System for and method of calculating responsibility of driver of vehicle

Abstract

To provide a system for and a method of calculating responsibility of a vehicle driver based on operations of a vehicle by the driver.SOLUTION: According to the present invention, a method of calculating a drive score of a driver of a vehicle includes specifying a risky event carried out by the driver of the vehicle by using a combination of a vehicle sensor, a video input and an on-board artificial intelligence and / or machine learning algorithm, generating, calculating and evaluating the drive score of the driver of the vehicle, and transmitting a calculation result to one or a plurality of entities.SELECTED DRAWING: Figure 7

Description

[Technical field]

[0001] The technology described below generally relates to systems, apparatus and methods for generating and calculating accident risk and operating costs of a vehicle by evaluating the operation or performance of the vehicle by a driver. More specifically, a personal driving score is generated or calculated based on at least sensors, video inputs and artificial intelligence algorithms.

[0002] Priority claim This application claims priority to and the benefit of Provisional Patent Application No. 62 / 849,763, filed in the United States Patent and Trademark Office on May 17, 2019, the entire contents of which are incorporated herein by reference for all applicable purposes as if fully set forth below. [Background technology]

[0003] Currently, the insurance industry relies on complex processes with overlapping systems and paperwork that relies heavily on humans to process claims. The insurance claims process often includes the steps of (1) receiving the accident report, (2) contacting the customer and verifying the policy information, (3) creating a hand-drawn accident diagram and sending it to the claims department, (4) the claims department contacting the customer and reviewing the accident information, and (5) manually entering the information into the claims system.

[0004] After a claim is entered into the system, an adjuster must review the damaged vehicle that is the subject of the claim to verify the facts and determine a cost estimate. If an accident involving personal injury is reported, an interview with the injured party is conducted. The adjuster then manually reviews similar accidents to determine projected costs, determine the percentage of fault, and issue payments to each party.

[0005] The above process requires a lot of manual processing and review, which increases the insurance company's costs and delays in reaching a settlement. Furthermore, the accuracy and neutrality of the process depends on which adjuster is assigned to the claim. Therefore, there is a need for an automated system and method to streamline the claims process, increase turnaround time, and make the process neutral. Summary of the Invention

[0006] The following presents a summary of one or more aspects of the present disclosure in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated features of the present disclosure, and is not intended to identify key or critical elements of all aspects of the present disclosure or to delineate the scope of any or all aspects of the present disclosure. Its sole purpose is to present some concepts of one or more aspects of the present disclosure in a format as a prelude to the more detailed description that is presented later.

[0007] In one aspect, the disclosure provides one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause one or more processors to perform operations comprising: receiving performance data from multiple sources related to a performance of a driver of a vehicle, identifying at least one hazardous event affecting the driver's performance, the at least one hazardous event adversely affecting the performance data below a pre-defined threshold, analyzing the performance data using a trained machine learning model to determine a severity level of each identified hazardous event affecting the driver's performance, the trained machine learning model employing multiple types of machine learning algorithms to analyze the performance data, generating at least one score based on the performance data for presentation via a user interface, and improving the machine learning model based on the generated at least one score, the improving including retraining the machine learning model based on at least one of the training corpora that has been modified based on the performance data.

[0008] The operations may further include notifying at least one user via a user interface of the at least one score, initiating recording of video data using a camera mounted on the vehicle, and analyzing the recorded video data with vehicle threshold events to identify at least one dangerous event.

[0009] The operations may further include using an object detection algorithm to identify from the recorded footage objects external to the vehicle that affect the performance data, and transmitting latitude and longitude coordinates of the identified objects to the diagnostic module processor for further processing to determine an influence of the objects on the at least one hazardous event.

[0010] The operations may further include initiating storage of vehicle data from the diagnostic module, the engine control unit module, and the autonomous driving module, and analyzing the stored vehicle data for vehicle threshold events to identify at least one unsafe event.

[0011] The operations may further include determining that an accident has occurred from the performance data, and transmitting information related to the accident to a third party.

[0012] The operations may further include updating at least one score after a severity level is assigned to the at least one hazardous event, storing the updated score in an on-board memory device in the vehicle, and transmitting the updated score to a remote data database.

[0013] According to another aspect, a computer-implemented method for assessing driver risk is provided, the method comprising: receiving, at a processor of a vehicle module onboard a vehicle, performance data relating to a performance of a driver of the vehicle from a plurality of sources onboard the vehicle; identifying, at the processor of the vehicle module, at least one hazardous event affecting the driver's performance, the at least one hazardous event adversely affecting the performance data below a pre-defined threshold; analyzing the performance data using a trained machine learning model in the processor of the vehicle module to determine a severity level of each identified hazardous event affecting the driver's performance, the trained machine learning model employing a plurality of types of machine learning algorithms to analyze the performance data; generating, at the processor of the vehicle module, at least one score based on the performance data for presentation via a user interface; and improving, at the processor of the vehicle module, the machine learning model based on the generated at least one score, the improving including retraining the machine learning model based on at least one of the training corpora that has been modified based on the performance data.

[0014] According to yet another aspect, a computing device is provided for onboard a vehicle, the device including an interface and a processing circuit coupled to the interface, the processing circuit configured to perform the steps of receiving performance data related to a performance of a driver of the vehicle from a plurality of sources, identifying at least one hazardous event affecting the driver's performance, the at least one hazardous event adversely affecting the performance data below a pre-defined threshold, analyzing the performance data using a trained machine learning model to determine a severity level of each identified hazardous event affecting the driver's performance, the trained machine learning model employing a plurality of types of machine learning algorithms to analyze the performance data, generating at least one score based on the performance data for presentation to a user, and improving the machine learning model based on the generated at least one score, the improving including retraining the machine learning model based on at least one of the training corpora modified based on the performance data. [Brief description of the drawings]

[0015] Various features, nature and advantages will become apparent from the following detailed description taken in conjunction with the drawings in which like reference characters identify correspondingly throughout. [Figure 1] FIG. 1 is a conceptual diagram illustrating the operating environment in which embodiments of the disclosed systems and methods may be found. [Diagram 2] FIG. 2 is a block diagram illustrating example hardware aspects of a vehicle module according to some aspects of the disclosure. [Diagram 3] FIG. 3 is a block diagram illustrating an example hardware implementation of a user interface module and a data platform module in accordance with some aspects of the disclosure. [Figure 4]FIG. 4 is a block diagram illustrating example hardware aspects of an apparatus (eg, an electronic device) that can support communications in accordance with certain aspects of the disclosure. [Diagram 5] FIG. 5 is a block diagram of an example hardware embodiment of a data platform module / apparatus configured to communicate in accordance with one or more aspects of the disclosure. [Figure 6] FIG. 6 illustrates a block diagram of an exemplary hardware embodiment of a user interface module / device configured to communicate in accordance with one or more aspects of the present disclosure. [Figure 7] FIG. 7 is a flow diagram illustrating an example method for calculating a driver score for a driver of a vehicle. [Figure 8] FIG. 8 is a flow chart illustrating an exemplary method for determining driver and vehicle safety. [Figure 9] Figure 9 summarizes the overall process of the insurance system related to insurance. [Figure 10] FIG. 10 illustrates the process of detecting an event. [Figure 11] FIG. 11 illustrates a process for using data from multiple device sensors to improve the accuracy of vehicle and object position and motion estimation upon event detection. [Figure 12] FIG. 12 illustrates how accident reports can be used to assign fault to participating entities. [Figure 13] FIG. 13 illustrates a process for reducing the amount of manual work required to bill and pay on behalf of a party. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] overview Exemplary systems, apparatus and methods are described herein that generate or calculate vehicle liability and operating costs based on the vehicle's driver's operations and performance. Using a combination of vehicle sensors, video inputs and on-board artificial intelligence and / or machine learning algorithms, the disclosed systems and methods can identify risky events performed by the vehicle's driver, generate, calculate and evaluate the vehicle's driver's driving score and trip score, and transmit the calculation results to one or more entities. The First Notice of Loss (FNOL) process, which is the initial report to an insurance company after loss, theft or damage to an insured property, is also automated for higher accuracy, response time, and lower operating costs.

