US 12,130,823 B2
Providing dynamically customized rankings of game items
Sejal Chauhan, San Jose, CA (US); Aswath Manoharan, Sunnyvale, CA (US); Nikolaus Sonntag, Foster City, CA (US); and Eric Holmdahl, San Mateo, CA (US)
Assigned to Roblox Corporation, San Mateo, CA (US)
Filed by Roblox Corporation, San Mateo, CA (US)
Filed on Sep. 1, 2020, as Appl. No. 17/008,732.
Prior Publication US 2022/0067052 A1, Mar. 3, 2022
Int. Cl. G06F 16/00 (2019.01); A63F 13/79 (2014.01); G06F 16/2457 (2019.01); G06F 16/28 (2019.01); G06N 20/00 (2019.01)
CPC G06F 16/24578 (2019.01) [A63F 13/79 (2014.09); G06F 16/285 (2019.01); G06N 20/00 (2019.01); A63F 2300/5546 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, from a user, a request for a list of items available on an online gaming platform;
identifying a particular cluster-specific trained machine learning model from a plurality of trained machine learning models based at least in part on user data associated with the user, wherein the user data includes user profile data and behavioral parameters, wherein each model of the plurality of trained machine learning models corresponds with a respective cluster as its cluster-specific machine learning model, wherein each cluster includes groups of users sharing a subset of one or more of the user profile data and the behavioral parameters, wherein no user is in more than one cluster, and wherein no cluster-specific trained machine learning model corresponds to more than one cluster;
providing an input feature vector to the particular cluster-specific trained machine learning model, wherein the input feature vector includes a plurality of default feature values for each item of a plurality of items, wherein the default feature values include user preferences for items of the plurality of items, and wherein the default feature values are common among users of the online gaming platform;
obtaining an output feature vector from the particular cluster-specific trained machine learning model, wherein the output feature vector includes a modified feature value that modifies each of the plurality of default feature values for each item in the output feature vector;
assigning a rank for each of the plurality of items based on the output feature vector;
generating the list of items, wherein items in the list of items are ordered based on respective ranks; and
providing a user interface to the user that includes the list of items.