Personal information agents for travel e-commerce Boi Faltings (http://liawww.epfl.ch/)

Slides:



Advertisements
Similar presentations
Fast Data at Massive Scale Lessons Learned at Facebook Bobby Johnson.
Advertisements

Introducing Egencia.
WebGDS platform a database of tourist services from many suppliers includes the following service types: Accommodation - Hotels of all types Car Rentals.
Find Nearest Airport Update your travel preferences Add a Car or Hotel Search by Price or by Schedule Concur Travel Book Air, Car, Hotel and even Taxi.
GFS Travel Resource Guide Training Instructions for On-line Booking through Cliqbook.
Objective Our objective is to provide tailored business solutions to Airlines, Airports, Civil Aviation Authorities, and other aviation service providers.
ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
Interactive Configuration
Basic I/O Relationship Knowledge-based: "Tell me what fits based on my needs"
© 2006 Amadeus IT Group SA 1 Amadeus Agency Internet Engine (e-Power) For Travel Agencies & Travel Portals.
Best-First Search: Agendas
Sapana Mehta (CS-6V81) Overview Of J2EE & JBoss Sapana Mehta.
_______________________________________________________________________________________________________________ E-Commerce: Fundamentals and Applications1.
1 Pertemuan 21 Software Agents for E-Commerce Matakuliah: M0284/Teknologi & Infrastruktur E-Business Tahun: 2005 Versi: >
Academic Advisor: Prof. Ronen Brafman Team Members: Ran Isenberg Mirit Markovich Noa Aharon Alon Furman.
Millions & Millions of people use the internet across the globe… …and they use it to book reservations… Your hotel cannot afford to miss this important.
© 2003, Educational Institute Chapter 3 Reservation Systems Managing Technology in the Hospitality Industry Fourth Edition (469T or 469)
Workflow Visualization Anna Sallstrom. The situation VLab portal VLab portal Tools for material analysis Tools for material analysis Portlets Portlets.
Jun Peng Stanford University – Department of Civil and Environmental Engineering Nov 17, 2000 DISSERTATION PROPOSAL A Software Framework for Collaborative.
McGraw-Hill/Irwin ©2005 The McGraw-Hill Companies, All rights reserved ©2005 The McGraw-Hill Companies, All rights reserved McGraw-Hill/Irwin.
What is AeroCRS? AeroCRS is a complete reservation and operational system for a small-medium airline, the system includes: Reservations Either by agents.
TOURISM INFORMATION SYSTEM AAR Technologies and Software Solution Pvt. Ltd A Flexible Business Intelligence Tool.
Belleza Geraldine E. Cabudoc Wilgiec A. Piacca Rowena C. Salcedo Arscelyn R. Zapata Mark Joseph I.
_______________________________________________________________________________________________________________ E-Commerce: Fundamentals and Applications1.
What is AeroCRS? AeroCRS is a complete reservation and operational system for a small-medium airline, the system includes: Reservations Either by agents.
Copyright © 1999 Anite Business Systems Limited E-Commerce Solutions for Tour Operators.
Configuration and E-commerce Invited talk, IFORS July 2002, Edinburgh, Scotland Jesper Møller IT University, Denmark [
E-Tourism Lecture 7. E-Tourism is used to refer to e-business in the field of travel and tourism, the use of ICT to enable tourism providers destinations.
A’lan Abruzzo Online Strategic Consulting and User Experience Design January 5 th 2009 Leading Hotels of the World Brainstorming.
Evinta - IBE A primary customer facing module through which the airline generates ticket sales & ancillary revenues. Offers a customized shopping experience.
Sabre Traveler Security June, service Sabre Red Value Suite Sabre Red Efficiency Suite Sabre Red Service Suite Air Car Hotel Rail Leisure Travel.
