Automatic product mapping

• US 10,223,737 B2
• Filed: 12/28/2015
• Issued: 03/05/2019
• Est. Priority Date: 12/28/2015
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Srinivasan, Vijay, Sidhu, Shalinder S., Mori, Koichi
• Primary Examiner(s): Fadok, Mark A
• Application Number:
  US14/981,508
• Publication Number:
  US 20170186077A1
• Time in Patent Office: 1,163 Days
• CPC Class Codes: G06Q 30/0639 Item locations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A method comprising receiving different types of crowd-sourced information, the different types of crowd-sourced information relating to a physical store that a plurality of electronic devices have visited. The method further comprises determining a plurality of products available in the physical store based on the different types of crowd-sourced information, and correlating the different types of crowd-sourced information to determine at least one product location of at least one product of the plurality of products available. Each product location of each product identifies a location of the product within the physical store.

Claims

1. A method, comprising:

at a server including at least one hardware processor;

receiving different types of crowd-sourced information, wherein the different types of crowd-sourced information relate to a physical store that a plurality of electronic devices have visited;

determining a plurality of products available in the physical store based on the different types of crowd-sourced information;

correlating the different types of crowd-sourced information to determine at least one product location of at least one product of the plurality of products available, wherein each product location of each product identifies a location of the product within the physical store; and

providing at least one electronic device with a first map and a second map for the physical store, wherein the first map identifies the at least one product location determined, the second map identifies at least one signal strength for the at least one product location determined, and the first map and the second map facilitate real-time localization of the at least one electronic device in the physical store and improve real-time navigation to one or more products within the physical store.

2. The method of claim 1, wherein the different types of crowd-sourced information comprise:

product buying behavior information identifying at least one product buying behavior, each product buying behavior captured by an electronic device of the plurality of electronic devices during a visit to the physical store;

product search and scan behavior information identifying at least one product search or scan behavior, each product search or scan behavior captured by an electronic device of the plurality of electronic devices during a visit to the physical store;

a plurality of in-store locations, each in-store location identifying a location within the physical store where one of a product buying behavior or a product search or scan behavior is captured by an electronic device of the plurality of electronic devices during a visit to the physical store, and at least one of the plurality of in-store locations is based on noisy location data obtained from pedestrian dead reckoning based on sensor data captured by the plurality of electronic devices; and

product payment information identifying at least one payment transaction, each payment transaction associated with an electronic device of the plurality of electronic devices during a visit to the physical store.

3. The method of claim 2, wherein correlating the different types of crowd-sourced information comprises:

generating a set of constraints for at least one potential product location based on the product search and scan behavior information and at least one in-store location of the plurality of in-store locations; and

for at least one product of the plurality of products available, determining a product location of the product based on the set of constraints.

4. The method of claim 2, wherein correlating the different types of crowd-sourced information comprises:

generating a set of constraints for at least one potential product location based on the product payment information, the product buying behavior information and at least one in-store location of the plurality of in-store locations; and

for at least one product of the plurality of products available, determining a product location of the product based on the set of constraints.

5. The method of claim 1, further comprising:

at the server;

generating the first map.

6. The method of claim 1, further comprising:

at the server;

generating the second map based on the at least one product location determined, wherein the second map comprises at least one location signature for at least one location within the physical store associated with at least one behavior captured by the plurality of electronic devices in relation to the plurality of products available at the physical store, and each location signature is one of a sensor or radio signal strength signature.

7. The method of claim 2, wherein:

for at least one electronic device of the plurality of electronic devices, the product search and scan behavior information comprises data relating to a visit by the electronic device to the physical store, the data comprising at least one product or product category associated with at least one product search or scan behavior captured by the electronic device during the visit, and at least one timestamp indicating when the at least one product search or scan behavior is captured.

8. The method of claim 2, wherein a product search or scan behavior captured by an electronic device of the plurality of electronic devices during a visit to the physical store comprises using the electronic device to scan one of a product or a barcode for the product, and search for information relating to the product.

9. The method of claim 2, wherein a product search or scan behavior captured by an electronic device of the plurality of electronic devices during a visit to the physical store comprises using the electronic device to perform an online search for information relating to a product available at the physical store.

10. The method of claim 2, wherein:

for at least one electronic device of the plurality of electronic devices, the product buying behavior information comprises data relating to a visit by the electronic device to the physical store, the data comprising at least one timestamp indicating when the electronic device captures at least one product buying behavior, and at least one of height information and orientation information associated with the at least one product buying behavior;

the height information indicating where, on at least one display structure, at least one product associated with the at least one product buying behavior is placed; and

the orientation information indicating, for each of the at least one display structure, a side of an aisle the display structure is located at.

11. The method of claim 2, wherein a product buying behavior captured by an electronic device of the plurality of electronic devices during a visit to the physical store comprises at least one inferred gesture representing a selection of a product at the physical store and placement of the product in a shopping container, and the at least one inferred gesture is based on sensor data captured by at least one sensor device of the electronic device.

