps.
Virtual assistance
LUIS has been used to build a wide
range of IoT applications ranging
from a simple voice activated lights
control to smart kitchen appliances,
smart vending machines, facial
recognition door, and many more
IoT experiences

16. LUIS Benefits
Expert:
Leverages MSR
technology
LUIS leverages innovative AI
technology from Microsoft Research.
Easy:
Use simple UX editor to
create language
understanding models
Create models for your application to
better understand intents like "turn on
the lights", or entities such as "start a
new jog/walk/hike/bikeride". Tune
your model with in-depth performance
visualizations.
Flexible:
Activate models on any
device
Activate your language understanding
models from your application on your
phone, tablet, or any other device that
has access to the Internet.
Fast:
Add conversational
intelligence to your apps
in minutes
LUIS has a powerful dialog engine that
enables you to maintain context,
author and execute any dialog in just a
few steps.

17. Speaker
Recognition
Text to Speech
Conversion
Speech
Recognition
450 6th St.
San
Francisco
Is this Anna’s voice?
Anna
Hear, understand, and
speak back to users
Recognize what the user said, who said it,
and respond with text to spoken audio

18. Category People; 1 face found
Adult / Racy? False / True
Black & White? No
Dominant colors
Accent color
Distill actionable
information from images
From objects, to faces, and feelings,
analyze images and take action

19. Search and extract knowledge
from the web or your data
Enable intelligent search experiences over
your own data or the collective knowledge of
the web

20. Microsoft Cognitive Services
• Get started at: microsoft.com/cognitive
• Documentation: aka.ms/cognitivedocs
Microsoft Azure
• www.microsoftazure.com
Microsoft BotFramework
• Get started at: www.botframework
• Documentation: docs.botframework.com
Q&A Maker
• Get started at: qnamaker.ai
• Documentation: aka.ms/cognitivedocs