Mais conteúdo relacionado Semelhante a Ibm watson boston meetup may 27 2015 (20) Ibm watson boston meetup may 27 20152. IMPORTANT DISCLAIMER
2
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.
4. Watson: a new partnership between human and
computers
Scale
expertise by elevating the
consistency and objectivity of
decision making across an
organization.
Enhance
the cognitive process of
professionals to strengthen
decision making in the
moment
Accelerate
development of expertise in
others by capturing the
expertise of top performers
© 2015 International Business Machines Corporation
5. Reusable services form the basis for all Watson
cognitive solutions
Services
The same services are used by business
partners, customers, and IBM Developers.
© 2015 International Business Machines Corporation
6. IBM has radically expand access to Watson
services
Access restricted to partners
and IBM developers
Accessible by anyone with a
Bluemix account
Wait until services are GA to
release
Release in Beta and gather
input from user community
North America Global
One service 12 services and more coming
© 2015 International Business Machines Corporation
7. Introducing a new way to access Watson services
© 2015 International Business Machines Corporation
8. Watson Developer Cloud Services Available
Now
© 2015 International Business Machines Corporation
• Personality Insights
• Tradeoff Analytics
• Relationship Extraction
• Concept Insights
• Speech to Text
• Text to Speech
• Visual Recognition
• Natural Language Classifier
• Language Identification
• Language Translation
• Question and Answer
• Concept Expansion
• Message Resonance
• AlchemyAPI Services
9. Personality Insights
What is it?
Improved understanding of people's preferences to help engage users
on their own terms
How does it work?
The IBM Watson Personality Insights service uses linguistic
analytics to extract cognitive and social characteristics, including
Big Five, Values, and Needs, from communications that the user
makes available, such as email, text messages, tweets, forum
posts, and more. By deriving cognitive and social preferences, the
service helps users to understand, connect to, and communicate
with other people on a more personalized level.
Use Cases-
The service can analyze text based on a customer’s twitter stream to
help a travel agency decide between leading with a budget or luxury
trip offer
Anywhere improving a customer engagement can help create an
organization differentiate itself.
© 2015 International Business Machines Corporation
http://en.wikipedia.org/wiki/Big_Five_personality_traits
10. © 2014 International Business Machines Corporation© 2015 International Business Machines Corporation 10
Personality Insights
Demo
http://your-celebrity-match.mybluemix.net/
http://www.msnbc.com/msnbc/how-
supercomputer-sees-the-state-the-union
11. Language Identification
What is it?
Identifies the language in which text is written
How does it work?
The Language Identification service detects the
language in which text is written. This helps inform
next steps such as translation, voice to text, or direct
analysis. The service can be used in tandem with the
Machine Translation service. Today, the service can
identify 15 languages – Arabic; Chinese (Simplified);
Chinese (Traditional); Cyrillic; Danish; Dutch; English;
Farsi; Finnish; French; German; Greek; Hebrew; Hindi;
Icelandic; Italian; Japanese; Korean; Norwegian
(Bokmal); Norwegian (Nynorsk); Portuguese; Spanish;
Swedish; Turkish; Urdu
Use Cases-
A building block for Machine Translation and future
tech
© 2015 International Business Machines Corporation
12. © 2014 International Business Machines Corporation© 2015 International Business Machines Corporation 12
Language
Identification Demo
http://ibmlaser.mybluemix.net/liddemo.ht
ml
13. What is it?
Globalize on the fly. Translate text from one language
to another.
How does it work?
The Machine Translation service converts text input in
one language into a destination language for the end
user. Translation is available among English, Brazilian
Portuguese, Spanish and French.
Use Cases-
A French speaking help desk representative is assisting
a Portuguese speaking customer through a chat
session and is able to interact through the translation
service
Machine Translation
© 2015 International Business Machines Corporation
14. © 2014 International Business Machines Corporation© 2015 International Business Machines Corporation 14
Machine Translation
Demo
http://ibmlaser.mybluemix.net/mtdemo.ht
ml
15. Speech to Text
What is it?
Automatic recognition of the words that are being spoken
in a live audio stream, and presents the highest-scoring
textual representation of that message.
