REVERSE AUTO GENERATION OF GENERATIVE AI ENGINE PROMPTS BASED ON OUTPUT RESULTS FOR SELF-VALIDATION

    公开(公告)号:US20250117645A1

    公开(公告)日:2025-04-10

    申请号:US18480802

    申请日:2023-10-04

    Inventor: Jin Zhang

    Abstract: A method for validating a generated output of a generative artificial intelligence (AI) is provided, including the following operations: receiving an input prompt through a user interface rendered by a user device; applying the input prompt to a generative AI to produce a generated output; applying the generated output to a reverse generative AI to produce a reverse-generated prompt; determining a similarity of the reverse-generated prompt to the input prompt; responsive to determining that the similarity meets or exceeds a predefined threshold, then providing the generated output for rendering through the user interface.

    AI RESPONSIVE LAYOUT FOR CROSS-PLATFORM ENVIRONMENTS

    公开(公告)号:US20250114695A1

    公开(公告)日:2025-04-10

    申请号:US18481121

    申请日:2023-10-04

    Abstract: A method including executing a video game to generate a video frame for presentation on a device of a first platform for a game play by a user. The method including determining a target device of a second platform. The method including mapping the video frame to the target device. The method including determining an area of focus in a scene in the video frame based on a game context. The method including classifying an asset in the area of focus using a computer vision model implementing artificial intelligence. The method including determining that the asset is important in the game play using the computer vision model. The method including determining that the asset in the video frame that is mapped does not meet a threshold of visibility. The method including modifying the video frame that is mapped so that the asset meets the threshold of visibility.

    Cooperative and coached gameplay
    7.
    发明授权

    公开(公告)号:US12145065B2

    公开(公告)日:2024-11-19

    申请号:US17828861

    申请日:2022-05-31

    Abstract: Methods and systems for cooperative or coached gameplay in virtual environments are disclosed. Memory may store a content control profile regarding a set of control input associated with an action in a virtual environment of a digital content title. A request may be received from a set of one or more users associated with different source devices regarding cooperative gameplay of the digital content title. At least one virtual avatar may be generated for an interactive session of the digital content title in response to the request. A plurality of control inputs may be received from the plurality of different source devices and combined into a combination set of control inputs. Generating the combination set of control input may be based on the content control profile. Virtual actions associated with the virtual avatar may be controlled within the virtual environment in accordance with the combination set of control inputs.

Patent Agency Ranking