Disambiguating between users

• US 10,353,982 B1
• Filed: 08/13/2013
• Issued: 07/16/2019
• Est. Priority Date: 08/13/2013
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Kumar, Dilip, Chinoy, Ammar, Raghavan, Sudarshan Narasimha, Vasudhevan, Shrivatsan, Kim, Jin Dong
• Primary Examiner(s): Cumbess, Yolanda R
• Application Number:
  US13/966,270
• Time in Patent Office: 2,163 Days
• Field of Search: None
• CPC Class Codes: G06F 17/00 Digital computing or data processing equipment or methods, specially adapted for specific functions information retrieval, database structures or file system structures therefor G06F16/00
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/08 Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders

Abstract

This disclosure describes a system for disambiguating between multiple potential users that may have performed an item action (e.g., item removal or item placement) at an inventory location. For example, if there are three picking agents (users) standing near an inventory location and one of the agents removes an item (item action) from the inventory location, the example systems and processes described herein may utilize various inputs to disambiguate between the users and determine which of the potential users performed the item action.

Claims

1. A computing system, comprising:

one or more processors; and

a memory coupled to the one or more processors and storing program instructions that when executed by the one or more processors cause the one or more processors to at least;

detect an item action, wherein the item action includes a user removing an item from an inventory location within a materials handling facility;

identify the item removed from the inventory location;

identify a plurality of users in the materials handling facility, wherein each of the identified plurality of users are near the inventory location;

for each of the plurality of users, determine a probability that the user performed the item action of removing the item from the inventory location; and

identify a user with a highest probability as the user that performed the item action of removing the item from the inventory location.

2. The computing system of claim 1, wherein the probability is determined based at least in part on a user identifier associated with the user, wherein the user identifier is at least one of a visual identifier attached to the user or a radio frequency identifier attached to the user.

3. The computing system of claim 2, wherein the inventory location includes an identifier array configured to detect the user identifier of the user that performed the item action.

4. The computing system of claim 3, wherein:

the identifier array includes at least one of a visual identifier reader or a radio frequency reader; and

the identifier array includes a plurality of antennas positioned in the inventory location to detect user identifiers.

5. The computing system of claim 1, wherein the program instructions that when executed by the one or more processors cause the one or more processors to at least:

receive a user identifier associated with the user;

determine that a position of the user identifier corresponds with a stored location of the item at the inventory location; and

confirm that the user associated with the user identifier is the user that performed the item action of removing the item from the inventory location.

6. The computing system of claim 1, wherein the program instructions that when executed by the one or more processors cause the one or more processors to at least:

determine a confidence score for the user with the highest probability, the confidence score indicating a likelihood that the user performed the item action; and

determine that the confidence score exceeds a threshold.

7. A system for identifying a user, comprising:

an antenna array including a plurality of antennas positioned within an inventory location and configured to receive identifiers; and

a computing system communicatively coupled to the antenna array and configured to at least;

identify an item associated with an item action;

determine that a plurality of users are located near the inventory location;

for each of the plurality of users, determine a probability that the user performed the item action;

determine a user from the plurality of users that performed the item action, wherein the determination is based at least in part on;

a received identifier; and

a user with a highest probability that the user performed the item action; and

associate the item action with the determined user that performed the item action.

8. The system of claim 7, further comprising an identifier reader communicatively coupled to the antenna array and the computing system and configured to associate a received identifier with an antenna of the antenna array that received the identifier.

9. The system of claim 7, wherein the item action is at least one of removing the item from the inventory location or placing the item at the inventory location.

10. The system of claim 7, wherein a time is associated with the received identifier identifying when the identifier was received by an antenna of the antenna array.

11. The system of claim 7, wherein a plurality of identifiers are received within a time period, wherein a first identifier of the plurality of identifiers is a user identifier and a second identifier of the plurality of identifiers is an item identifier.

12. The system of claim 7, wherein:

each of the plurality of antennas is positioned approximately three feet from at least one of the plurality of antennas; and

each of the plurality of antennas is configured to receive identifiers located within three feet of an antenna.

13. The system of claim 7, wherein the item associated with the item action is identified based at least in part on an association between the item and a location of an antenna within the inventory location that received the identifier.

14. The system of claim 7, wherein the received identifier is at least one of a user identifier or an item identifier.

15. The system of claim 7, further comprising an image capture device at the inventory location configured to capture an image of the user performing the item action.

16. The system of claim 15, wherein determining the user is further based at least in part on a processing of the image performed by the computing system.

17. A computer-implemented method for associating an item action with a user within a materials handling facility, comprising:

under control of one or more computing systems configured with executable instructions,

detecting an item action associated with an item performed by a user, the item located at an inventory location within the materials handling facility;

determining that a plurality of users are located near the inventory location;

disambiguating between the plurality of users to determine a user of the plurality of users that performed the item action, wherein disambiguating includes;

for each of the plurality of users, determining a probability that the user performed the item action; and

determining that a user with a highest probability performed the item action; and

associating the item action with the user with the highest probability.

18. The computer-implemented method of claim 17, wherein disambiguating further includes:

determining a confidence score for the user with highest probability, the confidence score indicating a likelihood that the user performed the item action; and

determining that the confidence score exceeds a threshold.

19. The computer-implemented method of claim 17, wherein the probability is based at least in part on one or more of a past purchase history of the user, items related to the item, a relationship between the item and additional items selected by the user while in the materials handling facility, a behavior presented by the user while performing the item action, items included in an item list associated with the user, an appearance of the user, a movement of the user, or an orientation of the user.

20. The computer-implemented method of claim 17, wherein disambiguating between each of the plurality of users further includes:

processing an image of the inventory location captured during an occurrence of the item action;

determining that the user that performed the item action is identifiable from the processed image; and

identifying the user that performed the item action.

21. The computer-implemented method of claim 20, wherein processing the image includes:

determining a skeletal structure of each of the plurality of users;

determining a skeletal structure involved in performing the item action; and

determining that a user identifier is associated with the skeletal structure that is performing the item action.

22. The computer-implemented method of claim 21, wherein the user identifier is at least one of a unique code associated with the user, a distinguishing feature of the user, or a visual identifier associated with the user.

23. The computer-implemented method of claim 22, wherein the distinguishing feature is temporarily associated with the user while the user is located within the materials handling facility.

24. A method, comprising:

detecting an item action performed with respect to an item located at an inventory location within a materials handling facility;

disambiguating between a first user and a second user that the first user was involved in the action, wherein disambiguating includes;

determining a first probability for the first user indicative that the first user was involved in the action; and

determining that the first probability is higher than a second probability indicative that the second user performed the action.

25. The method of claim 24, further comprising:

associating at least one of the action or the item with the first user.