How does it work?
In addition to converting a raw audio signal into a best-
guess of the words that are being spoken, intelligence
about the relevant grammar / how language is used within
a specific context is incorporated to generate a more
accurate transcription.
Example Use Cases
• A new integration paradigm for mobile apps.
• Voice-control of applications / embedded devices.
• Transcription of meetings and conference calls. Dictation
of emails.
• Critical building block for “Speech-to-Speech”
translation.
© 2015 International Business Machines Corporation 15
16. © 2014 International Business Machines Corporation© 2015 International Business Machines Corporation 16
Speech To Text Demo
https://speech-to-text-
demo.mybluemix.net/
17. Text to Speech
What is it?
Generates an audio file that has a verbal representation of the
input text – complete with appropriate cadence and
intonation, and, in the future, the ability to customize the
pronunciation of specific words.
How does it work?
Generates an audio file that has a verbal representation of the
input text – complete with appropriate cadence and
intonation.
Example Use Cases
• Enable a new interaction paradigm for mobile apps.
• Assistance tools for the vision-impaired.
• Read texts / emails aloud.
• Critical building block for enable “Speech-to-Speech
Translation”
© 2015 International Business Machines Corporation 17
18. © 2014 International Business Machines Corporation© 2015 International Business Machines Corporation 18
Text to Speech Demo
http://text-to-speech-demo.mybluemix.net/
19. Concept Insights
What is it?
Locate relevant documents that may not directly mention your
query.
How does it work?
The Concept Insights service links documents you provide with a
pre-existing graph of concepts based on Wikipedia (e.g. 'The
New York Times', 'Machine learning', etc.). Two types of links are
identified: explicit links when a document directly mentions a
concept, and implicit links which connect your documents to
relevant concepts that are not directly mentioned in them.
Example Use Cases
• A legal firm could utilize this service to identify cases which
may be related to the case in question
• Improve engagement on any external website
© 2015 International Business Machines Corporation 19
20. © 2014 International Business Machines Corporation© 2015 International Business Machines Corporation 20
Concept Insights Demo
http://concept-insights-
demo.mybluemix.net/
21. Relationship Extraction
What is it?
Intelligently finds relationships between sentences
components (nouns, verbs, subjects, objects, etc.)
How does it work?
Parses sentences into their various components and
detects relationships between the components. It can
process new terms (like people's names in a news feed) it
has never analyzed before through contextual analysis.
Sentence components include parts of speech (noun,
verb, adjective, conjunction, etc.) and functions (subjects,
objects, predicates, etc.). The service maps the
relationships between the components so that users or
analytics engines can more easily understand the
meaning of individual sentences and documents.
Use Cases-
The service can analyze a news article and pull out the
relevant people, organization, event type, date/time, or
location of actions taken. It then can relate the
components such as what adjective describes what noun
and what action a subject takes upon what object.
© 2015 International Business Machines Corporation
22. © 2014 International Business Machines Corporation© 2015 International Business Machines Corporation 22
Relationship Extraction
Demo
http://ibmlaser.mybluemix.net/siredemo.ht
ml
23. Natural Language Classifier
What is it?
Natural Language Classifier service uses machine learning algorithms which can help your application understand
the language of short texts and make predictions about how to handle them.
How does it work?
The Natural Language Classifier analyzes a string of text and assigns predefined categories to it by applying deep
learning technology. Deep learning is a relatively recent set of approaches that use algorithms with similarities to the way
the human brain works. Deep Learning algorithms offer state of the art approaches in image and speech recognition, and
the Natural Language Classifier now applies them to text classification.
Use Cases-
Classify tweets into a set of classes, such as events, news, or opinions.
Analyze text messages into categories, such as Personal, Work, or Promotions.
Sentiment analysis on text from social media or other sources and identify whether it relates positively or negatively to
an offering or service.
© 2015 International Business Machines Corporation
25. © 2014 International Business Machines Corporation© 2015 International Business Machines Corporation 25
Natural Language
Classifier Demo
http://natural-language-classifier-
demo.mybluemix.net/
26. Tradeoff Analytics
What is it?
