# US 2023/0054035 A1 · Personalized Data Driven Game Training System > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0054035 A1 - Document ID: US20230054035A1 - Status: Published application - Kind: A1 - Application number: 17/892,991 - Filed: 2022-08-22 - Published: 2023-02-23 - Earliest claimed: 2016-03-30 - Assignees: Sony Interactive Entertainment Inc. - Applicants: Sony Interactive Entertainment Inc. - Inventors: Sudha Krishnamurthy - Web page: https://patentgrep.com/patent/US20230054035A1 ## CPC - A63F 13/5375: for graphically or textually suggesting an action, e.g. by displaying an arrow indicating a turn in a driving game - 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 13/69: by enabling or updating specific game elements, e.g. unlocking hidden features, items, levels or versions - A63F 13/79: involving player-related data, e.g. identities, accounts, preferences or play histories - A63F 13/422: automatically for the purpose of assisting the player, e.g. automatic braking in a driving game - A63F: CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR ## Abstract 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. ## Claims ### Claim 1 A method implemented on a computer system, the method comprising: inputting, to an artificial intelligence (AI) model, data about an experience level of a user in playing a video game, wherein the AI model is trained based on user interactions with one or more video game contexts at different experience levels; receiving, from the AI model based on the data, an output indicating a parameter that controls an interaction of a virtual player in the video game; and causing a presentation of the interaction of the virtual player in the video game according to the parameter. ### Claim 2 (depends on 1) The method of claim 1, wherein the virtual player is a first virtual player that interacts with a second virtual player corresponding to the user, wherein the interaction is between the first virtual player and the second virtual player. ### Claim 3 (depends on 1) The method of claim 1, wherein the AI model comprises a neural network having an input layer and an output layer, wherein the input layer is mapped to feature vectors of the user, and wherein the output layer is mapped to the interaction. ### Claim 4 (depends on 3) The method of claim 3, wherein the output layer is mapped to potential parameters that control the interaction of the virtual player, and wherein the virtual player performs the interaction based on a subset of the potential parameters. ### Claim 5 (depends on 1) The method of claim 1, wherein the AI model is trained using a training data set that includes game session data of video game players at the different experience levels and across one or more video games. ### Claim 6 (depends on 5) The method of claim 5, wherein the game session data includes video frames and actions that correspond to the user interactions. ### Claim 7 (depends on 6) The method of claim 6, wherein the AI model is further trained to predict the experience level of the user based on a user interaction with a context in the video game. ### Claim 8 (depends on 6) The method of claim 6, wherein the AI model is trained for a genre of the video game, and wherein the user interactions are with different contexts in different video games of the genre. ### Claim 9 (depends on 1) The method of claim 1, wherein the AI model is trained using a training data set that includes a feature vector representing one or more interactions, one or more experience levels, one or more contexts, and one or more actions in the video game. ### Claim 10 A system comprising: one or more processors; and one or more memories storing computer-readable instructions that, upon execution by the one or more processors, configure the system to: generate an input to an artificial intelligence (AI) model, wherein the input includes data about an experience level of a user in playing a video game, wherein the AI model is trained based on user interactions with one or more video game contexts at different experience levels; determine an output of the AI model based on the input, wherein the output indicates a parameter that controls an interaction of a virtual player in the video game; and cause a presentation of the interaction of the virtual player in the video game according to the parameter. ### Claim 11 (depends on 10) The system of claim 10, wherein the virtual player is presented as an interactive graphical user interface (GUI) object, and wherein the output of the AI model sets the parameter that controls the interaction of the GUI object. ### Claim 12 (depends on 10) The system of claim 10, wherein the AI model, the input, and the output are a first AI model, a first input, and a first output, respectively, and wherein the one or more memories store additional computer-readable instructions that, upon execution by the one or more processors, configure the system to: generate a second input to a second AI model; and determine a second output of the second AI model based on the second input, wherein the second output controls a presentation of a context in the video game. ### Claim 13 (depends on 12) The system of claim 12, wherein the second input includes the experience level, the interaction, and the context, and wherein the second AI model selects the context from multiple contexts by predicting that the context has a higher likelihood of interacting with the context than remaining contexts of the multiple contexts. ### Claim 14 (depends on 12) The system of claim 12, wherein the one or more memories store further computer-readable instructions that, upon execution by the one or more processors, configure the system to: detect a user interaction with the context; and include the user interaction in the first input to the first AI model, wherein the first output of the first AI mode is further based on the user interaction. ### Claim 15 (depends on 10) The system of claim 10, wherein the parameter is a first parameter, and wherein the one or more memories store additional computer-readable instructions that, upon execution by the one or more processors, configure the system to: determine, based on the output of the AI model, a second parameter of the virtual player, wherein the second parameter is used to control how the virtual player plays the video game and corresponds to an experience level that is the same or higher than that of the user. ### Claim 16 (depends on 10) The system of claim 10, wherein the interaction corresponds to an action of the virtual player from potential actions in the video game, and wherein the AI model selects the action based on the action having higher likelihood of success than remaining actions of the potential actions. ### Claim 17 One or more non-transitory computer-readable storage media storing computer-readable instructions that, upon execution on a system, cause the system to perform operations comprising: generating an input to an artificial intelligence (AI) model, wherein the input includes data about an experience level of a user in playing a video game, wherein the AI model is trained based on user interactions with one or more video game contexts at different experience levels; determining an output of the AI model based on the input, wherein the output indicates a parameter that controls an interaction of a virtual player in the video game; and causing a presentation of the interaction of the virtual player in the video game according to the parameter. ### Claim 18 (depends on 17) The one or more non-transitory computer-readable storage media of claim 17, wherein the virtual player is a first virtual player that interacts with a second virtual player corresponding to the user, wherein the interaction is between the first virtual player and the second virtual player. ### Claim 19 (depends on 17) The one or more non-transitory computer-readable storage media of claim 17, wherein the AI model comprises a neural network having an input layer and an output layer, wherein the input layer is mapped to feature vectors of the user, and wherein the output layer is mapped to the interaction. ### Claim 20 (depends on 17) The one or more non-transitory computer-readable storage media of claim 17, wherein the AI model is trained using a training data set that includes game session data of video game players at the different experience levels and across one or more video games.