AI modeling for video game coaching and matchmaking

Patent metadata

Field	Value
Publication number	US-11065549-B2
Application number	US-201916355543-A
Country	US
Kind code	B2
Filing date	Mar 15, 2019
Priority date	Mar 15, 2019
Publication date	Jul 20, 2021
Grant date	Jul 20, 2021

Abstract

A method is provided, including the following operations: recording gameplay data from a first session of a video game, the first session defined for interactive gameplay of a user; training a machine learning model using the gameplay data, wherein the training causes the machine learning model to imitate the interactive gameplay of the user; after the training, determining a classification of the machine learning model by exposing the machine learning model to one or more scenarios of the video game, and evaluating actions of the machine learning model in response to the one or more scenarios; using the classification of the machine learning model to assign the user to a second session of the video game.

First claim

What is claimed is:

1. A method, comprising:
recording gameplay data from a first session of a video game, the first session defined for interactive gameplay of a user;
training a machine learning model using the gameplay data, wherein the training causes the machine learning model to imitate the interactive gameplay of the user;
after the training, determining a classification of the machine learning model by exposing the machine learning model to one or more scenarios of the video game, and evaluating actions of the machine learning model in response to the one or more scenarios;
using the classification of the machine learning model to assign the user to a second session of the video game, the second session defined for control of interactive gameplay by the user, the control of interactive gameplay including controlling in-game actions of a character or entity by the user during the second session.

2. The method of claim 1 , wherein the gameplay data includes video of the first session and user inputs during the interactive gameplay.

3. The method of claim 2 , wherein training the machine learning model uses the video and the user inputs to cause the machine learning model to respond to a given portion of the video by generating inputs similar to the user inputs that were generated in response to the given portion of the video during the first session.

4. The method of claim 3 , wherein the given portion of the video is defined by one or more image frames of the video.

5. The method of claim 2 , wherein the user inputs are defined from a controller device operated by the user during the first session.

6. The method of claim 1 , wherein the machine learning model is a neural network.

7. The method of claim 1 , wherein the one or more scenarios of the video game are defined by one or more image frames of the video game, that are not defined from the first session.

8. The method of claim 1 , wherein the gameplay data includes game state data from the first session of the video game.

9. The method of claim 1 ,
wherein the classification identifies a level of skill of the user; and
wherein using the classification to assign the user to the second session includes, identifying levels of skill of one or more other users, and configuring the second session to include one or more of the other users having levels of skill that are similar to the level of skill of the user.

10. The method of claim 1 ,
wherein the classification identifies a skillset of the user; and
wherein using the classification to assign the user to the second session includes, identifying skillsets of one or more other users, and configuring the second session to include one or more of the other users having skillsets that are complementary to the skillset of the user.

11. The method of claim 1 , wherein assigning the user to the second session of the video game includes, inserting an AI bot into the second session, the AI bot using the trained machine learning model to perform gameplay in the second session.

12. A method, comprising:
recording gameplay data from user sessions of a video game, the user sessions defined for interactive gameplay of the video game by a user;
using the gameplay data to train a machine learning model to mimic tendencies of the user in the interactive gameplay;
after the training, performing an evaluation of the trained machine learning model by exposing the trained machine learning model to predefined scenarios of the video game, and analyzing responses to the predefined scenarios by the trained machine learning model;
using the evaluation of the machine learning model to assign the user to a new session of the video game, the new session defined for control of interactive gameplay by the user, the control of interactive gameplay including controlling in-game actions of a character or entity by the user during the second session.

13. The method of claim 12 , wherein the gameplay data includes video and user inputs from the user sessions of the video game.

14. The method of claim 12 , wherein the tendencies of the user in the interactive gameplay are defined by activity and non-activity of the user in the interactive gameplay.

15. The method of claim 12 , wherein performing the evaluation of the trained machine learning model is configured to determine a skill level of the user, and wherein assigning the user to the new session is based on the determined skill level of the user.

16. The method of claim 12 , wherein performing the evaluation of the trained machine learning model is configured to determine a skill set of the user, and wherein assigning the user to the new session is based on the determined skill set of the user.

17. The method of claim 12 , wherein the machine learning model is a neural network.

Assignees

• Sony Interactive Entertainment Inc

Inventors

• Rico Javier Fernandez
• Taylor Michael
• Black Glenn

Classifications

• 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 Primary

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

• G06F18/24

  Classification techniques · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title