[0017] The term "sensor" may refer to any type of known sensor for sensing a dynamic condition of a vehicle. The sensor may be an original equipment or an aftermarket tool. The sensors may include, but are not limited to, mass airflow sensors, engine speed sensors, oxygen sensors, spark knock sensors, coolant sensors, manifold absolute pressure (MAF) sensors, fuel temperature sensors, voltage sensors, camshaft position sensors, throttle position sensors, vehicle speed sensors or speedometers, proximity sensors, accelerometers, global positioning systems, odometers, steering angle sensors, safety system data, radio detection and ranging (RADAR), light detection and ranging (LIDAR), and diagnostic trouble codes.

[0018] The terms "sensor data" and "vehicle sensor data" refer to data received from any sensor in the vehicle, whether it is original equipment or an aftermarket tool.

[0019] The term "vehicle" refers to any type of machine that transports people or cargo, including, but not limited to, cars, trucks, buses, motorcycles, airplanes and helicopters.

[0020] The term "hazardous event" refers to any occurrence or incident that occurs while driving that adversely affects a driver's performance, including, but not limited to, braking at a particular speed, accelerating at a particular speed, time to pull over before crashing, cornering at a particular speed, time of trip, distance of trip, failure to stop at a stop sign, rolling stop, full stop, speeding distance, cost of trip, time of trip start, time of trip stop, trip status and trip score.

[0021] Some of the methods described herein may be implemented in hardware, such as a server, a user interface or device, a vehicle module, and a data module, each of which may determine whether a hazardous event has occurred, generate a driver score, and transmit accident data to emergency response vehicles via cellular and / or other network communications.

[0022] The term "computer-readable medium" as used herein refers to any tangible storage device that participates in providing instructions to a processor for execution. Such media can take many forms, including, but not limited to, non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, NVRAM, or magnetic or optical disks. Volatile media include dynamic memory, such as main memory. Common forms of computer-readable media include, for example, floppy disks, flexible disks, hard disks, magnetic tapes, other magnetic media, magneto-optical media, CD-ROMs, other optical media, punch cards, paper tapes, other physical media with patterns of holes, RAM, PROMs, EPROMs, FLASH-EPROMs, solid-state media such as memory cards, other memory chips or cartridges, or other media that can be read by a computer. When the computer-readable medium is configured as a database, it is understood that it may be any type of database, such as relational, hierarchical, and / or object-oriented. For this reason, the present disclosure is deemed to include tangible storage media and equivalents and successor media recognized in the prior art, on which the software implementation of the present disclosure is stored.

[0023] As used herein, the terms "central processing unit," "processor," "processor circuitry," and "processing circuitry," as well as variations thereof, are used interchangeably and include, but are not limited to, a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic component, discrete gate or transistor logic, discrete hardware components, or any combination thereof, designed to perform the functions described herein. A general purpose processor may include any conventional processor, controller, microcontroller, or state machine, in addition to a microprocessor. A processor may also be implemented as a combination of computing components, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in combination with a DSP core, an ASIC and a microprocessor, or any number of other various configurations. These examples of processors are illustrative, and other suitable configurations are contemplated within the scope of the present disclosure. Additionally, a processor may be implemented as one or more processors, one or more controllers, and / or other structures configured to execute executable programming.

[0024] As used herein, the terms "determine," "calculate," and "operate," as well as variations thereof, are used interchangeably and include any type of methodology, process, mathematical operation, or technique.

[0025] The term "module" as used herein refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and software that is capable of performing the functions associated with that element.

[0026] The terms "user interface" and "user interface module" may be embodied or implemented in a server, personal computer, cell phone, smart phone, tablet, portable computer, machine, entertainment device, or other electronic device having circuitry. The system described herein can identify and draw bounding boxes around various objects, including, but not limited to, people, bicycles, cars, motorcycles, buses, trains, trucks, boats, traffic lights, fire hydrants, stop signs, and dogs.

[0027] The term "driver" can refer to a person or to a vehicle with automated driving features operating.

[0028] The detailed description set forth below in conjunction with the accompanying drawings is intended to describe various configurations and is not intended to represent the only configurations in which the concepts described herein may be implemented. The detailed description includes specific details to provide a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that the concepts may be implemented without the specific details. At times, well-known structures and components are shown in block diagram form in order not to obscure such concepts. In this specification, a reference to an element in the singular is intended to refer to the element in the plural.

[0029] 1 illustrates an exemplary architecture 100 for generating or calculating vehicle liability and operating costs based on the operation or performance of a driver's vehicle in which embodiments of the disclosed systems and methods may be found. The system includes a communication network 102 connecting a vehicle module 104, a user interface module 106, a data platform 108, and a remote file system or server 142. A third party application protocol interface 109 can access what is generated on the vehicle module 104 and the data platform 108. The vehicle module 104, the user interface 106, the data platform 108, the remote file system or server 142, and the third party application protocol interface 109 are described in more detail below.

[0030] The system 100 calculates one or more risk scores for a driver's operation of the vehicle using data obtained from the vehicle. The data is obtained from a combination of vehicle sensors, video inputs, and on-board artificial intelligence / machine learning.

[0031] In some embodiments, the system 100 can interact with a local data storage device 112 and / or a remote server 142, or any combination of local and remote data storage devices and file systems.

[0032] The local file system (and / or the remote file system) may control how data in the local data storage device 112 and / or the remote data storage device 142 is stored and retrieved. In some embodiments, the structure and logical rules used to manage the information stored as data in the local data storage device 112 and / or the remote data storage device 142 may be referred to as a "file system" (e.g., the local file system and / or the remote file system). The local file system and / or the remote file system may each have different structure and logic, speed, flexibility, security, size, and other characteristics. In some embodiments, the structure and logic of the local file system and / or the remote file system provide improved speed and security over other known file systems. The local data storage device and / or the remote data storage device may use the same or different media on which data is stored. Examples of media include magnetic disks, magnetic tapes, optical disks, and electronic memory (such as flash memory).

[0033] Communications between any or all of the apparatus, devices, systems, functions, modules, and services and servers described herein may occur over one or more wired and / or wireless communication networks 134. Examples of the one or more communication networks 134 include a public switched telephone network (PSTN), a wide area network (WAN), a local area network (LAN), a TCP / IP data network such as the Internet, and a wireless network such as the 3G, 4G, LTE, and 5G networks promulgated by the 3rd Generation Partnership Project (3GPP). The one or more communication networks 134 may be any one or combination of two or more communication networks such as, but not limited to, those communication networks.

[0034] 2 is a block diagram illustrating exemplary hardware aspects of an on-board vehicle module according to some aspects of the disclosure. The vehicle module 104 monitors the driver's actions in the vehicle. According to at least some embodiments, the vehicle module 104 may include a processor 110, a local data storage 112, one or more sensors 114, a diagnostic module 116, an engine control unit (ECU) 118, a communication interface 120, and an autonomous driving module 121 having an autonomous driving switch 123 for tracking when the autonomous driving function of the vehicle is activated, if available, when it is activated, whether the driver or the vehicle has activated the autonomous driving function, and when the autonomous driving function is deactivated. The information on whether the autonomous driving function is activated can be used to determine whether a dangerous event is caused by the driver or the vehicle.