12. The method of claim 2, wherein:

for at least one electronic device of the plurality of electronic devices, the product payment information comprises data relating to a payment transaction associated with the electronic device during a visit to the physical store, the data comprising at least one product purchased via the payment transaction, and a timestamp indicating when the payment transaction occurred.

13. A system, comprising:

at least one storage device;

at least one processor; and

a non-transitory processor-readable memory device storing instructions that when executed by the at least one processor causes the at least one processor to perform operations including;

receiving different types of crowd-sourced information, wherein the different types of crowd-sourced information relate to a physical store that a plurality of electronic devices have visited;

determining a plurality of products available in the physical store based on the different types of crowd-sourced information;

correlating the different types of crowd-sourced information to determine at least one product location of at least one product of the plurality of products available, wherein each product location of each product identifies a location of the product within the physical store; and

providing at least one electronic device with a first map and a second map for the physical store, wherein the first map identifies the at least one product location determined, the second map identifies at least one signal strength for the at least one product location determined, and the first map and the second map facilitate real-time localization of the at least one electronic device in the physical store and improve real-time navigation to one or more products within the physical store.

14. The system of claim 13, wherein the different types of crowd-sourced information comprise:

product buying behavior information identifying at least one product buying behavior, each product buying behavior captured by an electronic device of the plurality of electronic devices during a visit to the physical store;

product search and scan behavior information identifying at least one product search or scan behavior, each product search or scan behavior captured by an electronic device of the plurality of electronic devices during a visit to the physical store;

a plurality of in-store locations, each in-store location identifying a location within the physical store where one of a product buying behavior or a product search or scan behavior is captured by an electronic device of the plurality of electronic devices during a visit to the physical store, and at least one of the plurality of in-store locations is based on noisy location data obtained from pedestrian dead reckoning based on sensor data captured by the plurality of electronic devices; and

product payment information identifying at least one payment transaction, each payment transaction associated with an electronic device of the plurality of electronic devices during a visit to the physical store.

15. The system of claim 14, wherein correlating the different types of crowd-sourced information comprises:

generating a set of constraints for at least one potential product location based on at least one of the different types of crowd-sourced information; and

for at least one product of the plurality of products available, determining a product location of the product based on the set of constraints.

16. The system of claim 13, wherein the operations further include:

generating the first map; and

generating the second map based on the at least one product location determined, wherein the second map comprises at least one location signature for at least one location within the physical store associated with at least one behavior captured by the plurality of electronic devices in relation to the plurality of products available at the physical store, and each location signature is one of a sensor or radio signal strength signature.

17. A non-transitory computer readable storage medium including instructions to perform a method comprising:

receiving different types of crowd-sourced information, wherein the different types of crowd-sourced information relate to a physical store that a plurality of electronic devices have visited, and the different types of crowd-sourced information are maintained on at least one storage device;

determining a plurality of products available in the physical store based on the different types of crowd-sourced information;

correlating the different types of crowd-sourced information to determine at least one product location of at least one product of the plurality of products available, wherein each product location of each product identifies a location of the product within the physical store; and

providing at least one electronic device with a first map and a second map for the physical store, wherein the first map identifies the at least one product location determined, the second map identifies at least one signal strength for the at least one product location determined, and the first map and the second map facilitate real-time localization of the at least one electronic device in the physical store and improve real-time navigation to one or more products within the physical store.

18. A method, comprising:

at an electronic device including at least one sensor device;

capturing different types of information associated with a visit to a physical store;

transmitting the different types of information to a server, wherein the different types of information are correlated at the server to determine at least one product location of at least one product available at the physical store; and

receiving a first map and a second map for the physical store from the server, wherein the first map identifies the at least one product location determined, the second map identifies at least one signal strength for the at least one product location determined, and the first map and the second map facilitate real-time localization of the electronic device in the physical store and improve real-time navigation to one or more products within the physical store.

19. The method of claim 18, wherein the different types of information comprise at least one of the following:

product buying behavior information identifying at least one product buying behavior, each product buying behavior captured by the at least one sensor device during the visit;

product search and scan behavior information identifying at least one product search or scan behavior, each product search or scan behavior captured by the at least one sensor device during the visit; and

a plurality of in-store locations, each in-store location identifying a location within the physical store where one of a product buying behavior or a product search or scan behavior is captured by the at least one sensor device during the visit, and at least one the plurality of in-store locations is based on noisy location data obtained from pedestrian dead reckoning based on sensor data captured by the electronic device.

20. The method of claim 18, further comprising:

at the electronic device;

determining a real-time location of the electronic device in the physical store based on the second map; and

providing navigation to a desired product in the physical store based on the real-time location and the first map;

wherein the second map comprises at least one location signature for at least one location within the physical store associated with at least one behavior captured by the electronic device in relation to the at least one product available at the physical store, and each location signature is one of a sensor or radio signal strength signature.