A method, apparatus, equipment and medium for vehicle risk assessment

Abstract

This invention discloses a vehicle risk assessment method, apparatus, device, and medium. The method includes: acquiring events generated by at least one functional module within a preset time interval; filtering at least one fault event from the events; determining at least one non-fault event that is time-related to the at least one fault event, wherein the at least one fault event and its corresponding non-fault event constitute a vehicle event set; determining at least one basic evaluation index corresponding to each event in the vehicle event set based on the events corresponding to the vehicle event set; and filtering directional evaluation indicators from the at least one basic evaluation index. Embodiments of this invention can extract directional evaluation indicators from all basic evaluation indicators of autonomous vehicles for directional evaluation of vehicle performance and potential risks from the perspective of fault risk.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, equipment and medium for vehicle risk assessment. Background Technology

[0002] With the increasing popularity and widespread use of autonomous vehicles, people have higher and higher requirements for their safety. How to assess the risks of autonomous vehicles and thus determine whether they can continue to operate safely is one of the core issues of safe driving technology.

[0003] In related technologies, the existence of risks in autonomous vehicles is typically determined based on raw data generated during operation, such as driving data, decision-making data, and environmental data. However, some potential risks of autonomous vehicles may not be fully exposed and cannot be disclosed through raw data. Anomalies may occur during the operation of the autonomous vehicle but not be reflected in the raw data. Therefore, relying solely on raw data to determine the existence of risks in autonomous vehicles cannot assess potential risks, making it impossible for users to accurately determine whether autonomous vehicles can continue to operate safely. Summary of the Invention

[0004] This invention provides a vehicle risk assessment method, apparatus, equipment, and medium to address the problem in related technologies where vehicle risk assessment schemes rely solely on raw data to determine whether an autonomous vehicle poses a risk, failing to assess potential risks and thus preventing users from accurately determining whether an autonomous vehicle can continue to operate safely.

[0005] According to one aspect of the present invention, a vehicle risk assessment method is provided, comprising:

[0006] Acquire events generated by the at least one functional module within a preset time interval;

[0007] Filter out at least one fault event from the events;

[0008] Identify at least one non-fault event that is time-related to the at least one fault event, wherein the at least one fault event and its corresponding non-fault event constitute a vehicle event set;

[0009] Based on the parameters corresponding to the vehicle event set, at least one basic evaluation index is determined for each event in the vehicle event set.

[0010] Select directional evaluation indicators from the at least one basic evaluation indicator, wherein the directional evaluation indicators are basic evaluation indicators used for directional evaluation of vehicle performance.

[0011] According to another aspect of the present invention, a vehicle risk assessment device is provided, comprising:

[0012] The data acquisition module is used to acquire events generated by the at least one functional module within a preset time interval;

[0013] An event filtering module is used to filter out at least one fault event from the events;

[0014] An event determination module is used to determine at least one non-fault event that is time-related to the at least one fault event, wherein the at least one fault event and its corresponding non-fault event constitute a vehicle event set.

[0015] The indicator determination module is used to determine at least one basic evaluation indicator for each event in the vehicle event set based on the parameters corresponding to the vehicle event set.

[0016] The indicator filtering module is used to filter out directional evaluation indicators from the at least one basic evaluation indicator, wherein the directional evaluation indicator is a basic evaluation indicator used for directional evaluation of vehicle performance.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] At least one processor;

[0019] and a memory communicatively connected to the at least one processor;

[0020] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the vehicle risk assessment method according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle risk assessment method according to any embodiment of the present invention.

[0022] The technical solution of this invention involves acquiring events generated by at least one functional module within a preset time interval; then filtering out at least one fault event from the events; determining at least one non-fault event that is time-related to the at least one fault event, with the at least one fault event and its corresponding non-fault event constituting a vehicle event set; determining at least one basic evaluation index corresponding to each event in the vehicle event set based on the parameters corresponding to the vehicle event set; and finally filtering out a directional evaluation index from the at least one basic evaluation index. This directional evaluation index is a basic evaluation index used for directional evaluation of vehicle performance. This solves the problem in related technologies where vehicle risk assessment schemes rely solely on raw data to determine whether an autonomous vehicle has a risk, failing to evaluate the potential risks and preventing users from accurately determining whether an autonomous vehicle can continue to operate safely. The solution provides a directional evaluation index that can be extracted from all basic evaluation indicators of an autonomous vehicle to directionally evaluate vehicle performance from the perspective of fault risk, assess the potential risks of the autonomous vehicle, and assist users in accurately determining whether an autonomous vehicle can continue to operate safely. This directional evaluation index offers the beneficial effect of evaluating the potential risks of an autonomous vehicle and assisting users in accurately determining whether an autonomous vehicle can continue to operate safely.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a vehicle risk assessment method provided in Embodiment 1 of the present invention.

[0026] Figure 2 This is a flowchart of a vehicle risk assessment method provided in Embodiment 2 of the present invention.

[0027] Figure 3 This is a schematic diagram of a vehicle risk assessment device provided in Embodiment 3 of the present invention.

[0028] Figure 4 A schematic diagram of the structure of an electronic device for implementing the vehicle risk assessment method of this invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "target," "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising," "including," and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] Figure 1 This is a flowchart of a vehicle risk assessment method provided in Embodiment 1 of the present invention. This embodiment is applicable to assessing the potential risks of autonomous vehicles and determining whether autonomous vehicles can continue to operate safely. This method can be executed by a vehicle risk assessment device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0033] Step 101: Obtain events generated by at least one functional module within a preset time interval.