[0035] The vehicle module 104 collects driver data using various sensors 114 (e.g., speed sensors, accelerometers, GPS locators, tire pressure sensors, autonomous driving sensors, and audio / visual sensors such as backup cameras, anti-theft devices) provided in the vehicle, which are typically connected to the ECU via, for example, a Controller Area Network (CAN) bus. From the collected vehicle sensor data and / or video metadata, the processor 110 uses an artificial intelligence and / or machine learning module 124 to compute the collected data into a score based on insurance machine learning algorithms and extensive previously collected data collection and analysis, and calculates a driving score that includes risk and safety for a particular trip.

[0036] According to one aspect, the system can determine which vehicle sensors are available and disable modules and sensors as necessary. When the system disables modules and sensors, it takes into account the amount of data available and adjusts the risk calculation accordingly. For each vehicle's trip summary, the system can output a trip score and an overall trip severity. Over time, the system can build a risk profile for the driver based on the average trip score. This score can be used to estimate the cost and risk of the vehicle itself, as well as to evaluate the vehicle's driver.

[0037] The vehicle module 104 is also provided with a user interface 106 , a data platform 108 and a server 142 connected to the communication network 102 , and a network communication interface 120 that enables communication via a wireless communication link to the communication network 102 .

[0038] The machine learning module 124 is comprised of at least one insurance machine learning algorithm to analyze data from the sensors 114, the diagnostics module 116, the engine control unit 118, and the autonomous driving module 121 to generate a driver score and trip information. In various embodiments, the machine learning module 124 uses a machine learning training pipeline to generate the machine learning model.

[0039] The diagnostic module 116 can store and retrieve data related to the vehicle's self-diagnosis and reporting functions in on-board memory or local data storage 112. The diagnostic module 116 can analyze the received data, diagnose potential problems, and prepare the data for presentation to a user, driver, insurance company, or other entity. The diagnostic module 116 can communicate with the user interface module 106 and the data platform module 108 via the communication interface 120. The diagnostic module 106 can receive commands / instructions via the communication interface 120 or the processor 110, obtain and / or generate appropriate information, and provide it to the data platform module 108 for presentation to a user, driver, insurance company, or other entity.

[0040] By reading values ​​from sensors in the engine compartment, the ECU 118 controls a series of actuators of the internal combustion engine to ensure optimal engine performance. It interprets the data using multi-dimensional performance maps (called look-up tables) and adjusts the engine actuators. The ECU 118 can, for example, monitor and set the air-fuel mixture, ignition timing, idle speed, etc. Data from the ECU 118 is provided to a machine learning module 124, which uses it along with machine learning algorithms and previously collected data to calculate a driver risk score based on the driver's driving behavior.

[0041] 3 is a block diagram illustrating an example hardware embodiment of the user interface module 106 and the data platform module 108 according to some embodiments of the disclosure. The user interface module 106 allows third parties to obtain vehicle and driver data information as a result of accident / anomaly analysis, fault allocation, subrogation, and claim payment. This information can be transmitted to drivers and insurance companies via various user interfaces based on API connections configured to accept output from insurance systems.

[0042] The user interface module 106 may include a processor 132, a vehicle head-up display (HUD) module 134, a dashboard module 136, a communication interface 138, and a memory or data storage module 140. The user interface module allows a user to load and process sensor data that is provided directly to the machine learning module 124 (see FIG. 2).

[0043] The user interface module 106 allows external or third parties to receive the event and abnormal behavior data. The user interface module 106 can use its communication interface to establish a connection to an API on the user interface module 106 to retrieve data stored in local memory or remote data storage 142. The vehicle HUD module 136 and dashboard module 136 on the user interface module 106 allow the user to view the data.

[0044] The user interface module 106 is connected to the communication network 104 and thus may also be considered a network computing device. The user interface 106 may include a network or communication interface 138 or multiple network interfaces that enable the user interface module 106 to communicate over various types of communication networks. For example, the user interface module 106 may include a network interface card, an antenna, an antenna driver, an Ethernet port, and the like. Other examples of the user interface module 106 include, but are not limited to, a laptop, a tablet, a mobile phone, a personal digital assistant (PDA), a thin client, a supercomputer, a server, a proxy server, a communication switch, a set-top box (STB), a smart TV, and the like. The processor 110 uses the artificial intelligence and / or machine learning module 124 to calculate the collected data based on the insurance machine learning algorithms and extensive data collection and analysis previously collected to calculate a driving score including risk and safety for a particular trip. That is, the machine learning module 124 uses on-board machine learning methods to locally (on the vehicle module) calculate scores (such as driver score, trip score and risk score) based on the captured vehicle sensor and video data evaluated against a broader dataset previously collected. Once the scores and trip summaries are completed, the vehicle module 102 establishes a connection with a networked server to transmit the data, thereby enabling the user to evaluate the driver's performance against the established dataset.

[0045] Turning to the data platform module 108, it has high computational and memory capabilities compared to the on-board processing system of the vehicle module 104. This data platform 108 is used to further process the data sent to it, and can improve the accuracy of the estimation results using algorithms that are difficult to run on the vehicle due to performance, cost or physical size constraints. Furthermore, the data platform module 108 houses processes that enable communication with third parties to a) request data from other vehicles or devices, b) collect data from other vehicles or devices, and / or c) communicate with other vehicles or devices. Furthermore, this data platform 108 includes a processor 126, a graphic processing unit (GPU) 128, and a communication interface 130 that enables communication with third parties to a) request data from other vehicles or devices, b) collect data from other vehicles or devices, and / or c) communicate with other vehicles or devices.

[0046] According to one example, the system may retain up to 60 seconds of video data at a time using the GPU. When the system detects a hazardous event, the GPU may store 10 seconds of video footage before and after the hazardous event in the vehicle module's on-board storage. The data is retained to allow the system to reconstruct video clips and telemetry data around the event as it occurs and is observed. The system may update the remote data storage or server with the trip data at regular intervals. Regular intervals include, but are not limited to, at the start of a trip, at the end of a trip, and every 10 seconds of the trip.

[0047] Information resulting from a) accident / anomaly analysis, b) fault allocation, c) subrogation, and / or d) claim payment can be transmitted to drivers and insurance companies via various user interfaces based on API connections configured to accept output from insurance systems.

[0048] GPU input can come from vehicle cameras, such as dashboard cameras or driver assistance cameras. When a dashboard camera is started, the system verifies that the module is operational by taking a camera shot. If the system fails to take a camera shot, it can retry, for example every 0.01 seconds. If the system detects that the camera is not operational or that the footage has finished, the system sends a kill command to a sub-process that analyzes and processes the footage. The footage can be processed locally on the vehicle or on a separate device.

[0049] The user interface 106 is connected to the communication network 104 and thus may also be considered a network computing device. The user interface 106 may include a network or communication interface 138 or multiple network interfaces that enable the user interface 106 to communicate over various types of communication networks. For example, the user interface 106 may include a network interface card, an antenna, an antenna driver, an Ethernet port, etc. Other examples of the user interface 106 include, but are not limited to, a laptop, a tablet, a mobile phone, a personal digital assistant (PDA), a thin client, a supercomputer, a server, a proxy server, a communication switch, a set-top box (STB), a smart TV, etc.

[0050] Dangerous events are detected by monitoring data observed by the vehicle's sensors or CAN bus. If the system observes sensory data approaching pre-set threshold levels or risk patterns matching machine learning simulated models, it records a dangerous or abnormal situation. Once a dangerous or abnormal situation is recorded, the system's sensor module filters the event data and available video recordings and passes them on to a module that handles the scoring model.

