SlideShare una empresa de Scribd logo
1 de 22
the bing platform that powers cortana
savasp
http://savas.me
why a personal assistant?
cortana introduction
key scenarios and the cloud
lessons learnt
crazy scenarios we can build
increasing focus on information (& knowledge), personalization, context, wearables, …
anticipatory computing
importance of near-real time processing/reactive computing
transition from web to apps to personal assistants
PERSONAL
Cortana…
…is your truly personal assistant
…gets to know you
…is transparent
Examples:
 Learning
 Notebook
 Personal suggestions
 Transparency & control
LOOKS OUT FOR YOU
Cortana…
…looks out for you
…filters out the noise
…reminds you of what’s important
Examples:
 Useful and relevant alerts
 Planners
 Event scheduling
 Quiet hours and inner circle
 Reminders
DELIGHTFUL & EASY TO USE
Cortana…
…“just works”
…lets you interact on your terms
…has a fun & engaging personality
Examples:
 Voice & natural language
 Text input
 Personality (visual, spoken voice,
and behavior)
  
bing platform as the foundation for
personal assistant experiences
user centric
cloud-driven
service-oriented
asynchronous, reactive, functional, stateless
data-driven
configuration-driven
secure and available
ingredients – how to build a personal assistant
privacy/security
design
knowledge platform
machine learning platform
feedback loop infrastructure
notifications infrastructure
stream/complex event processing
metrics/data-driven engineering
speech recognition
natural language understanding
user understanding
conversational & intent understanding
personality
global datacenter footprint
legal
business development
…
the notebook
cortana home
rank
html
request
language
generation
bing knowledge
?retrieve the user’s profile,
context, pending questions
aggregate, filter
inferences
retrieve knowledge and
rank based on the
user’s current context
flight BA 49 is delayed
notification
information streams: sports, flights,
weather, traffic, news, packages,
user location, …
notification
information streams: sports, flights,
weather, traffic, news, packages,
user location, …
var subscription = streamPlatform
.GetObservable<FlightInfo>(Constants.FlightsStream)
.Where(f => f.StatusCode == FlightStatus.Landed)
.Select(f => string.Format("{0} {1}: {2}", f.Airline.Name, f.FlightNumber, f.StatusCode))
.Subscribe(...);
stream
processing
platform
is this your home?
commute to work around
8.30am on Mondays
inferences
user understanding/insight
“remind me to wish Paul
happy birthday”
speech recognition
natural language
understanding
conversation
management
representation
of intent
speech stream
Using Deep Neural Networks-trained models
and other machine-learning techniques, we
convert the voice stream to a representation
the computers can understand
We reason over the machine representation of the user’s
intent. We use what we know about the user (e.g. “home”
is transformed to an actual location) in order to fill in any
gaps in our understanding. We maintain a dialog with the
user (e.g. if the user had just said “remind me”, we would
have initiated a follow up question).
“when I get home, remind
me to take out the
garbage”
language
generation
user
profile/context
web socket
Using Deep Neural Networks-trained models
and other machine-learning techniques, we
convert the voice stream to a representation
the computers can understand
We reason over the machine representation of the user’s
intent. We use what we know about the user (e.g. “home”
is transformed to an actual location) in order to fill in any
gaps in our understanding. We maintain a dialog with the
user (e.g. if the user had just said “remind me”, we would
have initiated a follow up question).
“when I get home, remind
me to take out the
garbage”
language
generation
user
profile/context
web socket
mini reactor
“will I need a scarf
tomorrow?”
speech recognition
natural language
understanding
conversation
management
user
profile/context
html
speech stream
Using Deep Neural Networks-trained models
and other machine-learning techniques, we
convert the voice stream to a representation
the computers can understand
We reason over the machine representation of the user’s
intent. We consult Bing Knowledge and the user’s profile in
order to construct a response in the conversation with the
user. Since we are keeping the context of the conversation,
the user can follow up with a question such as “How about
next weekend?” or “What about Seattle?”.
language
generation
bing knowledge
rank
bing.com
rank
html
request
language
generation
bing knowledge
?retrieve the user’s profile,
context, pending questions
aggregate, filter
inferences
ideas
DISCLAIMER: what follows does NOT represent
future products or services by microsoft
while at Sydney 2011, you should talk to john s.
both of you were at paris 2010, rio 2009, and
istanbul 2002 conferences
you also seem to be reading the same journals on
knowledge representation
you both found the book “on intelligence”
interesting
finally, you both like sushi…
i suggest “blue sushi”, just two blocks from the
conference center
“what was the title of the song
that got me dancing during the
radiohead concert few days ago?”
emergence of personal assistant as ux
metaphore, consolidation of user experiences
anticipatory computing, task completion,
conversational
sensors, wearables
reactive, near-realtime
Coldplay at the Gorge
2009 – 07 – 10, 9.12pm
Weather: Warm and mostly sunny
Attending: 20,000
Song playing at the time of photograph: Viva La Vida
Did you know that it was Coldplay’s 1st appearance at the
Gorge?
Ad-hoc social streams: photos, tweets, emotions
i
savas parastatidis
the bing platform that powers Cortana
savasp
http://savas.me