[0034] Optionally, the vehicle is an autonomous vehicle. The vehicle includes at least one functional module. Each functional module can be a module within the vehicle's control system used to implement different functions. Each functional module can be implemented in hardware and / or software. The preset time interval is a pre-set time interval.

[0035] Optionally, an event generated by a functional module refers to the parameter state of any parameter of the functional module, which has a start time and an end time. The parameter state is either within the normal parameter value range or outside the normal parameter value range. An event generated by the functional module occurs when a parameter of the functional module is within or outside the normal parameter value range within a target time interval. The start time of the target time interval is the start time of this event, and the end time of the target time interval is the end time of this event. If the event includes a parameter state outside the normal parameter value range, the event is determined to be a fault event.

[0036] Optionally, the vehicle may include functional modules such as a perception and positioning module, a planning and control module, a chassis control module, a driving status module, and an operational status module.

[0037] Optionally, a perception and positioning module is used to receive multiple positioning information from multiple positioning sources and determine the vehicle pose based on the multiple positioning information. The vehicle pose includes the vehicle coordinates and the angles between the vehicle's heading and each coordinate axis. Positioning sources include, but are not limited to, Global Positioning System (GPS) positioning sources, visual positioning sources, and LiDAR positioning sources. The positioning information from the positioning sources includes, but is not limited to, pose information and confidence level. Pose information is the vehicle pose determined by the positioning source. Confidence level is the reliability of the vehicle pose determined by the positioning source.

[0038] Optionally, the parameters of the sensing and positioning module may include multiple positioning information from multiple positioning sources received by the sensing and positioning module within a preset time interval.

[0039] For example, events generated by the sensing and positioning module within a preset time interval include: the positioning information received by the sensing and positioning module from the GPS positioning source within the preset time interval is not within the normal value range of the positioning information; the positioning information received by the sensing and positioning module from the visual positioning source within the preset time interval is within the normal value range of the positioning information; and the positioning information received by the sensing and positioning module from the LiDAR positioning source within the preset time interval is within the normal value range of the positioning information.

[0040] Optionally, a planning and control module is used to monitor whether the vehicle deviates from a preset area during its driving process based on its position and orientation, and to perform path planning and decision-making based on the judgment results. The planning and control module is also used to monitor lane-changing operations during the vehicle's driving process.

[0041] Optionally, the parameters of the planning and control module may include the duration of each lane change by the vehicle within a preset time interval detected by the planning and control module. The vehicle status is either deviating from the preset area or not deviating from the preset area.

[0042] For example, the events generated by the planning control module within a preset time interval include: the vehicle status at each moment within the preset time interval detected by the planning control module is not deviating from the preset area, and the duration of each lane change by the vehicle within the preset time interval detected by the planning control module is less than a preset duration threshold.

[0043] Optionally, a chassis control module is used to generate and send control signals to the vehicle's underlying execution system, enabling the underlying execution system to control the vehicle to travel along a desired path. The vehicle's underlying execution system includes, but is not limited to, the vehicle controller, steering system, braking system, and drive system.

[0044] Optionally, the parameters of the chassis control module may include shift commands and emergency braking commands received by the chassis control module within a preset time interval, vehicle acceleration, vehicle speed, and vehicle steering angle at various moments within the preset time interval obtained by the chassis control module.

[0045] For example, the events generated by the chassis control module within a preset time interval include: the vehicle acceleration at each moment within the preset time interval obtained by the chassis control module is less than a preset acceleration threshold, and the vehicle speed at each moment within the preset time interval obtained by the chassis control module is less than a preset speed threshold.

[0046] Optional, a driving status module is provided to monitor manual takeover and intervention operations during vehicle operation.

[0047] Optionally, the parameters of the driving status module may include the start time, end time, and duration of each manual takeover operation, and the start time, end time, and duration of each manual intervention operation.

[0048] For example, events generated by the driving status module within a preset time interval include: the duration of each manual intervention operation within the preset time interval obtained by the chassis control module is less than a preset duration threshold.

[0049] Optional, an operational status module is used to monitor the autonomous driving mileage, autonomous driving time, and power consumption during vehicle operation.

[0050] Optionally, the parameters of the operation status module may include the autonomous driving mileage, autonomous driving time, and power consumption at various times within a preset time interval obtained by the operation status module.

[0051] For example, the events generated by the operation status module within a preset time interval include: the power consumption at each moment within the preset time interval obtained by the operation status module is less than a preset power consumption threshold.

[0052] Optionally, obtaining events generated by the at least one functional module within a preset time interval includes: performing the following operation for each functional module: obtaining events generated by the functional module within the preset time interval from the events stored in the functional module.

[0053] Optionally, acquiring events generated by the at least one functional module within a preset time interval includes: acquiring events uploaded by the user that were generated by the at least one functional module within a preset time interval.

[0054] Step 102: Select at least one fault event from the events.

[0055] Optionally, at least one fault event is selected from the events, including: for each functional module, performing the following operation: extracting fault events from the events generated by the functional module within a preset time interval, where the parameter status is outside the normal parameter value range. Thus, fault events generated by each functional module within the preset time interval are selected.

[0056] Step 103: Determine at least one non-fault event that is time-related to the at least one fault event in the events, wherein the at least one fault event and its corresponding non-fault event constitute a vehicle event set.