[0051] FIG. 4 illustrates a block diagram of an exemplary hardware embodiment of a vehicle module / apparatus 400 configured to communicate according to one or more aspects of the disclosure. The vehicle module 400 may include, for example, a communication interface 402. The communication interface 402 may enable input and output of data and control. The communication interface 402 may enable communication over one or more communication networks, for example, similar to the one or more communication networks 102 of FIG. 1. The communication interface 402 may be communicatively coupled to the one or more communication networks 102, directly or indirectly. The vehicle module 400 may include a local working memory device 404 and a processor system / function / module / device (hereinafter, processor 406). The processor 406 may use the working memory device 404 to store data to be operated on, data being operated on, or data that has recently been operated on. The processor 406 may store instructions on the working memory device 404 and / or on one or more other memory structures or devices, such as, for example, a non-transitory computer-readable medium system / function / module / device (hereinafter non-transitory computer-readable medium 408). The instructions, when executed by the processor 406, may, for example, cause the processor 406 to perform one or more aspects of the methods described herein.

[0052] The vehicle module 400 may be implemented with a bus architecture, generally represented by a bus 410. The bus 410 may include any number of interconnected buses and bridges, depending on the specific application and overall design constraints of the vehicle module 400. The bus 410 may communicatively couple various circuits, including one or more processors (generally represented by processor 406), a working memory device 404, a communication interface 402, and a non-transitory computer-readable medium 408. The bus 410 may also couple various other circuits and devices, such as timing sources, peripherals, voltage regulators, and power management circuits and devices, which are well known in the art and will not be described further.

[0053] The communication interface 402 provides a means for communicating with other devices over a transmission medium. In some aspects, the communication interface 402 includes circuitry and / or programming adapted to facilitate bidirectional communication of information with respect to one or more communication devices in a network. In some aspects, the communication interface 402 is adapted to facilitate wireless communication of the vehicle module 400. In these aspects, the communication interface 402 can be coupled to one or more antennas 412, as shown in FIG. 4, for wireless communication in a wireless communication system. In some aspects, the communication interface 402 can be configured for wire-based communication. For example, the communication interface 402 can be a bus interface, a transmit / receive interface, or other type of signal interface including drivers, buffers, or other circuits for outputting and / or obtaining signals (e.g., outputting signals from an integrated circuit and / or receiving signals into an integrated circuit). The communication interface 402 can be configured with one or more stand-alone receivers and / or transmitters, as well as one or more transceivers. In the illustrated example, the communication interface 402 includes a transmitter 414 and a receiver 416. The communication interface 402 serves as an example of a receiving means and / or a transmitting means.

[0054] The processor 406 may be responsible for managing the bus 410 and for overall processing, including the execution of software stored on the non-transitory computer-readable medium 408. The software, when executed by the processor 406, may cause the processor 406 to perform various functions, as described below for any particular device or module. The non-transitory computer-readable medium 408 and the working memory device 404 may also be used to store data that is manipulated by the processor 406 when executing the software.

[0055] One or more processors, such as processor 406 of vehicle module 400, may execute software. Software may be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. The software may reside in a non-transitory computer readable medium, such as non-transitory computer readable medium 408. The non-transitory computer readable medium 408 may include, for example, a magnetic storage device (e.g., a hard disk, a floppy disk, a magnetic tape, a magnetic strip), an optical disk (e.g., a compact disk (CD) or a digital versatile disk (DVD)), a smart card, a flash memory device (e.g., a card, stick or key drive), a random access memory (RAM), a read only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a register, a removable disk, and other suitable non-transitory medium for storing software, dates and / or instructions that can be accessed and read by the computer or processor 406. The computer readable medium may also include, for example, a carrier wave, a transmission line, and any other suitable medium for transmitting software and / or instructions that can be accessed and read by the computer or processor 406. The non-transitory computer-readable medium 408 may reside on the vehicle module 400 (e.g., the local data storage device 112 of FIG. 1 ), outside the vehicle module 400 (e.g., the remote data storage device 142 ), or distributed across multiple entities including the vehicle module 400 .

[0056] The processor 406 is configured to acquire, process, and / or transmit data, control data access and storage, issue commands, and control other desired operations. The processor 406, in at least one example, can include circuitry configured to implement desired programming provided by a suitable medium.

[0057] The non-transitory computer-readable medium 408 may be embodied by a computer program product. As an example, the computer program product may include the computer-readable medium in packaging materials. Those skilled in the art will recognize how best to implement the described functionality presented throughout this disclosure depending on the particular application and the overall design constraints imposed on the overall system.

[0058] In some aspects of the disclosure, the processor 406 may include circuits configured for various functions. For example, the processor 406 may include circuits / modules 420 for operation, configured to manage the operation of sensors and displays, perform input / output operations related to accessing the Internet web, and perform methods, for example, as described herein. For example, the processor 406 may include a data storage 422 system / function / module / device configured to store data, including, but not limited to, sensory data, event data, threshold levels, video data, driver data, score data, and previously collected data sets. For example, the processor 406 may include a file system / function / module / device 424 configured to control how data in local data storage and / or remote data storage is stored and retrieved. For example, the processor 406 may include a sensor system / function / module / device 426 configured to control sensor inputs and video inputs. For example, the processor 406 may include a diagnostic system / function / module / device 426 configured to, for example, handle email accounts, process email messages, consolidate emails for transmission, obtain and store vehicle self-reported data, recorded video, and perform methods described herein. For example, the processor 406 may include an engine control unit system / function / module / device 430 configured to control one or more electrical systems of a subsystem within the vehicle to an external server, and perform methods described herein. For example, the processor 406 may include an artificial intelligence system / function / module / device 432 configured to build a model of past usage. For example, the processor 406 may include an automated driving system / function / module / device 432 configured to determine whether the automated driving system of the automobile was engaged at the time of the hazardous event and whether the driver engaged the automated driving system or the vehicle engaged the automated driving function.

[0059] In some aspects of the disclosure, the non-transitory computer readable medium 408 of the vehicle module 400 may include instructions that can cause various systems / functions / modules / devices of the processor 406 to perform the methods described herein. For example, the non-transitory computer readable medium 408 may include operational instructions or code 420 to a circuit / module 420 for operation. For example, the non-transitory computer readable medium 408 may include data storage instructions 436 corresponding to a data storage system / function / module / device 422. For example, the non-transitory computer readable medium 408 may include file system instructions 438 corresponding to a file system / function / module / device 424. For example, the non-transitory computer readable medium 408 may include sensor instructions 440 corresponding to a sensor system / function / module / device 426. For example, the non-transitory computer readable medium 408 may include diagnostic instructions 442 corresponding to an engine control unit system / function / module / device 430. For example, the non-transitory computer readable medium 408 may include engine control unit instructions 444 corresponding to an engine control unit system / function / module / device 430. For example, the non-transitory computer readable medium 408 may include artificial intelligence instructions 446 corresponding to the artificial intelligence system / function / module / device 432. For example, the non-transitory computer readable medium 408 may include autonomous driving instructions 446 corresponding to the autonomous driving system / function / module / device 433.

[0060] FIG. 5 illustrates a block diagram of an exemplary hardware embodiment of a data platform module / apparatus 500 configured to communicate according to one or more aspects of the disclosure. The data platform module 500 may include, for example, a communication interface 502. The communication interface 502 may enable input and output of data and control. The communication interface 502 may enable communication over one or more communication networks, for example, similar to the one or more communication networks 102 of FIG. 1. The communication interface 502 may be communicatively coupled to the one or more communication networks 102, directly or indirectly. The data platform module 500 may include a working memory device 504 and a processor system / function / module / device (hereinafter processor 506). The processor 506 may use the working memory device 504 to store data to be manipulated, data being manipulated, or data that has recently been manipulated. The processor 506 may store instructions on the working memory device 504 and / or on one or more other memory structures or devices, such as, for example, a non-transitory computer-readable medium system / function / module / device (hereinafter non-transitory computer-readable medium 508). The instructions, when executed by the processor 506, may, for example, cause the processor 506 to perform one or more aspects of the methods described herein.

