User description based on contexts of location and time
A description of a user is estimated based on the context of a user's past and present locations. A disclosed data-processing system continually receives data points for each user that represent spatial and/or temporal events. These events represent, for example, presence of a person at a specific geographic location such as a geographic area or point of interest (POI). The data-processing system evaluates the received data points in relation to one or more of the geographic locations, yielding results that are also based on the demographic characteristics of each visited location and the commercial characteristics of each visited location. The data-processing system evaluates the data points also to determine patterns exhibited in each user's activity or inactivity, and patterns exhibited in the distance traveled and the type of travel. The data-processing system bases the user descriptions on the results of these evaluations.
1. A sensor analytics system, comprising:
a server system comprising one or more servers configured to be communicatively coupled to a data store;
one or more transceivers communicatively coupled to the one or more servers to facilitate access to a telecommunications network; and
the one or more servers communicatively coupled to memory storing instructions that, when executed by the one or more servers, cause the sensor analytics system to:
receive, via the telecommunications network and by the one or more transceivers a plurality of data points D N that are associated with a user and that are derived from a user device and/or position determining equipment, wherein each data point in the plurality of data points D N represents a spatial-temporal event such that i) a first data point D 1 from the plurality of data points D N includes an indication of a first time t 1 , and a first geolocation l 1 and ii) a second data point D 2 from the plurality of data points D N includes an indication of a second time t 2 and an indication of a second geolocation l 2 ;
process the plurality of data points D N to determine a plurality of characteristics c N and one or more differences between the first data point and the second data point, the processing comprising:
determine a difference in time between the first time t 1 and the second time t 2 ;
determine a difference in geolocation between the first geolocation l 1 and the second geolocation l 2 ;
determine a first characteristic c 1 from the plurality of characteristics C N , the first characteristic c 1 being a characteristic of the first geolocation l 1 ;
evaluate the first data point D 1 in relation to the first geolocation l 1 yielding a first result that is based at least in part on the first characteristic c 1 ;
determine a second characteristic c 2 from the plurality of characteristics c N , the second characteristic c 2 being a characteristic of the second geolocation l 2 ;
evaluate the second data point D 2 in relation to the second geolocation l 2 yielding a second result that is based at least in part on the second characteristic c 2 ;
determine an entropy of travel based at least in part on a pattern of inactivity represented in the plurality of data points D N and on a number of distinct characteristics represented in the plurality of characteristics c n , over an observation period t N , the entropy of travel characterizing randomness of the plurality of characteristics C N ;
generate a description of the user, based in part on the first result, the second result, and the entropy of travel of the plurality of data points D N , the description of the user denoting one or more attributes of the user in relation to the plurality of geolocations l N and the entropy of travel;
generate a signal indicating an action to be performed based at least in part on the description of the user; and
generate a signal to cause the description of the user to be stored in the data store.
2. The sensor analytics system of claim 1 , the instructions to cause the one or more servers to determine the entropy of travel further including instructions to cause the one or more servers to:
determine the entropy of travel based in part on patterns of activity represented in the plurality of data points D N .
3. The sensor analytics system of claim 1 , wherein the first geolocation l 1 is associated with a point of interest.
4. The sensor analytics system of claim 1 , the instructions further causing the sensor analytics system to:
assess distance traveled by the user based on the difference in geolocation between the first geolocation l 1 the second geolocation l 2 and the difference between the first time t 1 and the second time t 2 , the description of the user based in part on the distance traveled.
5. The sensor analytics system of claim 1 , the instructions further causing the sensor analytics system to:
assess the pattern of inactivity of the user based at least in part on the difference in time between the first time t 1 and the second time t 2 .
6. The sensor analytics system of claim 1 , wherein the characteristic is associated with at least one of a demographic category, a commercial category, or a type of travel category.
7. The sensor analytics system of claim 1 , the instructions further causing the sensor analytics system to:
generate customized content for the user based in part on the description of the user.
8. The sensor analytics system of claim 1 , the instructions further causing the sensor analytics system to normalize the plurality of data points D N based on a number of data points within the plurality of data points D N to yield a normalized data set N N , the first characteristic c 1 , the second characteristic c 2 , and the entropy of travel determined based on the normalized data set N N .
9. The sensor analytics system of claim 1 , wherein the user is a first user and the user device and/or position determining equipment is a first user device and/or position determining equipment, the instructions further causing the sensor analytics system to:
receive, via the telecommunications network, a plurality of data points D M that are associated with a second user and that are derived from a second user device and/or position determining equipment, each data point in the plurality of data points D M represents a spatial-temporal event such that a third data point D 3 from the plurality of data points D M includes an indication of a third time t 3 , and a third geolocation l 3 ;
process the plurality of data points D M to determine a plurality of characteristics c M ,
determining a third characteristic c 3 from the plurality of characteristics c M , the third characteristic c 3 being a characteristic of the third geolocation l 3 ; and
comparing the first characteristic c 1 to the third characteristic c 3 , the description of the first user generated based in part on the comparison of the first characteristic c 1 to the third characteristic c 3 .
