Watson innovation day purpose is helping you to understand how Watson can propel your business to a new level and give you a tangible feel of how IBM can partner with you.
2. 2 Š 2014 International Business Machines Corporation
Š 2014 International Business Machines Corporation
2
The Watson Ecosystem is about you, and this Watson
Innovation Day is for you
Hereâs what we hope you get out of today:
⢠Inspire you with a clearer understanding of how IBM
Watson can propel your business to a new level
⢠Help shape the vision for your Watson cognitive
application with an actionable success criteria
⢠Equip you with a pragmatic sense for the process to
build a Watson application and the enabling
technology that is available to you
⢠Give you a tangible feel for how IBM will partner
with you, from inception through go-to-market
and beyond to help you make money
3. 3 Š 2014 International Business Machines Corporation
3
Whatâs in it for you in the IBM Watson Ecosystem partnership?
⢠Growth through new revenue opportunities and reach to new clients
⢠Branding your cognitive application; âPowered by Watsonâ
⢠Build a competitive edge to disrupt your market
⢠Align with IBM Watson Research as we move build the
cognitive era
⢠Collaborative IBM/Partner presentations at industry &
IBM customer events
⢠Define a new industry standard
4. 4 Š 2014 International Business Machines Corporation
4
Time Agenda Speaker
8:00am â 8:30am Registration / Breakfast / Networking
8:30a-9:30am IBM Watson Level Set: What is Watson / Cognitive computing, What does the
Ecosystem have to offer you? Where is IBM taking Watson in the future?
Lauri Saft
Director, IBM Watson Partner
Recruiting
9:30am - 10:15am Getting Ready for Watson â How to Evaluate the Business and Technical
Synergy and Chart Your Course for a Watson Cognitive Application
Jodie Sasse
Director, IBM Watson Partner
Engagement
10:15am - 10:30am
Break
10:30am - 11:00pm
Our Journey with Watson
Jeff Cohen
Co-Founder, WellTok
11:00am â 11:45am Getting Started with Watson: An Overview of the âPowered by Watsonâ
Development Process with the Watson Developer Cloud
Sridhar Sudarsan
CTO, IBM Watson Ecosystem
11:45am â 12:00pm
Wrap up: Where Do I Go From Here?
Lauri Saft
12:00pm â 1:00pm
Lunch and Networking Chicago room
1:00pm â 3:00pm
1:1 Consultations with IBM Watson Executives
Hands on âWork with Watsonâ Sessions with IBM Watson Technologists
Breakout rooms
Agenda
6. 6 Š 2014 International Business Machines Corporation
On February 14, 2011
made history
7. 7 Š 2014 International Business Machines Corporation
Watson is ushering in a new era of computing
Tabulating
Systems Era
Programmable
Systems Era
Cognitive
Systems Era
1900 1950 2011
8. 8 Š 2014 International Business Machines Corporation
Š
20
Watson has opened up a world of
new possibilities
size
speed
corpus
flexibility
#users
size
speed
corpus
flexibility
#users
2880 cores
Single user system
2-3 sentences input
5+ days to retrain
Wikipedia, general corpus
Single Power 750, 240% faster
1000s of users
20 pages of input
< Day to ingest and train
Medical corpus
Watson cloud service
Millions of users
Dialog chaining
Few hours
Broad industry corpus
s
sp
corp
flexibi
#users
9. 9 Š 2014 International Business Machines Corporation
2013 recap
Watson
Engagement
Advisor - May 21st
Watson Engagement
Advisor announced
Cross-industry and cross-
geography play
January April July October
First Two Commercial
Offerings
February 8th
First 2 healthcare products
were announced with MSK and
WellPoint
2014
Watson Ecosystem
November 14th
Watson Ecosystem
announced
Driving innovation and
fostering new possibilities
Watson Healthcare
Update â Oct. 18
MD Anderson launches
Expert Oncology Advisor
powered by Watson
Watson used to bridge
clinical practice and
medical research
10. 10 Š 2014 International Business Machines Corporation
Watson has the potential to transform how industries and
individuals interact and make every day decisions. Watson
helps make individuals, enterprises and society smarter by
engaging the collective knowledge and insight of the market.
