Upload
swami-chandrasekaran
View
707
Download
2
Tags:
Embed Size (px)
Citation preview
What Will You Build with Watson on Bluemix?
Swami Chandrasekaran Executive Architect - CTO Office IBM Watson Innovations [email protected] @swamichandra
SXSW 2015
© 2015 IBM Corporation 2 SXSW 2015
Please Note
IBM’s statements regarding its plans, directions, and intent are subject to change or withdrawal without notice at IBM’s sole discretion.
Information regarding potential future products is intended to outline our general product direction and it should not be relied on in making a purchasing decision.
The information mentioned regarding potential future products is not a commitment, promise, or legal obligation to deliver any material, code or functionality. Information about potential future products may not be incorporated into any contract. The development, release, and timing of any future features or functionality described for our products remains at our sole discretion.
Performance is based on measurements and projections using standard IBM benchmarks in a controlled environment. The actual throughput or performance that any user will experience will vary depending upon many factors, including considerations such as the amount of multiprogramming in the user’s job stream, the I/O configuration, the storage configuration, and the workload processed. Therefore, no assurance can be given that an individual user will achieve results similar to those stated here.
© 2015 IBM Corporation 3 SXSW 2015
Let’s get started
Preface
© 2015 IBM Corporation 4 SXSW 2015
Hi, I’m Swami Chandrasekaran
Executive Architect @ IBM
Watson
@swamichandra
© 2015 IBM Corporation 5 SXSW 2015
Topics
• Preface
• Cognitive Computing
• IBM Watson & Bluemix
• Watson Platform on Bluemix
• Beer, Personality & Cognition
• Let’s go to the movies
• In-car entertainment in my terms
© 2015 IBM Corporation 6 SXSW 2015
Chapter 1
Cognitive Computing?
© 2015 IBM Corporation 7 SXSW 2015
What will an inquisitive mind want to know from text?
Rarely has there been a better time for start-ups to raise money from Silicon Valley venture capitalists. But this golden age may not last long. At least that is what
Bill Gurley says. Mr. Gurley is a prominent investor who has spent a career betting on who the winners and
losers will be in the future of technology. Ciao!
Entities /Concepts & Relationships
Expand Concepts
Explore information
based on Concept
Associations
Sentiment & Sentiment
Targets
Deeper understanding
on author’s personality
Language identification
Ask questions & interact in
natural language
Resonance of the text
© 2015 IBM Corporation 8 SXSW 2015 8
Food for thought:
What if your applications have these capabilities?
© 2015 IBM Corporation 9 SXSW 2015
Not …
Yet !
Cognitive Systems
© 2015 IBM Corporation 10 SXSW 2015
So what are the Characteristics of a Cognitive System?
Scale in Proportion
Provide Supporting Evidence
Ingest Variety of (Big) Data
Respond with
Degree of Confidence
Learn with Every
Interaction
Offer Contextual
Guidance & Insights
Support for Decision Making
Generate & Evaluate
Hypothesis
Understand Natural
Language
Understand personality
at a Deeper level
Relate between Terms &
Concepts
Engage in a Dialog
© 2015 IBM Corporation 11 SXSW 2015
Analytics Russian Doll
Descriptive What has happened?
Predictive What could happen?
Prescriptive What should I do to for the best outcome?
Cognitive Tell me the best course of action
Busin
ess
Va
lue
© 2015 IBM Corporation 12 SXSW 2015
Chapter 2
IBM Watson & Bluemix
© 2015 IBM Corporation 13 SXSW 2015
Watson is creating a new
partnership between people
and computers that
enhances, scales and
accelerates human expertise.
© 2015 IBM Corporation 14 SXSW 2015
What is IBM Watson?
Cognitive Technology
Read & Understand Natural Language
Generate multiple hypothesis with Evidence
Support for several usage patterns
Natural extension of what humans can do at their best
Learns over time
Engagement Discovery Insights Extraction Platform
© 2015 IBM Corporation 15 SXSW 2015
What is IBM Bluemix?