Más contenido relacionado

Destacado

Japan - The land of rising sun
Japan - The land of rising sunJapan - The land of rising sun
Japan - The land of rising sunAmod Tawade
 
Introducing The Amazon Echo
Introducing The Amazon EchoIntroducing The Amazon Echo
Introducing The Amazon EchoMicah Flores
 
Virtual personal assistant
Virtual personal assistantVirtual personal assistant
Virtual personal assistantShubham Bhalekar
 
Customizing the Django Admin
Customizing the Django AdminCustomizing the Django Admin
Customizing the Django AdminLincoln Loop
 
Please meet Amazon Alexa and the Alexa Skills Kit
Please meet Amazon Alexa and the Alexa Skills KitPlease meet Amazon Alexa and the Alexa Skills Kit
Please meet Amazon Alexa and the Alexa Skills KitAmazon Web Services
 
(MBL301) Creating Voice Experiences Using Amazon Alexa
(MBL301) Creating Voice Experiences Using Amazon Alexa(MBL301) Creating Voice Experiences Using Amazon Alexa
(MBL301) Creating Voice Experiences Using Amazon AlexaAmazon Web Services
 

Destacado (8)

Hadoop
HadoopHadoop
Hadoop
 
Japan - The land of rising sun
Japan - The land of rising sunJapan - The land of rising sun
Japan - The land of rising sun
 
Introducing The Amazon Echo
Introducing The Amazon EchoIntroducing The Amazon Echo
Introducing The Amazon Echo
 
Amazon Echo
Amazon EchoAmazon Echo
Amazon Echo
 
Virtual personal assistant
Virtual personal assistantVirtual personal assistant
Virtual personal assistant
 
Customizing the Django Admin
Customizing the Django AdminCustomizing the Django Admin
Customizing the Django Admin
 
Please meet Amazon Alexa and the Alexa Skills Kit
Please meet Amazon Alexa and the Alexa Skills KitPlease meet Amazon Alexa and the Alexa Skills Kit
Please meet Amazon Alexa and the Alexa Skills Kit
 
(MBL301) Creating Voice Experiences Using Amazon Alexa
(MBL301) Creating Voice Experiences Using Amazon Alexa(MBL301) Creating Voice Experiences Using Amazon Alexa
(MBL301) Creating Voice Experiences Using Amazon Alexa
 

Similar a The Bing Platform that Powers Cortana

Realizzare un Virtual Assistant con Bot Framework Azure e Unity
Realizzare un Virtual Assistant con Bot Framework Azure e UnityRealizzare un Virtual Assistant con Bot Framework Azure e Unity
Realizzare un Virtual Assistant con Bot Framework Azure e UnityMarco Parenzan
 
Teaching Computers to Chat
Teaching Computers to ChatTeaching Computers to Chat
Teaching Computers to ChatAvi Yaeli
 
VIRTUAL PERSONAL ASSISTANT.pdf
VIRTUAL PERSONAL ASSISTANT.pdfVIRTUAL PERSONAL ASSISTANT.pdf
VIRTUAL PERSONAL ASSISTANT.pdfAnkushSolanki6
 
Life Beyond Embodiment
Life Beyond EmbodimentLife Beyond Embodiment
Life Beyond EmbodimentLeandro Agro'
 
virtual-assistant-160214154006.pdf
virtual-assistant-160214154006.pdfvirtual-assistant-160214154006.pdf
virtual-assistant-160214154006.pdfHarshKumar534677
 
