IP Library Granted Patent US 9,870,403
Granted Patent B1
US 9,870,403 · App. 14/191,354 · Granted Jan 16, 2018

Estimating social content interactions

Inventors: Junbin Teng (Cupertino, CA); Alessandra Mazzia (Sunnyvale, CA); Chih-Wei Chen (Sunnyvale, CA); Anja Hauth (Zurich, CH); Pascal Tom Getreuer (San Francisco, CA)
Assignee: Google LLC
G06F17/30528G06F17/18G06F17/2247G06F17/30353G06Q30/0202G06Q30/0282
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 9,870,403
App. No.
14/191,354
Granted
Jan 16, 2018
Kind
B1
Abstract

Techniques for estimating social content interactions are provided. An example method includes determining counts of one or more user interactions with one or more content items created by an author, each user interaction of the one or more user interactions having an associated time, classifying, based on respective associated times of the user interactions, the determined counts of the user interactions with the content items into predetermined time intervals spanning a first duration, computing an engagement model for the author based on the classified counts corresponding to the predetermined time intervals and a number of the content items created by the author and estimating, at a particular time for a second duration, a number of interactions with a particular content item created by the author based on the engagement model and a determined actual number of interactions with the particular content item.

Claims (17)

1. A method comprising:

determining counts of one or more user interactions with one or more content items created by an author, each user interaction of the one or more user interactions having an associated time;

classifying, based on respective associated times of the user interactions, the determined counts of the user interactions with the content items into predetermined time intervals spanning a first duration;

computing an engagement model for the author comprising a plurality of engagement values corresponding to the predetermined time intervals, wherein the plurality of engagement values are computed by dividing the classified counts corresponding to the predetermined time intervals by a number of the content items created by the author;

determining, at a particular time in the first duration, an actual number of interactions with a particular content item created by the author;

estimating, at the particular time for a second duration, an estimated number of interactions with the particular content item created by the author based on a summation of the plurality of engagement values of the engagement model and the determined actual number of interactions with the particular content item;

computing a popularity score for the particular content item based on the estimated number of interactions;

determining a display location of the particular content item in a displayed content stream based on the popularity score;

and providing the particular content item for display in the displayed content stream based on the determined display location.

2. The method of claim 1 , wherein the user interactions include a user reading the particular content item, the user selecting the particular content item, the user sharing the particular content item, the user commenting on the particular content item, or the user endorsing the particular content item.

3. The method of claim 1 , further comprising reading the second duration from a memory.

4. The method of claim 1 , further comprising reading the number of content items created by the author from a user account of the author from a social data repository.

5. The method of claim 1 , further comprising:

determining, at another time in the first duration following the particular time, an updated actual number of interactions with a particular content item created by the author;

refining the estimated number of interactions by applying an extrapolation process throughout the first duration based on the determined updated actual number of interactions;

computing a popularity score for the particular content item based on the refined estimated number of interactions; and

providing the particular content item for display based on the popularity score.

Assignments (2)
CHANGE OF NAME Recorded Oct 20, 2017
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 044567/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 6, 2014
From: TENG, JUNBIN; MAZZIA, ALESSANDRA; CHEN, CHIH-WEI; HAUTH, ANJA; GETREUER, PASCAL TOM
To: GOOGLE INC.
Reel/Frame 032371/0480 →