Behavior-based inferences and actions

• US 9,574,894 B1
• Filed: 11/19/2010
• Issued: 02/21/2017
• Est. Priority Date: 11/19/2010
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Karakotsios, Kenneth, Bozarth, Bradley, Freed, Ian W.
• Primary Examiner(s): Nguyen, Cuong H
• Application Number:
  US12/950,929
• Time in Patent Office: 2,286 Days
• Field of Search: 701/209, 701409-411, 701/408, 701532-533, 701 55- 56, 701468-469, 701/424, 701467-469, 701521-522, 701/526, 342/350, 342/450, 342/431, 342/457, 455/456.1, 455/457, 455/456.3, 705/500, 705/7.12, 705/14.4, 705/14.63, 715/840, 340/539.13, 706/21
• US Class Current: 1/1
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G01C 21/3617 using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement
• CPC Class Codes: G06Q 10/08 Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
• CPC Class Codes: G07C 5/085 using electronic data carriers
• CPC Class Codes: G07C 5/0858 wherein the data carrier is removable
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/023 using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
• CPC Class Codes: H04W 4/027 using movement velocity, acceleration information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

The position and/or movement of at least one device for a user can be monitored over time, and various types of information inferred based on patterns in that user behavior. A device can determine various locations where a user typically stays for a period of time, as well as the routes the user takes to get to those locations. Based upon time, date, and various other information, the device can infer the type of location and/or route, as well as the likelihood that the user will take a given route to one of those locations at any time. By being able to infer future actions and locations of the user at certain times, a device can proactively provide a variety of functionality to the user, such as to provide suggested alternative routes, move meetings, notify others of estimated times of arrival, and perform other such tasks.

Claims

1. A computer-implemented method, comprising:

monitoring, using a global positioning system (GPS), first location information of a first electronic device associated with a user over at least a first period of time;

storing the first location information for the first electronic device;

monitoring second location information of a second electronic device associated with the user over at least a second period of time after the first period of time, the second electronic device being different from the first electronic device;

storing the second location information for the second electronic device;

analyzing the first location information and the second location information using at least one pattern detection algorithm to identify at least one route and at least one dwell, the at least one dwell corresponding to an approximate range of time and an approximate location where the user was located for at least a minimum amount of time with a first minimum occurrence value, the at least one route corresponding to at least one path that is to, from, or includes the at least one dwell with a second minimum occurrence value;

determining third location information using at least one of the first electronic device or the second electronic device over a third period of time after the second period of time; and

determining a location of the user for at least one future time based at least in part on the third location information and information associated with the at least one route and the at least one dwell.

3. The computer-implemented method of claim 1, further comprising:

storing user behavior information, including one or more actions with respect to at least one of the first electronic device or the second electronic device, at times corresponding to the information associated with the at least one route and the at least one dwell; and

detecting an action with respect to the at least one of the first electronic device or the second electronic device,

wherein the action includes following at least a portion of the at least one route, arriving at the at least one dwell, leaving the at least one dwell, completing a task, or inputting information into the at least one of the first electronic device or the second electronic device, and

wherein the location of the user for the at least one future time is further determined based at least in part by comparing the action with the user behavior information.

2. A non-transitory computer-readable medium including instructions, the instructions when executed by a processor of a computing device causing the computing device to:

monitor, using a GPS, first location information of the computing device over at least a first period of time, the computing device associated with a user;

monitor second location information of a second computing device associated with the user over at least a second period of time after the first period of time, the second computing device being different from the computing device;

analyze the first location information and the second location information to identify a route and a dwell;

determine third location information using at least one of the computing device or the second computing device over at least a third period of time after the second period of time; and

determine a location of the user for at least one future time based at least in part on the third location information and information associated with the route and the dwell.

16. The non-transitory computer-readable medium of claim 2, wherein the instructions when executed further cause the computing device to:

perform at least one task based at least in part upon the location of the user for the at least one future time.