3-in-1 talk on Serverless Chatbots, Alexa skills & Voice UI best practices (t...
3-in-1 talk on Serverless Chatbots, Alexa skills & Voice UI best practices (t...3-in-1 talk on Serverless Chatbots, Alexa skills & Voice UI best practices (t...
3-in-1 talk on Serverless Chatbots, Alexa skills & Voice UI best practices (t...Daniel Zivkovic
 
Phase III Presentation
Phase III PresentationPhase III Presentation
Phase III PresentationGrey Vaisius
 
Multimodal virtual assistant(2170171).pptx
Multimodal virtual assistant(2170171).pptxMultimodal virtual assistant(2170171).pptx
Multimodal virtual assistant(2170171).pptxVivekKumar243534
 
Artificial Intelligence (Unit - 2).pdf
Artificial Intelligence   (Unit  -  2).pdfArtificial Intelligence   (Unit  -  2).pdf
Artificial Intelligence (Unit - 2).pdfSathyaNarayanan47813
 
Sl languages convention 2010
Sl languages convention 2010Sl languages convention 2010
Sl languages convention 2010kayleewest
 
Meetup 6/3/2017 - Artificiële Intelligentie: over chatbots & robots
Meetup 6/3/2017 - Artificiële Intelligentie: over chatbots & robotsMeetup 6/3/2017 - Artificiële Intelligentie: over chatbots & robots
Meetup 6/3/2017 - Artificiële Intelligentie: over chatbots & robotsDigipolis Antwerpen
 
The Next Generation of Flash User Experience
The Next Generation of Flash User ExperienceThe Next Generation of Flash User Experience
The Next Generation of Flash User ExperienceKevin Suttle
 
Conversational AI with Rasa - PyData Workshop
Conversational AI with Rasa - PyData WorkshopConversational AI with Rasa - PyData Workshop
Conversational AI with Rasa - PyData WorkshopTom Bocklisch
 
Designing for conversation
Designing for conversationDesigning for conversation
Designing for conversationyiibu
 
Voxxed Athens 2018 - UX design and back-ends: When the back-end meets the user
Voxxed Athens 2018 - UX design and back-ends: When the back-end meets the userVoxxed Athens 2018 - UX design and back-ends: When the back-end meets the user
Voxxed Athens 2018 - UX design and back-ends: When the back-end meets the userVoxxed Athens
 
A.I. in the Enterprise: Computer Speech
A.I. in the Enterprise: Computer SpeechA.I. in the Enterprise: Computer Speech
A.I. in the Enterprise: Computer SpeechChristopher Mohritz
 

Similar a The Bing Platform that Powers Cortana (20)

Realizzare un Virtual Assistant con Bot Framework Azure e Unity
Realizzare un Virtual Assistant con Bot Framework Azure e UnityRealizzare un Virtual Assistant con Bot Framework Azure e Unity
Realizzare un Virtual Assistant con Bot Framework Azure e Unity
 
Teaching Computers to Chat
Teaching Computers to ChatTeaching Computers to Chat
Teaching Computers to Chat
 
VIRTUAL PERSONAL ASSISTANT.pdf
VIRTUAL PERSONAL ASSISTANT.pdfVIRTUAL PERSONAL ASSISTANT.pdf
VIRTUAL PERSONAL ASSISTANT.pdf
 
Life Beyond Embodiment
Life Beyond EmbodimentLife Beyond Embodiment
Life Beyond Embodiment
 
virtual-assistant-160214154006.pdf
virtual-assistant-160214154006.pdfvirtual-assistant-160214154006.pdf
virtual-assistant-160214154006.pdf
 
3-in-1 talk on Serverless Chatbots, Alexa skills & Voice UI best practices (t...
3-in-1 talk on Serverless Chatbots, Alexa skills & Voice UI best practices (t...3-in-1 talk on Serverless Chatbots, Alexa skills & Voice UI best practices (t...
3-in-1 talk on Serverless Chatbots, Alexa skills & Voice UI best practices (t...
 