[0061] The data platform module 500 may be implemented with a bus architecture, generally represented by a bus 510. The bus 510 may include any number of interconnected buses and bridges, depending on the specific application and overall design constraints of the data platform module 500. The bus 510 may communicatively couple various circuits, including one or more processors (generally represented by processor 506), a working memory device 504, a communication interface 502, and a non-transitory computer-readable medium 508. The bus 510 may also couple various other circuits and devices, such as timing sources, peripherals, voltage regulators, and power management circuits and devices, which are well known in the art and will not be described further.

[0062] The communication interface 502 provides a means for communicating with other devices over a transmission medium. In some aspects, the communication interface 502 includes circuitry and / or programming adapted to facilitate bidirectional communication of information with respect to one or more communication devices in a network. In some aspects, the communication interface 502 is adapted to facilitate wireless communication of the data platform module 500. In these aspects, the communication interface 502 can be coupled to one or more antennas 512, as shown in FIG. 5, for wireless communication in a wireless communication system. In some aspects, the communication interface 502 can be configured for wire-based communication. For example, the communication interface 502 can be a bus interface, a transmit / receive interface, or other type of signal interface including drivers, buffers, or other circuits for outputting and / or obtaining signals (e.g., outputting signals from an integrated circuit and / or receiving signals into an integrated circuit). The communication interface 502 can be configured with one or more stand-alone receivers and / or transmitters, as well as one or more transceivers. In the illustrated example, the communication interface 502 includes a transmitter 514 and a receiver 516. The communication interface 502 serves as an example of a receiving means and / or a transmitting means.

[0063] The processor 506 may be responsible for managing the bus 510 and for overall processing, including the execution of software stored on the non-transitory computer-readable medium 508. The software, when executed by the processor 506, may cause the processor 506 to perform various functions, as described below for any particular device or module. The non-transitory computer-readable medium 508 and the working memory device 504 may also be used to store data that is manipulated by the processor 506 when executing the software.

[0064] One or more processors, such as processor 506 of vehicle module 500, may execute software. Software may be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. The software may reside in a non-transitory computer readable medium, such as non-transitory computer readable medium 508. The non-transitory computer readable medium 508 may include, for example, a magnetic storage device (e.g., a hard disk, a floppy disk, a magnetic tape, a magnetic strip), an optical disk (e.g., a compact disk (CD) or a digital versatile disk (DVD)), a smart card, a flash memory device (e.g., a card, stick or key drive), a random access memory (RAM), a read only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a register, a removable disk, and other suitable non-transitory medium for storing software, dates and / or instructions that can be accessed and read by the computer or processor 506. The computer readable medium may also include, for example, a carrier wave, a transmission line, and any other suitable medium for transmitting software and / or instructions that can be accessed and read by the computer or processor 506. The non-transitory computer-readable medium 508 may reside within the data platform module 500 (e.g., the local data storage device 112 of FIG. 1 ), may reside outside the data platform module 500 (e.g., the remote data storage device 142), or may be distributed across multiple entities, including the data platform module 500.

[0065] The processor 506 is configured to acquire, process, and / or transmit data, control data access and storage, issue commands, and control other desired operations. The processor 506, in at least one example, can include circuitry configured to implement desired programming provided by a suitable medium.

[0066] The non-transitory computer-readable medium 508 may be embodied by a computer program product. As an example, the computer program product may include the computer-readable medium in packaging materials. Those skilled in the art will recognize how best to implement the described functionality presented throughout this disclosure depending on the particular application and the overall design constraints imposed on the overall system.

[0067] In some aspects of the disclosure, the processor 506 may include circuits configured for various functions. For example, the processor 506 may include circuits / modules 520 for operation, configured to manage the operation of data received from the vehicle module 104 (FIG. 1) and the user interface module 106 (FIG. 1), perform input / output operations related to accessing the Internet web, and perform methods, for example, as described herein. For example, the processor 506 may include a data storage 522 system / function / module / device configured to store data, including, but not limited to, sensory data, event data, threshold levels, video data, driver data, score data, and previously collected data sets. For example, the processor 506 may include a file system / function / module / device 524 configured to control how data in the local data storage and / or remote data storage is stored and retrieved. For example, the processor 506 may include a graphics processor system / function / module / device 526 configured to control video input and output at a camera mounted on the vehicle.

[0068] In some aspects of the disclosure, the non-transitory computer readable medium 508 of the data platform module 500 may include instructions that can cause various systems / functions / modules / devices of the processor 506 to perform methods described herein. For example, the non-transitory computer readable medium 508 may include operational instructions or code 528 for circuitry / modules 520 for operation. For example, the non-transitory computer readable medium 508 may include data storage instructions 530 corresponding to the data storage system / function / module / device 522. For example, the non-transitory computer readable medium 508 may include file system instructions 532 corresponding to the file system / function / module / device 524. For example, the non-transitory computer readable medium 508 may include graphics processor instructions 534 corresponding to the graphics processor system / function / module / device 526.

[0069] FIG. 6 illustrates a block diagram of an exemplary hardware embodiment of a user interface module / apparatus 600 configured to communicate according to one or more aspects of the disclosure. The user interface module 600 may include, for example, a communication interface 402. The communication interface 602 may enable input and output of data and control. The communication interface 602 may enable communication over one or more communication networks, for example, similar to the one or more communication networks 102 of FIG. 1. The communication interface 602 may be communicatively coupled to the one or more communication networks 102, directly or indirectly. The user interface module 600 may include a working memory device 604 and a processor system / function / module / device (hereinafter, processor 606). The processor 606 may use the working memory device 604 to store data to be manipulated, data being manipulated, or data that has recently been manipulated. The processor 606 may store instructions on the working memory device 604 and / or on one or more other memory structures or devices, such as, for example, a non-transitory computer-readable medium system / function / module / device (hereinafter non-transitory computer-readable medium 608). The instructions, when executed by the processor 606, may, for example, cause the processor 606 to perform one or more aspects of the methods described herein.

[0070] The user interface module 600 may be implemented in a bus architecture, generally represented by a bus 610. The bus 610 may include any number of interconnected buses and bridges, depending on the specific application of the user interface module 600 and the overall design constraints. The bus 610 may communicatively couple various circuits, including one or more processors (generally represented by a processor 606), a working memory device 604, a communication interface 602, and a non-transitory computer-readable medium 608. The bus 610 may also couple various other circuits and devices, such as timing sources, peripherals, voltage regulators, and power management circuits and devices, which are well known in the art and will not be described further.

[0071] The communication interface 602 provides a means for communicating with other devices over a transmission medium. In some aspects, the communication interface 602 includes circuitry and / or programming adapted to facilitate bidirectional communication of information with respect to one or more communication devices in a network. In some aspects, the communication interface 602 is adapted to facilitate wireless communication of the user interface module 600. In these aspects, the communication interface 602 can be coupled to one or more antennas 612, as shown in FIG. 6, for wireless communication in a wireless communication system. In some aspects, the communication interface 602 can be configured for wire-based communication. For example, the communication interface 602 can be a bus interface, a transmit / receive interface, or other type of signal interface including drivers, buffers, or other circuits for outputting and / or obtaining signals (e.g., outputting signals from an integrated circuit and / or receiving signals to an integrated circuit). The communication interface 602 can be configured with one or more stand-alone receivers and / or transmitters, as well as one or more transceivers. In the illustrated example, the communication interface 602 includes a transmitter 614 and a receiver 616. The communication interface 602 serves as an example of a receiving means and / or a transmitting means.

