US 11,842,404 B2
Enhancement using analytics based on vehicle kinematic data
Christopher J. Carver, Bainbridge Island, WA (US); and Kevin Wolsey, Calgary (CA)
Assigned to SPEEDGAUGE, INC., San Francisco, CA (US)
Filed by SPEEDGAUGE, INC., San Francisco, CA (US)
Filed on Dec. 30, 2019, as Appl. No. 16/730,104.
Application 16/730,104 is a division of application No. 16/103,441, filed on Aug. 14, 2018.
Application 16/103,441 is a continuation of application No. 14/687,099, filed on Apr. 15, 2015, granted, now 10,049,408, issued on Aug. 14, 2018.
Claims priority of provisional application 61/979,972, filed on Apr. 15, 2014.
Prior Publication US 2020/0134735 A1, Apr. 30, 2020
Int. Cl. G06Q 40/08 (2012.01); G07C 5/00 (2006.01)
CPC G06Q 40/08 (2013.01) [G07C 5/008 (2013.01)] 21 Claims
OG exemplary drawing
 
15. An apparatus for vehicle analytics and feedback, the apparatus comprising:
a database that stores information identifying a virtual map of a plurality of road segments;
a memory that stores instructions; and
a processor that executes the instructions, wherein execution of the instructions by the processor causes the processor to:
receive vehicle traffic data corresponding to the plurality of road segments and movement of a plurality of vehicles;
receive a plurality of global navigation satellite system (GNSS) coordinates of a first vehicle along a particular road segment of the plurality of road segments from a telemetric device carried by the first vehicle, wherein the plurality of GNSS coordinates of the first vehicle are along a trip of the first vehicle;
identify one or more exceedances by the first vehicle based on the plurality of GNSS coordinates, each of the one or more exceedances indicating a respective time at which an aspect of vehicle driving exceeded one or more thresholds in light of one or more respective environmental conditions;
identify one or more temporal risk patterns associated with the one or more exceedances by the first vehicle using: pattern recognition based on reverse mining data that includes at least the plurality of GNSS coordinates and that is indicative of the one or more exceedances and one or more similar events with similar environmental conditions;
identify a change in operator behavior over time based on a change in the one or more temporal risk patterns over time such that more recent risk patterns are to be biased above less recent risk patterns;
identify one or more weights to associate with the one or more temporal risk patterns to use in generating: a driver safety index, wherein the one or more weights bias the more recent risk patterns over the less recent risk patterns to bias toward the change in operator behavior;
rank the first vehicle against the plurality of vehicles based on the one or more exceedances according to one or more road segments that correspond to the one or more exceedances, the one or more temporal risk patterns, and the one or more weights;
generate the driver safety index for an operator of the first vehicle based at least one the ranking of the first vehicle against the plurality of vehicles, wherein the driver safety index for the operator is portable across vehicles operated by the operator and across environments that the operator operates;
associating, by the processor, the driver safety index with the plurality of GNSS coordinates of the first vehicle within the virtual map of the plurality of road segments; and
providing risk feedback to a computing device based on the driver safety index and the virtual map.