Designing for Voice
Designing for VoiceDesigning for Voice
Designing for Voice
 
Phase III Presentation
Phase III PresentationPhase III Presentation
Phase III Presentation
 
Multimodal virtual assistant(2170171).pptx
Multimodal virtual assistant(2170171).pptxMultimodal virtual assistant(2170171).pptx
Multimodal virtual assistant(2170171).pptx
 
Artificial Intelligence (Unit - 2).pdf
Artificial Intelligence   (Unit  -  2).pdfArtificial Intelligence   (Unit  -  2).pdf
Artificial Intelligence (Unit - 2).pdf
 
Sl languages convention 2010
Sl languages convention 2010Sl languages convention 2010
Sl languages convention 2010
 
Meetup 6/3/2017 - Artificiële Intelligentie: over chatbots & robots
Meetup 6/3/2017 - Artificiële Intelligentie: over chatbots & robotsMeetup 6/3/2017 - Artificiële Intelligentie: over chatbots & robots
Meetup 6/3/2017 - Artificiële Intelligentie: over chatbots & robots
 
ERTS diagram
ERTS diagramERTS diagram
ERTS diagram
 
Every Business Needs a Chatbot
Every Business Needs a ChatbotEvery Business Needs a Chatbot
Every Business Needs a Chatbot
 
The Next Generation of Flash User Experience
The Next Generation of Flash User ExperienceThe Next Generation of Flash User Experience
The Next Generation of Flash User Experience
 
Ai and bots
Ai and botsAi and bots
Ai and bots
 
Conversational AI with Rasa - PyData Workshop
Conversational AI with Rasa - PyData WorkshopConversational AI with Rasa - PyData Workshop
Conversational AI with Rasa - PyData Workshop
 
Designing for conversation
Designing for conversationDesigning for conversation
Designing for conversation
 
Voxxed Athens 2018 - UX design and back-ends: When the back-end meets the user
Voxxed Athens 2018 - UX design and back-ends: When the back-end meets the userVoxxed Athens 2018 - UX design and back-ends: When the back-end meets the user
Voxxed Athens 2018 - UX design and back-ends: When the back-end meets the user
 
A.I. in the Enterprise: Computer Speech
A.I. in the Enterprise: Computer SpeechA.I. in the Enterprise: Computer Speech
A.I. in the Enterprise: Computer Speech
 

Último

9643097474 Full Enjoy @24/7 Call Girls In Moti Nagar Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Moti Nagar Delhi Ncr9643097474 Full Enjoy @24/7 Call Girls In Moti Nagar Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Moti Nagar Delhi Ncrthapariya601
 
FULL ENJOY Call Girls In Gurgaon Call 8588836666 Escorts Service
FULL ENJOY Call Girls In Gurgaon  Call 8588836666 Escorts ServiceFULL ENJOY Call Girls In Gurgaon  Call 8588836666 Escorts Service
FULL ENJOY Call Girls In Gurgaon Call 8588836666 Escorts ServiceCALLGIRLS DELHI
 
Justdial Call Girls In Vaishali, Ghaziabad 8800357707 Escorts Service
Justdial Call Girls In Vaishali, Ghaziabad 8800357707 Escorts ServiceJustdial Call Girls In Vaishali, Ghaziabad 8800357707 Escorts Service
Justdial Call Girls In Vaishali, Ghaziabad 8800357707 Escorts Servicemonikaservice1
 
Tibetan Call Girls In Majnu Ka Tilla Delhi 9911107661
Tibetan Call Girls In Majnu Ka Tilla Delhi 9911107661Tibetan Call Girls In Majnu Ka Tilla Delhi 9911107661
Tibetan Call Girls In Majnu Ka Tilla Delhi 9911107661safdarjungdelhi1
 
Call Us ➥9911191017▻Young Call Girls In Guru Dronacharya Metro Station Delhi NCR
Call Us ➥9911191017▻Young Call Girls In Guru Dronacharya Metro Station Delhi NCRCall Us ➥9911191017▻Young Call Girls In Guru Dronacharya Metro Station Delhi NCR
Call Us ➥9911191017▻Young Call Girls In Guru Dronacharya Metro Station Delhi NCRsafdarjungdelhi1
 
9643097474 Full Enjoy @24/7 Call Girls In Mahipalpur Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Mahipalpur Delhi Ncr9643097474 Full Enjoy @24/7 Call Girls In Mahipalpur Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Mahipalpur Delhi Ncrthapariya601
 
8800357707, Munirka Metro Good Looking For Call Girls And Escort Service Delhi
8800357707, Munirka Metro Good Looking For Call Girls And Escort Service Delhi8800357707, Munirka Metro Good Looking For Call Girls And Escort Service Delhi
8800357707, Munirka Metro Good Looking For Call Girls And Escort Service Delhimonikaservice1
 
