Predicting user navigation events based on chronological history data

• US 8,655,819 B1
• Filed: 09/15/2011
• Issued: 02/18/2014
• 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:
  US13/233,314
• Time in Patent Office: 887 Days
• Field of Search: None
• US Class Current: 706/45
• 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:

storing a set of navigation data, the navigation data comprising one or more navigation events and one or more selection counts associated with each navigation event, the navigation events and selection counts indexed by chronological data, and a value of the chronological data indicating when a navigation event was selected;

determining a current chronological value, the current chronological value representing a present time;

identifying a subset of the navigation data corresponding to the current chronological value;

determining, using a processor, a ratio of a selection count of a particular navigation event contained within the subset of the navigation data to a count of all selection counts contained within the subset of the navigation data; and

determining a probability of selection of the particular navigation event using the ratio, such that the probability may be used by a web browser to assist with network navigation.

2. The method of claim 1, further comprising identifying the given navigation event as a likely navigation event based upon the probability of selection.

3. The method of claim 2, further comprising:

determining a probability of selection of a plurality of navigation events; and

identifying one of the navigation events of the plurality of navigation events with the highest probability of selection as a likely navigation event.

4. The method of claim 2, further comprising:

determining a probability of selection of a plurality of navigation events; and

identifying any navigation event with a probability of selection that exceeds a threshold value as a likely navigation event.

5. The method of claim 2, further comprising prerendering the likely navigation event.

6. The method of claim 2, wherein the chronological data is at least 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.

7. The method of claim 1, wherein the averaging is done using a weighted average.

8. The method of claim 7, wherein a weight for a particular probability is determined by at least one of a number of counts used to calculate the probability and a standard deviation value associated with both the navigation event and the chronological data used to calculate the probability.

9. A non-transitory computer-readable storage medium comprising instructions that, when executed by a processor, cause the processor to perform a method comprising:

storing a set of navigation data, the navigation data comprising one or more navigation events and one or more selection counts associated with each navigation event, the navigation events and selection counts indexed by chronological data, and a value of the chronological data indicating when a navigation event was selected;

determining a current chronological value, the current chronological value representing a present time;

identifying a subset of the navigation data corresponding to the current chronological value;

determining a ratio of a selection count of a particular navigation event contained within the subset of the navigation data to a count of all selection counts contained within the subset of the navigation data; and

determining a probability of selection of the particular navigation event using the ratio, such that the probability may be used by a web browser to assist with network navigation.

10. The non-transitory computer-readable storage medium of claim 9, further comprising identifying the given navigation event as a likely navigation event based upon the probability of selection.

11. The non-transitory computer-readable storage medium of claim 10, further comprising:

determining a probability of selection of a plurality of navigation events; and

identifying a navigation event with the highest probability of selection as a likely navigation event.

12. The non-transitory computer-readable storage medium of claim 10, further comprising:

determining a probability of selection of a plurality of navigation events; and

identifying one of the navigation events of the plurality of navigation events with the highest probability of selection as a likely navigation event.

13. The non-transitory computer-readable storage medium of claim 10, further comprising prerendering the likely navigation event.

14. The non-transitory computer-readable storage medium of claim 10, wherein the chronological data is at least 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. A processing system for predicting a user navigation event, the processing system comprising:

at least one processor; and

a memory, coupled to the processor, for storing a set of navigation data, the navigation data comprising one or more navigation events and one or more selection counts associated with each navigation event, the navigation events and selection counts indexed by chronological data, and a value of the chronological data indicating when a navigation event was selected;

wherein the processor is configured to;

determine a current chronological value, the current chronological value representing a present time;

identify a subset of the navigation data corresponding to the current chronological value;

determine a ratio of a selection count of a particular navigation event contained within the subset of the navigation data to a count of all selection counts contained within the subset of the navigation data; and

determine a probability of selection of the particular navigation event using the ratio, such that the probability may be used by a web browser to assist with network navigation.

16. The processing system of claim 15, wherein the processor is further configured to identify the given navigation event as a likely navigation event based upon the probability of selection.

17. The processing system of claim 16, wherein the processor is further configured to execute the web browser to prerender the most likely network navigation destination.

18. The processing system of claim 15, wherein the chronological data is at least one of a day of week, a day of month, a minute of an hour, a time of day, a month of year, and a weekday or weekend.

19. The processing system of claim 15, wherein the navigation events are uniform resource locator pairs, the pairs representing a source uniform resource locator and a destination uniform resource locator pair.

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

storing a set of navigation data, the navigation data comprising one or more navigation events and one or more selection counts associated with each navigation event, the navigation events and selection counts indexed by chronological data, and a value of the chronological data indicating when a navigation event was selected;

determining a current chronological value, the current chronological value representing a present time;

identifying a plurality of subsets of the navigation data, each subset corresponding to a particular type of chronological data and to the current chronological value;

determining, using a processor, a plurality of probabilities of the given navigation event, with a probability associated with each of the subsets, and each probability associated with a different type of chronological data; and

determining an overall probability of the given navigation event by averaging the plurality of probabilities, such that the overall probability may be used by a web browser to assist with network navigation.