| CPC G06N 7/01 (2023.01) [G06F 9/542 (2013.01)] | 19 Claims |

|
1. A system for determining risky events, comprising:
an input interface for receiving sensor data on environmental conditions, wherein the sensor data comprises Global Positioning System (GPS) data, and wherein the environmental conditions comprise intersection complexity; and
a processor for:
determining that the environmental conditions indicate an increase in event probability, comprising:
determining that an intersection is unknown based on the GPS data;
in response to a determination that the intersection is unknown:
determining an intersection type of the unknown intersection based on three or more of the following:
determining a road configuration;
determining a number of roads present;
determining a number of lanes present;
determining a number of directions of traffic;
determining signs;
determining lights;
determining pedestrian crosswalks;
determining bicycle lanes; and/or
determining rail tracks;
determining a set of intersections of the same intersection type as the unknown intersection;
determining an average risk level of the set of intersections of the same intersection type as the unknown intersection;
determining that the average risk level is less than a risk threshold level; and
in response to a determination that the average risk level is less than the risk threshold level, determining that the environmental conditions do not indicate an increase in the event probability;
in response to a determination that the environmental conditions indicate the increase in the event probability, adjusting an event detection threshold;
determining that a sensor data event measure is greater than the event detection threshold; and
in response to a determination that the sensor data event measure is greater than the event detection threshold, transferring data related to an event associated with the event detection threshold.
|