IBM is investing in Watsonâs future â January, 2014 announce
â˘IBM Watson Group
â˘2000+ professionals
â˘$1B+ invested over next few years
â˘New Watson HQ â NY (Silicon Alley)
â˘New Watson Offerings
â˘$100M equity investment in the Watson
Ecosystem
11. 11 Š 2014 International Business Machines Corporation
Understands
natural language
and human style
communication
Adapts and learns
from training,
interaction, and
outcomes
Generates and
evaluates
evidence-based
hypothesis
1 2
3
Watson combines transformational capabilities to deliver a new
world experience
Watson understands me.
Watson engages me.
Watson learns and
improves over time.
Watson helps me
discover.
Watson establishes trust.
Watson has endless
capacity for insight.
Watson operates in a
timely fashion.
12. 12 Š 2014 International Business Machines Corporation
Watson makes sense of natural language, like:
Welch ran
this?
âIf leadership is an art
then surely Jack Welch
has proved himself a
master painter during his
tenure at GE.â
Person Organization
L. Gerstner IBM
J. Welch GE
W. Gates Microsoft
Structured Data Unstructured Data
Understanding language is critical to 21st century computing
⢠Noses that run and feet that smell?
⢠Ship by truck and send cargo by ship?
⢠How can a slim chance and a fat chance
be the same, while a wise man and a wise
guy are opposites?
⢠How can a house burn up as it burns down?
⢠Why do we fill in a form by filling it out?
⢠How does an alarm go off by going on?
13. 13 Š 2014 International Business Machines Corporation
Deep natural language processing is NOT keyword search
Watson is not about rules-based search or speech processing
Traditional systems use keyword and synonym matching to
find documents
Expert systems need rules to demonstrate expertise
These systems trade off precision for accuracy outside of
what they are programmed to recognize
Cognitive systems, like humans, know how to apply context,
fill in the gaps, resolve ambiguity and uncertainty, and
accurately interpret language
Keyword search and
expert systems are
not able to recognize
the subtleties,
idiosyncrasies, and
ambiguities inherent
in common human
language
14. 14 Š 2014 International Business Machines Corporation
Answering complex questions requires more than keyword
evidence
explorer
India
In May
1898
India
In May
celebrated
anniversary
in Portugal
In May, Gary arrived in India
after he celebrated his
anniversary in Portugal
Portugal
400th
anniversary
celebrated
Gary
In May 1898 Portugal celebrated
the 400th anniversary of this
explorerââââs arrival in India
This evidence suggests
âGaryâ is the answer
BUT the system must
learn that keyword
matching may be
weak relative to other
types of evidence
arrived in
arrival in
Legend
Keyword ââââHitââââ
Reference Text
Answer
Weak evidenceRed Text
Question: Supporting Evidence:
15. 15 Š 2014 International Business Machines Corporation
Watson leverages multiple algorithms to perform deeper
analysis
27th May
1498
Vasco da
Gama
landed in
arrival
in
explorer
India
Para-
phrases
Geo-
KB
Date
Match Stronger evidence can be
much harder to find and
scoreâŚ
Search far and wide
Explore many hypotheses
Find judge evidence
Many inference
algorithms
On the 27th of May 1498, Vasco
da Gama landed in Kappad
Beach
400th anniversary
Portugal
May 1898
celebrated
In May 1898 Portugal celebrated the
400th anniversary of this explorerââââs
arrival in India.
Kappad
Beach
Legend
Temporal Reasoning
Reference Text
Answer
Statistical Paraphrasing
GeoSpatial Reasoning
Question: Supporting Evidence:
17. 17 Š 2014 International Business Machines Corporation
Enhance customer / member /Enhance customer / member /Enhance customer / member /Enhance customer / member /
citizen / patients experiencecitizen / patients experiencecitizen / patients experiencecitizen / patients experience
Watson Developer Cloud
delivers the tools,
methodologies, software
developer kits and API(s) for
App Partners to build the next
generation of cognitive
applications.
