US 11,789,905 B2
Automated generation of game tags
Eric Holmdahl, San Mateo, CA (US); Nikolaus Sonntag, San Mateo, CA (US); and Aswath Manoharan, San Mateo, CA (US)
Assigned to Roblox Corporation, San Mateo, CA (US)
Filed by Roblox Corporation, San Mateo, CA (US)
Filed on May 27, 2020, as Appl. No. 16/885,047.
Prior Publication US 2021/0374098 A1, Dec. 2, 2021
Int. Cl. G06F 16/16 (2019.01); G06N 3/08 (2023.01)
CPC G06F 16/164 (2019.01) [G06N 3/08 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method to generate one or more text tags for a game using a trained machine learning model, the method comprising:
providing, as input to the trained machine learning model, data that includes a game identifier of the game and a set of digital assets of different classes associated with the game;
generating, using the trained machine learning model and based on the set of digital assets of different classes associated with the game, a plurality of predicted text tags, each predicted text tag associated with a respective prediction score, wherein each predicted text tag is determined based on a respective class of the set of digital assets; and
selecting one or more text tags from the plurality of predicted text tags based on an agreement between at least a particular number of the one or more predicted text tags determined based on the different classes of the set of digital assets, wherein at least one of the one or more selected text tags is indicative of a genre of the game.