Granted Patent B2

US 12,551,795 · App. 18/193,158 · Granted Feb 17, 2026

Inventors: Siddharth Mysore Sthaneshwar (San Mateo, CA); Yunqi Zhao (Sunnyvale, CA); Xin Gao (San Francisco, CA); Alec Jarred Antrim (Algonquin, IL); Harold Henry Chaput (Castro Valley, CA); Fernando de Mesentier Silva (San Francisco, CA)

Assignee: Electronic Arts Inc.

A63F13/5375A63F13/79G06N3/092

Abstract

Claims (47)

1 . A computer-implemented method comprising:

as implemented by an interactive computing system configured with specific computer-executable instructions,

accessing a feature vector associated with a user, wherein the feature vector is extracted from a set of user interaction data associated with the user and obtained based on interaction by the user with a video game during video game play via the interactive computing system, and wherein the feature vector comprises a set of variables that store data determined from the interaction by the user with the video game;

accessing a cluster map comprising a representation of a mapping of user clusters, wherein each location within the cluster map is associated with a set of users whose feature vectors extracted from each user's interaction with the video game during video game play are within a threshold degree of similarity of each other;

determining a map location within the cluster map associated with the user based at least in part on the feature vector, wherein the map location represents a cluster of users whose feature vectors are within a degree of similarity of the feature vector associated with the user;

determining a target map location within the cluster map;

determining a guidance action based at least in part on the target map location and the map location associated with the user; and

executing the guidance action.

2 . The computer-implemented method of claim 1 , wherein the cluster map comprises a self-organizing map generated by processing, using a neural network, a set of feature vectors extracted from user interaction data for a plurality of users that interact with the video game.

3 . The computer-implemented method of claim 1 , wherein determining the map location within the cluster map comprises comparing the feature vector with a set of features associated the map location.

4 . The computer-implemented method of claim 3 , wherein the set of features are determined based on a set of feature vectors associated with a set of users associated with the map location.

5 . The computer-implemented method of claim 1 , wherein the guidance action corresponds to an in-game tutorial, and wherein executing the guidance action comprises outputting the in-game tutorial.

6 . The computer-implemented method of claim 1 , wherein the guidance action corresponds to playable content of the video game, and wherein executing the guidance action comprises causing the playable content to be made available to the user.

7 . The computer-implemented method of claim 6 , wherein the playable content is dynamically generated.

8 . The computer-implemented method of claim 1 , wherein the target map location is associated with a set of features, and wherein the guidance action is determined to reduce a difference between the feature vector of the user and the set of features of the target map location over time thereby adjusting the map location associated with the user to be the target map location.

9 . The computer-implemented method of claim 1 , wherein the target map location and the map location associated with the user are the same, and wherein the guidance action is determined so as to maintain the user associated with the target map location.

10 . The computer-implemented method of claim 1 , wherein the guidance action is determined using a reinforcement-learning based policy.

11 . The computer-implemented method of claim 10 , wherein the guidance action is executed at a first time, and wherein, at a second time that is later than the first time, the method further comprises:

determining a second map location within the cluster map associated with the user based at least in part on a second feature vector associated with the user;

determining whether the second map location matches the target map location; and

in response to determining that the second map location does not match the target map location, initiating a remedial action.

12 . The computer-implemented method of claim 11 , wherein the remedial action modifies the reinforcement-learning based policy.

13 . The computer-implemented method of claim 1 , further comprising:

receiving an indication of a target goal associated with the video game; and

selecting the target map location based at least in part on the target goal.

14 . The computer-implemented method of claim 1 , further comprising:

extracting a set of features from a set of user interaction data associated with a plurality of users that interact with the video game;

applying a map-based machine learning algorithm to the set of features to obtain the cluster map;

receiving an identification of a key feature indicator; and

categorizing clusters of users within the cluster map based at least in part on the key feature indicator.

15 . The computer-implemented method of claim 14 , wherein the map location is associated with a first value of the key feature indicator, wherein the first value of the key feature indicator is associated with the feature vector of the user, and wherein a second value of the key feature indicator is associated with the target map location.

16 . A system comprising:

an electronic data store configured to store a cluster map comprising a mapping of user clusters; and

a hardware processor of an interactive computing system in communication with the electronic data store, the hardware processor configured to execute specific computer-executable instructions to at least:

access a feature vector associated with a user, wherein the feature vector is extracted from a set of user interaction data associated with the user and obtained based on interaction by the user with a video game during video game play via the interactive computing system, and wherein the feature vector comprises a set of variables that store data determined from the interaction by the user with the video game;

access the cluster map from the electronic data store, wherein each location within the cluster map is associated with a set of users whose feature vectors extracted from each user's interaction with the video game during video game play are within a threshold degree of similarity of each other;

determine a map location within the cluster map associated with the user based at least in part on the feature vector, wherein the map location represents a cluster of users whose feature vectors are within a degree of similarity of the feature vector associated with the user;

identify a target map location within the cluster map;

select a guidance action based at least in part on the target map location and the map location associated with the user; and

cause the guidance action to be executed.

17 . The system of claim 16 , wherein the guidance action comprises a recommendation of playable content within the video game to access, and wherein the hardware processor causes the guidance action to be executed by causing a modification to a state of the video game to trigger initiation of the playable content.

18 . The system of claim 16 , wherein the guidance action comprises a user-specific in-game tutorial, and wherein the hardware processor causes the guidance action to be executed by causing the video game to present the user-specific in-game tutorial to the user.

19 . The system of claim 16 , wherein the guidance action is selected to modify user interaction with the video game such that the association of the user with the map location changes to an association with the target map location over a time period.

20 . The system of claim 16 , wherein the hardware processor is further configured to execute specific computer-executable instructions to at least:

determine a second map location within the cluster map associated with the user after the user interacts with the video game for a threshold time period;

compare the second map location to the target map location; and

update a guidance policy that include the guidance action based at least in part on the comparison of the second map location to the target map location.

Assignments (1)

Continuity (1)

References Cited (184)