Personalized data driven game training system
A video game console, a video game system, and a computer-implemented method are described. Generally, a video game and video game assistance are adapted to a player. For example, a narrative of the video game is personalized to an experience level of the player. Similarly, assistance in interacting with a particular context of the video game is also personalized. The personalization learns from historical interactions of players with the video game and, optionally, other video games. In an example, a deep learning neural network is implemented to generate knowledge from the historical interactions. The personalization is set according to the knowledge.
1. A computer-implemented method comprising:
determining, by a computer system, an experience level of a video game player in playing a video game;
generating, by the computer system based on an artificial intelligence (AI) model, a context of the video game from potential contexts, the context generated by the AI model based on predicted outcomes of presenting the potential contexts in the video game given the experience level of the video game player, each one of the predicted outcomes corresponding to a potential context and comprising a likelihood of interest of the video game player in the potential context, the context selected from the potential contexts based on the likelihood predicted for the context, the AI model trained based on historical interactions of video game players with the video game; and
causing, by the computer system, a presentation of the context in the video game such that the video game is adapted to the experience level of the video game player.
2. The computer-implemented method of claim 1 , wherein causing the presentation of the context comprises changing a narrative of the video game based on the context.
3. The computer-implemented method of claim 1 , wherein the AI model comprises a neural network, wherein an input layer of the neural network is mapped to feature vectors of the video game players, wherein the feature vectors comprise the historical interactions, and wherein an output layer of the neural network is mapped to the potential contexts.
4. The computer-implemented method of claim 3 , further comprising:
detecting, by the computer system, an interaction of the video game player with the context of the video game; and
generating, by the computer system, a next context based on inputting information about the interaction and the context to the neural network.
5. The computer-implemented method of claim 3 , wherein the experience level of the video game player is estimated as an output from the neural network, and further comprising:
tracking, by the computing system, an interaction history of the video game player with the video game during a game session; and
inputting, by the computing system, the interaction history of the video game player to the neural network.
6. The computer-implemented method of claim 1 , wherein the historical interactions of video game players used to train the AI model correspond to video game players that have different experience levels.
7. A computer system comprising:
a processor; and
a memory storing computer-readable instructions that, upon execution by the processor, configure the computer system to:
determine an experience level of a video game player in playing a video game;
generate, based on an artificial intelligence (AI) model, a context of the video game from potential contexts, the context generated by the AI model based on predicted outcomes of presenting the potential contexts in the video game given the experience level of the video game player, each one of the predicted outcomes corresponding to a potential context and comprising a likelihood of interest of the video game player in the potential context, the context selected from the potential contexts based on the likelihood predicted for the context, the AI model trained based on historical interactions of video game players with the video game; and
cause a presentation of the context in the video game such that the video game is adapted to the experience level of the video game player.
8. The computer system of claim 7 , wherein an input to the AI model comprises the experience level of the video game player and game session data of the video game.
9. The computer system of claim 8 , wherein the game session data comprises an interaction of the video game player with the context, and wherein an output of the AI model comprises a change to the context.
10. The computer system of claim 8 , wherein the game session data comprises an interaction of the video game player with a second context, and wherein an output of the AI model comprises the context.
11. The computer system of claim 7 , wherein the AI model is trained based on the historical interactions to output a parameter that defines an interactivity of the context and a value of the parameter, wherein the parameter and the value are an output of the AI model based on an input to the AI model comprising the experience level of the video game player and an interaction of the video game player with one or more contexts in the video game.
12. The computer system of claim 11 , wherein the AI model is trained based on the historical interactions to further output a second parameter that defines a presentation of the context in the video game and a second value of the second parameter.
13. The computer system of claim 7 , wherein the AI model is trained based on the historical interactions to output parameters of the context, wherein the parameters comprise timing, presentation format, type, and interactivity level of the context, and wherein the parameters are an output of the AI model based on an input to the AI model comprising the experience level and game session data of the video game player.
14. The computer system of claim 7 , wherein the AI model learns, based on the historical interactions of the video game players, interactions with contexts, outcomes of the interactions, and parameters of the contexts given the different experience levels.
15. The computer system of claim 14 , wherein the historical interaction correspond to interactions of the video game players with contexts presented in different video games that are of a same video game genre.
16. A video game console comprising:
a processor; and
a memory storing computer-readable instructions that, upon execution by the processor, configure the video game console to:
present, in a video game, a virtual player for a video game player, the video game player associated with an experience level in playing the video game;
access a context of the video game based on an artificial intelligence (AI) model, the context generated by the AI model based on predicted outcomes of presenting potential contexts in the video game given the experience level of the video game player, each one of the predicted outcomes corresponding to a potential context and comprising a likelihood of interest of the video game player in the potential context, the context selected from the potential contexts based on the likelihood predicted for the context, the AI model trained based on historical interactions of video game players with the video game; and
present the context in the video game such that the video game is adapted to the experience level of the video game player.
17. The video game console of claim 16 , wherein the AI model is trained to select the context from the potential contexts based on the predicted outcomes, wherein the potential contexts and the predicted outcomes are learned by the AI model based on the historical interaction data.
18. The video game console of claim 17 , wherein the context is selected based on a predicted outcome of the context indicating that the AI model predicts a higher likelihood of interest of the video game player in the context relative to another context from the potential contexts.
19. The video game console of claim 16 , wherein the AI model comprises a neural network, and wherein an output layer of the neural network is mapped to the potential contexts.
20. The video game console of claim 19 , wherein an input to the neural network comprises a feature vector associated with the experience level and game session data of the video game player.