10. The sensor analytics system of claim 1 , wherein the user is a first user and the user device and/or position determining equipment is a first user device and/or position determining equipment, the instructions further causing the sensor analytics system to:
receive, via the telecommunications network, a plurality of data points D M that are associated with a second user and that are derived from a second user device and/or position determining equipment, each data point in the plurality of data points D M represents a spatial-temporal event such that a third data point D 3 from the plurality of data points D M includes an indication of a third time t 3 , and a third geolocation l 3 ;
normalize the plurality of data points D N based on a number of geolocations represented in the plurality of data points D N to yield a normalized data set N N , the plurality of characteristics C N determined based on the normalized data set N N ;
normalize the plurality of data points D M based on a number of geolocations represented in the plurality of data points D M to yield a normalized data set N M ;
process the normalized data set N M to determine a plurality of characteristics c M ; and
comparing the plurality of characteristic c N to the plurality of characteristics c M , the description of the first user generated based in part on the comparison of the first plurality of characteristics c N to the second plurality of characteristics c M .
11. The sensor analytics system of claim 1 , further comprising:
identify a plurality of usage gaps associated with differences in time between data points having indications of different geolocations in the plurality of data points D N to yield an inactivity measure, the entropy of travel based in part on the inactivity measure; and
assign each usage gap from the plurality of usage gaps to a bucket from a plurality of buckets that is associated with a length of that usage gap, the entropy of travel based at least in part on the plurality of usage gaps and the distribution of the plurality of usage gaps between the plurality of buckets.
12. A method comprising:
receiving, via a network, by a transceiver of a data-processing system, i) a plurality of data points D N that are associated with a first user and that are derived from a first user device and/or position determining equipment and ii) a plurality of data points D M that are associated with a second user and that are derived from a second user device and/or position determining equipment, each data point from each of the plurality of data points D N and the plurality of data points D M includes an indication of a geolocation and an indication of a time;
determining one or more differences between a first data point from the plurality of data points D N and a second data point from the plurality of data points D N ;
normalizing the plurality of data points D N based on a number of geolocations represented in the plurality of data points D N and an observational period represented by the plurality of data points D N to yield a normalized data set N N ,
determining, by the data-processing system and using the normalized data set N N , a characteristic of the first user based on a characteristic of at least one geolocation visited by the first user, yielding a value for the characteristic of the first user that is based at least in part on the characteristic of the at least one geolocation visited by the first user;
generating, by the data-processing system, a description of the first user, based in part on the value of the characteristic of the first user;
determining one or more differences between a third data point from the plurality of data points D M and a fourth data point from the plurality of data points D M ;
normalizing the plurality of data points D M based on the number of geolocations represented in the plurality of data points D M and an observational period represented by the plurality of data points D M to yield a normalized data set N M ;
determining, by the data-processing system and using the normalized data set N M , a characteristic of the second user based on a characteristic of at least one geolocation visited by the second user, yielding a value for the characteristic of the second user that is based at least in part on the at least one geolocation visited by the second user;
comparing the value of the characteristic of the first user to the value of the characteristic of the second user; and
generating, by the data-processing system, a signal indicating an action to be performed based at least in part on the comparison of the value of the characteristic of the first user to the value of the characteristic of the second user.
13. The method of claim 12 , further comprising:
determining, by the data-processing system, an entropy of the plurality of data points D N , based at least in part on a number of distinct geolocations represented in the plurality of data points D N the description of the first user based at least in part on the entropy.
14. The method of claim 12 , further comprising:
storing, by the data-processing system, the description of the first user in a data store communicatively coupled to the data-processing system; and
storing an indication of the action to be performed.
15. The method of claim 12 , wherein the first data point from the plurality of data points D N is associated with a first geolocation l 1 , the method further comprising:
evaluating the first data point from the plurality of data points D N , yielding the characteristic associated with the first-geolocation l 1 , the first geolocation l 1 associated with a geographic point of interest, the description of the first user based in part on the characteristic associated with the first geolocation l 1 .
16. The method of claim 12 , wherein determining one or more differences between the first data point from the plurality of data points D N and the second data point from the plurality of data points D N includes assessing distance traveled by the first user based on a difference between a first geolocation associated with the first data point and a second geolocation associated with the second data point, the description of the first user based in part on the distance traveled.
17. The method of claim 12 , wherein the first data point from the plurality of data points D N and the second data point from the plurality of data points D N are each associated with a single geolocation, the method further comprising:
assessing inactivity of the first user based at least in part on a difference in time between a first time associated with the first data point and a second time associated with the second data point, the description of the first user based in part on the inactivity.
18. The method of claim 12 , wherein the characteristic is associated with at least one of a demographic category, a commercial category, or a type of travel category.
19. The method of claim 12 , further comprising:
generating customized content for the first user based in part on the description of the first user.