Method for adaptive location assignment to IP-indexed data streams from partially observable data
Disclosed is a method of adaptive assignment of location to internet protocol (IP) indexed data streams using machine learning from partially observable location data. The method includes (i) generating an IP to location map (NM1) and a location to IP map (NM2) by (i) mapping the IP address from location indexed data streams to corresponding location temporally and vice versa, in a base map, (ii) scoring and ranking each entry in the NM1 and the NM2 based on a frequency of use of the IP address, and a number of unique entity identifiers per IP address or per location, (iii) filtering each entry in the NM1 and the NM2 to generate a dynamic IP to location map, and (iv) estimating, a location for an IP indexed data streams at multiple levels of resolutions based on the dynamic IP to location map and an active ST region of each entity.
1. A method for predicting a real-time location for non-location indexed data events based on a partially observable plurality of location indexed data streams, the method comprising:
obtaining, in real time, a plurality of location indexed data streams of entity activities from a plurality of independently controlled data sources, wherein the plurality of location indexed data streams partially characterizes an activity of at least one entity;
generating and updating in the real-time, an IP to location map by mapping a first set of internet protocol (IP) addresses from the one or more location indexed data streams to a first set of locations temporally, wherein entries in the IP to location map has a one-to-many relationship;
generating and updating in the real-time, a location to IP map by mapping a second set of locations from the one or more location indexed data streams to a second set of IP addresses temporally, wherein entries in the location to IP map has a one-to-many relationship;
scoring and ranking each entry in the IP to location map and the location to IP map based on a frequency of use of IP address, and a number of unique entity identifiers for each IP address or each location;
classifying each IP address in the IP to location map and the location to IP map as a static or a dynamic IP address based on the scoring and ranking of each entry;
filtering each entry in the IP to location map and the location to IP map based on the scoring and the ranking of each entry in the IP to location map and the location to IP map to generate a dynamic IP to location map;
training a machine learning model with (i) real-time location indexed data streams along with an active Spatio-Temporal region of each unique entity identifier, (ii) the dynamic IP to location map and a table comprising last known locations of the at least one entity; and
predicting the real-time location for the non-location indexed data event using the machine learning model that is trained using the dynamic IP to location map and the active Spatio-Temporal (ST) region for each unique entity identifier associated with the IP address, wherein the non-location indexed data event is an event of data production via an entity device without corresponding location of the entity device.
2. The method of claim 1 , further comprising identifying the active Spatio-Temporal region for each unique entity identifier associated with the IP address based on the plurality of location indexed data streams.
3. The method of claim 1 , wherein the method comprises extrapolating data points in the plurality of location indexed data streams to estimate missed location data on time series and adding an estimated location to the IPs to fill in time-gaps in the plurality of location indexed data streams.
4. The method of claim 3 , wherein the method comprises updating the IP to location map and the location to IP map based on the plurality of location indexed data streams filled with missed location data on time series.
5. The method of claim 1 , wherein the method comprises updating the IP to location map and the location to IP map when a new set of data streams arrives with Bayesian updating technique using Kalman filter.
6. The method of claim 1 , wherein the machine learning model that is trained receives an input query comprises an IP address and to output real-time location information associated with IP address received.
7. The method of claim 1 , wherein the plurality of location indexed data streams comprises latitude data and longitude data.
8. The method of claim 1 , wherein the plurality of location indexed data streams comprises an IP address, a Spatio-Temporal information and at least one entity identifier, wherein the at least one entity identifier comprises at least one of (i) an advertisement identifier (AdID), (ii) a cookie identifier (C) or (iii) a device identifier.
9. The method of claim 1 , wherein the plurality of location indexed data streams of the entity activity comprises at least one of (i) location pings from one or more application engaged on the one or more entity devices, (ii) access pings from wireless hot-spots, (iii) active subscriber's data and location in different geo-areas (GSM) from the mobile network, and (iv) local information from traffic sensors or a public CCTV camera for security.
