US 11,816,906 B2
Messaging system for engagement analysis based on labels
Vítor Silva Sousa, Los Angeles, CA (US); Nils Murrugarra-Llerena, Los Angeles, CA (US); Leonardo Ribas Machado das Neves, Marina del Rey, CA (US); and Neil Shah, Los Angeles, CA (US)
Assigned to Snap Inc., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on Jan. 22, 2021, as Appl. No. 17/248,400.
Claims priority of provisional application 63/132,916, filed on Dec. 31, 2020.
Prior Publication US 2022/0207080 A1, Jun. 30, 2022
Int. Cl. G06V 20/70 (2022.01); G06F 16/58 (2019.01); G06N 3/08 (2023.01); G06F 18/214 (2023.01); G06F 18/2431 (2023.01); G06N 3/04 (2023.01); H04L 51/10 (2022.01)
CPC G06V 20/70 (2022.01) [G06F 16/5866 (2019.01); G06F 18/214 (2023.01); G06F 18/2431 (2023.01); G06N 3/08 (2013.01); G06N 3/04 (2013.01); G06V 2201/10 (2022.01); H04L 51/10 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
processing, by one or more processors, content items comprising images to identify elements in the images;
determining, by one or more processors, labels for the images based on conditions indicating when to associate a label of the labels with an image of the images based on the elements in the image;
in response to determining to associate the label with the image, associating the label with the content item;
determining engagement scores for the label based on interactions of users with the content items associated with label;
determining trends in the labels; and
adjusting the engagement scores to determine a dynamic seasonality for an interaction of the interactions of the users, the dynamic seasonality based on an average of subtracting a trend component from values of the interaction.