[0057] Optionally, each fault event has a corresponding start time and end time; determining at least one non-fault event that is time-related to the at least one fault event includes: performing the following operation for each fault event: determining whether there is a fault event within at least one time period, either a first preset duration before the start time or a second preset duration after the end time; if not, determining the event corresponding to the at least one time period as a non-fault event that is time-related to the fault event.

[0058] Optionally, the start time of a fault event is the time when the fault event occurs, and the end time of a fault event is the time when the fault event ends. The first preset duration and the second preset duration are preset durations. The first preset duration and the second preset duration can be the same or different durations. The events corresponding to a time period are events that occur within that time period.

[0059] Optionally, non-fault events that are time-related to the fault event are events that occur before or after the fault event, but are not fault events.

[0060] Optionally, if there are fault events in each time period, then it is determined that there are no non-fault events that are time-related to the fault events.

[0061] In a specific example, the first preset duration is 30 minutes, and the second preset duration is 45 minutes. For a given fault event: It is determined whether a fault event exists within 30 minutes before the start time and 45 minutes after the end time. If no fault event exists within either of these timeframes, the event corresponding to the event 30 minutes before the start time is identified as a non-fault event time-related to the fault event, and the event corresponding to the event 45 minutes after the end time is also identified as a non-fault event time-related to the fault event. If a fault event exists within either of these timeframes, it is identified as a non-fault event time-related to the fault event. If a fault event exists within both of these timeframes, it is determined that no non-fault event time-related to the fault event exists.

[0062] Optionally, at least one selected fault event and at least one non-fault event that is time-related to the at least one fault event constitute a vehicle event set.

[0063] In a specific instance, n fault events are selected: μ1, μ2, ..., μ n Identify at least one non-faulty event that is time-related to each faulty event, resulting in m non-faulty events: μ n+1 μ n+2 , ..., μ n+m The vehicle event set {μ1, μ2, ..., μm} consists of n fault events and m non-fault events. n+m}

[0064] Step 104: Based on the parameters corresponding to the vehicle event set, determine at least one basic evaluation index corresponding to each event in the vehicle event set.

[0065] Optionally, the basic evaluation index is a statistical parameter obtained based on at least one parameter corresponding to the event.

[0066] Optionally, the parameters corresponding to the vehicle event set are the parameters corresponding to each event in the vehicle event set. The parameters corresponding to each event are the parameters of the at least one functional module during the occurrence of the event.

[0067] Optionally, based on the parameters corresponding to the vehicle event set, at least one basic evaluation index corresponding to each event in the vehicle event set is determined, including: performing the following operation for each event in the vehicle event set: statistically analyzing the parameters corresponding to the event to determine at least one basic evaluation index corresponding to the event.

[0068] Optionally, the basic evaluation indicators corresponding to the event include: the maximum, minimum, and average confidence scores of the multiple location information received by the sensing and positioning module during the event.

[0069] Optionally, the basic evaluation indicators corresponding to the event may also include: the number of times the vehicle status deviated from the preset area during the event, the cumulative time the vehicle status deviated from the preset area during the event, the number of times the vehicle changed lanes during the event, and the cumulative time the vehicle changed lanes during the event.

[0070] Optionally, the basic evaluation indicators corresponding to the event may also include: the number of times the vehicle shifts to park during the event, the cumulative time the vehicle shifts to park during the event, the number of times the vehicle brakes suddenly during the event, the cumulative time the vehicle brakes suddenly during the event, the number of times the vehicle's steering angle exceeds a preset steering angle threshold during the event, the cumulative time the vehicle's steering angle exceeds a preset steering angle threshold during the event, the number of times the product of vehicle speed and vehicle acceleration exceeds a first preset product threshold during the event, the cumulative time the product of vehicle speed and vehicle acceleration exceeds a first preset product threshold during the event, the number of times the product of vehicle speed and vehicle steering angle exceeds a second preset product threshold during the event, and the cumulative time the product of vehicle speed and vehicle steering angle exceeds a second preset product threshold during the event.

[0071] Optionally, the preset steering angle threshold is a pre-set vehicle steering angle threshold. The first preset product threshold is a pre-set threshold for the product of vehicle speed and vehicle acceleration. The second preset product threshold is a pre-set threshold for the product of vehicle speed and vehicle steering angle.

[0072] In a specific example, based on the vehicle acceleration and steering angle at each moment during the event, the product of the vehicle acceleration and steering angle at each moment during the event is calculated. Then, based on the product of the vehicle acceleration and steering angle at each moment during the event, statistics are performed to determine the number of times the product of the vehicle speed and steering angle during the event is greater than a second preset product threshold, and the cumulative time during the event when the product of the vehicle speed and steering angle is greater than the second preset product threshold.

[0073] Optionally, the basic evaluation indicators for the event may also include: the number of times manual takeover was performed during the event, and the number of times manual intervention was performed during the event.

[0074] Optionally, the basic evaluation indicators corresponding to the event may also include: autonomous driving mileage during the event, autonomous driving time during the event, and the ratio of autonomous driving mileage to power consumption during the event.

[0075] Step 105: Select directional evaluation indicators from the at least one basic evaluation indicator, wherein the directional evaluation indicators are basic evaluation indicators used for directional evaluation of vehicle performance.

[0076] Optionally, the step of selecting directional evaluation indicators from the at least one basic evaluation indicator includes: constructing a vehicle event sample set based on the basic evaluation indicator and fault attribute corresponding to each event in the vehicle event set, wherein the fault attribute characterizes whether an event is a fault event; determining the importance value of each basic evaluation indicator according to the vehicle event sample set; and determining basic evaluation indicators with an importance value greater than a preset threshold as directional evaluation indicators.

