Systems and methods for reducing distractions within a vehicle

    公开(公告)号:US11097741B1

    公开(公告)日:2021-08-24

    申请号:US15873391

    申请日:2018-01-17

    Abstract: A computer-implemented method is provided for adjusting at least one of a visual or an auditory setting correlated to the provision of entertainment within a vehicle. The method includes receiving information indicative of one or more changes in behavior that coincides with a provision of entertainment within a vehicle. The information indicative of the one or more changes in behavior is based on data captured by one or more sensors of the vehicle. The method includes analyzing the one or more changes in behavior in order to determine a modification to the provision of entertainment within the vehicle. The modification is commensurate with the one or more changes in behavior. The method includes based on the determined modification, providing, an output signal for adjusting at least one of a visual or an auditory setting correlated to the provision of entertainment within the vehicle.

    Method of controlling for undesired factors in machine learning models

    公开(公告)号:US10769518B1

    公开(公告)日:2020-09-08

    申请号:US15383499

    申请日:2016-12-19

    Abstract: A method of training and using a machine learning model that controls for consideration of undesired factors which might otherwise be considered by the trained model during its subsequent analyses of new data. For example, the model may be a neural network trained on a set of training images to evaluate an insurance applicant based upon an image or audio data of the insurance applicant as part of an underwriting process to determine an appropriate life or health insurance premium. The model is trained to probabilistically correlate an aspect of the applicant's appearance with a personal and/or health-related characteristic. Any undesired factors, such as age, sex, ethnicity, and/or race, are identified for exclusion. The trained model receives the image (e.g., a “selfie”) of the insurance applicant, analyzes the image without considering the identified undesired factors, and suggests the appropriate insurance premium based only on the remaining desired factors.

    Technology for detecting onboard sensor tampering

    公开(公告)号:US10755495B1

    公开(公告)日:2020-08-25

    申请号:US15714919

    申请日:2017-09-25

    Abstract: Systems and methods detecting onboard sensor tampering are disclosed. According to embodiments, data captured by interior sensors within a vehicle may be analyzed to determine an indication that the activity of the vehicle operator either cannot be sufficiently detected or cannot be sufficiently identified using the captured data (e.g., that the captured data may be compromised). A date and time associated with the indication may be recorded, and a vehicle operator associated with the indication may be identified. A possible cause for the compromised data may be diagnosed, and notification may be generated indicating that the activity of the vehicle operator either cannot be sufficiently detected or cannot be sufficiently identified, and/or the possible cause. Additionally, a recommendation for restoring sensor functionality may be generated for the vehicle operator based the possible cause.

    Technology for assessing emotional state of vehicle operator

    公开(公告)号:US10717444B1

    公开(公告)日:2020-07-21

    申请号:US16291226

    申请日:2019-03-04

    Abstract: Systems and methods for analyzing sensor data to determine an inferred emotional state of a vehicle operator and generate a recommendation based on the inferred emotional state are disclosed. According to embodiments, an electronic device may analyze image data depicting a vehicle operator to identify a behavior. The electronic device may also compare vehicle dynamics data to baseline vehicle dynamics data to determine if the vehicle dynamics data differs from the baseline vehicle dynamics data by a threshold amount. Based on the identified behavior and the vehicle dynamics data, the electronic device may determine an inferred emotional state of the vehicle operator. The electronic device may generate a recommendation for the vehicle operator based on the inferred emotional state.

    Technology for using image data to assess vehicular risks and communicate notifications

    公开(公告)号:US10373500B1

    公开(公告)日:2019-08-06

    申请号:US15713227

    申请日:2017-09-22

    Abstract: Systems and methods for generating and communicating notifications indicating risks associated with vehicular operation are provided. According to certain aspects, an electronic device may access and analyze image data that depicts a vehicle operator in a certain state. The electronic device may determine, based on the state of the vehicle operator, whether a risk exists as well as information that may be helpful to communicate to additional vehicle operators. The electronic device may generate a notification that indicates the information and transmit the notification to at least one additional vehicle and/or to an infrastructure component.

    Technology for assessing emotional state of vehicle operator

    公开(公告)号:US10322727B1

    公开(公告)日:2019-06-18

    申请号:US15713576

    申请日:2017-09-22

    Abstract: Systems and methods for analyzing sensor data to determine an inferred emotional state of a vehicle operator and generate a recommendation based on the inferred emotional state are disclosed. According to embodiments, an electronic device may analyze image data depicting a vehicle operator to identify a behavior. The electronic device may also compare vehicle dynamics data to baseline vehicle dynamics data to determine if the vehicle dynamics data differs from the baseline vehicle dynamics data by a threshold amount. Based on the identified behavior and the vehicle dynamics data, the electronic device may determine an inferred emotional state of the vehicle operator. The electronic device may generate a recommendation for the vehicle operator based on the inferred emotional state.

    Method of controlling for undesired factors in machine learning models

    公开(公告)号:US10282789B1

    公开(公告)日:2019-05-07

    申请号:US15383659

    申请日:2016-12-19

    Abstract: A method of training and using a machine learning model that controls for consideration of undesired factors which might otherwise be considered by the trained model during its subsequent analyzes of new data. For example, the model may be a neural network trained on a set of training images to evaluate an insurance applicant based upon an image or audio data of the insurance applicant as part of an underwriting process to determine an appropriate life or health insurance premium. The model is trained to probabilistically correlate an aspect of the applicant's appearance with a personal and/or health-related characteristic. Any undesired factors, such as age, sex, ethnicity, and/or race, are identified for exclusion. The trained model receives the image (e.g., a “selfie”) of the insurance applicant, analyzes the image without considering the identified undesired factors, and suggests the appropriate insurance premium based only on the remaining desired factors.

Patent Agency Ranking