Driver screening

Abstract

A vehicle has one or more cameras configured to record one or more images of a driver of the vehicle. The cameras can be configured to send biometric image data derived from the images. The vehicle can include a computing system configured to receive the biometric data and determine a risk score of the driver based on the received biometric data and an AI technique such as an ANN or a decision tree. The received biometric data or a derivative thereof can be an input for the AI technique. The computing system can also be configured to transmit the risk score of the driver to a customer so that the customer can decide whether to book a ride with the vehicle.

Description

[0001] Related applications

[0002] This application claims priority to U.S. Patent Application No. 16 / 854,634, filed April 21, 2020, entitled “DRIVER SCREENING,” the entire disclosure of which is hereby incorporated herein by reference. Technical Field

[0003] At least some of the embodiments disclosed herein relate to a networked system for driver screening. For example, at least some of the embodiments disclosed herein relate to a networked system for screening drivers for ride-sharing services. Background Technology

[0004] Carpooling has become a common mode of transportation in the United States and is growing globally. Carpooling services connect passengers with drivers or vehicles via websites or other types of applications. Currently, several carpooling services match customers with vehicles through mobile applications. Carpooling services can be called ride-hailing services, and such services can also be used to share rides with other types of transportation, including airplanes and ships.

[0005] In sparsely populated or impoverished areas where taxis typically cannot provide service, carpooling has become widespread. Moreover, carpooling has become widely adopted because people perceive it as cheaper than taxis. Furthermore, carpooling has proven beneficial, as it has shown promise in reducing drunk driving rates in some cities where such services can be operated.

[0006] One problem with ride-sharing is that it's perceived as less safe than hailing a taxi or a professional ride-hailing service. However, people are taking steps to overcome safety concerns and worries about fraudulent ride-sharing services. On the other hand, intoxicated, fraudulent, or aggressive customers can cause trouble for drivers. Furthermore, fatigued, intoxicated, fraudulent, or aggressive drivers can cause trouble for customers.

[0007] To protect drivers and customers, ride-sharing services are regulated at the city and state levels. In some jurisdictions, ride-sharing has been banned due to safety concerns and potential lobbying by taxi companies. Regulations for ride-sharing services may include requirements regarding driver background checks, fares, the number of drivers, licenses, and driver wages. Attached Figure Description

[0008] This disclosure will be more fully understood from the detailed description given below and from the accompanying drawings of various embodiments thereof.

[0009] Figure 1 The diagram illustrates an example vehicle configured to perform driver screening for a ride-sharing service according to some embodiments of the present disclosure.

[0010] Figures 2 to 4 This description illustrates an example networked system according to some embodiments of the present disclosure, comprising at least a mobile device and a vehicle, and a ride-sharing service system (RSSS) configured to perform driver screening for ride-sharing services.

[0011] Figures 5 to 6 This describes some embodiments of the present disclosure that can be provided by Figure 1 The vehicles or Figures 2 to 4 The flowchart illustrates the instance operations performed by aspects of a networked system. Detailed Implementation

[0012] At least some of the embodiments disclosed herein relate to a networked system for driver screening. For example, at least some of the embodiments disclosed herein relate to a networked system for screening drivers for ride-sharing services. In some embodiments, a taxi or ride-sharing service vehicle may photograph or record video of the driver in the taxi or vehicle and generate a risk score for the driver. The risk score may be related to whether the driver is fatigued, intoxicated, or driving erratically. The score may even be related to the driver's level of intoxication or fatigue, as well as the driver's mental state or stability. The score may also be related to the driver's physical or cognitive impairment, the driver's criminal history, and the driver's driving history. When booking a ride, the risk score may be presented to the customer via a mobile device. Moreover, when the risk score is higher than a threshold, the passenger may be alerted or prompted to decline the driver. This may occur when a customer uses a mobile device to book a ride. In other words, when booking a taxi or ride-sharing service, the vehicle may photograph the driver and assess the driver's performance readiness level (e.g., whether the driver is fatigued, slow to react, intoxicated, current performance level relative to peak performance level, driving style, etc.). The assessment may then be transmitted to potential taxi or ride-sharing customers during the decision-making process.

[0013] In some embodiments, connected systems for driver screening use artificial intelligence (AI) to generate risk scores. AI technologies (such as artificial neural networks (ANNs), convolutional neural networks (CNNs), etc.) can be trained to recognize patterns in input data and generate risk scores. While conventional linear computer programming techniques follow strict rules, AI technologies (such as ANNs, CNNs, etc.) can use machine learning to learn and adapt to changing inputs. This ability to learn and adapt to changing inputs makes AI technologies a useful component of connected systems for driver screening.

[0014] Generally, ANNs can be trained using supervised methods, where the parameters of the ANN are tuned to minimize or reduce the error between the known output caused by the corresponding input and the computational output generated by applying the input to the ANN. Examples of supervised learning / training methods include reinforcement learning and learning with error correction.

[0015] Alternatively or in combination, ANNs can be trained using unsupervised methods, where the accurate output resulting from a given set of inputs is unknown until training is complete. ANNs can be trained to classify items into multiple categories or data points into clusters. Various training algorithms are available for complex machine learning / training paradigms.

[0016] In some embodiments, to train the carpooling service system for a specific user, a customer or passenger can view sample images of the driver and provide a corresponding risk score. The system can then use artificial intelligence to learn, in general, to provide risk scores similarly to customers or carpooling customers of the service based on this input. This learning (or machine learning) can be accomplished using datasets, such as several sets of images of the driver and their corresponding risk scores. For example, if a customer has the opportunity to determine the driver's risk score by observing the driver briefly (e.g., using the system's carpooling app), what the customer or passenger observes can be similarly observed by a camera. The system cannot determine how the customer decides the risk score; however, the system can train or adjust the parameters of AI techniques (such as ANN, CNN, or decision trees) to minimize the difference between the risk score generated by the customer (or, generally, customers of the service) and the score calculated by the AI ​​techniques. The dataset input to the AI ​​techniques can be made more complex by adding other biometric inputs (such as voice, alcohol content from a breathalyzer, body temperature, etc.). Using each additional dataset, the AI ​​techniques continuously learn, adapt, and improve the risk scores. This machine learning can be considered supervised machine learning.

[0017] In some embodiments, the vehicle may include at least one camera configured to record at least one image of the driver in the vehicle during a period of time. The camera may also be configured to transmit image data derived from at least one image of the driver. Recording of at least one image may occur in response to a customer request to assess the driver in order to determine whether a vehicle ride has been booked. The request may occur during said period of time.

[0018] The vehicle may also include a computing system configured to receive image data from at least one camera and determine a driver risk score for a given period of time based on the received image data and AI technology. The AI ​​technology may include ANNs, decision trees, or other types of AI tools, or any combination thereof. The received biometric data or its derivatives may be inputs generally used for AI technologies or specifically designed for ANNs, decision trees, or other types of AI tools, or any combination thereof. The computing system may also be configured to transmit the driver's risk score to a customer, allowing the customer to decide whether to book a ride.