[0077] Optionally, the basic evaluation index and fault attribute corresponding to each event in the vehicle event set can be determined as a sample in the vehicle event sample set, thereby constructing the vehicle event sample set.

[0078] In a specific instance, the vehicle event set contains n+m events {μ1, μ2, ..., μm}. n+m The basic evaluation index and fault attribute corresponding to each event in the vehicle event set are determined as a sample in the vehicle event sample set, thereby constructing a vehicle event sample set {(X1, Y1), (X2, Y2), ..., (X...} containing n+m samples. n+m Y n+m X1 contains each basic evaluation index corresponding to event μ1. Y1 is the fault attribute corresponding to the event. (X1, Y1) is a sample in the vehicle event sample set. A fault attribute of 1 indicates that the event is a fault event. A fault attribute of 0 indicates that the event is a non-fault event.

[0079] Optionally, determining the importance value of each basic evaluation indicator based on the vehicle event sample set includes: training a random forest model with the fault attribute corresponding to each event in the vehicle event sample set as the dependent variable and the basic evaluation indicator corresponding to each event in the vehicle event sample set as the independent variable, to obtain the contribution of each basic evaluation indicator to the random forest model; and determining the contribution of each basic evaluation indicator to the random forest model as the importance value of each basic evaluation indicator.

[0080] Optionally, the vehicle event sample set is divided into a training sample set and a test sample set. A random forest model is trained using the fault attribute corresponding to each event in the training sample set as the dependent variable and the basic evaluation index corresponding to each event in the training sample set as the independent variable. The random forest model is then tested using the test sample set to obtain its accuracy. If the accuracy is greater than a preset accuracy threshold, the random forest model is considered successfully trained. The Gini coefficient in the trained random forest model is used to determine the contribution of each independent variable to the random forest model, i.e., the contribution of each basic evaluation index to the random forest model. The contribution of an independent variable to the random forest model characterizes the importance of the independent variable to the random forest model and the degree of influence of the independent variable on the dependent variable. A large contribution of the basic evaluation index to the random forest model indicates that the basic evaluation index has a significant impact on the fault attribute and plays an important role in determining whether a fault has occurred during vehicle operation.

[0081] Optionally, the contribution of each basic evaluation indicator to the random forest model is determined as the importance value of each basic evaluation indicator. The importance value characterizes the degree to which the basic evaluation indicator is important in determining whether a malfunction has occurred during vehicle operation. A higher importance value indicates that the basic evaluation indicator plays an important role in determining whether a malfunction has occurred during vehicle operation. A lower importance value indicates that the basic evaluation indicator plays a less important role in determining whether a malfunction has occurred during vehicle operation.

[0082] Optionally, the preset threshold is a pre-set importance value threshold. Basic evaluation indicators with importance values ​​greater than the preset threshold are identified as directional evaluation indicators. This allows for the selection of basic evaluation indicators that play a crucial role in determining whether a vehicle malfunction has occurred during operation, thus serving as directional evaluation indicators.

[0083] Therefore, from all the basic evaluation indicators, we can extract targeted evaluation indicators to evaluate vehicle performance from the perspective of failure risk, assess the potential risks of autonomous vehicles, and assist users of autonomous vehicles in accurately judging whether autonomous vehicles can continue to operate safely.

[0084] Optionally, after selecting directional evaluation indicators from the at least one basic evaluation indicator, the method further includes: determining the directional evaluation score of each functional module based on the directional evaluation indicator associated with each functional module.

[0085] Optionally, the orientation evaluation score of each functional module is determined based on the orientation evaluation index associated with each functional module, including: obtaining the parameters of each functional module within the time interval to be detected; determining the orientation evaluation index corresponding to the time interval to be detected based on the parameters; determining the basic score of the orientation evaluation index according to the index type of the orientation evaluation index; and calculating the orientation evaluation score of each functional module based on the basic score and importance value of the orientation evaluation index associated with each functional module.

[0086] Optionally, the time interval to be tested is the time period during which the vehicle needs to be tested for potential malfunction risks. The directional evaluation index corresponding to the time interval to be tested is obtained by statistically analyzing the parameters within the time interval.

[0087] Optional, the types of directional evaluation indicators include risk indicators and excellence indicators.

[0088] Optionally, the directional evaluation indicator can be a risk indicator, indicating that a higher directional evaluation indicator may increase vehicle operational risk and failure rate. Examples include the number of times the vehicle braked suddenly during the detection time interval, or the number of times the vehicle deviated from the preset area during the event.

[0089] Optionally, the orientation evaluation index can be classified as an "excellent" index, indicating that a higher orientation evaluation index suggests a better vehicle operating condition and potentially lower operational risks and failure rates. For example, the average confidence level among multiple location data received within the detection time interval.

[0090] Optionally, based on the indicator type of the directional evaluation indicator, determine the basic score of the directional evaluation indicator, including: performing the following operation for each directional evaluation indicator: normalizing the directional evaluation indicator based on the historical maximum and historical minimum values ​​corresponding to the directional evaluation indicator, to obtain the normalized result m of the directional evaluation indicator. i If the indicator type of the directional evaluation indicator is a risk indicator, then the basic score for the directional evaluation indicator is determined to be 1-m. i If the indicator type of the directional evaluation indicator is a good indicator, then the base score of the directional evaluation indicator is determined to be m. i .

[0091] Optionally, if the directional evaluation index is a statistical parameter obtained based on the parameters of a certain functional module, then the directional evaluation index is determined to be the directional evaluation index associated with that functional module.

