20120411 travelalliancemcguinnessfinal

24
Towards the Semantic Concierge Deborah L. McGuinness Tetherless World Senior Constellation Chair Professor of Computer and Cognitive Science Rensselaer Polytechnic Institute, Troy, NY & CEO McGuinness Associates, Latham, NY OpenTravel 2012 Advisory Forum April 11, 2012

Upload: deborah-mcguinness

Post on 15-Jan-2015

875 views

Category:

Health & Medicine


3 download

DESCRIPTION

The Semantic Travel Concierge - a vision of the potential of semantic technologies for the travel industry. Deborah L. McGuinness Keynote at the Opentravel Alliance Advisory Forum - Miami, Fla, April 11, 2012.

TRANSCRIPT

Page 1: 20120411 travelalliancemcguinnessfinal

Towards the Semantic Concierge

Deborah L. McGuinness Tetherless World Senior Constellation Chair

Professor of Computer and Cognitive Science

Rensselaer Polytechnic Institute, Troy, NY

& CEO McGuinness Associates, Latham, NY

OpenTravel 2012 Advisory Forum April 11, 2012

Page 2: 20120411 travelalliancemcguinnessfinal

Background

– Semantic Technologies – technological support for encoding

meaning in a form computers can understand and

manipulate – are maturing and increasing in usage

– Computational encodings of meaning can be used to help

integrate, validate, filter,…. Essentially to make smarter,

more context-aware applications

– This can provide competitive advantage in todays

increasingly networked and competitive environments

– Motivating Vision

– Semantic Web intro through examples: Ontologies, Mobile

Advisor, Linked Data

– Discussion

Delivered by semantic web guru and road warrior…

Page 3: 20120411 travelalliancemcguinnessfinal
Page 4: 20120411 travelalliancemcguinnessfinal

Scenario 1: Real

Time Travel Change

Change and the disrupted traveler

• Weather or mechanical issues mean leaving a traveler

stranded at an intermediate destination

• Default coping strategy is not desirable to traveler (i.e., local

intermediate hotel and transportation the next day)

• Transportation to an alternative airport somewhat near

desired destination along with confirmed new last one way

leg (e.g. one way car rental available at the arrival time)

would be vastly superior

Page 5: 20120411 travelalliancemcguinnessfinal

Scenario 1 Information

Requirements • Location:

– Current airport

– Destination airport (and/or final destination)

– Airports within x hour driving radius

• Schedules

– Flights to alternative airports in correct time period

• Connections to other ecosystem partners

– Other transportation options to final destination (train, bus, car with

a local starting point)

– Other transportation options from alternative destination to final

destination

– Critical parameters: availability, one-way rental, operating hours for

pickup/drop off

Much of this is freely available and with passenger data

including loyalty memberships, this could be connected easily

Page 6: 20120411 travelalliancemcguinnessfinal

Scenario 2: Advance

Travel purchase

• Known departure and destination airport

• With air loyalty program information, could offer air approp. options

(confirmed upgrades, lay back seat, reclining seat, discounted

business vs. full fare economy….)

• With destination address and hotel loyalty programs, could offer hotel

rooms near address with loyalty brands (including benefits of loyalty

program customer tier – e.g., upgrades, discounts, etc.)

• With car loyalty programs, could offer car options

• If additional tickets purchased, could offer larger car

• If with spouse (often in air systems), could offer more leisure

packages

• If connected to restaurant booking (foursquare, open table, …) or

preferences, could offer dinner bookings

• If connected to online calendar (e.g., Google), could pick up

conference information

Page 7: 20120411 travelalliancemcguinnessfinal

Semantic Web: Introduction

through examples

• Semantic Sommelier: Mobile Context Aware Semantic Wine

Advisor

• SemantAqua: Semantically-Aware information aggregator &

visualizer

There are many more….

• PopSciGrid – aimed at Preventable Cancers

• DARPA Personal Assistant that Learns -> SIRI

• IARPA Analyst Workbench -> Watson

• Home Theatre Advisor Configurator

Page 8: 20120411 travelalliancemcguinnessfinal

Notes

• Examples are from other domains because travel domains

have not been built out to the same level. Most travel

examples are at a syntactic level (or light weight semantics)

such as aggregators or natural language interfaces with

some semantics (such as Siri) but less about actually

“thinking” or acting as a personal assistant and more about

finding information

• One take home message after these examples will be that

the time is now to build the same kind of applications

described in the next few slides in travel…. Creating

customized semantic concierges

Page 9: 20120411 travelalliancemcguinnessfinal

Semantically-enabled advisors

utilize:

• Ontologies

• Reasoning

• Social

• Mobile

• Provenance

• Context

Patton & McGuinness.et. al

tw.rpi.edu/web/project/Wineagent

Page 10: 20120411 travelalliancemcguinnessfinal

Semantic

Sommelier

Previous versions used ontologies

to infer descriptions of wines for

meals and query for wines

New version uses

Context: GPS location, local

restaurants and wine lists, user

preferences

Social input: Twitter, Facebook, Wiki,

mobile, …

Source variability in quality,

contradictions exist,

Maintenance is an issue… however

new models emerging

Page 11: 20120411 travelalliancemcguinnessfinal

SemantEco/SemantAqua

• Enable/Empower citizens &

scientists to explore pollution

sites, facilities, regulations,

and health impacts along with

provenance.