Watson Talent
Hub bridges
App Partners
resource gaps
by providing a
marketplace for
critical
cognitive, big
data, UI, and
mobility skills.
IBM Watson Ecosystem â a community of complementary,
interconnected partners
Watson Content
Store provides
sources of free
and fee based
content
including public,
subscribed and
enterprise
content.
App
Partner
Talent
Partner
Content
Provider/Partner
Watson
Content
Store
WatsonWatsonWatsonWatson
DeveloperDeveloperDeveloperDeveloper
CloudCloudCloudCloud
Watson
Platform
& Tools
18. 18 Š 2014 International Business Machines Corporation
A community for ongoing dialogue, collaboration & interaction
Developer Q&A Forum: DeveloperWorks
Active forums and blogs
https://www.ibmdw.net/watson/
Engagement with IBM Watson
technologists and other SMEâs
âOffice Hoursâ on the dW forum
12-1pm EST through April 14, 2014
Watson âTech Talksâ web conferences â
coming in Q2, 2014
Growing social dialogue
Twitter: @IBMWatson
LinkedIn: Watson Advocates Group
Facebook: facebook.com/ibmwatson
In process
Single community with tools, tips, tricks, ideas
and conversation
Meet-ups and hangouts with Cognitive
business & tech leaders
Content, Interaction, and events
19. 19 Š 2014 International Business Machines Corporation
1
⢠Work with a handful of partners in target industries (healthcare, retail, travel & transportation)
⢠Harden platform & tools
⢠Refine content ingestion
⢠Build scalable approach to the broader partner marketplace
2Q 2014
⢠First âPowered by Watsonâ cognitive application partners commercialize products
and bring to market
⢠Expand content partnerships for general domain and industry specific content stores
⢠Talent partnerships expanded to meet needs of new partners and new markets
2H 2014
⢠Expansion into English speaking international markets
⢠Streamlined self-service tools deployed through Watson Experience Manager
⢠Additional Watson capabilities/services brought online for Ecosystem Partners
1H 2015
⢠Developer Cloud opened to a broader
partner marketplace
The Partner Ecosystem will expand aggressively each quarter
1H 2014
20. 20 Š 2014 International Business Machines Corporation
A clearing house of unique and varying sources of data â
general knowledge, industry specific content, and subject
matter expertise â from a variety of sources.
The Watson Content Store offers fuel for apps
20Š 2014 International Business Machines Corporation
ISVs
â˘Fuel your application with a
variety of content
â˘Easily access multiple sources
â˘Quickly get value from content
Content Providers
⢠Distribute via a new channel
⢠Generate revenue
⢠Control price & use
⢠Gain insight into adoption
Benefits
21. 21 Š 2014 International Business Machines Corporation
Healthcare Example using IBM Watson Content Store
Clients
Types of Content
⢠Content Store: General,
Domain Specific
⢠App: Partner Specific,
Client Specific
Content Models
⢠Subscription
⢠Transaction
⢠Other
MedInsights
Procedures
MMG Best
Practices
Domain
Content
Partner
App
Client &
Partner
Content
Healthcare Platform
General
Content
Watson Healthcare Cloud
MidWest Medical
Group
Excel Physicians
Practice
MedInsights
powered by IBM Watson
Watson Platform
Medical
Journals
22. 22 Š 2014 International Business Machines Corporation
IBM Watson works with talent partners to make their skills available in
the Watson Talent Hub to assist Development Partners
Watson SMEs
provide input and
coaching to the
Talent Partners
Talent Partners
develop Watson-
validated talent
Talent Partners
build individual
landing pages
Talent Partners
engage App
Partners to learn
about their needs
Talent Partner
receive project
requests from App
Partners
App Partners
agree to terms
and provide
basic information
App Providers
gain access to
Watson-validated
talent
App
Partners
Talent
Partners
Watson hosts a
Talent Hub within
the Experience
Manager
