Associating items based at least in part on physical location information

• US 9,799,065 B1
• Filed: 06/16/2014
• Issued: 10/24/2017
• Est. Priority Date: 06/16/2014
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Dorner, Charles Shearer
• Primary Examiner(s): Rosen, Nicholas D
• Application Number:
  US14/305,833
• Time in Patent Office: 1,226 Days
• Field of Search: None
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0639 Item locations

Abstract

Systems and methods are provided for associating items based at least in part on physical location information that includes a physical location of at least two items. By associating items based at least in part on physical location information, associations among items may be identified that would otherwise be difficult to determine without usage of physical location information. In one embodiment, physical location information of various items may be collected by electronically recording the physical location of the items in a physical retail store. A degree of association may be derived from an analysis of the physical proximity between the items. The determined association information may later be used to recommend items to a user or for other purposes.

Claims

1. A system comprising:

an electronic data store configured to at least store item identification information associated with each item of a plurality of items listed in an electronic catalog; and

a computing device including one or more processors, the computing device in communication with the electronic data store and configured to at least;

receive a set of physical location information that identifies physical locations of a plurality of tags identified by a sensor within a first physical retail store, wherein each of the plurality of tags were attached to a different item in the first physical retail store when the set of physical location information was determined by the sensor, wherein the sensor identified each tag based on at least one of radio frequency identification or near field communication;

determine, based at least in part on mapping information that associates tag identifiers with item identifiers, that a first tag of the plurality of tags is associated with a first item in the electronic catalog and that a second tag of the plurality of tags is associated with a second item in the electronic catalog;

determine a first physical location of the first tag and a first physical location of the second tag;

determine a physical proximity between the first physical location of the first tag and the first physical location of the second tag;

determine a degree of association between the first item and the second item based at least in part on (a) the determined physical proximity between the first physical location of the first tag and the first physical location of the second tag, and (b) a physical proximity between the first physical location of the first tag and a first physical location of a third tag associated with a third item;

associate the second item and the first item based at least in part on a determination that the determined degree of association between the first item and the second item is greater than a threshold;

determine that the first item is of interest to a user based at least in part on a selection by the user via a user interface of item identification information identifying the first item; and

based at least in part on the determination that the first item is of interest to the user, cause presentation of item identification information identifying the second item as a recommended item for the user.

2. The system of claim 1, wherein the computing device is further configured to at least associate the second item and the first item based at least in part on a physical proximity between a second physical location of the first item and a second physical location of the second item in a second physical retail store different than the first physical retail store.

3. A system comprising:

an electronic data store configured to at least store item identification information associated with each item of a plurality of items; and

a computing device including one or more processors, the computing device in communication with the electronic data store and configured to at least;

determine, from physical location information captured by a sensor, a first physical location of a first item and a first physical location of a second item, wherein the sensor captured (a) the first physical location of the first item based at least in part on a first tag attached to the first item and (b) the first physical location of the second item based at least in part on a second tag attached to the second item;

determine a physical proximity between the first physical location of the first item and the first physical location of the second item;

determine a degree of association between the first item and the second item based at least in part on (a) the determined physical proximity between the first physical location of the first item and the first physical location of the second item, and (b) a physical proximity between the first physical location of the first item and a first physical location of a third item; and

based at least in part on a determination that the first item is of interest, cause presentation of item identification information identifying the second item as a recommended item.

4. The system of claim 3, wherein the computing device is further configured to at least determine the degree of association between the first item and the second item based at least in part on item attribute information that describes the first item and the second item.

5. The system of claim 3, wherein the computing device is further configured to at least:

determine a degree of association between the first item and the third item based at least in part on the determined physical proximity between the first physical location of the first item and the first physical location of the third item; and

associate the second item and the first item based at least in part on a determination that the degree of association between the first item and the second item is greater than a first threshold and that the degree of association between the first item and the third item is less than a second threshold.

6. The system of claim 3, wherein the computing device is further configured to at least determine the degree of association between the first item and the second item by applying a linear scale to the physical proximity between the first physical location of the first item and the first physical location of the second item.

7. The system of claim 3, wherein the computing device is further configured to at least determine the degree of association between the first item and the second item by applying a nonlinear scale to the physical proximity between the first physical location of the first item and the first physical location of the second item.

8. The system of claim 3, wherein the computing device is further configured to at least associate the second item and the first item based at least in part on a determination that the degree of association between the first item and the second item is greater than a threshold, wherein the threshold is set based at least in part on item attribute information indicating that a first category associated with the first item is different than a second category associated with the second item.

9. The system of claim 3, wherein the determination that the first item is of interest comprises identifying that the first item has been or will be presented to a user in one or more user interfaces.

10. The system of claim 3, wherein determining the physical proximity between the first physical location of the first item and the first physical location of the second item includes identifying a path that avoids one or more objects between the first physical location of the first item and the first physical location of the second item, wherein the path is longer than a shortest distance between the first physical location of the first item and the first physical location of the second item.

11. A computer-implemented method comprising:

as implemented by one or more computing devices configured with specific executable instructions,

determining, from physical location information captured by a sensor, a first physical location of a first item and a first physical location of a second item, wherein the sensor captured (a) the first physical location of the first item based at least in part on a first tag attached to the first item and (b) the first physical location of the second item based at least in part on a second tag attached to the second item;

determining a physical proximity between the first physical location of the first item and the first physical location of the second item;

determining a degree of association between the first item and the second item based at least in part on (a) the physical proximity between the first physical location of the first item and the first physical location of the second item, and (b) a physical proximity between the first physical location of the first item and a first physical location of a third item; and

associating the second item and the first item in an electronic catalog based at least in part on a determination that the determined degree of association between the first item and the second item is greater than a threshold.

12. The method of claim 11, wherein the determining the degree of association between the first item and the second item is based at least in part on a second physical location of the first item and a second physical location of the second item, wherein the second physical location of the first item and the second physical location of the second item are recorded at a time different than a time that the first physical location of the first item and the first physical location of the second item are recorded.

13. The method of claim 12, wherein the first physical location of the first item and the first physical location of the second item are recorded within a first physical area, wherein the second physical location of the first item and the second physical location of the second item are recorded within a second physical area different than the first physical area.

14. The method of claim 11, wherein the first physical location of the first item is a location relative to at least one point of reference, wherein the at least one point of reference comprises at least one of a room, a building, a mannequin, a shelf or a rack.

15. A computer-readable, non-transitory storage medium storing computer executable instructions that, when executed by one or more computer systems, configure the one or more computer systems to perform operations comprising:

determining, from physical location information captured by a sensor, a first physical location of a first item and a first physical location of a second item, wherein the sensor captured (a) the first physical location of the first item based at least in part on a first tag attached to the first item and (b) the first physical location of the second item based at least in part on a second tag attached to the second item;

determining a physical proximity between the first physical location of the first item and the first physical location of the second item;

determining a degree of association between the first item and the second item based at least in part on (a) the determined physical proximity between the first physical location of the first item and the first physical location of the second item, and (b) a physical proximity between the first physical location of the first item and a first physical location of a third item; and

based at least in part on a determination that the first item is of interest, causing presentation of item identification information identifying the second item as a recommended item.

16. The computer-readable, non-transitory storage medium of claim 15, wherein the operations further comprise associating the first item and the second item in an electronic data store based at least in part on a determination that the degree of association between the first item and the second item is greater than a threshold.