IP Library › Granted Patent US 10,133,789
Granted Patent B2
US 10,133,789 · App. 15/174,826 · Granted Nov 20, 2018

Real-time trend detection in a social network

Inventors: Jun Li (Sammamish, WA); Li Ju (Woodinville, WA); Bradley Green (Snohomish, WA); Lars Backstrom (Mountain View, CA)
Assignee: FACEBOOK, INC.
G06F17/3053G06F17/30601G06Q30/02G06Q50/01H04L67/18H04L67/22
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,133,789
App. No.
15/174,826
Granted
Nov 20, 2018
Kind
B2
Abstract

Systems, methods, and apparatuses for tracking trends at an online presence are described. In some embodiments, an interactivity data structure and a tenured interactivity data structure are utilized in determining trends quickly.

Claims (36)

1. A computer-implemented method comprising:

accumulating, by a communication system, a count of instances of interactivity with an interactivity object within the communication system by users of the communication system during a monitoring time period;

designating the accumulated count of instances of interactivity with the interactivity object as tenured interactivity data in response to the accumulated count of instances of interactivity reaching a threshold;

calculating a divergence score for the interactivity object using the accumulated count of interactivity during the monitoring time period designated as tenured and based upon a reference number of instances of interactivity during a previous instance of the monitoring time period; and

displaying the interactivity object as a trending object of the communication system to a user at least partially based on the divergence score of the interactivity object.

2. The computer-implemented method of claim 1 , wherein accumulating the count of instances of interactivity includes checking an interactivity log of the communication system for the interactivity object, wherein the interactivity log records interaction with the interactivity object when each user interacts with the communication system regarding the interactivity object.

3. The computer-implemented method of claim 1 , further comprising:

discarding an instance of interaction with the interactivity object if the instance of interaction is determined to be interactivity caused by a temporal effect, wherein the temporal effect is an effect on interactivity due to at least one of time of a day, day of a week, day of a month, and time of a year.

4. The computer-implemented method of claim 1 , wherein the interactivity object is displayed as a trending object further based on co-visitation by the users of the communication system, wherein co-visitation comprises one or more interactivity objects accessed by a same user during a determined time period, and wherein the one of the one or more interactivity objects co-visited by the users of the communication system are displayed along with the interactivity object as a cluster.

5. The computer-implemented method of claim 1 , wherein the interactivity object is displayed as a trending object further based on a measure of acceleration of number of instances of interactivity during the monitoring time period.

6. The computer-implemented method of claim 1 , wherein the interactivity object comprises one of: a uniform resource locator (URL), a hashtag, a topic, a page, a subscription, an online group, a user profile, and an application software.

7. The computer-implemented method of claim 1 , wherein calculating the divergence score comprises calculating a divergence between the reference number of instances of interactivity during the previous instance of the monitoring time period and the accumulated count of instances of interactivity during the monitoring time period.

8. The computer-implemented method of claim 1 , wherein calculating the divergence score comprises calculating a divergence between a distribution of interactivity during the monitoring time period and a distribution of interactivity during the previous instance of the monitoring time period.

9. The computer-implemented method of claim 1 , wherein calculating the divergence score comprises calculating a Kullback-Leibler divergence.

10. A non-transitory computer-readable storage medium comprising instructions that, when executed by at least one processor, cause a computer device to:

accumulate, by a communication system, a count of instances of interactivity with an interactivity object within the communication system by users of the communication system during a monitoring time period;

designate the accumulated count of instances of interactivity with the interactivity object as tenured interactivity data in response to the accumulated count of instances of interactivity reaching a threshold;

calculate a divergence score for the interactivity object using the accumulated count of interactivity during the monitoring time period designated as tenured and based upon a reference number of instances of interactivity during a previous instance of the monitoring time period; and

display the interactivity object as a trending object of the communication system to a user at least partially based on the divergence score of the interactivity object.

11. The non-transitory computer-readable storage medium of claim 10 , wherein accumulating the count of instances of interactivity includes checking an interactivity log of the communication system for the interactivity object, wherein the interactivity log records interaction with the interactivity object when each user interacts with the communication system regarding the interactivity object.

12. The non-transitory computer-readable storage medium of claim 10 , further comprising instructions to, when executed by the at least one processor, cause the system to:

discard an instance of interaction with the interactivity object if the instance of interaction is determined to be interactivity caused by a temporal effect, wherein the temporal effect is an effect on interactivity due to at least one of time of a day, day of a week, day of a month, and time of a year.

13. The non-transitory computer-readable storage medium of claim 10 , wherein the interactivity object is displayed as a trending object further based upon demographic information of the user.

14. The non-transitory computer-readable storage medium of claim 10 , wherein the interactivity object is displayed as a trending object further based on co-visitation by the users of the communication system, wherein co-visitation is one or more interactivity objects accessed by a same user during a determined time period, and wherein one of the one or more interactivity objects co-visited by the users of the communication system are displayed along with the interactivity object as a cluster.

15. The non-transitory computer-readable storage medium of claim 10 , wherein the interactivity object is displayed as a trending object further based on past activities of the user or past activities of users within a community to which the user belongs.

16. The non-transitory computer-readable storage medium of claim 10 , wherein the interactivity object is displayed as a trending object further based on a location of the user.

17. The non-transitory computer-readable storage medium of claim 10 , wherein the interactivity object is displayed as a trending object further based on a measure of acceleration of number of instances of interactivity during the monitoring time period.

18. The non-transitory computer-readable storage medium of claim 10 , wherein the interactivity object is one of: a uniform resource locator (URL), a hashtag, a topic, a page, a subscription, an online group, a user profile, and an application software.

19. A communication system comprising:

at least one processor; and

at least one non-transitory computer readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the communication system to:

accumulate a count of instances of interactivity with an interactivity object within the communication system by users of the communication system during a monitoring time period;

designate the accumulated count of instances of interactivity with the interactivity object as tenured interactivity data in response to the accumulated count of instances of interactivity reaching a threshold;

calculate a divergence score for the interactivity object using the accumulated count of interactivity during the monitoring time period designated as tenured and based upon a reference number of instances of interactivity during a previous instance of the monitoring time period; and

display the interactivity object as a trending object of the communication system to a user at least partially based on the divergence score of the interactivity object.

20. The communication system of claim 19 , wherein accumulating the count of instances of interactivity includes checking an interactivity log of the communication system for the interactivity object, wherein the interactivity log records interaction with the interactivity object when each user interacts with the communication system regarding the interactivity object.

Assignments (2)
CHANGE OF NAME Recorded Dec 20, 2021
From: FACEBOOK, INC.
To: META PLATFORMS, INC.
Reel/Frame 058961/0436 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 6, 2016
From: LI, JUN; JU, LI; GREEN, BRADLEY; BACKSTROM, LARS
To: FACEBOOK, INC.
Reel/Frame 038822/0486 →
Continuity (2)
Continuation 13961789 · Aug 7, 2013
Related Publication 20160283487A1 · Sep 29, 2016