Abstract: Methods and systems are described herein for generating structured classification data of a website. A computing device captures a plurality of webpages from a website. The computing device extracts data from each of the plurality of webpages based upon a plurality of features. The computing device generates a plurality of classes for each of the plurality of webpages by using a plurality of classifiers. The computing device assigns a consensus class to each webpage based upon the plurality of classes for the plurality of webpages.
Type:
Grant
Filed:
August 7, 2017
Date of Patent:
January 23, 2024
Assignee:
Criteo Technology SAS
Inventors:
Pierre Grimaud, Jean-Sébastien Faure, Julien Duminy