EP-4735138-A1 - SYSTEMS AND METHODS FOR GENERATING NONPLAYER CHARACTERS ACCORDING TO GAMEPLAY CHARACTERISTICS

Abstract

Systems and methods for generating nonplayer characters are described. An artificial intelligence (Al) model is trained based on gameplay by one or more users to generate the nonplayer characters. The nonplayer characters have similar gameplay characteristics as that of a game character controlled by one of the users. The Al model is trained to have a percentage of gameplay characteristics learned from gameplay by the one the users and a percentage of gameplay characteristics from gameplay by another one of the users.

Inventors

• DORN, VICTORIA
• REIFSNIDER, Daniel
• GOJI, Nataliya
• BARTOLOME, ANGELA
• CHIANG, Jessica

Assignees

• Sony Interactive Entertainment LLC
• Sony Interactive Entertainment Inc.

Dates

Publication Date

20260506

Application Date

20240816

Claims (20)

1. 1 . A method for generating a nonplayer character (NPC), comprising: receiving a user input from a first player; determining, based on the user input, that the first player does not wish to play a game for a session with a second player; and in response to determining that the first player does not wish to play the game with the second player, accessing an artificial intelligence (Al) model to generate the nonplayer character to interact with a character controlled by the first player, wherein the nonplayer character has substantially similar' game skills as that of the first player.
2. 2. The method of claim 1, wherein the nonplayer character has a gameplay style that is substantially similar to that of the first player.
3. 3. The method of claim 2, wherein the Al model is trained based on a style of gameplay of the game by the first player.
4. 4. The method of claim 1, wherein the Al model is trained based on gameplay characteristics of a second player.
5. 5. The method of claim 4, wherein the Al model is trained to apply a first predetermined percentage of gameplay characteristics of the first player and a second predetermined percentage of the gameplay characteristics of the second player.
6. 6. The method of claim 1, wherein the user input indicates that a character controlled by the second player is not to be included during the session for the play of the game with the character controlled by the first player.
7. 7. The method of claim 1, further comprising accessing the Al model to generate an additional nonplayer character to interact with the character controlled by the first player, wherein the additional nonplayer character has substantially similar game skills as that of the first player.
8. 8. A server for generating a nonplayer character (NPC), comprising: a processor configured to: receive a user input from a first player; determine, based on the user input, that the first player does not wish to play a game for a session with a second player; and in response to the determination that the first player does not wish to play the game with the second player, access an artificial intelligence (Al) model to generate the nonplayer character to interact with a character controlled by the first player, wherein the nonplayer character has substantially similar game skills as that of the first player; and a memory device coupled to the processor.
9. 9. The server of claim 8, wherein the nonplayer character has a gameplay style that is substantially similar to that of the first player.
10. 10. The server of claim 9, wherein the Al model is trained based on a style of gameplay of the game by the first player.
11. 11. The server of claim 8, wherein the Al model is trained based on gameplay characteristics of a second player.
12. 12. The server of claim 11, wherein the Al model is trained to apply a first predetermined percentage of gameplay characteristics of the first player and a second predetermined percentage of the gameplay characteristics of the second player.
13. 13. The server of claim 8, wherein the user input indicates that a character controlled by the second player is not to be included during the session for the play of the game with the character controlled by the first player.
14. 14. The server of claim 8, wherein the processor is configured to access the Al model to generate an additional nonplayer character to interact with the character controlled by the first player, wherein the additional nonplayer character has substantially similar game skills as that of the first player.
15. 15. A non-transitory computer readable medium containing program instructions for generating a nonplayer character (NPC), wherein execution of the program instructions by one or more processors of a computer system causes the one or more processors to carry out operations of: receiving a user input from a first player; determining, based on the user input, that the first player does not wish to play a game for a session with a second player; and in response to determining that the first player does not wish to play the game with the second player, accessing an artificial intelligence (Al) model to generate the nonplayer character to interact with a character controlled by the first player, wherein the nonplayer character has substantially similar game skills as that of the first player.
16. 16. The non-transitory computer readable medium of claim 15, wherein the nonplayer character has a gameplay style that is substantially similar to that of the first player.
17. 17. The non-transitory computer readable medium of claim 16, wherein the Al model is trained based on a style of gameplay of the game by the first player.
18. 18. The non-transitory computer readable medium of claim 15, wherein the Al model is trained based on gameplay characteristics of a second player.
19. 19. The non-transitory computer readable medium of claim 18, wherein the AT model is trained to apply a first predetermined percentage of gameplay characteristics of the first player and a second predetermined percentage of the gameplay characteristics of the second player.
20. 20. The non-transitory computer readable medium of claim 15, wherein the user input indicates that a character controlled by the second player is not to be included during the session for the play of the game with the character controlled by the first player.