9911558886 Cash on Hand Low Costly Russian Call Girls In Naraina Vihar
9911558886 Cash on Hand Low Costly Russian Call Girls In Naraina Vihar9911558886 Cash on Hand Low Costly Russian Call Girls In Naraina Vihar
9911558886 Cash on Hand Low Costly Russian Call Girls In Naraina Viharmalikasharmakk1
 
Call Girls In Sector 62, Noida꧁❤ 8800357707 ❤꧂Top Quality Escorts Service
Call Girls In Sector 62, Noida꧁❤ 8800357707 ❤꧂Top Quality Escorts ServiceCall Girls In Sector 62, Noida꧁❤ 8800357707 ❤꧂Top Quality Escorts Service
Call Girls In Sector 62, Noida꧁❤ 8800357707 ❤꧂Top Quality Escorts Servicemonikaservice1
 
9899855202 Call Girls In Goa This Ads Is Only For Those Clients Who Are Looki...
9899855202 Call Girls In Goa This Ads Is Only For Those Clients Who Are Looki...9899855202 Call Girls In Goa This Ads Is Only For Those Clients Who Are Looki...
9899855202 Call Girls In Goa This Ads Is Only For Those Clients Who Are Looki...delhincr993
 
Book Call Girls In Mahipalpur Delhi 8800357707 Hot Female Escorts Service
Book Call Girls In Mahipalpur Delhi 8800357707 Hot Female Escorts ServiceBook Call Girls In Mahipalpur Delhi 8800357707 Hot Female Escorts Service
Book Call Girls In Mahipalpur Delhi 8800357707 Hot Female Escorts Servicemonikaservice1
 
Call Us ≽ 9643900018 ≼ Call Girls In Dwarka Sector 7 (Delhi)
Call Us ≽ 9643900018 ≼ Call Girls In Dwarka Sector 7 (Delhi)Call Us ≽ 9643900018 ≼ Call Girls In Dwarka Sector 7 (Delhi)
Call Us ≽ 9643900018 ≼ Call Girls In Dwarka Sector 7 (Delhi)ayushiverma1100
 
Call Girls In indirapuram Ghaziabad ¶ 9667422720 ⎷ Delhi Escorts All Star
Call Girls In indirapuram Ghaziabad ¶ 9667422720 ⎷ Delhi Escorts All StarCall Girls In indirapuram Ghaziabad ¶ 9667422720 ⎷ Delhi Escorts All Star
Call Girls In indirapuram Ghaziabad ¶ 9667422720 ⎷ Delhi Escorts All StarLipikasharma29
 
No-1 Call Girls In North Goa Panaji 98998 VIP 855202 Escort service In North Goa
No-1 Call Girls In North Goa Panaji 98998 VIP 855202 Escort service In North GoaNo-1 Call Girls In North Goa Panaji 98998 VIP 855202 Escort service In North Goa
No-1 Call Girls In North Goa Panaji 98998 VIP 855202 Escort service In North Goadelhincr993
 
9643097474 Full Enjoy @24/7 Call Girls In Aerocty Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Aerocty Delhi Ncr9643097474 Full Enjoy @24/7 Call Girls In Aerocty Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Aerocty Delhi Ncrthapariya601
 
69 Girls ❓ 9711014705❓ Call Girls In Majnu Ka Tilla Delhi
69 Girls ❓ 9711014705❓ Call Girls In Majnu Ka Tilla Delhi69 Girls ❓ 9711014705❓ Call Girls In Majnu Ka Tilla Delhi
69 Girls ❓ 9711014705❓ Call Girls In Majnu Ka Tilla Delhithapagita
 
9643097474 Full Enjoy @24/7 Call Girls in Saket Metro Delhi NCR
9643097474 Full Enjoy @24/7 Call Girls in Saket Metro Delhi NCR9643097474 Full Enjoy @24/7 Call Girls in Saket Metro Delhi NCR
9643097474 Full Enjoy @24/7 Call Girls in Saket Metro Delhi NCRthapariya601
 
Call Girls In New Delhi Railway Station 9667422720 Top Quality Escorts Service
Call Girls In New Delhi Railway Station 9667422720 Top Quality Escorts ServiceCall Girls In New Delhi Railway Station 9667422720 Top Quality Escorts Service
Call Girls In New Delhi Railway Station 9667422720 Top Quality Escorts ServiceLipikasharma29
 
