| CPC B60W 40/08 (2013.01) [G01C 21/30 (2013.01); G06N 20/20 (2019.01); G06Q 50/26 (2013.01); G06Q 50/40 (2024.01); H04W 4/027 (2013.01); H04W 4/029 (2018.02); H04W 4/38 (2018.02); H04W 4/48 (2018.02); B60W 2540/227 (2020.02); B60W 2556/45 (2020.02)] | 14 Claims |
|
1. A method for identifying and/or classifying a user of a vehicle based on sensory data measured by a plurality of sensors of a mobile device of the user, the plurality of sensors at least comprising an accelerometer and a gyroscope, the mobile device comprising at least one wireless connection, wherein by the at least one wireless connection, the mobile device acts as a wireless node within a cellular data transmission network by antenna connections of the mobile device to the cellular data transmission network, the plurality of sensors being connected to a monitoring mobile node application of the mobile device, and wherein the monitoring mobile node application captures usage-based and/or user-based telematics data of the mobile device and/or the user of the mobile device, the method comprising:
measuring, by processing circuitry, gravitational acceleration movement sensory data based on measuring parameters obtained from the accelerometer and gyroscope movement sensory data based on measuring parameters obtained from the gyroscope;
detecting, by the processing circuitry, vehicle entering or exiting movement patterns of the user from the acceleration movement sensory data at least comprising an acceleration movement sensory data pattern for a base axis and a degree of rotation associated with a vehicle entering or exiting movement of the user;
triggering, by the processing circuitry using the detected vehicle entering or exiting movement patterns of the user as input features, recognition of a vehicle entering or exiting movement of the user by performing a decision-tree classification on the input features to determine whether the user entered or exited the vehicle from a left side or a right side of the vehicle, wherein the gyroscope movement sensory data are used to select at least verse and degree of the rotation associated with the vehicle entering or exiting movement; and
detecting, by the processing circuitry, a moment in which the user is entering or exiting the vehicle by detecting an acceleration in an up or down direction related to an earth reference system from the acceleration movement sensory data and by measuring or not measuring a variance of discontinuities in acceleration signals in a smartphone reference system, the gravitational acceleration movements being correlated with an orientation of the mobile device building the smartphone reference system, wherein
the acceleration movement sensory data are triggered for a timely gap associable with a time window just before opening a door of the vehicle immediately before entering the vehicle or a downwards movement performed during a sitting movement,
upon detecting a movement pattern suitable for the sitting movement, the acceleration movement sensory data are triggered for rotations with an overlap with the sitting movement, and a decision tree is performed to classify the user as a driver or a passenger depending on a counterclockwise or clockwise direction of rotation, and
for separating the movement pattern from timely gaps, a variance of the acceleration in the up or down direction is processed by a threshold filter, wherein the acceleration in the up or down direction corresponds to a signal rotated in the earth reference system.
|