Smart ring system for measuring stress levels and using machine learning techniques to predict high risk driving behavior
The described systems and methods determine a driver's fitness to safely operate a moving vehicle based at least in part upon observed stress patterns. A smart ring, wearable on a user's finger, continuously monitors user's physiological and behavioral parameters indicative of being under stress. This stress data, representing stress patterns, can be utilized, in combination with driving data, to train a machine learning model, which will predict the user's level of risk exposure based at least in part upon observed stress patterns. The user can be warned of this risk to prevent them from driving or to encourage them to use an appropriate stress coping strategy before or during driving. In some instances, the disclosed smart ring system may interact with the user's vehicle to prevent it from starting while exposed to high risk due to deteriorated psychological or physiological conditions stemming from being under stress.
1 . A method for predicting driving risk exposure based at least in part upon observed stress patterns, the method comprising:
receiving a machine learning (ML) model that is trained to determine a correlation between a stress pattern and a driving pattern using a set of first data and a set of second data, wherein:
the set of first data is indicative of the stress pattern and is collected via a stress monitoring device; and
the set of second data is indicative of the driving pattern and is collected via one or more sensors disposed on or within a vehicle;
detecting a first cortisol level of a user from a smart ring worn by the user prior to a driving session;
analyzing, via the ML model, the first cortisol level of the user prior to the driving session, wherein the analyzing includes:
determining whether the first cortisol level of the user represents a level of correspondence between a particular stress pattern of the user and the stress pattern correlated with the driving pattern; and
predicting, based upon the level of correspondence between the particular stress pattern of the user and the stress pattern correlated with the driving pattern, a level of driving risk for the user prior to the driving session;
generating a first notification prior to the driving session, wherein the first notification provides the user with a remediating action comprising a first stress coping strategy, based on the level of driving risk for the user as predicted prior to the driving session;
transmitting the first notification to the user;
after transmitting the first notification:
using one or more sensors to track a behavior of the user during the driving session, wherein initiation of the driving session is detected by one or more of speed, acceleration, braking, or swerving of the vehicle;
detecting a second cortisol level of the user from the smart ring worn by the user during the driving session;
performing a correlation of real-time stress data to a driving compliance of the user with the remediating action, wherein the real-time stress data is based on the second cortisol level of the user and the behavior of the user during the driving session;
based on the correlation, determining a new remediating action;
generating a second notification, wherein the second notification provides the user with:
an alert to display to the user (i) the level of driving risk for the user during the driving session, and (ii) the new remediating action; and
transmitting the second notification to the user.
2 . The method of claim 1 , wherein the set of first data comprises physiological data or biochemical data collected via a physiological sensor or a biochemical sensor.
3 . The method of claim 1 , wherein the set of second data comprises gestural data or hand grip pressure data collected via a gesticulation sensor or a pressure sensor on a steering wheel.
4 . The method of claim 1 , wherein the set of second data comprises the set of second data collected via a sensor disposed within the smart ring.
5 . The method of claim 1 , wherein the set of second data comprises the set of second data collected via a vehicle computer or a dedicated electronic driving tracker device.
6 . The method of claim 1 , wherein providing the second notification further comprises:
providing the second notification at the smart ring or at an in-dash display of the vehicle.
7 . The method of claim 1 , further comprising:
analyzing the first cortisol level of the user prior to the driving session, comprising:
comparing a first level of driving risk to a known threshold to determine whether the first level of driving risk exceeds the known threshold, wherein the first level of driving risk is based on the first cortisol level;
responding to determining that the first level of driving risk exceeds the known threshold by generating a system action that prevents the user from operating the vehicle; and
preventing the user from starting the vehicle.
8 . The method of claim 1 , further comprising:
analyzing the second cortisol level of the user during the driving session, comprising:
comparing a second level of driving risk to a known threshold to determine whether the second level of driving risk exceeds the known threshold;
responding to determining that the second level of driving risk exceeds the known threshold by generating a system action that prevents the user from operating the vehicle; and
overtaking control of the vehicle while the vehicle is in operation by the user.
9 . The method of claim 1 , further comprising:
utilizing the first cortisol level of the user prior to the driving session representing the particular stress pattern to further train the ML model.
