Abstract: A user's environment is scanned and an augmented reality game such as a treasure is set up based on the scan. The user needs to use a phone to uncover clues in a game environment that is customized to user's own personal real-world environment, which is discovered using SLAM or GPS so that a map of furniture can be built. The game hides a virtual object behind a virtualized image of the real-world furniture. Machine learning may be used to train a model with common objects and where interesting hidden spaces could exist. Given the user's inputted data, real world physical room data and objects are used to determine a likely location to hide a virtual object.

Abstract: Data processing/GUIs for NFT block chain data to “tell the story” of ownership or highlight “cool” aspects of a computer game-related NFT in simplified way. Machine learning (ML) may be used to boil down the complexity of data to what people need or want to understand. The displayed timeline of ownership as presented in a GUI can be interactive. Types of metadata to encapsulate in the NFT are discussed.

Abstract: Methods and system for generating an image for a user prompt provided by a user includes receiving the user prompt from the user. The user prompt is analyzed to detect text input and keywords included within. Keyword variations are provided to one or more keywords for user selection. An adjusted user prompt is generated by replacing keywords in the user prompt with keyword variations selected by the user. An image customized for the adjusted user prompt is generated to include image features that are influenced by content of the adjusted user prompt. The customized image providing a visual representation of the adjusted prompt is returned to a client device for rendering.

Abstract: Methods and systems for tracking a game asset used in a video game includes generating a non-fungible token for the game asset used in the video game. Use of the game asset in the video game is monitored during gameplay to identify a qualifying event occurring in the video game in which the game asset is used. The NFT is updated using metadata associated with the qualifying event. The metadata is used to build legacy of the game asset and to track use of the digital asset in the video game.

Abstract: A user's environment is scanned and an augmented reality game such as a treasure is set up based on the scan. The user needs to use a phone to uncover clues in a game environment that is customized to user's own personal real-world environment, which is discovered using SLAM or GPS so that a map of furniture can be built. The game hides a virtual object behind a virtualized image of the real-world furniture. Machine learning may be used to train a model with common objects and where interesting hidden spaces could exist. Given the user's inputted data, real world physical room data and objects are used to determine a likely location to hide a virtual object.

Abstract: Application context may be interpolated between application state updates from structured and unstructured application state data. Irrelevant unimodal modules may be deactivated based on the structured application state data while relevant unimodal modules remain active. Unimodal features are generated from the unstructured application using the relevant modules. A neural module selection network module may be trained with a machine learning algorithm. Each unimodal modules may generate unimodal feature vectors from unstructured application data. A context state update module may determine which unimodal modules are irrelevant from structured application state data and deactivate the irrelevant modules but not the relevant ones. A multimodal neural network may take the active unimodal feature vectors and predict structured context data and send it to a uniform data system.

Abstract: A system for generating gameplay context information for a game may include a game screen classification module trained to classify contextually relevant data from gameplay data, one or more game object recognition modules trained to detect game icons from gameplay data, and a multimodal context generation neural network module trained to generate structured gameplay context information from the contextually relevant data and icons within the gameplay data. The multimodal context generation neural network module at least partially generates structured gameplay context information. The modules may include neural networks trained by suitable machine learning algorithms using suitable masked data and labeled data.

Abstract: A method includes receiving text corresponding to a conversation between two or more people, receiving information for use in customizing a summary of the conversation that is to be generated, and generating the summary of the conversation that is customized according to the received information. The summary of the conversation is generated by feeding the received text and the received information into an artificial intelligence model that uses the received text and the received information as inputs. A system includes a network interface and a processor-based system configured to receive text corresponding to a conversation between two or more people, receive information for use in customizing a summary of the conversation that is to be generated, and generate the summary of the conversation that is customized according to the received information.

Abstract: An audio comment feature is added to livestream chat. A viewer of the livestream can record a voice clip and post that audio comment to the chat. A screening system ingests the audio clip, converting it to text using a speech-to-text algorithm. The text version of the audio clip is processed by an AI moderation algorithm to filter out objectionable content. Clips that pass through the filter are displayed to the livestreamer as a text comment with an option to play the audio live on the air. The livestreamer can watch this feed of text comments during the stream. Upon identifying a comment worth broadcasting on the stream, the streamer can click a Play button on the text version of the comment to play the audio version of the comment live on the stream.

Abstract: A non-fungible token (NFT) representing a computer game asset can be purchased for a limited time by a gamer or a spectator and in some cases extended up to a maximum period, after which time the NFT is placed back on the market.

Abstract: Methods and systems for providing augment reality overlay associated with a real-world object includes detecting a gaze target of a user viewing the real-world environment using a pair of AR glasses by tracking a gaze of the user. Position parameters affecting the gaze of the user are tracked and one or more attributes of the gaze target are selectively corrected to allow the user to maintain their gaze on the gaze target. An AR trigger element associated with the gaze target is triggered in response to the gaze of the user. The AR trigger element provides additional information related to the gaze target selected by the user.

