Transitioning inventory search from large geographic area to immediate personal area

Patent metadata

Field	Value
Publication number	US-12373782-B2
Application number	US-202318348134-A
Country	US
Kind code	B2
Filing date	Jul 6, 2023
Priority date	Jun 20, 2018
Publication date	Jul 29, 2025
Grant date	Jul 29, 2025

Abstract

In one aspect, the present disclosure relates to a method for improved efficiency of an inventory management system. The method can include: performing a first inventory search of inventory data stored in a database using search criteria; receiving, from a beacon sensor, inventory data broadcast from a plurality of beacons; performing a second inventory search by correlating the inventory data broadcast from the plurality of beacons with results of the first inventory search; receiving image data from a camera; performing image classification on the image data to determine one or more class labels for an inventory item within the field-of-view of the camera; performing a third inventory search by correlating the class labels with results of the second inventory search; and presenting results of the third inventory search to a user.

First claim

The invention claimed is:

1. A method for improved efficiency of an inventory management system, the method comprising:
detecting interaction with an application executing on a user device;
upon the interaction with the application and without further initiating from a user of the user device, automatically initiating a first inventory search of inventory data stored in a database using location information provided by the user device, wherein the first inventory search comprises at least a geospatial search of the inventory data using the location information;
receiving image data from a camera associated with the user device, the image data comprising image data for an inventory item within a field-of-view of the camera;
determining a class label for the inventory item within the field-of-view of the camera;
performing a second inventory search by correlating the class label with results of the first inventory search; and
providing for display on the user device, results of the second inventory search, the provided results comprising inventory data corresponding to at least one search result from the first inventory search.

2. The method of claim 1 , wherein the inventory data comprises a unique identifier for each inventory item in the inventory data.

3. The method of claim 1 , wherein determining, by the user device, the class label for the inventory item within the field-of-view of the camera comprises:
performing image classification on the image data to determine the class label.

4. The method of claim 1 , wherein performing the second inventory search by correlating class labels with the results of the second inventory search comprises:
matching the class labels against descriptive information for each inventory item in the second inventory search.

5. The method of claim 4 , further comprising:
determining that there are multiple potential matches between the class labels and the descriptive information; and
based on the determining, applying one or more heuristics to determine a best match inventory item.

6. The method of claim 1 , further comprising:
receiving the location information from beacon data co-located with the user device.

7. The method of claim 1 , comprising:
storing the results of the first inventory search to a non-volatile memory of the user device, wherein presenting the results of the second inventory search comprises using the results of the first inventory search stored to the non-volatile memory of the user device.

8. A non-transitory computer readable medium having instructions stored thereon, which, when executed by a processor, causes a system to perform operations comprising:
automatically initiating, without input from a user, a first inventory search of inventory data stored in a database using location information of the user, wherein the first inventory search comprises at least a geospatial search of the inventory data using the location information;
receiving image data from a camera associated with the system, the image data comprising image data for an inventory item within a field-of-view of the camera;
determining a class label for the inventory item within the field-of-view of the camera;
performing a second inventory search by correlating the class label with results of the first inventory search; and
providing for display, results of the second inventory search, the provided results comprising inventory data corresponding to at least one search result from the first inventory search.

9. The non-transitory computer readable medium of claim 8 , wherein the inventory data comprises a unique identifier for each inventory item in the inventory data.

10. The non-transitory computer readable medium of claim 8 , wherein determining the class label for the inventory item within the field-of-view of the camera comprises:
performing image classification on the image data to determine the class label.

11. The non-transitory computer readable medium of claim 8 , wherein performing the second inventory search by correlating class labels with the results of the second inventory search comprises:
matching the class labels against descriptive information for each inventory item in the second inventory search.

12. The non-transitory computer readable medium of claim 11 , further comprising:
determining that there are multiple potential matches between the class labels and the descriptive information; and
based on the determining, applying one or more heuristics to determine a best match inventory item.

13. The non-transitory computer readable medium of claim 8 , further comprising:
receiving the location information from beacon data co-located with the system.

14. The non-transitory computer readable medium of claim 8 , comprising:
storing the results of the first inventory search, wherein presenting the results of the second inventory search comprises using the stored results of the first inventory search.

15. A system comprising:
a processor; and
a memory having programming instructions stored thereon, which, when executed by the processor causes the system to perform operations, comprising:
detecting interaction with an application;
upon the interaction with the application and without further initiating from a user of the system, automatically initiating a first inventory search of inventory data stored in a database using location information of the user, wherein the first inventory search comprises at least a geospatial search of the inventory data using the location information;
receiving image data from a camera associated with the system, the image data comprising image data for an inventory item within a field-of-view of the camera;
determining a type of inventory item corresponding to the inventory item within the field-of-view of the camera;
performing a second inventory search by correlating the type of inventory item with results of the first inventory search; and
providing, for display, results of the second inventory search, the provided results comprising inventory data corresponding to at least one search result from the first inventory search.

16. The system of claim 15 , wherein the inventory data comprises a unique identifier for each inventory item in the inventory data.

17. The system of claim 15 , wherein determining the type of inventory item corresponding to the inventory item within the field-of-view of the camera comprises:
performing image classification on the image data using one or more computer vision techniques.

18. The system of claim 15 , wherein performing the second inventory search by correlating the type of inventory item with the results of the second inventory search comprises:
comparing the type of inventory item to descriptive information for each inventory item in the second inventory search.

19. The system of claim 18 , further comprising:
determining that there are multiple potential matches between the type of inventory item and the descriptive information; and
based on the determining, applying one or more heuristics to determine a best match inventory item.

20. The system of claim 15 , wherein the operations further comprise:
storing the results of the first inventory search to a non-volatile memory of the system, wherein presenting the results of the second inventory search comprises using the results of the first inventory search stored to the non-volatile memory of the system.

Assignees

• Capital One Services Llc

Inventors

• Hoover Jason
• Tang Qiaochu
• Price Micah
• Dagley Geoffrey
• Wylie Stephen

Classifications

• G06V10/764

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

• G06F18/24

  Classification techniques · CPC title

• G06F16/245

  Query processing · CPC title

• G06F16/29

  Geographical information databases · CPC title

• G06Q10/087 Primary

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