Call Girls In Noida Sector 15 Metro꧁❤ 8800357707 ❤꧂Escorts Service
Call Girls In Noida Sector 15 Metro꧁❤ 8800357707 ❤꧂Escorts ServiceCall Girls In Noida Sector 15 Metro꧁❤ 8800357707 ❤꧂Escorts Service
Call Girls In Noida Sector 15 Metro꧁❤ 8800357707 ❤꧂Escorts Servicemonikaservice1
 

Último (20)

9643097474 Full Enjoy @24/7 Call Girls In Moti Nagar Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Moti Nagar Delhi Ncr9643097474 Full Enjoy @24/7 Call Girls In Moti Nagar Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Moti Nagar Delhi Ncr
 
FULL ENJOY Call Girls In Gurgaon Call 8588836666 Escorts Service
FULL ENJOY Call Girls In Gurgaon  Call 8588836666 Escorts ServiceFULL ENJOY Call Girls In Gurgaon  Call 8588836666 Escorts Service
FULL ENJOY Call Girls In Gurgaon Call 8588836666 Escorts Service
 
Justdial Call Girls In Vaishali, Ghaziabad 8800357707 Escorts Service
Justdial Call Girls In Vaishali, Ghaziabad 8800357707 Escorts ServiceJustdial Call Girls In Vaishali, Ghaziabad 8800357707 Escorts Service
Justdial Call Girls In Vaishali, Ghaziabad 8800357707 Escorts Service
 
Tibetan Call Girls In Majnu Ka Tilla Delhi 9911107661
Tibetan Call Girls In Majnu Ka Tilla Delhi 9911107661Tibetan Call Girls In Majnu Ka Tilla Delhi 9911107661
Tibetan Call Girls In Majnu Ka Tilla Delhi 9911107661
 
Call Us ➥9911191017▻Young Call Girls In Guru Dronacharya Metro Station Delhi NCR
Call Us ➥9911191017▻Young Call Girls In Guru Dronacharya Metro Station Delhi NCRCall Us ➥9911191017▻Young Call Girls In Guru Dronacharya Metro Station Delhi NCR
Call Us ➥9911191017▻Young Call Girls In Guru Dronacharya Metro Station Delhi NCR
 
9643097474 Full Enjoy @24/7 Call Girls In Mahipalpur Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Mahipalpur Delhi Ncr9643097474 Full Enjoy @24/7 Call Girls In Mahipalpur Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Mahipalpur Delhi Ncr
 
8800357707, Munirka Metro Good Looking For Call Girls And Escort Service Delhi
8800357707, Munirka Metro Good Looking For Call Girls And Escort Service Delhi8800357707, Munirka Metro Good Looking For Call Girls And Escort Service Delhi
8800357707, Munirka Metro Good Looking For Call Girls And Escort Service Delhi
 
9911558886 Cash on Hand Low Costly Russian Call Girls In Naraina Vihar
9911558886 Cash on Hand Low Costly Russian Call Girls In Naraina Vihar9911558886 Cash on Hand Low Costly Russian Call Girls In Naraina Vihar
9911558886 Cash on Hand Low Costly Russian Call Girls In Naraina Vihar
 
Call Girls In Sector 62, Noida꧁❤ 8800357707 ❤꧂Top Quality Escorts Service
Call Girls In Sector 62, Noida꧁❤ 8800357707 ❤꧂Top Quality Escorts ServiceCall Girls In Sector 62, Noida꧁❤ 8800357707 ❤꧂Top Quality Escorts Service
Call Girls In Sector 62, Noida꧁❤ 8800357707 ❤꧂Top Quality Escorts Service
 
9899855202 Call Girls In Goa This Ads Is Only For Those Clients Who Are Looki...
9899855202 Call Girls In Goa This Ads Is Only For Those Clients Who Are Looki...9899855202 Call Girls In Goa This Ads Is Only For Those Clients Who Are Looki...
9899855202 Call Girls In Goa This Ads Is Only For Those Clients Who Are Looki...
 
