利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

5 条记录 (耗时 0.025 秒)

    Systems and methods for modeling item similarity using converted image information
    1.
    发明授权
    Systems and methods for modeling item similarity using converted image information 有权

    公开(公告)号：US11294971B1

    公开(公告)日：2022-04-05

    申请号：US17157284

    申请日：2021-01-25

    申请人： Coupang Corp.

    发明人： Nuri Mehmet Gokhan ,  Varun A Samtani

    IPC分类号： G06K9/62 ,  G06Q30/02 ,  G06F16/951 ,  G06T7/194 ,  G06T11/60 ,  G06N5/00

    摘要： Systems and methods for correlating item data are disclosed. A system for correlating item data may include a memory storing instructions and at least one processor configured to execute instructions to perform operations including: receiving text and image data associated with a reference item from a remote device; converting, using a computer-modeled embedding layer, at least one image to an image embedding; comparing the image embedding to reference embeddings stored in a database; selecting a subset of the candidate item text as candidate text data based on the comparison; selecting a subset of the candidate item images as candidate image data based on the comparison; selecting a text correlation model; determining a first similarity score; selecting an image correlation model; determining a second similarity score; calculating a confidence score based on the first and second similarity scores; and performing a responsive action based on the calculated confidence score.

    SYSTEMS AND METHODS FOR EXPERIMENTATION OF E-COMMERCE PRICING DISTRIBUTION BASED ON TIME-INTERLEAVING
    4.
    发明申请
    SYSTEMS AND METHODS FOR EXPERIMENTATION OF E-COMMERCE PRICING DISTRIBUTION BASED ON TIME-INTERLEAVING 有权

    公开(公告)号：US20210350401A1

    公开(公告)日：2021-11-11

    申请号：US16871126

    申请日：2020-05-11

    申请人： COUPANG CORP.

    发明人： JIE WENG ,  Nuri Mehmet Gokhan ,  Qian Weng

    IPC分类号： G06Q30/02 ,  G06F16/958

    摘要： A system for experimentation of e-commerce pricing distribution based on time-interleaving includes one or more processors configured to identifying a first set of items from a plurality of items based on one or more item pricing policies. Scheduling the first set of items to be published on a website during a first time slot from a plurality of time slots by applying a scheduling algorithm. Identifying a first subset of substitutable items and a second subset of substitutable items from the first set of items based on one or more item substitution rules. Assigning the first subset of substitutable items with a first pricing policy and the second subset of substitutable items with a second pricing policy. Publishing the first subset of substitutable items and the second subset of substitutable items. Determining pricing distribution data based on monitoring customer interaction.

    Systems and methods for modeling item similarity and correlating item information
    5.
    发明授权
    Systems and methods for modeling item similarity and correlating item information 有权

    公开(公告)号：US11048773B1

    公开(公告)日：2021-06-29

    申请号：US17158308

    申请日：2021-01-26

    申请人： Coupang Corp.

    发明人： Nuri Mehmet Gokhan ,  Shanshan Wang ,  Cheng Ing Chia

    IPC分类号： G06F17/15 ,  G06K9/62 ,  G06F16/951 ,  G06F40/279

    摘要： Disclosed herein are systems and methods for correlating item data. A system for correlating item data may comprise a memory storing instructions and at least one processor configured to execute instructions to perform operations comprising: receiving reference text data associated with a reference item from a device; receiving reference image data associated with the reference item from the remote device; determining candidate text data and candidate image data associated with at least one candidate item; selecting a text correlation model; determining a first similarity score by applying the text correlation model to the reference text data and the candidate text data; selecting an image correlation model; determining a second similarity score by applying the image correlation model to the reference image data and the candidate image data; calculating a confidence score based on the first and second similarity scores; and performing a responsive action based on the calculated confidence score.