Meta Platforms, Inc.
Product page classification

Abstract:

In one embodiment, a method includes extracting a document object model (DOM) for a content page. The DOM comprises a hierarchical tree-based data structure. The method also includes traversing the DOM to identify, in the content page, candidate features of a product page. The method further includes for each of the candidate features, determine candidate feature attributes based on a respective context of the candidate feature in the DOM. The method additionally includes determining whether the content page qualifies as a product page based on whether the candidate features fulfill a required set of characteristics for a product page.