[0019] In some embodiments, the vehicle may include at least one sensor configured to sense at least one non-visual biometric feature of the driver during a certain time period and to transmit non-visual biometric data derived from the at least one sensed non-visual biometric feature of the driver. In such embodiments and others, a computing system may be configured to receive non-visual biometric data from at least one sensor and determine a risk score for the driver during the time period based on received image data, the received non-visual biometric data, and AI technology. The received non-visual biometric data or its derivatives may be inputs generally used for AI technology or specifically for ANNs, decision trees, or other types of AI tools, or any combination thereof.

[0020] In some embodiments, at least one sensor may include a breathalyzer configured to sense a driver's blood alcohol content during a given time period, and at least one sensor may be configured to transmit data derived from the sensed blood alcohol content as at least a portion of non-visual biometric data. In such embodiments and others, at least one sensor may include a thermometer configured to sense a driver's body temperature during a given time period, and at least one sensor may be configured to transmit data derived from the sensed body temperature as at least a portion of non-visual biometric data. In such embodiments and others, at least one sensor may include a microphone configured to convert the sound of a driver's speech during a given time period into an audio signal, and at least one sensor may be configured to transmit data derived from the audio signal as at least a portion of non-visual biometric data.

[0021] In some embodiments, received image data transmitted from at least one camera may include information about the driver's posture. Furthermore, in such embodiments and others, received image data transmitted from at least one camera may include information about the driver's facial features.

[0022] In some embodiments, the vehicle's computing system is configured to train AI technology using supervised learning. The input to the supervised learning for the AI ​​technology may include image data of a sample driver and a risk score determined by a customer based on the sample driver's image. In this way, AI technology (e.g., an ANN or decision tree) can be specifically customized and trained for the customer. Furthermore, the input to the supervised learning for the AI ​​technology may include image data of a sample driver and a risk score determined by a ride-sharing service customer based on the sample driver's image. In this way, AI technology can generally be enhanced and trained for the service's customers. The input to the supervised learning of the ANN may also include non-visual biometric information of the sample driver and a risk score determined by the customer (or generally, the service's customers) based on the sample driver's non-visual biometric information.

[0023] In some embodiments, the vehicle's computing system is configured to determine the driver's biographical information via a carpooling service app, based at least on received biometric data and / or a database of the carpooling service's drivers. The database may store biographical information about registered drivers who have registered for the carpooling service. Furthermore, the stored biographical information may include at least one of the registered driver's biometrics, criminal history, driving behavior history, or service or traffic violation history, or any combination thereof. In such embodiments and others, the vehicle's computing system may be configured to determine a driver's risk score based on received biometric data, AI technology, and the determined biographical information. Inputs to the AI ​​technology may include biometric data or derivatives thereof and / or the determined biographical information or derivatives thereof.

[0024] Figure 1 A diagram illustrating an example vehicle 10 configured to perform driver screening for a ridesharing service, according to some embodiments of this disclosure. (See diagram for reference.) Figure 1 As shown, vehicle 10 includes a passenger compartment 12, which includes a driver's seat 14a, another front seat 14b, and a rear seat 14c. The passenger compartment 12 also includes a camera 16 facing the driver's seat 14a. The camera 16 has a field of view 18. Figure 1 In the embodiment shown, the viewing angle 18 appears to be less than 180 degrees. Viewing angle 18 allows camera 16 to record at least one image or video of the driver seated in driver's seat 14a. As shown, viewing angle 18 provides a field of view including the driver's head 20 and the driver's right shoulder 22b and left shoulder 22a. As shown, camera 16 is positioned away from the front of vehicle 10 or the vehicle's windshield (the windshield is...). Figure 1 (Not depicted in the text).

[0025] Camera 16 is shown in the passenger compartment 12 of vehicle 10. However, it should be understood that the camera used to record the driver can be positioned and attached to any part of vehicle 10, as long as it is positioned to capture an image or video of the driver in driver's seat 14a. As shown, Figure 1 A top-view cross-sectional view of vehicle 10, depicting the main body of the vehicle below the roof, is provided to show the vehicle's passenger compartment 12. And as... Figure 1 As shown, camera 16 is not a panoramic camera configured to record images from a wide horizontal angle; however, in some embodiments, camera 12 may be a panoramic camera. It should be understood that the camera's field of view can be any angle, as long as the field of view of this camera used to record images of the driver covers a sufficient area to capture the driver's behavior or characteristics in the driver's seat.

[0026] It should also be understood that different numbers of cameras can be used, and cameras with different or the same viewing angles can be used. In some embodiments, the fields of view of the cameras in the horizontal plane may or may not overlap. Moreover, in some embodiments, the vehicle may include one or more omnidirectional cameras to cover at least one complete circle in the horizontal plane relative to the interior of the vehicle's passenger compartment, or to cover the entire or nearly entire sphere having the interior of the vehicle's passenger compartment. Such embodiments can be used to capture the characteristics or behavior of the driver from other locations in the passenger compartment of the vehicle besides the driver's seat.

[0027] Figures 2 to 4 This description describes an example networked system 100 according to some embodiments of the present disclosure, comprising at least one ridesharing service system (RSSS), mobile devices, and vehicles (e.g., see mobile devices 140 to 142 and 302 and vehicles 102, 202, and 130 to 132), and configured to perform driver screening for ridesharing services. Any or more of vehicles 102, 202, and 130 to 132 may be... Figure 1 The vehicle 10 shown in the image or at least some parts of the vehicle 10 are included.

[0028] Networking system 100 is networked via one or more communication networks 122. The communication networks described herein (e.g., communication network 122) may include at least one local-to-device network (e.g., Bluetooth or the like), a wide area network (WAN), a local area network (LAN), an intranet, a mobile wireless network such as 4G or 5G, an extranet, the Internet, and / or any combination thereof. Nodes of networking system 100 (e.g., see mobile devices 140, 142, and 302, vehicles 102, 130, 132, and 202, and one or more RSSS servers 150) may each be part of a peer-to-peer network, a client-server network, a cloud computing environment, or the like. Furthermore, any of the devices, computing devices, vehicles, sensors, or cameras and / or user interfaces described herein may include some kind of computer system (e.g., see vehicle computing systems 104 and 204). This computer system may include network interfaces to other devices in the LAN, intranet, extranet, and / or the Internet. The computer system can also operate as a server or client machine in a client-server network environment, as a peer machine in a peer-to-peer (or distributed) network environment, or as a server or client machine in a cloud computing infrastructure or environment.

[0029] like Figure 2As shown, the networked system 100 may include at least one vehicle 102, which includes a vehicle computing system 104 (containing an RSSS client application 106, also referred to herein as RSSS client 106), a main body and controllable components of the main body (not depicted), a powertrain and controllable components of the powertrain (not depicted), a main body control module 108 (which is a type of electronic control unit or ECU), a powertrain control module 110 (which is a type of ECU), and a power steering control unit 112 (which is a type of ECU). The vehicle 102 also includes multiple sensors (e.g., see sensors 114a to 114b, which may include biometric sensors) and multiple cameras (e.g., see cameras 118a to 118b, which may include...). Figure 1 The image shows a camera 16 and a controller area network (CAN) bus 120, which connects at least the vehicle computing system 104, the main control module 108, the powertrain control module 110, the power steering control unit 112, multiple sensors, and multiple cameras to each other. Furthermore, as shown, the vehicle 102 is connected to the network 122 via the vehicle computing system 104. Also as shown, vehicles 130 to 132 and mobile devices 140 to 142 are connected to the network 122 and are thus communicatively coupled to the vehicle 102.

