US 12,235,929 B2
Database management system and method for updating a training dataset of an item identification model
Sailesh Bharathwaaj Krishnamurthy, Irving, TX (US); Sumedh Vilas Datar, Grapevine, TX (US); Tejas Pradip Rode, Coppell, TX (US); and Shahmeer Ali Mirza, Celina, TX (US)
Assigned to 7-ELEVEN, INC., Irving, TX (US)
Filed by 7-Eleven, Inc., Irving, TX (US)
Filed on Nov. 19, 2021, as Appl. No. 17/455,892.
Application 17/455,892 is a continuation in part of application No. 17/362,261, filed on Jun. 29, 2021, granted, now 11,887,332.
Prior Publication US 2022/0414398 A1, Dec. 29, 2022
Int. Cl. G06F 18/214 (2023.01); G01G 21/22 (2006.01); G06F 18/22 (2023.01); G06K 7/14 (2006.01); G06T 7/62 (2017.01); G06V 10/44 (2022.01); G06V 10/56 (2022.01); G06V 20/00 (2022.01); H04N 13/207 (2018.01); H04N 13/271 (2018.01); H04N 23/90 (2023.01)
CPC G06F 18/2148 (2023.01) [G06F 18/22 (2023.01); G06K 7/1413 (2013.01); G06T 7/62 (2017.01); G06V 10/44 (2022.01); G06V 10/56 (2022.01); G06V 20/00 (2022.01); H04N 13/207 (2018.05); H04N 13/271 (2018.05); H04N 23/90 (2023.01); G01G 21/22 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for updating a training dataset of an item identification model, comprising:
a plurality of cameras, wherein each camera is configured to capture images of at least a portion of a platform;
a memory, operable to store a training dataset of an item identification model, wherein:
the item identification model is configured to identify items based at least in part upon images of the items; and
the training dataset comprises a plurality of images of different items; and
a processor, operably coupled with the memory, and configured to:
determine that a first item is not included in the training dataset;
in response to determining that the first item is not included in the training dataset:
obtain an identifier associated with the first item;
detect a triggering event at the platform, wherein the triggering event corresponds to a user placing the first item on the platform;
capture one or more first images from the first item using the plurality of cameras, wherein the one or more first images are captured from one or more angles;
for at least one image from among the one or more first images:
extract a first set of features associated with the first item from the at least one image, wherein each feature corresponds to a physical attribute of the first item;
associate the first item to the identifier and the first set of features; and
add a new entry to the training dataset, wherein the new entry represents the first item labeled with at least one of the identifier and the first set of features.