Abstract: Methods and systems for personalizing an avatar for a user for use in a game includes extracting features of the avatar associated with the user. Receiving inputs from the user for customizing at least a feature of the game that is identified as customizable. Constraints of the game are determined and used during updating of a skin of the avatar, wherein the skin of the avatar is updated by adjusting the feature to include the attribute customized using the inputs of the user. The updated skin used to generate an updated avatar that is stored in a user profile of the user and used to represent the user in the game.

Abstract: Systems and methods for dynamic content display generation for multiple device setups are provided. Supplemental content files associated with an interactive content title may be stored in memory in association with parameters specific to different types of user devices. A current interactive session associated with a first device may be monitored and determined to include a virtual environment presentation associated with the interactive content title. A type of a secondary device associated with the user may be identified. A supplemental content package may be generated for the secondary device based on a selected set of supplemental content and a set of the parameters associated with the type of the secondary device. The supplemental content package may be provided to the secondary device during the current interactive session, and the secondary device may generate a presentation of the selected set of supplemental content files in accordance with the set of parameters.

Abstract: System, process and device configurations are provided for detecting user socialization preferences and controlling multiplayer selection. A method can include receiving user voice output during gameplay for a first user, and determining a socialization preference for the first user based on the user voice output. The method may also include updating a user profile for the first user based on the socialization preference, selecting at least one second user, and controlling a gameplay session for the first user and the at least one second user, wherein audio output for the first user is controlled using a the user profile. Socialization preferences detected during gameplay may be used to select other users for multiplayer game sessions. The socialization preferences may also be used to control audio output by way of selection/terminating players from a session, filtering audio output to a user, filtering intensity and/or modifying audio output to a user.

Abstract: A method is provided, including the following operations: receiving video of a first user; processing the video to identify signed communications in a first sign language made by the first user; translating the signed communications in the first sign language into signed communications in a second sign language; rendering an avatar of the user performing the translated signed communications in the second sign language; presenting the avatar on a display for viewing by a second user.

Abstract: A method is provided for facilitating communication between players in a video game, including the following operations: receiving video of a first player during gameplay of the video game; analyzing the video to identify gestures made by the first player; responsive to identifying the gestures, then translating the gestures into a text communication, wherein translating the gestures uses a context of the video game to determine content of the text communication; presenting the text communication through an in-game chat of the video game, for viewing by a second player during the gameplay of the video game.

Abstract: System, process and device configurations are provided for analyzing video data, such as electronic game data, and generating scoring data for video data. Processes and device configurations include training a video data analysis model to generate scoring parameters, and for an evaluation tool for video data. Highly viewed and popular videos may be used as training input to the video analysis model. At least one score parameter may be determined for scoring videos. For electronic games, at least one score may be associated with a game scene, gameplay storylines, and for scoring video data in general. Analysis of game titles and game design may be performed during design to ensure that game scenes will have a high likelihood of user interest. Embodiments may also include modifying gameplay and gameplay storylines, and evaluating game promotional videos.

Abstract: Alerts can be generated to inform a prime user to unblock another user, whose audio and/or video the prime user has blocked, owing to an emerging context that may be of interest to the prime user. The prime user can be informed of such a context and provided the ability to selectively view the blocked user's comments so the full context can be understood. This aims to help protect the prime user who may have been the subject of harassment from the blocked user originally causing the blocked user to be muted or otherwise blocked in the first place.

Abstract: A parallelepiped-shaped body has a flat top surface on which a user draws computer simulation controller buttons with a layout and spacing best fitting the user's physical needs. The user connects wires in the body to random GPIOs and maps the drawn buttons to desired game controller functions using an off-the-shelf controller connected to an MCU by pressing drawn buttons on the body along with corresponding buttons on the off-the-shelf controller, establishing which drawn button has which game controller function.

Abstract: Alerts can be generated to inform a prime user to unblock another user, whose audio and/or video the prime user has blocked, owing to an emerging context that may be of interest to the prime user. The prime user can be informed of such a context and provided the ability to selectively view the blocked user's comments so the full context can be understood. This aims to help protect the prime user who may have been the subject of harassment from the blocked user originally causing the blocked user to be muted or otherwise blocked in the first place.

Abstract: Systems and methods of intelligent reporting within online communities are provided. A current communication session associated with a plurality of user device may be monitored. The current communication session may include a stream of audio-visual content generated in real-time based on interactions between the user devices. A recording trigger may be detected within the current communication session. A recording of a portion of the stream of audio-visual content may be recorded in response to the detected trigger event. The recording may be analyzed to attribute one or more sub-portions within the recording to one or more of the user devices. At least one of the sub-portions attributed to an identified one of the user devices may be determined to meet a moderation event. A report regarding the identified user device may be generated that includes the at least one sub-portion that meets the moderation event.

