Systems and methods for probabilistic point of interest visit count estimation
In some implementations, a device may obtain location data associated with one or more user devices, wherein the location data indicates, for the one or more user devices, respective geographic locations and respective durations. The device may determine, based on the location data, one or more point of interest (POI) locations associated with respective user devices from the one or more user devices. The device may determine, for each user device from the one or more user devices, probability values for respective POI locations from the one or more POI locations, wherein the probability values indicate likelihoods of user visits at the respective POI locations. The device may determine one or more probability metrics for the respective POI locations, from the one or more POI locations, associated with user visits to the respective POI locations. The device may store the one or more probability metrics.
1 . A method, comprising:
obtaining, by a device, location data associated with one or more user devices,
wherein the location data indicates, for the one or more user devices, respective geographic locations and respective durations, and
determining, by the device and based on the location data, one or more point of interest (POI) locations associated with respective user devices from the one or more user devices;
determining, by the device and for each user device from the one or more user devices, probability values for respective POI locations from the one or more POI locations,
wherein the probability values indicate likelihoods of user visits at the respective POI locations, and
wherein the probability values are based on uncertainty ranges associated with the respective geographic locations and geographic footprints associated with the respective POI locations;
determining, by the device, one or more probability metrics for the respective POI locations associated with user visits to the respective POI locations,
wherein the one or more probability metrics include an estimated total visit count, and
wherein determining the one or more probability metrics comprises:
identifying, for a POI location from the one or more POI locations, one or more durations, from the respective durations, associated with the POI location;
determining estimated visit durations based on the one or more durations and respective probability values, from the probability values, associated with the POI location and associated with the respective durations; and
determining an estimated total visit duration based on a sum of the estimated visit durations; and
performing, by the device, an action based on the one or more probability metrics.
2 . The method of claim 1 , wherein determining the probability values comprises:
determining, for a user device from the one or more user devices, visit scores for the respective POI locations based on a geographic location and an uncertainty range associated with the user device and geographic footprints associated with the respective POI locations; and
determining the probability values based on the visit scores for the respective POI locations and a total visit score associated with the user device.
3 . The method of claim 2 , wherein the visit scores for the respective POI locations are based on a geographic overlap of an uncertainty range associated with the geographic location and the geographic footprints associated with the respective POI locations.
4 . The method of claim 2 , wherein the visit scores for the respective POI locations are based on a location probability distribution over an uncertainty range associated with the geographic location and the geographic footprints associated with the respective POI locations.
5 . The method of claim 1 , wherein the one or more probability metrics include at least one of:
the estimated total visit count,
the estimated total visit duration, or
an error metric.
6 . The method of claim 1 , wherein the one or more probability metrics include an estimated total visit count, and wherein determining the one or more probability metrics comprises:
determining, for a POI location from the one or more POI locations, the estimated total visit count based on a sum of one or more probability values, from the probability values for the respective POI locations, that are associated with the POI location.
7 . The method of claim 1 , wherein the one or more probability metrics include a error metric, and wherein determining the one or more probability metrics comprises:
determining the error metric for a POI location, from the one or more POI locations, based on a coefficient of variation associated with one or more probability values, from the probability values, associated with the POI location.
8 . The method of claim 1 , wherein the one or more probability metrics include an error metric, and wherein the error metric, for a POI location from the one or more POI locations, includes a standard deviation of a distribution of one or more probability values, from the probability values, associated with the POI location.
9 . The method of claim 1 , wherein the location data is based on triangulation data.
10 . The method of claim 1 , wherein the location data includes one or more parameters associated with communications between the one or more user devices and one or more base stations.
11 . A device, comprising:
one or more processors configured to:
obtain location data associated with one or more user devices,
wherein the location data indicates, for the one or more user devices, respective geographic locations and respective durations, and
determine, based on the location data, one or more point of interest (POI) locations associated with respective user devices from the one or more user devices;
determine, for each user device from the one or more user devices, probability values for respective POI locations from the one or more POI locations,
wherein the probability values indicate a likelihood of a user visit at the respective POI locations;
determine one or more probability metrics for the respective POI locations, from the one or more POI locations, associated with user visits to the respective POI locations,
wherein the one or more probability metrics include an estimated total visit count, and
wherein determining the one or more probability metrics comprises:
identifying, for a POI location from the one or more POI locations, one or more durations, from the respective durations, associated with the POI location;
determining estimated visit durations based on the one or more durations and respective probability values, from the probability values, associated with the POI location and associated with the respective durations; and
determining an estimated total visit duration based on a sum of the estimated visit durations; and
perform an action based on the one or more probability metrics.
12 . The device of claim 11 , wherein the probability values are based on an uncertainty range associated with the respective geographic locations and a geographic footprint associated with the respective POI locations.
13 . The device of claim 11 , wherein the one or more processors, to determine the probability values, are configured to:
determine, for a user device from the one or more user devices, a visit score for the respective POI locations based on a geographic location and an uncertainty range associated with the user device and a geographic footprint associated with the respective POI locations; and
determine the probability values based on the visit score for the respective POI locations and a total visit score associated with the user device.
14 . The device of claim 11 , wherein the one or more probability metrics include at least one of:
the estimated total visit count,
the estimated total visit duration, or
an error metric.
15 . The device of claim 11 , wherein the one or more probability metrics include an error metric, and wherein the error metric, for a POI location from the one or more POI locations, includes a generalized binomial distribution of one or more probability values, from the probability values, associated with the POI location.
16 . The device of claim 11 , wherein the location data includes one or more parameters associated with communications between the one or more user devices and one or more base stations.
17 . A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the device to:
obtain location data associated with one or more user devices,
wherein the location data indicates, for the one or more user devices, respective geographic locations and respective durations;
determine, based on the location data, one or more point of interest (POI) locations associated with respective user devices from the one or more user devices;
determine, for each user device from the one or more user devices, probability values for respective POI locations from the one or more POI locations,
wherein the probability values indicate likelihoods of user visits at the respective POI locations, and
wherein the probability values are based on uncertainty ranges associated with the respective geographic locations and geographic footprints associated with the respective POI locations;
determine one or more probability metrics for the respective POI locations associated with user visits to the respective POI locations,
wherein the one or more probability metrics include an estimated total visit count, and
wherein determining the one or more probability metrics comprises:
identifying, for a POI location from the one or more POI locations, one or more durations, from the respective durations, associated with the POI location;
determining estimated visit durations based on the one or more durations and respective probability values, from the probability values, associated with the POI location and associated with the respective durations; and
determining an estimated total visit duration based on a sum of the estimated visit durations; and
store the one or more probability metrics.
18 . The non-transitory computer-readable medium of claim 17 , wherein the one or more instructions, that cause the device to determine the probability values, cause the device to:
determine, for a user device from the one or more user devices, visit scores for the respective POI locations based on a geographic location associated with the user device and the geographic footprints associated with the respective POI locations; and
determine the probability values based on the visit score for the respective POI locations and a total visit score associated with the user device.
19 . The non-transitory computer-readable medium of claim 18 , wherein the visit scores for the respective POI locations are based on a geographic overlap between an uncertainty range associated with the geographic location and the geographic footprints associated with the respective POI locations.
20 . The non-transitory computer-readable medium of claim 18 , wherein the visit scores for the respective POI locations are based on a location probability distribution over an uncertainty range associated with the geographic location and the geographic footprints associated with the respective POI locations.