IP Library Granted Patent US 12,290,754
Granted Patent B2
US 12,290,754 · App. 17/131,048 · Granted May 6, 2025

Automated artificial intelligence (AI) personal assistant

Inventors: Steven Osman (San Francisco, CA); Jeffrey R. Stafford (Redwood City, CA); Javier F. Rico (Pacifica, CA); Michael G. Taylor (San Mateo, CA); Todd S. Tokubo (Newark, CA)
Assignee: Sony Interactive Entertainment Inc.
A63F13/67A63F13/335A63F13/5375A63F13/795A63F13/798A63F13/85G06N5/04A63F2300/407A63F2300/535A63F2300/6027
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,290,754
App. No.
17/131,048
Granted
May 6, 2025
Kind
B2
Abstract

A method for assisting game play. The method includes monitoring game play of the user playing a gaming application, wherein the user has a defined task to accomplish, wherein the task is associated with a task type. The method includes determining a task type proficiency rule for the task type based on results of a plurality of players taking on a plurality of tasks having the task type. The method includes determining a player proficiency score for accomplishing the task based on the task type proficiency rule. The method includes determining a user predictive rate of success in accomplishing the task based on the player proficiency score, the task type proficiency rule, and the task. The method includes determining a recommendation for the user based on the user predictive rate of success.

Claims (90)

1. A method, comprising:

establishing at a game server a multi-player gaming session of a gaming application, wherein a first client device of a first player and a second client device of a second player are communicatively coupled to the game server via a network to enable participation in the multi-player gaming session;

monitoring at the game server a first game play of the first player and a second game play of the second player in the multi-player gaming session of the gaming application to determine a current game context using a first artificial intelligence (AI) model configured to learn a plurality of game contexts of the of the gaming application;

executing the first AI model to identify a plurality of tasks potentially presented in the multi-player gaming session based on the current game context, wherein the plurality of tasks correspond with a plurality of task types;

dynamically determining at the game server during the multi-player gaming session a plurality of player proficiency scores for the first player and the second player in association with the plurality of tasks types based on first data collected by the game server from a first plurality of game plays of a first plurality of gaming applications by the first player and second data collected by the game server from a second plurality of game plays by a second plurality of gaming applications of the second player, wherein the first plurality of game plays includes the first game play of the first player and the second plurality of game plays includes the second game play of the second player;

executing a second AI model configured to predict rates of success when accomplishing tasks encountered in the gaming application to determine at the game server during the multi-player gaming session a plurality of predictive rates of success for different combinations of task pairs from the plurality of tasks that could be performed by the first player and the second player based on the plurality of player proficiency scores;

assigning at the game server during the multi-player gaming session a first task of a first task type to the first player and a second task of a second task type to the second player that has the maximum predictive rate of success from the plurality of predictive rates of success, wherein the plurality of tasks include the first task and the second task;

sending a first notification over the network to the first client device that the first task to be performed in the multi-player gaming session is assigned to the first player; and

sending a second notification over the network to the second client device that the second task to be performed in the multi-player gaming session is assigned to the second player,

wherein the game server is configured to control the multi-player gaming session.

2. The method of claim 1 , further comprising:

determining a first player proficiency score for the first player in association with the first task type;

determining a second player proficiency score for the second player in association with the second task type; and

determining a predictive rate of success for accomplishing the first task by the first player and the second task by the second player based on the first player proficiency score for the first player and the second player proficiency score for the second player.

3. The method of claim 1 , further comprising:

determining a first corresponding task type and a second corresponding task type for each of the different combinations of task pairs;

determining a first corresponding player proficiency score for the first corresponding task type for the first player;

determining a second corresponding player proficiency score for the second corresponding task type for the second player; and

determining a predictive rate of success for accomplishing tasks in the each of the different combinations of task pairs based on the first corresponding player proficiency score and the second corresponding player proficiency score.

4. The method of claim 2 ,

wherein the first player proficiency score is based on current and past performances of the first player when encountering the first plurality of tasks of the first task type.

5. The method of claim 1 , further comprising:

assigning a plurality of tasks of a plurality of task types between the first player and the second player to maximize a combined predictive rate of success for accomplishing the plurality of tasks,

wherein the first player and the second player work cooperatively to accomplish the plurality of tasks.

