Identifying augmented reality visuals influencing user behavior in virtual-commerce environments

• US 10,726,629 B2
• Filed: 11/13/2018
• Issued: 07/28/2020
• Est. Priority Date: 02/15/2017
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Inc.
• Inventors: Hiranandani, Gaurush, Varsha, Chinnaobireddy, Maram, Sai Varun Reddy, Ayush, Kumar, Sinha, Atanu Ranjan
• Primary Examiner(s): Nguyen, Anh-Tuan V
• Application Number:
  US16/189,638
• Publication Number:
  US 20190102952A1
• Time in Patent Office: 623 Days
• Field of Search: None
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: G06T 19/006 Mixed reality object pose determination, tracking or camera calibration for mixed reality G06T7/00

Abstract

Certain embodiments involve enhancing personalization of a virtual-commerce environment by identifying an augmented-reality visual of the virtual-commerce environment. For example, a system obtains a data set that indicates a plurality of augmented-reality visuals generated in a virtual-commerce environment and provided for view by a user. The system obtains data indicating a triggering user input that corresponds to a predetermined user input provideable by the user as the user views an augmented-reality visual of the plurality of augmented-reality visuals. The system obtains data indicating a user input provided by the user. The system compares the user input to the triggering user input to determine a correspondence (e.g., a similarity) between the user input and the triggering user input. The system identifies a particular augmented-reality visual of the plurality of augmented-reality visuals that is viewed by the user based on the correspondence and stores the identified augmented-reality visual.

Claims

1. A method for enhancing personalization of a virtual-commerce environment by identifying augmented-reality visual content of the virtual-commerce environment, the method comprising:

obtaining, by a processor, data indicating a plurality of augmented-reality visuals generated in the virtual-commerce environment and provided for view by a user;

obtaining, by the processor, data indicating a triggering user input, the triggering user input indicating a predetermined user input provideable by the user as the user views an augmented-reality visual of the plurality of augmented-reality visuals and detectable by the processor;

obtaining, by the processor, data indicating a user input provided by the user to generate manipulated augmented-reality visuals from the plurality of augmented-reality visuals;

predicting, by the processor, an epoch time by applying a machine-learning algorithm to the data indicating the user input, wherein the machine-learning algorithm is trained to predict epoch times during which users are likely to provide user inputs corresponding to the triggering user input;

identifying, by the processor, a particular manipulated augmented-reality visual of the manipulated augmented-reality visuals that is viewed by the user at or nearest the epoch time; and

storing the identified manipulated augmented-reality visual.

2. The method of claim 1, further comprising:

identifying, by the processor and in response to determining a correspondence between the user input and the triggering user input, an additional particular augmented-reality visual provided to the user at a time associated with the user input.

3. The method of claim 2, wherein identifying the additional particular augmented-reality visual provided to the user at the time associated with the user input further comprises:

obtaining, by the processor, a time stamp associated with each of the plurality of augmented-reality visuals;

obtaining, by the processor, the time associated with the user input corresponding to the triggering user input; and

identifying, by the processor, the additional particular augmented-reality visual provided to the user at the time the user provides the user input corresponding to the triggering user input based on a comparison of the time stamp associated with each of the plurality of augmented-reality visuals and the time associated with the user input corresponding to the triggering user input.

4. The method of claim 1, further comprising:

predicting the epoch time responsive to a determination of a lack of correspondence between the user input and the triggering user input.

5. The method of claim 1, further comprising training, by the processor, the machine-learning algorithm using the data indicating the plurality of augmented-reality visuals, the data indicating the triggering user input, and the data indicating the user input.

6. The method of claim 1, wherein the triggering user input indicates a request for information associated with a virtual object in a virtual-reality visual of the plurality of augmented-reality visuals.

7. The method of claim 1, further comprising:

identifying, by the processor, a group of augmented-reality visuals based on the user input and the triggering user input;

obtaining, by the processor, accelerometer data associated with each identified augmented-reality visual; and

identifying, by the processor, a subset of the identified group of augmented-reality visuals based on a comparison of the accelerometer data associated with each identified augmented-reality visual and a threshold accelerometer value.

8. A system comprising:

a processing device; and

a non-transitory computer-readable medium communicatively coupled to the processing device, wherein the processing device is configured to perform operations comprising;

obtaining data indicating a plurality of augmented-reality visuals generated in a virtual-commerce environment and provided for view by a user;

obtaining data indicating a triggering user input, the triggering user input indicating a predetermined user input provideable by the user as the user views an augmented-reality visual of the plurality of augmented-reality visuals;

obtaining data indicating a user input provided by the user to generate manipulated augmented-reality visuals from the plurality of augmented-reality visuals;

predicting, by the processing device, an epoch time by applying a machine-learning algorithm to the data indicating the user input, wherein the machine-learning algorithm is trained to predict epoch times during which users are likely to provide user inputs corresponding to the triggering user input;

identifying a particular manipulated augmented-reality visual of the manipulated augmented-reality visuals that is viewed by the user at or nearest the epoch time; and

storing the identified manipulated augmented-reality visual.

