Pattern labeling
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 point in time. The log spans a period of time and some of 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 a pattern among the geo-locations of the user at the points in time; and determining for some of the geo-locations of the user at the points in time, a place corresponding to the geo-location; and inferring by the computing device a routine of the user based at least in part the pattern and the places.
1. A method comprising:
by a computing device, accessing a log associated with a user, the log comprising 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, each of 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 one or more geo-location centroids based on a distance between the respective geo-location centroid and each of the geo-location data points, wherein each geo-location centroid is representative of the plurality of geo-location data points obtained during the particular time of day of the particular day of a week;
by the computing device, determining a place corresponding to each of the geo-location centroids, wherein the place corresponds to one or more particular activities;
by the computing device, updating a social graph associated with the user with information associated with the activities;
by the computing device, determining a spatial center of a plurality of geo-location centroids based on a distance between each geo-location centroid and its respective spatial center, each spatial center representing one or more of the plurality of geo-location centroids of the particular time of the particular day of the week;
by the computing device, determining a time-based routine of the particular day of the week based at least in part on a number of spatial centers of each particular time of day of the particular day of the week, the time-based routine comprising a pattern of a plurality of spatial centers of a plurality of times of the day of the particular day of the week; and
by the computing device, determining a probability that the user will be at a particular spatial center at the particular time of day of the particular day of the week based at least in part on the number of geo-location centroids being represented by the particular spatial center.
2. The method of claim 1 , the method further comprising inferring by the computing device the user is employed at a particular business based at least in part on a number of entries corresponding to a geo-location of the particular business at past points of time corresponding to working hours.
3. The method of claim 1 , wherein the place comprises a residence, grocery store, restaurant, supermarket, sporting venue, landmark, freeway, movie theater, or place of employment.
4. The method of claim 3 , wherein the activity comprises working, patronizing, residing, attending an event, or visiting.
5. The method of claim 1 , wherein:
the social graph comprises a plurality of nodes and edges connecting the nodes; and
at least one node in the graph corresponding to the user.
6. One or more computer-readable non-transitory storage media storing computer-readable instructions which when executed by a processor device, cause to processor device to:
access a log associated with a user, the log comprising 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, each of 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 one or more geo-location centroids based on a distance between the respective geo-location centroid and each of the geo-location data points, wherein each geo-location centroid is representative of the plurality of geo-location data points obtained during the particular time of day of the particular day of a week:
determine a place corresponding to each of the geo-location centroids, wherein the place corresponds to one or more particular activities;
update a social graph associated with the user with information associated with the activities;
determine a spatial center of a plurality of geo-location centroids based on a distance between each geo-location centroid and its respective spatial center, each spatial center representing one or more of the plurality of geo-location centroids of the particular time of the particular day of the week;
determine a time-based routine of the particular day of the week based at least in part on a number of spatial centers of each particular time of day of the particular day of the week, the time-based routine comprising a pattern of a plurality of spatial centers of a plurality of times of the day of the particular day of the week; and
determine a probability that the user will be at a particular spatial center at the particular time of day of the particular day of the week based at least in part on the number of geo-location centroids being represented by the particular spatial center.
7. The media of claim 6 , comprising instructions to infer the user is employed at a particular business based at least in part on a number of entries corresponding to a geo-location of the particular business at past points of time corresponding to working hours.
8. The media of claim 6 , wherein the place comprises a residence, grocery store, restaurant, supermarket, sporting venue, landmark, freeway, movie theater, or place of employment.
9. The media of claim 8 , wherein the activity comprises working, patronizing, residing, attending an event, or visiting.
10. The media of claim 6 , wherein the social graph comprises a plurality of nodes and edges connecting the nodes; and at least one node in the graph corresponding to the user.
11. 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, the log comprising 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, each of 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 one or more geo-location centroids based on a distance between the respective geo-location centroid and each of the geo-location data points, wherein each geo-location centroid is representative of the plurality of geo-location data points obtained during the particular time of day of the particular day of a week;
determine a place corresponding to each of the geo-location centroids, wherein the place corresponds to one or more particular activities;
update a social graph associated with the user with information associated with the activities;
determine a spatial center of a plurality of geo-location centroids based on a distance between each geo-location centroid and its respective spatial center, each spatial center representing one or more of the plurality of geo-location centroids of the particular time of the particular day of the week;
determine a time-based routine of the particular day of the week based at least in part on a number of spatial centers of each particular time of day of the particular day of the week, the time-based routine comprising a pattern of a plurality of spatial centers of a plurality of times of the day of the particular day of the week; and
determine a probability that the user will be at a particular spatial center at the particular time of day of the particular day of the week based at least in part on the number of geo-location centroids being represented by the particular spatial center.