App Partners find
Talent Partner
landing pages
through WEM
Talent Hub
23. 23 Š 2014 International Business Machines Corporation
Talent groups follow the cognitive application development
lifecycle. NLP and AI skills are not required to launch a âPowered
by Watson app
Content
Management
User Experience
Design
Cross-Platform /
Web
Mobile
Front-end
Development
Web Crawling &
Content Scraping
Web Scripting
Parsing
User Experience
User Interface Web Framework Libraries
Programming
TalentGroupsSpecialtyFields
Talent groups launching in 2Q 2014
24. 24 Š 2014 International Business Machines Corporation
Access to talent is simplified and streamlined
25. 25 Š 2014 International Business Machines Corporation
Talent validation will evolve into a formal Certification Program
Content Management
Situational Exam
Watson Fundamentals
Multiple Choice
User Experience
Situational Exam
Front-end Development
Situational Exam
Content Collection
Content Curation
Formatting
Cleansing
Recurring feeds
UI/UX Design
Visual
Copy
Cross-platform Application
Development
Mobile Application
Development
Ideation
Prototyping
Broad-based knowledge of Watson
Talent Partner Qualified Talent
Level II: Demonstrated domain expertise as it relates to Watson
Level I: Demonstrated general domain expertise and understanding of Watson
26. 26 Š 2014 International Business Machines Corporation
Take the Watson Developer Challenge:
⢠Opportunity for Mobile
Developers to create the next
great cognitive mobile app â
announced at Mobile World
Congress by Ginni Rometty
⢠Finalists get access to Watson
for one business week to
prototype their Watson
instance and mobile app
⢠The top 5 prototypes present
live to IBM Executives
⢠Winners join the Watson
Ecosystem and get access to
IBM Interactive design Services
27. 27 Š 2014 International Business Machines Corporation
Contest Overview
Submissions: 2/26/2014 â 4/15/2014
Finalist selection: 4/28
Prototyping Period: 4/28 â 5/20
Winners Announced: 5/31
⢠Submission phase: Applicant submit
their application concepts.
⢠Judging is based on:
⢠Target market that is clearly
defined
⢠Compelling use case for Watson
⢠Can be delivered via mobile
⢠Access to data to provide insight
(English prose in text form)
⢠Existing customer base
28. 28 Š 2014 International Business Machines Corporation
1:1 business and technical consultations are available
today from 1-3pm. Sign up at registration desk.
29. Getting Ready for Watson
Evaluating the Business and Technical
Synergy and Charting Your Course
Jodie Sasse
Program Director, Engagements
IBM Watson Ecosystem
30. 30 Š 2014 International Business Machines Corporation
How do I start my journey with IBM Watson?
1.What is the business value to the âPowered by Watsonâ
application you intend to build?
2.Does the application draw upon the unique characteristics
and capabilities of a cognitive offering?
3.Has the content that will fuel the application been
identified and can it be secured/licensed for the intended use?
Have a question and
answer interaction
pattern, with questions
posed in natural
language
Seek answers and
insights from a
defined content
repository comprised
largely of
unstructured data
Need transparency
and supporting
evidence for
confidence weighted
responses to questions
and queries
The best use cases mustâŚ..
31. 31 Š 2014 International Business Machines Corporation
Content
Capabilities
ConceptCommitment
Clients
⢠Ownership / Access to content
⢠Form - unstructured
⢠Format â ingestible
⢠Use case
alignment
w/technology
⢠Leverages
cognitive
strengths
⢠Market potential
⢠Market impact
(disruptive)
⢠Exec sponsorship
⢠Priority capability
⢠Resource
commitment
⢠Anchor client
potential
⢠Installed base
Requirements for rapid success
32. 32 Š 2014 International Business Machines Corporation
What do I get as an IBM Watson Ecosystem Application Partner?