[0030] The RSSS client 106 included in the vehicle computing system 104 can communicate with the RSSS server 150. The RSSS client 106 may be or include an RSSS client specifically configured for use by customers of the carpooling service. Furthermore, the RSSS client 106 may be or include an RSSS client specifically configured for use by drivers of the carpooling service.

[0031] In some embodiments, vehicle 102 may include a body, powertrain, and chassis, as well as at least one camera and at least one sensor (e.g., see cameras 118a to 118b and sensors 114a to 114b). At least one camera and at least one sensor may each be attached to at least one of the body, powertrain, or chassis, or any combination thereof. For example, the camera or sensor may be embedded in or attached to the ceiling of the body of vehicle 102, the side wall of the body compartment, the door of the body, the front of the body compartment, or the rear of the body compartment (e.g., in or near the rear seat of the compartment). The camera or sensor may be configured to face inwards toward the compartment of vehicle 102 and capture, sense, or record a field of view covering up to a semicircle or a full circle relative to the horizontal plane of the vehicle to capture at least one image or non-visual biometric information of the driver within the vehicle compartment.

[0032] In such embodiments and others, vehicle 102 includes at least one camera (e.g., see cameras 118a to 118b) configured to record at least one image of the driver in the vehicle. Recording by the at least one camera can occur during a period of time. The at least one camera can be configured to generate and transmit biometric image data derived from the at least one image of the driver. Recording of at least one image can occur in response to a customer request to assess the driver to determine whether a ride in vehicle 102 has been booked. Recording of at least one image can occur during the period in which the customer makes the request. In other words, the request can occur during the period in which at least one image of the driver is recorded. The customer can make the request from a mobile device (e.g., see mobile devices 140 to 142 and mobile device 302).

[0033] In such embodiments and others, vehicle 102 includes a vehicle computing system 104 configured to receive image data from at least one camera (e.g., see cameras 118a-118b). Vehicle computing system 104 may also be configured to determine a driver's risk score based on the received image data, for example via an RSSS client 106. Vehicle computing system 104 may also be configured to determine a driver's risk score based on the received image data within a requested time period, for example via an RSSS client 106. The risk score may also be determined based on AI technology. AI technology may include ANNs, decision trees, or other types of AI tools, or any combination thereof. The received biometric image data or its derivatives may be inputs generally used for AI technologies or specifically used for one or more of the aforementioned AI tools. For example, the received biometric data or its derivatives may be inputs for ANNs. Vehicle computing system 104 may also be configured to transmit the driver's risk score to a customer, allowing the customer to decide whether to book a ride. The transmission of the risk score may reach the customer's mobile device (e.g., see mobile devices 140-142 and mobile device 302).

[0034] In such embodiments and others, vehicle 102 includes at least one sensor (e.g., see sensors 114a to 114b) configured to sense at least one non-visual biometric feature of the driver. Sensing of at least one non-visual biometric feature of the driver can occur during a period in which an image of the driver is recorded. The at least one sensor can also be configured to transmit non-visual biometric data derived from at least one sensed non-visual biometric feature of the driver. Sensing of at least one non-visual biometric feature of the driver can occur in response to a customer request to assess the driver in order to determine whether to book a ride in vehicle 102. And sensing of at least one non-visual biometric feature can occur during the period in which the customer makes the request. In other words, the request can occur during the period in which at least one non-visual biometric feature of the driver is sensed. And the customer can make the request from a mobile device (e.g., see mobile devices 140 to 142 and mobile device 302).

[0035] In such embodiments and others, the vehicle computing system 104 may also be configured to receive non-visual biometric data from at least one sensor (e.g., see sensors 114a to 114b). The vehicle computing system 104 may also be configured to determine a driver's risk score based on the received non-visual biometric data, for example via an RSSS client 106. The vehicle computing system 104 may also be configured to determine a driver's risk score for a requested time period based on the received non-visual biometric data, for example via an RSSS client 106. The risk score may also be determined based on AI technology. AI technology may include ANNs, decision trees, or other types of AI tools, or any combination thereof. The received non-visual biometric data or its derivatives may be inputs generally used for AI technologies or specifically used for one or more of the aforementioned AI tools. For example, the received non-visual biometric data or its derivatives may be inputs for ANNs. In other words, the risk score may be determined based on image data, non-visual biometric data, or ANNs or other types of AI technologies, or any combination thereof. In such instances, received non-visual biometric data or derivatives thereof and / or received image data or derivatives thereof may serve as input for ANNs or other types of AI technologies. Furthermore, in such instances, the vehicle computing system 104 may also be configured to transmit a driver's risk score to a customer, allowing the customer to decide whether to book a ride, and the transmission of the risk score may reach the customer's mobile device (e.g., see mobile devices 140 to 142 and mobile device 302).

[0036] In such embodiments and others, the vehicle computing system 104 may be configured to receive biometric image data and / or non-visual biometric data, for example, via an RSSS client 106, and determine a driver risk score, for example, via the RSSS client 106, based on the received biometric data and AI technology. The AI ​​technology may include ANNs, decision trees, or other types of AI tools, or any combination thereof. The received biometric data or its derivatives may be inputs generally used for AI technologies or specifically used for one or more of the aforementioned AI tools. The vehicle computing system 104 may also be configured to determine, for example, via the RSSS client 106, whether to notify potential customers of the risk score of vehicle 102 based on the risk score exceeding a risk threshold. This may occur before the driver's risk score is transmitted to the customer.

[0037] In such embodiments and others, at least one sensor (e.g., see sensors 114a to 114b) may include a breathalyzer configured to sense the driver's blood alcohol content during a certain period, and at least one sensor may be configured to transmit data derived from the sensed blood alcohol content as at least a portion of non-visual biometric data. In such embodiments and others, at least one sensor (e.g., see sensors 114a to 114b) may include a thermometer configured to sense the driver's body temperature during a certain period, and at least one sensor may be configured to transmit data derived from the sensed body temperature as at least a portion of non-visual biometric data. In such embodiments and others, at least one sensor (e.g., see sensors 114a to 114b) may include a microphone configured to convert the sound of the driver's speech during a certain period into an audio signal, and at least one sensor may be configured to transmit data derived from the audio signal as at least a portion of non-visual biometric data.

[0038] In some embodiments, received image data transmitted from at least one camera (e.g., see cameras 118a to 118b) may include information about the driver's posture. And in such embodiments and others, received image data transmitted from at least one camera may include information about the driver's facial features.

