公开(公告)号：US20180336574A1

公开(公告)日：2018-11-22

申请号：US15596368

申请日：2017-05-16

Applicant: Facebook, Inc.

Inventor： Vandana Mohan ,  Halil Bayrak ,  Mridul Malpani ,  Vinay Ramesh Jain ,  Eric Gaudet ,  Shashikant Khandelwal

IPC: G06Q30/02 ,  G06Q50/00 ,  G06F17/30 ,  G06N99/00 ,  G06N7/00

Abstract: A method is disclosed which includes: receiving, from a third-party content provider, a link to a structured document on an external server, where the link is associated with a post of the online social network by the third-party content provider, and retrieving the structured document from the external server, where the structured document includes content and input fields.. This step is followed by extracting a predefined set of information from the structured document about the content and input fields of the structured document. The extracted set of information from the structured document are then evaluated to determine one or more feature-values of the structured document. A machine learning model is used to classify the structured document as an external lead-generation type page based on the one or more feature-values of the structured document and a notification is sent to the third-party content provider if the structured document is classified as an external lead-generation type page.

公开(公告)号：US20190034534A1

公开(公告)日：2019-01-31

申请号：US15660731

申请日：2017-07-26

Applicant: Facebook, Inc.

Inventor： Shashikant Khandelwal ,  Eric Gaudet ,  Hamza Aftab ,  Risha Nagin Chheda ,  Xintao Chen ,  Mary Ann Haile ,  Zoheb I. Hajiyani

IPC: G06F17/30 ,  G06K9/46 ,  G06K9/62

Abstract: In one embodiment, a method includes accessing, by a crawling module, a first structured document from an external server, where the first structured document is associated with a first post by a third-party content provider and includes multiple image objects and information associated with the image objects, extracting from the first structured document a sub-set of image objects and information associated with each of the image objects, analyzing the extracted image objects and information to identify categories of image objects based on their features, selecting a first category of image objects that has a highest number of image objects compared to a number of image objects in each other category of image objects, and generating a second post including a multi-image display that includes two or more of the image objects from the first category of image objects.

公开(公告)号：US10685378B2

公开(公告)日：2020-06-16

申请号：US15607226

申请日：2017-05-26

Applicant: Facebook, Inc.

Inventor： Hamza Aftab ,  Rohan Kuruvilla ,  Eric Gaudet ,  Shashikant Khandelwal ,  Kai Ding ,  Risha Nagin Chheda ,  Xintao Chen

IPC: G06Q30/02 ,  G06F16/335

Abstract: An online system aggregates content item from third party systems for presentation to users of the online system. To do so, the online system accesses the web pages of third party systems to trigger tracking pixels that have been previously placed by the third party systems. A triggered tracking pixel sends a server call to the online system that includes tracking pixel data such as information about the content item that was available on the web page. Based on the information gathered through various tracking pixels, the online system generates a catalog of the content item that can then be presented to a user of the online system such that the user can browse content items of the third party system while accessing the online system.