中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.011 seconds)

    SYSTEMS AND METHODS OF DETERMINING MARGINS OF AN IMAGE FOR CONTENT INSERTION TO FORM A COMPOSITE IMAGE
    1.
    发明公开
    SYSTEMS AND METHODS OF DETERMINING MARGINS OF AN IMAGE FOR CONTENT INSERTION TO FORM A COMPOSITE IMAGE 审中-公开

    公开(公告)号：US20240112304A1

    公开(公告)日：2024-04-04

    申请号：US17957545

    申请日：2022-09-30

    Applicant: Salesforce, Inc.

    Inventor： Michael Sollami ,  Jessica Lundin

    IPC: G06T5/50 ,  G06T7/13 ,  G06V10/46

    CPC classification number: G06T5/50 ,  G06T7/13 ,  G06V10/462 ,  G06T2207/20024 ,  G06T2207/20221

    Abstract: Systems and methods are provided for determining a first upper bound of a x-direction frame margin of a downsampled image and a second upper bound for a y-direction frame margin of the downsampled image. A total value for each row and column of a weighted grayscale image formed from the downsampled image may be determined. An outlier filtering may be applied to the determined total values for each row and column of the weighted grayscale image. A peak of pairwise ratios of consecutive values from left and right sides of the weighted grayscale image may be used to determine an x-margin, and a peak of pairwise ratios of consecutive values from top and bottom sides of the weighted grayscale image may be used to determine a y-margin. Content may be applied to the image based on the determined x-margin and y-margin values to form a composite image.

    Systems and methods of generating color palettes with a generative adversarial network
    2.
    发明授权
    Systems and methods of generating color palettes with a generative adversarial network 有权

    公开(公告)号：US11593975B2

    公开(公告)日：2023-02-28

    申请号：US17751862

    申请日：2022-05-24

    Applicant: Salesforce, Inc.

    Inventor： Michael Sollami ,  Amir Hossein Raffiee ,  Owen Winne Schoppe

    IPC: G06T11/00 ,  G06K9/62 ,  G06T7/90 ,  G06V10/75

    Abstract: A server of a generative adversarial network (GAN) for color selection; generates a training set of color palettes. A color palette generator of the server generates a first set of color palettes based on the training set of color palettes. The first set of color palettes may be compared with a reference set of color palettes to predict a curated set of color palettes. Colors from the curated set of color palettes may be removed that are within a predetermined distance from one another in a color space. The GAN may be validated by performing cluster analysis to determine outlier latent dimensions to be changed for the color selection by the GAN. Proposed color palettes may be generated based on the GAN to be displayed on a display device.

    CONTENT GENERATION FOR USER INTERESTS
    3.
    发明公开
    CONTENT GENERATION FOR USER INTERESTS 审中-公开

    公开(公告)号：US20240257418A1

    公开(公告)日：2024-08-01

    申请号：US18102369

    申请日：2023-01-27

    Applicant: Salesforce, Inc.

    Inventor： Jessica Lundin ,  Michael Sollami

    IPC: G06T11/60 ,  G06F40/289

    CPC classification number: G06T11/60 ,  G06F40/10 ,  G06F40/289

    Abstract: Systems, devices, and techniques are disclosed for content generation for user interests. Topic phrases may be received. Image content and text content may be generated based on the topic phrases using generative systems. A first generative system may generate the image content and a second generative system may generate the text content. Additional topic phrases may be generated with an auto-summarization system based on the image content. Additional image content and additional text content may be generated based on the additional topic phrases. A third generative system may generate items of candidate content based on the image content, additional image content, text content, and additional text content. The items of candidate content may include an image from either the image content or the additional image content and text from the text content or the additional text content.

    TRAINING NEURAL NETWORKS FOR NAME GENERATION
    4.
    发明公开
    TRAINING NEURAL NETWORKS FOR NAME GENERATION 审中-公开

    公开(公告)号：US20240169194A1

    公开(公告)日：2024-05-23

    申请号：US17989871

    申请日：2022-11-18

    Applicant: Salesforce, Inc.

    Inventor： Michael Sollami

    IPC: G06N3/08 ,  G06F40/279 ,  G06F40/40 ,  G06N3/04

    CPC classification number: G06N3/08 ,  G06F40/279 ,  G06F40/40 ,  G06N3/0454

    Abstract: Systems, device and techniques are disclosed for training neural networks for name generation. A target set including words associated with an object type may be received. A discriminator network and a generator network may be trained. The discriminator network may be trained with a training data set that is based on the target set and the generator network may be trained with random inputs and the discriminator network. The discriminator network may be trained for two epochs for each epoch for which the generator network is trained. The generator network may generate words.