1 CMPT 275 High Level Design Phase Architecture. Janice Regan, Objectives of Design  The design phase takes the results of the requirements analysis.
Presentation for travel agencies TICKETING AUTOMATION PRO COPYRIGHT© UNIVERSAL INTELLIGENT SOLUTIONS.
SWE205 Review Spring Why is software unusable? Users are no longer trained. Why? Feature creep Inherently hard: a problem of communication Designed.
Copyright © PASS Consulting Corp., Miami 2001 XX/1 XML Application Server.
1 Constraints for Multimedia Presentation Generation Joost Geurts, Multimedia and Human-Computer Interaction CWI Amsterdam
MOBILE AGENTS What is a software agent ? Definition of an Agent (End-User point of view): An agent is a program that assists people and acts on their behalf.
Software Engineering, Lecture 4 Mohamed Elshaikh.
Constraint Satisfaction Problems/Programming ZUI 2012/2013.
Framework for MDO Studies Amitay Isaacs Center for Aerospace System Design and Engineering IIT Bombay.
Mobile Agent Migration Problem Yingyue Xu. Energy efficiency requirement of sensor networks Mobile agent computing paradigm Data fusion, distributed processing.
Constraint Systems Laboratory 11/26/2015Zhang: MS Project Defense1 OPRAM: An Online System for Assigning Capstone Course Students to Sponsored Projects.
OWL Representing Information Using the Web Ontology Language.
1 Object Oriented Logic Programming as an Agent Building Infrastructure Oct 12, 2002 Copyright © 2002, Paul Tarau Paul Tarau University of North Texas.
Non-Stop Savings. Guaranteed. ResX 4.0 System Updates And Upgrades.
Chapter 2) CSP solving-An overview Overview of CSP solving techniques: problem reduction, search and solution synthesis Analyses of the characteristics.
Intelligent Agents. 2 What is an Agent? The main point about agents is they are autonomous: capable of acting independently, exhibiting control over their.
Dispatching Java agents to user for data extraction from third party web sites Alex Roque F.I.U. HPDRC.
1/14/ :59 PM1/14/ :59 PM1/14/ :59 PM Research overview Koen Victor, 12/2007.
Providing web services to mobile users: The architecture design of an m-service portal Minder Chen - Dongsong Zhang - Lina Zhou Presented by: Juan M. Cubillos.
Chapter 5. Advanced Search Fall 2011 Comp3710 Artificial Intelligence Computing Science Thompson Rivers University.
From NARS to a Thinking Machine Pei Wang Temple University.
Fall 2000C.Watters1 World Wide Web and E-Commerce Servers & Server Side Processing.
The Internet Salihu Ibrahim Dasuki (PhD) CSC102 INTRODUCTION TO COMPUTER SCIENCE.
Travel Solutions Program Drexel University ravel Solutions Program Drexel University T ravel Solutions Program.
Welcome to Travel Incorporated’s Concur ‘Experienced User’ Webinar.
TravelCarma Technology that delivers Profit. About TravelCarma  TravelCarma is one of the leading travel technology providers in the world  TravelCarma.
PROVAB, a leading web services company, provides best in class web services including web application development and online booking system. We work as.
Composing semantic Web services under constraints E.Karakoc, P.Senkul Journal: Expert Systems with Applications 36 (2009)
Introduction to Oracle Forms Developer and Oracle Forms Services
Alternatives to Mobile Agents
Introduction to Oracle Forms Developer and Oracle Forms Services
World Travel, Inc. Concur Online User Guide
3.3. Case-Based Reasoning (CBR)
Introduction to Oracle Forms Developer and Oracle Forms Services
CS 188: Artificial Intelligence
An example design for an Amadeus APIv2 Web Server Application
Flight Booking System Flight Ticket Booking SoftwareFlight Ticket Booking SoftwareAirline Ticketing Software Flight Booking Software,
Chapter 6: Architectural Design
Presentation transcript:

Personal information agents for travel e-commerce Boi Faltings (

Traditional travel distribution UAL Galileo SwissairAvisHiltonEasyJet CRS GDS + Sabre, Amadeus, Worldspan Travel agents

Traditional travel e-commerce UAL Galileo Trip.com SwissairAvisHiltonEasyJet CRS GDS + Sabre, Amadeus, Worldspan Edifact Web server

Travel e-commerce with agents UAL Agent.com SwissairAvisHiltonEasyJet CRS Internet Travel portal Personal agent

Why personal agents? Customize information systems Create persistent interaction Negotiate on user’s behalf Be proactive Load distribution/low latency interaction

Requirements Customize: –represent choices and preferences –filter data according to individual combinations Persistence: –memorize partially solved tasks Load distribution: –lightweight

Individual preferences Trip from Geneva(GVA) to San Francisco (SFO): 1.Leave after 8 am 2.Arrive by 2 pm 3.Preferred airline: Swissair 4.Price < $500 5.No transfer at London Heathrow –Everyone has their own criteria!

Different people, different tradeoffs: Departur e time Arrival time AirlineTransferCost 1.6:4512:15 Lufthansa FRA$485conscie ncious 2.14:1519:20 Swissair ZRH$720bureau crat 3.11:0515:30 Air France PAR$380budget 4.8:5013:50 British Air LHR$660busy

Finding a solution: People can’t state their preferences Interaction = conversation: –Agent proposes solutions –User states/updates preferences Different tradeoffs: no unique optimal solution

Memorizing partially solved tasks State of problem solving = combination of preferences Same preferences => same solutions Advantages: –Complete problem-solving in stages –Optimal rebooking –High-quality data about customer

Lightweight Preference Flight schedule Fare Preference Flight schedule Flight schedule Flight schedule Flight schedule Flight schedule Fare Uniform and simple mechanism Optimal answers

Constraint Programming Planning = search for the best flight combinations User preferences = constraints Partially solved task = set of constraints A form of declarative programming...and also very lightweight (Java Constraint Library at

Constraint Satisfaction Problems Variables x 1,x 2,...,x n = choices Domains D 1,D 2,...,D n = possible values Relations R 1 = (x i,x j ), R 2 = (x k,x l,x m ),...,R m Constraints C 1 = ((v 1,v 2 ),(v 3,v 4 ),...),C 2,...,C m All are fixed for a certain problem Find: Solutions x 1 = v i, v 2 = v j,...,x n =v k such that all constraints are satisfied

Solving a CSP Backtrack search: assign values to variables in sequence, always satisfying all constraints Powerful pruning and variable ordering methods Parallel methods: assign random values to all variables and make local changes until all constraints are satisfied.

Valued CSP Each constraint carries a weight that models its importance Solution = value combination with lowest violation cost Solving process = online optimization (branch-and-bound search)

Most tractable problems are CSP CSP is general enough to formulate most interesting NP-hard problems: Resource allocation: a coloring problem Scheduling Planning (assumption: finite world state and operators) Diagnosis

Constraint programming for agent intelligence Software: does the same thing Agent: does the right thing Adaptation to context requires abduction (online optimization)

Logical inference modes… Deduction: bird(tweety) => flies (tweety) Abduction: flies(tweety) => bird (tweety) Most inference in information systems is abduction Abduction requires closed-world assumption (CWA) to be sound: Birds are the only things that fly

Implementing abduction CWA => transform into deduction (procedural programs) Programmer makes CWA => inflexible Constraint satisfaction makes CWA at runtime => software that easily adapts Drawback: NP-hard

Dealing with NP-hardness Tightness = 1 must be avoided!

User interaction Java applet/application with graphical displays Conversation: –user states preferences/constraints –agent displays solutions

1.Drop-down menus allow fine tuning of preferences 2. Preferences are stored and can be reused at any time

What Iconomic Systems built: Agent.com Travel portal (mediator) Personal agent UAL Galileo SwissairAvisHiltonEasyJet CRS GDS

The applet: All included All you need to download from the internet for travel planning is 10kb!

Flights/availability Fares with conditions/rules Hotels Availability/prices Car availability/prices Java Applet Search engine HTML browser WAP browser Java Servlet Search engine Server Itinerary and Profile Server Bookings CRS/GDS/… Web serverCustomer ISY Travel Modules isy-travel: Architecture