Use of the Watson Developer Cloud,
including:
Watson Experience Manger and other tooling
API to access the QA service to Watson
Documentation and tutorials
Workspace to enrich Watson with content
Workspace to train and test your application
Customizable user interface to embed into your
application
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
33. 33 Š 2014 International Business Machines Corporation
Work
with IBM
team to
solidify
use case
strategy
Define
business
case &
content
strategy
Access the
Watson
Dev Cloud
through
tools and
API
Build the
prototype
solution
Socialize in
market
Build a commercial
application, enrich,
train and test
application
Final testing before
product release
Execute on
Go to
Market
Deploy the
product
âPowered
by Watsonâ
Expand
usage in
future
releases
Planning your Watson application roadmap in 12 â 16 weeks
⢠Align use
case with
rapid start
criteria
Sign up
IBM
PartnerWorl
d
Submit
Ecosystem
application
Ready Engage Prototype Build Deploy
Go-to-Market Plan and Execute
34. 34 Š 2014 International Business Machines Corporation
1. Explore use case for Watson business and technical alignment
2. Submit Watson Ecosystem application
https://ibm.biz/watsonecosystemapply
3. Join the IBM PartnerWorld community at
http://www.ibm.com/PartnerWorld
Step 1: Ready Phase
Ready Engage Prototype Build Deploy
35. 35 Š 2014 International Business Machines Corporation
Access the Watson Developer Cloud
Enrich Watson : Acquire, Upload, Ingest, Deploy content using the Watson
Experience Manager
Create application prototype with Watson as a component
Identify and begin acquiring content
Create user experience mockups
Develop Q&A pairs
Test
Socialize prototype with client base
Phase 2: Prototype
Ready Engage Prototype Build Deploy
36. 36 Š 2014 International Business Machines Corporation
Capture market requirements through advanced discussions with early clients
Create a minimum viable product âPowered by Watsonâ
Continue to refine the architecture, design for interaction and integration
patterns with Watson
Sign beta clients
Develop application Iteratively:
Enrich Watson further with content
Train Watson using Subject Matter Experts
Test functionally and non-functionally
Plan for go-to-market
(sales, support, marketing)
Formalize content strategy
Phase 3: Build
Ready Engage Prototype Build Deploy
37. 37 Š 2014 International Business Machines Corporation
Prepare for commercialization, launch and other go-to-market activities
Plan for application rollout with initial set
of users
Set up support, system usage metrics, and
other parameters for application monitoring
Execute on plan to expand users, application
functionality and content
Based on market feedback and usage,
iteratively plan and build out scenario(s)
further and more broadly
Phase 4: Deploy
Ready Engage Prototype Build Deploy
38. 38 Š 2014 International Business Machines Corporation
What is the cost to be part of the IBM Watson Ecosystem?
Application Partners
IBM Developer Cloud
Engage, Prototype, Build Phase: Free
Deploy phase : Revenue share
Deploy phase,: Application Hosting thru Softlayer
Optional) Contracted and billed separately
IBM Watson Content Store
⢠Free to upload own data
⢠Content available via Content Store with standard
terms: Free and Fee
IBM Watson Talent Hub
⢠Certified talent resources: Fee based determined by
talent provider
Content Partners
⢠Free to upload and process content on the IBM Watson
Content Store
⢠Revenue share for content used
Talent Partners
⢠Free participation (qualified) in IBM Watson Talent Hub
⢠Revenue share for talent services provided
39. Getting Started with
Watson
An Overview of the Watson
Development Process
Sridhar Sudarsan
Chief Technical Officer
IBM Watson Ecosystem
40. 40 Š 2014 International Business Machines Corporation
Access Watson Developer Cloud
using Watson Experience Manager
Develop app
âPowered by
Watsonâ
using APIs
Enrich
Watson
with content
Train
Watson
using tools
and experts
Test app
functional and
non-functional
Deploy
application
The process for building your âPowered by Watsonâ app
41. 41 Š 2014 International Business Machines Corporation
Access Watson Developer Cloud
using Watson Experience Manager
Develop app
âPowered by
Watsonâ
using APIs
Enrich
Watson
with content
Train
Watson
using tools
and experts
Test app
