Clustering of items with heterogeneous data points

Patent metadata

Field	Value
Publication number	US-2024119409-A1
Application number	US-202217963903-A
Country	US
Kind code	A1
Filing date	Oct 11, 2022
Priority date	Oct 11, 2022
Publication date	Apr 11, 2024
Grant date	—

Abstract

In some embodiments, apparatuses and methods are provided herein useful to updating inventory of products. In some embodiments, there is provided a system for updating inventory of products including a database; at least one image capture device; and a control circuit. The control circuit is configured to: process an image by: detecting units of one or more products in the image; grouping each detected unit into one or more clusters based on at least one of textual similarities, visual similarities, geometrical similarities, or relative spatial distance; detecting a product identifier for each cluster; identifying a product corresponding to the detected product identifier of each cluster; and counting the detected units associated with each cluster. The control circuit is configured to cause an update to the inventory of products in the database based on the counted detected units of each cluster.

First claim

What is claimed is:

1 . A system for updating inventory of products at a product storage facility, the system comprising:
an electronic database configured to store data corresponding to the inventory of products; at least one image capture device configured to capture one or more images of an area having one or more products at the product storage facility; and a control circuit coupled to the at least one image capture device, the control circuit configured to:
process an image of the one or more images by:
detecting units of the one or more products in the image;
grouping each detected unit into one or more clusters based on at least one of textual similarities, visual similarities, geometrical similarities, or relative spatial distance;
detecting a product identifier for each cluster of the one or more clusters;
identifying a product corresponding to the detected product identifier of each cluster; and
counting the detected units associated with each cluster; and

cause an update to the inventory of products in the electronic database based on the counted detected units of each cluster.

2 . The system of claim 1 , wherein the at least one image capture device is mounted on a motorized robotic unit.

3 . The system of claim 1 , wherein the area comprises a rack, a pallet, and a shelving unit.

4 . The system of claim 1 , wherein the product identifier comprises a barcode and a QR code.

5 . The system of claim 1 , wherein the product storage facility comprises a product distribution center, a fulfillment center, and a retail store.

6 . The system of claim 1 , wherein the control circuit is further configured to:
output each detected product identifier and a corresponding count of the detected units of the product associated with the detected product identifier; and cause an additional control circuit to update the inventory of products based on the detected product identifier and the count.

7 . The system of claim 1 , wherein the control circuit is further configured to:
determine that one or more product identifiers have been detected in a first cluster of the one or more clusters; determine that the one or more product identifiers correspond to a first product identifier; in response to the determination that the one or more product identifiers correspond to the first product identifier, associate each of the detected units of the first cluster with a first product corresponding to the first product identifier; and cause an update to an inventory of the first product in the electronic database based on a count of the detected units of the first cluster.

8 . The system of claim 1 , wherein the control circuit is further configured to:
determine that a plurality of product identifiers have been detected in a first cluster of the one or more clusters; determine that a first product identifier of the plurality of product identifiers that have been detected the most relative to other product identifiers of the plurality of product identifiers; in response to the determination that the first product identifier of the plurality of product identifiers have been detected the most, associate each of the detected units of the first cluster with a first product corresponding to the first product identifier; and trigger an alert corresponding to a request to verify that the detected units of the first cluster is associated with the first product identifier.

9 . The system of claim 1 , wherein the control circuit is further configured to:
determine that no product identifiers have been detected in a first cluster of the one or more clusters; in response to the determination that no product identifiers have been detected in the first cluster, associate each of the detected units of the first cluster with a temporary product identifier; and in response to a determination that the first cluster has been associated with the temporary product identifier, trigger an alert requesting verification of a correct product identifier to associate with each of the detected units of the first cluster.

10 . The system of claim 1 , further comprising a trained machine learning model comprising a computer program code stored in a memory, the machine learning model is executed by the control circuit to process the image.

11 . A method for updating inventory of products at a product storage facility, the method comprising:
processing, by a control circuit, an image of one or more images of an area having one or more products at the product storage facility, the one or more images are captured by at least one image capture device, the processing of the image comprising:
detecting units of the one or more products in the image;
grouping each detected unit into one or more clusters based on at least one of textual similarities, visual similarities, geometrical similarities, or relative spatial distance;
detecting a product identifier for each cluster of the one or more clusters;
identifying a product corresponding to the detected product identifier of each cluster; and
counting the detected units associated with each cluster; and
causing, by the control circuit, an update to inventory of products stored in an electronic database based on the counted detected units of each cluster.

12 . The method of claim 11 , wherein the at least one image capture device is mounted on a motorized robotic unit.

13 . The method of claim 11 , wherein the area comprises a rack, a pallet, and a shelving unit.

14 . The method of claim 11 , wherein the product identifier comprises a barcode and a QR code.

15 . The method of claim 11 , wherein the product storage facility comprises a product distribution center, a fulfillment center, and a retail store.

16 . The method of claim 11 , further comprising:
outputting, by the control circuit. each detected product identifier and a corresponding count of the detected units of the product associated with the detected product identifier; and updating, by an additional control circuit, the inventory of products based on the detected product identifier and the count.

17 . The method of claim 11 , further comprising:
determining, by the control circuit, that one or more product identifiers have been detected in a first cluster of the one or more clusters; determining, by the control circuit, that the one or more product identifiers correspond to a first product identifier; in response to the determination that the one or more product identifiers correspond to the first product identifier, associating, by the control circuit, each of the detected units of the first cluster with a first product corresponding to the first product identifier; and causing, by the control circuit, an update to an inventory of the first product in the electronic database based on a count of the detected units of the first cluster.

18 . The method of claim 11 , further comprising:
determining, by the control circuit, that a plurality of product identifiers have been detected in a first cluster of the one or more clusters; determining, by the control circuit, that a first product identifier of the plurality of product identifiers that have been detected the most relative to other product identifiers of the plurality of product identifiers; in response to the determination that the first product identifier of the plurality of product identifiers have been detected the most, associating, by the control circuit, each of the detected units of the first cluster with a first product corresponding to the first produ

Assignees

• Walmart Apollo Llc

Inventors

• Balusu Raghava
• Jade Avinash M
• Zhang Lingfeng
• Muktevi Srinivas
• Jhunjhunwala Amit

Classifications

• G06Q10/08772

  Inventory counting methods · CPC title

• G06F16/55 Primary

  Clustering; Classification · CPC title

• G06Q10/087 Primary

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