Predictive page loading based on navigation

• US 9,299,030 B1
• Filed: 03/01/2011
• Issued: 03/29/2016
• Est. Priority Date: 03/01/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Hotchkies, Blair L., Brundage, Michael L., Teeraparpwong, Pongsakorn, Patrikios, Jason P., Williams, Sarah E., Mills, Brent Robert, Indrei, Alexandru I., Parshall, Daniel R., Nilles, John M., Saifullah, Sikandar
• Primary Examiner(s): RIFKIN, BEN M
• Application Number:
  US13/037,829
• Time in Patent Office: 1,855 Days
• Field of Search: 706/52
• US Class Current: 1/1
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9574 of access to content, e.g. by caching
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems

Abstract

Disclosed are various embodiments for predictive network page loading. Content corresponding to a network request is obtained. A next network page associated with the obtained page content is predicted. If the prediction is confident relative to a predetermined confidence threshold, then a first network page is generated. The first network page includes the page content corresponding to the network request and a portion of content for the predicted network page. The generated first network page is provided to a client. A request for another network page is received. If the another network page in the request corresponds to the predicted next network page, a second network page is generated. The second network page includes the remainder of the content for the predicted page content.

Claims

1. A method, comprising:

obtaining, in a computing device, page content corresponding to a network request received from a client device via a network;

calculating, in the computing device, after the obtaining, based at least in part on probability of selection data, a probability of selection for a predicted network page associated with the page content;

determining, in the computing device, if the probability of selection meets a predetermined confidence threshold;

in response to the network request, if the probability of selection meets the predetermined confidence threshold, generating a first network page that includes the page content corresponding to the network request and a portion of content for the predicted network page, and providing the first network page;

receiving a request for another network page;

if the another network page in the request corresponds to the predicted network page, generating a second network page that includes a remainder of the content for the predicted network page excluding the portion of content for the predicted network page; and

wherein the probability of selection data is aggregated across a plurality of users, at least one of the users being distinct from a one of the users from which the network request was obtained.

2. The method of claim 1, wherein the probability of selection data is based at least in part on page view data indicating transitions by the users between pages of a network site.

3. The method of claim 1, wherein the probability of selection data includes probabilities for one of the users viewing one page in a multi-page search result after viewing other pages in the multi-page search result.

4. The method of claim 1, further comprising:

if the probability of selection fails to meet the predetermined threshold, then generating a third network page that includes the page content corresponding to the network request but without the portion of the predicted network page.

5. The method of claim 1, further comprising:

if the another network page in the request does not correspond to the predicted network page, generating a fourth network page that includes content for the another page in the request.

6. The method of claim 1, further comprising:

receiving the network request from a browser; and

providing the first network page in response to the network request.

7. The method of claim 1, further comprising:

receiving the request for the another network page from a browser; and

providing the second network page to the browser in response to the request.

8. The method of claim 1, wherein the probability of selection data indicates at least one probability of at least one corresponding action occurring with respect to the page content.

9. The method of claim 8, wherein the at least one corresponding action comprises a selection of an object or a link included in the page content.

10. The method of claim 1, wherein the probability of selection data is based at least in part on at least one previous search query or at least one previous page view.

11. A system, comprising:

at least one computing device;

an application implemented in the at least one computing device, comprising;

logic that obtains page content corresponding to a network request received from a client device via a network;

logic that calculates, after obtaining the page content, based at least in part on probability of selection data, a probability of selection for a predicted network page associated with the page content;

logic that determines if the probability of selection meets a predetermined confidence threshold;

logic that generates, in response to the network request, if the probability of selection meets the predetermined confidence threshold, a first network page that includes the page content corresponding to the network request and a portion of content for the predicted network page, and providing the first network page;

logic that receives a request for another network page;

logic that, if the another network page in the request corresponds to the predicted network page, generates a second network page that includes a remainder of the content for the predicted network page excluding the portion of content for the predicted network page; and

wherein the probability of selection data is aggregated across a plurality of users, at least one of the users being distinct from a one of the users from which the network request was obtained.

12. The system of claim 11, wherein the probability of selection data is based at least in part on page view data indicating transitions by the users between pages of a network site.

13. The system of claim 11, wherein the probability of selection data includes probabilities for one of the users viewing one page in a multi-page search result after viewing other pages in the multi-page search result.

14. The system of claim 11, wherein the application further comprises logic that, if the probability of selection fails to meet the predetermined threshold, generates a third network page that includes the page content corresponding to the network request but without the portion of the predicted network page.

15. The system of claim 11, wherein the application further comprises logic that, if the another network page in the request does not correspond to the predicted network page, generates a fourth network page that includes content for the another page in the request.

16. The system of claim 11, wherein the application further comprises:

logic that receives the network request from a browser; and

logic that provides the first network page in response to the network request.

17. The system of claim 11, wherein the application further comprises:

logic that receives the request for the another network page from a browser; and

logic that provides the second network page to the browser in response to the request.

18. A non-transitory computer-readable medium embodying a program executable in a computing device, the program comprising:

code that obtains page content corresponding to a network request received from a client device via a network;

code that calculates, after obtaining the page content, based at least in part on probability of selection data, a probability of selection for a predicted network page associated with the page content;

code that determines if the probability of selection meets a predetermined confidence threshold;

code that, in response to the network request, if the probability of selection meets the predetermined confidence threshold, generates a first network page that includes the page content corresponding to the network request and a portion of content for the predicted network page, and providing the first network page;

code that receives a request for another network page;

code that, if the another network page in the request corresponds to the predicted network page, generates a second network page that includes a remainder of the content for the predicted network page excluding the portion of content for the predicted network page; and

wherein the probability of selection data is aggregated across a plurality of users, at least one of the users being distinct from a one of the users from which the network request was obtained.

19. The non-transitory computer-readable medium of claim 18, wherein the probability of selection data is based at least in part on page view data indicating transitions by the users between pages of a network site.

20. The non-transitory computer-readable medium of claim 18, wherein the probability of selection data includes probabilities for one of the users viewing one page in a multi-page search result after viewing other pages in the multi-page search result.

21. The non-transitory computer-readable medium of claim 18, the program further comprising:

code that, if the probability of selection fails to meet the predetermined threshold, generates a third network page that includes the page content corresponding to the network request but without the portion of the predicted network page.