[0039] In some embodiments, the vehicle computing system 104 of vehicle 102 is configured to train AI technology using supervised learning. The input to the supervised learning for the AI ​​technology may include image data of a sample driver and a risk score determined by a customer based on the sample driver's image. In this way, AI technology (e.g., an ANN or decision tree) can be specifically customized and trained for the customer. Furthermore, the input to the supervised learning for the AI ​​technology may include image data of a sample driver and a risk score determined by a ride-sharing service customer based on the sample driver's image. In this way, AI technology can generally be enhanced and trained for the service's customers. The input to the supervised learning for the ANN may also include non-visual biometric information of the sample driver and a risk score determined by the customer (or generally, the service's customers) based on the sample driver's non-visual biometric information.

[0040] In some embodiments, the vehicle computing system 104 of vehicle 102 is configured to determine the biographical information of the vehicle's drivers, for example, via RSSS client 106, based at least on received biometric data and / or a database of drivers for the carpooling service (e.g., connected to or part of the database of RSSS server 150). The database may store biographical information about registered drivers for the carpooling service. The stored biographical information may include the registered driver's biometrics and at least one of the registered driver's criminal history, driving behavior history, or service or traffic violation history, or any combination thereof. In such embodiments and others, the vehicle computing system 104 of vehicle 102 may be configured to determine a driver's risk score based on received biometric data, AI technology, and the determined biographical information of the driver. Inputs for the AI ​​technology may include biometric data or derivatives thereof and / or determined biographical information or derivatives thereof.

[0041] In some embodiments, received biometric data from cameras and / or sensors (e.g., see cameras 118a to 118b and sensors 114a to 114b) may include information about the driver's gait when approaching vehicle 102 before driving, information about the driver's posture when approaching or inside the vehicle, or information about the driver's facial features, or any combination thereof. The received biometric data may also include information about the driver's blood alcohol content, the driver's body temperature, or the driver's voice, or any combination thereof.

[0042] The mobile devices described herein (e.g., see mobile devices 140 to 142 and mobile device 302) may include a user interface (e.g., see [reference]). Figure 4Other components 316 of the mobile device 302 shown herein are configured to output a risk score, for example, via an RSSS client 106. The risk score can be output by the mobile device's UI to notify the customer when the vehicle calculation system 104 of vehicle 102 determines that the risk score exceeds a risk threshold. The user interface of the mobile device can be configured to provide, for example, a graphical user interface (GUI), a haptic user interface, or an auditory user interface, or any combination thereof, via the RSSS client 106. Furthermore, the embodiments described herein may include one or more user interfaces of any type, including haptic UI (touch), visual UI (vision), auditory UI (sound), olfactory UI (odor), balance UI (balance), and gustatory UI (taste).

[0043] Figure 2 Not described in the text but as Figure 1 As depicted, vehicle 102 may include cameras (e.g., see cameras 16 and 118a-118b) that face inward toward the vehicle compartment in one or more directions to have a field of view covering at least a semicircle in a horizontal plane relative to the vehicle. The cameras may include at least one camera configured to record at least one image of the driver and to generate and transmit biometric data derived from the at least one image of the driver. In some embodiments, the cameras may have a field of view covering at least one full circle in a horizontal plane to record at least one image of the driver in vehicle 102 from any direction in the horizontal plane.

[0044] In some embodiments, the vehicle computing system 104 (e.g., via RSSS client 106) may be configured to receive and process data (e.g., data containing instruction data for the vehicle and its systems and / or data relating to the driver's biometric information and / or biographical information stored in the RSSS database). For example, data may be received by the vehicle computing system 104 (e.g., via RSSS client 106) via components of network 122 from cameras, sensors, and / or RSSS server 150, and the received data may then be processed to be included in other processing steps described herein. The received data may include information derived from at least associated risk score data, image data, sensed non-visual biometric data, time data, location data, or other background data about the driver sent from vehicle 102 or other vehicles (e.g., see vehicles 130 to 132). In some embodiments, the derivation and / or subsequent processing of the received data may be based on AI technology, and the AI ​​technology may be trained by the RSSS computing system, vehicle 102, or the driver's or customer's mobile device (e.g., see mobile devices 140 to 142). In such embodiments and others, the customer's mobile device may include a user interface (e.g., a graphical user interface) (see, for example, see...). Figure 4Other components 316 of the mobile device 302 depicted may include a GUI configured to provide a client with at least a portion of the received and processed data.

[0045] Vehicle 102 includes vehicle electronics, including at least electronic components for controllable parts of the main body, controllable parts of the powertrain, and controllable parts of the power steering. Vehicle 102 includes controllable parts of the main body, and such parts and subsystems are connected to a main body control module 108. The main body includes at least one frame supporting the powertrain. The vehicle chassis may be attached to the vehicle frame. The main body may also include an interior for at least one driver or passenger. The interior may include seats. The controllable parts of the main body may also include one or more power doors and / or one or more power windows. The main body may also include any other known components of the vehicle body. Furthermore, the controllable parts of the main body may include a convertible roof, sunroof, power seats, and / or any other type of controllable parts of the vehicle body. The main body control module 108 controls the controllable parts of the main body. Moreover, vehicle 102 also includes controllable parts of the powertrain. Controllable parts of the powertrain and its components and subsystems are connected to a powertrain control module 110. The controllable parts of the powertrain may include at least one engine, transmission, drive shaft, suspension and steering system, and powertrain electrical system. The powertrain may also include any other known components of the vehicle powertrain, and the controllable components of the powertrain may include any other known controllable components of the powertrain. Furthermore, the controllable power steering components may be controlled via the power steering control unit 112.

[0046] The vehicle 102 may include multiple sensors (e.g., see sensors 114a to 114b) and / or multiple cameras (e.g., see cameras 118a to 118b) of any type, configured to sense and / or record one or more characteristics or features of the driver or the surrounding environment of the vehicle 102 within the vehicle compartment (e.g., see compartment 12), for example when the driver is near a vehicle in the surrounding environment. The sensors or cameras of the vehicle 102 may also be configured to output generated data corresponding to one or more characteristics or features of the driver. Any of the multiple sensors or cameras may also be configured to transmit the generated data corresponding to one or more characteristics or features of the driver to the vehicle computing system 104 or other electronic circuitry of the vehicle 102, for example, via CAN bus 120. Transmitting data to other electronic circuitry of the vehicle 102 may be useful when the driver is intoxicated, fatigued, ill, or otherwise unable to drive properly. For example, in response to a driver being intoxicated, fatigued, ill, or otherwise unable to drive properly, data or its derivatives may be sent to the main control module 108 to lock or position the driver's seat to alert the driver that he should not drive, to the powertrain control module 110 to prevent the engine from starting, and / or to the power steering control unit 112 to lock the wheels in the direction of movement toward the vehicle's parking position.

