Predicting user navigation events

• US 9,443,197 B1
• Filed: 01/10/2014
• Issued: 09/13/2016
• Est. Priority Date: 09/15/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Burkard, Timo, Hamon, Dominic, Jain, Arvind
• Primary Examiner(s): CHEN, ALAN S
• Application Number:
  US14/151,988
• Time in Patent Office: 977 Days
• Field of Search: None
• US Class Current: 1/1
• 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: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/048 Fuzzy inferencing

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:

receiving, using one or more processors, a set of navigation events associated with a web browser, each navigation event in the set including chronological data, the chronological data comprising one or more chronological index values indicating when the navigation event was selected, wherein a chronological index value is associated with a type of chronological data;

indexing, using the one or more processors, the set of navigation events into subsets of navigation events corresponding to chronological index values of the chronological data;

identifying, using the one or more processors, current event data indicating a current time a query is performed;

determining, using the one or more processors, a selection probability for each navigation event of the set of navigation events based on whether a navigation event is indexed in a subset of navigation events that corresponds to a chronological index value of the current event data; and

selecting, using the one or more processors, a particular navigation event from the set of navigation events as a likely next navigation event for prerendering, the particular navigation event having a highest selection probability.

2. The method of claim 1, further comprising prerendering the likely next navigation event at the web browser.

3. The method of claim 1, further comprising determining a ratio of a selection count for a given navigation event to a count of all selection counts for other navigation events of the set of navigation events, the ratio being used to determine the selection probability of the given navigation event.

4. The method of claim 1, wherein the type chronological data is one of a day of week, a minute of an hour, a day of month, a time of day, a month of year, and a weekday or weekend.

5. The method of claim 1, further comprising determining an overall selection probability for a particular subset of navigation events by averaging the selection probabilities associated with navigation events in the particular subset, the chronological data associated with the particular subset of navigation events corresponding to the current event data.

6. The method of claim 5, wherein the averaging uses a weight value representing a number of navigation events in the particular subset.

7. The method of claim 6, wherein the number of navigation events in the particular subset satisfies a threshold value.

8. A non-transitory computer readable storage medium comprising instructions that, when executed by one or more processors, cause the processors to perform a method, the method comprising:

receiving, using the one or more processors, a set of navigation events associated with a web browser, each navigation event in the set including chronological data, the chronological data comprising one or more chronological index values indicating when the navigation event was selected, wherein a chronological index value is associated with a type of chronological data;

indexing, using the one or more processors, the set of navigation events into subsets of navigation events corresponding to chronological index values of the chronological data;

identifying, using the one or more processors, current event data indicating a current time a query is performed;

determining, using the one or more processors, a selection probability for each navigation event of the set of navigation events based on whether a navigation event is indexed in a subset of navigation events that corresponds to a chronological index value of the current event data; and

selecting, using the one or more processors, a particular navigation event from the set of navigation events as a likely next navigation event for prerendering, the particular navigation event having a highest selection probability.

9. The non-transitory computer readable medium of claim of claim 8, wherein the method further comprising prerendering the likely next navigation event at the web browser.

10. The non-transitory computer readable medium of claim of claim 8, wherein the method further comprising determining a ratio of a selection count for a given navigation event to a count of all selection counts for other navigation events of the set of navigation events, the ratio being used to determine the selection probability of the given navigation event.

11. A system for predicting a user navigation event, comprising:

a memory; and

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

receive a set of navigation events associated with a web browser, each navigation event in the set including chronological data, the chronological data comprising one or more chronological index values indicating when the navigation event was selected, wherein a chronological index value is associated with a type of chronological data;

index the set of navigation events into subsets of navigation events corresponding to chronological index values of the chronological data;

identify current event data indicating a current time a query is performed;

determine a selection probability for each navigation event of the set of navigation events based on whether a navigation event is indexed in a subset of navigation events that corresponds to a chronological index value of the current event data; and

select a particular navigation event from the set of navigation events as a likely next navigation event for prerendering, the particular navigation event having a highest selection probability.

12. The system of claim 11, wherein the one or more processors are further configured to prerender the likely next navigation event at the web browser.

13. The system of claim 11, wherein the one or more processors are further configured to determine a ratio of a selection count for a given navigation event to a count of all selection counts for other navigation events of the set of navigation events, the ratio being used to determine the selection probability of the given navigation event.

14. The system of claim 11, wherein the type chronological data is one of a day of week, a minute of an hour, a day of month, a time of day, a month of year, and a weekday or weekend.

15. The system of claim 11, wherein the one or more processors are further configured to determine an overall selection probability for a particular subset of navigation events by averaging the selection probabilities associated with navigation events in the particular subset, the chronological data associated with the particular subset of navigation events corresponding to the current event data.

16. The system of claim 15, wherein the averaging uses a weight value representing a number of navigation events in the particular subset.

17. The system of claim 16, wherein the number of navigation events in the particular subset satisfies a threshold value.