functional and
non-functional
Deploy
application
The process for building your âPowered by Watsonâ app
42. 42 Š 2014 International Business Machines Corporation
Design and Develop
âPowered by Watsonâ
apps using the QA API 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
Key points
Access Watson Developer Cloud
using Watson Experience Manager
Develop app
âPowered by
Watsonâ
using APIs
Enrich
Watson
with
content
Train
Watson
using tools
and experts
Test app
functional and
non-functional
Deploy
application
43. 43 Š 2014 International Business Machines Corporation
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
44. 44 Š 2014 International Business Machines Corporation
Guidelines for interaction patterns with Watson
Use the following guidelines when evaluating the suitability of a specific
solution:
â˘Tips for the âAskâ service
â˘Answers must be found in the content resources ingested in Watson
â˘Answers must be explicit in the content; Watson cannot synthesize
answers
â˘Answers must be discrete â Watson cannot combine information
from various documents or create an answer that is a deduction
from passages it finds (future)
â˘Questions must not require Watson to make judgments
â˘Descriptive questions
â˘Questions can be approximately one to three sentences long
â˘Questions should require answers of a small paragraph (about three
sentences or less)
45. 45 Š 2014 International Business Machines Corporation
Watson works with different types of interactions
Question Type Description Example
Factoid
( only supported question capability in
Jeopardy )
Simple fact regarding time,
location, reference,
quantity
Q: What fees are charged
with XXX fund?
Descriptive Description about a topic
Q: How are Roth and
traditional IRAs different?
Yes /No
Simple one response
answers
Q: Are Roth IRA
contributions tax
deductible?
Procedural â How To
How to question that returns
list of steps
Q: How do I plan for college
education?
Procedural â
Troubleshooting
Troubleshooting questions
Q: Why did I have a fee
charged on my brokerage?
Definition Definition of industry terms Q: What is a 529 plan?
Training on each type of question enables Watson to provide a high
quality experience for each user
46. 46 Š 2014 International Business Machines Corporation
Using the QAAPI with Watson
Integrate and Interact
with Watson from
Mobile or other Self
Care Apps using a
RESTful API
Response, confidence
evidence and other
response metadata
can be manipulated,
enriched and used
part of a conversation;
or to a component in
the system
downstream for further
processing
Configure parameters,
including Basic Auth using
the user id and password
for Watson Developer
Cloud, POST question;
Receive question, obtain
response JSON
Return JSON response
and authentication token
Receive response from
Watson
Send response to user or
further processing
47. 47 Š 2014 International Business Machines Corporation
Integration with Watson â Sample JSON request / response
REQUEST
RESPONSEConfidence
Evidence
Answer #1
48. 48 Š 2014 International Business Machines Corporation
Access the Watson Developer Cloud using the
Watson Experience Manager (WEM)
With Watson Experience Manager:
⢠Developers can use APIs to access
Watson and test âPowered by
Watsonâ apps
⢠Data Scientists can manage their
content used to enrich Watson
⢠User experience developers
can customize or create user
interaction models with Watson
⢠Domain experts can train and test
their âPowered by Watsonâ apps
WEM provides a role based set of tools for SME, Watson administrators,
and Domain Experts
49. 49 Š 2014 International Business Machines Corporation
Administration
Manage User Roles
View Usage Reports
Configuration
Configure, Style, & Theme out of the box UI
Define confidence threshold
Watson Experience Manager â Configuration
50. 50 Š 2014 International Business Machines Corporation
Enrich Watson
with content
1. Enrich Watson with relevant
content to fuel the
applications
2. Use Watson Experience
Manager to upload, ingest,
deploy content
3. Leverage the Watson
Content Store to acquire
public, subscribed or
enterprise content
Key points
Access Watson Developer Cloud
using Watson Experience Manager
Develop app
âPowered by
Watsonâ
using APIs
Enrich
Watson
with
content
Train
Watson
using tools
and experts
Test app
functional and
non-functional