Book Call Girls In Mahipalpur Delhi 8800357707 Hot Female Escorts Service
Book Call Girls In Mahipalpur Delhi 8800357707 Hot Female Escorts ServiceBook Call Girls In Mahipalpur Delhi 8800357707 Hot Female Escorts Service
Book Call Girls In Mahipalpur Delhi 8800357707 Hot Female Escorts Service
 
Call Us ≽ 9643900018 ≼ Call Girls In Dwarka Sector 7 (Delhi)
Call Us ≽ 9643900018 ≼ Call Girls In Dwarka Sector 7 (Delhi)Call Us ≽ 9643900018 ≼ Call Girls In Dwarka Sector 7 (Delhi)
Call Us ≽ 9643900018 ≼ Call Girls In Dwarka Sector 7 (Delhi)
 
Call Girls In indirapuram Ghaziabad ¶ 9667422720 ⎷ Delhi Escorts All Star
Call Girls In indirapuram Ghaziabad ¶ 9667422720 ⎷ Delhi Escorts All StarCall Girls In indirapuram Ghaziabad ¶ 9667422720 ⎷ Delhi Escorts All Star
Call Girls In indirapuram Ghaziabad ¶ 9667422720 ⎷ Delhi Escorts All Star
 
No-1 Call Girls In North Goa Panaji 98998 VIP 855202 Escort service In North Goa
No-1 Call Girls In North Goa Panaji 98998 VIP 855202 Escort service In North GoaNo-1 Call Girls In North Goa Panaji 98998 VIP 855202 Escort service In North Goa
No-1 Call Girls In North Goa Panaji 98998 VIP 855202 Escort service In North Goa
 
9643097474 Full Enjoy @24/7 Call Girls In Aerocty Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Aerocty Delhi Ncr9643097474 Full Enjoy @24/7 Call Girls In Aerocty Delhi Ncr
9643097474 Full Enjoy @24/7 Call Girls In Aerocty Delhi Ncr
 
69 Girls ❓ 9711014705❓ Call Girls In Majnu Ka Tilla Delhi
69 Girls ❓ 9711014705❓ Call Girls In Majnu Ka Tilla Delhi69 Girls ❓ 9711014705❓ Call Girls In Majnu Ka Tilla Delhi
69 Girls ❓ 9711014705❓ Call Girls In Majnu Ka Tilla Delhi
 
9643097474 Full Enjoy @24/7 Call Girls in Saket Metro Delhi NCR
9643097474 Full Enjoy @24/7 Call Girls in Saket Metro Delhi NCR9643097474 Full Enjoy @24/7 Call Girls in Saket Metro Delhi NCR
9643097474 Full Enjoy @24/7 Call Girls in Saket Metro Delhi NCR
 
9953056974 Low Rate Call Girls Delhi NCR
9953056974 Low Rate Call Girls Delhi NCR9953056974 Low Rate Call Girls Delhi NCR
9953056974 Low Rate Call Girls Delhi NCR
 
Call Girls In New Delhi Railway Station 9667422720 Top Quality Escorts Service
Call Girls In New Delhi Railway Station 9667422720 Top Quality Escorts ServiceCall Girls In New Delhi Railway Station 9667422720 Top Quality Escorts Service
Call Girls In New Delhi Railway Station 9667422720 Top Quality Escorts Service
 
Call Girls In Noida Sector 15 Metro꧁❤ 8800357707 ❤꧂Escorts Service
Call Girls In Noida Sector 15 Metro꧁❤ 8800357707 ❤꧂Escorts ServiceCall Girls In Noida Sector 15 Metro꧁❤ 8800357707 ❤꧂Escorts Service
Call Girls In Noida Sector 15 Metro꧁❤ 8800357707 ❤꧂Escorts Service
 

