Automated artificial intelligence (AI) control mode for playing specific tasks during gaming applications

Patent metadata

Field	Value
Publication number	US-10888788-B2
Application number	US-201715426581-A
Country	US
Kind code	B2
Filing date	Feb 7, 2017
Priority date	Jun 30, 2016
Publication date	Jan 12, 2021
Grant date	Jan 12, 2021

Abstract

A method for gaming. The method includes assigning a default game play profile to a user, wherein the default game play profile includes a default game play style that simulates human game play, and wherein the default game play profile is configured to control game play for the user based on the default game play style. The method includes monitoring a plurality of game plays of the user playing a plurality of gaming applications. The method includes generating a user game play profile of the user by adjusting the default game play style based on the plurality of game plays, wherein the user game play profile includes a user game play style customized to the user. The method includes controlling an instance of a first gaming application based on the user game play style of the user game play profile.

First claim

What is claimed is:

1. A method for gaming, comprising:
assigning a default game play profile to a user, wherein the default game play profile comprises a default game play style that simulates human game play, wherein the default game play profile is generated based on a first plurality of game plays of a plurality of players playing a first plurality of gaming applications, wherein the default game play profile is configured to control game play of the user based on the default game play style;
monitoring a second plurality of game plays of the user playing a second plurality of gaming applications;
generating a user game play profile of the user by adjusting the default game play style defined by the default game play profile based on the second plurality of game plays, wherein the user game play profile comprises a user game play style customized to the user, wherein the user game play profile is generated by providing to a deep learning engine a plurality of action states defining types of actions associated with a plurality of tasks presented to the user within the second plurality of game plays, a plurality of action metrics defining actions taken by the user to address the plurality of tasks, and a plurality of action results defining results of the user in addressing the plurality of tasks, wherein the deep learning engine includes a network of interconnected nodes within an input layer, one or more hidden layers, and an output layer, wherein the deep learning engine implementing the user game play profile outputs a player response for a task provided as an input; and
controlling an instance of a gaming application based on the user game play style of the user game play profile, wherein the controlling is done automatically by artificial intelligence (AI) control using the user game play profile.

2. The method of claim 1 , wherein the generating the user game play profile includes:
monitoring a plurality of responses by the user in the second plurality of game plays to a first plurality of tasks each of which is defined by a task type, wherein the default game play style includes a default response to tasks of the task type; and
generating a user response to the tasks of the task type by adjusting the default response based on the plurality of responses by the user.

3. The method of claim 2 , further comprising:
monitoring a plurality of responses by the plurality of players in the first plurality of game plays to a second plurality of tasks each of which is defined by the task type;
generating the default response in the default game play profile based on the plurality of responses by the plurality of players.

4. The method of claim 2 , wherein the generating the user response includes:
applying a least squares function to the plurality of responses by the user to generate the user response.

5. The method of claim 2 , wherein the controlling the instance of the gaming application includes:
detecting that user is presented with the task of the task type in the game play of the user playing the gaming application; and
approaching the task in the game play of the user based on the user response.

6. The method of claim 5 , further comprising:
detecting one or more failed responses to the task in the game play of the user; and
generating for display to the user a query in the instance of the gaming application asking if the user needs help when addressing the task.

7. The method of claim 6 , further comprising:
receiving a request for help; and
generating a hint for display to the user in the instance of the gaming application.

8. The method of claim 6 , further comprising:
receiving a request for help; and
taking full control of the game play of the user in the instance of the gaming application based on the user game play style.

9. The method of claim 6 , further comprising:
receiving a request to automatically handle the task.

10. The method of claim 1 , further comprising:
receiving a request to automatically control the instance of the gaming application.

11. The method of claim 1 , wherein the AI control is facilitated using the processing performed by the deep learning engine configured to model the user with the user game play profile.

12. The method of claim 1 , wherein the controlling the instance of the gaming application includes:
determining that the user is in need of assistance in the game play of the user associated with the instance of the gaming application; and
initiating the controlling of the instance of the gaming application.

13. The method of claim 1 , wherein the controlling the instance of the gaming application includes:
determining that the user is on a break in the game play of the user associated with the instance of the gaming application; and
initiating the controlling of the instance of the gaming application.

14. A method for gaming, comprising:
generating a user game play profile of a user, wherein the user game play profile comprises a user game play style that simulates game play of the user;
receiving a take-over request to switch the game play of the user playing a gaming application to automated game play control; and
controlling an instance of the gaming application based on the user game play style of the user game play profile including a logical structure that defines learned game play responses based on user generated responses from previously conducted game plays of the user playing a plurality of gaming applications, wherein the controlling is done automatically by artificial intelligence (AI) control using the user game play profile,
wherein the user game play profile is generated by providing to a deep learning engine a plurality of action states defining types of actions associated with a plurality of tasks presented to the user within the previously conducted game plays of the user, a plurality of action metrics defining actions taken by the user to address the plurality of tasks, and a plurality of action results defining results of the user in addressing the plurality of tasks, wherein the deep learning engine includes a network of interconnected nodes within an input layer, one or more hidden layers, and an output layer, wherein the deep learning engine implementing the user game play profile outputs a player response for a task provided as an input.

15. The method of claim 14 , further comprising;
limiting the controlling the instance of the gaming application to a time period.

16. The method of claim 14 , further comprising:
receiving a progress control factor in the take-over request;
maintaining a status quo in the game play of the user during the automated game play control when the progress control factor indicates low progress; and
aggressively playing the gaming application in the game play of the user during the automated game play control when the progress control factor indicates high progress.

17. The method of claim 14 , further comprising:
assigning a default game play profile to the user, wherein the default game play profile includes a default game play style that simulates human game play, wherein the default game play profile is generated based on a first plurality of game plays of a plurality of players playing a first plurality of gaming applications, wherein the default game play profile is configured to control the game play of the user based on the default game play style;
monitoring a second plurality of game plays of the user playing a second plurality of gaming applications; and
generating the user game play profile of the user by adjusting t

Assignees

• Sony Interactive Entertainment Inc

Inventors

• Osman Steven
• Stafford Jeffrey R
• Rico Javier F

Classifications

• A63F13/422

  automatically for the purpose of assisting the player, e.g. automatic braking in a driving game · CPC title

• A63F13/45

  Controlling the progress of the video game · CPC title

• A63F13/5375

  for graphically or textually suggesting an action, e.g. by displaying an arrow indicating a turn in a driving game · 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