• Demonstrates semantic

monitoring possibilities.

• Map presentation of analysis

• Explanations and

Provenance available

1

2 3

http://was.tw.rpi.edu/swqp/map.html and

http://aquarius.tw.rpi.edu/projects/semantaqua

4 5

1. Map view of analyzed results

2. Explanation of pollution

3. Possible health effect of contaminant (from EPA)

4. Filtering by facet to select type of data

5. Link for reporting problems

Page 13: 20120411 travelalliancemcguinnessfinal

Why did I present wine and

water applications?

• Wine advisor shows semantic technology in action making actionable recommendations

• Water application shows a “typical” semantic integration web 3.0 application

• Both of these styles are needed for a semantic concierge and these features are realizable today

• Next – they depend on – Semantic web stack

– Data availability – linked data cloud is growing

– Ontologies

– Semantic methodologies

– Understandable and Actionable applications

Page 14: 20120411 travelalliancemcguinnessfinal

SPARQL to Xquery translator RDFS materialization

(Billion triple winner)

Govt metadata search

Linked Open Govt Data

SPARQL WG, earlier QL –

OWL-QL, Classic’ QL, …

OWL 1 & 2 WG Edited main OWL

Docs, quick reference,

OWL profiles (OWL RL),

Earlier languages: DAML,

DAML+OIL, Classic

RIF WG

AIR accountability tool

DL, KIF, CL, N3Logic

Inference Web, Proof

Markup Language, W3C

Provenance Working

group formal model,

W3C incubator group,

Inference Web IW Trust,

Air + Trust

Visualization APIs

S2S

Govt Data

Ontology repositories

(ontolinguag),

Ontology Evolution env:

Chimaera,

Semantic eScience

Ontologies, MANY other ontologies

Transparent Accountable

Datamining Initiative (TAMI)

Foundations: Web Layer Cake

Page 15: 20120411 travelalliancemcguinnessfinal
Page 17: 20120411 travelalliancemcguinnessfinal

Ontology Spectrum

Catalog/

ID

General

Logical

constraints

Terms/

glossary

Thesauri

“narrower

term”

relation

Formal

is-a

Frames

(properties)

Informal

is-a

Formal

instance Value

Restrs.

Disjoint-

ness,

Inverse,

part-of…

From 99 AAAI panel with Gruninger, Lehmann, McGuinness, Uschold, Welty. , 2000 Dagstuhl talk by McGuinness

Page 18: 20120411 travelalliancemcguinnessfinal

Originally developed for VSTO, now in SSIII, SESDI, SESF, OOI …

The Virtual Solar-Terrestrial

Observatory: A Deployed Semantic Web Application Case Study for Scientific Research. Proc. 19

Conf. on Innovative Applications of Artificial Intelligence (IAAI-07),

http://www.vsto.org

Page 19: 20120411 travelalliancemcguinnessfinal

Inference Web: Making Data Transparent and

Actionable Using Semantic Technologies

• How and when does it make sense to use smart system results & how do we

interact with them?

19

Knowledge

Provenance in Virtual

Observatories

1

9

Hypothesis

Investigation /

Policy Advisors

(Mobile)

Intelligent

Agents

Intelligence Analyst

Tools

NSF Interops:

SONET

SSIII – Sea Ice

Page 20: 20120411 travelalliancemcguinnessfinal

Back to Travel

Existing mobile and web site applications allow online

browsing, status checks, mobile access, with purchase

options

However they often

• Are not well connected into travel ecosystems

• Do not use sensor-based context – e.g., GPS

• Are not connected to user context – previous queries, and

actions, google calendar, loyalty connections, status

levels etc.

Page 21: 20120411 travelalliancemcguinnessfinal

Remember Scenario 1 and 2

Page 22: 20120411 travelalliancemcguinnessfinal

The Semantic Web

enables…

• New models of intelligent services

• E-commerce solutions

• M-commerce

• Web assistants

• …

• Semantic Technologies: ready for use

• Tools & tutorials available; deep apps

future planning may benefit from

consultants

• Context-aware, semantic

apps are the future

New forms of web assistants/agents that act on a

human’s behalf requiring less from humans

and their communication devices…

More info: dlm @ cs.rpi.edu

Page 23: 20120411 travelalliancemcguinnessfinal

Questions?

dlm @ cs . rpi . edu

What would you like from your semantic travel concierge ?

Acknowledgements: Thanks to Opentravel and Thematix for motivating discussions.

Page 24: 20120411 travelalliancemcguinnessfinal

Extra