[0092] Optionally, based on the baseline score and importance value of the orientation evaluation indicator associated with each functional module, the orientation evaluation score for each functional module is calculated, including: calculating the orientation evaluation score for each functional module using the following formula:

[0093]

[0094] Where i = 1, 2, ..., j. F is the orientation evaluation score of the functional module, j is the number of orientation evaluation indicators associated with the functional module, and w i x represents the importance value of the i-th directional evaluation indicator associated with the functional module. i This is the base score for the i-th directional evaluation indicator associated with the functional module.

[0095] Optionally, the directional evaluation score of a functional module characterizes its performance within the tested time interval. A higher directional evaluation score indicates that the functional module is in good condition and has a low failure rate within the tested time interval. A lower directional evaluation score indicates that the functional module has a higher failure rate within the tested time interval. A directional evaluation score indicates that the functional module is in good condition and has a low failure rate. A directional evaluation score indicates that the functional module is in good condition and has a low failure rate.

[0096] Optionally, after determining the orientation evaluation score for each functional module, the method further includes: providing the orientation evaluation score to a target user. The target user can be either the vehicle user or the technician responsible for managing the vehicle.

[0097] Optionally, the directional evaluation score is sent to the target user's terminal device so that the target user can determine the performance of each functional module in the time interval to be tested based on the directional evaluation score, and determine the status and failure rate of each functional module in the time interval to be tested.

[0098] Optionally, a visualization chart for displaying the directional evaluation indicators is generated, and the visualization chart is sent to the target user's terminal device.

[0099] Optionally, after selecting directional evaluation indicators from the at least one basic evaluation indicator, the method further includes: generating a visualization chart for displaying the directional evaluation indicator, and providing the visualization chart to the target user so that the target user can verify the directional evaluation indicator and verify whether the directional evaluation indicator is a basic evaluation indicator that has a significant impact on the fault attribute.

[0100] Optionally, after selecting directional evaluation indicators from the at least one basic evaluation indicator, the method further includes: verifying, through analysis of variance, whether the directional evaluation indicator is a basic evaluation indicator that has a significant impact on the fault attributes.

[0101] The technical solution of this invention involves acquiring events generated by at least one functional module within a preset time interval; then filtering out at least one fault event from the events; determining at least one non-fault event that is time-related to the at least one fault event, with the at least one fault event and its corresponding non-fault event constituting a vehicle event set; determining at least one basic evaluation index corresponding to each event in the vehicle event set based on the parameters corresponding to the vehicle event set; and finally filtering out a directional evaluation index from the at least one basic evaluation index. This directional evaluation index is a basic evaluation index used for directional evaluation of vehicle performance. This solves the problem in related technologies where vehicle risk assessment schemes rely solely on raw data to determine whether an autonomous vehicle has a risk, failing to evaluate the potential risks and preventing users from accurately determining whether an autonomous vehicle can continue to operate safely. The solution provides a directional evaluation index that can be extracted from all basic evaluation indicators of an autonomous vehicle to directionally evaluate vehicle performance from the perspective of fault risk, assess the potential risks of the autonomous vehicle, and assist users in accurately determining whether an autonomous vehicle can continue to operate safely. This directional evaluation index offers the beneficial effect of evaluating the potential risks of an autonomous vehicle and assisting users in accurately determining whether an autonomous vehicle can continue to operate safely.

[0102] Targeted evaluation indicators help users identify potential risks in vehicle operation and uncover malfunctions. These indicators also assist on-site personnel in determining whether a vehicle is malfunctioning or posing a potential risk. In the event of a major accident, targeted evaluation indicators help on-site and R&D personnel quickly troubleshoot the problem.

[0103] Example 2

[0104] Figure 2 This is a flowchart of a vehicle risk assessment method provided in Embodiment 2 of the present invention. This embodiment of the present invention can be combined with various optional solutions from one or more of the above embodiments. For example... Figure 2 As shown, the method includes:

[0105] Step 201: Obtain events generated by at least one functional module within a preset time interval.

[0106] Step 202: Select at least one fault event from the events.

[0107] Step 203: Determine at least one non-fault event that is time-related to the at least one fault event in the events, wherein the at least one fault event and its corresponding non-fault event constitute a vehicle event set.

[0108] Step 204: Based on the parameters corresponding to the vehicle event set, determine at least one basic evaluation index corresponding to each event in the vehicle event set.

[0109] Step 205: Based on the basic evaluation indicators and fault attributes corresponding to each event in the vehicle event set, construct a vehicle event sample set, wherein the fault attributes characterize whether an event is a fault event.

[0110] Optionally, the basic evaluation index and fault attribute corresponding to each event in the vehicle event set can be determined as a sample in the vehicle event sample set, thereby constructing the vehicle event sample set.

[0111] In a specific instance, the vehicle event set contains n+m events {μ1, μ2, ..., μm}. n+m The basic evaluation index and fault attribute corresponding to each event in the vehicle event set are determined as a sample in the vehicle event sample set, thereby constructing a vehicle event sample set {(X1, Y1), (X2, Y2), ..., (X...} containing n+m samples. n+m Y n+m X1 contains each basic evaluation index corresponding to event μ1. Y1 is the fault attribute corresponding to the event. (X1, Y1) is a sample in the vehicle event sample set. A fault attribute of 1 indicates that the event is a fault event. A fault attribute of 0 indicates that the event is a non-fault event.

