×

Federation of content items in a social network based on personalized relevance

  • US 10,395,260 B2
  • Filed: 02/27/2015
  • Issued: 08/27/2019
  • Est. Priority Date: 01/30/2015
  • Status: Active Grant
First Claim
Patent Images

1. A method, comprising:

  • obtaining, by one or more computer processors, a first content item from a first content item source, the first content item provided along with a first selection metric determined by the first content item source that indicates an estimated likelihood that the first content item will be interacted with when presented at a first presentation position on a user feed;

    obtaining a second content item from a second content item source that is different than the first content item source, the second content item provided along with a second selection metric determined by the second content item source that indicates an estimated likelihood that the second content item will be interacted with when presented at a second presentation position on a user feed;

    causing the first content item to be presented on user feeds of users at the first presentation position, and the second content item to be presented on user feeds of users at the second presentation position;

    receiving user interaction data indicating interactions by users with the first content item and the second content item;

    determining, based on the user interaction data, an interaction percentage for the first content item and an interaction percentage for the second content item, the interaction percentage for the first content item indicating a percentage of presentations of the first content item that resulted in a user interaction, and the interaction percentage for the second content item indicating a percentage of presentations of the second content item that resulted in a user interaction;

    determining, based on the interaction percentage for the first content and the interaction percentage for the second content item, a first selection metric adjustment for content items received from the first content item source, and a second selection metric adjustment for content items received from the second content item source, the first selection metric adjustment indicating a determined variance between the interaction percentage for the first content time and the estimated likelihood indicated by the first selection metric received from the first content item source, and the second selection metric adjustment indicating a determined variance between the interaction percentage for the second content time and the estimated likelihood indicated by the second selection metric received from the second content item source;

    obtaining profile data for a member of the social network from the electronic data storage;

    for a set of content items obtained from the first data source and a set of content items obtained from the second data source, determining a relevance score of the respective content item to the profile data of the member;

    for each content item from the set of content items obtained from the first data source, determining a utility value for the respective content item based on the first selection metric, the first selection metric adjustment for content items received from the first content item source, and the relevance score of the respective content item;

    for each content item from the set of content items obtained from the second data source, determining a utility value for the respective content item based on the second selection metric, the second selection metric adjustment for content items received from the second content item source, and the relevance score of the respective content item; and

    causing a user device associated with the member to display content items from the first set of content items and the second set of content items based, at least in part, on their respective utility values.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×