SYSTEMS AND METHODS FOR ROUTE RECONSTRUCTION

1 . A system for managing a fleet of ridesharing vehicles, the system comprising:

a communications interface configured to receive Global Positioning System (GPS) data from the fleet of ridesharing vehicles;

at least one processor configured to:

for each ridesharing vehicle in the fleet:

i) determine a plurality of GPS locations, wherein each GPS location includes an associated a time stamp;

ii) split the plurality of GPS locations into substantially unique segments, wherein each segment includes a number of GPS locations that is based on one or more predetermined factors;

iii) for each segment, determine a most probable location for each of the plurality of GPS locations to determine a partial route for each segment that the current rideshare vehicle rode on; and

iv) determine a complete route for the current rideshare by concatenating the partial routes for each segment based on the time stamp.

2 . The system of claim 1 wherein each segment includes one or two GPS locations that overlaps with one or two segments that have a sequential time stamp that is after, before or both.

3 . The system of claim 1 further comprising filtering the plurality of GPS locations if the distance between any of the plurality of GPS locations is below a predefined threshold.

4 . The system of claim 1 further comprising filtering the plurality of GPS locations if its corresponding speed is below a predefined threshold.

5 . The system of claim 1 wherein the one or more predetermined factors are time duration, distance, desired computational time, or any combination thereof.

6 . The system of claim 1 wherein the splitting further comprises avoiding splitting at GPS locations where the corresponding speed is below a predefined threshold.

7 . The system of claim 1 wherein determining a most probable location for each of the plurality of GPS locations for each segment is performed for all segments in parallel.

8 . The system of claim 1 wherein determining a most probable location for each of the plurality of GPS locations for each segment further comprises determining a confidence for each GPS location with its corresponding determined most probable location, and retaining the most probable location if the confidence is above a threshold, otherwise discarding the GPS location in the respective segment.

9 . The system of claim 1 wherein determining the complete route further comprises determining if the end and start points of each sequential partial route match, and if not, returning to step ii) and splitting the segments at different locations then previously split.

10 . The system of claim 1 wherein determining a partial route for each segment that the current rideshare vehicle rode on further comprises applying a Markovian algorithm, dynamic programming, Viterbi algorithm, Kalman filter, or integer algorithm to the GPS locations in the respective segment.

11 . A method for managing a fleet of ridesharing vehicles, the method comprising:

receiving, by a computing device, Global Positioning System (GPS) data from the fleet of ridesharing vehicles;

for each ridesharing vehicle in the fleet:

i) determining, by a computing device, a plurality of GPS locations, wherein each GPS location includes an associated a time stamp;

ii) splitting, by the computing device, the plurality of GPS locations into substantially unique segments, wherein each segment includes a number of GPS locations that is based on one or more predetermined factors;

iii) for each segment, determining, by the computing device, a most probable location for each of the plurality of GPS locations to determine a partial route for each segment that the current rideshare vehicle rode on; and

iv) determining, by the computing device, a complete route for the current rideshare by concatenating the partial routes for each segment based on the time stamp.

12 . The method of claim 11 wherein each segment includes one or two GPS locations that overlaps with one or two segments that have a sequential time stamp that is after, before or both.

13 . The method of claim 11 further comprising filtering the plurality of GPS locations if the distance between any of the plurality of GPS locations is below a predefined threshold.

14 . The method of claim 11 further comprising filtering the plurality of GPS locations if its corresponding speed is below a predefined threshold.

15 . The method of claim 11 wherein the one or more predetermined factors are time duration, distance, desired computational time, or any combination thereof.

16 . The method of claim 11 wherein the splitting further comprises avoiding splitting at GPS locations where the corresponding speed is below a predefined threshold.

17 . The method of claim 11 wherein determining a most probable location for each of the plurality of GPS locations for each segment is performed for all segments in parallel.

18 . The method of claim 11 wherein determining a most probable location for each of the plurality of GPS locations for each segment further comprises determining a confidence for each GPS location with its corresponding determined most probable location, and retaining the most probable location if the confidence is above a threshold, otherwise discarding the GPS location in the respective segment.

19 . The method of claim 11 wherein determining the complete route further comprises determining if the end and start points of each sequential partial route match, and if not, returning to step ii) and splitting the segments at different locations then previously split.

20 . The method of claim 11 wherein determining a partial route for each segment that the current rideshare vehicle rode on further comprises applying a Markovian algorithm, dynamic programming, Viterbi algorithm, Kalman filter, or integer algorithm to the GPS locations in the respective segment.