10
On Planning Sightseeing Tours with TripBuilder Igo Brilhante 1 , Jose Antonio Macedo 1 Franco Maria Nardini 2 , Raffaele Perego 2 , Chiara Renso 2 1 Federal University of Ceará, Fortaleza, Brasil 2 ISTI-CNR, Pisa, Italy

Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

Embed Size (px)

Citation preview

Page 1: Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

On Planning Sightseeing Tourswith TripBuilder

Igo Brilhante1, Jose Antonio Macedo1

Franco Maria Nardini2, Raffaele Perego2, Chiara Renso2

1 Federal University of Ceará, Fortaleza, Brasil2 ISTI-CNR, Pisa, Italy

Page 2: Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

Trip Planning

What should I visit in San Francisco?

Constraints:• Time: 2 days;• My preferences.

How do other touristsvisit such places?

How many of these “trajectories”can I enjoy?

TripBuilder: an unsupervised framework for trip planning.

4 h

4 h

8 h

Page 3: Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

Flickr

• Vast amount of rich data– 586 M public Photos uploaded in

2013– (Geo-)Tags, Titles, likes,

Descriptions, Comments, Social profiles

• Easy to crawl• Existing large public crawls:– CoPhIR: http://cophir.isti.cnr.it/

• Bulk uploading very common

Page 4: Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

(credits to David Crandall et al., Cornell University)

Page 5: Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

Trajectories from Flickr & Wikipedia

Page 6: Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

The TripCover Problem• Given:

– A set of popular trajectories crossing a set of PoIs and their time cost

– The relevance of the trajectories w.r.t. the category set

– The Time Budget and Preferences of a user

– A measure of PoI-User interest

• Find:– the subset of trajectories that

maximizes user interest and fits in the time budget

Page 7: Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

TrajSP: Joining Trajectories

• A TripCover solution is a set of trajectories fitting user interest and time budget – Local search heuristics based on 2-opt and 3-opt moves

for connecting the solution in a single sightseeing tour

Page 8: Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

TripBuilder: Overview

Page 9: Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

http://tripbuilder.isti.cnr.it

Coming Soon oniTunes Store and Google Play!

Page 10: Trip Builder: Plan you city tour with machine learning - DataBeers Tuscany

Thanks!