Open-standards
based PaaS
Build, manage &
run diff types of
apps
Web
Mobile
Big Data
IoT
Cognitive
More…
Prebuilt capabilities
via API’s
DevOps Hybrid Apps
Layered Security
Containers, Runtimes, & Scalability
© 2015 IBM Corporation 16 SXSW 2015
Chapter 3
Watson Platform on Bluemix
© 2015 IBM Corporation 17 SXSW 2015
What if your app can do these from unstructured text?
Entities /Concepts & Relationships
Expand Concepts
Explore information
based on Concept
Associations
Sentiment & Sentiment
Targets
Deeper understanding
on author’s personality
Language identification
Ask questions & interact in
natural language
Resonance of the text
The tech industry will descend on Austin, Texas, starting March 13 for the annual music, film and
interactive festival known as South by Southwest. Here's why SXSW organizers now call Twitter -- a standout success at the event eight years ago -- an
"albatross."
© 2015 IBM Corporation 18 SXSW 2015
Visualization Rendering Graphical representations of data analysis for easier understanding
Personality Insights Engage users on their own terms
Language Identification Identifies the language in which text is written
Machine Translation Translate text from one language to another.
Concept Expansion Maps euphemisms to more commonly understood phrases
Message Resonance Communicate with people with a style and words that suits them
Question and Answer Direct responses to users inquiries fueled by primary document sources
Relationship Extraction Intelligently finds relationships between sentences components
Concept Insights Explores concepts behind your input, identifying associations beyond traditional text matching
Speech to Text Transcribes English speech to text with low latency
Text to Speech Synthesizes natural-sounding speech from English or Spanish text
Tradeoff Analytics Helps users make better choices by weighing multiple and often conflicting goals
Visual Recognition Analyzes the visual content of images and video frames to understand their content directly
Beta Watson Platform services available now with more in plan
© 2015 IBM Corporation 19 SXSW 2015
What will you build with Bluemix & Watson?
© 2015 IBM Corporation 20 SXSW 2015
Chapter 4
Beer, Personality & Cognition
© 2015 IBM Corporation 21 SXSW 2015 21
Which brewery / pub should I visit around SXSW?
© 2015 IBM Corporation 22 SXSW 2015
Visiting a new city
Pic Source: http://blog.reverbnation.com/2012/05/01/how-to-stand-out-from-the-crowd-tips-from-managers-sxsw-video/
After a long day …
… want to visit a local brewery
and watch the Thus night game
… so which brewery to choose?
© 2015 IBM Corporation 23 SXSW 2015
huge amount of data that is
available to help make a decision
Truth be told, more data often
leads to obfuscation
© 2015 IBM Corporation 24 SXSW 2015
What’s the atmosphere like in the brewery?
What kind of beers do they
offer?
What is difference between
“Hefeweizen and Kristalweizen”?
© 2015 IBM Corporation 25 SXSW 2015
What are the deeper social characteristics as exhibited
by other patrons in that location?
Can someone do linguistic analytics to infer cognitive and social characteristics?
© 2015 IBM Corporation 26 SXSW 2015
Informed decision-making comes from a long tradition of guessing and then blaming others for inadequate results.
- Scott Adams
© 2015 IBM Corporation 27 SXSW 2015
Introducing Brewery Master
• Show list of breweries / pubs based on geolocation
• Analyze tweets (originating from and/or about a brewery) and presents a psychographic vibe about that brewery below its list of beers
• Answer questions about beer and related topics using Watson Q&A
• Leverages IBM Watson cognitive services including Watson Personality Insights & Watson Question & Answer (Q&A)
• Responsive Node.js & AngularJS based application built & deployed on IBM Bluemix
• Also uses 3rd party API’s including BreweryDB, Twitter and Google Maps
© 2015 IBM Corporation 28 SXSW 2015
List of breweries around your
location
© 2015 IBM Corporation 29 SXSW 2015
Linguistic analytics to extract cognitive and social
characteristics, incl “Big Five” based on tweets about the
brewery / pub.
