Automated assessment of custom game levels

Patent metadata

Field	Value
Publication number	US-12083436-B2
Application number	US-202016948503-A
Country	US
Kind code	B2
Filing date	Sep 21, 2020
Priority date	Sep 21, 2020
Publication date	Sep 10, 2024
Grant date	Sep 10, 2024

Abstract

A game server accesses player model representing subset of players. Player model is generated based on previous in-game behavior of the subset of players while playing a computer-implemented game. The game server accesses a set of interactive content items associated with the game. The game server forecasts, using the player model, a sequence of user actions of the subset of players during gameplay of the game. The sequence of user actions represents a prediction of user interaction with the set of interactive content items. The game server computes, based on the forecasted sequence of user actions and software-defined outcomes of the forecasted sequence of user actions in the game, configuration values for the set of interactive content items. The game server causes execution of gameplay at a client device associated with the player model. The gameplay is according to the computed configuration values for the set of interactive content items.

First claim

What is claimed is:

1. A method implemented at a game server, the method comprising:
accessing a player model representing a subset of players, the player model being generated based on previous in-game behavior of the subset of players while playing a computer-implemented game, wherein the player model is a multi-dimensional model comprising multiple parametric values respectively representing player behavior in each of a corresponding set of gameplay attributes;
accessing a game level for the game, the game level being a gameplay unit playable according to a predefined associated set of rules including a set of interactive content items encountered by a player character during play of the game level consistent with the set of rules;
using a simulator comprising one or more computer hardware devices configured therefor, performing an automated gameplay simulation for the game level consistent with the player model, the gameplay simulation comprising forecasting, using the player model, a sequence of gameplay actions which together represent a play-through of the game level when played consistent with the player model, wherein the forecasting of the sequence of gameplay actions comprises, via the simulator, performing operations sequentially comprising:
automatically presenting an initial game condition based on the set of content items and the set of rules, to prompt a gameplay action;
automatically calculating the gameplay action based on the respective parametric values from the player model for one or more of the gameplay attributes associated with the respective gameplay action;
automatically performing the gameplay action;
thereafter automatically presenting a resultant game condition based on the set of rules and the set of interactive content items;
automatically calculating a subsequent gameplay action based on the respective parametric values from the player model for one or more of the gameplay attributes associated with the subsequent gameplay action;
automatically performing the subsequent gameplay action; and
iteratively repeating the operations of presenting a resultant game condition, calculating a subsequent gameplay action, and performing the subsequent gameplay action to completion of the game level;

in an automated operation performed by one or more computer processor devices configured therefor, computing, based on the gameplay simulation and on software-defined outcomes of the forecasted sequence of gameplay actions in the game, configuration values for the set of interactive content items, thereby producing a custom game level; and
provisioning the custom game level for execution of gameplay at a client device associated with the player model.

2. The method of claim 1 , wherein forecasting, using the player model, the sequence of gameplay actions leverages a statistical engine.

3. The method of claim 2 , wherein the statistical engine comprises a utility response curve or at least one artificial neural network.

4. The method of claim 1 , further comprising:
optimizing the configuration values based on at least one metric.

5. The method of claim 4 , wherein the at least one metric comprises one or more of: a target win rate, a repeat gameplay metric, a gameplay duration, a game engagement metric, and a revenue metric.

6. The method of claim 1 , wherein each player of the subset of players represented by the player model corresponds to a data point in a multiple dimensional space, and wherein the player model corresponds to a data point at a centroid of the subset of players in the multiple dimensional space.

7. The method of claim 1 , wherein the set of interactive content items prompts the sequence of gameplay actions as per non-simulated playthrough of the game level.

8. A non-transitory machine-readable medium storing instructions which, when executed by a game server, cause the game server to perform operations comprising:
accessing a player model representing a subset of players, the player model being generated based on previous in-game behavior of the subset of players while playing a computer-implemented game, wherein the player model is a multi-dimensional model comprising multiple parametric values respectively representing player behavior in each of a corresponding set of gameplay attributes;
accessing a game level for the game, the game level being a gameplay unit playable according to a predefined associated set of rules including a set of interactive content items encountered by a player character during play of the game level consistent with the set of rules;
performing an automated gameplay simulation for the game level consistent with the player model, the gameplay simulation comprising forecasting, using the player model, a sequence of gameplay actions which together represent a play-through of the game level when played consistent with the player model, wherein the forecasting of the sequence of gameplay actions comprises performing operations sequentially comprising:
automatically presenting an initial game condition based on the set of content items and the set of rules, to prompt a gameplay action;
automatically calculating the gameplay action based on the respective parametric values from the player model for one or more of the gameplay attributes associated with the respective gameplay action;
automatically performing the gameplay action;
thereafter automatically presenting a resultant game condition based on the set of rules and the set of interactive content items;
automatically calculating a subsequent gameplay action based on the respective parametric values from the player model for one or more of the gameplay attributes associated with the subsequent gameplay action;
automatically performing the subsequent gameplay action; and
iteratively repeating the operations of presenting a resultant game condition, calculating a subsequent gameplay action, and performing the subsequent gameplay action to completion of the game level;

computing, based on the gameplay simulation and on software-defined outcomes of the forecasted sequence of gameplay actions in the game, configuration values for the set of interactive content items, thereby producing a custom game level; and
provisioning the custom game level for execution of gameplay at a client device associated with the player model.

9. The machine-readable medium of claim 8 , wherein forecasting, using the player model, the sequence of gameplay actions leverages a statistical engine.

10. The machine-readable medium of claim 9 , wherein the statistical engine comprises a utility response curve or at least one artificial neural network.

11. The machine-readable medium of claim 8 , further comprising:
optimizing the configuration values based on at least one metric.

12. The machine-readable medium of claim 11 , wherein the at least one metric comprises one or more of: a target win rate, a repeat gameplay metric, a gameplay duration, a game engagement metric, and a revenue metric.

13. The machine-readable medium of claim 8 , wherein each player of the subset of players represented by the player model corresponds to a data point in a multiple dimensional space, and wherein the player model corresponds to a data point at a centroid of the subset of players in the multiple dimensional space.

14. The machine-readable medium of claim 8 , wherein the set of interactive content items prompts the sequence of gameplay actions as per non-simulated playthrough of the game level.

15. A game server comprising:
processing circuitry; and
a memory storing instructions which, when executed by the processing circuitry,

Assignees

• Zynga Inc

Inventors

• Dicken Luke
• Pagnutti Johnathan
• Wen Yang

Classifications

• A63F13/53

  involving additional visual information provided to the game scene, e.g. by overlay to simulate a head-up display [HUD] or displaying a laser sight in a shooting game · CPC title

• A63F13/30

  Interconnection arrangements between game servers and game devices; Interconnection arrangements between game devices; Interconnection arrangements between game servers · CPC title

• A63F13/58

  by computing conditions of game characters, e.g. stamina, strength, motivation or energy level · CPC title

• A63F13/35

  Details of game servers · CPC title

• A63F13/77

  involving data related to game devices or game servers, e.g. configuration data, software version or amount of memory · CPC title