Systems and methods of verifying price tag label-product pairings

Patent metadata

Field	Value
Publication number	US-12367457-B2
Application number	US-202217983773-A
Country	US
Kind code	B2
Filing date	Nov 9, 2022
Priority date	Nov 9, 2022
Publication date	Jul 22, 2025
Grant date	Jul 22, 2025

Abstract

Systems and methods of verifying pairings of price tag labels and products at a product storage facility include an image capture device that moves about and captures images of product storage structures at the product storage facility, and a database that stores inventory data associated with the products stocked at the product storage facility. A computing device processes the images to extract one or more characters from the price tag labels and products detected in the images, correlates the extracted characters to the inventory data to identify a product code and a product name that matches the characters extracted from the price tag labels and the products. If the characters extracted from the price tag and from the on-shelf product to which the price tag label is allocated match, the database is updated to reflect that the price tag label is properly allocated to the appropriate on-shelf product.

First claim

What is claimed is:

1. A system for verifying pairings of on-shelf tag labels and products at a product storage facility, the system comprising:
an electronic database configured to store inventory data for the product storage facility;
a device configured for movement throughout the product storage facility;
a single camera incorporated into the device, the single camera configured to capture a single image of a product storage structure in the product storage facility, wherein the single camera has a field of view that is wide enough to capture the entirety of the product storage structure in the single image, and wherein the product storage structure is a free-standing product display that is independent from other product storage structures in the product storage facility; and
a computing device communicatively coupled to the single camera, the computing device configured to:
detect, in the single image, a price tag label affixed to the product storage structure and a product arranged on the product storage structure;
extract character(s) from the product in the single image and character(s) from the price tag label in the single image, wherein the character(s) extracted from the product are independent from a bar code on the product and the character(s) extracted from the price tag label are independent from a bar code on the price tag label;
determine, based on the character(s) extracted from the price tag label, a product code associated with the price tag label, the product code being identified without referencing the bar code on the price tag label;
determine, based on the character(s) extracted from the product, a keyword instance indicating both a keyword on the product and a specific location of the keyword on the product;
correlate the keyword instance with the inventory data stored in the electronic database to identify a product name associated with the product, the product name being identified without referencing the bar code on the product;
determine that the product name associated with the product matches the product code associated with the price tag label; and
transmit, to the electronic database, a signal indicating that the price tag label is properly allocated to the product storage structure responsive to determining that the product name associated with the product matches the product code associated with the price tag label.

2. The system of claim 1 , wherein the computing device is further configured to extract graphical object(s) from the product detected in the single image, the product name being identified by correlating both the graphical object(s) extracted from the product and the keyword instance with the inventory data stored in the electronic database.

3. The system of claim 2 , wherein the graphical object(s) extracted from the product are independent from the bar code on the product.

4. The system of claim 2 , wherein the graphical object(s) extracted from the product are independent from the character(s) extracted from the product.

5. The system of claim 2 , wherein the computing device determines the keyword instance by generating a virtual boundary around the character(s) extracted from the product and performing optical character recognition within the virtual boundary to identify the keyword.

6. The system of claim 5 , wherein the virtual boundary excludes the graphical object(s) extracted from the product and the bar code on the product.

7. A method for verifying pairings of on-shelf labels and products at a product storage facility, the method comprising:
capturing, via a single camera incorporated into a device configured for movement throughout the product storage facility, a single image of a product storage structure in the product storage facility, wherein the single camera has a field of view that is wide enough to capture the entirety of the product storage structure in the single image, and wherein the product storage structure is a free-standing product display that is independent from other product storage structures in the product storage facility;
detecting, in the single image, a price tag label affixed to the product storage structure and a product arranged on the product storage structure;
extracting character(s) from the product in the single image and character(s) from the price tag label in the single image, wherein the character(s) extracted from the product are independent from a bar code on the product and the character(s) extracted from the price tag label are independent from a bar code on the price tag label;
determining, based on the character(s) extracted from the price tag label, a product code associated with the price tag label, the product code being identified without referencing the bar code on the price tag label;
determining, based on the character(s) extracted from the product, a keyword instance indicating both a keyword on the product and a specific location of the keyword on the product;
correlating the keyword instance with inventory data stored in an electronic database to identify a product name associated with the product, the product name being identified without referencing the bar code on the product;
determining that the product name associated with the product matches the product code associated with the price tag label; and
transmitting, to the electronic database, a signal indicating that the price tag label is properly allocated to the product storage structure responsive to determining that product name associated with the product matches the product code associated with the price tag label.

8. The method of claim 7 , further comprising extracting graphical object(s) from the product detected in the single image, the product name being identified by correlating both the graphical object(s) extracted from the product and the keyword instance with the inventory data stored in the electronic database.

9. The method of claim 8 , wherein the graphical object(s) extracted from the product are independent from the bar code on the product.

10. The method of claim 8 , wherein the graphical object(s) extracted from the product are independent from the character(s) extracted from the product.

11. The method of claim 8 , wherein determining the keyword instance comprises generating a virtual boundary around the character(s) extracted from the product and performing optical character recognition within the virtual boundary to identify the keyword.

12. The method of claim 11 , wherein the virtual boundary excludes the graphical object(s) extracted from the product and the bar code on the product.

13. A method for verifying pairings of on-shelf labels and products at a product storage facility, the method comprising:
receiving a single image of a product storage structure in the product storage facility, the single image having been captured by a single camera having a field of view wide enough to capture the entirety of the product storage structure in the single image, wherein the single camera is incorporated into a device moving throughout the product storage facility, and wherein the product storage structure is a free-standing product display that is independent from other product storage structures in the product storage facility;
detecting, in the single image, a price tag label affixed to the product storage structure and a product arranged on the product storage structure;
extracting character(s) from the product in the single image and character(s) from the price tag label in the single image, wherein the character(s) extracted from the product are independent from a bar code on the product and the character(s) extracted from the price tag label are i

Assignees

• Walmart Apollo Llc

Inventors

• Zhang Lingfeng
• Wang Wei
• Jade Avinash Madhusudanrao
• Balusu Raghava
• Yuan Mingquan
• Wang Jing
• Zhang Han
• Duan Zhaoliang
• Robinson Jr William Craig
• Ellison Benjamin R
• Lobo Paul Lewis

Classifications

• G06V30/19007

  Matching; Proximity measures · CPC title

• G06V30/30

  based on the type of data · CPC title

• G06V20/50

  Context or environment of the image · CPC title

• G06V30/1801

  Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections (extracting features by contour coding G06V30/182) · CPC title

• G06V30/148

  Segmentation of character regions · CPC title