Abstract: A method performed for evaluating activity in a video game, including: executing a multi-player session of a video game; during the multi-player session, receiving flag event data from a first player device, the flag event data indicating that a first player has flagged a gameplay incident occurring during the multi-player session as potentially inappropriate; responsive to receiving the flag event data, then sending a request to a plurality of second player devices, wherein responsive to said request each of the plurality of second player devices renders a voting interface to obtain voting input from each of a plurality of second players regarding whether the gameplay incident is inappropriate; receiving said voting input from the plurality of second player devices, and responsive to said voting input identifying a threshold amount of the plurality of second players considering the gameplay incident to be inappropriate, then administering a penalty for the gameplay incident.

Abstract: A system uses map data of a virtual environment and object data of an avatar object including a moveset to generate an action path for traversal of the virtual environment by the avatar object. The system applies machine learning model(s) to generate one or more pathways through the virtual environment, and decompose the one or more pathways into one or more pathway segments that can be evaluated for feasibility and other factors. The system can iteratively generate and evaluate a move sequence of the action path having one or more parameters for execution by the avatar object. The system can construct the action path by combination of a plurality of pathway segments to satisfy one or more constraints associated with traversal by the avatar object from a start location to a destination location within the virtual environment.

Abstract: Systems and methods for generating images are described. A method includes receiving a textual description describing a first image. The method further includes executing an artificial intelligence (AI) model to compute a weight for each word of the textual description and to extract contextual biasing words based on the computed weights. The method further includes generating a suggestion including a proposed modification to the first image based on the contextual biasing words and receiving input data responsive to the suggestion. The method further includes generating a second image based on the suggestion and the input data and providing the second image to a client device for display.

Abstract: System, process, and device configurations are provided for nonplayer character (NPC) personalization and electronic game control. Methods can include receiving user input to personalize at least one nonplayer character (NPC) of an electronic game, generating at least one NPC seed element for the at least one NPC character, and controlling output of the electronic game with at least one NPC character presented including an NPC seed element. NPC seed elements may be determined from one or more of communication steams including messaging data, game chat and voice communications. In addition, systems and methods include training a machine learning model for generatively producing NPC communications, NPC interactions, and NPC appearance. Operations also allow for detecting electronic game data to identify NPC messaging for a game including modification of a communication style NPC character while maintain NPC game messaging.

Abstract: A method including executing game logic of a video game to generate a plurality of video frames for a game play of the video game by a player, wherein game state data is generated during the executing the game logic. The method including determining a current context in the game play of the video game based on the game state data. The method including determining a user sentiment of the player towards the current context in the game play of the video game. The method including determining that the user sentiment of the player is inconsistent with an expected user sentiment for the current context. The method including generating an in-game effect for the current context. The method including presenting the in-game effect simultaneous with one or more video frames associated with the current context in the game play of the video game.

Abstract: The present technology provides solutions for spectator-based interactions in a virtual esports environment. A method can include establishing an interactive session associated with the virtual esports environment, the interactive session including a plurality of user devices, wherein a subset of the user devices is associated with designated players, and another subset of the user devices is associated with designated spectators; receiving data from one of the user devices over a communication network, the data indicating a spectator action performed by a spectator associated with the user device; identifying that the spectator action is associated with one of the players in the virtual esports environment; and modifying the virtual esports environment based on the spectator action and the association with the identified player.

Abstract: Methods and systems for providing audio synchronization control for game scenes of a game include receiving audio data identified for providing the audio synchronization control and processing the audio data while the game is played by the user to identify characteristics of the audio data and an audio signal that is included with the audio data. Input parameters for the audio data is identified and one or more of the input parameters are used as audio synchronization control of at least two assets rendered in one or more game scenes. The audio synchronization control acts to control changes in movements of the assets in accordance to the input parameters.

Abstract: Methods and systems for providing audio synchronization control for game scenes of a game includes receiving audio data that is identified for defining the audio synchronization control desired for the game. The audio data is processed to identify a language spoken in the audio signal and to determine characteristics of the audio signal by extracting keywords spoken in the audio signal. A correlation between the keywords is determined and used to identify a sentiment expressed in the audio signal. A subset of the characteristics including the sentiment is provided as input parameters to a game logic. The input parameters include audio synchronization control usable by the game logic to control at least some interactions between two or more assets rendering in one or more game scenes of the game.

Abstract: Machine learning is used to transform screen renders from the viewpoint of the player's character to be from the viewpoint of other non-player characters (NPC) in the room. One or more neural networks are trained using game images captured during a human play session, and then subsequently the neural networks are used to create realistic video from the NPC viewpoints. To avoid rendering multiple viewpoints simultaneously, a single viewpoint is rendered, and neural networks are used to transform it for the viewpoints of other NPCs in the area. A group of NPCs may be treated as a batch and a single viewpoint transformed to multiple viewpoints in a single inference pass. For cloud gaming the game video can be rendered/sent immediately for the player but the actions of the NPCs are delayed for a frame while the neural network generates the behavior.

Abstract: A method for providing assistance during gameplay is described. The method includes accessing a profile model associated with a user account of a user. The profile model is used to generate one or more predictive indicators based on a plurality of game contexts of one or more games. The method further includes receiving a request for accessing a game for a game session via the user account and generating assistance input for the user responsive to the one or more predictive indicators that the user will be unable to complete a task in the game. The task is associated to a game context. The assistance input is provided before the user performs the task.