# US 2022/0032199 A1 · Classifying gaming activity to identify abusive behavior

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0032199 A1
- Document ID: US20220032199A1
- Status: Published application
- Kind: A1
- Application number: 16/945,568
- Filed: 2020-07-31
- Published: 2022-02-03
- Earliest claimed: 2020-07-31
- Assignees: Sony Interactive Entertainment Inc.
- Applicants: Sony Interactive Entertainment LLC
- Inventors: Olga Rudi; Lucie Roberts; Rebecca MacDonald
- Web page: https://patentgrep.com/patent/US20220032199A1

## CPC

- A63F 13/67: adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use
- A63F 13/75: Enforcing rules, e.g. detecting foul play or generating lists of cheating players
- A63F 13/35: Details of game servers
- A63F 13/533: for prompting the player, e.g. by displaying a game menu
- A63F 13/79: involving player-related data, e.g. identities, accounts, preferences or play histories
- A63F 13/86: Watching games played by other players
- G06F 18/24: Classification techniques
- G06N 20/00: Machine learning
- A63F: CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method of controlling online gaming behavior. The method including monitoring at a game server a plurality of game plays of a plurality of players playing a video game in a gaming session over a period of time. The method including extracting features from the plurality of game plays related to a plurality of activities associated with the plurality of game plays, the plurality of activities being controlled by the plurality of players. The method including running the features through an artificial intelligence (AI) learning model configured to classify the plurality of activities. The method including classifying an activity as abusive behavior.

## Claims

### Claim 1

A method of controlling online gaming behavior, comprising:
monitoring at a game server a plurality of game plays of a plurality of players playing a video game in a gaming session over a period of time;
extracting features from the plurality of game plays related to a plurality of activities associated with the plurality of game plays, the plurality of activities being controlled by the plurality of players;
running the features through an artificial intelligence (AI) learning model configured to classify the plurality of activities; and
classifying an activity as abusive behavior.

### Claim 2 (depends on 1)

The method of claim 1,
wherein the abusive behavior is performed to negatively impact the gaming experience of at least one other player.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
determining that the activity results in a player leaving the gaming session.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
determining a first player that is controlling the abusive behavior;
determining a second player that is a target of the abusive behavior;
sending a notification to a device of the second player that the abusive behavior has been identified.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
receiving confirmation from the device of the second player indicating that the abusive behavior is abusive; and
receiving confirmation from the second player that the abusive behavior was directed to the second player.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
identifying features associated with the abusive behavior;
inputting the features associated with the abusive behavior to the AI learning model for purposes of training the AI learning model; and
marking each the features associated with the abusive behavior as being true indicators of a class indicating the abusive behavior.

### Claim 7 (depends on 4)

The method of claim 4, further comprising:
receiving selection of the selectable icon in the notification, wherein the selectable icon that when selected by the second player makes a request for performing remedial action; and
performing the remedial action,
wherein the remedial action includes:
sending a warning to the first player; or
masking the second player from the first player; or
masking the first player and the second player from each other.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
determining a player that is controlling the abusive behavior; and
sending a warning to a device of the player indicating that if the abusive behavior continues further remedial action will be taken against the player.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
generating a video recording of the abusive behavior; and
sending the video recording to the device of the player.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
receiving initiation of a flag from a flagging player indicating possible undesirable activity, wherein the period of time is associated with a point in time when the flag was initiated;
determining a player that is controlling the abusive behavior;
generating a video recording of the abusive behavior;
presenting the video recording to a group of players; and
receiving a determination from the group of players indicating whether the abusive behavior is abusive or not abusive.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
receiving selection of a selectable icon that when selected by the flagging player makes a request for verification of the abusive behavior through crowd sourcing by the group of players,
wherein the group of players includes the flagging player.

### Claim 12 (depends on 10)

The method of claim 10, wherein the determination from the group of players indicates that the abusive behavior is abusive, the method further comprising:
identifying features associated with the abusive behavior; and
inputting the features associated with the abusive behavior to the AI learning model for purposes of training the AI learning model; and
marking each the features associated with the abusive behavior as being true indicators of a class indicating the abusive behavior.

### Claim 13 (depends on 1)

The method of claim 1, wherein the monitoring of the plurality of game plays includes:
receiving telemetry data associated with the plurality of game plays,
wherein the telemetry data includes at least one of:
user saved data of a corresponding game play of a player; or
game state data of the corresponding game play; or
metadata of the corresponding game play.

### Claim 14 (depends on 1)

The method of claim 1, further comprising:
classifying another activity as being desirable behavior.

### Claim 15 (depends on 14)

The method of claim 14, further comprising:
determining a first player that is controlling the desirable behavior;
sending a notification to a second player in a group pf players that includes the first player and the second player,
wherein the notification includes a video recording of the desirable behavior including the another activity;
wherein the notification includes a selectable icon that when selected by the second player provides an accolade to the first player,
wherein an accumulation of accolades by a corresponding player defines a reputation of the corresponding player within an online community.

### Claim 16

A non-transitory computer-readable medium storing a computer program for implementing a method of controlling online gaming behavior, the computer-readable medium comprising:
program instructions for monitoring at a game server a plurality of game plays of a plurality of players playing a video game in a gaming session over a period of time;
program instructions for extracting features from the plurality of game plays related to a plurality of activities associated with the plurality of game plays, the plurality of activities being controlled by the plurality of players;
program instructions for running the features through an artificial intelligence (AI) learning model configured to classify the plurality of activities; and
program instructions for classifying an activity as abusive behavior.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium of claim 16,
wherein in the method the abusive behavior is performed to negatively impact the gaming experience of at least one other player.

### Claim 18 (depends on 16)

The non-transitory computer-readable medium of claim 16, further comprising:
program instructions for determining that the activity results in a player leaving the gaming session.

### Claim 19

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 of controlling online gaming behavior comprising:
monitoring at a game server a plurality of game plays of a plurality of players playing a video game in a gaming session over a period of time;
extracting features from the plurality of game plays related to a plurality of activities associated with the plurality of game plays, the plurality of activities being controlled by the plurality of players;
running the features through an artificial intelligence (AI) learning model configured to classify the plurality of activities; and
classifying an activity as abusive behavior.

### Claim 20 (depends on 19)

The computer system of claim 19, wherein the method further comprises:
determining that the activity results in a player leaving the gaming session,
wherein the abusive behavior is performed to negatively impact the gaming experience of at least one other player.