Helps make better choices under multiple conflicting goals.
Combines smart visualizations and analytical recommendations
for tradeoff exploration.
How does it work?
Tradeoff Analytics helps people make better choices when
multiple conflicting goals come into play. Tradeoff Analytics
uses Pareto filtering techniques in order to surface out only the
optimal alternatives across multiple criteria. It then help the
decision maker analyze the tradeoffs within the optimal set of
alternatives helping them select the option that best meets
their preferences and priorities.
Use Cases
• Wealth management using the technology to help choose
mutual funds
© 2015 International Business Machines Corporation 26
27. © 2014 International Business Machines Corporation© 2015 International Business Machines Corporation 27
Tradeoff Analytics Demo
http://tradeoff-analytics-
demo.mybluemix.net/
http://hedge.mybluemix.net/
28. Message Resonance
Visionary mobile protoype
What is it?
Communicate with people with a style and words that
suits them
How does it work?
The message resonance service analyzes draft content
and scores how well it is likely to be received by a
specific target audience. This analysis is based on
content that’s been written by the target audience
itself such as fans of a specific sports team or new
parents. Today, analysis can be done against people
active in cloud computing or discussions but future
versions will let users provide their own community
data.
Use Cases-
Among people active in cloud computing discussions,
option A content is likely to resonate very well, option
B poorly, and option C moderately well.
© 2015 International Business Machines Corporation
29. © 2014 International Business Machines Corporation© 2015 International Business Machines Corporation 29
Message Resonance
Demo
http://watson-mr-demo.mybluemix.net/
30. Concept Expansion
What is it?
Maps euphemisms or colloquial terms to more
commonly understood phrases
How does it work?
The Concept Expansion service analyses text and
interprets its meaning based on usage in other similar
contexts. For example, it could interpret “The Big
Apple” as meaning “New York City”. It can be used to
create a dictionary of related words and concepts so
that euphemisms, colloquialisms, or otherwise unclear
phrases can be better understood and analyzed.
Use Cases-
“drugs” can be expanded to:
start seed terms motrin, aspirin, Keflex
post expansion allegra, lisinopril, metformin,
aspirin, equagesic, cimetidine, fiorinal, vancomycin,
avelox, protonix, glimepiride, protonix, verapamil,
norco, inderal, hctz, advair
© 2015 International Business Machines Corporation
31. Question and Answer
Understands question
Produces possible answers and
evidence
Analyzes evidence
Computes confidence
Delivers response, evidence and
confidence
Asks a question
Considers response and
evidence
What is it?
Direct responses to users inquiries fueled by primary
document sources
How does it work?
Interprets and answers user questions directly based
on primary data sources (brochures, web pages,
manuals, records, etc.) that have been selected and
gathered into a body of data or ‘corpus’. The service
returns candidate responses with associated
confidence levels and links to supporting evidence.
The current data corpora on BlueMix focuses on the
Travel and Healthcare industries.
Use Cases-
Healthcare: What is a stroke? What is the cause of
Wilson Disease?
Travel: Where is the best place to stay in Prague?
© 2015 International Business Machines Corporation
32. Visualization Rendering
Visionary mobile prototype
What is it?
Graphical representations of data analysis for easier
understanding
How does it work?
The service takes input data and graphically renders it
as an interactive visualization which can range from a
common business chart to more advanced layouts.
The visualizations can be easily modified to match
user needs, visual styling, and types of data being
analyzed.
Use Cases-
The service could represent neighborhood
demographic data as mini pie charts showing income
levels centered on geographic locations on maps, or as
tree maps that can switch from looking at income by
age to house size or by education level.
© 2015 International Business Machines Corporation
33. AlchemyLanguage
Text Analysis Functions:
Entity Extraction - AlchemyAPI's named entity extraction is capable of identifying people,
companies, organizations, cities, geographic features and other typed entities from your HTML, text
or web-based content.
Sentiment Analysis - The sentiment analysis API is capable of computing document-level
sentiment, sentiment for a user-specified target, entity-level sentiment, quotation-level sentiment,
directional-sentiment and keyword-level sentiment. These multiple modes of sentiment analysis
provide for a variety of use cases ranging from social media monitoring to trend analysis.
