Generating data-driven geo-fences

• US 9,838,843 B1
• Filed: 10/13/2016
• Issued: 12/05/2017
• Est. Priority Date: 10/13/2016
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Bajaj, Payal, Mehta, Sanket Vaibhav, Goyal, Tanya, Revankar, Shriram Venkatesh Shet
• Primary Examiner(s): Sarwar, Babar
• Application Number:
  US15/292,982
• Time in Patent Office: 418 Days
• Field of Search: 4554042, 4554121-4142, 455418-4221, 4555521, 4554561-457
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/022 with dynamic range variability

Abstract

The present disclosure is directed toward systems and method for generating geo-fences having boundaries around geographic regions of interest based on historical activity data of a user application on a plurality of client devices. For example, systems and methods described herein involve tracking activity data to identify instances of an application activity associated with an action to promote and identify locations where users more frequently perform the application activity. In addition, systems and methods described herein involve tracking activity data over time to determine geographic regions of interest at different time periods where users more frequently perform application activities. Further, systems and methods described herein involve generating geo-fences around one or more geographic regions of interest.

Claims

1. In a digital medium environment that tracks locations and activities of client devices, a computer-implemented method of dynamically defining a virtual boundary comprising:

receiving an indication of a user action to promote;

identifying an application activity of a user application associated with the user action to promote;

tracking activity data of a plurality of client devices having the user application thereon, the activity data comprising instances of the application activity and an associated location for each instance of the application activity;

analyzing the activity data to determine a geographic region of interest in which a first plurality of users of the plurality of client devices located within the geographic region of interest perform the application activity with a higher frequency than a second plurality of users of the plurality of client devices located outside the geographic region; and

generating a geo-fence comprising a boundary around the geographic region of interest.

2. The method of claim 1, further comprising selectively providing a communication to any client devices having the user application thereon and determined to be located within the boundary of the geo-fence.

3. The method of claim 1, wherein identifying the application activity of the user application associated with the user action to promote comprises identifying a correlation between a client device performing the application activity and a user of the client device performing the user action to promote.

4. The method of claim 1, wherein tracking the activity data of the plurality of client devices comprises:

receiving a collection of activity data; and

filtering the collection of activity data to identify a subset of application activities comprising instances of the application activity of the user application associated with the user action to promote.

5. The method of claim 1, wherein analyzing the activity data to determine the geographic region of interest comprises determining a probability of the plurality of client devices that performed the application activity while at each location across a plurality of locations.

6. The method of claim 5, wherein analyzing the activity data to determine the geographic region of interest further comprises determining a probability that a given client will perform the application activity proximate to each location across the plurality of locations.

7. The method of claim 6, wherein analyzing the activity data to determine the geographic region of interest further comprises identifying ranges of locations of the plurality of locations where the probabilities exceeds a predicted probability threshold.

8. The method of claim 7, wherein generating the geo-fence comprising the boundary around the geographic region of interest comprises defining the boundary of the geo-fence around the ranges of locations of the plurality of locations where a distribution of the probabilities exceeds the predicted probability threshold.

9. The method of claim 1, wherein:

the activity data further comprises an associated time for each instance of the application activity; and

analyzing the activity data to determine the geographic region of interest comprises determining the geographic region of interest for a first time period based on tracked activity data limited to instances of the application activity having an associated time within the first time period.

10. The method of claim 9, further comprising:

analyzing the activity data to determine a second geographic region of interest for a second time period based on tracked activity data limited to instances of the application activity having an associated time within the second time period; and

generating another geo-fence for the second time period comprising a modified boundary around the second geographic region of interest.

11. The method of claim 1, further comprising generating a second geo-fence comprising a second boundary around a non-adjacent geographic region of interest from the boundary around the determined geographic region of interest.

12. In a digital medium environment that tracks locations and activities of client devices, a computer-implemented method of dynamically defining geographic boundaries, the method comprising:

tracking activity data of a plurality of client devices having a user application thereon, the activity data comprising instances of an application activity and associated time and location for each instance of the application activity, the application activity comprising one or more user inputs with respect to the user application;

a step for generating a geo-fence based on the tracked activity data, the geo-fence comprising a boundary around a geographic region of interest within which a first plurality of users of the plurality of client devices have a higher probability to perform the application activity than a second plurality of users of the plurality of client devices outside the geographic region of interest; and

modifying the geo-fence between a first time period and a second time period by adjusting the boundary of the geo-fence based on a difference between the tracked activity for the first time period and the tracked activity for the second time period.

13. The method of claim 12, wherein the step for generating the geo-fence comprises analyzing the activity data to determine one or more geographic regions of interest over time within which users of the plurality of client devices have at least a threshold probability to perform the application activity.

14. The method of claim 12, further comprising:

providing a first communication during the first time period to client devices having the user application thereon and determined to be located within the boundary of the geo-fence during the first time period; and

providing a second communication during the second time period to client devices having the user application thereon and determined to be located within the boundary of the modified geo-fence during the second time period.

15. The method of claim 12, further comprising:

receiving an indication of a user action to promote; and

identifying that the application activity is associated with the user action to promote, wherein tracking the activity data of the plurality of client devices comprises selectively tracking instances of the application activity associated with the user action to promote.

16. The method of claim 12, wherein modifying the geo-fence comprises enlarging the boundary of the geo-fence from the first time period to the second time period to reflect a higher frequency of tracked instances of the application activity within a proximity of the boundary of the geo-fence for the first time period.

17. The method of claim 12, wherein modifying the geo-fence comprises shrinking the boundary of the geo-fence from the first time period to the second time period to reflect a lower frequency of tracked instances of the application activity within a proximity of the boundary of the geo-fence for the first time period.

18. The method of claim 12, further comprising generating a new geo-fence for the second time period having a non-adjacent boundary to a boundary of modified geo-fence.

19. A system for tracking locations and activities of client devices and generating geographic boundaries comprising:

a memory comprising;

an indication of a user action to promote; and

activity data comprising tracked instances of application activities by a plurality of client devices associated with the user action to promote, the activity data further comprising time and geographic data associated with each instance of the application activity, the application activity comprising one or more user inputs with respect to a user application on the plurality of client devices; and

a server device comprising instructions thereon that, when executed by at least one processor, cause the server device to;

analyze the activity data to determine a geographic region of interest, wherein analyzing the activity data to determine the geographic region of interest comprises;

determining, based on the activity data, a predicted probability across a plurality of locations that indicates a probability at each location of the plurality of locations that a given client device at each location would perform the application activity; and

identifying a range of locations of the plurality of locations having determined predicted probabilities that exceed a threshold probability; and

generate a geo-fence comprising a boundary around the determined geographic region of interest.

20. The system of claim 19, further comprising instructions that cause the server device to:

determine that a client device having the user application is located within the boundary of the geo-fence; and

in response to determining that the client device having the user application is located within the boundary of the geo-fence, provide a communication to the client device via the user application.