[0112] Step 206: Using the fault attribute corresponding to each event in the vehicle event sample set as the dependent variable and the basic evaluation index corresponding to each event in the vehicle event sample set as the independent variable, train the random forest model to obtain the contribution of each basic evaluation index to the random forest model.

[0113] Optionally, the vehicle event sample set is divided into a training sample set and a test sample set. A random forest model is trained using the fault attribute corresponding to each event in the training sample set as the dependent variable and the basic evaluation index corresponding to each event in the training sample set as the independent variable. The random forest model is then tested using the test sample set to obtain its accuracy. If the accuracy is greater than a preset accuracy threshold, the random forest model is considered successfully trained. The Gini coefficient in the trained random forest model is used to determine the contribution of each independent variable to the random forest model, i.e., the contribution of each basic evaluation index to the random forest model. The contribution of an independent variable to the random forest model characterizes the importance of the independent variable to the random forest model and the degree of influence of the independent variable on the dependent variable. A large contribution of the basic evaluation index to the random forest model indicates that the basic evaluation index has a significant impact on the fault attribute and plays an important role in determining whether a fault has occurred during vehicle operation.

[0114] Step 207: Determine the contribution of each basic evaluation index to the random forest model as the importance value of each basic evaluation index.

[0115] Optionally, the contribution of each basic evaluation indicator to the random forest model is determined as the importance value of each basic evaluation indicator. The importance value characterizes the degree to which the basic evaluation indicator is important in determining whether a malfunction has occurred during vehicle operation. A higher importance value indicates that the basic evaluation indicator plays an important role in determining whether a malfunction has occurred during vehicle operation. A lower importance value indicates that the basic evaluation indicator plays a less important role in determining whether a malfunction has occurred during vehicle operation.

[0116] Step 208: Determine the basic evaluation indicators whose importance value is greater than the preset threshold as directional evaluation indicators.

[0117] Optionally, the preset threshold is a pre-set importance value threshold. Basic evaluation indicators with importance values ​​greater than the preset threshold are identified as directional evaluation indicators. This allows for the selection of basic evaluation indicators that play a crucial role in determining whether a vehicle malfunction has occurred during operation, thus serving as directional evaluation indicators.

[0118] Therefore, from all the basic evaluation indicators, we can extract targeted evaluation indicators to evaluate vehicle performance from the perspective of failure risk, assess the potential risks of autonomous vehicles, and assist users of autonomous vehicles in accurately judging whether autonomous vehicles can continue to operate safely.

[0119] Step 209: Determine the orientation evaluation score for each functional module based on the orientation evaluation index associated with each functional module.

[0120] Optionally, the orientation evaluation score of each functional module is determined based on the orientation evaluation index associated with each functional module, including: obtaining the parameters of each functional module within the time interval to be detected; determining the orientation evaluation index corresponding to the time interval to be detected based on the parameters; determining the basic score of the orientation evaluation index according to the index type of the orientation evaluation index; and calculating the orientation evaluation score of each functional module based on the basic score and importance value of the orientation evaluation index associated with each functional module.

[0121] Optionally, the time interval to be tested is the time period during which the vehicle needs to be tested for potential malfunction risks. The directional evaluation index corresponding to the time interval to be tested is obtained by statistically analyzing the parameters within the time interval.

[0122] Optional, the types of directional evaluation indicators include risk indicators and excellence indicators.

[0123] Optionally, the directional evaluation indicator can be a risk indicator, indicating that a higher directional evaluation indicator may increase vehicle operational risk and failure rate. Examples include the number of times the vehicle braked suddenly during the detection time interval, or the number of times the vehicle deviated from the preset area during the event.

[0124] Optionally, the orientation evaluation index can be classified as an "excellent" index, indicating that a higher orientation evaluation index suggests a better vehicle operating condition and potentially lower operational risks and failure rates. For example, the average confidence level among multiple location data received within the detection time interval.

[0125] Optionally, based on the indicator type of the directional evaluation indicator, determine the basic score of the directional evaluation indicator, including: performing the following operation for each directional evaluation indicator: normalizing the directional evaluation indicator based on the historical maximum and historical minimum values ​​corresponding to the directional evaluation indicator, to obtain the normalized result m of the directional evaluation indicator. i If the indicator type of the directional evaluation indicator is a risk indicator, then the basic score for the directional evaluation indicator is determined to be 1-m. i If the indicator type of the directional evaluation indicator is a good indicator, then the base score of the directional evaluation indicator is determined to be m. i .

[0126] Optionally, if the directional evaluation index is a statistical parameter obtained based on the parameters of a certain functional module, then the directional evaluation index is determined to be the directional evaluation index associated with that functional module.

[0127] Optionally, based on the baseline score and importance value of the orientation evaluation indicator associated with each functional module, the orientation evaluation score for each functional module is calculated, including: calculating the orientation evaluation score for each functional module using the following formula:

[0128]

[0129] Where i = 1, 2, ..., j. F is the orientation evaluation score of the functional module, j is the number of orientation evaluation indicators associated with the functional module, and w i x represents the importance value of the i-th directional evaluation indicator associated with the functional module. i This is the base score for the i-th directional evaluation indicator associated with the functional module.

[0130] Optionally, the directional evaluation score of a functional module characterizes its performance within the tested time interval. A higher directional evaluation score indicates that the functional module is in good condition and has a low failure rate within the tested time interval. A lower directional evaluation score indicates that the functional module has a higher failure rate within the tested time interval. A directional evaluation score indicates that the functional module is in good condition and has a low failure rate. A directional evaluation score indicates that the functional module is in good condition and has a low failure rate.

