IP Library › Granted Patent US 12,589,310
Granted Patent B2
US 12,589,310 · App. 18/309,833 · Granted Mar 31, 2026

Systems and methods for artificial intelligence (AI)-assisted communication within video game

Inventors: Glenn Black (San Mateo, CA); Jeffrey Stafford (San Mateo, CA)
Assignee: Sony Interactive Entertainment Inc.
A63F13/67A63F13/87
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 12,589,310
App. No.
18/309,833
Granted
Mar 31, 2026
Kind
B2
Abstract

Input data is received that includes a message for communication to a target player of a video game. A portion of the input data defining the message is automatically identified using a first artificial intelligence model component. A meaning of the message defined by the portion of the input data is automatically determined using a second artificial intelligence model component. A third artificial intelligence model component is used to automatically determine, based on the meaning of the message, whether or not the message is relevant to a current game state and game context of the target player. A communication to the target player that conveys the meaning of the message is automatically composed through use of a fourth artificial intelligence model component, when the message is determined to be relevant to the current game state and game context of the target player. The communication is delivered to the target player.

Claims (52)

1 . A system for artificial intelligence-assisted communication within a video game, comprising:

an input processor configured to receive input data that includes a message for communication to a target player of the video game;

a message identification engine having a first artificial intelligence model component configured and trained to automatically process the input data to identify a portion of the input data defining the message;

a message interpretation engine having a second artificial intelligence model component configured and trained to automatically determine a meaning of the message defined by the portion of the input data as identified by the message identification engine;

a message relevancy assessment engine having a third artificial intelligence model component configured and trained to automatically determine whether or not the message is relevant to a current game state of the target player and a current game context of the target player based on the meaning of the message as determined by the message interpretation engine;

a communication conveyance engine having a fourth artificial intelligence model component configured and trained to automatically compose a communication to the target player that conveys the meaning of the message as determined by the message interpretation engine when the message is determined to be relevant by the message relevancy assessment engine; and

an output processor configured to deliver the communication as composed by the communication conveyance engine to the target player.

2 . The system as recited in claim 1 , wherein the input data includes one or more of a video of a person making a gesture and tracking metadata associated with the person making the gesture, and wherein the message for communication to the target player is provided at least in part by the gesture.

3 . The system as recited in claim 2 , wherein the tracking metadata defines one or more of a pose of the person, a movement of the person, a position of a controller device, an orientation of the controller device, a movement of the controller device, a position of a wearable device worn by the person, an orientation of the wearable device worn by the person, and a movement of the wearable device worn by the person.

4 . The system as recited in claim 2 , wherein the input data includes one or more of an audio clip and a video game controller input, and wherein the message for communication to the target player is provided at least in part by one or more of the audio clip and the video game controller input.

5 . The system as recited in claim 2 , wherein the portion of the input data defining the message is identified as a pixel region within each of a number of video frames of the video of the person making the gesture.

6 . The system as recited in claim 2 , wherein the second artificial intelligence model component is configured and trained to determine the meaning of the message through identification of a body part used to make the gesture and through identification of one or more of a positioning of the body part and a manner of movement of the body part.

7 . The system as recited in claim 2 , wherein the second artificial intelligence model component is configured and trained to determine the meaning of the message before the person finishes making the gesture.

8 . The system as recited in claim 1 , wherein the third artificial intelligence model component is configured and trained to evaluate the meaning of the message to identify a subject of the message and an action associated with the subject of the message, and wherein the third artificial intelligence model component is configured and trained to deem the message relevant when it is determined that the subject of the message is still present within the current game context of the target player and the action associated with the subject of the message is still pertinent to the current game state of the target player.

9 . The system as recited in claim 8 , wherein the third artificial intelligence model component is configured and trained to cancel further processing of the message by the system when it is determined that the subject of the message is no longer present within the current game context of the target player or the action associated with the subject of the message is no longer pertinent to the current game state of the target player.

10 . The system as recited in claim 8 , wherein the third artificial intelligence model component is configured and trained to cancel further processing of the message by the system when it is determined that the action associated with the subject of the message is not beneficial for improving the current game state of the target player.

11 . The system as recited in claim 8 , wherein the third artificial intelligence model component is configured and trained to cancel further processing of the message by the system when it is determined that the subject of the message and the action associated with the subject of the message are redundant with another communication already conveyed to the target player.

12 . The system as recited in claim 1 , wherein the fourth artificial intelligence model component is configured and trained to automatically compose a consolidated communication to the target player that conveys a similar meaning of multiple messages as determined by the message interpretation engine in lieu of automatically composing multiple communications to the target player for the multiple messages.

13 . The system as recited in claim 1 , wherein the fourth artificial intelligence model component is configured and trained to automatically recognize a higher urgency level for conveying the communication to the target player, and wherein the fourth artificial intelligence model component is configured and trained to automatically compose an abbreviated communication to the target player that conveys a shorter version of the message in response to recognizing the higher urgency level for conveying the communication to the target player.