[0047] A set of mechanical components for controlling the drive of vehicle 102 may include: (1) a braking mechanism on the wheels of the vehicle (for stopping wheel rotation); (2) a throttle mechanism on the engine of the vehicle or engine (for regulating how much gasoline or current enters the engine), which determines how fast the drive shaft can rotate and thus how fast the vehicle can travel; and (3) a steering mechanism for the direction of the front wheels of the vehicle (e.g., so that the vehicle travels in the direction the wheels are pointing). These mechanisms can control the braking (or deceleration), acceleration (or throttling), and steering of vehicle 102. The driver can control the vehicle via a user-operable UI element (e.g., see [link to relevant documentation]). Figure 3 Other components 216 of the vehicle 202 shown (which are typically the brake pedal, accelerator pedal, and steering wheel) indirectly control these mechanisms. The pedals and steering wheel are not necessarily mechanically connected to the drive mechanism for braking, acceleration, and steering. Such components may have or be close to sensors that measure how much force the driver applies to the pedals and / or how much the steering wheel is turned. The sensed control inputs are transmitted via wires to a control unit (and thus can be drive-by-wire). Such a control unit may include a main control module 108 or 220, a powertrain control module 110 or 222, a power steering control unit 112 or 224, a battery management system 226, etc. This output can also be sensed and / or recorded by the sensors and cameras described herein (e.g., see sensors 114a to 114b or 217a to 217b and cameras 118a to 118b or 219a to 219b). The outputs of the sensors and cameras can be further processed, for example, by an RSSS client 106 and then reported to an RSSS server 150 for data processing to accumulate background data related to the vehicle's driver.

[0048] In vehicles such as the 102 or 202, the driver controls the vehicle via physical control elements (e.g., steering wheel, brake pedal, accelerator, paddle shifter, etc.), which are connected to drive components via mechanical linkages and some electromechanical linkages. However, increasingly more vehicles now have control elements that connect to mechanical powertrain components (e.g., braking system, steering mechanism, drivetrain, etc.) via electronic control elements or modules (e.g., electronic control unit or ECU). These electronic control elements or modules can be part of drive-by-wire technology. Drive-by-wire technology can include electrical or electromechanical systems for performing vehicle functions typically achieved by mechanical linkages. The technology can replace traditional mechanical control systems with electronic control systems (e.g., pedal and steering feel simulators) using electromechanical actuators and human-machine interfaces. Components such as steering levers, intermediate shafts, pumps, hoses, belts, coolers, vacuum servos, and master cylinders can be eliminated from the vehicle. Drive-by-wire technology exists in different degrees and types. Vehicles with drive-by-wire technology, such as vehicles 102 and 202, may include a modulator (e.g., a modulator comprising an ECU and / or an advanced driver assistance system or ADAS, or a part thereof) that receives input from a user or driver (e.g., via more conventional control or via drive-by-wire control or a combination thereof). The modulator can then use the driver's input to modulate the input or transform it into a matching input for a "safe driver".

[0049] In some embodiments, the electronic circuitry of a vehicle (e.g., see vehicles 102 and 202) that may include a computing system of the vehicle or a part thereof may include at least one of the following: engine electronics, transmission electronics, chassis electronics, driver or passenger environment and comfort electronics, in-vehicle entertainment electronics, in-vehicle safety electronics, or navigation system electronics, or any combination thereof (e.g., see respectively in Figure 2 and 3 The main control modules 108 and 220, powertrain control modules 110 and 222, power steering control unit 112 and 224, battery management system 226, and infotainment electronics 228 are shown in the diagram. In some embodiments, the vehicle's electronic circuitry may include electronics for an autonomous driving system.

[0050] like Figure 3 As shown, the network system 100 may include at least vehicles 130 to 132 and vehicle 202. Vehicle 202 includes at least one vehicle computing system 204, a main body (not shown) with interior (not shown), a powertrain (not shown), a climate control system (not shown), and an entertainment information system (not shown). Vehicle 202 may also include other vehicle components.

[0051] Vehicle computing system 204, which may have a similar structure and / or functionality to vehicle computing system 104, may be connected to communication network 122. Communication network 122 may include at least one local-to-device network (e.g., Bluetooth or similar), wide area network (WAN), local area network (LAN), intranet, mobile wireless network such as 4G or 5G, extranet, Internet, and / or any combination thereof. Vehicle computing system 204 may be a machine capable of executing a set of instructions (sequential or otherwise) specifying actions to be taken by the machine. Moreover, although a single machine for vehicle computing system 204 has been described, the term "machine" should also be considered as any collection of machines that individually or jointly execute a set (or more sets) of instructions to perform a method or operation. It may include at least one bus (e.g., see bus 206) and / or a motherboard, one or more controllers (e.g., one or more CPUs, see controller 208), a main memory that may include temporary data storage devices (e.g., see memory 210), at least one type of network interface (e.g., see network interface 212), a storage system that may include permanent data storage devices (e.g., see data storage system 214), and / or any combination thereof. In some multi-device embodiments, one device may perform some parts of the method described herein and then send the result via a network to another device, allowing the other device to continue with the remaining steps of the method described herein.

[0052] Figure 3Example components of a vehicle computing system 204 that may include and implement an RSSS client 106 are also described. The vehicle computing system 204 is communicatively coupled to a network 122, as shown. The vehicle computing system 204 includes at least one bus 206, a controller 208 (e.g., a CPU) capable of executing instructions for the RSSS client 106, a memory 210 capable of storing the execution instructions for the RSSS client 106, a network interface 212, a data storage system 214 capable of storing instructions for the RSSS client 106, and other components 216. These other components 216 may be any type of component found in a mobile or computing device (e.g., a GPS component), I / O components (e.g., cameras and various types of user interface components (which may include one or more of the multiple UI elements described herein), and sensors (which may include one or more of the multiple sensors described herein). The other components 216 may include one or more user interfaces (e.g., GUI, auditory user interface, haptic user interface, vehicle control, etc.), a display, different types of sensors, haptic, audio, and... / or visual input / output devices, additional dedicated memory, one or more additional controllers (e.g., GPUs), or any combination thereof. The vehicle computing system 204 may also include sensor and camera interfaces configured to interface with the sensors and cameras of the vehicle 202, which may be one or more of the sensors or cameras described herein (e.g., see sensors 217a to 217b and cameras 219a to 219b). In some embodiments, bus 206 communicatively couples controller 208, memory 210, network interface 212, data storage system 214, other components 216, and sensors and cameras, as well as the sensor and camera interfaces. The vehicle computing device 204 includes a computer system comprising at least controller 208, memory 210 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM) (e.g., synchronous DRAM (SDRAM) or Rambus DRAM (RDRAM)), static random access memory (SRAM), cross-point memory, interleaved memory, etc.), and data storage system 214, which communicate with each other via bus 206 (which may include multiple buses).

[0053] In some embodiments, the vehicle computing system 204 may include a set of instructions for causing the machine to perform any or more of the methods discussed herein during execution. In such embodiments, the machine may be connected (e.g., networked via network interface 212) to other machines in a LAN, intranet, extranet, and / or the Internet (e.g., network 122). The machine may operate as a server or client machine in a client-server network environment, as a peer-to-peer machine in a peer-to-peer (or distributed) network environment, or as a server or client machine in a cloud computing infrastructure or environment.