10 . A system for acquiring data indicative of stress patterns, and utilizing the data to predict driving risk exposure, comprising:
a server communicatively coupled to a smart ring, the server configured to:
receive a machine learning (ML) model that is trained to determine a correlation between a stress pattern and a driving pattern using a set of first data and a set of second data, wherein:
the set of first data is indicative of the stress pattern collected via a stress monitoring device; and
the set of second data is indicative of the driving pattern collected via one or more sensors disposed on or within a vehicle;
detect a first cortisol level of a user from the smart ring worn by the user prior to a driving session;
analyze, via the ML model, the first cortisol level of the user prior to the driving session, wherein the server is configured to:
determine whether the first cortisol level of the user represents a level of correspondence between a particular stress pattern of the user and the stress pattern correlated with the driving pattern;
predict, based upon the level of correspondence between the particular stress pattern of the user and the stress pattern correlated with the driving pattern, a level of driving risk for the user prior to the driving session; and
generate a first notification prior to the driving session, wherein the first notification provides the user with a remediating action comprising a first stress coping strategy, based on the level of driving risk for the user as predicted prior to the driving session;
transmit the first notification to the user;
after transmitting the first notification:
detect a second cortisol level of the user during the driving session from the smart ring worn by the user;
perform a correlation of real-time stress data to a driving compliance of the user with the remediating action, wherein the real-time stress data is based on the second cortisol level of the user and a behavior of the user during the driving session;
based on the correlation, determine a new remediating action;
generate a second notification, wherein the second notification provides the user with:
an alert to display to the user (i) the level of driving risk for the user during the driving session, and (ii) the new remediating action; and
transmit the second notification to the user.
11 . The system of claim 10 , wherein the set of first data includes physiological or biochemical data collected by physiological or a biochemical sensor.
12 . The system of claim 10 , wherein the set of first data includes behavioral data collected by a behavioral sensor.
13 . The system of claim 10 , wherein the smart ring has an inner diameter within a range between 13 mm and 23 mm.
14 . The system of claim 10 , wherein the server is configured to generate the second notification to alert the user of the level of driving risk by one or more of: providing the second notification to the smart ring, a vehicle computer, or a mobile device in communication with the server.
15 . The system of claim 10 , wherein the set of first data includes a stress pattern data for a user other than the user associated with the smart ring.
16 . The system of claim 10 , wherein the set of second data includes a driving pattern for a user other than the user associated with the smart ring.
17 . A server for predicting driving risk exposure based at least in part upon acquired stress patterns, the server comprising:
a communication interface;
one or more processors coupled to the communication interface; and
a memory coupled to the one or more processors and storing computer readable instructions that, when implemented, cause the one or more processors to:
receive a machine learning (ML) model that is trained to determine a correlation between a stress pattern and a driving pattern using a set of first data and a set of second data, wherein:
the set of first data is indicative of the stress pattern collected via a stress monitoring devices; and
the set of second data is indicative of the driving pattern collected via one or more sensors disposed on or within a vehicle;
detect a first cortisol level of a user from a smart ring worn by the user prior to a driving session;
analyze, via the ML model, the first cortisol level of the user prior to the driving session, wherein the processor is configured to:
determine whether the first cortisol level of the user represents a level of correspondence between a particular stress pattern of the user and the stress pattern correlated with the driving pattern; and
predict, based upon the level of correspondence between the particular stress pattern of the user and the stress pattern correlated with the driving pattern, a level of driving risk for the user prior to the driving session;
generate a first notification prior to the driving session, wherein the first notification provides the user with a remediating action comprising a first stress coping strategy, based on the level of driving risk for the user as predicted prior to the driving session;
transmit the first notification to the user;
after transmitting the first notification:
detect a second cortisol level of the user during the driving session from the smart ring worn by the user;
perform a correlation of real-time stress data to a driving compliance of the user with the remediating action, wherein the real-time stress data is based on the second cortisol level of the user and a behavior of the user during the driving session;
based on the correlation, determine a new remediating action;
generate a second notification, wherein the second notification provides the user with:
an alert to display to the user (i) the level of driving risk for the user during the driving session, and (ii) the new remediating action; and
transmit the second notification to the user.
18 . The server of claim 17 , wherein to cause the one or more processors to generate the second notification to alert the user of the level of driving risk comprises: to cause the one or more processors to transmit the second notification to any of: the smart ring, a vehicle computer, or a mobile device.
19 . The server of claim 17 , wherein the level of driving risk is a binary or ternary parameter.
20 . The server of claim 17 , wherein the computer readable instructions, when implemented, further cause the one or more processors to:
compare a first level of driving risk to a known threshold to determine whether the first level of driving risk exceeds the known threshold, wherein the first level of driving risk is based on the first cortisol level; and
when the first level of driving risk exceeds the known threshold, generate a system action and transmit the system action to a vehicle computer for the vehicle to cause the vehicle computer to prevent the user from operating the vehicle.