Location graph based derivation of attributes
Location graph-based derivation of user attributes. Location data associated with a user, such as a current and/or past location at which the user has been, is received. A user attribute data associated with the location data is determined and used to update a user profile associated with the user.
1. A method, comprising:
storing, in a computing apparatus, first location data identifying:
a predetermined first location, and
a set of demographic attributes of past users who have visited the predetermined first location and thus associated with the predetermined first location in the computing apparatus;
receiving, in the computing apparatus, a second location of a mobile device of a user;
mapping, by the computing apparatus, the second location of the mobile device to the predetermined first location;
identifying, by the computing apparatus based on the mapping and the first location data stored in the computing apparatus, the set of demographic attributes of users who have visited the predetermined first location; and
updating, by the computing apparatus, a profile of the user by adjusting the profile of the user, using a weighted algorithm, based on the set of demographic attributes that are identified, via the mapping, from the first location data, wherein in response to further locations of the mobile device being mapped into further predetermined locations that have respective sets of attributes of users who have visited the further predetermined locations respectively, the updating the profile is repeated according to the further predetermined locations, based on the weighted algorithm and the respective sets of attributes, to incrementally improve accuracy of the profile, including confidence levels of attributes in the user profile.
2. The method of claim 1 , wherein a first attribute is associated with a pattern of second users visiting a set of predetermined locations; and the method further comprises:
determining whether locations of the mobile device of the user as being mapped to the set of predetermined locations has the pattern; and
in response to a determination that the locations of the mobile device of the user as being mapped to the set of predetermined locations has the pattern, updating the user profile to include the first attribute.
3. The method of claim 2 , wherein the pattern is based at least in part on times of visiting the set of predetermined locations.
4. The method of claim 1 , wherein the predetermined first location corresponds to a predefined geographic area in which the second location of the mobile device is mapped; and the second location is received in a form of a set of coordinates.
5. The method of claim 1 , further comprising:
updating the first location data for the predetermined first location based on the profile of the user.
6. The method of claim 5 , wherein the updating of the first location data for the predetermined first location is in response to the second location of the mobile device of the user being mapped to the predetermined first location.
7. A method implemented in a computing apparatus, the method comprising:
storing, in the computing apparatus, a plurality of defined location profiles for a plurality of defined locations respectively, wherein:
each of the defined locations is a predetermined geographical area; and
a respective defined location profile in the defined location profiles includes:
a set of demographic attributes of past users who have visited the predetermined geographical area;
storing, in the computing apparatus, a plurality of user profiles for a plurality users respectively, wherein each respective user profile in the user profiles includes:
a set of user attributes; and
a confidence level of each respective user attribute in the set of user attributes that a user represented by the respective user profile has the respective user attribute;
receiving, in the computing apparatus, a location of a mobile device of a user;
mapping, by the computing apparatus, the location of the mobile device of the user to a first defined location among the plurality of defined locations; and
updating, by the computing apparatus, a user profile in the user profiles by adjusting the user profile, using a weighted algorithm, based on the set of demographic attributes that are identified, via the mapping, from the respective defined location profile for the first defined location, wherein in response to further locations of the mobile device being mapped into further defined locations among the plurality of defined locations, the updating the user profile is repeated according to the further defined locations among the plurality of defined locations, based on the weighted algorithm and the respective sets of demographic attributes for the further defined locations, to incrementally improve accuracy of the user profile, including confidence levels of attributes in the user profile.
8. The method of claim 7 , wherein the mapping is performed using a look up table that maps a grid location, determined from coordinates of the location of the first user in a grid reference system, to the first defined location.
9. The method of claim 8 , wherein the grid reference system is a military grid reference system (MGRS).
10. The method of claim 8 , further comprising:
converting, by the computing apparatus, the coordinates of the location of the first user to the grid location in the grid reference system.
11. A method implemented in a computing apparatus, the method comprising:
storing, in the computing apparatus, a plurality of defined location profiles for a plurality of defined locations respectively, wherein:
each of the defined locations is a predetermined geographical area; and
a respective defined location profile in the defined location profiles includes:
a set of demographic attributes of past users who have visited the predetermined geographical area;
storing, in the computing apparatus, a plurality of user profiles for a plurality users respectively, wherein each respective user profile in the user profiles includes:
a set of user attributes; and
a confidence level of each respective user attribute in the set of user attributes that a user represented by the respective user profile has the respective user attribute;
storing, in the computing apparatus, a look up table that maps grid locations predefined in a grid reference system to respective ones of the defined locations;
receiving, in the computing apparatus, coordinates of a location of a mobile device of a user;
converting, by the computing apparatus, the coordinates of the location of the mobile device to a grid location in the grid reference system;
looking up, by the computing apparatus using the grid location converted from the coordinates as a key in the look up table, a first defined location among the plurality of defined locations; and
updating, by the computing apparatus, a user profile in the user profiles by adjusting the user profile, using a weighted algorithm, based on the set of demographic attributes that are identified, via the looking up, from the respective defined location profile for the first defined location, wherein in response to further defined locations among the plurality of defined locations being looked up, the updating the user profile is repeated according to the further defined locations among the plurality of defined locations, based on the weighted algorithm and the respective sets of demographic attributes for the further defined locations, to incrementally improve accuracy of the user profile, including confidence levels of attributes in the user profile.
12. The method of claim 11 , wherein the grid reference system is a military grid reference system (MGRS).
13. The method of claim 11 , wherein the converting, the looking up, and the updating are repeated in response to further receiving coordinates of locations of the users to incrementally improve accuracy of the user profiles and the defined location profiles.
14. The method of claim 11 , further comprising:
personalizing, by the computing apparatus, services provided to the users based on the user profiles.
15. The method of claim 14 , wherein the services include selected content.