利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

1830 records (took 0.022 seconds)

    AI-BASED ADVERTISEMENT PREDICTION AND OPTIMIZATION
    2.
    发明公开
    AI-BASED ADVERTISEMENT PREDICTION AND OPTIMIZATION 审中-公开

    公开(公告)号：US20240346547A1

    公开(公告)日：2024-10-17

    申请号：US18661454

    申请日：2024-05-10

    Applicant: AiAdvertising, Inc.

    Inventor： Kevin Myers

    IPC: G06Q30/0242 ,  G06Q30/0241

    CPC classification number: G06Q30/0244 ,  G06Q30/0276

    Abstract: The performance of a digital asset is analyzed via artificial intelligence. Data associated with a plurality of users from a plurality of data sources are received, that includes tracked activities of the plurality of users using artificial intelligence. A learning model is generated for one or more virtual personas based on the received data, each persona associated with a demographic and a pattern of behavior. One or more elements of an asset is automatically tagged. Artificial intelligence tracks one or more metrics associated with the asset, the metrics sorted based on the one or more virtual personas. Performance of the asset is predicted for a user that shares a common trait with one of the personas. A new asset is generated associated with a persona associated with the user based on the one or more metrics by updating the one or more elements of the asset.

    Fair demographic ratio pacing
    5.
    发明授权
    Fair demographic ratio pacing 有权

    公开(公告)号：US12067597B2

    公开(公告)日：2024-08-20

    申请号：US17940941

    申请日：2022-09-08

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Yana Volkovich ,  Moussa Taifi

    IPC: G06Q30/0273 ,  G06Q30/0241 ,  G06Q30/0242 ,  G06Q30/0251

    CPC classification number: G06Q30/0275 ,  G06Q30/0244 ,  G06Q30/0269 ,  G06Q30/0277

    Abstract: Aspects of the subject disclosure may include, for example, receiving information defining an attribute of interest for the impression, wherein the attribute of interest comprises a plurality of categories of values, and receiving information defining a respective probability for each respective value of the plurality of categories of values for the impression. Further, information about current values of the plurality of categories for the attribute of interest may be received and a pacing value may be determined based on the respective probability for each respective value of the plurality of categories of values, along with the information about current values the plurality of categories for the attribute of interest. A respective bid value of a bid may be adjusted using the pacing value and the adjusted bid value may be used in an auction to fill the impression. This permits automatic detection and correction of an inadvertent skew introduced when serving ads and other content. Other embodiments are disclosed.

    SYSTEMS AND METHODS FOR TARGETING BID AND POSITION FOR A KEYWORD
    6.
    发明公开
    SYSTEMS AND METHODS FOR TARGETING BID AND POSITION FOR A KEYWORD 审中-公开

    公开(公告)号：US20240249317A1

    公开(公告)日：2024-07-25

    申请号：US18626673

    申请日：2024-04-04

    Applicant: Capital One Services, LLC

    Inventor： James O. H. MONTGOMERY ,  Athanassios KINTSAKIS ,  Keegan HINES

    IPC: G06Q30/0251 ,  G06Q30/0241 ,  G06Q30/0242 ,  G06Q30/0273

    CPC classification number: G06Q30/0256 ,  G06Q30/0244 ,  G06Q30/0275 ,  G06Q30/0277

    Abstract: Disclosed are methods, systems, and non-transitory computer-readable medium for targeting bid and position for a keyword. For instance, the method may include obtaining information about the keyword, the information about the keyword including observations of value with respect to position for the keyword. The method may further include applying a Gaussian Process Model on the observations to obtain a prediction function and associated uncertainties, the prediction function and the associated uncertainties relating positions to expected values; applying a Thompson sampling reinforcement learning model on the expected values and the positions to obtain a target position; and applying a bid model to the target position to obtain bid information for the keyword. The method may also include transmitting a bid message to a search engine, the bid message including the bid information.

    SYSTEM AND METHODS UTILIZING GENERATIVE AI FOR OPTIMIZING TV ADS, ONLINE VIDEOS, AUGMENTED REALITY & VIRTUAL REALITY MARKETING, AND OTHER AUDIOVISUAL CONTENT
    8.
    发明公开
    SYSTEM AND METHODS UTILIZING GENERATIVE AI FOR OPTIMIZING TV ADS, ONLINE VIDEOS, AUGMENTED REALITY & VIRTUAL REALITY MARKETING, AND OTHER AUDIOVISUAL CONTENT 审中-公开

    公开(公告)号：US20240232937A1

    公开(公告)日：2024-07-11

    申请号：US18440543

    申请日：2024-02-13

    Applicant: Timothy Christopher D'Auria

    Inventor： Timothy Christopher D'Auria

    IPC: G06Q30/0242 ,  G06N3/0475

    CPC classification number: G06Q30/0244 ,  G06N3/0475

    Abstract: This invention presents a system and methods for optimizing audiovisual content, including TV commercials, online videos, and AR/VR marketing, using generative models. It processes varied audiovisual data, generating an intermediary output that captures key elements like color schemes, audio patterns, entity interactions, and narrative structures. The system's attribute recognition module, combined with an effectiveness measurement module, enables comprehensive pattern recognition, enhancing the creation of optimized content across mediums. It incorporates various AI models, such as LLMs and GPTs, and employs text mining, uncertainty measurement, and SHAP values. The system is adaptable for different performance metrics, such as advertising effectiveness and ROI. This approach streamlines the audiovisual content development process, reducing time and costs, and is applicable in television, online video production, social media advertising, and AR/VR marketing.

Patent Agency Ranking