Predicting user navigation events

• US 10,089,579 B1
• Filed: 06/05/2015
• Issued: 10/02/2018
• Est. Priority Date: 07/15/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Hamon, Dominic
• Primary Examiner(s): Chen, Alan S
• Application Number:
  US14/731,936
• Time in Patent Office: 1,215 Days
• Field of Search: None
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/954 Navigation, e.g. using categorised browsing
• CPC Class Codes: G06F 40/134 Hyperlinking
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

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 computer-implemented method for predicting a user navigation event, the method comprising:

rendering a web page in a web browser;

identifying, by one or more processors, one or more hyperlinks within the web page;

identifying, by the one or more processors, a probability value representing a probability of selection of each of the one or more hyperlinks using a navigation history map that maps one or more source addresses to one or more destination addresses, each destination address being associated with a frequency value indicating a number of visits to the destination address from an associated source address of the one or more source addresses, wherein the probability value is determined by dividing the frequency of a particular destination address from a particular source address by the frequency of all navigation events from the particular source address; and

predicting, by the one or more processors, a next navigation event using the probability value for each hyperlink.

2. The method of claim 1, wherein the next navigation event is predicted to be a web page associated with the destination address with a highest probability value.

3. The method of claim 1, further comprising prerendering, by the one or more processors, the predicted next navigation event.

4. The method of claim 3, further comprising prerendering, by the one or more processors, one or more additional web pages based on the associated probability values.

5. The method of claim 3, wherein prerendering the predicted next navigation event further comprises determining that a probability value for each hyperlink exceeds a minimum value.

6. The method of claim 1, wherein identifying a probability value further comprises comparing a first list of hyperlinks currently available on the web page to a second list of destination addresses within the navigation history map.

7. A processing system for accessing network content, the processing system comprising:

a memory, coupled to the at least one processor, storing a navigation history map that maps one or more source addresses to one or more destination addresses, each destination address being associated with a frequency value indicating a number of visits to the destination address from an associated source address of the one or more source addresses, wherein the probability value is determined by dividing the frequency of a particular destination address from a particular source address by the frequency of all navigation events from the particular source address; and

at least one processor, the at least one processor configured to;

rendering a web page in a web browser;

identify one or more hyperlinks within the web page;

identify a probability value representing a probability of selection of each of the one or more hyperlinks using a navigation history map; and

predict a next navigation event using the probability value for each hyperlink.

8. The system of claim 7, wherein the next navigation event is predicted to be a web page associated with the destination address with a highest probability value.

9. The method of claim 7, wherein the at least one processor is further configured to prerender the predicted next navigation event.

10. The method of claim 9, wherein the at least one processor is further configured to prerender one or more additional web pages based on the associated probability values.

11. The method of claim 9, wherein the at least one processor is further configured to prerender the predicted next navigation event by determining that a probability value for each hyperlink exceeds a minimum value.

12. The method of claim 7, wherein the at least one processor is further configured to identify a probability value by comparing a first list of hyperlinks currently available on the web page to a second list of destination addresses within the navigation history map.

13. A non-transitory computer-readable storage medium on which computer readable instructions of a program are stored, the instructions, when executed by one or more processors, cause the one or more processors to perform a method, the method comprising:

rendering a web page in a web browser;

identifying one or more hyperlinks within the web page;

identifying a probability value representing a probability of selection of each of the one or more hyperlinks using a navigation history map that maps one or more source addresses to one or more destination addresses, each destination address being associated with a frequency value indicating a number of visits to the destination address from an associated source address of the one or more source addresses, wherein the probability value is determined by dividing the frequency of a particular destination address from a particular source address by the frequency of all navigation events from the particular source address; and

predicting a next navigation event using the probability value for each hyperlink.

14. The medium of claim 13, wherein the next navigation event is predicted to be a web page associated with the destination address with a highest probability value.

15. The medium of claim 13, wherein the method further comprises prerendering the predicted next navigation event.

16. The medium of claim 15, wherein the method further comprises prerendering one or more additional web pages based on the associated probability values.

17. The medium of claim 15, wherein prerendering the predicted next navigation event further comprises determining that a probability value for each hyperlink exceeds a minimum value.

18. The medium of claim 13, wherein identifying a probability value further comprises comparing a first list of hyperlinks currently available on the web page to a second list of destination addresses within the navigation history map.