Pallet label check

Patent metadata

Field	Value
Publication number	US-2026099808-A1
Application number	US-202519042214-A
Country	US
Kind code	A1
Filing date	Jan 31, 2025
Priority date	Oct 9, 2024
Publication date	Apr 9, 2026
Grant date	—

Abstract

Examples provide a system for enhanced pallet label checking using computer vision and optical character recognition for faster and more efficient resolution of pallet label exceptions. The system includes a pallet manager component that obtains images of pallets from one or more image capture devices. Computer vision and machine learning is utilized to identify pallet labels on pallets which are missing or damaged such that the pallet labels are at least partially unreadable. An initial pallet label exception is created. The exceptions are assigned scores indicating a degree of confidence that the exceptions are accurate and require attention to resolve the issues associated with each label. The exceptions having high confidence scores are enhanced with customized label check instructions and real time images of the pallets. The enhanced pallet label exceptions assist users in locating pallets and resolving issues associated with pallet labels with greater speed and accuracy.

First claim

What is claimed is:

1 . A system for label checking, the system comprising:
a processor; and a computer-readable medium storing instructions that are operative upon execution by the processor to: identify an object of interest having a label that is missing or damaged using an image of the object, the image generated by an image capture device; generate an initial label exception associated with the object of interest having the label; assign a confidence score to the initial label exception, the confidence score indicating a degree of confidence associated with the initial label exception; classify the initial label exception according to a type of issue with the label responsive to the assigned confidence score exceeding a threshold score, the type of the issue comprising a missing label type of issue or a damaged label type of issue; create customized label check instructions based on the type of the issue associated with the label, wherein the customized label check instructions guide a user in locating the object of interest and correcting the type of the issue associated with the label; update the initial label exception with the customized label check instructions to create an enhanced label exception, the enhanced label exception comprising the customized label check instructions and a real-time image of the object of interest; and present the enhanced label exception with the customized label check instructions via a user interface device enabling improved efficiency locating and correcting the issue associated with the label.

2 . The system of claim 1 , wherein the instructions are further operative to:
assign a score for each initial label exception in a plurality of initial label exceptions associated with a plurality of objects within a retail facility; identify a set of high confidence initial label exceptions in the plurality of initial label exceptions using the score assigned to each initial label exception; and generate the customized label check instructions for checking labels on a set of objects associated with the set of high confidence initial label exceptions, wherein the customized label check instructions are presented to at least one user via a user interface device.

3 . The system of claim 1 , wherein the instructions are further operative to:
identify a plurality of confidence scores associated with a plurality of label exceptions having confidence scores within a threshold range; select initial label exceptions having a confidence score within the threshold range; and update each selected initial label exception with a classification of the type of issue associated with the label and customized label check instructions for resolving the type of the issue associated with each label.

4 . The system of claim 1 , wherein the instructions are further operative to:
identify a selected object having a label with text instructions identifying the object as an object to be excluded from inventory using optical character recognition; and filter the identified object from a plurality of objects undergoing label check.

5 . The system of claim 1 , wherein the instructions are further operative to:
generate a first set of customized label check instructions for resolving a first type of issue associated with a missing label, wherein the first set of customized label check instructions includes instructions for creating a new label for the object which is missing the label; generate a second set of customized label check instructions for resolving a second type of issue associated with an unreadable label, wherein the second set of customized label check instructions includes instructions for replacing a damaged label, wherein text on the damaged label is unreadable; and generate a third set of customized label check instructions for resolving a third type of issue associated with a partially damaged label which is present and at least partially readable, wherein the partially damaged label is at least partially unreadable.

6 . The system of claim 1 , wherein the instructions are further operative to:
update an inventory system using information associated with a replaced label responsive to receiving an indication that the issue associated with the enhanced label exception is resolved.

7 . The system of claim 1 , wherein the instructions are further operative to:
prompt a user to provide feedback regarding the enhanced label exception, wherein the feedback comprises an indication whether the issue associated with the enhanced label exception is a correct label exception accurately identifying a label issue or a false positive; and using the feedback associated with a plurality of enhanced label exceptions to retrain a label manager generating the enhanced label exceptions.

8 . A method for label checking, the method comprising:
obtaining an image of an object having an issue associated with a label that is missing or unreadable, the image generated by an image capture device; generating an initial label exception responsive to a determination the label is absent or unreadable; classifying the initial label exception according to a type of issue with the label; creating customized label check instructions based on classification of the type of the issue with the label, wherein the customized label check instructions guide a user in locating the object and correcting the type of issue associated with the label; creating an enhanced label exception including the customized label check instructions and a real-time image of the object; and providing the enhanced label exception with the customized label check instructions via a user interface device enabling improved efficiency locating and correcting the issue associated with the label.

9 . The method of claim 8 , further comprising:
assigning a score for each initial label exception in a plurality of initial label exceptions associated with a plurality of objects within a retail facility; identifying a set of high confidence initial label exceptions in the plurality of initial label exceptions using the score assigned to each initial label exception; and generating the customized label check instructions for checking labels on a set of s associated with the set of high confidence initial label exceptions, wherein the customized label check instructions are presented to at least one user via a user interface device.

10 . The method of claim 8 , further comprising:
identifying a plurality of confidence scores associated with a plurality of initial label exceptions having confidence scores within a threshold range; selecting a set of initial label exceptions from the plurality of initial label exceptions having a confidence score within the threshold range; and updating each selected initial label exception with a classification of the type of issue associated with the label and customized label check instructions for resolving the type of the issue associated with each label.

11 . The method of claim 8 , further comprising:
analyzing images of labels associated with a plurality of objects within a retail facility using optical character recognition; identifying a selected object having a label with text instructions identifying the object to be excluded from inventory; and filtering the identified object from the plurality of objects undergoing label check.

12 . The method of claim 8 , further comprising:
generating a set of customized label check instructions for resolving a first type of issue associated with a missing label, wherein the customized label check instructions includes instructions for creating a new label.

Assignees

• Walmart Apollo Llc

Inventors

• Zhao Chongrui
• Rader Eric W
• Griffith Mitchell Thomas
• Benson Tracy E
• Duan Zhaoliang
• Zhang Han
• Zhang Lingfeng
• Yuan Mingquan
• Robinson William Craig
• Jade Avinash M
• Ellison Benjamin
• Huang Zhiwei
• Siler Elizabeth Ann

Classifications

• G06V30/12

  Detection or correction of errors, e.g. by rescanning the pattern · CPC title

• G06Q10/06311

  Scheduling, planning or task assignment for a person or group · CPC title

• G06V2201/07

  Target detection · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06Q10/087 Primary

  Inventory or stock management, e.g. order filling, procurement or balancing against orders · CPC title