Patents by Inventor Luke Sernau

Luke Sernau has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Machine-learning model for ranking diverse content
    Patent number: 11170006
    Abstract: In one embodiment, a method includes a computing system accessing a content item associated with a content provider, the content item having a first set of attributes and a second set of attributes. The system may generate, using a first machine-learning model, a first ranking score of the content item for a user based on the first set of attributes. The system may generate cluster representations of the second set of attributes of the content item. The system may generate, using a second machine-learning model, a second ranking score of the content item for the user based on the cluster representations. The system may generate, using a third machine-learning model, a third ranking score of the content item for the user based on the first ranking score and the second ranking score. The system may select the content item for presentation to the user based on the third ranking score.
    Type: Grant
    Filed: January 3, 2018
    Date of Patent: November 9, 2021
    Assignee: Facebook, Inc.
    Inventors: Luke Sernau, Jonjo Twist
  • Machine-Learning Model for Ranking Diverse Content
    Publication number: 20190205402
    Abstract: In one embodiment, a method includes a computing system accessing a content item associated with a content provider, the content item having a first set of attributes and a second set of attributes. The system may generate, using a first machine-learning model, a first ranking score of the content item for a user based on the first set of attributes. The system may generate cluster representations of the second set of attributes of the content item. The system may generate, using a second machine-learning model, a second ranking score of the content item for the user based on the cluster representations. The system may generate, using a third machine-learning model, a third ranking score of the content item for the user based on the first ranking score and the second ranking score. The system may select the content item for presentation to the user based on the third ranking score.
    Type: Application
    Filed: January 3, 2018
    Publication date: July 4, 2019
    Inventors: Luke Sernau, Jonjo Twist