Player model
A player model for a video game is generated based on inputs received from users who have played past versions of the game. The player model can be used to simulate user actions in a new version of the video game and make predictions about average user session length, average earnings per session, number of games played per day, etc. More than one player model may be generated for a game. Each player model for a game may represent one or more features, such as a user skill level, for a group of users.
1. A computer-implemented method, comprising:
obtaining, by a processor, a plurality of input signals from a plurality of devices of a plurality of users of an application;
obtaining, by the processor, a first plurality of draw signals for the application;
determining, by the processor, correlations between at least a portion of the first plurality of draw signals for the application, and at least a portion of the input signals from the plurality of devices of the plurality of users of the application; and
generating, by the processor, at least one computer-implemented player model based on the correlations, the at least one computer-implemented player model configured to produce performance indicators, from a plurality of simulations of operations of a first version of the application, to be used to develop a second version of the application.
2. The method of claim 1 , wherein the plurality of input signals from the plurality of devices of the plurality of users of the application is selected from the group consisting of: a signal produced from a touch input, a signal produced from a voice input, a signal produced from a keystroke, a signal produced from an analog joystick input, and a signal produced from a wireless device input.
3. The method of claim 1 , further comprising clustering, by the processor, the correlations, wherein the generating is based on a plurality of clusters.
4. The method of claim 1 , further comprising:
receiving, by the processor, a second plurality of draw signals for a third version of the application; and
performing, by the processor, the plurality of simulations of the third version of the application using the at least one computer-implemented player model.
5. The method of claim 4 , further comprising:
comparing, by the processor, the first plurality of draw signals for the application to the second plurality of draw signals for the application;
determining, by the processor, draw signals from the first plurality of draw signals that resemble draw signals from the second plurality of draw signals;
estimating, by the processor, a response of the at least one computer-implemented player model to draw signals from the first plurality of draw signals that do not resemble draw signals from the second plurality of draw signals; and
modifying, by the processor, the at least one computer-implemented player model based on a result of the determining the draw signals from the first plurality of draw signals that resemble the draw signals from the second plurality of draw signal and a result of the estimating the response of the at least one computer-implemented player model to the draw signals from the first plurality of draw signals that do not resemble the draw signals from the second plurality of draw signals.
6. The method of claim 4 , further comprising providing, by the processor, a performance indicator for the third version of the application based on the plurality of simulations of the third version of the application.
7. The method of claim 6 , wherein the performance indicator is selected from the group consisting of: a number of games played per day, an average session length, a profitability indication, an error indication, and a social indication.
8. The method of claim 4 , further comprising providing, by the processor, at least one image from at least one of the plurality of simulations of the third version of the application.
9. The method of claim 1 , wherein the generating the at least one computer-implemented player model is performed using a machine learning technique.
10. The method of claim 1 , wherein the application is a video game application.
11. A system, comprising:
a database configured to store a plurality of input signals;
a processor connected to the database and configured to:
obtain the plurality of input signals from a plurality of devices of a plurality of users of an application;
obtain a first plurality of draw signals for the application;
determine correlations between at least a portion of the first plurality of draw signals for the application, and at least a portion of the input signals from the plurality of devices of the plurality of users of the application; and
generate at least one computer-implemented player model based on the correlations, the at least one computer-implemented player model configured to produce performance indicators, from a plurality of simulations of operations of a first version of the application, to be used to develop a second version of the application.
12. The system of claim 11 , wherein the plurality of input signals from the plurality of devices of the plurality of users of the application is selected from the group consisting of: a signal produced from a touch input, a signal produced from a voice input, a signal produced from a keystroke, a signal produced from an analog joystick input, and a signal produced from a wireless device input.
13. The system of claim 11 , the processor further configured to cluster the correlations, wherein the processor is configured to generate the at least one computer-implemented player model based on a plurality of clusters.
14. The system of claim 11 , the processor further configured to:
receive a second plurality of draw signals for a third version of the application; and
perform a plurality of simulations of the third version of the application using the at least one computer-implemented player model.
15. The system of claim 14 , the processor further configured to:
compare the first plurality of draw signals for the application to the second plurality of draw signals for the application;
determine draw signals from the first plurality of draw signals that resemble draw signals from the second plurality of draw signals;
estimate a response of the at least one computer-implemented player model to draw signals from the first plurality of draw signals that do not resemble draw signals from the second plurality of draw signals; and
modify the at least one computer-implemented player model based on a result of a determination of the draw signals from the first plurality of draw signals that resemble the draw signals from the second plurality of draw signals and a result of an estimation of the response of the at least one computer-implemented player model to the draw signals from the first plurality of draw signals that do not resemble the draw signals from the second plurality of draw signals.
16. The system of claim 14 , the processor further configured to provide a performance indicator for the third version of the application based on the plurality of simulations of the third version of the application.
17. The system of claim 16 , wherein the performance indicator is selected from the group consisting of: a number of games played per day, an average session length, a profitability indication, an error indication, and a social indication.
18. The system of claim 14 , the processor further configured to provide at least one image from at least one of the plurality of simulations of the third version of the application.
19. The system of claim 11 , wherein the processor is configured to generate the at least one computer-implemented player model by using a machine learning technique.
20. The system of claim 11 , wherein the application is a video game application.