US 12,427,426 B2
Automatic detection of prohibited gaming content
Matt Kaufman, San Carlos, CA (US); Shyna Khurana, San Francisco, CA (US); Dean Neal Browne, San Carlos, CA (US); and Arthur Remy Malan, Menlo Park, CA (US)
Assigned to Roblox Corporation, San Mateo, CA (US)
Filed by Roblox Corporation, San Mateo, CA (US)
Filed on Oct. 16, 2023, as Appl. No. 18/380,315.
Application 18/380,315 is a continuation of application No. 17/172,866, filed on Feb. 10, 2021, granted, now 11,786,824.
Prior Publication US 2024/0033644 A1, Feb. 1, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. A63F 13/75 (2014.01); A63F 13/79 (2014.01); G06N 20/00 (2019.01)
CPC A63F 13/75 (2014.09) [A63F 13/79 (2014.09); G06N 20/00 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving data associated with a virtual environment, the data indicative of at least one developer, at least one user, and content of a particular virtual experience;
determining input features based on the data indicative of the at least one developer, the at least one user, and the content, wherein determining the input features comprises iteratively obtaining portions of one or more of a multidimensional vector or a matrix representation based on the data indicative of the at least one developer, the at least one user, and the content, until a threshold number of the input features have been determined;
providing the input features to a trained machine learning model, the model trained to assign classifications to virtual experiences; and
obtaining, as output of the machine learning model, a classification of the particular virtual experience.