Predicting user navigation events

• US 9,846,842 B2
• Filed: 12/20/2013
• Issued: 12/19/2017
• Est. Priority Date: 07/01/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Jain, Arvind, Hamon, Dominic
• Primary Examiner(s): Smith, Paulinho E
• Application Number:
  US14/136,136
• Publication Number:
  US 20160189030A1
• Time in Patent Office: 1,460 Days
• CPC Class Codes: G06F 16/9574 of access to content, e.g. by caching
• CPC Class Codes: G06F 16/9577 Optimising the visualization of content, e.g. distillation of HTML documents
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition

Abstract

A method and system for predicting a next navigation event are described. Aspects of the disclosure minimize the delay between a navigation event and a network response by predicting the next navigation event. The system and method may then prerender content associated with the next navigation event. For example, the method and system may predict a likely next uniform resource locator during web browsing to preemptively request content from the network before the user selects the corresponding link on a web page. The methods describe a variety of manners of predicting the next navigation event, including examining individual and aggregate historical data, text entry prediction, and cursor input monitoring.

Claims

1. A system, comprising:

a memory; and

one or more processors coupled to the memory, the one or more processors being configured to;

receive a first text input related to a web browser;

identify a first set of probability data based on the first character of text input, the set of probability data associated with one or more links from a navigation history;

determine a first confidence value for each link associated with the first set of probability data, the confidence value indicating a frequency at which the link has been accessed based on the navigation history;

prerender a webpage associated with at least one link associated with the first set of probability data based on the confidence value associated with the link;

receive a second character of text input related to the web browser;

identify a second set of probability data different from the first set of probability data based on both the first and second character of text input, the second set of probability data associated with one or more links from the navigation history;

determine a second confidence value for each link associated with the second set of probability data, the confidence value indicating a frequency at which the link has been accessed based on the navigation history; and

prerender a webpage associated with at least one link associated with the second set of probability data based on the confidence value.

2. The system of claim 1, wherein the one or more processors are further configured to index the sets of probability data based on the one or more previous text inputs.

3. The system of claim 1, wherein the one or more processors are further configured to:

receive an indication that a user has selected at least one link associated with the set of probability data; and

update the confidence value associated with the selected link based on the indication.

4. The system of claim 3, wherein the one or more processors are further configured to:

decay the confidence value for non-selected links by a certain percentage;

determine whether the confidence value for a given non-selected link is below a particular level; and

when the confidence value for the given non-selected link is below the particular level, remove the given non-selected link from the set of probability data.

5. The system of claim 1, wherein prerendering a webpage associated with a link based on a confidence value further comprises prerendering a webpage based on an amount of network traffic associated with the prerendered link.

6. The system of claim 1, wherein prerendering a webpage associated with a link based on a confidence value further comprises prerendering a webpage based on a speed at which content is changing at the prerendered link.

7. The system of claim 1, wherein to determine the confidence value the one or more processors are further configured to compare a frequency value for a given link associated with the set of probability data with a sum of frequency values for other links in the navigation history, the frequency value indicating a number of times the links are accessed.

8. The system of claim 1, wherein to determine the confidence value the one or more processors are further configured to determine a number of times that a given link associated with the set of probability data is accessed from a current link.

9. A method comprising:

receiving a first text input via a text field of a browser;

identifying, with one or more processors, a first set of probability data based on the first text input, wherein the first set of probability data associates at least one destination in a navigation history with the number of times a user selected the destination, wherein the navigation history comprises a history of user-selected selected destinations on a network;

determining, with the one or more processors, a first probability value for a first destination, wherein the first destination is associated with the first set of probability data and wherein the first probability value is based on the number of times a user selected the first destination;

loading, with the one or more processors, content from the first destination when the first probability value exceeds a threshold;

providing for display, with the one or more processors and via the browser, the content loaded from the first destination when a user selects the first destination;

receiving, after the first text input, a second text input via the text field and;

identifying, with the one or more processors, a second set of probability data based on both the first text input and the second text input, wherein the second set of probability data associates at least one of the destinations in the navigation history with the number of times a user selected the destination, and wherein the second set of probability data is different from the first set of probability data;

determining, with the one or more processors, a second probability value for a second destination, wherein the second destination is associated with the second set of probability data and wherein the second probability value is based on the number of times a user selected the second destination;

loading, with the one or more processors, content from the second destination when the second probability value exceeds a threshold; and

providing for display, with the one or more processors and via the browser, the content loaded from the second destination when a user selects the second destination.

10. The method of claim 9 wherein the browser is a web browser and the network is the Internet.

11. The method of claim 9 wherein the first set of probability data associates the at least one destination in the navigation history with the number of times a user of said browser selected the destination after the first text input.

12. The method of claim 9 wherein the first set of probability data associates the at least one destination in the navigation history with the number of times a plurality of users, each using a different browser, selected the destination after the first text input.

13. The method of claim 9 wherein the probability is further based on the number of times a user did not select the first destination based on the first text input.

14. The method of claim 9 wherein the content loaded from the first destination is discarded when the second text input is received.

15. A system comprising:

a memory; and

one or more processors coupled to the memory, the one or more processors being configured to;

receive first text input via a text field of a browser;

identify a first set of probability data based on the first text input, wherein the first set of probability data associates at least one destination in a navigation history with the number of times a user selected the destination, wherein the navigation history comprises a history of user-selected destinations on a network;

determine a first probability value for a first destination, wherein the first destination is associated with the first set of probability data and wherein the first probability value is based on the number of times a user selected the first destination;

load content from the first destination when the first probability value exceeds a threshold;

provide for display, via the browser, the content loaded from the first destination when a user selects the first destination;

receive, after the first text input, a second text input via the text field;

identify a second set of probability data based on both the first text input and the second text input, wherein the second set of probability data associates at least one of the destinations in the navigation history with the number of times a user selected the destination, and wherein the second set of probability data is different from the first set of probability data;

determine a second probability value for a second destination, wherein the second destination is associated with the second set of probability data and wherein the second probability value is based on the number of times a user selected the second destination;

load, with the one or more processors, content from the second destination when the second probability value exceeds a threshold; and

provide for display, with the one or more processors and via the browser, the content loaded from the second destination when a user selects the second destination.

16. The system of claim 15 wherein the instructions further comprise:

providing a list of destinations for display in response to receiving the first text input, the list including the first destination and another destination associated with the first set of probability data; and

providing the content loaded from the first destination for display when the user selects the first destination from the list.

17. The system of claim 16 wherein the list of destinations comprises a list of URLs.

18. The system of claim 15 wherein the first set of probability data is indexed by the first text input and the first set of probability data is indexed by the second text input.

19. The system of claim 15 wherein the first set of probability data associates the at least one destination in the navigation history with the number of times a user of said browser selected the destination after the first text input.

20. The system of claim 15 wherein the system further comprises a plurality of client devices and wherein first set of probability data associates the at least one destination in the navigation history with the number of times a plurality of client devices, each using a different browser, selected the destination after the first text input.