© 2015 IBM Corporation 30 SXSW 2015
List / types of beer sold at that location
© 2015 IBM Corporation 31 SXSW 2015
Ask questions in natural language about beers,
breweries, and all matter of facts related to beer
© 2015 IBM Corporation 32 SXSW 2015
© 2015 IBM Corporation 33 SXSW 2015
Chapter 5
Let’s go to the movies
© 2015 IBM Corporation 34 SXSW 2015
Ask questions about movie in
natural language
Enrichment based on extraction of concepts from
question
Sentiment of the movie based on
social media data
Multiple answering agents
Movie recommendation
based on user personality
Movie recommendation
based on user personality
© 2015 IBM Corporation 35 SXSW 2015
Heat map of tweets about Movies from around the
globe
Response from Watson
Question & Answer
Tweets about movie
extracted from Question
Sentiment of 100 tweets
dynamically extc’d abt the
movie
Lookup extracted
movie from QN in iTunes
Personality insights from
Watson Personality
Insights
© 2015 IBM Corporation 36 SXSW 2015
© 2015 IBM Corporation 37 SXSW 2015
© 2015 IBM Corporation 38 SXSW 2015
Chapter 6
In-car entertainment in my terms
© 2015 IBM Corporation 39 SXSW 2015
Consider this Scenario for a moment….
• Meet John Smith
• Very vocal person and maintains a strong digital presence
• Has a long day at work !!
• Tweets with certain emotions and walks to his car
2. Walk to Car
1. Tweets before
leaving work
© 2015 IBM Corporation 40 SXSW 2015
What if John Smith’s Connected Car app understood him at a deeper level including the current state of
his personality?
© 2015 IBM Corporation 41 SXSW 2015
Now reconsider this Scenario again ….
• Meet John Smith
• Very vocal person and maintains a strong digital
presence
• Has a long day at work !!
• Tweets with certain emotions and walks to his car
• Connected Car app in his car has done a psychographic analysis of his tweets / email / social
media data using Watson Personality Insights
• Personality Insights service provides the Big 5, Values, and Needs characteristics & associated values
• App recommends or auto-tunes to track / radio channel that would be appropriate
• Could potentially suggest other car settings incl seat adjustment, air conditioning, max speed limit *
Personality Insights
Share Location & Context
Walk to Car
Prediction
Past Interactions
Recommended Infotainment
© 2015 IBM Corporation 42 SXSW 2015
User Modeled Radio – Connected Car App
© 2015 IBM Corporation 43 SXSW 2015
User Modeled Radio – Connected Car App
Radio tracks / station from 8tracks played
based on User Modeling
characteristics
Extracted Tweets from the driver
Watson User Modeling
characteristics & values
Explanation for why the track / station was selected from
8tracks
© 2015 IBM Corporation 44 SXSW 2015
And many more ….
• Chef Watson
• Medical Diagnosis
• Drug Target Identification
• Personal Shopping Assistant
• Sales Assistant
• Digital Virtual Agent
• Travel Planning
• Veterinary Diagnosis
• Personal Wellness
• http://www.informationweek.com/big-data/big-data-analytics/ibm-watson-10-new-jobs-for-cognitive-computing/d/d-id/131942
© 2015 IBM Corporation 45 SXSW 2015
Access to Watson services has been radically expanded …
• Bluemix is an open-standards based PaaS & helps build your hybrid apps rapidly
• IBM Watson enhances, scales and accelerates human expertise
• Applications of the future will, – Augment our Senses
• Converse in natural language
• Deeper understanding of the individual & group
– Support Discovery & Decision Making
• Hypotheses based inferences
• Offer contextual insights
• Support at point of decision making
• Are you planning for these capabilities?
• What will you do with Watson & Bluemix?
© 2015 IBM Corporation 46 SXSW 2015
Call to Action
• https://ibm.biz/Bluemix-SXSW
• IBM Watson – http://www.ibmwatson.com
• IBM Bluemix – http://www.bluemix.net
• Watson Ecosystem program – http://www.ibm.com/smarterplanet/us/en/ibmwatson/ecosystem.html
• Growing social dialogue
– Twitter: @IBMWatson
• IBM Watson: A Platform for Innovation in the New Era of Computing – http://asmarterplanet.com/blog/2014/04/ibm-watson-ecosystem-platform-innovation.html