    Region-specific content creation
    7.
    发明授权
    Region-specific content creation 有权

    公开(公告)号：US12265947B2

    公开(公告)日：2025-04-01

    申请号：US17811273

    申请日：2022-07-07

    Applicant: Salesforce, Inc.

    Inventor： Scott Bokma ,  Brian J. Lonsdorf ,  Sönke Rohde ,  Alan Martin Ross ,  Michael Sollami ,  David Woodward ,  Jessica Lundin

    IPC: G06Q30/00 ,  G06Q10/101 ,  G06T11/60

    Abstract: A method receives an input file. The input file includes a plurality of entries where different entries are associated with a different characteristic. A selection of a guide for an entry is determined where a guide includes guidelines for formatting content in an entry in the plurality of entries. The method performs analyzing an image from the entry to generate image variations. Then, the method analyzes the image and the image variations to place text items from the entry in the image and the image variations where the text items in the image and the image variations are formatted based on the guidelines in the guide for the entry. A plurality of design variants is generated for the entry based on the image and the image variations that include text items.

    USER INTEREST DETECTION FOR CONTENT GENERATION
    8.
    发明公开
    USER INTEREST DETECTION FOR CONTENT GENERATION 审中-公开

    公开(公告)号：US20240257179A1

    公开(公告)日：2024-08-01

    申请号：US18102591

    申请日：2023-01-27

    Applicant: Salesforce, Inc.

    Inventor： Jessica Lundin ,  Michael Sollami

    IPC: G06Q30/0251 ,  G06Q30/0241

    CPC classification number: G06Q30/0254 ,  G06Q30/0252 ,  G06Q30/0253 ,  G06Q30/0277

    Abstract: Systems, devices, and techniques are disclosed for user interest detection for content generation. A set of time series data including user interactions with computer accessible resources may be received. A set of expected event data may be received. Irregular event data may be received. A prediction of user interest in an event, including an identification of the event, a time of the event, and levels of user interest before, during and after the time of the event may be generated from the set of time series data, the set of expected event data, and the set of irregular event data. An item of content may be displayed to a user at a time based on the prediction of user interest in the event.

    REGION-SPECIFIC CONTENT CREATION
    9.
    发明公开
    REGION-SPECIFIC CONTENT CREATION 审中-公开

    公开(公告)号：US20240013151A1

    公开(公告)日：2024-01-11

    申请号：US17811273

    申请日：2022-07-07

    Applicant: Salesforce, Inc.

    Inventor： Scott Bokma ,  Brian J. Lonsdorf ,  Sönke Rohde ,  Alan Martin Ross ,  Michael Sollami ,  David Woodward ,  Jessica Lundin

    IPC: G06Q10/10 ,  G06T11/60

    CPC classification number: G06Q10/101 ,  G06T11/60

    Abstract: A method receives an input file. The input file includes a plurality of entries where different entries are associated with a different characteristic. A selection of a guide for an entry is determined where a guide includes guidelines for formatting content in an entry in the plurality of entries. The method performs analyzing an image from the entry to generate image variations. Then, the method analyzes the image and the image variations to place text items from the entry in the image and the image variations where the text items in the image and the image variations are formatted based on the guidelines in the guide for the entry. A plurality of design variants is generated for the entry based on the image and the image variations that include text items.

    Systems and methods of determining margins of an image for content insertion to form a composite image
    10.
    发明授权
    Systems and methods of determining margins of an image for content insertion to form a composite image 有权

    公开(公告)号：US11989858B2

    公开(公告)日：2024-05-21

    申请号：US17957545

    申请日：2022-09-30

    Applicant: Salesforce, Inc.

    Inventor： Michael Sollami ,  Jessica Lundin

    IPC: G06T5/50 ,  G06T7/13 ,  G06V10/46

    CPC classification number: G06T5/50 ,  G06T7/13 ,  G06V10/462 ,  G06T2207/20024 ,  G06T2207/20221

    Abstract: Systems and methods are provided for determining a first upper bound of a x-direction frame margin of a downsampled image and a second upper bound for a y-direction frame margin of the downsampled image. A total value for each row and column of a weighted grayscale image formed from the downsampled image may be determined. An outlier filtering may be applied to the determined total values for each row and column of the weighted grayscale image. A peak of pairwise ratios of consecutive values from left and right sides of the weighted grayscale image may be used to determine an x-margin, and a peak of pairwise ratios of consecutive values from top and bottom sides of the weighted grayscale image may be used to determine a y-margin. Content may be applied to the image based on the determined x-margin and y-margin values to form a composite image.

Patent Agency Ranking