10. One or more non-transitory computer-readable storage medium storing the one or more sequence of instructions, which when executed by the one or more processors, causes to perform a method of predicting a real-time location for non-location indexed data events based on a partially observable plurality of location indexed data streams comprising:
obtaining, in real time, a plurality of location indexed data streams of entity activities from a plurality of independently controlled data sources, wherein the plurality of location indexed data streams partially characterizes an activity of at least one entity;
generating and updating in the real-time, an IP to location map by mapping a first set of internet protocol (IP) addresses from the one or more location indexed data streams to a first set of locations temporally, wherein entries in the IP to location map has a one-to-many relationship;
generating and updating in the real-time, a location to IP map by mapping a second set of locations from the one or more location indexed data streams to a second set of IP addresses temporally, wherein entries in the location to IP map has a one-to-many relationship;
scoring and ranking each entry in the IP to location map and the location to IP map based on a frequency of use of IP address, and a number of unique entity identifiers for each IP address or each location;
classifying each IP address in the IP to location map and the location to IP map as a static or a dynamic IP address based on the scoring and ranking of each entry;
filtering each entry in the IP to location map and the location to IP map based on the scoring and the ranking of each entry in the IP to location map and the location to IP map to generate a dynamic IP to location map;
training a machine learning model with (i) real-time location indexed data streams along with an active Spatio-Temporal region of each unique entity identifier, (ii) the dynamic IP to location map and a table comprising last known locations of the at least one entity; and
predicting the real-time location for the non-location indexed data event using the machine learning model that is trained using the dynamic IP to location map and the active Spatio-Temporal (ST) region for each unique entity identifier associated with the IP address, wherein the non-location indexed data event is an event of data production via an entity device without corresponding location of the entity device.
11. A system for predicting a real-time location for non-location indexed data events based on a partially observable plurality of location indexed data streams, wherein said system comprises,
a processor;
a memory that stores set of instructions, which when executed by the processor, causes to perform:
obtaining, in real time, a plurality of location indexed data streams of entity activities from a plurality of independently controlled data sources, wherein the plurality of location indexed data streams partially characterizes an activity of at least one entity;
generating and updating in the real-time, an IP to location map by mapping a first set of internet protocol (IP) addresses from the one or more location indexed data streams to a first set of locations temporally, wherein entries in the IP to location map has a one-to-many relationship;
generating and updating in the real-time, a location to IP map by mapping a second set of locations from the one or more location indexed data streams to a second set of IP addresses temporally, wherein entries in the location to IP map has a one-to-many relationship;
scoring and ranking each entry in the IP to location map and the location to IP map based on a frequency of use of IP address, and a number of unique entity identifiers for each IP address or each location;
classifying each IP address in the IP to location map and the location to IP map as a static or a dynamic IP address based on the scoring and ranking of each entry;
filtering each entry in the IP to location map and the location to IP map based on the scoring and the ranking of each entry in the IP to location map and the location to IP map to generate a dynamic IP to location map;
training a machine learning model with (i) real-time location indexed data streams along with an active Spatio-Temporal region of each unique entity identifier (ii) the dynamic IP to location map and a table comprising last known locations of the at least one entity; and
predicting the real-time location for the non-location indexed data event using the machine learning model that is trained using the dynamic IP to location map and the active Spatio-Temporal (ST) region for each unique entity identifier associated with the IP address, wherein the non-location indexed data event is an event of data production via an entity device without corresponding location of the entity device.
12. The system of claim 11 , wherein the processor is configured to identify the active Spatio-Temporal region for each unique entity identifier associated with the IP address based on the plurality of location indexed data streams.
13. The system of claim 11 , wherein the processor is configured to extrapolate data points in the plurality of location indexed data streams to estimate missed location data on time series and add estimated location to the IPs to fill in time-gaps in the plurality of location indexed data streams.
14. The system of claim 13 , wherein the processor is configured to update the IP to location map and the NM2 based on the plurality of location indexed data streams filled with missed location data on time series.
15. The system of claim 11 , wherein the processor is configured to update the IP to location map and the location to IP map when a new set of data streams arrives with Bayesian updating technique using Kalman filter.
16. The system of claim 11 , wherein the machine learning model that is trained receives an input query comprises an IP address and to output real-time location information associated with IP address received.
17. The system of claim 11 , wherein the plurality of location indexed data streams comprises an IP address, a Spatio-Temporal information and at least one entity identifier, wherein the at least one entity identifier comprises at least one of (i) an advertisement identifier (AdID), (ii) a cookie identifier (C) or (iii) a device identifier.
18. The system of claim 11 , wherein the plurality of location indexed data streams of the entity activity comprises at least one of (i) location pings from one or more application engaged on the one or more entity devices, (ii) access pings from wireless hot-spots, (iii) active subscriber's data and location in different geo-areas (GSM) from the mobile network, and (iv) local information from traffic sensors or a public CCTV camera for security.