利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

15 条记录 (耗时 0.073 秒)

    SYSTEM AND METHOD FOR GENERATING FINANCING STRUCTURES USING CLUSTERING
    3.
    发明申请
    SYSTEM AND METHOD FOR GENERATING FINANCING STRUCTURES USING CLUSTERING 有权

    公开(公告)号：US20230136862A1

    公开(公告)日：2023-05-04

    申请号：US18092500

    申请日：2023-01-03

    申请人： Capital One Services, LLC

    发明人： Saman Baghestani ,  Rohan Shah ,  Nicholas E. Dolle

    IPC分类号： G06Q30/0201 ,  G06N20/00 ,  G06F18/213 ,  G06F18/23213

    摘要： Described herein is a system for generating financing structures. A learning engine may extract data sets associated with sellers of various products. The learning engine may be trained using the data sets. The learning engine may identify a subset of dimensions that cause a change in a determination of a final price for a given product. The learning engine may compute a value for each of the sellers with respect to each dimension. The learning engine may group the sellers into different clusters. The learning engine may generate using a model, including the subset of dimensions. The learning engine may receive a request to generate a financing structure for a specified product sold by a specified seller. The learning engine may generate financing structures for the specified product sold by the specified seller based on the generated model.

    DATA PROCESSING METHOD AND APPARATUS
    4.
    发明申请
    DATA PROCESSING METHOD AND APPARATUS 有权

    公开(公告)号：US20230117973A1

    公开(公告)日：2023-04-20

    申请号：US18084267

    申请日：2022-12-19

    申请人： HUAWEI TECHNOLOGIES CO., LTD.

    发明人： Yudong Zhu ,  Jinghui Xiao ,  Di Zhou

    IPC分类号： G06F18/213 ,  G06N3/0985 ,  G06N3/063 ,  G06N3/048 ,  G06F18/2451

    摘要： This application discloses a data processing method, applied to the field of artificial intelligence, including: obtaining to-be-processed data; and processing the to-be-processed data by using a trained neural network, to output a processing result. The neural network includes a feature extraction network and a classification network. The feature extraction network is configured to extract a feature vector expressed by the to-be-processed data in hyperbolic space. The classification network is configured to process the feature vector based on an operation rule of the hyperbolic space, to obtain the processing result. In this application, precision of processing by a model a data set including a tree-like hierarchical structure can be improved, and a quantity of model parameters can be reduced.

    SYSTEMS AND METHODS FOR DETECTING IMAGE RECAPTURE
    6.
    发明申请
    SYSTEMS AND METHODS FOR DETECTING IMAGE RECAPTURE 有权

    公开(公告)号：US20230117683A1

    公开(公告)日：2023-04-20

    申请号：US18085856

    申请日：2022-12-21

    申请人： TruePic Inc.

    发明人： Oliver RICE ,  Justin Mark STAYTON ,  Gordon Charles HUGHES

    IPC分类号： G06T7/00 ,  G06V10/40 ,  G06F18/213

    摘要： Systems, computer-implemented methods, and non-transitory machine-readable storage media are provided for detecting recapture attacks of images. One method comprises extracting one or more features from an image captured by a device; applying the one or more features as input to a trained machine learning model, wherein the trained machine learning model outputs a first score based on the extracted features; obtaining metadata of the image; performing a statistical analysis of the metadata of the image; generating a second score based on the statistical analysis of the metadata of the image; and generating a probability that the image is a recapture of an original image based on the first score and the second score.

    Detecting ink gestures based on spatial and image data processing
    7.
    发明授权
    Detecting ink gestures based on spatial and image data processing 有权

    公开(公告)号：US11587346B2

    公开(公告)日：2023-02-21

    申请号：US17117151

    申请日：2020-12-10

    申请人： Microsoft Technology Licensing, LLC

    发明人： Oz Solomon ,  Oussama Elachqar ,  Sergey Aleksandrovich Doroshenko ,  Nima Mohajerin ,  Badal Yadav

    IPC分类号： G06V30/32 ,  G06V40/20 ,  G06K9/62 ,  G06F18/213

    摘要： Ink-processing technology is set forth herein for detecting a gesture that a user performs in the course of interacting with an ink document. The technology operates by identifying a grouping of ink strokes created by the user. The technology then determines whether the grouping expresses a gesture based on a combination of spatial information and image information, both of which describe the grouping. That is, the spatial information describes a sequence of positions traversed by the user in drawing the grouping of ink strokes using an ink capture device, while the image information refers to image content in an image produced by rendering the grouping into image form. The technology also provides a technique for identifying the grouping by successively expanding a region of analysis, to ultimately provide a spatial cluster of ink strokes for analysis.

    METHOD AND APPARATUS FOR TRACKING TARGET
    9.
    发明申请
    METHOD AND APPARATUS FOR TRACKING TARGET 有权

    公开(公告)号：US20230115606A1

    公开(公告)日：2023-04-13

    申请号：US18073737

    申请日：2022-12-02

    申请人： Samsung Electronics Co., Ltd.

    发明人： HyunJeong LEE ,  Changbeom PARK ,  Hana LEE ,  Sung Kwang CHO

    IPC分类号： G06T7/246 ,  G06T7/73 ,  G06V10/40 ,  G06F18/22 ,  G06F18/213

    摘要： A target tracking method and apparatus is provided. The target tracking apparatus includes a memory configured to store a neural network, and a processor configured to extract feature information of each of a target included in a target region in a first input image, a background included in the target region, and a searching region in a second input image, using the neural network, obtain similarity information of the target and the searching region and similarity information of the background and the searching region based on the extracted feature information, obtain a score matrix including activated feature values based on the obtained similarity information, and estimate a position of the target in the searching region from the score matrix.

    Method, device, and computer program product for self-supervised learning of pixel-wise anatomical embeddings in medical images
    10.
    发明授权
    Method, device, and computer program product for self-supervised learning of pixel-wise anatomical embeddings in medical images 有权

    公开(公告)号：US11620359B2

    公开(公告)日：2023-04-04

    申请号：US17208128

    申请日：2021-03-22

    申请人： Ping An Technology (Shenzhen) Co., Ltd.

    发明人： Ke Yan ,  Jinzheng Cai ,  Youbao Tang ,  Dakai Jin ,  Shun Miao ,  Le Lu

    IPC分类号： G06F18/214 ,  G06T7/70 ,  G06N3/08 ,  G06T7/00 ,  G06V30/262 ,  G06F18/213

    摘要： The present disclosure provides a method, a device, and a computer program product using a self-supervised anatomical embedding (SAM) method. The method includes randomly selecting a plurality of images; for each image of the plurality of images, performing random data augmentation to obtain a patch pair, generating global and local embedding tensors for each patch of the patch pair, and selecting positive pixel pairs from the patch pair and obtaining positive embedding pairs; for each positive pixel pair, computing global and local similarity maps, finding global hard negative embeddings, selecting global random negative embeddings, pooling the global hard negative embeddings and the global random negative embeddings to obtain final global negative embeddings, and finding local hard negative embeddings using the global and local similarity maps, and randomly sampling final local negative embeddings from the local hard negative embeddings; and minimizing a final info noise contrastive estimation (InfoNCE) loss.