An audio sample including speech and ambient sounds is transmitted to a vehicle computer. Recorded audio is received from the vehicle computer, the recorded audio including the audio sample broadcast by the vehicle computer and recorded by the vehicle computer and recognized speech from the recorded audio. The recognized speech and text of the speech are input to a machine learning program that outputs whether the recognized speech matches the text. When the output from the machine learning program indicates that the recognized speech does not match the text, the recognized speech and the text are included in a training dataset for the machine learning program.

An audio sample including speech and ambient sounds is transmitted to a vehicle computer. Recorded audio is received from the vehicle computer, the recorded audio including the audio sample broadcast by the vehicle computer and recorded by the vehicle computer and recognized speech from the recorded audio. The recognized speech and text of the speech are input to a machine learning program that outputs whether the recognized speech matches the text. When the output from the machine learning program indicates that the recognized speech does not match the text, the recognized speech and the text are included in a training dataset for the machine learning program.

This disclosure is generally directed to systems and methods for providing a software sensor in a vehicle. In an example embodiment, a determination is made regarding the availability of a feature upgrade to a vehicle and a request may be made (to a cloud computer, for example), for obtaining the feature upgrade. The cloud computer provides an emulation software module based on emulating a first sensor that is unavailable in the vehicle. The feature upgrade may be installed in the vehicle by executing the emulation software module and by use of a second sensor that is available in the vehicle. In an example implementation, the second sensor available in the vehicle is a type of hardware sensor such as, for example, a camera, and the first sensor that is emulated is a different type of hardware sensor such as, for example, an air quality sensor.

This disclosure is generally directed to systems and methods for providing a software sensor in a vehicle. In an example embodiment, a determination is made regarding the availability of a feature upgrade to a vehicle and a request may be made (to a cloud computer, for example), for obtaining the feature upgrade. The cloud computer provides an emulation software module based on emulating a first sensor that is unavailable in the vehicle. The feature upgrade may be installed in the vehicle by executing the emulation software module and by use of a second sensor that is available in the vehicle. In an example implementation, the second sensor available in the vehicle is a type of hardware sensor such as, for example, a camera, and the first sensor that is emulated is a different type of hardware sensor such as, for example, an air quality sensor.

Methods and systems are described herein for improvements for cybersecurity of telecommunication devices. For example, cybersecurity for telecommunication devices may be improved by analyzing activity log data of telecommunication devices for a candidate event (e.g., the uploading of malware) and disabling one or more services of a telecommunication device. By doing so, cybersecurity for telecommunication devices may be improved by detecting a possible malware intrusion attempt and disabling one or more services of the telecommunication devices. For example, activity log data of telecommunication devices may be obtained. A candidate event indicating malware may be detected in the activity log data. A number of proximate telecommunication devices satisfying a proximity threshold condition may be determined. The number of proximate telecommunication devices that satisfy a density threshold condition may be determined. Responsive to the number of telecommunication devices satisfying a density threshold condition, services of telecommunication devices may be disabled.

Methods and systems are described herein for improvements for cybersecurity of telecommunication devices. For example, cybersecurity for telecommunication devices may be improved by analyzing activity log data of telecommunication devices for a candidate event (e.g., the uploading of malware) and disabling one or more services of a telecommunication device. By doing so, cybersecurity for telecommunication devices may be improved by detecting a possible malware intrusion attempt and disabling one or more services of the telecommunication devices. For example, activity log data of telecommunication devices may be obtained. A candidate event indicating malware may be detected in the activity log data. A number of proximate telecommunication devices satisfying a proximity threshold condition may be determined. The number of proximate telecommunication devices that satisfy a density threshold condition may be determined. Responsive to the number of telecommunication devices satisfying a density threshold condition, services of telecommunication devices may be disabled.

Some examples relate to classifying IoT malware at a network device. An example includes receiving, by a network device, network traffic from an Internet of Things (IoT) device. Network device may analyze network parameters from the network traffic with a machine learning model. In response to analyzing, network device may classify the network traffic into a category of malware activity. Network device may determine an effectiveness of network traffic classification by measuring a deviation of the network parameters from previously trained network parameters that were used for training the machine learning model. In response to a determination that the deviation of the network parameters from the trained network parameters is more than a pre-defined threshold, network device may generate an alert highlighting the deviation, which allows a user to perform a remedial action pertaining to the IoT device.

Some examples relate to classifying IoT malware at a network device. An example includes receiving, by a network device, network traffic from an Internet of Things (IoT) device. Network device may analyze network parameters from the network traffic with a machine learning model. In response to analyzing, network device may classify the network traffic into a category of malware activity. Network device may determine an effectiveness of network traffic classification by measuring a deviation of the network parameters from previously trained network parameters that were used for training the machine learning model. In response to a determination that the deviation of the network parameters from the trained network parameters is more than a pre-defined threshold, network device may generate an alert highlighting the deviation, which allows a user to perform a remedial action pertaining to the IoT device.

A computerized method for transforming an interactive graphical user interface according to machine learning includes selecting a persona, loading a data structure associated with the selected persona, and generating the interactive graphical user interface. The method includes, in response to a user selecting a first selectable element, inputting a first set of explanatory variables to a first trained machine learning model to generate a first metric, and transforming the user interface according to the selected persona and the first metric. The method includes, in response to the user selecting a second selectable element, inputting a second set of explanatory variables to a second trained machine learning model to generate a second metric, and transforming the user interface according to the selected persona and the second metric. In various implementations, first metric is a first probability of the persona being approved for a first prior authorization prescription.

A computerized method for transforming an interactive graphical user interface according to machine learning includes selecting a persona, loading a data structure associated with the selected persona, and generating the interactive graphical user interface. The method includes, in response to a user selecting a first selectable element, inputting a first set of explanatory variables to a first trained machine learning model to generate a first metric, and transforming the user interface according to the selected persona and the first metric. The method includes, in response to the user selecting a second selectable element, inputting a second set of explanatory variables to a second trained machine learning model to generate a second metric, and transforming the user interface according to the selected persona and the second metric. In various implementations, first metric is a first probability of the persona being approved for a first prior authorization prescription.