6. The method of claim 1 , further comprising:

determining a first player proficiency score for the first player in accomplishing the first task;

determining a first predictive rate of success in accomplishing the first task based on the first player proficiency score; and

determining a recommendation for the first player in association with accomplishing the first task based on the first player proficiency score.

7. The method of claim 1 , further comprising:

determining a first player proficiency score for the first player in association with accomplishing tasks of a first task type encountered in the gaming application.

8. A non-transitory computer-readable medium storing a computer program for performing a method, the non-transitory computer-readable medium comprising:

program instructions for establishing at a game server a multi-player gaming session of a gaming application, wherein a first client device of a first player and a second client device of a second player are communicatively coupled to the game server via a network to enable participation in the multi-player gaming session;

program instructions for monitoring at the game server a first game play of the first player and a second game play of the second player in the multi-player gaming session of the gaming application to determine a current game context using a first artificial intelligence (AI) model configured to learn a plurality of game contexts of the of the gaming application;

program instructions for executing the first AI model to identify a plurality of tasks potentially presented in the multi-player gaming session based on the current game context, wherein the plurality of tasks correspond with a plurality of task types;

program instructions for dynamically determining at the game server during the multi-player gaming session a plurality of player proficiency scores for the first player and the second player in association with the plurality of tasks types based on first data collected by the game server from a first plurality of game plays of a first plurality of gaming applications by the first player and second data collected by the game server from a second plurality of game plays by a second plurality of gaming applications of the second player, wherein the first plurality of game plays includes the first game play of the first player and the second plurality of game plays includes the second game play of the second player;

program instructions for executing a second AI model configured to predict rates of success when accomplishing tasks encountered in the gaming application to determine at the game server during the multi-player gaming session a plurality of predictive rates of success for different combinations of task pairs from the plurality of tasks that could be performed by the first player and the second player based on the plurality of player proficiency scores;

program instructions for assigning at the game server during the multi-player gaming session a first task of a first task type to the first player and a second task of a second task type to the second player that has the maximum predictive rate of success from the plurality of predictive rates of success, wherein the plurality of tasks include the first task and the second task;

program instructions for sending a first notification over the network to the first client device that the first task to be performed in the multi-player gaming session is assigned to the first player; and

program instructions for sending a second notification over the network to the second client device that the second task to be performed in the multi-player gaming session is assigned to the second player,

wherein the game server is configured to control the multi-player gaming session.

9. The non-transitory computer-readable medium of claim 8 , further comprising:

program instructions for determining a first player proficiency score for the first player in association with the first task type;

program instructions for determining a second player proficiency score for the second player in association with the second task type; and

program instructions for determining a predictive rate of success for accomplishing the first task by the first player and the second task by the second player based on the first player proficiency score for the first player and the second player proficiency score for the second player.

10. The non-transitory computer-readable medium of claim 8 , further comprising:

program instructions for determining a first corresponding task type and a second corresponding task type for each of the different combinations of task pairs;

program instructions for determining a first corresponding player proficiency score for the first corresponding task type for the first player;

program instructions for determining a second corresponding player proficiency score for the second corresponding task type for the second player; and

program instructions for determining a predictive rate of success for accomplishing tasks in the each of the different combinations of task pairs based on the first corresponding player proficiency score and the second corresponding player proficiency score.

11. The non-transitory computer-readable medium of claim 9 ,

wherein in the method the first player proficiency score is based on current and past performances of the first player when encountering the first plurality of tasks of the first task type.

12. The non-transitory computer-readable medium of claim 8 , further comprising:

program instructions for assigning a plurality of tasks of a plurality of task types between the first player and the second player to maximize a combined predictive rate of success for accomplishing the plurality of tasks,

wherein the first player and the second player work cooperatively to accomplish the plurality of tasks.

13. The non-transitory computer-readable medium of claim 8 , further comprising:

program instructions for determining a first player proficiency score for the first player in accomplishing the first task;

program instructions for determining a first predictive rate of success in accomplishing the first task based on the first player proficiency score; and

program instructions for determining a recommendation for the first player in association with accomplishing the first task based on the first player proficiency score.

14. The non-transitory computer-readable medium of claim 8 , further comprising:

program instructions for determining a first player proficiency score for the first player in association with accomplishing tasks of a first task type encountered in the gaming application.

