Trip planning via the Semantic Web

I am delighted to announced that DERI, NUI Galway and Tourist Republic Ltd. have been successful in receiving funding from Enterprise Ireland (under the Innovation Partnership programme) to work on the TripPlanr project: a semantically-enabled collaborative trip-planning application for individuals and groups.

Before the advent of the Web, a traveller’s options were limited by the scarcity of information he or she could find about a destination. Planning a trip involved visiting travel agencies, making phone calls and asking friends or friends-of-a-friend for their experiences. These days, the Web allows the traveller to purchase travel tickets, accommodation and other travel products with the minimum of human intervention. However, the lack of expert guidance has made processing and assessing various travel products extremely difficult. The traveller is presented with a surfeit of similarly sounding destination descriptions and offers. In short, a problem of information deficit has been replaced with the problem of information overload.

Last year, Jan Blanchard, the CEO of Tourist Republic, approached myself and Conor Hayes in DERI with the idea of extending their existing TouristR destination review site to help the traveller plan a more complex travel product, such as a trip with multiple destinations on a fixed budget and timeline. In this situation, there is no online assistance to help the traveller cope with the additional problem of selecting and combining multiple elements so that budgetary, geographical, temporal and other personal constraints and preferences are observed.

TripPlanr, an integrated trip-planning advisor, is the result: a joint project between Tourist Republic and DERI that will tackle the information overload and planning problems by filtering and making recommendations based on the preferences of the traveller and their social network. The TripPlanr application builds on the existing TouristR platform and DERI’s specialised expertise in recommender systems, information mining, the Semantic Web and Web 2.0.

Today, online travel booking is used mainly for trips with few parts, like airline tickets. Unlike existing trip planning applications, it is envisioned that the new TripPlanr application will allow users to book more complex and personalised trips with a number of parts. By collecting relevant data and suggesting it to the right user at the right time, TripPlanr increases the probability for that user to book or purchase the product or service in question.

Last month, there was an interesting interview by Marie Boran in the Irish Independent with the creator of the Web, Tim Berners-Lee, in which he outlined a typical travel scenario that can be aided by Semantic Web technologies:

Your flight is to JFK airport, your business meetings are in New Jersey but you want to go sightseeing in New York and your hotel must be near a diabetic-friendly restaurant. Planning a business trip can be stressful at the best of times but doing it all through the web can be an eye-opening experience, says Tim Berners-Lee, as he explains how his invention, the world wide web, has its limitations and why he has spent the past decade working on its upgrade: the semantic web. “To make a detailed travel decision or similar, you need to see all that information on the same map. Currently, you have to print out all the data, sort through it and then stand back and see if you can make the connections yourself. “With a semantic website you could pull all these information forms together instantly and put them on the same map.”

Advertisements

5 thoughts on “Trip planning via the Semantic Web”

  1. Well done !

    I’m sure that SW can add lots of novel features to such applications.
    I would be happy to get an advisor that reads my various FOAF profiles, my iCal file and so on to suggest me things like “why not postpone your travel from one week, you’ll be able to see xxx in concert and meet yyy who’s traveling there”

    BTW, do you know the PICSEL project ?
    They have a use case dedicated to travel management from heterogenous data sources using ontologies:
    http://www.lri.fr/~sais/picsel3/prevproj.php
    ftp://ftp.inria.fr/INRIA/Projects/gemo/gemo/GemoReport-287.pdf (in french)
    http://www.lri.fr/~goasdoue/bib/GoasdoueLattesRousset-IJCIS-00.pdf

  2. Introduction

    Why is it that our computers have no grasp of ordinary life? Wouldn?t it be great if your search engine knew enough about life so that it could conclude that when you typed in ?a gift for my brother?, it knew that because he had just moved into his first apartment that he could probably use some new furniture? Or if your cell phone knew enough about emergencies that, even though you had silenced it in the movie theatre, it could know to ring if your mother were to call from the hospital? Or if your personal digital assistant knew enough about people that it could know to cancel a hiking trip with a friend who had just broken a leg?

    see: http://web.media.mit.edu/%7Epush/Kurzweil.html/
    retrieved on Tue March 25th 2008

  3. Hi John,
    Congratulations!

    I was wondering if you know about tripit.com which builds itineraries for users based on raw data you get from travel agencies, hotel reservations etc. What is also interesting from the social network point view is that you can find places that you and your trusted friends visit at the same time. Do you plan something like that in your project?
    Tomas

  4. Hi John,
    Congratulations!

    I hope the Semantic Web will be popular. I am in Stanford and attending in Social Information Processing. But, I am surprising most people in this session do not like Semantic Web. I think I will face big challenges.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s