Mobility gene for visit data
Mobility observations may be analyzed to create so-called mobility genes, which may be intermediate data forms from which various analyses may be performed. The mobility genes may include a trajectory gene, which may describe a trajectory through which a user may have travelled. The trajectory gene may be analyzed from raw location observations and processed into a form that may be more easily managed. The trajectory genes may be made available to third parties for analysis, and may represent a large number of location observations that may have been condensed, smoothed, and anonymized. By analyzing only trajectories, a third party may forego having to analyze huge numbers of individual observations, and may have valuable data from which to make decisions.
1. A system comprising:
a hardware platform comprising at least one computer processor;
an analysis system executing on said hardware platform configured to:
receive raw location observations, said raw observations comprising a device identifier, a timestamp and a location definition;
process said raw location observations into a plurality of mobility genes, said mobility genes comprising visits, each of said visits being identified by:
determining a distance traveled from a previous observation;
determining whether said previous observation was classified as a stay;
when said previous observation is classified as a stay, applying a first predefined radius and time period as a classification threshold;
when said previous observation is not classified as a stay, applying a second predefined radius and time period as said classification threshold; and
applying said classification threshold to identify each of said visits;
store said mobility genes;
receive a request for at least one of said mobility genes; and
transmit said at least one of said mobility genes in response to said request.
2. The system of claim 1 , said raw location observations comprising telecom location observations.
3. The system of claim 2 , said telecom location observations comprising access point connection locations.
4. The system of claim 2 , said telecom location observations comprising locations determined by mobile devices.
5. The system of claim 1 , said analysis system further configured to:
identify a first location;
identify a subset of said raw location observations comprising said first location;
generate a set of location statistics for said first location; and
store said set of location statistics as one of said mobility genes.
6. The system of claim 5 :
said first location being a location type; and
said subset of raw location observations being for locations comprising said location type, said subset of raw location observations being for a plurality of physical locations.
7. The system of claim 5 , said location statistics comprising a length of stay.
8. The system of claim 5 :
said request comprising inbound trajectories; and
said mobility genes comprising inbound trajectories.
9. The system of claim 8 , said mobility genes further comprising at least one statistic representing said inbound trajectories.
10. The system of claim 5 :
said request comprising outbound trajectories; and
said mobility genes comprising outbound trajectories.
11. The system of claim 10 , said outbound trajectories being anonymized trajectories.
12. The system of claim 11 , said anonymized trajectories being truncated trajectories.
13. The system of claim 10 , said outbound trajectories comprising a transport mode.
14. A method performed on at least one computer processor, said method comprising:
receiving raw location observations, said raw observations comprising a device identifier, a timestamp and a location definition;
processing said raw location observations into a plurality of mobility genes, said mobility genes comprising visits, each of said visits being identified by:
determining a distance traveled from a previous observation;
determining whether said previous observation was classified as a stay;
when said previous observation is classified as a stay, applying a first predefined radius and time period as a classification threshold;
when said previous observation is not classified as a stay, applying a second predefined radius and time period as said classification threshold; and
applying said classification threshold to identify each of said visits;
storing said mobility genes;
receiving a request for at least one of said mobility genes; and
transmitting said at least one of said mobility genes in response to said request.
15. The method of claim 14 further comprising:
identifying a first location;
identifying a subset of said raw location observations comprising said first location;
generating a set of location statistics for said first location; and
storing said set of location statistics as one of said mobility genes.
16. The method of claim 15 :
said first location being a location type; and
said subset of raw location observations being for locations comprising said location type, said subset of raw location observations being for a plurality of physical locations.
17. The method of claim 15 :
said request comprising inbound trajectories; and
said mobility genes comprising inbound trajectories.
18. The method of claim 17 , said mobility genes further comprising at least one statistic representing said inbound trajectories.
19. The method of claim 15 :
said request comprising outbound trajectories; and
said mobility genes comprising outbound trajectories.
20. The method of claim 19 , said outbound trajectories being anonymized trajectories.