Routine deviation notification
In one embodiment, a method includes accessing a log associated with a user. The log includes a number of entries that each indicate a geo-location of the user at a particular time of day of a particular day of a week. The entries are based on a geo-location determined and reported by a mobile computing device of the user without manual user input. The method also includes determining one or more geo-location centroids based on a distance between the respective geo-location centroid and each geo-location data point. Each geo-location centroid is representative of one or more of the geo-location data points obtained during the particular time of day of the particular day of a week. The method also includes determining a routine center of one or more of the number of geo-location centroids based on a distance between its respective routine center and each geo-location centroid.
1. A method comprising:
by a computing device, accessing a log associated with a user, wherein the log comprises a plurality of entries that each indicate a geo-location of the user at a particular time of day of a particular day of a week, wherein at least some of the data points being based on a geo-location determined and reported by a mobile computing device of the user without manual user input;
by the computing device, determining a plurality of geo-location centroids based on a distance between the respective geo-location centroid and each geo-location data point, wherein each geo-location centroid is representative of a cluster comprising one or more of the geo-location data points obtained during the particular time of day of the particular day of a week;
by the computing device, determining a routine center of two or more of the plurality of geo-location centroids based on a distance between its respective routine center and each geo-location centroid, wherein each routine center is a spatial center of a respective plurality of geo-location centroids of the particular time of the particular day of the week;
by the computing device, identifying a particular one of the routine centers with a minimum distance to a current geo-location of the mobile computing device, wherein the particular time of day of the particular day of a week of the identified particular one of the routine centers corresponds a current time of the current day of the week; and
by the computing device, sending a notification indicating that the user is deviating from a routine defined by the identified particular one of the routine centers to one or more other users in response to determining that a distance between the identified particular one of the routine centers and the current geo-location of the user is greater than a pre-determined threshold-deviation distance.
2. The method of claim 1 , further comprising determining whether respective current geo-locations of one or more of the other users are within a pre-determined threshold-proximity distance from the current geo-location of the user.
3. The method of claim 2 , wherein sending the notification is further based on a determination that one or more of the other users are within the pre-determined threshold-proximity distance from the current geo-location of the user.
4. The method of claim 1 , further comprising:
accessing a social graph of a social networking system; and
identifying one or more of the other users based at least in part on a node corresponding to the user being connected to one or more nodes corresponding to one or more of the other users by a respective edge of the social graph.
5. The method of claim 4 , wherein the notification is sent via the social-networking system.
6. The method of claim 1 , wherein the notification comprises information identifying the user and the current geo-location.
7. The method of claim 1 , further comprising sending a signal to the mobile computing device that adjusts polling frequency of the geo-location reporting based on the distance between the identified particular one of the routine centers and the current geo-location of the user.
8. The method of claim 1 , wherein the signal increases the polling frequency based on the distance between the identified particular one of the routine centers and the current geo-location of the user being greater than the pre-determined threshold-deviation distance.
9. The method of claim 1 , further comprising determining an exigent circumstance based on detecting a substantially simultaneous deviation of the user and one or more of the other users from the identified particular one of the routine centers.
10. The method of claim 1 , further comprising determining an exigent circumstance based on detecting a deviation of the user from the identified particular one of the routine centers to an unusual geo-location for a prolonged period of time.
11. One or more computer-readable non-transitory storage media embodying software configured when executed to:
access a log associated with a user, wherein the log comprises a plurality of entries that each indicate a geo-location of the user at a particular time of day of a particular day of a week, wherein at least some of the data points being based on a geo-location determined and reported by a mobile computing device of the user without manual user input;
determine a plurality of geo-location centroids based on a distance between the respective geo-location centroid and each geo-location data point, wherein each geo-location centroid is representative of a cluster comprising one or more of the geo-location data points obtained during the particular time of day of the particular day of a week;
determine a routine center of two or more of the plurality of geo-location centroids based on a distance between its respective routine center and each geo-location centroid, wherein each routine center is a spatial center of a respective plurality of geo-location centroids of the particular time of the particular day of the week;
identify a particular one of the routine centers with a minimum distance to a current geo-location of the mobile computing device, wherein the particular time of day of the particular day of a week of the identified particular one of the routine centers corresponds a current time of the current day of the week; and
send a notification indicating that the user is deviating from a routine defined by the identified particular one of the routine centers to one or more other users in response to determining that a distance between the identified particular one of the routine centers and the current geo-location of the user is greater than a pre-determined threshold-deviation distance.
12. The media of claim 11 , wherein the software is further configured to determine whether respective current geo-locations of one or more of the other users are within a pre-determined threshold-proximity distance from the current geo-location of the user.
13. The media of claim 12 , wherein sending the notification is further based on a determination that one or more of the other users are within the pre-determined threshold-proximity distance from the current geo-location of the user.
14. The media of claim 11 , wherein the software is further configured to:
access a social graph of a social networking system; and
identify one or more of the other users based at least in part on a node corresponding to the user being connected to one or more nodes corresponding to one or more of the other users by a respective edge of the social graph.
15. The media of claim 14 , wherein the notification is sent via the social-networking system.
16. A device comprising:
one or more processors; and
one or more computer-readable non-transitory storage media coupled to the processors and embodying software configured when executed to:
access a log associated with a user, wherein the log comprises a plurality of entries that each indicate a geo-location of the user at a particular time of day of a particular day of a week, wherein at least some of the data points being based on a geo-location determined and reported by a mobile computing device of the user without manual user input;
determine a plurality of geo-location centroids based on a distance between the respective geo-location centroid and each geo-location data point, wherein each geo-location centroid is representative of a cluster comprising one or more of the geo-location data points obtained during the particular time of day of the particular day of a week;
determine a routine center of two or more of the plurality of geo-location centroids based on a distance between its respective routine center and each geo-location centroid, wherein each routine center is a spatial center of a respective plurality of geo-location centroids of the particular time of the particular day of the week;
identify a particular one of the routine centers with a minimum distance to a current geo-location of the mobile computing device, wherein the particular time of day of the particular day of a week of the identified particular one of the routine centers corresponds a current time of the current day of the week; and
send a notification indicating that the user is deviating from a routine defined by the identified particular one of the routine centers to one or more other users in response to determining that a distance between the identified particular one of the routine centers and the current geo-location of the user is greater than a pre-determined threshold-deviation distance.
17. The device of claim 16 , wherein the processor is further operable to determine whether respective current geo-locations of one or more of the other users are within a pre-determined threshold-proximity distance from the current geo-location of the user.
18. The device of claim 17 , wherein sending the notification is further based on a determination that one or more of the other users are within the pre-determined threshold-proximity distance from the current geo-location of the user.
19. The device of claim 16 , wherein the processor is further operable to:
access a social graph of a social networking system; and
identify one or more of the other users based at least in part on a node corresponding to the user being connected to one or more nodes corresponding to one or more of the other users by a respective edge of the social graph.
20. The device of claim 19 , wherein the notification is sent via the social-networking system.