[0131] Optionally, after determining the orientation evaluation score for each functional module, the method further includes: providing the orientation evaluation score to a target user. The target user can be either the vehicle user or the technician responsible for managing the vehicle.

[0132] Optionally, the directional evaluation score is sent to the target user's terminal device so that the target user can determine the performance of each functional module in the time interval to be tested based on the directional evaluation score, and determine the status and failure rate of each functional module in the time interval to be tested.

[0133] Optionally, a visualization chart for displaying the directional evaluation indicators is generated, and the visualization chart is sent to the target user's terminal device.

[0134] The technical solution of this invention provides a method to extract directional evaluation indicators from all basic evaluation indicators of autonomous vehicles. These indicators are used to evaluate vehicle performance from the perspective of fault risk, assess potential risks of autonomous vehicles, and assist users in accurately judging whether autonomous vehicles can continue to operate safely. A directional evaluation score for each functional module can be determined based on these indicators. By combining these indicators with the scores of each functional module, potential risks of autonomous vehicles can be evaluated, helping users accurately judge whether autonomous vehicles can continue to operate safely. This helps users better understand the vehicle's driving status and the performance of each functional module within a specified time interval, assists users in identifying potential risks in vehicle operation, and uncovers the beneficial effects of faults.

[0135] Example 3

[0136] Figure 3 This is a schematic diagram of a vehicle risk assessment device provided in Embodiment 3 of the present invention. The device can be configured in an electronic device. Figure 3 As shown, the device includes: a data acquisition module 301, an event filtering module 302, an event determination module 303, an indicator determination module 304, and an indicator filtering module 305.

[0137] The system includes: a data acquisition module 301, used to acquire events generated by at least one functional module within a preset time interval; an event filtering module 302, used to filter at least one fault event from the events; an event determination module 303, used to determine at least one non-fault event in the events that is time-related to the at least one fault event, wherein the at least one fault event and its corresponding non-fault event constitute a vehicle event set; an indicator determination module 304, used to determine at least one basic evaluation indicator corresponding to each event in the vehicle event set based on parameters corresponding to the vehicle event set; and an indicator filtering module 305, used to filter directional evaluation indicators from the at least one basic evaluation indicator, wherein the directional evaluation indicator is a basic evaluation indicator used for directional evaluation of vehicle performance.

[0138] The technical solution of this invention involves acquiring events generated by at least one functional module within a preset time interval; then filtering out at least one fault event from the events; determining at least one non-fault event that is time-related to the at least one fault event, with the at least one fault event and its corresponding non-fault event constituting a vehicle event set; determining at least one basic evaluation index corresponding to each event in the vehicle event set based on the parameters corresponding to the vehicle event set; and finally filtering out a directional evaluation index from the at least one basic evaluation index. This directional evaluation index is a basic evaluation index used for directional evaluation of vehicle performance. This solves the problem in related technologies where vehicle risk assessment schemes rely solely on raw data to determine whether an autonomous vehicle has a risk, failing to evaluate the potential risks and preventing users from accurately determining whether an autonomous vehicle can continue to operate safely. The solution provides a directional evaluation index that can be extracted from all basic evaluation indicators of an autonomous vehicle to directionally evaluate vehicle performance from the perspective of fault risk, assess the potential risks of the autonomous vehicle, and assist users in accurately determining whether an autonomous vehicle can continue to operate safely. This directional evaluation index offers the beneficial effect of evaluating the potential risks of an autonomous vehicle and assisting users in accurately determining whether an autonomous vehicle can continue to operate safely.

[0139] In an optional embodiment of the present invention, each fault event may have a corresponding start time and end time; the event determination module 303 is specifically used to perform the following operation for each fault event: within at least one time period between a first preset duration before the start time and a second preset duration after the end time, determine whether there is a fault event; if not, determine the event corresponding to the at least one time period as a non-fault event that is time-related to the fault event.

[0140] In an optional embodiment of the present invention, the indicator screening module 305 is specifically configured to: construct a vehicle event sample set based on the basic evaluation indicators and fault attributes corresponding to each event in the vehicle event set, wherein the fault attributes characterize whether an event is a fault event; determine the importance value of each basic evaluation indicator according to the vehicle event sample set; and determine basic evaluation indicators with an importance value greater than a preset threshold as directional evaluation indicators.

[0141] In an optional embodiment of the present invention, the indicator screening module 305, when performing the operation of determining the importance value of each basic evaluation indicator based on the vehicle event sample set, specifically performs the following: using the fault attribute corresponding to each event in the vehicle event sample set as the dependent variable and the basic evaluation indicator corresponding to each event in the vehicle event sample set as the independent variable, training the random forest model to obtain the contribution of each basic evaluation indicator to the random forest model; and determining the contribution of each basic evaluation indicator to the random forest model as the importance value of each basic evaluation indicator.

[0142] In one optional embodiment of the present invention, the basic evaluation index may be a statistical parameter obtained based on at least one parameter corresponding to the event.

[0143] In an optional embodiment of the present invention, the vehicle risk assessment device may further include: a module scoring module, used to determine the orientation assessment score of each functional module based on the orientation assessment index associated with each functional module.

[0144] In an optional embodiment of the present invention, the vehicle risk assessment device may further include a scoring module for providing the directional assessment score to a target user.

[0145] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0146] The vehicle risk assessment device described above can execute the vehicle risk assessment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the vehicle risk assessment method.

