Using playstyle patterns to generate virtual representations of game players

Patent metadata

Field	Value
Publication number	US-11944903-B2
Application number	US-202117184979-A
Country	US
Kind code	B2
Filing date	Feb 25, 2021
Priority date	Mar 29, 2019
Publication date	Apr 2, 2024
Grant date	Apr 2, 2024

Abstract

In various embodiments of the present disclosure, playstyle patterns of players are learned and used to generate virtual representations (“bots”) of users. Systems and methods are disclosed that use game session data (e.g., metadata) from a plurality of game sessions of a game to learn playstyle patterns of users, based on user inputs of the user in view of variables presented within the game sessions. The game session data is applied to one or more machine learning models to learn playstyle patterns of the user for the game, and associated with a user profile of the user. Profile data representative of the user profile is then used to control or instantiate bots of the users, or of categories of users, according to the learned playstyle patterns.

First claim

What is claimed is:

1. A method comprising:
receiving first game session data corresponding to a first user during a first instance of a game;
based at least on a selection associated with the first user, executing a second instance of the game that includes at least an instantiation of a bot associated with the first user;
selecting a machine learning model based at least on a similarity between the first game session data and second game session data associated with a second user that is different than the first user; and
controlling the instantiation of the bot within the second instance of the game based at least on the machine learning model.

2. The method of claim 1 , further comprising:
storing a profile associated with the second user, the profile representative of the second game session data corresponding to the second user and collected over one or more game sessions; and
associating the machine learning model with the profile,
wherein the selecting the machine learning model is based at least on the profile.

3. The method of claim 2 , wherein the machine learning model is trained using at least a portion of the second game session data.

4. The method of claim 1 , wherein the controlling the instantiation of the bot within the second instance of the game comprises:
computing, using the machine learning model and based at least on third game session data associated with the second instance of the game, data indicative of one or more simulated inputs to one or more simulated input devices, the one or more simulated inputs devices including one or more of a control pad, a keyboard, a mouse, a touch-screen display, a controller, a remote, or a headset; and
controlling the instantiation of the bot within the second instance of the game based at least on the one or more simulated inputs.

5. The method of claim 1 , wherein the machine learning model includes a neural network trained using inverse reinforcement learning.

6. The method of claim 1 , wherein the first game session data includes at least one of image data or audio data generated during the first instance of the game from a perspective of the first user.

7. The method of claim 1 , wherein the selecting the machine learning model comprises:
comparing, based at least on the first game session data and the second game session data, a first playstyle associated with the first user to a second playstyle associated with the second user; and
selecting the machine learning model based at least on the comparing the first playstyle to the second playstyle.

8. The method of claim 1 , further comprising:
receiving, from a user device associated with a third user, the selection associated with the first user,
wherein the second instance of the game further includes the third user.

9. A system comprising:
one or more processors; and
one or more computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
identifying, based at least on first game session data corresponding to a first user during a first instance of a game, a machine learning model associated with a second user that is different than the first user;
generating second game session data corresponding to a second instance of the game, the second game session data including at least one of image data or audio data generated during the second instance of the game;
computing, using the machine learning model and based at least on the second game session data, data indicative of one or more simulated inputs; and
controlling an instantiation of a bot associated with the first user and within the second instance of the game based at least on the one or more simulated inputs.

10. The system of claim 9 , wherein the one or more computer-readable media store further instructions that, when executed by the one or more processors, cause the one or more processors to perform further operations comprising:
retrieving a profile associated with the second user, the profile representative of historical game session data corresponding to the second user and collected over a plurality of game sessions,
wherein the identifying the machine learning model is further based at least on the profile.

11. The system of claim 10 , wherein the machine learning model is trained using at least a portion of the historical game session data.

12. The system of claim 9 , wherein the one or more simulated inputs are associated with one or more of a control pad, a keyboard, a mouse, a touch-screen display, a controller, a remote, or a headset.

13. The system of claim 9 , wherein the machine learning model includes a neural network trained using inverse reinforcement learning.

14. The system of claim 9 , wherein the controlling the instantiation of the bot includes applying input data representative of the one or more simulated inputs to the second instance of the game.

15. The system of claim 9 , wherein the identifying the machine learning model comprises:
determining, based at least on the first game session data and the second game session data, that a first playstyle associated with the first user is related to a second playstyle associated with the second user; and
identifying the machine learning model based at least on the first playstyle being related to the second playstyle.

16. A system comprising:
one or more processors; and
one or more computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
generating first game session data corresponding to a first instance of a game that includes at least a first user;
determining, based at least on a portion of the first game session data corresponding to the first user, a machine learning model that is associated with a profile of a second user;
generating second game session data corresponding a second instance of the game, the second instance of the game including at least a third user and a bot associated with the first user;
computing, using the machine learning model and based at least on the second game session data, data indicative of one or more simulated inputs; and
controlling an instantiation of the bot within the second instance of the game based at least on the one or more simulated inputs.

17. The system of claim 16 , wherein the one or more computer-readable media store further instructions that, when executed by the one or more processors, cause the one or more processors to perform further operations comprising:
at an end of the first instance of the game, generating a user interface that includes at least an indication of the first user; and
receiving data representative of a selection of the indication of the first user,
wherein the determining the machine learning model is further based at least on the selection.

18. The system of claim 16 , wherein the machine learning model is trained using training game session data captured during one or more historical instances of the game participated in by the second user.

19. The system of claim 16 , wherein the one or more simulated inputs devices include one or more of a control pad, a keyboard, a mouse, a touch-screen display, a controller, a remote, or a headset.

20. The system of claim 16 , wherein the system is comprised in at least one of:
a system for performing deep learning operations;
a system implemented using an edge device;
a system incorporating one or mor

Assignees

• Nvidia Corp

Inventors

• Fear Andrew
• Burke Brian
• Prasad Pillulta Venkata Naga Hanumath
• Lalwani Abhishek

Classifications

• A63F13/56 Primary

  Computing the motion of game characters with respect to other game characters, game objects or elements of the game scene, e.g. for simulating the behaviour of a group of virtual soldiers or for path finding · CPC title

• A63F13/67 Primary

  adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use · CPC title

• A63F13/798

  for assessing skills or for ranking players, e.g. for generating a hall of fame · CPC title

• G06N3/088

  Non-supervised learning, e.g. competitive learning · CPC title

• G06N7/00

  Computing arrangements based on specific mathematical models · CPC title