[0072] The processor 606 may be responsible for managing the bus 610 and for overall processing, including the execution of software stored on the non-transitory computer-readable medium 608. The software, when executed by the processor 606, may cause the processor 606 to perform various functions, as described below for any particular device or module. The non-transitory computer-readable medium 608 and the working memory device 404 may also be used to store data that is manipulated by the processor 606 when executing the software.

[0073] One or more processors, such as processor 606 of user interface module 600, may execute software. Software may be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. The software may reside in a non-transitory computer readable medium, such as non-transitory computer readable medium 608. The non-transitory computer readable medium 608 may include, for example, a magnetic storage device (e.g., a hard disk, a floppy disk, a magnetic tape, a magnetic strip), an optical disk (e.g., a compact disk (CD) or a digital versatile disk (DVD)), a smart card, a flash memory device (e.g., a card, stick or key drive), a random access memory (RAM), a read only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a register, a removable disk, and other suitable non-transitory medium for storing software, dates and / or instructions that can be accessed and read by the computer or processor 606. The computer readable medium may also include, for example, a carrier wave, a transmission line, and any other suitable medium for transmitting software and / or instructions that can be accessed and read by the computer or processor 606. The non-transitory computer-readable medium 608 may reside within the user interface module 600 (e.g., the local data storage device 112 of FIG. 1), may reside outside the user interface module 600 (e.g., the remote data storage device 142), or may be distributed across multiple entities including the user interface module 600.

[0074] The processor 606 is configured to acquire, process, and / or transmit data, control data access and storage, issue commands, and control other desired operations. The processor 606, in at least one example, can include circuitry configured to implement desired programming provided by a suitable medium.

[0075] The non-transitory computer-readable medium 608 may be embodied by a computer program product. As an example, the computer program product may include the computer-readable medium in packaging materials. Those skilled in the art will recognize how best to implement the described functionality presented throughout this disclosure depending on the particular application and the overall design constraints imposed on the overall system.

[0076] In some aspects of the disclosure, the processor 606 may include circuits configured for various functions. For example, the processor 606 may include circuits / modules 620 for operations, configured to manage operations of data received from the vehicle module 104 (FIG. 1) and the data platform module 108 (FIG. 1), perform input / output operations related to accessing the Internet web, and perform methods, for example, as described herein. For example, the processor 606 may include a data storage 622 system / function / module / device configured to store data, including, but not limited to, sensory data, event data, threshold levels, video data, driver data, score data, and previously collected data sets. For example, the processor 606 may include a file system / function / module / device 624 configured to control how data in the local data storage and / or remote data storage is stored and retrieved. For example, the processor 606 may include a vehicle HUD system / function / module / device 626 configured to perform video input and output. For example, the processor 606 may include a vehicle HUD system / function / module / device 626 configured to control an automotive head-up display on a vehicle.

[0077] In some aspects of the disclosure, the non-transitory computer readable medium 608 of the user interface module 600 may include instructions that can cause various systems / functions / modules / devices of the processor 606 to perform the methods described herein. For example, the non-transitory computer readable medium 608 may include operational instructions or code 630 for a circuit / module 620 for operation. For example, the non-transitory computer readable medium 608 may include data storage instructions 632 corresponding to a data storage system / function / module / device 622. For example, the non-transitory computer readable medium 608 may include file system instructions 634 corresponding to a file system / function / module / device 624. For example, the non-transitory computer readable medium 608 may include vehicle HUD instructions 636 corresponding to a vehicle HUD system / function / module / device 626. For example, the non-transitory computer readable medium 608 may include dashboard instructions 638 corresponding to a vehicle HUD system / function / module / device 626.

[0078] 7 and 8 illustrate an exemplary process for collecting data from a combination of vehicle sensors, video inputs, and on-board artificial intelligence and / or machine learning modules, and generating, calculating, and evaluating driving scores and trip information from the data for a driver of a vehicle, if the driver is a human, or for a driver of a vehicle, if the driver is a vehicle that has engaged an automated driving function. The process may also transmit the calculation results to one or more entities, or allow one or more entities to retrieve the calculation results. Each process is illustrated as a collection of logic flow chart blocks, which represent a sequence of operations that may be performed in hardware, software, or a combination thereof. In the case of software, the blocks represent computer-executable instructions that, when executed by one or more processors, perform the described operations. In general, computer-executable instructions include routines, programs, objects, components, data structures, and the like, that perform particular functions or implement particular abstract data types. The order in which the operations are described is not intended to be construed as a limitation, and any number of the described blocks may be combined in any order and / or in a mirror arrangement to implement a process. For purposes of explanation, the processes herein are described with reference to the architecture 100 of FIGS. 1-3.

[0079] FIG. 7 is a flow diagram illustrating an example method 700 for calculating a driver score for a driver of a vehicle. As mentioned above, the driver may be a human or, if autonomous driving features are activated, the vehicle itself. Execution of the driver score calculation process 700 may begin when the vehicle's engine is started to begin a trip (702). As the vehicle progresses through the trip, a vehicle module on the vehicle collects or harvests data from sensors, diagnostic modules, engine control units, and / or autonomous driving modules (704). The vehicle module continuously monitors for unsafe events (706). If no unsafe events are detected (708), the vehicle module determines whether the trip is over (710).

[0080] If a dangerous event is detected (712), the vehicle module initiates recording of video and / or vehicle data for on-board and off-board analysis by vehicle threshold events to indicate an abnormal situation (714). According to one example, the vehicle module can use a 5-10 second window to determine the peak of the dangerous event. For example, if the driver brakes suddenly, the vehicle module can check the corresponding sensor data over a 10 second time frame to determine the time of maximum deceleration. If the vehicle module determines that a dangerous event has occurred, a severity level, for example 0-3 (or 0-4), is assigned and the trip summary is updated. The trip summary may be stored on the vehicle module on board the vehicle as well as transmitted to a remote database or server at the start and end of the trip and every 10 seconds. All severity levels of the dangerous events detected during the course of the trip can be used to calculate the trip severity, which can be used to evaluate the trip score. According to one example, the system may automatically assume a trip severity of 4 for each minute of the trip, where the trip score is a number between 0 and 100, taking into account the configured typical severity of the trip (or pre-set severity or threshold) and the actual severity per minute. Table 1 below shows severities associated with hazardous events, according to one example. Table 1 is intended to be an illustrative and non-limiting example, and may include other hazardous events and severity levels. TIFF2025013788000002.tif116170

[0081] When an event is detected, the system may use 60 seconds of video data to store 10 seconds of video before and 10 seconds after the event timestamp. The vehicle module then analyzes the recorded content and uses an object detection algorithm to draw a box around each object it recognizes. After creating the bounding box for the object, the vehicle module sends the box coordinates to a processor for processing of the hazardous event. That is, the system may identify objects outside the vehicle that have impacted the driver's driving performance. The box uses an object detection algorithm to identify objects outside the vehicle from the recorded video that have impacted the performance data. The latitude and longitude coordinates of the identified objects may be determined and sent to the diagnostic module processor for further processing to determine the impact on driver performance.

[0082] Based on all data collected from the trip, the system calculates a trip-based driver scoring for a cumulative overall driver score (716). The system then uses artificial intelligence and / or machine learning to calculate the collected vehicle sensor and / or video metadata based on the data collection and analysis and develops a driving score, including risk and safety scores (718). If no more hazardous events are detected and the trip is determined to be over (720), the system stops collecting data.

