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

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Hartman, Joshua Daniel, Chao, Kai, Goyal, Anuj
• Primary Examiner(s): Featherstone, Mark D
• Assistant Examiner(s): Wu, Tony
• Application Number:
  US14/633,624
• Publication Number:
  US 20160224560A1
• Time in Patent Office: 1,642 Days
• CPC Class Codes: G06F 16/211 Schema design and management
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9577 Optimising the visualization of content, e.g. distillation of HTML documents
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0243 Comparative campaigns
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/303 Terminal profiles
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 67/55 Push-based network services

Abstract

A system and method for the federation of content items of a social network based on personalized relevance includes obtaining content items from first and second content item sources. Profile data for a member of the social network is obtained from the electronic data storage. A relevance score of the content item to the profile data of the member is determined for each of the content items. A utility value is determined based on the selection value, the value metric for content items from the first content item source, and the relevance score. A user device associated with the member displays the content items based on their respective utility values.

Claims

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.

2. The method of claim 1, wherein each of the content items from the first data source and the second data sources has a data type, wherein determining the relevance score for each of the content items is based on the data type in comparison with the profile data of the member.

3. The method of claim 1, wherein determining the relevance score is further based, at least in part, on a size of a social network of the member based on a social graph data.

4. The method of claim 2, wherein determining the relevance score is further based, at least in part, on a number of the plurality of profile data items that correspond with the data type.

5. The method of claim 2, further comprising:

obtaining activity data of members having profile data related to the data type of the content item, wherein determining the relevance score is further based on the activity data.

6. The method of claim 5, wherein determining the relevance score is further based on a percentage difference with which the member interacts with content items of the data type in comparison with other members.

7. The method of claim 3, wherein the size of the social network of the member is based, at least in part, on a number of social network connections between the member and other members of the social network.

8. A system comprising:

one or more computer processors; and

one or more computer-readable mediums storing instructions that, when executed by the one or more computer processors, cause the system to perform operations comprising;

obtaining 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.

9. The system of claim 8, wherein each of the content items from the first data source and the second data sources has a data type, wherein determining the relevance score for each of the content items is based on the data type in comparison with the profile data of the member.

10. The system of claim 8, wherein determining the relevance score is further based, at least in part, on a size of a social network of the member based on a social graph data.

11. The system of claim 9, wherein determining the relevance score is further based, at least in part, on a number of the plurality of profile data items that correspond with the data type.

12. The system of claim 9, the operations further comprising:

obtaining activity data of members having profile data related to the data type of the content item, wherein determining the relevance score is further based on the activity data.

13. The system of claim 12, wherein determining the relevance score is further based on a percentage difference with which the member interacts with content items of the data type in comparison with other members.

14. The system of claim 10, wherein the size of the social network of the member is based, at least in part, on a number of social network connections between the member and other members of the social network.

15. A non-transitory computer-readable medium storing instructions that, when executed by one or more computer processors of a computing device, cause the computing device to perform operations comprising:

obtaining 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.

16. The non-transitory computer-readable medium of claim 15, wherein each of the content items from the first data source and the second data sources has a data type, wherein determining the relevance score for each of the content items is based on the data type in comparison with the profile data of the member.

17. The non-transitory computer-readable medium of claim 15, wherein determining the relevance score is further based, at least in part, on a size of a social network of the member based on a social graph data, the size of the social network of the member being based, at least in part, on a number of social network connections between the member and other members of the social network.

18. The non-transitory computer-readable medium of claim 16, wherein determining the relevance score is further based, at least in part, on a number of the plurality of profile data items that correspond with the data type.

19. The non-transitory computer-readable medium of claim 16, the operations further comprising:

obtaining activity data of members having profile data related to the data type of the content item, wherein determining the relevance score is further based on the activity data.

20. The non-transitory computer-readable medium of claim 19, wherein determining the relevance score is further based on a percentage difference with which the member interacts with content items of the data type in comparison with other members.