Granted Patent B2

US 12,283,201 · App. 17/563,322 · Granted Apr 22, 2025

Inventors: Yair Adato (Kfar Ben Nun, IL); Nir Hemed (Tel Aviv, IL); Dolev Pomeranz (Hod Hasharon, IL)

Assignee: Trax Technology Solutions Pte Ltd.

G09F13/045G01G19/52G06Q10/063114G06Q10/087G06Q30/0201G06Q30/0223G06Q30/0238G06Q30/0241G06Q30/0601G06Q30/0625G06V20/68G06V40/10G09F3/204G09F3/208G09F13/12

Abstract

Claims (67)

1. A non-transitory computer-readable medium including instructions that when executed by a processor cause the processor to perform a method for selecting items for presentation on electronic visual displays in retail stores, the method comprising:

obtaining a plurality of images of products in a retail store captured using at least one image sensor, wherein the plurality of images comprises at least a first image corresponding to a first point in time and a second image corresponding to a second point in time, wherein the first point in time is earlier than the second point in time;

with a trained machine learning model, analyzing the first image to determine whether products of a particular product type are available at the first point in time;

based on the determination that products of the particular product type are available at the first point in time, selecting to display the particular product type on an electronic visual display in the retail store;

in response to the selection to display the particular product type, causing the electronic visual display to display the particular product type;

with the trained machine learning model, in response to a user removing a product of the particular product type, analyzing the second image to determine that products of the particular product type are not available at the second point in time;

based on the determination that products of the particular product type are not available at the second point in time, selecting not to display the particular product type on the electronic visual display;

and

in response to the selection not to display the particular product type, causing the electronic visual display not to display the particular product type.

2. The non-transitory computer-readable medium of claim 1 , wherein the method further comprises:

in response to a determination that products of the particular product type are missing at the first point in time and a determination that products of the particular product type are missing at the second point in time, selecting not to display the particular product type on the electronic visual display in the retail store; and

in response to at least one of a determination that products of the particular product type are available at the first point in time and a determination that products of the particular product type are available at the second point in time, selecting to display the particular product type on the electronic visual display in the retail store.

3. The non-transitory computer-readable medium of claim 1 , wherein the method further comprises:

in response to a determination that products of the particular product type are missing at the first point in time and a determination that products of the particular product type are missing at the second point in time, selecting not to display the particular product type on the electronic visual display in the retail store; and

in response to at least one of a determination that products of the particular product type are available at the first point in time and a determination that products of the particular product type are available at the second point in time, selecting to display the particular product type on the electronic visual display in the retail store.

4. The non-transitory computer-readable medium of claim 1 , wherein the plurality of images comprises a preceding image corresponding to a preceding point in time, wherein the preceding point in time is earlier than the first point in time, and wherein the method further comprises:

analyzing the preceding image to determine whether products of the particular product type are available at the preceding point in time; and

further basing the selection of whether to display the particular product type on the electronic visual display in the retail store on the determination of whether products of the particular product type are available at the preceding point in time.

5. The non-transitory computer-readable medium of claim 4 , wherein the method further comprises:

in response to a determination that products of the particular product type are missing at the preceding point in time, a determination that products of the particular product type are available at the first point in time and a determination that products of the particular product type are missing at the second point in time, selecting not to display the particular product type on the electronic visual display in the retail store; and

in response to a determination that products of the particular product type are available at the preceding point in time, the determination that products of the particular product type are available at the first point in time and the determination that products of the particular product type are missing at the second point in time, selecting not to display the particular product type on the electronic visual display in the retail store.

6. The non-transitory computer-readable medium of claim 4 , wherein the method further comprises:

in response to a determination that products of the particular product type are missing at the preceding point in time, a determination that products of the particular product type are missing at the first point in time and a determination that products of the particular product type are missing at the second point in time, selecting not to display the particular product type on the electronic visual display in the retail store; and

in response to at least one of a determination that products of the particular product type are available at the preceding point in time, a determination that products of the particular product type are available at the first point in time and the determination that products of the particular product type are available at the second point in time, selecting to display the particular product type on the electronic visual display in the retail store.

7. The non-transitory computer-readable medium of claim 4 , wherein the method further comprises:

in response to a determination that products of the particular product type are missing at the preceding point in time, a determination that products of the particular product type are missing at the first point in time and a determination that products of the particular product type are missing at the second point in time, selecting not to display the particular product type on the electronic visual display in the retail store; and

in response to at least one of a determination that products of the particular product type are available at the preceding point in time, a determination that products of the particular product type are available at the first point in time and the determination that products of the particular product type are available at the second point in time, selecting to display the particular product type on the electronic visual display in the retail store.