[0083] FIG. 8 is a flow diagram illustrating an example method 800 for determining driver and vehicle safety. Execution of the safety score calculation process 800 begins with acquiring, collecting, and / or detecting data during a trip. As described above, the driver may be a human or the vehicle itself if automated driving features are activated. Diagnostic data is collected (802), it is determined from the diagnostic data whether a trouble code occurred during the trip (804), unsafe event data is identified (806), and a severity level for the unsafe event is assigned (808). Driving data is also collected (810), it is determined from the driving data whether abnormal behavior is detected (812), unsafe event data is identified (814), and a severity level for the unsafe event is assigned (816). Using the collected data, the detected trouble codes, the identified unsafe events, and the assigned severity levels for the events, the system determines an intermediate score (818) during the progress of the trip. Once a trip is completed (820), a trip severity is assigned (822) and a trip score is determined (824). A driver score is calculated (826) using the trip severity level and the trip score.

[0084] Factors that may be analyzed in determining the Trip Score include, but are not limited to, observed driver behavior, available vehicle safety systems, level of vehicle maintenance, and mileage and time traveled.

[0085] According to one aspect of the present disclosure, once the system determines an anomaly of sufficient severity, it can contact and dispatch emergency responders and tow trucks, and also assist those involved in selecting medical and vehicle repair facilities. The system can track the vehicle's location and orientation. If an inertial measurement unit (IMU) is fitted, the system can process the IMU data separately from the GPS samples, thereby providing more detailed vehicle information. The system can obtain vehicle information every second from the GPS and IMU, such as longitude, latitude, altitude, speed, direction, longitude error (meters), latitude error (meters), speed error (meters / sec), altitude error (meters), and direction error (degrees).

[0086] The GPS module then processes the GPS data using an unscented Kalman localization filter, which helps increase the precision and accuracy of the information the system receives. The localization filter itself estimates the vehicle's position based on speed and direction and matches it with the information received from GPS. In areas with poor reception, the system can give more weight to the localization filter's predictions rather than placing more weight on the GPS data.

[0087] Figure 9 summarizes the overall insurance system process related to insurance. It shows four main processes that take place when an incident is detected: a) detection of accidents and other anomalies, b) reconstruction and description of the anomalies, c) incident costs and fault attribution, and d) subrogation and payment.

[0088] FIG. 10 illustrates the process for detecting accidents or anomalies, i.e., incidents. During driving, an allocated amount of data storage is reserved to hold one minute's worth of vehicle sensor information. When an accident or anomaly is detected, an alert is issued to surrounding vehicles and devices that may have seen the incident. Data from vehicles and devices within range that may have seen the incident is sent to the insurance system's data platform for further analysis.

[0089] Figure 11 illustrates a process for using data from multiple device sensors to improve the accuracy of vehicle and object location and motion estimation at the time of a detected incident. The diagram also illustrates a process for reconstructing the detected object activity from the device and vehicle sensor data, such as path predictions for the detected object and actions that may have led to the detected anomaly / incident. The result of this process is an incident report and event log of the activity that occurred.

[0090] Figure 12 illustrates how incident reports can be used to assign fault to involved entities. A model trained on the results of past insurance claims based on anomaly types is run on the incident report. The model assigns fault to objects and entities detected at the location of the incident along with potential faults that may be contributed by, but are not limited to, part manufacturers or vehicle software manufacturers. After fault is assigned, costs are estimated from a model trained on past insurance claims information. Additionally, if the driver or passenger took a photo of the incident with their mobile phone, the photo can be uploaded to the insurance system's data platform to run a cost estimation model trained on the images of the incident. Given the estimated cost and the accuracy of the cost estimate, a decision can be made to automatically make a payment to the insured or to request approval from a human agent.

[0091] Figure 13 illustrates a process to reduce the amount of manual work to subrogate claims and payments to parties. First, using data generated from the incident, a discrimination model is run on the detected objects to detect vehicle license plate information to retrieve the party's insurance company from a remote database. If that information alone is not enough to identify the party, an individual can take a photo of the driver's license with their mobile phone. The driver's license image is used to extract the party's information by a model trained to detect written letters and numbers. The identified party and its insurance company are then notified of their share of fault based on the output of the historical fault model. Based on the assigned share of fault, the payment is subrogated and the party receives the insurance money.

[0092] The system can store accident data on the vehicle and on the device.

[0093] The system can be used to tailor hazard signature calculations and anomaly detection to available sensor and / or data inputs.

[0094] The system can be used for driver and vehicle risk estimation and safety assessment for fleet management.

[0095] Following an accident, the system can be used to transmit accident data to an emergency response service via cellular and / or other network connection.

[0096] The system can be used to estimate vehicle repairs, insurance claims and personal injury from accident data.

[0097] The system can be used for driver and / or vehicle safety analysis.

[0098] The system described above can be applied in both the finance and insurance industries. It can be used for residual value calculations for leases and loans. The risk calculations and estimates generated can be used to estimate the residual value of a vehicle by identifying the movements and vehicle mileage. The residual value can then be used to estimate lease prices, fleet management sales, vehicle prices, auction prices, and total loss insurance valuations. The estimated driver scores and trip summaries can be used to calculate the cost of a trip per mile driven, changes in driver insurance premiums, and vehicle wear and tear.

[0099] Conclusion In this disclosure, the word "exemplary" is used to mean "serving as an example, instance, or illustration." Any aspect or aspect described herein as "exemplary" should not necessarily be construed as preferred or advantageous over other aspects of the disclosure. Likewise, the term "aspect" does not require that all aspects of the disclosure include the described feature, advantage, or mode of operation. As used herein, the term "coupled" is used to refer to a direct or indirect coupling between two objects. For example, if object A is in physical contact with object B, and object B is in contact with object C, then object A and object C can be considered to be coupled to each other even though they are not in direct physical contact. For example, a first object may be coupled to a second object even though the first object is not in direct physical contact with the second object. The terms "circuit" and "electrical circuitry" are used broadly and are intended to include both hardware implementations of electrical devices and conductors that, when connected and configured, enable the performance of the functions described in this disclosure, and software implementations of information and instructions that, when executed by a processor, enable the performance of the functions described in this disclosure. "At least one" and "one or more" may be used interchangeably herein.

[0100] In this disclosure, the use of the components "A and / or B" can mean "A or B or A and B," or can alternatively be expressed as "A, B, or a combination thereof" or "A, B, or both." In this disclosure, the use of the components "A, B, and / or C" can mean "A or B or C, or any combination thereof," or can alternatively be expressed as "A, B, C, or any combination thereof."

[0101] One or more of the components, steps, features and / or functions described herein may be rearranged and / or combined into a single component, step, feature or function, or embodied in multiple components, steps or functions. Also, additional elements, components, steps and / or functions may be added without departing from the novel features disclosed herein. The apparatus, devices and / or components described herein may be configured to perform one or more of the methods, features or steps described herein. Also, the novel algorithms described herein may be efficiently implemented in software and / or incorporated into hardware.

[0102] It is understood that the specific order or hierarchy of steps in the disclosed methods is an example of an example process. It is understood that the specific order or hierarchy of steps in the methods can be rearranged based on design desirability. The accompanying method claims present elements of the various steps in a sample order, and are not intended to be limited to the specific order or hierarchy presented, unless specifically stated therein.

