Abstract: A computer-implemented method to determine a device of a driver including receiving, from a first user device of a first user in a vehicle, first telematics data, receiving from a second user device of a second user in the vehicle, second telematics data, determining, using a trained machine learning model, patterns in the first and second telematics data, determining relative positions of the first user device and the second user device by analyzing the telematics data to identify that one of the devices experiences a change in vertical acceleration before the other, determining a delay between the changes in vertical acceleration, determining a front-to-rear positioning of the first user device relative to the second user device based on the delay, determining a predicted position of the first user device relative to the second user device, and identifying the driver of the vehicle based upon the predicted position. Other embodiments are described.

Abstract: A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations: comparing, by an electronic device, at least one parameter of a set of telematics data associated with a vehicle and at least one additional parameter of an additional set of telematics data associated with one or more other vehicles within a threshold distance of the vehicle to determine a difference between the at least one parameter and the at least one additional parameter; and displaying, by the electronic device, the difference to the operator of the vehicle to notify the operator of the vehicle about the difference. Other embodiments are described.

Abstract: A method for revoking access to personal information. The method can include obtaining personal data of a user. The method further can include storing the personal data in a digital wallet. The method also can include determining that at least a portion of the personal data in the digital wallet is subject to a data security risk. The method additionally can include transmitting for display on a device of the user, an alert regarding the data security risk and a control to revoke access to the at least the portion of the personal data. Other embodiments are disclosed.

Abstract: A telematics analysis computing device for monitoring driving behavior of a driver of a vehicle comprising one or more processors in communication with a memory device comprising computer instructions that, when run on the one or more processors, cause the one or more processors to execute operations including aggregating real-time telematics data from multiple electronic devices of multiple drivers of multiple vehicles based at least in part upon a common location for the multiple drivers, determining, in real time, one or more outliers in the real-time telematics data, determining, based at least in part upon the one or more outliers, that at least one driver poses an accident risk for one or more other drivers, and transmitting a real-time notification to one or more electronic devices associated with the one or more other drivers at the common location. Other embodiments are described.

Abstract: A credit score prediction (CSP) computing device comprising at least one processor in communication with a memory device. The at least one processor can be configured to receive current user data and current vehicle telematics data associated with a first user. The at least one processor further can be configured to apply a model, as trained, to the current user data and the current vehicle telematics data to predict a credit score associated with the first user. The model can be trained using a training dataset. The at least one processor also can be configured to determine a probability of error associated with the credit score, as predicted, based upon a number of records in the current vehicle telematics data. The probability of error can be lower when the number of records in the current vehicle telematics data is higher.

Abstract: 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.

Abstract: A computer-implemented method including receiving driving data of a vehicle indicative of a driving automation system (DAS) operating the vehicle, wherein the DAS comprises DAS features, determining a DAS score for the vehicle based on the driving data, conducting evaluations of combinations of one or more of the DAS features under one or more driving conditions, receiving historical system DAS rating data for a vehicle type of the vehicle, determining a historical DAS score for the vehicle type based on the historical system DAS rating data, analyzing the historical DAS score with the DAS score to determine a DAS rating for the vehicle, and adjusting a mode of operation of at least one of the DAS features based upon the DAS rating and the evaluations of the combinations of the one or more of the DAS features under the one or more driving conditions. Other embodiments are described.

Abstract: A computer-implemented method can include receiving personal data associated with a user. The method also can include predicting, by a trained predictive possession model, a set of items owned by the user based at least in part upon the personal data associated with the user. The trained predictive possession model is configured to extract data associated with the set of items from the personal data. The method additionally can include assigning, by the trained predictive possession model, a predicted value for each item of the set of items. The method further can include causing information indicative of an item of the set of items and the predicted value for the item to be displayed on a user device of the user. The method additionally can include receiving an adjusted value for the item in the set of items. The method further can include causing the trained predictive possession model to be updated based on the adjusted value for the item. Other embodiments are described.

Abstract: A system for displaying information can include a ring band configured to be worn on a finger of a user. The system for displaying information also can include a processor disposed within the ring band and configured to receive data from a sensor within the ring band. The system for displaying information further can include an output device communicatively coupled to the processor comprising a display. The display of the output device can be configured to emit a first color based on a battery level of a ring. The display of the output device also can be configured to emit a second color based on a malfunction of the ring. The display of the output device further can be configured to emit a third color based on an active communicative link with the ring. Other embodiments are disclosed.

Abstract: A computer-implemented method for generating driver risk credentials. The method can include obtaining telematics data from an electronic device of a driver over a time period. The method also can include generating, using a trained model, a driver risk score for the driver based on the telematics data. The method additionally can include transmitting a verified digital credential for the driver to a recipient, wherein the verified digital credential is based on the driver risk score. Other embodiments are described.

