Methods, systems and computer program products for identifying primary product objects on a web page. A primary product object is the object that shows the best view of the product the web page is detailing. A set of features is extracted for one or more objects on the web page. The primary product objects are identified by computing the probabilities of one or more objects on the web page being a primary product object, the probabilities indicating the likelihood of the one or more objects being the primary product object. The probabilities are computed by querying a statistical model.
Michael Tung - Mountain View CA, US Shashikant Khandelwal - Mountain View CA, US Gurpreet Singh Sachdev - Mountain View CA, US Madhur Khandelwal - Mountain View CA, US
Assignee:
The Find Inc. - Mountain View CA
International Classification:
G06N 5/00
US Classification:
706 47, 706 45
Abstract:
A method for identifying primary product objects on webpages over the Internet. A primary product object displays the best view of the product that a webpage is detailing. Each webpage is divided into sections based on the primary product objects in the webpage. Features of candidate product objects in each section are extracted. The primary product objects are identified by computing probabilities of the candidate product objects in each section being primary product objects, based on a statistical model. The identified primary product objects are stored for subsequent retrieval and display.