8. The non-transitory computer-readable medium of claim 4 , wherein the method further comprises:

in response to a determination that products of the particular product type are missing at the preceding point in time, a determination that products of the particular product type are available at the first point in time and a determination that products of the particular product type are missing at the second point in time, selecting to display the particular product type on the electronic visual display in the retail store; and

in response to at least one of a determination that products of the particular product type are available at the preceding point in time and a determination that products of the particular product type are available at the second point in time, selecting to display the particular product type on the electronic visual display in the retail store.

9. The non-transitory computer-readable medium of claim 1 , wherein the selection of whether to display the particular product type on the electronic visual display in the retail store is further based on an elapsed time between the first point in time and the second point in time.

10. The non-transitory computer-readable medium of claim 1 , wherein the selection of whether to display the particular product type on the electronic visual display in the retail store is further based on an elapsed time since the second point in time.

11. The non-transitory computer-readable medium of claim 1 , wherein the selection of whether to display the particular product type on the electronic visual display in the retail store is further based on information related to a person in a vicinity of the electronic visual display.

12. The non-transitory computer-readable medium of claim 1 , wherein the selection of whether to display the particular product type on the electronic visual display in the retail store is further based on a time of day.

13. The non-transitory computer-readable medium of claim 1 , wherein the electronic visual display is connected to a shelf in the retail store.

14. The non-transitory computer-readable medium of claim 1 , wherein the electronic visual display is connected to a door of a retail storage container in the retail store.

15. The non-transitory computer-readable medium of claim 1 , wherein the electronic visual display is part of a personal device of a store associate.

16. The non-transitory computer-readable medium of claim 1 , wherein the electronic visual display is part of a personal device of a customer.

17. The non-transitory computer-readable medium of claim 1 , wherein the method further comprises:

obtaining data captured at the first point in time using a plurality of sensors positioned on a shelf in the retail store and configured to be positioned between the shelf and products positioned on the shelf;

obtaining data captured at the second point in time using the plurality of sensors;

basing the determination of whether products of the particular product type are available at the first point in time on an analysis of the data captured at the first point in time using the plurality of sensors; and

basing the determination of whether products of the particular product type are available at the second point in time on an analysis of the data captured at the second point in time using the plurality of sensors.

18. The non-transitory computer-readable medium of claim 1 , wherein the method further comprises:

obtaining weight data captured at the first point in time using a weight sensor corresponding to at least part of a shelf in the retail store;

obtaining weight data captured at the second point in time using the weight sensor;

basing the determination of whether products of the particular product type are available at the first point in time on an analysis of the weight data captured at the first point in time using the weight sensor; and

basing the determination of whether products of the particular product type are available at the second point in time on an analysis of the weight data captured at the second point in time using the weight sensor.

19. A method for selecting items for presentation on electronic visual displays in retail stores, the method comprising:

obtaining a plurality of images of products in a retail store captured using at least one image sensor, wherein the plurality of images comprises at least a first image corresponding to a first point in time and a second image corresponding to a second point in time, wherein the first point in time is earlier than the second point in time;

with a trained machine learning model, analyzing the first image to determine whether products of a particular product type are available at the first point in time;

based on the determination that products of the particular product type are available at the first point in time, selecting to display the particular product type on an electronic visual display in the retail store;

in response to the selection to display the particular product type, causing the electronic visual display to display the particular product type;

with the trained machine learning model, in response to a user removing a product of the particular product type, analyzing the second image to determine that products of the particular product type are not available at the second point in time;

based on the determination that products of the particular product type are not available at the second point in time, selecting not to display the particular product type on the electronic visual display in the retail store;

and

in response to a selection not to display the particular product type, causing the electronic visual display not to display the particular product type.

20. A system for selecting items for presentation on electronic visual displays in retail stores, the system comprising:

at least one processor configured to:

obtain a plurality of images of products in a retail store captured using at least one image sensor, wherein the plurality of images comprises at least a first image corresponding to a first point in time and a second image corresponding to a second point in time, wherein the first point in time is earlier than the second point in time;

with a trained machine learning model, analyze the first image to determine whether products of a particular product type are available at the first point in time;

based on the determination that products of the particular product type are available at the first point in time, selecting to display the particular product type on an electronic visual display in the retail store;

in response to the selection to display the particular product type, causing the electronic visual display to display the particular product type;

with the trained machine learning model, in response to a user removing a product of the particular product type, analyze the second image to determine that products of the particular product type are not available at the second point in time;

based on the determination that products of the particular product type are not available at the second point in time, select not to display a particular product type on an electronic visual display in the retail store;

and

in response to the selection not to display the particular product type, causing the electronic visual display not to display the particular product type.

Assignments (3)

Continuity (3)

References Cited (13)

Cited By (2)

US 12,518,537 US 12,573,237