Machine learning inventory management

Patent metadata

Field	Value
Publication number	US-2019080277-A1
Application number	US-201715704534-A
Country	US
Kind code	A1
Filing date	Sep 14, 2017
Priority date	Sep 14, 2017
Publication date	Mar 14, 2019
Grant date	—

Abstract

Systems and methods for machine learning inventory management. The methods comprise: capturing images by a plurality of image capture devices of different types (e.g., visual camera, 3D camera and/or thermal camera); reading item identification codes for items represented in the images; and using at least a first portion of the images and known physical appearances of a plurality of items by a machine learning algorithm to learn relationships between the items represented in the images and the item identification codes. At least a second portion of the images are used to learn various types of information that is useful for inventory management (e.g., changes in inventory amounts for display equipment, changes in equipment cleanliness, changes in inventory packaging, item misplacements, etc.).

First claim

We claim:

1 . A method for machine learning inventory management, comprising:
capturing images by a plurality of image capture devices of different types; reading item identification codes for items represented in the images; and using at least a first portion of the images and known physical appearances of a plurality of items by a machine learning algorithm to learn relationships between the items represented in the images and the item identification codes.

2 . The method according to claim 1 , wherein the plurality of image capture devices comprise at least one of a visual camera, a 3D camera, and a thermal camera.

3 . The method according to claim 1 , further comprising using Point of Sale (“POS”) transaction information to learn patterns of changes in amounts of inventory over time.

4 . The method according to claim 1 , further comprising using at least a second portion of the images which were captured at a Point of Sale (“POS”) to identify items represented therein based on the learned relationships between the items represented in the first portion of images and the item identification codes.

5 . The method according to claim 1 , further comprising using the images, the known physical appearances, the item identification codes, and Point of Sale (“POS”) transaction information to detect theft and learn patterns of theft over time.

6 . The method according to claim 1 , further comprising analyzing the images to learn changes in item packaging.

7 . The method according to claim 6 , wherein the changes in image packaging are further learned based on at least one of the item identification codes, Point of Sale (“POS”) transaction information, and stored information for display equipment inventory.

8 . The method according to claim 1 , further comprising using at least a second portion of the images to learn at least one of a change in a type of item disposed on a piece of equipment and a change in an amount of an item disposed on a piece of equipment.

9 . The method according to claim 1 , further comprising using at least a second portion of the images to learn conditions of equipment or areas adjacent to the equipment.

10 . The method according to claim 1 , further comprising using at least a second portion of the images to learn individuals' interactions with equipment and inventory disposed on the equipment.

11 . The method according to claim 1 , further comprising using at least a second portion of the images to learn when equipment has been moved to a given location, and resetting learned information for the equipment.

12 . The method according to claim 1 , further comprising using at least a second portion of the images to learn when an item has been misplaced.

13 . A system, comprising:
a processor; and a non-transitory computer-readable storage medium comprising programming instructions that are configured to cause the processor to implement a method for machine learning inventory management, wherein the programming instructions comprise instructions to:
obtain images captured by a plurality of image capture devices of different types;
obtain item identification codes read for items represented in the images; and
use at least a first portion of the images and known physical appearances of a plurality of items by a machine learning algorithm to learn relationships between the items represented in the images and the item identification codes.

14 . The system according to claim 12 , wherein the plurality of image capture devices comprise a visual camera, a 3D camera, and a thermal camera.

15 . The system according to claim 12 , wherein the programming instructions further comprise instructions to use Point of Sale (“POS”) transaction information to learn patterns of changes in amounts of inventory for given items over time.

16 . The system according to claim 12 , wherein the programming instructions further comprise instructions to use at least a second portion of the images which were captured at a Point of Sale (“POS”) to identify items represented therein based on the learned relationships between the items represented in the first portion of images and the item identification codes.

17 . The system according to claim 12 , wherein the programming instructions further comprise instructions to use the images, the known physical appearances, the item identification codes, and Point of Sale (“POS”) transaction information to detect theft and learn patterns of theft over time.

18 . The system according to claim 12 , wherein the programming instructions further comprise instructions to analyze the images to learn changes in item packaging.

19 . The system according to claim 18 , wherein the changes in image packaging are further learned based on at least one of the item identification codes, Point of Sale (“POS”) transaction information, and stored information for display equipment inventory.

20 . The system according to claim 12 , wherein the programming instructions further comprise instructions to use at least a second portion of the images to learn at least one of a change in a type of item disposed on a piece of equipment and a change in an amount of an item disposed on a piece of equipment.

21 . The system according to claim 12 , wherein the programming instructions further comprise instructions to use at least a second portion of the images to learn conditions of equipment or areas adjacent to the equipment.

22 . The system according to claim 12 , wherein the programming instructions further comprise instructions to use at least a second portion of the images to learn individuals' interactions with equipment and inventory disposed on the equipment.

23 . The system according to claim 12 , wherein the programming instructions further comprise instructions to use at least a second portion of the images to learn when equipment has been moved to a given location, and resetting learned information for the equipment.

24 . The system according to claim 12 , wherein the programming instructions further comprise instructions to use at least a second portion of the images to learn when an item has been misplaced.

Assignees

• Trivelpiece Steve E
• Trivelpiece Craig E
• Marchesano Matt
• Tarrant Declan
• Wicks Brian
• Tyco Fire & Security Gmbh

Inventors

• Trivelpiece Steve E
• Trivelpiece Craig E
• Marchesano Matt
• Tarrant Declan
• Wicks Brian

Classifications

• G06N20/00

  Machine learning · CPC title

• G06Q20/3224

  Transactions dependent on location of M-devices · CPC title

• G06Q20/3278

  RFID or NFC payments by means of M-devices · CPC title

• G06Q20/203

  Inventory monitoring · CPC title

• G06Q20/208

  Input by product or record sensing, e.g. weighing or scanner processing · CPC title