Deploy
application
51. 51 Š 2014 International Business Machines Corporation
Proprietary Content
Acquire
Cleanse
Curate
Aggregate
Contract
Identify
Public Domain & Social
IBM Watson
Validate
Application
Partners
Source Prepare
Ingest
De
ploy
Select Content
Build Apps w/APIâs
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
52. 52 Š 2014 International Business Machines Corporation
Content guidelines in detail
IBM Watson requires a knowledge
database (corpus) that contains
information from which to formulate
correct answers
Content ingested into IBM Watson
means that content is processed by
the system such that correct
segments of data can be quickly
retrieved
Content can come from a variety of
sources and will have to be
physically made available
Content requires a level of
cleansing and curation for Watson
to be effective
Proprietary Content
Acquire
Cleanse
Curate
Aggregate
Contract
Identify
Public Domain & Social
Validate
Unstructured Data From
Enterprise Apps
CRM eComm
Workforce HR
Product
Catalog
Trouble
Ticket
Domain Specific
Content Providers
Email,
Collaboration,
Open Data
ECM KMS
53. 53 Š 2014 International Business Machines Corporation
Content ingestion â Supported content
Types of Unstructured Data that can be Ingested in Watson
HTML
Websites
Domain Independent Content
FAQ pages
Forums
Product Descriptions
Product Catalog Export
Product Reviews
Social Network Extracts
Microsoft Word
Operational Runbookâs
Policies & Procedures
Contracts & Agreements
Terms & Conditions
PDF
â Product Manuals
â Financial Reports (sans graphs)
â Analyst Research
â User Guides
â Troubleshooting Guide
â Terms & Conditions
â Setup & Configuration Guides
â Magazines & Journals
Text
â Extracted Interaction Logs from CRM,
Trouble Ticket, Care, Media Asset
Management applications
54. 54 Š 2014 International Business Machines Corporation
Understand graphics (images, videos, sound âŚ)
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 âŚ.
55. 55 Š 2014 International Business Machines Corporation
What
Works?
Documents that are relevant to the use case under consideration
Understanding the validity of documents & frequency of changes
Well formed semantics â titles, sections, headings, sub-headings
What Does
Not?
Access to glossary, abbreviations would be helpful and preferred
If HTML â 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
56. 56 Š 2014 International Business Machines Corporation
Content crawling & curation â 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
57. 57 Š 2014 International Business Machines Corporation
Content crawling & curation â Example content
Based on this content one might be interested in
understanding the following.
Various domain (medical health in this case) terms or
concepts such as diseases, symptoms (headache, sore
throat etc.), associated health conditions (asthma,
diabetes etc.), vaccinations etc.
Concepts or terms expressed in different ways (flu Vs.
influenza, running nose Vs. cold etc.)
Timing in terms of when the disease is more prevalent
during a given year.
Statistics in terms of how many people were affected over
the years.
Locations and other geo references made in the
document with respect to the concepts or terms.
Co-references or relationships or associated side effects
with other health conditions (GuillainâBarrĂŠ Syndrome,
chronic lung disease etc.), vaccination options etc.
58. 58 Š 2014 International Business Machines Corporation
Based on this content one might be
interested in understanding the following.
Various domain (telecom in this case) terms
or concepts such as equipment types
(gateway, router, receiver), problems
(connection issues, no audio etc.), associated
conditions (correct cabling, receiver
configuration, etc.), abbreviations etc.
Concepts or terms expressed in different ways
(receiver Vs STB Vs DVR, router Vs gateway
etc.)
Timing in terms of when a particular problem
is more prevalent post service install &
activation
Statistics in terms of how many people were
affected over the years.
Locations and other geo references made in
the document with respect to the concepts
or terms.
Co-references or relationships or associated
service problems with other conditions or
issues (DVR Recording & Memory Capacity,
Data Features & Connectivity etc.),
upgrades, value added options etc.
