-
公开(公告)号:US11294971B1
公开(公告)日:2022-04-05
申请号:US17157284
申请日:2021-01-25
Applicant: Coupang Corp.
Inventor: Nuri Mehmet Gokhan , Varun A Samtani
Abstract: 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.
-
公开(公告)号:US12118046B2
公开(公告)日:2024-10-15
申请号:US17653151
申请日:2022-03-02
Applicant: Coupang Corp.
Inventor: Nuri Mehmet Gokhan , Varun A Samtani
IPC: G06V10/74 , G06F16/951 , G06F18/22 , G06F18/23 , G06F18/2413 , G06N3/02 , G06N5/01 , G06N20/00 , G06Q10/0875 , G06Q30/02 , G06Q30/0201 , G06Q30/0283 , G06T7/194 , G06T11/60 , G06V20/40 , G10L17/10
CPC classification number: G06F16/951 , G06F18/22 , G06F18/23 , G06F18/24147 , G06N3/02 , G06N5/01 , G06N20/00 , G06Q10/0875 , G06Q30/02 , G06Q30/0201 , G06Q30/0283 , G06T7/194 , G06T11/60 , G06V10/761 , G06V20/41 , G10L17/10
Abstract: 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.
-