Abstract: A method for providing information in an HMD. The method includes defining an active zone in a virtual reality (VR) viewing environment of a user as presented through a 3D display of the HMD. The method includes placing main content in the active zone of the VR viewing environment. The method includes defining one or more peripheral zones outside of the active zone. The method includes placing secondary content in the first peripheral zone of the VR viewing environment. The method includes displaying an attractor within the active zone in conjunction with the entry of new data in the secondary content, wherein the attractor brings attention of the user to the first peripheral zone. The method includes detecting rotation of the HMD from the first orientation directed to the active zone towards a second orientation directed to the first peripheral zone. The method includes pausing the main content.

Abstract: A method for gaming, including receiving from a client device of a user selection of a video recording of game play of a player for a gaming application, and streaming the video recording to the client device. The video recording is associated with a snapshot captured at a first point in the recorded game play. Selection of a jump point in the recorded game play is received from the client device. An instance of the gaming application is initiated based on the snapshot to initiate a jump game play. Input commands used to direct the game play and associated with the snapshot are accessed. Image frames are generated based on the input commands for rendering at the client device, the image frames replaying the game play to the jump point. Input commands from the client device are handled beginning from the jump point for the jump game play.

Abstract: The present disclosure is directed to controlling outcomes in a game that includes multiple different users playing respective roles of specific virtual characters. The multiple different users may be present at a same physical location, or the different users may be located at different physical locations when movement of their eyes is tracked. Here, a user may choose one of a set of provided selections by simply looking at the chosen selection for a period of time or by looking at the chosen selection and performing an action or gesture. This functionality allows multiple different users to control actions performed by different specific characters via an online multiplayer system. Depending on what a first user looks at, that first user or a second user may be provided with a corresponding set of selections or audio/visual content via respective gaming devices operated by the first and the second user.

Abstract: A method including generating an image using an image generation artificial intelligence system configured for implementing latent diffusion, wherein the image is decoded from a latent space representation. The method including receiving selection of a portion of the image. The method including receiving commentary of a user corresponding to the portion of the image. The method including generating a text prompt to modify the portion of the image based on the commentary. The method including encoding the portion of the image using latent diffusion based on the text prompt. The method including modifying the latent space representation of the image using latent diffusion to generate a modified image, wherein the text prompt and the encoded portion of the image are provided as input to the image generation artificial intelligence system.

Abstract: A method is provided, including: receiving a game image, said game image being captured from gameplay of a video game and said game image depicting a scene of the video game; receiving game state data describing attributes of the scene of the video game that is depicted in the game image; receiving, over a network from a client device, modification data describing changes to the game image, the modification data defined from user input received at the client device; applying the game image, the game state data, and the user input, by an image generation artificial intelligence (AI) to generate an AI generated image; transmitting the AI generated image over the network to the client device for rendering to a display.

Abstract: A method for generating an avatar for a video game is provided, including: receiving, over a network from a client device, a captured image of a user and modification data, the modification data being generated from user input received at the client device, the modification data describing characteristics for generating an avatar for the user; using an image generation artificial intelligence (AI) to generate the avatar based on the image of the user and the modification data; wherein the avatar is configured for use in a video game, and wherein the image generation AI is configured to generate the avatar having a style consistent with a style of the video game in which the avatar will be used; applying the avatar to a session of the video game.

Abstract: Data processing/GUIs for NFT block chain data to “tell the story” of ownership or highlight “cool” aspects of a computer game-related NFT in simplified way. Machine learning (ML) may be used to boil down the complexity of data to what people need or want to understand. The displayed timeline of ownership as presented in a GUI can be interactive. Types of metadata to encapsulate in the NFT are discussed.

Abstract: Methods for tagging content in a video game title during game play executed on a game cloud system, and social sharing methods. One method includes receiving a pause indication during the game play and suspending the game play to hold the video game title in a current frame image, storing the game state, and receiving the tag data that is associated to a location in the current frame image and to a user identifier for the current frame image. The method further includes generating a video recording of the game play having the tag data and generating a mini-game from a portion of the video game title. The mini-game includes a playable portion to enable view of a portion of the video recording for the mini-game and an executable portion to enable the play of game code for the mini-game that is a portion of the video game title.

Abstract: Computer implemented systems and methods for cross-platform spoiler blocking are provided herein. An example method includes ascertaining by a data platform data potentially available to a user of a service having a media object; identifying by the data platform at least one object revealed by the media object, the at least one object being associated with an application; receiving by the data platform metadata associated with the at least one object, the metadata indicative of whether the at least one object should be hidden from the user; determining by the data platform, based on the metadata, the at least one object is a potential spoiler; and blocking by the data platform, the user from interacting with the media object through the service.