Selecting social networking system user information for display via a timeline interface

• US 10,242,067 B2
• Filed: 03/26/2014
• Issued: 03/26/2019
• Est. Priority Date: 09/21/2011
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Piantino, Serkan, Case, Ryan, Funiak, Stanislav, Gibson, Daniel Klatzko, Huang, Jeff, Mack, Ryan David, McDonald, Paul M., Vijayvergiya, Arun, Wiseman, Joshua, Yang, Zizhuang, Young, Steven, Yung, Raylene Kay, Zuckerberg, Mark E.
• Primary Examiner(s): Hong, Stephen S
• Assistant Examiner(s): Ludwig, Matthew J
• Application Number:
  US14/226,767
• Publication Number:
  US 20140214737A1
• Time in Patent Office: 1,826 Days
• Field of Search: 715203, 715764
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/447 Temporal browsing, e.g. timeline
• CPC Class Codes: G06F 16/904 Browsing; Visualisation therefor for navigating the web G06F16/954; browsing optimisation for the web G06F16/957
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

The invention provides a display interface in a social networking system that enables the presentation of information related to a user in a timeline or map view. The system accesses information about a user of a social networking system, including both data about the user and social network activities related to the user. The system then selects one or more of these pieces of data and/or activities from a certain time period and gathers them into timeline units based on their relatedness and their relevance to users. These timeline units are ranked by relevance to the user, and are used to generate a timeline or map view for the user containing visual representations of the timeline units organized by location or time. The timeline or map view is then provided to other users of the social networking system that wish to view information about the user.

Claims

1. A method comprising:

accessing a first request from a first viewing user and a second request from a second viewing user for a user profile page related to a subject user of a social networking system, where the first and second viewing users are different from the subject user;

generating a set of timeline units based on narrative data associated with the subject user, each timeline unit of the set of timeline units including one or more content items from the narrative data;

for the first viewing user and the second viewing user;

generating a score for each of the set of timeline units, wherein each score comprises a measure of the relevance of a timeline unit to the respective viewing user;

generating a ranking of the set of timeline units based on the scores generated for each of the set of timeline units for the respective viewing user; and

selecting a subset of the set of timeline units based on the ranking for the respective viewing user, wherein the selected subset of timeline units for the first viewing user is different than the selected subset of timeline units for the second viewing user; and

transmitting the user profile page to the first viewing user and the second viewing user, the user profile page comprising a timeline interface that includes the selected subset of timeline units for the respective viewing user.

2. The method of claim 1, wherein the set of timeline units have different types, and the scores for the set of timeline units are normalized across timeline units of different types.

3. The method of claim 2, wherein selecting the subset of timeline units comprises performing a diversification process to ensure a diversity of timeline unit types.

4. The method of claim 1, wherein the score for each timeline unit is generated by a machine-learned model.

5. The method of claim 4, wherein the machine-learned model uses social data signals as input to generate a score.

6. The method of claim 5, wherein the social data signals comprise “

likes”

, user comments, user tags, user views, or user affinity.

7. The method of claim 4, wherein the machine-learned model uses at least one of image features, video features, and textual features as inputs to generate scores for the one or more timeline units.

8. The method of claim 4, wherein user curation data collected from the timeline interface is used as training data to train the machine-learned model.

9. The method of claim 1, wherein selecting the subset of the set of timeline units comprises performing a de-duplication of timeline units to prevent repetitive display of narrative data.

10. The method of claim 9, wherein performing the de-duplication of timeline units comprises removing duplicated narrative data from a timeline unit based on it having a lower score than another timeline unit containing the same narrative data.

11. A method comprising:

accessing a first request from a first viewing user and a second request from a second viewing user for a user profile page related to a subject user, the subject user being associated with a plurality of content items, and the first and second viewing users being different from the subject user;

selecting a set of the plurality of content items;

generating a plurality of timeline units based on the selected set of content items;

for the first viewing user and the second viewing user;

generating a score for each of the plurality of timeline units, wherein each score comprises a measure of the relevance of a timeline unit to the respective viewing user;

generating a ranking of the plurality of timeline units based on the scores generated for each of the plurality of timeline units for the respective viewing user; and

selecting a subset of the plurality of timeline units based on the ranking for the respective viewing user, wherein the selected subset of timeline units for the first viewing user is different than the selected subset of timeline units for the second viewing user; and

transmitting the user profile page to the first viewing user and the second viewing user, the user profile page comprising a timeline interface that includes the selected subset of timeline units for the respective viewing user.

12. The method of claim 11, wherein the plurality of timeline units have different types, and the scores for the plurality of timeline units are normalized across timeline units of different types.

13. The method of claim 12, wherein selecting the subset of timeline units comprises performing a diversification process to ensure a diversity of timeline unit types.

14. The method of claim 11, wherein the score for each timeline unit is generated by a machine-learned model.

15. The method of claim 14, wherein the machine-learned model uses social data signals as input to generate a score.

16. The method of claim 14, wherein the machine-learned model uses at least one of image features, video features, and textual features as inputs to generate scores for the plurality of timeline units.

17. The method of claim 14, wherein user curation data collected from the timeline interface is used as training data to train the machine-learned model.

18. The method of claim 11, wherein selecting the subset of timeline units further comprises performing de-duplication of timeline units to prevent repetitive display of narrative data.

19. A non-transitory computer-readable storage medium comprising instructions that, when executed by a processor, cause the processor to:

access a first request from a first viewing user and a second request from a second viewing user for a user profile page related to a subject user of a social networking system, where the first and second viewing users are different from the subject user;

generate a set of timeline units based on narrative data associated with the subject user, each timeline unit of the set of timeline units including one or more content items from the narrative data;

for the first viewing user and the second viewing user;

generate a score for each of the set of timeline units, wherein each score comprises a measure of the relevance of a timeline unit to the respective viewing user;

generate a ranking of the set of timeline units based on the scores generated for each of the set of timeline units for the respective viewing user; and

select a subset of the set of timeline units based on the ranking for the respective viewing user, wherein the selected subset of timeline units for the first viewing user is different than the selected subset of timeline units for the second viewing user; and

transmit the user profile page to the first viewing user and the second viewing user, the user profile page comprising a timeline interface that includes the selected subset of timeline units for the respective viewing user.

20. The computer-readable storage medium of claim 19, wherein the set of timeline units have different types, and the scores for the set of timeline units are normalized across timeline units of different types.