[0147] Example 4

[0148] Figure 4 A schematic diagram of an electronic device 10, which can be used to implement the vehicle risk assessment method of embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0149] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or a computer program constructed from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0150] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0151] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle risk assessment methods.

[0152] In some embodiments, the vehicle risk assessment method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is built into RAM 13 and executed by processor 11, one or more steps of the vehicle risk assessment method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle risk assessment method by any other suitable means (e.g., by means of firmware).

[0153] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0154] Computer programs used to implement the vehicle risk assessment method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0155] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0156] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0157] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0158] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0159] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0160] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle risk assessment method, wherein the vehicle includes at least one functional module, characterized in that, include: Acquire events generated by the at least one functional module within a preset time interval; wherein, the events generated by the functional module are parameter states of any parameter of the functional module with start and end times; At least one fault event is selected from the events; wherein, a fault event is an event in which the parameter status is outside the normal parameter value range; Determine at least one non-fault event that is temporally associated with the at least one fault event, wherein the at least one fault event and its corresponding non-fault event constitute a vehicle event set; wherein, the non-fault event that is temporally associated with the fault event is an event that is not a fault event that occurs before or after the fault event. Based on the parameters corresponding to the vehicle event set, at least one basic evaluation index is determined for each event in the vehicle event set; wherein, the basic evaluation index is a statistical parameter obtained based on at least one parameter corresponding to the event, and the parameter corresponding to the event is the parameter of the at least one functional module during the event occurrence. Select directional evaluation indicators from the at least one basic evaluation indicator, wherein the directional evaluation indicators are basic evaluation indicators used to directionally evaluate vehicle performance. Based on the directional evaluation indicators associated with each functional module, the directional evaluation score of each functional module is determined. Specifically, parameters for each functional module within the testing time interval are obtained. Based on these parameters, the directional evaluation indicators corresponding to the testing time interval are determined. The base score of each directional evaluation indicator is determined according to its indicator type. The directional evaluation score of each functional module is calculated based on the base score and importance value of the directional evaluation indicators associated with each functional module. The testing time interval is the time interval during which the vehicle's potential for malfunction needs to be detected, and the directional evaluation score of the functional module is used to characterize the performance of the functional module within the testing time interval.

2. The method according to claim 1, characterized in that, Each fault event has a corresponding start time and end time; The determination of at least one non-fault event that is time-related to the at least one fault event includes: Perform the following actions for each failure event: Determine whether there is a fault event within at least one of the time periods of a first preset duration before the start time and a second preset duration after the end time. If not, the event corresponding to the at least one time period is determined as a non-fault event that is time-related to the fault event.

3. The method according to claim 1, characterized in that, The step of selecting directional evaluation indicators from the at least one basic evaluation indicator includes: Based on the basic evaluation indicators and fault attributes corresponding to each event in the vehicle event set, a vehicle event sample set is constructed, wherein the fault attributes characterize whether an event is a fault event. Based on the vehicle event sample set, determine the importance value of each basic evaluation indicator; The basic evaluation indicators whose importance value is greater than the preset threshold are determined to be directional evaluation indicators.

4. The method according to claim 3, characterized in that, The step of determining the importance value of each basic evaluation indicator based on the vehicle event sample set includes: Using the fault attribute corresponding to each event in the vehicle event sample set as the dependent variable and the basic evaluation index corresponding to each event in the vehicle event sample set as the independent variable, the random forest model is trained to obtain the contribution of each basic evaluation index to the random forest model. The contribution of each basic evaluation index to the random forest model is determined as the importance value of each basic evaluation index.

5. The method according to claim 1, characterized in that, After determining the directional evaluation score for each functional module, the following is also included: The directional evaluation score is provided to the target user.

6. A vehicle risk assessment device, wherein the vehicle includes at least one functional module, characterized in that, include: The data acquisition module is used to acquire events generated by the at least one functional module within a preset time interval; wherein, the events generated by the functional module are the parameter states of any parameter of the functional module with start and end times. An event filtering module is used to filter out at least one fault event from the events; wherein, a fault event is an event in which the parameter status is outside the normal parameter value range; An event determination module is used to determine at least one non-fault event that is temporally associated with the at least one fault event, wherein the at least one fault event and its corresponding non-fault event constitute a vehicle event set; wherein, the non-fault event that is temporally associated with the fault event is an event that does not constitute a fault event but occurs before or after the fault event. The indicator determination module is used to determine at least one basic evaluation indicator for each event in the vehicle event set based on the parameters corresponding to the vehicle event set; wherein, the basic evaluation indicator is a statistical parameter obtained based on at least one parameter corresponding to the event, and the parameter corresponding to the event is the parameter of the at least one functional module during the event occurrence. The indicator screening module is used to screen out directional evaluation indicators from the at least one basic evaluation indicator, wherein the directional evaluation indicator is a basic evaluation indicator used for directional evaluation of vehicle performance. The module scoring module is used to determine the orientation evaluation score of each functional module based on the orientation evaluation indicators associated with each functional module. Specifically, it acquires parameters for each functional module within the testing time interval; determines the orientation evaluation indicators corresponding to the testing time interval based on the parameters; determines the base score of the orientation evaluation indicators according to their indicator types; and calculates the orientation evaluation score of each functional module based on the base score and importance value of the orientation evaluation indicators associated with each functional module. The testing time interval is the time interval during which the vehicle's potential for malfunction needs to be detected, and the orientation evaluation score of the functional module characterizes the performance of the functional module within the testing time interval.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the vehicle risk assessment method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the vehicle risk assessment method according to any one of claims 1-5.

Images