公开(公告)号：US20210073833A1

公开(公告)日：2021-03-11

申请号：US17015822

申请日：2020-09-09

Applicant: eBay Inc.

Inventor： Maxim Manco ,  Fang Fang ,  Natraj Srinivasan ,  Alexander Akerman ,  Michael Ebin ,  Eran Ben Tovim

IPC: G06Q30/02 ,  G06Q50/04 ,  G06Q30/06 ,  G06Q10/08 ,  G06N3/04 ,  G06N3/08 ,  G05B13/02 ,  G06F3/12 ,  B33Y50/02

Abstract: An autonomous item generation system implements a trained machine learning model configured to output fabrication instructions for generating an item and metadata describing the item, automatically and independent of user input. Fabrication instructions output by the machine learning model are transmitted to a fabrication device for generating the item. The autonomous item generation system generates a listing for the item based on the metadata output by the machine learning model and publishes the listing to a virtual marketplace. Analytics data describing feedback for the item listing is used to generate training data for the machine learning model. The training data is input to the machine learning model, which causes the machine learning model to refine at least one control parameter according to a loss function that penalizes negative differences between predicted and observed feedback data for the item. The machine learning model with the refined parameter(s) is then used by the autonomous item generation system to generate fabrication instructions and metadata for an additional item.

公开(公告)号：US20230098794A1

公开(公告)日：2023-03-30

申请号：US18061740

申请日：2022-12-05

Applicant: eBay Inc.

Inventor： Maxim Manco ,  Fang Fang ,  Natraj Srinivasan ,  Alexander Akerman ,  Michael Ebin ,  Eran Ben Tovim

IPC: G06Q30/06 ,  G06F9/451 ,  B33Y50/02 ,  G05B13/02 ,  G06Q30/02 ,  G06F3/12 ,  G06N3/08 ,  G06F21/62 ,  G06Q50/04 ,  G06N20/00 ,  G06Q10/08 ,  G06N3/04 ,  G06F3/0482 ,  G06F3/0484

Abstract: An autonomous item generation system implements a trained machine learning model configured to output fabrication instructions for generating an item and metadata describing the item, automatically and independent of user input. Fabrication instructions output by the machine learning model are transmitted to a fabrication device for generating the item. The autonomous item generation system generates a listing for the item based on the metadata output by the machine learning model and publishes the listing to a virtual marketplace. Analytics data describing feedback for the item listing is used to generate training data for the machine learning model. The training data is input to the machine learning model, which causes the machine learning model to refine at least one control parameter according to a loss function that penalizes negative differences between predicted and observed feedback data for the item. The machine learning model with the refined parameter(s) is then used by the autonomous item generation system to generate fabrication instructions and metadata for an additional item.

公开(公告)号：US11816143B2

公开(公告)日：2023-11-14

申请号：US15887667

申请日：2018-02-02

Applicant: eBay Inc.

Inventor： Mary Adaway Titus ,  Hyuntae Kim ,  Benjamin Eliot Klein ,  Bo Li ,  Maxim Manco ,  Stephen Anthony Neola ,  Andrew Daniel Shea

IPC: G06F16/532 ,  G06F16/732 ,  G06F16/50 ,  G06F16/955 ,  G06F3/04817 ,  G06F3/0483 ,  G06F3/04845 ,  G06F3/0486 ,  H04L67/02

CPC classification number: G06F16/532 ,  G06F3/0483 ,  G06F3/0486 ,  G06F3/04817 ,  G06F3/04845 ,  G06F16/50 ,  G06F16/7335 ,  G06F16/9558 ,  H04L67/02

Abstract: In various embodiments, methods and systems for implementing an integrated image search system are provided. The integrated image search system supports an image search feature of a content application on a mobile device. An image identifier is received to execute an image search operation. The image identifier is received via a native operating system action that is customized to support the image search feature. The native operating system action defines an entry point to the image search feature. The entry points can be based on image identifiers identified from a share image action, a share Uniform Resource Locator (URL) action, a copy share URL action, or a drag and drop action. An image of the image identifier is used to execute the image search operation to identify image search results. An image search results page having one or more images search results is caused to be displayed.

公开(公告)号：US20190026316A1

公开(公告)日：2019-01-24

申请号：US15887667

申请日：2018-02-02

Applicant: eBay Inc.

Inventor： Mary Adaway Titus ,  Hyuntae Kim ,  Benjamin Eliot Klein ,  Bo Li ,  Maxim Manco ,  Stephen Anthony Neola ,  Andrew Daniel Shea

IPC: G06F17/30 ,  G06F3/0483 ,  G06F3/0481 ,  G06F3/0486 ,  G06F3/0484

Abstract: In various embodiments, methods and systems for implementing an integrated image search system are provided. The integrated image search system supports an image search feature of a content application on a mobile device. An image identifier is received to execute an image search operation. The image identifier is received via a native operating system action that is customized to support the image search feature. The native operating system action defines an entry point to the image search feature. The entry points can be based on image identifiers identified from a share image action, a share Uniform Resource Locator (URL) action, a copy share URL action, or a drag and drop action. An image of the image identifier is used to execute the image search operation to identify image search results. An image search results page having one or more images search results is caused to be displayed.