Tracking user behavior relative to a network page

• US 8,914,496 B1
• Filed: 09/12/2011
• Issued: 12/16/2014
• Est. Priority Date: 09/12/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Sriram, Siddharth, Dillard, Logan Luyet, Fox, Eric B., Richardson, Jared L.
• Primary Examiner(s): Osman, Ramy M
• Application Number:
  US13/230,153
• Time in Patent Office: 1,191 Days
• Field of Search: 709/203, 709/217, 709/223, 709/224, 709/227, 715/704
• US Class Current: 709/224
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 67/025 for remote control or remote monitoring of applications
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Disclosed are various embodiments for tracking user behavior relative to a network page and identifying user interest in various content items of the network page according to the user behavior. A network page that includes multiple content items is rendered for display in a client. A user action is obtained relative to the network page. A user behavior report is sent to one or more servers. The user behavior report indicates the user action, a timestamp associated with the user action, and one or more of the content items that are associated with the user action.

Claims

1. A non-transitory computer-readable medium embodying at least one program executable in at least one first computing device, wherein, when executed, the at least one program causes the at least one first computing device to at least:

generate a network page, the network page including a plurality of content items to be presented on a rendered version of the network page;

collect user behavior data indicating at least one user action relative to the rendered version of the network page, the at least one user action being selected from the group consisting of;

a zooming action and a copying action;

report the user behavior data to the at least one first computing device according to a predefined time interval;

send the network page, user behavior monitoring code, and user behavior reporting code to a plurality of second computing devices;

obtain a plurality of user behavior reports relative to the rendered version of the network page from the plurality of second computing devices;

identify an aggregate user interest in a proper subset of the content items based at least in part on the plurality of user behavior reports; and

emphasize the proper subset of the content items in the network page in response to identifying the aggregate user interest.

2. The non-transitory computer-readable medium of claim 1, wherein the content items include a plurality of sentences corresponding to a customer review of a product, and the proper subset of the content items corresponds to a portion of the customer review prompting the aggregate user interest.

3. A system comprising:

a data store configured to store content data; and

at least one first computing device in communication with the data store, the at least one first computing device configured to at least;

generate a network page, the network page including;

a plurality of content items to be presented on a rendered version of the network page;

code configured to cause a second computing device to at least collect user behavior data indicating at least one user action relative to the rendered version of the network page, the at least one user action corresponding to at least one of;

a copying action applied to at least one of the content items or a zooming action; and

code configured to cause the second computing device to at least report the user behavior data to the at least one first computing device;

send the network page to a second computing device;

obtain the user behavior data from the second computing device; and

identify a user interest in a proper subset of the content items based at least in part on the user behavior data.

4. The system of claim 3, wherein the at least one first computing device is further configured to at least identify an aggregate user interest in another proper subset of the content items based at least in part on the user behavior data and user behavior data obtained from a plurality of other second computing devices.

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

determine whether a user action reported in the user behavior data is predicted to indicate the user interest; and

exclude the user action from consideration in identifying the user interest when the user action is not predicted to indicate the user interest.

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

determine whether the user action is correlated to a commencement of a period of user inattention to the rendered version of the network page; and

determine that the user action is not predicted to indicate the user interest when the user action is correlated to the commencement of the period of user inattention to the rendered version of the network page.

7. The system of claim 3, wherein the user behavior data indicates a timestamp associated with the at least one user action.

8. The system of claim 7, wherein a level of the user interest in individual ones of the proper subset of the content items is determined based at least in part on the timestamp.

9. The system of claim 3, wherein a level of the user interest in individual ones of the proper subset of the content items is determined based at least in part on a corresponding action type associated with individual ones of the at least one user action.

10. The system of claim 3, wherein a level of the user interest in individual ones of the proper subset of the content items is determined based at least in part on a type of client associated with the at least one user action.

11. The system of claim 3, wherein the at least one user action corresponds to the copying action applied to the at least one of the content items.

12. The system of claim 3, wherein the at least one user action corresponds to a selection action applied to at least one of the content items.

13. The system of claim 3, wherein the at least one user action corresponds to an action that initiates rendering of a different portion of the rendered version of the network page on a display.

14. The system of claim 13, wherein the action is selected from the group consisting of:

a scrolling action and the zooming action.

15. The system of claim 3, wherein the at least one user action corresponds to a hovering action relative to at least one of the content items.

16. The system of claim 15, wherein the proper subset of the content items are identified based at least in part on an estimated distance between a cursor performing the hovering action and an actual location of user attention.

17. The system of claim 16, wherein the at least one first computing device is further configured to at least determine the estimated distance based at least in part on a reported location of the cursor and a location of a subsequently selected component on the rendered version of the network page.

18. The system of claim 3, wherein at least some of the content items are individually associated with a corresponding unique identifier within the network page, and the code configured to cause the second computing device to at least collect the user behavior data is further configured to at least associate at least one of the unique identifiers with the at least one user action.

19. The system of claim 18, wherein at least one of the content items corresponds to a sentence of text.

20. A computer-implemented method comprising:

sending, via at least one first computing device, user behavior monitoring code, user behavior reporting code, and instructions for generating a network page to a plurality of second computing devices, the network page including a plurality of content items to be presented on a rendered version of the network page, the user behavior monitoring code being configured to collect user behavior data indicating at least one user action relative to the rendered version of the network page, the user behavior reporting code being configured to report the user behavior data to the at least one first computing device according to a predefined time interval;

obtaining, via the at least one first computing device, a plurality of user behavior reports relative to the rendered version of the network page from the plurality of second computing devices;

identifying, via the at least one first computing device, an aggregate user interest in a subset of the plurality of content items based at least in part on the plurality of user behavior reports; and

causing, via the at least one first computing device, the subset of the plurality of content items to be emphasized in the network page in response to identifying the aggregate user interest.

21. The computer-implemented method of claim 20, wherein the plurality of content items include at least one sentence corresponding to a customer review of a product, and the subset of the plurality of content items corresponds to a portion of the customer review prompting the aggregate user interest.

22. The computer-implemented method of claim 20, wherein at least one of the plurality of user behavior reports further indicates a respective computing device type corresponding to a particular second computing device of the plurality of second computing devices.

23. The computer-implemented method of claim 20, wherein at least one of the plurality of user behavior reports indicates individual content items by a respective content identifier.

24. The computer-implemented method of claim 20, wherein at least one of the plurality of user behavior reports indicates a hovering action over at least one of the plurality of content items.

25. The computer-implemented method of claim 20, wherein at least one of the plurality of user behavior reports indicates a copying action applied to at least one of the plurality of content items.

26. The computer-implemented method of claim 20, wherein at least one of the plurality of user behavior reports indicates a selection action applied to at least one of the plurality of content items.

27. The computer-implemented method of claim 20, wherein at least one of the plurality of user behavior reports indicates an action that initiates rendering of a different portion of the network page on a display.

28. The computer-implemented method of claim 20, wherein at least one of the plurality of user behavior reports indicates a zooming action.