知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

8 条记录 (耗时 0.016 秒)

    Probabilistic search biasing and recommendations
    2.
    发明授权
    Probabilistic search biasing and recommendations 有权

    公开(公告)号：US11282100B2

    公开(公告)日：2022-03-22

    申请号：US16288373

    申请日：2019-02-28

    申请人： Mercari Inc.

    发明人： Byong Mok Oh ,  Dhruv Mehrotra ,  Chiaki Osaka ,  Naoya Makino ,  Patrick Michael Wiseman ,  Minami Sueyasu

    IPC分类号： G06Q30/00 ,  G06Q30/02 ,  G06Q30/06 ,  G06F16/903 ,  G06F16/908 ,  G06F16/9032 ,  G06N3/08 ,  G06F16/951

    摘要： Disclosed herein are system, method, and computer program product embodiments for probabilistic search biasing and recommendations. A system including at least one processor may be configured to receive an input relating to an identified item, generate a database query based on the input, and receive a response to the database query. The response may include information on comparable items similar to the identified item, and corresponding metadata for the comparable items. The corresponding metadata may include a range of values corresponding to the comparable items. The system may be further configured to generate a probability score for at least two values of the range of values, based at least on the corresponding metadata for the comparable items. The system may be further configured to output at least a suggested value based on at least the generated probability score for the range of values and prompt for further input.

    MACHINE-LEARNING PREDICTION OR SUGGESTION BASED ON OBJECT IDENTIFICATION
    3.
    发明申请
    MACHINE-LEARNING PREDICTION OR SUGGESTION BASED ON OBJECT IDENTIFICATION 有权

    公开(公告)号：US20220067571A1

    公开(公告)日：2022-03-03

    申请号：US17007438

    申请日：2020-08-31

    申请人： Mercari, Inc.

    发明人： John Alexander Lagerling ,  Byong Mok Oh ,  Fritz Mikio Kuribayashi ,  Takuma Yamaguchi ,  Rishabh Kumar Shrivastava ,  Takaya Ukai ,  Viswakumar Sukeesh Babu

    IPC分类号： G06N20/00 ,  G06N5/02 ,  G06Q30/02 ,  G06F16/23

    摘要： Disclosed herein are system, computer-program product (non-transitory computer-readable medium), and method embodiments for machine-learning prediction or suggestion based on object identification. A system including at least one processor may be configured to cross-reference an identifier of a selected object with a list of known unique identifiers. The selected object may be selected via received selection. The at least one processor may further retrieve a set of values associated with the identifier of the selected object, upon determining that the list of known unique identifiers includes the identifier of the selected object, and perform machine-learning to derive a predicted-value set based at least in part on the set of values associated with the identifier of the selected object and a category applicable to the selected object. The at least one processor may determine that the predicted-value set satisfies a predetermined confidence condition, and output at least part of the predicted-value set.

    Probabilistic item matching and searching
    4.
    发明授权
    Probabilistic item matching and searching 有权

    公开(公告)号：US11074634B2

    公开(公告)日：2021-07-27

    申请号：US16288379

    申请日：2019-02-28

    申请人： Mercari Inc.

    发明人： Byong Mok Oh ,  Dhruv Mehrotra ,  Chiaki Osaka ,  Naoya Makino ,  Patrick Michael Wiseman ,  Minami Sueyasu

    IPC分类号： G06Q30/00 ,  G06Q30/06 ,  G06N7/00

    摘要： Disclosed herein are system, method, and computer program product embodiments for probabilistic item matching and searching. A system including at least one processor may be configured to receive a data point relating to a specific item, generate a database query based on the data point, and receive a response to the database query. The response may include multiple candidate items relating to the specific item. The system may be further configured to receive a first input relating to the specific item and generate a probability score for at least two candidate items of the multiple candidate items in the response, based on at least the second input. The system may be further configured to select a selected item from the candidate items, based on the probability score for the selected item. The system may be further configured to output a reference to, or value representing, the selected item.

    Determining sellability score and cancellability score
    5.
    发明授权
    Determining sellability score and cancellability score 有权

    公开(公告)号：US11816686B2

    公开(公告)日：2023-11-14

    申请号：US16288158

    申请日：2019-02-28

    申请人： Mercari, Inc.

    发明人： John Alexander Lagerling ,  Kai Chun Cheung ,  Byong Mok Oh ,  Dhruv Mehrotra ,  Jeffrey Kenichiro Hara

    IPC分类号： G06Q30/00 ,  G06Q30/0202 ,  G06N20/00 ,  G06Q30/0601

    CPC分类号： G06Q30/0202 ,  G06N20/00 ,  G06Q30/0601

    摘要： Disclosed herein are system, method, and computer program product embodiments for generating sellability and cancellability scores for selling objects on an electronic marketplace. An embodiment operates by receiving, from a mobile device, an image including an object for sale and determining information associated with the object for sale. Information associated with pre-identified objects is determined from information associated with pre-identified objects, where each of the pre-identified objects corresponds to the object for sale. A sellability score and/or a cancellability score is generated based at least in part on the information associated with the object for sale and the information associated with the pre-identified objects. The sellability score and the cancellability score are further provided to users.