Description

SYSTEMS AND METHODS FOR GENERATING NONPLAYER CHARACTERS ACCORDING TO GAMEPLAY CHARACTERISTICS FIELD [0001] The present disclosure relates to systems and methods for generating nonplayer characters according to gameplay characteristics are described. BACKGROUND [0002] The online gaming industry has seen many changes over the years and has been trying to find ways to enhance video game play experiences for players and increase player engagement with video games and/or online gaming systems. When a player increases his/her engagement with a video game, the player is more likely to continue playing the video game and play the video game more frequently. [0003] A growing trend in the video game industry is online harassment and cyber bullying in video games by players commonly referred to as abusive players, bad faith players, griefers and/or disruptive players. For example, a disruptive player can be a player in a multiplayer video game who deliberately irritates, annoys, and harasses other players of the video game. In some instances, the disruptive player will use aspects of the video game in unintended ways to disrupt normal play of the video game. The disruptive actions by disruptive players in the video game can prevent other good faith players from becoming fully immersed in their play of the video game, and thereby diminish the good faith player's game play experience. Unfortunately, identifying disruptive players and monitoring their actions during their play of the video game can be difficult and can utilize a significant amount of resources, including computing resources, human resources, energy resources, economic resources, data storage resources, and data communication bandwidth resources, among other types of resources. Therefore, management of disruptive players in the video games is not currently done as well as possible. [0004] It is in this context that embodiments of the invention arise. SUMMARY [0005] Embodiments of the present disclosure provide systems and methods for generating nonplayer characters according to gameplay characteristics. [0006] In an embodiment, a method for matching a user, such as a gamer or a player, with artificial intelligence (Al) friends, is described. If the player wants to play a squad-based game, e.g., a co-op game, or a multiplayer game, the player finds other players to play with. If available players have skills of a low level or have negative behavior, such as rudeness or anger or other disruptive behavior, the player is discouraged from playing the squad-based game. [0007] In one embodiment, a method provides an AT model that learns player characteristics by using game data, history, scores, and style of play of the player. The player characteristics are sometimes referred to herein as game characteristics. The Al model determines a type of the player based on the player characteristics to generate data for displaying a non-player character (NPC). The NPC is created to play with the player. The NPC player is an Al player or an Al friend that will behave similar to the style of the play of the player and is compatible with the squad-based game. [0008] In one embodiment, if the player logs in and there are no other players, such as real people, to play the squad-based game with, the system can generate one or more custom Al players, such as NPCs. Each custom Al player is a little different, and have slightly different tendencies, but still be compatible with the player. This allows for playing a game with multiple Al players, and provide good enjoyment to the player, regardless if there are actual real people available to play or when the player does not wish to play with other players with disruptive behavior. [0009] In an embodiment, an Al player is modeled on one of gaming network friends of the player, and the Al player has the tenancies and skills of the gaming network friend. [0010] In one embodiment, an Al player modeled after the player can be made available to other players, such as the gaming network friends, in case the player is not available to play. [0011] Some advantages of the herein described systems and methods include using the Al model to generate data for displaying one or more NPCs. The NPCs play the squad-based game based on the game characteristics of the player. By providing the NPCs that adapt over time to the game characteristics of the player, the player continues to be interested in the squad-based game. Also, the NPCs are generated to protect the player from other players who behave in a negative manner against the player. Also, additional advantages of the herein described systems and methods include using the Al model to generate one or more NPCs that play the squad-based game according to game characteristics of different players. For example, an NPC plays the squadbased game for some time period based on the game characteristics of the player and for another time period based on the game characteristics of the gaming network