Keyword Extraction - AlchemyAPI's keyword extraction API is capable of finding keywords in text
and ranking them.
Concept Tagging - The concept tagging API is capable of making high-level abstractions by
understanding how concepts relate, and can identify concepts that aren't necessarily directly
referenced in the text.
Relation Extraction - AlchemyAPI's relation extraction API is capable of parsing sentences into
subject, action and object form and then adding additional semantic information such as entity
extraction, keyword extraction, sentiment analysis and location identification.
© 2015 International Business Machines Corporation
34. AlchemyLanguage
Text Analysis Functions (contd.):
Taxonomy Classification - Using complex statistics and natural language processing technology,
the taxonomy API can classify your content into its most likely topic category up to five levels deep.
Author Extraction - Automatically extract author information from news articles or blog posts.
Language Detection - AlchemyAPI provides a robust language detection facility capable of
detecting the language of any text, HTML or web-based content.
Text Extraction - AlchemyAPI can automatically extract the important information from a
webpage, removing navigation links, advertisements and other undesired content.
Microformats Parsing - Use microformat parsing to enhance webpage categorization and
indexing and to perform content discovery tasks.
Feed Detection - AlchemyAPI's feed detection API can find the feeds within webpages and return
the links.
Linked Data Support - Linked Data is a method of exposing, sharing and connecting data on the
web via dereferenceable URIs. Linked Data aims to extend the Web with a data commons by
publishing various open datasets as RDF on the Web and by setting RDF links between data items
from different data sources.
© 2015 International Business Machines Corporation
35. AlchemyVision
Image Link Extraction - Given any URL, the Image Link Extraction API will scan the designated page
to find the most prominent image and directly retrieve the URL for that image. It can then be
appropriately classified and tagged.
Image Tagging - With AlchemyVision’s image tagging API, you can quickly categorize and organize
image libraries at a massive scale.
Face Detection/Recognition - When provided an image file or URL, the AlchemyVision Face
Detection and Recognition API returns the position, age, gender, and, in the case of celebrities, the
identities of the people in the photo.
© 2015 International Business Machines Corporation
36. AlchemyData News
News + Blogs + NLP
TARGETED SEARCH
Give me news articles and blog posts about:
Apple [the company]
Watch [the product]
Have a positive sentiment
Include the verb "buy"
TREND ANALYSIS
Give me time series data for:
Articles in the past 72 hours that mention "IBM" the company
Return time series data in one hour increments
AND MANY MORE…
Detect financial events (company acquisitions or product announcements)
Enrich CRM data
Identify Content Marketing opportunities
Research on a particular topic or person
© 2015 International Business Machines Corporation
37. Who is using the services today?
We ran a five week closed beta with twelve participants. Examples:
“…we were able to
quickly and easily
embed Watson's
capabilities into our
eyeQinsights platform
to provide an even
more personalized
shopping experience”
“we’re able to work with
cognitive computing
capabilities that we
couldn’t dream of
creating ourselves - it’s
a fantastic opportunity
and a real chance to
transform our industry”
“[this] is like putting the
Hubble telescope in the
hands of a backyard
astronomer… Watson’s
cognitive possibilities
alone will spawn a
completely new service
industry…”
38. © 2015 International Business Machines Corporation
IBM Watson Developer Cloud Resources
38
Website: http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/
and http://www.alchemyapi.com/
Documentation:
http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/doc and
http://www.alchemyapi.com/api
Sample Apps on Github: https://github.com/watson-developer-cloud
Twitter: @IBMWatson
Stackoverflow: http://stackoverflow.com/tags/ibm-watson/info
Community: https://developer.ibm.com/watson/
Get your account on Bluemix - https://ibm.biz/cloudboston
IBM Watson Hackathon @ World of Watson 2015 -
http://ibmwatsonhackathon.challengepost.com
Notas do Editor Question is passed through he API
Watson decomposes the question to understand multiple interpretations of it
Generates hypothesis through multiple sources
Scores the hypothesis and evidence
Synthesis the scoring to generate a response
Delivers response Evidence