[0103] The above description is provided to enable those skilled in the art to practice the various embodiments described herein. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments. As such, the claims are not intended to be limited to the embodiments shown herein, but are to be accorded the full scope consistent with the language of the claims, and references to elements in the singular shall mean "one or more" and not "only one" unless otherwise specified. The term "some" refers to one or more, unless otherwise specified. A phrase referring to "at least one" of a list of items refers to any combination of those items, including single members. For example, "at least one of a, b, or c" is intended to include a; b; c; a and b; a and c; b and c; a, b, and c. All structural and functional equivalents to the elements of the various embodiments described throughout this disclosure that are known or later become known to those skilled in the art are expressly incorporated herein by reference and are intended to be included within the scope of the claims. Moreover, nothing disclosed herein is intended to be dedicated to the public, regardless of whether such disclosure is expressly recited in the claims. No claim element is to be construed under the provisions of 35 U.S.C. 112(f) unless the claim element is expressly recited using the phrase "means for," or, in the case of a method claim, the phrase "step for."

[0104] As used herein, the term "determining" encompasses a wide variety of actions. For example, "determining" can include calculating, computing, processing, deriving, investigating, searching (e.g., searching in a table, database or other data structure), ascertaining, and the like. "Determining" can also include receiving (e.g., receiving information), accessing (e.g., accessing data in a memory), and the like. "Determining" can also include seeking, selecting, choosing, establishing, and the like.

[0105] While the above disclosure sets forth exemplary embodiments, it should be noted that various changes and modifications may be made herein without departing from the scope of the appended claims. Also, the functions, steps, or actions of the method claims according to the embodiments described herein do not have to be performed in any particular order unless specifically stated. Further, although elements may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is expressly stated.

Claims

1. One or more non-transitory computer-readable media storing computer-executable instructions, The computer-executable instructions, when executed, cause one or more processors to perform operations, the operations including: receiving performance data from a plurality of sources relating to the performance of a driver of the vehicle; identifying at least one risky event affecting a driver's performance, the at least one risky event adversely affecting the performance data below a pre-defined threshold; analyzing the performance data using a trained machine learning model to determine a severity level of each identified dangerous event affecting the driver's performance, the trained machine learning model employing multiple types of machine learning algorithms to analyze the performance data; generating at least one score based on the performance data for presentation via a user interface; improving the machine learning model based on the generated at least one score, the improving including retraining the machine learning model based on at least one of the training corpora that has been modified based on the performance data; 1. One or more non-transitory computer-readable media comprising:

2. 10. The one or more non-transitory computer readable media of claim 1, 4. The one or more non-transitory computer-readable media, wherein the operations further comprise communicating the at least one score to at least one user via the user interface.

3. 10. The one or more non-transitory computer readable media of claim 1, 11. The one or more non-transitory computer-readable media, wherein the performance data is selected from at least one of sensor data, data from a diagnostic module, data from an engine control unit module, and data from an autonomous driving module.

4. 10. The one or more non-transitory computer readable media of claim 1, The operation, starting recording of video data using a camera mounted on the vehicle; and analyzing the recorded video data using vehicle threshold events to identify the at least one hazardous event.

5. 5. The one or more non-transitory computer readable media of claim 4, One or more non-transitory computer readable media, characterized in that a memory device installed in a vehicle stores 10 seconds of video recorded before and after the at least one hazardous event.

6. 5. The one or more non-transitory computer readable media of claim 4, The operation, using an object detection algorithm to identify from the recorded video an object external to the vehicle that affects the performance data; and transmitting latitude and longitude coordinates of the identified object to a diagnostic module processor for further processing to determine an influence of the object on the at least one hazardous event.

7. 10. The one or more non-transitory computer readable media of claim 1, The operation, initiating storage of vehicle data from the diagnostic module, the engine control unit module, and the autonomous driving module; and analyzing the stored vehicle data for vehicle threshold events to identify the at least one unsafe event.

8. 10. The one or more non-transitory computer readable media of claim 1, The operation, determining the occurrence of an accident from the performance data; and transmitting information related to the accident to a third party.

9. 10. The one or more non-transitory computer readable media of claim 1, 13. The one or more non-transitory computer readable media, wherein the at least one score is generated on-board a vehicle.

10. 10. The one or more non-transitory computer readable media of claim 1, The operation, updating said at least one score after a severity level has been assigned to said at least one hazardous event; storing the updated scores in an on-board memory device located in the vehicle; and transmitting the updated scores to a remote data database.

11. 11. The one or more non-transitory computer readable media of claim 10, The one or more non-transitory computer readable media, wherein the at least one score is a driver score and a trip score.

12. 1. A computer-implemented method comprising: receiving, at a processor of a vehicle module onboard the vehicle, performance data relating to a performance of a driver of the vehicle from a plurality of sources onboard the vehicle; identifying, with a processor of the vehicle module, at least one unsafe event affecting a driver's performance, the at least one unsafe event adversely affecting performance data below a pre-defined threshold; analyzing the performance data using a trained machine learning model in a processor of the vehicle module to determine a severity level of each identified unsafe event affecting a driver's performance, the trained machine learning model employing multiple types of machine learning algorithms to analyze the performance data; generating, by a processor of the vehicle module, at least one score based on the performance data for presentation via a user interface; and at a processor of the vehicle module, improving a machine learning model based on the generated at least one score, where the improving includes retraining the machine learning model based on at least one of the training corpora that has been modified based on the performance data.

13. 2. The computer-implemented method of claim 1, causing the processor to initiate recording of video data using a camera mounted on the vehicle; and wherein the processor analyzes the recorded video data using vehicle threshold events to identify the at least one risk.

14. 14. The computer implemented method of claim 13, a diagnostic module in communication with a module installed in the vehicle using an object detection algorithm to identify from the recorded video an object external to the vehicle that affects the performance data; and transmitting the latitude and longitude coordinates of the identified object to a diagnostic module processor for further processing to determine an influence of the object on the at least one hazardous event.

15. 14. The computer implemented method of claim 13, Initiating storage of vehicle data from a diagnostic module, an engine control unit module, and an autonomous driving module on board the vehicle by the processor; and wherein the processor analyzes stored vehicle data for vehicle threshold events to identify the at least one unsafe event.

16. A computing device installed in a vehicle, An interface; a processing circuit coupled to the interface, the processing circuit comprising: receiving performance data from a plurality of sources relating to the performance of a driver of the vehicle; identifying at least one risky event affecting a driver's performance, the at least one risky event adversely affecting the performance data below a pre-defined threshold; analyzing the performance data using a trained machine learning model to determine a severity level of each identified dangerous event affecting the driver's performance, the trained machine learning model employing multiple types of machine learning algorithms to analyze the performance data; generating at least one score based on the performance data for presentation to a user; improving the machine learning model based on the generated at least one score, the improving including retraining the machine learning model based on at least one of the training corpora that has been modified based on the performance data; 23. A computing device configured to:

17. 17. The computing device of claim 16, The processing circuitry comprises: Start recording video data using the camera mounted on the vehicle, The computing device, further configured to analyze the recorded video data using vehicle threshold events to identify the at least one hazardous event.

18. 17. The computing device of claim 16, The processing circuitry comprises: Uses object detection algorithms to identify objects from recorded video that are external to the vehicle and affect performance data; and transmitting latitude and longitude coordinates of the identified object to a diagnostic module processor for further processing to determine an influence of the object on the at least one hazardous event.

19. 17. The computing device of claim 16, The processing circuitry comprises: Initiate the storage of vehicle data from the diagnostic module, the engine control unit module, and the autonomous driving module; 13. The computing device, further configured to analyze vehicle threshold events of stored vehicle data to identify the at least one unsafe event.

20. 17. The computing device of claim 16, The processing circuitry comprises: Determining the occurrence of an accident from the performance data; The computing device, further configured to transmit information related to the accident to a third party.

Images