[0054] Controller 208 represents one or more general-purpose processing devices, such as microprocessors, central processing units, or the like. More particularly, the processing device may be a Complex Instruction Set Computing (CISC) microprocessor, a Reduced Instruction Set Computing (RISC) microprocessor, a Very Long Instruction Word (VLIW) microprocessor, a Single Instruction Multiple Data (SIMD), a Multiple Instruction Multiple Data (MIMD) processor, or a processor implementing other instruction sets or a combination of instruction sets. Controller 208 may also be one or more special-purpose processing devices, such as ASICs, programmable logic (e.g., FPGAs), digital signal processors (DSPs), network processors, or the like. Controller 208 is configured to execute instructions for performing the operations and steps discussed herein. Controller 208 may further include a network interface device, such as network interface 212, communicating via one or more communication networks (e.g., network 122).

[0055] Data storage system 214 may include machine-readable storage media (also referred to as computer-readable media) on which one or more sets of instructions or software embodying any or more of the methods or functions described herein are stored. Data storage system 214 may be executable, for example, it may at least partially execute instructions residing in the data storage system. Instructions may also reside wholly or at least partially in memory 210 and / or controller 208 during execution by a computer system, memory 210 and controller 208 also constituting machine-readable storage media. Memory 210 may be or include the main memory of system 204. Memory 210 may be executable, for example, it may at least partially execute instructions residing in memory.

[0056] Vehicle 202 may also include a main body control module 220, a powertrain control module 222, a power steering control unit 224, a battery management system 226, infotainment electronics 228, and a CAN bus 218. The CAN bus 218 connects at least the vehicle computing system 204, the body control module, the powertrain control module, the power steering control unit, the battery management system, and the infotainment electronics. Furthermore, as shown, vehicle 202 is connected to network 122 via vehicle computing system 204. Also as shown, vehicles 130 to 132 and mobile devices 140 to 142 are connected to network 122 and are therefore communicatively coupled to vehicle 202.

[0057] Vehicle 202 is also shown to have multiple sensors (e.g., see sensors 217a to 217b) and multiple cameras (e.g., see cameras 219a to 219b) that may be part of vehicle computing system 204. In some embodiments, CAN bus 218 can connect the multiple sensors and multiple cameras, vehicle computing system 204, vehicle control module, powertrain control module, power steering control unit, battery management system, and infotainment electronics to at least vehicle computing system 204. The multiple sensors and multiple cameras can be connected to vehicle computing system 204 via sensor and camera interfaces of the computing system.

[0058] like Figure 4 As shown, the networking system 100 may include at least one mobile device 302 and mobile devices 140 to 142. Mobile device 302 (which may have a structure and / or functionality somewhat similar to vehicle computing systems 104 or 204) can connect to communication network 122 and thus to vehicles 102, 202, and 130 to 132 and mobile devices 140 to 142. Mobile device 302 (or mobile devices 140 or 142) may include one or more of the sensors mentioned herein, one or more of the UI elements mentioned herein, a GPS device, and / or one or more of the cameras mentioned herein. Therefore, mobile device 302 (or mobile devices 140 or 142) can function similarly to vehicle computing systems 104 or 204 and can manage and run RSSS client 106.

[0059] Depending on the embodiment, mobile device 302 may be or include mobile devices or the like, such as smartphones, tablets, IoT devices, smart TVs, smartwatches, glasses or other smart home appliances, in-vehicle infotainment systems, wearable smart devices, game consoles, PCs, digital cameras, or any combination thereof. As shown, mobile device 302 may be connected to communication network 122, which includes at least one local-to-device network (e.g., Bluetooth or the like), wide area network (WAN), local area network (LAN), intranet, mobile wireless network such as 4G or 5G, extranet, Internet, and / or any combination thereof.

[0060] Each of the mobile devices described herein may be, or replace, a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, a network device, a server, a network router, a switch, or a bridge, or any machine capable of executing a set of instructions (sequential or otherwise) specifying actions to be taken by the machine. The computing system of the vehicle described herein may be a machine capable of executing a set of instructions (sequential or otherwise) specifying actions to be taken by the machine.

[0061] Furthermore, while a single machine is described for use in the computing systems and mobile devices described herein, the term "machine" should also be considered as any collection of machines that individually or jointly execute one (or more) sets of instructions to perform any or more of the methods or operations discussed herein. Each of the described mobile devices may each include at least one bus and / or motherboard, one or more controllers (e.g., one or more CPUs), main memory that may include temporary data storage devices, at least one type of network interface, a storage system that may include permanent data storage devices, and / or any combination thereof. In some multi-device embodiments, one device may perform some parts of the methods described herein and then send the completed result via a network to another device, allowing the other device to continue with the remaining steps of the methods described herein.

[0062] Figure 4 Example components of a mobile device 302 according to some embodiments of the present disclosure are also described. The mobile device 302 is communicatively coupled to a network 122, as shown. The mobile device 302 includes at least one bus 306, a controller 308 (e.g., a CPU), a memory 310, a network interface 312, a data storage system 314, and other components 316 (which may be any type of component found in mobile or computing devices, such as GPS components, I / O components, various types of user interface components, and sensors (e.g., biometric sensors), and one or more cameras). Other components 316 may include one or more user interfaces (e.g., GUI, auditory user interface, haptic user interface, etc.), a display, different types of sensors, haptic (e.g., biometric sensors), audio and / or visual input / output devices, additional dedicated memory, one or more additional controllers (e.g., GPUs), or any combination thereof. The bus 306 communicatively couples the controller 308, memory 310, network interface 312, data storage system 314, and other components 316. The mobile device 302 includes a computer system that includes at least a controller 308, a memory 310 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM) (e.g., synchronous DRAM (SDRAM) or Rambus DRAM (RDRAM)), static random access memory (SRAM), cross-point memory, interleaved memory, etc.) and a data storage system 314, which communicate with each other via a bus 306 (which may include multiple buses).

[0063] in other words, Figure 4This is a block diagram of a mobile device 302 having a computer system operable in embodiments of the present disclosure. In some embodiments, the computer system may include a set of instructions for causing the machine to perform some of the methods discussed herein during execution. In such embodiments, the machine may be connected (e.g., networked via network interface 312) to other machines in a LAN, intranet, extranet, and / or the Internet (e.g., network 122). The machine may operate as a server or client machine in a client-server network environment, as a peer-to-peer (or distributed) network environment, or as a server or client machine in a cloud computing infrastructure or environment.

[0064] Controller 308 represents one or more general-purpose processing devices, such as microprocessors, central processing units, or the like. More particularly, the processing device may be a Complex Instruction Set Computing (CISC) microprocessor, a Reduced Instruction Set Computing (RISC) microprocessor, a Very Long Instruction Word (VLIW) microprocessor, a Single Instruction Multiple Data (SIMD), a Multiple Instruction Multiple Data (MIMD) processor, or a processor implementing other instruction sets or a combination of instruction sets. Controller 308 may also be one or more special-purpose processing devices, such as ASICs, programmable logic (e.g., FPGAs), digital signal processors (DSPs), network processors, or the like. Controller 308 is configured to execute instructions for performing the operations and steps discussed herein. Controller 308 may further include a network interface device, such as network interface 312, communicating via one or more communication networks (e.g., network 122).