15. A computer system comprising:

a processor; and

memory coupled to the processor and having stored therein instructions that, if executed by the computer system, cause the computer system to execute a method comprising:

establishing at a game server a multi-player gaming session of a gaming application, wherein a first client device of a first player and a second client device of a second player are communicatively coupled to the game server via a network to enable participation in the multi-player gaming session;

monitoring at the game server a first game play of the first player and a second game play of the second player in the multi-player gaming session of the gaming application to determine a current game context using a first artificial intelligence (AI) model configured to learn a plurality of game contexts of the of the gaming application;

executing the first AI model to identify a plurality of tasks potentially presented in the multi-player gaming session based on the current game context, wherein the plurality of tasks correspond with a plurality of task types;

dynamically determining at the game server during the multi-player gaming session a plurality of player proficiency scores for the first player and the second player in association with the plurality of tasks types based on first data collected by the game server from a first plurality of game plays of a first plurality of gaming applications by the first player and second data collected by the game server from a second plurality of game plays by a second plurality of gaming applications of the second player, wherein the first plurality of game plays includes the first game play of the first player and the second plurality of game plays includes the second game play of the second player;

executing a second AI model configured to predict rates of success when accomplishing tasks encountered in the gaming application to determine at the game server during the multi-player gaming session a plurality of predictive rates of success for different combinations of task pairs from the plurality of tasks that could be performed by the first player and the second player based on the plurality of player proficiency scores;

assigning at the game server during the multi-player gaming session a first task of a first task type to the first player and a second task of a second task type to the second player that has the maximum predictive rate of success from the plurality of predictive rates of success, wherein the plurality of tasks include the first task and the second task;

sending a first notification over the network to the first client device that the first task to be performed in the multi-player gaming session is assigned to the first player; and

sending a second notification over the network to the second client device that the second task to be performed in the multi-player gaming session is assigned to the second player,

wherein the game server is configured to control the multi-player gaming session.

16. The computer system of claim 15 , the method further comprising:

determining a first player proficiency score for the first player in association with the first task type;

determining a second player proficiency score for the second player in association with the second task type; and

determining a predictive rate of success for accomplishing the first task by the first player and the second task by the second player based on the first player proficiency score for the first player and the second player proficiency score for the second player.

17. The computer system of claim 15 , the method further comprising:

determining a first corresponding task type and a second corresponding task type for each of the different combinations of task pairs;

determining a first corresponding player proficiency score for the first corresponding task type for the first player;

determining a second corresponding player proficiency score for the second corresponding task type for the second player; and

determining a predictive rate of success for accomplishing tasks in the each of the different combinations of task pairs based on the first corresponding player proficiency score and the second corresponding player proficiency score.

18. The computer system of claim 15 , the method further comprising:

assigning a plurality of tasks of a plurality of task types between the first player and the second player to maximize a combined predictive rate of success for accomplishing the plurality of tasks,

wherein the first player and the second player work cooperatively to accomplish the plurality of tasks.

19. The computer system of claim 15 , the method further comprising:

determining a first player proficiency score for the first player in accomplishing the first task;

determining a first predictive rate of success in accomplishing the first task based on the first player proficiency score; and

determining a recommendation for the first player in association with accomplishing the first task based on the first player proficiency score.