Abstract: A computer-implemented method can comprise receiving, from a mobile device, telemetry data associated with one or more vehicle operations. The telemetry data can be collected by the mobile device upon receiving a heartbeat signal that activates an application on the mobile device from a dormant mode to an active or background mode or from a background mode to an active mode. The computer-implemented method can also comprise identifying, based at least on the telemetry data: one or more time periods indicative of a user of the mobile device operating a vehicle, and one or more time periods indicative of an absence of expected telemetry data associated with the one or more vehicle operations. The computer-implemented method can further comprise transmitting to the mobile device, an alert indicating the absence of the expected telemetry data when an amount of absences of the expected telemetry data meets or exceeds a predetermined threshold in a predetermined period of time. Other embodiments are described.

Abstract: A computer-implemented method can comprise receiving a heartbeat signal with an application on a mobile device. The computer-implemented method can also comprise, after receiving the heartbeat signal: activating the application to an active or background mode or from a background mode to an active mode, and collecting telemetry data associated with one or more vehicle operations. The computer-implemented method can further comprise transmitting the telemetry data to a computing device. The computing device can identify, based at least on the telemetry data: one or more time periods indicative of a user of the mobile device operating a vehicle, and one or more time periods indicative of an absence of expected telemetry data associated with the one or more vehicle operations.

Abstract: A ring for displaying information includes a ring band. The ring also includes one or more sensors located at least partially within the ring band to detect one or more conditions. The ring further includes a processor located within the ring band and configured to analyze data to identify the one or more conditions. The ring further includes an output device communicatively coupled to the processor. The output device is configured to display a red color to indicate a first condition. The output device is also configured to display a green color to indicate a second condition. The output device is further configured to display a flash to indicate a third condition. Other embodiments are disclosed.

Abstract: A computer-implemented method for risk assessment based on usage of autonomous driving systems. The method can include obtaining one or more data sets collected based on a driver operating one or more vehicles having one or more autonomous driving systems. The method also can include determining usage patterns for the one or more autonomous driving systems based at least on the one or more data sets. The method further can include generating, using a machine-learning model, a risk metric based at least on the usage patterns. The method additionally can include outputting the risk metric. Other embodiments are described.

Abstract: A charging system can include a removable power source housing. The removable power source housing can be devoid of being worn on a finger of a user. The removable power source housing can include a first LED activated in response to a first activity at the removable power source housing. The removable power source housing can include a second LED activated in response to a second activity at the removable power source housing. The second activity can be different from the first activity. The removable power source housing can include a third LED activated in response to a third activity at the removable power source housing. The third activity can be different from the first activity and the second activity. The charging system also can include a ring housing. The ring housing can be configured to be removably coupled to the removable power source housing. Other embodiments are disclosed.

Abstract: A method can include providing a machine learning model based in part on a user profile for a user. The method can also include transmitting the machine learning model, as compressed, to a mobile user device. The method can further include generating, on the mobile user device, a personalized machine learning model by training the machine learning model, as compressed, based in part on dynamic data of the user. The method can additionally include determining, by the personalized machine learning model on the mobile user device, a risk score of the user. Other embodiments are described.

Abstract: A computer-implemented method for operating a computing device including: receiving telematics data from one or more sensors of an electronic device of a user; assessing driving behavior of the user based on the telematics data; generating a personalized digital training program for the user based at least on the driving behavior of the user; generating one or more driving scores for the user based on performance of the user on the personalized digital training program; and outputting a driving credential for the user based on the one or more driving scores. Other embodiments are described.

Abstract: A method can include receiving telematics data from one or more sensors of an electronic device of a user. The method can also include determining a respective skill level for each of a plurality of driving skills of the user based on the telematics data. The method can further include determining, from among the plurality of driving skills, a driving skill for the user to improve. The method can additionally include generating personalized feedback for the user. The personalized feedback is for improving the driving skill. The method can also include transmitting the personalized feedback to a mobile device of the user for display to the user. Other embodiments are disclosed.

Abstract: A method for feature extraction from telematics data. The method includes obtaining telematics data for a plurality of trips for one or more drivers for a policy. The method also includes generating, using an automatic feature extraction encoder, respective latent representation embeddings each of the plurality of trips for the one or more drivers for the policy. The method additionally includes combining the respective latent representation embeddings for the plurality of trips to generate a combined embedding representation for the policy. The method further includes generating an output for the policy, using a supervised machine-learning model, based on inputs to the supervised machine-learning model comprising the combined embedding representation. Other embodiments are described.

Abstract: A method can include receiving a state of a tire of a vehicle, and collecting telematics data for an operator of the vehicle. The method can further include determining an expected state of the tire, and transmitting, for display on a user device, a message regarding the expected state of the tire. The method can also include repeating the collecting, the determining, and the transmitting. The method can further include receiving a current state of the tire. The method can additionally include determining whether the current state of the tire is within a predetermined threshold of the expected state of the tire. The method can also include, when the current state of the tire is determined to not be within the predetermined threshold of the expected state of the tire, resetting the expected state of the tire to be the current state of the tire. Other embodiments are disclosed.