Content crawling & curation â Example content
59. 59 Š 2014 International Business Machines Corporation
Watson Experience Manager â Corpus management
Content:
Content Upload & Management â Not an ECM tool
View Ingested Corpus
Allows for on-demand corpus pre-processing & ingestion
Number of
Docs Ingested
as Corpus
View Ingested
Document &
CAS
Tag Each
Document
Ingest into
Corpus on-
demand
Upload &
Delete
Documents
60. 60 Š 2014 International Business Machines Corporation
Train Watson
with tools and experts
1. Watson is a cognitive
system that is trained by
experts and users and
learns over time
2. Watson Experience
Manager allows domain
experts to provide training
data like question and
answer pairs
3. Watson is trained iteratively
â follows a cycle of
collecting realistic training
data, running training
experiments, testing, error
analysis.
Key points
Access Watson Developer Cloud
using Watson Experience Manager
Develop app
âPowered by
Watsonâ
using APIs
Enrich
Watson
with
content
Train
Watson
using
tools
and
experts
Test app
functional and
non-functional
Deploy
application
61. 61 Š 2014 International Business Machines Corporation
Training:
Allow SMEâs to enter & manage âQuestion & Answerâ pairs
Review & Approve Q&A Pairs
Forms the basis for training data to help train Watson
Goal is to build a representative set that enables Watson to understand the domain's
language characteristics
Drive towards a
goal
Approve, Edit,
Add Comments
Sample Q&A
Pair Instance
Watson Experience Manager â Create Q&A pairs to help train
Watson
62. 62 Š 2014 International Business Machines Corporation
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 â Watson common tooling platform
63. 63 Š 2014 International Business Machines Corporation
Test âPowered by Watsonâ apps
(Functional and non-functional)
1. Watson Experience
Manager offers ways to test
the responses from Watson
2. Testing is an iterative
process to improve
responses; and test
integration with Watson
3. In addition to functional
tests, plan to perform stress
tests based on user ramps,
and other non functional
tests.
Key points
Access Watson Developer Cloud
using Watson Experience Manager
Develop app
âPowered by
Watsonâ
using APIs
Enrich
Watson
with
content
Train
Watson
using tools
and experts
Test app
functional and
non-functional
Deploy
application
64. 64 Š 2014 International Business Machines Corporation
Watson Experience Manager â Testing
Testing
Test system by asking
questions
Additional
Considerations
Confidence of
the response
Evidence -
where the
answer
passage was
provided
65. 65 Š 2014 International Business Machines Corporation
Deploy âPowered by Watsonâ
applications
1. Roll out the application
using the production
topology
2. Set up support teams and
processes for handling user
queries
3. Establish a set of metrics to
be collected, with tools to
support the process.
Key points
Access Watson Developer Cloud
using Watson Experience Manager
Develop app
âPowered by
Watsonâ
using APIs
Enrich
Watson
with
content
Train
Watson
using tools
and experts
Test app
functional and
non-functional
Deploy
application
66. 66 Š 2014 International Business Machines Corporation
Deploying your âPowered by Watsonâ solution
⢠Rollout iteratively
â˘Create a rollout plan with the user base
â˘Size the system based on peak and scaled usage,
failover and availability requirements and response times
â˘Establish SLAs and other metrics needed from the
Watson Developer Cloud
â˘Determine any additional security provision needed
â˘Promote the powered by Watson application to the
production zone in the Watson Developer Cloud
67. 67 Š 2014 International Business Machines Corporation
Summary - 3 key takeaways
1
2
3
Committed to partner success. New business unit, HQ in NY,
brings together research, development, service and go-to-
market and features Innovation Hub with incubator, client
solutions center and design lab
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.
69. 69 Š 2014 International Business Machines Corporation
Where do I go from here?
Apply
https://ibm.biz/watsonecosystemapply
Share:
https://ibm.biz/watsondeveloper
Learn:
https://ibm.biz/watsonecosystem-youtube