8. Understands
natural language and
human style
communication
Adapts and learns from
training, interaction, and
outcomes
Generates and
evaluates evidence-
based hypothesis
1
2
3
Cognitive computing is changing the game
9. So why is it so hard for computers to understand humans?
Noses that run and feet that smell?
How can a house can burn up as it burns down?
Does CPD represent a complex comorbidity of lung cancer?
What mix of zero-coupon, non-callable, A+ munis fit my risk
portfolio?
Person Organization
L. Gerstner IBM
J. Welch GE
W. Gates Microsoft
“If leadership is an art
then surely Jack Welch
has proved himself a
master painter during
his tenure at GE.”
Welch ran
this?
14. In less than 180 days Watson Ecosystem delivered …
$100M
Direct Investments
Fund
100K+
Visit Watson Mobile
Developer
Challenge
2500+
Ecosystem Partner
Inquiries
8
Major Universities
Announce Cognitive
Course Fall 2014
15. 4
… and created over 1B impressions!
Want to Work with
IBM's Watson?
IBM's Watson Woos
Developers
Have at it,
programmers: IBM
makes Watson
available via API
IBM Opens Up Its Watson
Cognitive Computer for
Developers
IBM Offers Watson as
Cloud Application Tool
IBM to Open Up Jeopardy
Winner Watson's 'Brain'
for Everyone
Seismic shift underway
in computing thanks to
IBM Watson
Cognitive Computing
For All: IBM Releases
a Legion of Watsons
IBM to Open Up
Watson to Third-
Party Developers
Soon Everyone Will Be
Able To Use Watson
IBM's Watson Artificial
Intelligence to Get
New Homes
IBM to Announce More
Powerful Watson via
the Internet
IBM's Watson Plays a
New Role as an
Application
Development Platform
IBM to Launch Watson
Cloud-Based
Development Platform
IBM Adds Rent-An-
Artificial-Intelligence
Powers to Watson
17. Watson Ecosystem
Tools, methodologies,
software developer kits
(SDKs) and API(s)
Free and fee based
content including general
knowledge and industry
content
Marketplace for critical
cognitive, big data, UI,
and mobility skills
• Cloud based sandbox
• Hosting Services
• Self-service portal – API
/ Tooling / SDK /
Methodology
• Starter Content
• General content
• Domain content
• Taxonomies
• Third-Party Content
• IBM subject matter
experts (500+)
• Third-party specialists
• Certification
WATSON
DEVELOPER CLOUD
WATSON CONTENT
STORE
WATSON TALENT
HUB
18. 4
Data
Ingestion
Training
Application
Scale at
Market
PartnerCo. & IBM
bring to market a
first of its kind
experience
PartnerCo., is
interested in the
Watson Ecosystem
Partner Program.
PartnerCo seeks
to personalize
customer
experiences.
PartnerCo.
identifies and
uploads content.
IBM collaborates
with PartnerCo. On
UX experience
Engaging the Watson Ecosystem
Key Enablers
Watson Sandbox
Watson Experience Manager
(APIs, Tools, SDKs)
Watson Resources
Launch Support & Scale Plan
Watson reads and
learns through Q&A
23. Design and Develop “Powered by Watson” apps using the API
Access Watson Developer Cloud
using Watson Experience Manager
Develop app “Powered
by Watson”
using APIs
Enrich Watson
with content
Train Watson
using tools and
experts
Test app
functional and
non-functional
Deploy application
1. Design interaction and integration patterns with Watson and implement
proof points as necessary
2. Establish the architecture with Watson and other components
3. Implement and model solution to scale as a product with customization
24. Application powered by Watson using QAAPI
Pose Natural
language question
Communicates
with Watson using
QAAPI
Get response
Optionally, further apply
Watson response
and/or other metadata
An example solution pattern used with Watson
• Design a solution with Watson as a key component
• Model the interaction patterns with Watson
• Create user experience mockups for the solution
25. Access the Watson Developer Cloud using the
Watson Experience Manager (WEM)
Use of the Watson Developer Cloud:
Watson Experience Manger to enrich content, train, and
test your Watson application
API to access the QA service to Watson
Customizable user interface to embed into your app
Guidelines on using Watson elements in the application
Upload content into the Watson Content Store or
source through Ecosystem partners
Access to a network of partners, customers,
content and talent
Support from a collaborative community of IBM
technical, marketing and sales resources
26. Proprietary Content
Acquire
Cleanse
Curate
Aggregate
Contract
Identify
Public Domain & Social
IBM Watson
Validate
Application
Partners
Source Prepare
Ingest
Deploy
Select
Content
Build Apps
w/API’s
Leverage
App Users
Unstructured Data
From Enterprise Apps
CRM eComm
Workforce HR
Product
Catalog
Trouble
Ticket
Domain Specific
Content Providers
Email,
Collaboration,
Open Data
ECM KMS
End Users
The content journey
Publish
Publish
Watson Content
Store
27. Understand graphics (images,
videos, sound …)
Ingest directly from a
structured data source
(Database, Datawarehouse)
There are architectural
patterns and capabilities in
Watson to be able to
integrate with structured
data sources
Nested tabular data
Call data records, sensor logs,
meter data, etc.
What Watson cannot ingest yet ….
28. What
Works?
Documents that are relevant to the use case under consideration
Understanding the validity of documents & frequency of changes
Well formed semantics – titles, sections, headings, sub-headings
What Does
Not?
Access to glossary, abbreviations would be helpful and preferred
If HTML – removing headers, footers, sidebars improves responses
Corpus contain answers to the intended questions
Scanned Docs (OCR), Charts, Non-English, Password Protected, Noisy Chat Logs
Nested Tables; Image right document with no descriptions; Log & Sensor Data
Mismatch in the content ingested and the questions end users are asking
General guidance on content selection
29. Content crawling & curation – Items to consider
Content Acquisition
– Crawling
– Integration with
ECM/KMS/DMS systems
– Open Services for
Lifecycle Collaboration
Content Curation
– Cleansing, Preparation,
Aggregation &
Enrichment
Content Lifecycle
Management
– Stale content
– Refreshing content
Content Metadata, Licenses &
Attribution
30. » Suite of tools for training
and testing Watson
» Test, train, and improve the
accuracy of the system
» SDK and a set of extensions
points to develop tools to add to
the platform
Training
Experiment,
Error Analysis
Key tools & capabilities – Watson common tooling platform
31. Summary - 3 key takeaways
1
2
3
Consider the possible interaction patterns when designing your Watson
app to create the optimal user experience (including factoids, descriptive,
Yes/No, procedural, procedural troubleshooting and definitions).
The Watson Experience Manager (WEM), provides a platform to upload
content, train Watson with question and answer pairs, and test the system
by asking questions.
The process for building a Watson app involves an iterative process of
integrating Watson capabilities using the QAAPI, uploading content, training
Watson, and testing the application for the appropriate response.
32. Let’s Take a Break…
Coming Next…
How Watson is Changing
The Game in Retail
Neil Patil
President, Software Group