14 . The system as recited in claim 1 , wherein the fourth artificial intelligence model component is configured and trained to automatically determine a format for the communication to the target player, wherein the format is one or more of a textual format, an audible format, a graphical format, and a haptic format.

15 . A method for artificial intelligence-assisted communication within a video game, comprising:

receiving input data that includes a message for communication to a target player of the video game;

automatically identifying a portion of the input data defining the message through execution of a first artificial intelligence model component;

automatically determining a meaning of the message defined by the portion of the input data through execution of a second artificial intelligence model component;

automatically determining based on the meaning of the message whether or not the message is relevant to a current game state and game context of the target player through execution of a third artificial intelligence model component;

automatically composing a communication to the target player that conveys the meaning of the message through execution of a fourth artificial intelligence model component when the message is determined to be relevant to the current game state and game context of the target player; and

delivering the communication to the target player.

16 . The method as recited in claim 15 , wherein the input data includes one or more of a video of a person making a gesture and tracking metadata associated with the person making the gesture, and wherein the message for communication to the target player is provided at least in part by the gesture.

17 . The method as recited in claim 16 , wherein the tracking metadata defines one or more of a pose of the person, a movement of the person, a position of a controller device, an orientation of the controller device, a movement of the controller device, a position of a wearable device worn by the person, an orientation of the wearable device worn by the person, and a movement of the wearable device worn by the person.

18 . The method as recited in claim 16 , wherein the input data includes one or more of an audio clip and a video game controller input, and wherein the message for communication to the target player is provided at least in part by one or more of the audio clip and the video game controller input.

19 . The method as recited in claim 16 , wherein the portion of the input data defining the message is identified as a pixel region within each of a number of video frames of the video of the person making the gesture.

20 . The method as recited in claim 16 , further comprising:

executing the second artificial intelligence component to automatically identify a body part used to make the gesture and to automatically identify one or more of a positioning of the body part and a manner of movement of the body part; and

executing the second artificial intelligence component to analyze the body part, the positioning of the body part, and the manner of movement of the body part to determine the meaning of the message.

21 . The method as recited in claim 16 , further comprising:

executing the second artificial intelligence model component to determine the meaning of the message before the person finishes making the gesture.

22 . The method as recited in claim 15 , further comprising:

executing the third artificial intelligence model component to evaluate the meaning of the message to identify a subject of the message and an action associated with the subject of the message; and

executing the third artificial intelligence model component to deem the message relevant when it is determined that the subject of the message is still present within the current game context of the target player and the action associated with the subject of the message is still pertinent to the current game state of the target player.

23 . The method as recited in claim 22 , further comprising:

executing the third artificial intelligence model component to cancel further processing of the message when it is determined that the subject of the message is no longer present within the current game context of the target player or the action associated with the subject of the message is no longer pertinent to the current game state of the target player.

24 . The method as recited in claim 22 , further comprising:

executing the third artificial intelligence model component to cancel further processing of the message when it is determined that the action associated with the subject of the message is not beneficial for improving the current game state of the target player.

25 . The method as recited in claim 22 , further comprising:

executing the third artificial intelligence model component to cancel further processing of the message when it is determined that the subject of the message and the action associated with the subject of the message are redundant with another communication already conveyed to the target player.

26 . The method as recited in claim 15 , further comprising:

executing the fourth artificial intelligence model component to automatically compose a consolidated communication to the target player that conveys a similar meaning of multiple messages as determined by the second artificial intelligence model component in lieu of automatically composing multiple communications to the target player for the multiple messages.

27 . The method as recited in claim 15 , further comprising:

executing the fourth artificial intelligence model component to automatically recognize a higher urgency level for conveying the communication to the target player; and

executing the fourth artificial intelligence model to automatically compose an abbreviated communication to the target player that conveys a shorter version of the message in response to recognizing the higher urgency level for conveying the communication to the target player.

28 . The method as recited in claim 15 , further comprising:

executing the fourth artificial intelligence model component to automatically determine a format for the communication to the target player, wherein the format is one or more of a textual format, an audible format, a graphical format, and a haptic format.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 1, 2023
From: BLACK, GLENN; STAFFORD, JEFFREY
To: SONY INTERACTIVE ENTERTAINMENT INC.
Reel/Frame 063488/0363 →
Continuity (1)
Related Publication 20240367055A1 · Nov 7, 2024
References Cited (71)
US 7785197B2 · Smith · 2010 [cited by applicant]
US 8523673B1 · Boyd et al. · 2013 [cited by applicant]
US 8751215B2 · Tardif · 2014 [cited by applicant]
US 9684430B1 · Perigault · 2017 [cited by applicant]
US 10179291B2 · Thomas et al. · 2019 [cited by applicant]
US 10607134B1 · Cosic · 2020 [cited by examiner]
US 10915178B2 · Iwanami · 2021 [cited by applicant]
US 10946280B2 · Kunieda · 2021 [cited by applicant]
US 11126266B1 · Xiao et al. · 2021 [cited by applicant]
US 11369884B2 · Niwa et al. · 2022 [cited by applicant]
US 11402917B2 · Yokokawa · 2022 [cited by applicant]
US 12131586B2 · Carlock et al. · 2024 [cited by applicant]
US 20020178011A1 · Yotoriyama et al. · 2002 [cited by applicant]
US 20070191097A1 · Johnson · 2007 [cited by applicant]
US 20090217211A1 · Hildreth et al. · 2009 [cited by applicant]
US 20100112530A1 · Schoenbach · 2010 [cited by applicant]
US 20100199228A1 · Latta et al. · 2010 [cited by applicant]
US 20110059801A1 · Shigi et al. · 2011 [cited by applicant]
US 20110301934A1 · Tardif · 2011 [cited by applicant]
US 20120054646A1 · Hoomani et al. · 2012 [cited by applicant]
US 20130084978A1 · Olomskiy · 2013 [cited by applicant]
US 20140046661A1 · Bruner · 2014 [cited by applicant]
US 20140329208A1 · Jones et al. · 2014 [cited by applicant]
US 20160005336A1 · Peng et al. · 2016 [cited by applicant]
US 20160042228A1 · Opalka et al. · 2016 [cited by applicant]
US 20160059120A1 · Komorous-King et al. · 2016 [cited by applicant]
US 20170173455A1 · Sheil et al. · 2017 [cited by applicant]
US 20180075659A1 · Browy et al. · 2018 [cited by applicant]
US 20180161683A1 · Thomas et al. · 2018 [cited by applicant]
US 20180260577A1 · Adams et al. · 2018 [cited by applicant]
US 20180345128A1 · Ahmed et al. · 2018 [cited by applicant]
US 20190038964A1 · Veeramani et al. · 2019 [cited by applicant]
US 20190171716A1 · Weber · 2019 [cited by applicant]
US 20190251344A1 · Menefee et al. · 2019 [cited by applicant]
US 20190340426A1 · Rangarajan et al. · 2019 [cited by applicant]
US 20190391662A1 · Yokokawa · 2019 [cited by applicant]
US 20200193714A1 · Browy et al. · 2020 [cited by applicant]
US 20200258099A1 · Alghamdi · 2020 [cited by examiner]
US 20200276497A1 · Nietfeld et al. · 2020 [cited by applicant]
US 20200298131A1 · Pinto et al. · 2020 [cited by applicant]
US 20200380793A1 · Browy et al. · 2020 [cited by applicant]
US 20210146255A1 · Taylor et al. · 2021 [cited by applicant]
US 20210390289A1 · Yang et al. · 2021 [cited by applicant]
US 20220096937A1 · Dorn et al. · 2022 [cited by applicant]
US 20220165013A1 · Velez et al. · 2022 [cited by applicant]
US 20220171960A1 · Nelson et al. · 2022 [cited by applicant]
US 20220188538A1 · Vieira et al. · 2022 [cited by applicant]
US 20220327309A1 · Carlock et al. · 2022 [cited by applicant]
US 20220343576A1 · Marey et al. · 2022 [cited by applicant]
US 20220362680A1 · Stafford et al. · 2022 [cited by applicant]
US 20230087879A1 · An et al. · 2023 [cited by applicant]
US 20240335737A1 · Bean et al. · 2024 [cited by applicant]
US 20240335740A1 · Bean et al. · 2024 [cited by applicant]
US 20240367034A1 · Tokubo et al. · 2024 [cited by applicant]
US 20240375011A1 · Black et al. · 2024 [cited by applicant]
CN 106943740A · 2017 [cited by applicant]
CN 113557069A · 2021 [cited by applicant]
EP 3979050A1 · 2022 [cited by applicant]
JP 2011212296A · 2011 [cited by applicant]
JP 2013135761A · 2013 [cited by applicant]
JP 2020031903A · 2020 [cited by applicant]
JP 2020065656A · 2020 [cited by applicant]
JP 2020513960A · 2020 [cited by applicant]
JP 2020177438A · 2020 [cited by applicant]
JP 2022522402A · 2022 [cited by applicant]
KR 102304608B1 · 2021 [cited by applicant]
WO WO2017081896A1 · 2017 [cited by applicant]
WO WO2020176106A1 · 2020 [cited by applicant]
Extended European Search Report in European Appln. No. 24173343.5, mailed on Oct. 17, 2024, 10 pages. [cited by applicant]
Uzma et al., “Advances in machine translation for sign language: approaches, limitations, and challenges, ” Neural Computing, London, May 18, 2021, 33(21):1-43. [cited by applicant]
wikipedia.org [online], “Emote,” Jan. 11, 2023, retrieved on Mar. 19, 2025, retrieved from URL< https://en.wikipedia.Org/w/index.php?title=Emote&oldid=1132929070>, 2 pages. [cited by applicant]