20. The computer system of claim 15 , the method further comprising:

determining a first player proficiency score for the first player in association with accomplishing tasks of a first task type encountered in the gaming application.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 20, 2025
From: OSMAN, STEVEN; STAFFORD, JEFFREY R.; RICO, JAVIER F.; TAYLOR, MICHAEL G.; TOKUBO, TODD S.
To: SONY INTERACTIVE ENTERTAINMENT INC.
Reel/Frame 070279/0348 →
Continuity (4)
Continuation 16268384 · Feb 5, 2019
Continuation 15467557 · Mar 23, 2017
Provisional Application 62357248 · Jun 30, 2016
Related Publication 20210106919A1 · Apr 15, 2021
References Cited (49)
US 6966832B2 · Leen et al. · 2005 [cited by applicant]
US 7452273B2 · Amaitis et al. · 2008 [cited by applicant]
US 9108108B2 · Zalewski et al. · 2015 [cited by applicant]
US 9443192B1 · Cosic · 2016 [cited by applicant]
US 9498704B1 · Cohen et al. · 2016 [cited by applicant]
US 9662584B2 · Youm et al. · 2017 [cited by applicant]
US 10112113B2 · Krishnamurthy · 2018 [cited by applicant]
US 10828566B2 · Krishnamurthy · 2020 [cited by applicant]
US 10828567B2 · Krishnamurthy · 2020 [cited by applicant]
US 11420124B2 · Krishnamurthy · 2022 [cited by applicant]
US 20030045359A1 · Leen et al. · 2003 [cited by applicant]
US 20040097287A1 · Postrel · 2004 [cited by applicant]
US 20050118996A1 · Lee et al. · 2005 [cited by applicant]
US 20060247055A1 · O'Kelley et al. · 2006 [cited by applicant]
US 20070112706A1 · Herbrich et al. · 2007 [cited by applicant]
US 20080220854A1 · Midgley et al. · 2008 [cited by applicant]
US 20130005452A1 · Chatani · 2013 [cited by applicant]
US 20130084985A1 · Green et al. · 2013 [cited by applicant]
US 20130316779A1 · Vogel · 2013 [cited by applicant]
US 20130316836A1 · Vogel et al. · 2013 [cited by applicant]
US 20150231502A1 · Allen et al. · 2015 [cited by applicant]
US 20160067612A1 · Ntoulas et al. · 2016 [cited by applicant]
US 20160071355A1 · Morrison et al. · 2016 [cited by applicant]
US 20160166935A1 · Condrey et al. · 2016 [cited by applicant]
US 20160279522A1 · De Plater et al. · 2016 [cited by applicant]
US 20170282063A1 · Krishnamurthy · 2017 [cited by applicant]
US 20190358545A1 · Aghdaie et al. · 2019 [cited by applicant]
CN 101160158A · 2008 [cited by applicant]
CN 101313322A · 2008 [cited by applicant]
CN 105302963A · 2016 [cited by applicant]
CN 105426969A · 2016 [cited by applicant]
CN 106406912A · 2017 [cited by applicant]
JP 2006341086A · 2006 [cited by applicant]
JP 2007069005A · 2007 [cited by applicant]
JP 2010201035A · 2010 [cited by applicant]
JP 2011218102A · 2011 [cited by applicant]
JP 2012205749A · 2012 [cited by applicant]
CN Application No. 202210669703.8 Office Action, Dated Jun. 8, 2023, Total 7 pages. [cited by applicant]
CN Application No. 202210669703.8 Office Action, Dated Mar. 28, 2023, Total 5 pages. [cited by applicant]
Bogdanovic et al., “Deep Apprenticeship Learning for Playing Video Games,” Learning for General Competency in Video Games: Papers from the 2015 AAAI Workshop, 2015, 7-9. [cited by applicant]
International Preliminary Report on Patentability in International Appln. No. PCT/US2017/029864, mailed on Jan. 1, 2019, 10 pages. [cited by applicant]
International Search Report and Written Opinion PCT/US2017/029864, mailed on Aug. 14, 2017, 17 pages. [cited by applicant]
Masato, “Research on game AI that automatically acquires human-like behavior,” Thesis for the degree of Doctor of Engineering, Kwansei Gakuin University, Jun. 18, 2016, 2 pages (abstract only). [cited by applicant]
Min et al., “Deep Learning-Based Goal Recognition in Open-Ended Digital Games,” Department of Computer Science, North Carolina State University, Raleigh, NC, 2014, 37-43. [cited by applicant]
Mnih et al., “Human-level control through deep reinforcement learning,” Nature, Feb. 26, 2015, 518(7540):529-533. [cited by applicant]
Mnih et al., “Playing Atari with Deep Reinforcement Learning,” DeepMind Technologies, Dec. 2013, 9 pages. [cited by applicant]
Vice.com [online], “This Deep Learning Algorithm Can Predict Your Next Move in a Video Game,” Sep. 9, 2014, retrieved on Jan. 21, 2025, retrieved from URL<https://www.vice.com/en/article/this-deep-learning-algorithm-can… [cited by applicant]
Wired.com [online], “In Forza Horizon 2, Computers Finally Drive as Crazy as Humans,” Sep. 25, 2014, retrieved on Jan. 21, 2025, retrieved from URL<https://www.wired.com/2014/09/forza-horizon-2-drivatars/>, 15 pages. [cited by applicant]
Yusuke et al., “Imitating the Behavior of Human Players in Action Games,” Information Processing Society of Japan, Mar. 5, 2007, 2007(2): 1-8 (abstract only). [cited by applicant]