[0065] Data storage system 314 may include machine-readable storage media (also referred to as computer-readable media) on which one or more sets of instructions or software embodying any or more methods or functions described herein are stored. Data storage system 314 may be executable, for example, it may at least partially execute instructions residing in the data storage system. Instructions may also reside wholly or at least partially in memory 310 and / or controller 308 during execution by a computer system, memory 310 and controller 308 also constituting machine-readable storage media. Memory 310 may be or include the main memory of device 302. Memory 310 may be executable, for example, it may at least partially execute instructions residing in memory.

[0066] Although the memory, controller, and data storage components are each shown as a single component in the exemplary embodiments, each component should be considered as a single component or multiple components that can store instructions and perform their respective operations. The term "machine-readable storage medium" should also be considered as any medium capable of storing or encoding a set of instructions that are executed by a machine and cause the machine to perform any or more of the methods of this disclosure. The term "machine-readable storage medium" should accordingly be considered as including (but not limited to) solid-state memory, optical media, and magnetic media.

[0067] like Figure 4 As shown, mobile device 302 may include a user interface (e.g., see other component 316). The user interface may be configured to provide a graphical user interface (GUI), a haptic user interface, or an auditory user interface, or any combination thereof. For example, the user interface may be or include a display connected to at least one of a wearable structure, computing device, or camera, or any combination thereof, which may also be part of mobile device 302, and the display may be configured to provide a GUI. Furthermore, the embodiments described herein may include one or more user interfaces of any type, including haptic UI (touch), visual UI (vision), auditory UI (sound), olfactory UI (odor), balance UI (balance), and gustatory UI (taste).

[0068] Figure 5 This describes some embodiments of the present disclosure that can be provided by Figure 1 Vehicle 10 depicted in the text and Figures 2 to 4 The flowchart illustrates an instance operation of method 400 performed by an aspect of the networked system 100. For example, method 400 may be performed by... Figures 1 to 4 The computing system and / or other components of any vehicle and / or mobile device depicted herein are executed.

[0069] exist Figure 5In this method, method 400 begins at step 402, wherein during a time period, the vehicle or the driver's mobile device receives a mobile device request from a customer to determine whether they have booked a ride in the vehicle, and assesses the driver. At step 404, method 400 continues by one or more cameras in the vehicle (or one or more cameras on the driver's mobile device in the vehicle) recording one or more images of the driver in the vehicle during the time period. At step 406, method 400 continues by the cameras transmitting biometric image data derived from at least one image of the driver. At step 408, method 400 continues by one or more sensors in the vehicle (or one or more sensors on the driver's mobile device in the vehicle) sensing one or more non-visual biometric features of the driver during the time period. At step 410, method 400 continues by the sensors transmitting non-visual biometric data derived from the non-visual biometric features. At step 412, method 400 continues by the vehicle's (or the mobile device's) computing system receiving biometric data from the cameras and / or sensors. In step 414, method 400 continues by having the computing system determine the driver's risk score for the time period based on an ANN or decision tree and received biometric data (e.g., the ANN or decision tree is received from an RSSS server or the customer's mobile device). In step 416, method 400 continues by having the computing system transmit the driver's risk score to the customer's mobile device, allowing the customer to decide whether to book a ride.

[0070] Figure 6 This describes some embodiments of the present disclosure that can be provided by Figure 1 Vehicle 10 depicted in the text and Figures 2 to 4 The flowchart illustrates an instance operation of method 500 performed by an aspect of the networked system 100. For example, method 500 may be performed by... Figures 1 to 4 The computing system and / or other components of any vehicle and / or mobile device depicted herein are executed.

[0071] exist Figure 6 In this method, 500 may begin at step 502a, wherein the mobile device of a ride-hailing customer receives biometric information of a first sample driver. Method 500 may also begin at step 502b, wherein the mobile device receives biometric information of a second sample driver. Method 500 may also begin at step 502c, wherein the mobile device receives biometric information of another sample driver. As shown, method 500 may begin with at least three different examples of receiving biometric information of at least three corresponding sample drivers. The reception of biometric information may occur simultaneously or sequentially.

[0072] In step 504a, method 500 continues to display the biometric information of the first sample driver via the mobile device. In step 504b, method 500 continues to display the biometric information of the second sample driver via the mobile device. In step 504c, method 500 continues to display the biometric information of another sample driver via the mobile device. As shown, method 500 continues to display at least three different examples of biometric information of at least three corresponding sample drivers. The display of biometric information may occur simultaneously or sequentially.

[0073] In step 506a, method 500 continues by requesting the user, via the mobile device, to input a first risk score for the first sample driver based on the biometric information of the first sample driver. In step 506b, method 500 continues by requesting the user, via the mobile device, to input a second risk score for the second sample driver based on the biometric information of the second sample driver. In step 506c, method 500 continues by requesting the user, via the mobile device, to input another risk score for another sample driver based on the biometric information of another sample driver. As shown, method 500 continues by requesting the user to input risk scores for at least three different corresponding sample drivers. The request for the user to input risk scores for at least three different corresponding sample drivers may occur simultaneously or sequentially.

[0074] In step 508a, method 500 continues to receive a first risk score from the customer via the mobile device. In step 508b, method 500 continues to receive a second risk score from the customer via the mobile device. In step 508c, method 500 continues to receive another risk score from the customer via the mobile device. As shown, method 500 continues to receive risk scores from at least three different corresponding sample drivers from the customer. The receipt of risk scores from the customer may occur simultaneously or sequentially.

[0075] In step 510, method 500 continues to train an ANN or decision tree using the risk score and biometric information of the sample driver as training input from the customer's mobile device or one or more servers of the ride-hailing service. For example, the training at step 510 may involve repeatedly inputting biometric information corresponding to the received selected risk score until the ANN or decision tree substantially outputs the received selected risk score, and repeating this training process for each received risk score to enhance the ANN or decision tree for different risk scores.

[0076] In some embodiments, it should be understood that the steps of methods 400 and 500 can be implemented as a continuous process, for example, each step can operate independently by monitoring input data, performing an operation, and outputting data to subsequent steps. Moreover, such steps of each method can be implemented as discrete-event processes, for example, each step can be triggered on an event that it should trigger and produce a specific output. It should also be understood that... Figures 5 to 6 Each figure in the diagram represents a ratio Figures 2 to 4The middle part presents a more complex computer system, which may have a larger minimum method within the larger method. Therefore, Figures 5 to 6 Each step depicted in each figure can be combined with other steps fed into and fed out of the step from other steps associated with a larger method for a more complex system.

