Facebook, Inc.

Daniel Schafer

Joshua Van Dyke Watzman

Luke St Clair

Daniel E Weaver

Raylene Kay Yung

Li Zhang

Wayne Kao

Maxim Gubin

Serkan Piantino

Francis Luu

William Samuel Bailey

Bret Steven Taylor

Neel Ishwar Murarka

Carl Philip Sjogreen

Philip Fung

Cory Rudolph Ondrejka

Niv Seker

Dwayne Lloyd Reeves

Kendall Blair Hopkins

Adam Mosseri

Lee Williams Byron

Nicholas Hage Schrock

Maria S Pimenova

Wendy Weihuan Mu

In one embodiment, a method includes receiving a cover feed interaction history from a device associated with a user of a social-networking system. An order for a plurality of content boards may be determined based on the cover feed interaction history (e.g., viewing history, download status, the current order of content boards in the cover feed, user interaction history, whether the user bookmarked or pinned a particular content board), user information related to the user, and device information about device-based events and device status. Finally, the order for the content boards may be sent to the device. The determination of the order for the content boards may be based on the cover feed interaction history, recency of content included in the content boards, popularity of the content, relevance of content to the user, or device-based events.

Re-ranking story content

In one embodiment, a method includes generating a first query requesting a data structure of a specific data type, retrieving the data structure of the specific data type from one or more hierarchical graphs using the first query, retrieving one or more data items from the hierarchical graphs using the data structure, and validating the retrieved data items by determining whether the data structure corresponds to the retrieved data items.

Graph query logic

In one embodiment, user information for a user of a social-networking system is retrieved. Device information is determined for a device associated with the user. Based on the device information or the user information, content associated with the user is retrieved. Using the retrieved content, a content board is composed for use in a cover feed displayed on the device The content board may comprise a background image. Finally, the content board is sent to the device. In one embodiment, updated information for content associated with the user is retrieved. The updated information may be associated with content that was included in a previously-provided content board. Using the updated information, an update to the previously-provided content boards is composed. Finally, the updates may be sent to the previously-provided content boards to the device.

Social cover feed interface

To generate stories for presentation to social networking system users, one or more story generation engines receives a set of actions of social networking system users. Various story generation engines output stories of different types that collect particular types of actions and arrange the actions in a specified format for presentation. The story generators may avoid selecting the same actions for different stories. Stories generated by the various story generators may be ranked and the ranking used to select stories for presentation to one or more social networking system users.

Aggregating social networking system user information for display via stories

Technology for optimizing policy evaluation is disclosed. A policy may include an ordered rule set. When evaluated, the highest priority rule in the order that does not skip may control the outcome of the policy. Rules within a policy may have associated costs and an associated probability of not skipping. The rules of a policy may not need to be executed in a particular order for a system to determine the correct evaluation of the policy and groups of rules, or 'batches,' may be run simultaneously. Technology is disclosed to optimize policy evaluation by creating batches and orderings of those batches which have a lower expected cost than other ordered sets of batches. The expected cost for each ordered set of batches may be calculated based on: rule costs, probabilities associated with one or more rules, the organization of the rules into batches, and the ordering of batches within sets.

Policy performance ordering

One embodiment selects from a plurality of actions performed by one or more users of a social networking system a first action and one or more second actions, wherein each action has one or more attributes; computes a score for each second action by comparing the one or more attributes of each second action with the one or more attributes of the first action; ranks the one or more second actions according to the score computed for each second action; and selects from the one or more second actions one or more highest-ranking second actions as being related to the first action.

Action clustering for news feeds

Growing community of inventors

San Francisco, CA, United States of America

Daniel Schafer