9. The system of claim 8, wherein the processing device is further configured to perform operations comprising:

predicting the epoch time responsive to a determination of a lack of correspondence between the user input and the triggering user input.

10. The system of claim 8, wherein the processing device is further configured to perform operations comprising:

identifying, in response to determining a correspondence between the user input and the triggering user input, an additional particular augmented-reality visual.

11. The system of claim 10, wherein the processing device is further configured to identify the additional particular augmented-reality visual by identifying, in response to determining the correspondence, the additional particular augmented-reality visual provided to the user at a time associated with the user input.

12. The system of claim 11, wherein the processing device is further configured to identify the additional particular augmented-reality visual generated and provided to the user at the time associated with the user input by:

obtaining a time stamp associated with each of the plurality of augmented-reality visuals;

obtaining the time associated with the user input corresponding to the triggering user input; and

identifying, by the processing device, the additional particular augmented-reality visual provided to the user at the time the user provides the user input corresponding to the triggering user input based on a comparison of the time stamp associated with each of the plurality of augmented-reality visuals and the time associated with the user input corresponding to the triggering user input.

13. The system of claim 8, wherein the triggering user input corresponds to user input indicates a request for information associated with a virtual object in a virtual-reality visual of the plurality of augmented-reality visuals.

14. The system of claim 8, wherein the processing device is further configured to perform operations comprising:

identifying a group of augmented-reality visuals based on the user input and the triggering user input;

obtaining accelerometer data associated with each identified augmented-reality visual; and

identifying a subset of the identified group of augmented-reality visuals based on a comparison of accelerometer data associated with each identified augmented-reality visual and a threshold accelerometer value.

15. A non-transitory computer-readable medium storing program code executable by a processor for enhancing personalization of a virtual-commerce environment by identifying augmented-reality visual content of the virtual-commerce environment, the program code comprising:

program code for obtaining, by the processor, data indicating a plurality of augmented-reality visuals generated in the virtual-commerce environment and provided for view by a user;

program code for obtaining, by the processor, data indicating a triggering user input, the triggering user input indicating a predetermined user input provideable by the user as the user views an augmented-reality visual of the plurality of augmented-reality visuals;

program code for obtaining, by the processor, data indicating a user input provided by the user to generate manipulated augmented-reality visuals from the plurality of augmented-reality visuals;

program code for predicting, by the processor, an epoch time by applying a machine-learning algorithm to the data indicating the user input, wherein the machine-learning algorithm is trained to predict epoch times during which users are likely to provide user inputs corresponding to the triggering user input;

program code for identifying, by the processor, a particular manipulated augmented-reality visual of the manipulated augmented-reality visuals that is viewed by the user at or nearest the epoch time; and

program code for storing the identified manipulated augmented-reality visual.

16. The non-transitory computer-readable medium of claim 15, further comprising:

program code for identifying, by the processor and in response to determining correspondence between the user input and the triggering user input, an additional particular augmented-reality visual at a time associated with the user input.

17. The non-transitory computer-readable medium of claim 16, wherein identifying the additional particular augmented-reality visual based on the correspondence comprises:

obtaining, by the processor, a time stamp associated with each of the plurality of augmented-reality visuals;

obtaining, by the processor, the time associated with the user input corresponding to the triggering user input; and

identifying, by the processor, the additional particular augmented-reality visual provided to the user at the time the user provides the user input corresponding to the triggering user input based on a comparison of the time stamp associated with each of the plurality of augmented-reality visuals and the time associated with the user input corresponding to the triggering user input.

18. The non-transitory computer-readable medium of claim 15, wherein the program code further comprises:

program code for predicting, by the processor and in response to a determination of a lack of correspondence between the user input and the triggering user input, the epoch time indicating a particular time that the user is likely to provide additional user input corresponding to the triggering user input.

19. The non-transitory computer-readable medium of claim 15, wherein the program code further comprises program code for training, by the processor, the machine-learning algorithm using the data indicating the plurality of augmented-reality visuals, the data indicating the triggering user input, and the data indicating the user input.

20. The non-transitory computer-readable medium of claim 15, wherein the program code further comprises:

program code for identifying, by the processor, a group of augmented-reality visuals based on the user input and the triggering user input;

program code for obtaining, by the processor, accelerometer data associated with each identified augmented-reality visual; and

program code for identifying, by the processor, a subset of the identified group of augmented-reality visuals based on a comparison of the accelerometer data associated with each identified augmented-reality visual and a threshold accelerometer value.