[0077] It should be understood that the vehicle described herein can be any type of vehicle unless otherwise specified. Vehicles can include automobiles, trucks, ships, and aircraft, as well as vehicles or vehicle equipment used for construction, agriculture, or recreational purposes. Electronic devices used by a vehicle, vehicle components, or the driver or passengers of a vehicle can be considered vehicle electronics. Vehicle electronics can include electronics used for engine management, ignition, radio, vehicle computers, telematics, in-vehicle entertainment systems, and other components of the vehicle. Vehicle electronics can be used in conjunction with or by ignition and engine and transmission control, and can be found in vehicles with internal combustion engine machinery, such as gasoline-powered cars, trucks, motorcycles, ships, aircraft, forklifts, tractors, and excavators. Furthermore, vehicle electronics can be used by or with related components to control electrical systems found in hybrid and electric vehicles (e.g., hybrid or electric vehicles). For example, electric vehicles can use power electronics for main propulsion motor control and battery system management. Autonomous vehicles rely almost entirely on vehicle electronics.

[0078] Some parts of the foregoing detailed description have been presented based on the algorithms and symbolic representations of operations on data bits within computer memory. These algorithmic descriptions and representations are the means by which those skilled in the art of data processing most effectively communicate the essence of their work to others skilled in the art. Algorithms are generally conceived herein as self-consistent sequences of operations that lead to desired results. Operations are operations that require the physical manipulation of physical quantities. Usually, but not always, these quantities take the form of electrical or magnetic signals that can be stored, combined, compared, and otherwise manipulated. It has proven convenient, primarily for common reasons, to refer to these signals as bits, values, elements, symbols, characters, items, numbers, or the like.

[0079] However, it should be remembered that all these and similar terms should be associated with appropriate physical quantities and are merely convenient labels for application to those quantities. This disclosure may relate to the operation and processes of a computer system or similar electronic computing device that manipulate and transform data representing physical (electronic) quantities in the registers and memories of the computer system into other data similarly represented in the memory or registers of the computer system or other such information storage systems.

[0080] This disclosure also relates to apparatus for performing the operations described herein. Such apparatus may be specifically constructed for its intended purpose, or may comprise a general-purpose computer selectively activated or reconfigured by a computer program stored in a computer. This computer program may be stored in a computer-readable storage medium, such as any type of disk (including floppy disks, optical disks, CD-ROMs, and magneto-optical disks), read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic cards, or optical cards, or any type of media suitable for storing electronic instructions, each coupled to a computer system bus.

[0081] The algorithms and displays presented herein are not inherently related to any particular computer or other device. Various general-purpose systems can be used with the teachings and procedures herein, or it may be proven convenient to construct more specialized devices to implement the methods. The structures of various such systems will appear as described below. Furthermore, this disclosure does not refer to any particular programming language. It should be understood that various programming languages ​​can be used to implement the teachings of this disclosure described herein.

[0082] This disclosure may be provided as a computer program product or software, which may include a machine-readable medium having instructions stored thereon, the instructions being used to program a computer system (or other electronic device) to perform processes according to this disclosure. The machine-readable medium includes any means for storing information in a form readable by a machine (e.g., a computer). In some embodiments, the machine-readable (e.g., computer-readable) medium includes machine-readable storage media, such as read-only memory (“ROM”), random access memory (“RAM”), disk storage media, optical storage media, flash memory components, etc.

[0083] In the foregoing description, embodiments thereof have been described with reference to specific examples of this disclosure. It is apparent that various modifications may be made to this disclosure without departing from the broader spirit and scope of the embodiments set forth in the appended claims. Therefore, the specification and drawings should be considered illustrative rather than limiting.

Claims

1. An apparatus comprising: At least one processing device; and A memory containing instructions configured to instruct the at least one processing device to perform the following operations: Receive image data provided by at least one camera of the vehicle, wherein the image data is derived from at least one image of the driver in the vehicle, and wherein the at least one camera is configured to record the at least one image in response to a request from a first user of a first mobile device outside the vehicle; The risk score of the driver is determined using an artificial neural network with input based on received image data, wherein the artificial neural network has been trained using previous images of the driver and corresponding risk scores; as well as Communication transmissions are made to the first mobile device for use in providing a display on the first mobile device based on a determined risk score.

2. The device of claim 1, further comprising at least one sensor, wherein the instructions are further configured to instruct the at least one processing device: Receive biometric data provided by the at least one sensor; The input to the artificial neural network is further based on the received biometric data.

3. The device of claim 2, wherein the at least one sensor comprises a breathalyzer configured to sense the driver’s blood alcohol content.

4. The device of claim 2, wherein the at least one sensor comprises a thermometer configured to sense the driver's body temperature.

5. The device of claim 2, wherein the at least one sensor includes a microphone.

6. The device of claim 1, wherein the display on the first mobile device includes biometric data about the driver.

7. The device of claim 1, wherein the received image data includes data relating to at least one of the driver's posture or facial features.

8. The device of claim 1, wherein the instructions are further configured to instruct the at least one processing device to train the artificial neural network based on data from the at least one camera.

9. The device of claim 8, wherein the input for the artificial neural network is further based on data relating to images of a first driver of other vehicles and a corresponding risk score determined by a user for the first driver.

10. The device of claim 9, wherein the input for the artificial neural network is further based on the biometric data of the first driver.

11. A system comprising: At least one camera configured to record at least one image of the driver in the vehicle, wherein the at least one image is recorded in response to a request from a user of a mobile device outside the vehicle; and The computing system is configured to: Receive image data derived from the at least one image; The risk score of the driver is determined using an artificial neural network or decision tree with input based on received image data, wherein the artificial neural network or decision tree has been trained using previous images of the driver and corresponding risk scores; as well as The communication used to provide the display on the mobile device based on the determined risk score is transmitted to the mobile device.

12. The system of claim 11, further comprising at least one sensor, wherein the computing system is further configured to: Receive biometric data from the at least one sensor; The input to the artificial neural network or decision tree is further based on the received biometric data.

13. The system of claim 12, wherein the at least one sensor comprises a breathalyzer configured to sense the driver’s blood alcohol content and provide data derived from the sensed blood alcohol content as part of the biometric data.

14. The system of claim 12, wherein the at least one sensor comprises a thermometer configured to sense the driver’s body temperature and provide data derived from the sensed body temperature as part of the biometric data.

15. The system of claim 12, wherein the at least one sensor includes a microphone configured to convert the sound of the driver's speech into an audio signal and to provide data derived from the audio signal as part of the biometric data.

16. The system of claim 11, wherein the received image data includes data about the driver's posture.

17. The system of claim 11, wherein the received image data includes the driver's facial features.

18. The system of claim 11, wherein the computing system is further configured to train the artificial neural network or decision tree using supervised learning.

19. The system of claim 11, wherein the input for the artificial neural network or decision tree is further based on data about the drivers of other vehicles.

20. A method comprising: Image data derived from at least one image of a driver in a vehicle is received by at least one memory device and via a bus from at least one camera, wherein the at least one camera records the at least one image in response to a request from a user of a mobile device outside the vehicle; The risk score of the driver is determined by at least one processing device and using an artificial neural network with input based on the image data, wherein the artificial neural network has been trained using previous images of the driver and corresponding risk scores. as well as Communication is transmitted to the mobile device relating to the driver based on a determined risk score.

Images