18. The non-transitory computer-readable medium of claim 16, wherein the at least one task includes at least one of making an appointment, making a reservation, contacting a second user or a third computing device, adjusting performance of at least one of the computing device or the second computing device, determining available options, or requesting input from the user.

4. A computer-implemented method, comprising:

monitoring, using a GPS, first location information of a first electronic device associated with a user over at least a first period of time;

monitoring second location information of a second electronic device associated with the user over at least a second period of time after the first period of time, the second electronic device being different from the first electronic device;

analyzing the first location information and the second location information to identify a route and a dwell;

determining third location information using at least one of the first electronic device or the second electronic device over at least a third period of time after the second period of time; and

determining a location of the user for at least one future time based at least in part on the third location information and information associated with the route and the dwell.

5. The computer-implemented method of claim 4, wherein the second location information includes at least one of a position, rate of movement, acceleration, direction of movement, path of movement, or duration of movement.

6. The computer-implemented method of claim 4, wherein the dwell corresponds to an approximate location visited for at least a minimum period of time, and

wherein the route corresponds to at least one path to, from, or including the dwell.

7. The computer-implemented method of claim 6, wherein roads are excluded from being determined as dwells.

10. The computer-implemented method of claim 4, further comprising:

obtaining position data, from an accelerometer, and storing at least a portion of the position data with a time of occurrence as at least a portion of the second location information.

11. The computer-implemented method of claim 4, wherein the location of the user for the at least one future time is further determined based at least in part on at least one of calendar, task, address, schedule, or contact information.

12. The computer-implemented method of claim 4, further comprising:

based at least in part upon the location of the user for the at least one future time, performing at least one task using at least one of the first electronic device or the second electronic device.

13. The computer-implemented method of claim 12, wherein the at least one task includes at least one of prompting with second information based on the at least one task, contacting another device with third information about the at least one task, obtaining additional information about the location of the user for the at least one future time, moving a scheduled item based on the location of the user for the at least one future time, or scheduling an item based on the location of the user for the at least one future time.

14. The computer-implemented method of claim 4, further comprising:

determining whether the user will arrive at a scheduled meeting at or before a scheduled time.

15. The computer-implemented method of claim 14, further comprising:

determining that the user will arrive at the scheduled meeting after the scheduled time; and

performing at least one of moving the scheduled meeting, rescheduling the scheduled meeting, sending a notification, suggesting different routes to the scheduled meeting, or suggesting at least one alternative action.

17. The computer-implemented method of claim 12, wherein the at least one task includes at least one of making an appointment, making a reservation, modifying performance of the at least one of the first electronic device or the second electronic device, determining available options, or requesting input.

19. The computer-implemented method of claim 4, further comprising:

storing user behavior information, comprising one or more actions, with respect to at least one of the first electronic device or the second electronic device at times corresponding to the information associated with the route and the dwell; and

detecting an action with respect to the at least one of the first electronic device or the second electronic device,

wherein the one or more actions include at least one of being near a specific position, having a rate of movement, having a direction of movement, following a path of movement, or having a duration of movement,

wherein the location of the user for the at least one future time is further determined based at least in part by comparing the action with the user behavior information.

8. A computing device, comprising:

a processor;

a GPS; and

a memory device including instructions that, when executed by the processor, cause the computing device to;

monitor, using the GPS, first location information of the computing device over at least a first period of time, the computing device associated with a user;

monitor second location information of a second computing device associated with the user over at least a second period of time after the first period of time, the second computing device being different from the computing device;

analyze the first location information and the second location information to identify a route and a dwell;

determine third location information using at least one of the computing device or the second computing device over at least a third period of time after the second period of time; and

determine a location of the user for at least one future time based at least in part on the third location information and information associated with the route and the dwell.

9. The computing device of claim 8, wherein the instructions when executed further cause the computing device to:

perform at least one task based at least in part upon the location of the user for the at least one future time.