The Bing Platform that Powers Cortana

  • 1. the bing platform that powers cortana savasp http://savas.me
  • 2. why a personal assistant? cortana introduction key scenarios and the cloud lessons learnt crazy scenarios we can build
  • 3. increasing focus on information (& knowledge), personalization, context, wearables, … anticipatory computing importance of near-real time processing/reactive computing transition from web to apps to personal assistants
  • 4.
  • 5. PERSONAL Cortana… …is your truly personal assistant …gets to know you …is transparent Examples:  Learning  Notebook  Personal suggestions  Transparency & control LOOKS OUT FOR YOU Cortana… …looks out for you …filters out the noise …reminds you of what’s important Examples:  Useful and relevant alerts  Planners  Event scheduling  Quiet hours and inner circle  Reminders DELIGHTFUL & EASY TO USE Cortana… …“just works” …lets you interact on your terms …has a fun & engaging personality Examples:  Voice & natural language  Text input  Personality (visual, spoken voice, and behavior)   
  • 6.
  • 7. bing platform as the foundation for personal assistant experiences user centric cloud-driven service-oriented asynchronous, reactive, functional, stateless data-driven configuration-driven secure and available
  • 8. ingredients – how to build a personal assistant privacy/security design knowledge platform machine learning platform feedback loop infrastructure notifications infrastructure stream/complex event processing metrics/data-driven engineering speech recognition natural language understanding user understanding conversational & intent understanding personality global datacenter footprint legal business development …
  • 10. cortana home rank html request language generation bing knowledge ?retrieve the user’s profile, context, pending questions aggregate, filter inferences retrieve knowledge and rank based on the user’s current context
  • 11. flight BA 49 is delayed notification information streams: sports, flights, weather, traffic, news, packages, user location, … notification information streams: sports, flights, weather, traffic, news, packages, user location, … var subscription = streamPlatform .GetObservable<FlightInfo>(Constants.FlightsStream) .Where(f => f.StatusCode == FlightStatus.Landed) .Select(f => string.Format("{0} {1}: {2}", f.Airline.Name, f.FlightNumber, f.StatusCode)) .Subscribe(...); stream processing platform
  • 12. is this your home? commute to work around 8.30am on Mondays inferences user understanding/insight
  • 13. “remind me to wish Paul happy birthday” speech recognition natural language understanding conversation management representation of intent speech stream Using Deep Neural Networks-trained models and other machine-learning techniques, we convert the voice stream to a representation the computers can understand We reason over the machine representation of the user’s intent. We use what we know about the user (e.g. “home” is transformed to an actual location) in order to fill in any gaps in our understanding. We maintain a dialog with the user (e.g. if the user had just said “remind me”, we would have initiated a follow up question). “when I get home, remind me to take out the garbage” language generation user profile/context web socket Using Deep Neural Networks-trained models and other machine-learning techniques, we convert the voice stream to a representation the computers can understand We reason over the machine representation of the user’s intent. We use what we know about the user (e.g. “home” is transformed to an actual location) in order to fill in any gaps in our understanding. We maintain a dialog with the user (e.g. if the user had just said “remind me”, we would have initiated a follow up question). “when I get home, remind me to take out the garbage” language generation user profile/context web socket mini reactor
  • 14. “will I need a scarf tomorrow?” speech recognition natural language understanding conversation management user profile/context html speech stream Using Deep Neural Networks-trained models and other machine-learning techniques, we convert the voice stream to a representation the computers can understand We reason over the machine representation of the user’s intent. We consult Bing Knowledge and the user’s profile in order to construct a response in the conversation with the user. Since we are keeping the context of the conversation, the user can follow up with a question such as “How about next weekend?” or “What about Seattle?”. language generation bing knowledge rank
  • 15. bing.com rank html request language generation bing knowledge ?retrieve the user’s profile, context, pending questions aggregate, filter inferences
  • 16. ideas DISCLAIMER: what follows does NOT represent future products or services by microsoft
  • 17. while at Sydney 2011, you should talk to john s. both of you were at paris 2010, rio 2009, and istanbul 2002 conferences you also seem to be reading the same journals on knowledge representation you both found the book “on intelligence” interesting finally, you both like sushi… i suggest “blue sushi”, just two blocks from the conference center
  • 18. “what was the title of the song that got me dancing during the radiohead concert few days ago?”
  • 19. emergence of personal assistant as ux metaphore, consolidation of user experiences anticipatory computing, task completion, conversational sensors, wearables reactive, near-realtime
  • 20.
  • 21. Coldplay at the Gorge 2009 – 07 – 10, 9.12pm Weather: Warm and mostly sunny Attending: 20,000 Song playing at the time of photograph: Viva La Vida Did you know that it was Coldplay’s 1st appearance at the Gorge? Ad-hoc social streams: photos, tweets, emotions i
  • 22. savas parastatidis the bing platform that powers Cortana savasp http://savas.me

Notas del editor

  1. Kinect avatars that are connected to a knowledge base Kids interact with the avatars and can ask questions “a virtual tutor, companion” Social experience… a virtual class