Method and system for judging traffic accident liability and readable storage medium

Abstract

The invention provides a traffic accident liability judgment method and system and a readable storage medium. The method comprises the steps that whether a vehicle-mounted AVM function is started or not is judged according to vehicle state data; if the vehicle-mounted AVM function is started, acquiring collision intensity according to the image monitoring data and the radar ranging data; judging whether the collision intensity is greater than a first preset intensity threshold value or not; if yes, calling a vehicle movement track within a third preset time before the collision occurs, and generating at least one behavior type and a driver behavior score in one-to-one correspondence with the at least one behavior type according to the vehicle movement track; and calculating a final score according to the behavior type and the driver behavior score, and outputting a responsibility judgment result according to the final score. According to the invention, responsibility determination can be accurately and efficiently carried out on the traffic accident.

Description

Technical Field

[0001] This application relates to the field of traffic accident liability determination technology, and in particular to a method, system and readable storage medium for determining traffic accident liability. Background Technology

[0002] In the field of traffic accident liability determination, existing technologies are showing a diversified development trend. In the traditional model, traffic police rely on their professional knowledge and on-site investigation experience, combined with factors such as witness testimonies, to determine accident liability.

[0003] However, the determination of liability in traffic accidents still primarily relies on traffic police; traffic monitoring systems cannot independently make such determinations. In practice, the data collected by traffic monitoring systems often requires manual review, analysis, and judgment by traffic police. From the time an accident occurs until the police acquire and process this data and make a liability determination, there is often a significant delay. This not only consumes a considerable amount of the driver's time, leaving them waiting for extended periods and disrupting their normal life and work, but also consumes substantial human resources from the traffic police, who must dedicate time and effort to multiple stages, including accident scene investigation, data review and analysis, and communication with the driver. Furthermore, the delay in determining liability leads to vehicles remaining at the scene for extended periods, disrupting normal traffic order, causing traffic congestion, and potentially triggering secondary accidents, thus posing a greater threat to road safety. Summary of the Invention

[0004] Based on this, the purpose of this application is to propose a method, system and readable storage medium for determining liability in traffic accidents, which aims to solve the problem that relying solely on traffic police determination results in a large amount of time spent by drivers and even causes accident vehicles to remain at the scene for a long time.

[0005] Firstly, this application proposes a method for determining liability in traffic accidents, the method comprising: When the vehicle is powered on, vehicle status data is acquired every first preset time interval, and the vehicle status data is used to determine whether to enable the vehicle AVM function. If the vehicle AVM function is enabled, image monitoring data and radar ranging data will be acquired every second preset time interval, and the collision intensity will be obtained based on the image monitoring data and the radar ranging data. Determine whether the collision intensity is greater than a first preset intensity threshold; If the collision intensity is greater than the first preset intensity threshold, the vehicle movement trajectory within a third preset time before the collision occurs is retrieved, and at least one behavior type and a driver behavior score corresponding to the at least one behavior type are generated based on the vehicle movement trajectory. The final score is calculated based on the behavior type and the driver behavior score, and the liability determination result is output based on the final score.

[0006] In some embodiments, the step of acquiring vehicle status data every first preset time interval after the vehicle is powered on, and determining whether to enable the in-vehicle AVM function based on the vehicle status data, includes: The vehicle status data includes the vehicle battery voltage and current vehicle speed; Determine whether the vehicle battery voltage is within a first preset voltage range and whether the current vehicle speed is within a first preset speed range; If the vehicle battery voltage is within a first preset voltage range and the current vehicle speed is within a first preset speed range, then the in-vehicle AVM function is activated.

[0007] In some embodiments, if the in-vehicle AVM function is enabled, image monitoring data and radar ranging data are acquired every second preset time interval, and the collision intensity is obtained based on the image monitoring data and the radar ranging data; including: The degree of vehicle deformation and the range of parts scattered are extracted from the image monitoring data, and the collision duration and peak deceleration are extracted from the radar ranging data; The collision intensity is calculated using the following formula: ; in, For collision intensity, , , , All are weighting coefficients. The degree of vehicle deformation, The area where the parts were scattered. For the duration of the collision, This represents the peak deceleration.

[0008] In some embodiments, the method further includes: The collision intensity is corrected according to the following formula: ; in, The corrected collision strength. The correction factor corresponds to the collision type, which includes side impact, rear-end collision, and angled impact. This is the vehicle structural stiffness coefficient.

[0009] In some embodiments, generating at least one behavior type and a driver behavior score corresponding one-to-one with the at least one behavior type based on the vehicle's motion trajectory includes: The vehicle trajectory is defined as time series data. ,in, , , The data points are the motion data at the 1st, 2nd, and nth time points, respectively. Each data point includes the acceleration and turning angle at the corresponding time. The average acceleration, average steering angle, acceleration standard deviation, and steering angle standard deviation are calculated from the time series data. The average acceleration, average steering angle, acceleration standard deviation, and steering angle standard deviation are then input into a pre-trained LSTM model to obtain at least one behavior type and a driver behavior score corresponding to the at least one behavior type.

[0010] In some embodiments, calculating the final score based on the behavior type and the driver behavior score includes: The weights corresponding to each behavior type are retrieved from the preset database, and the final score is calculated according to the following formula: ; in, For the final score, The number of behavior types, The weight of the i-th behavior type, Rate the driver's behavior for the i-th behavior type.

[0011] In some embodiments, the step of outputting a responsibility determination result based on the final score includes: If the final score is greater than the first threshold, the driver is deemed fully responsible. If the final score is greater than the second threshold and less than or equal to the first threshold, then the driver is deemed primarily responsible. If the final score is greater than the third threshold and less than or equal to the second threshold, then the driver is deemed to be secondarily responsible. If the final score is less than the third threshold, the driver is deemed not at fault.

[0012] Secondly, this application proposes a system for determining liability in traffic accidents, the system comprising: The image function detection module is used to acquire vehicle status data every first preset time after the vehicle is powered on, and to determine whether to enable the vehicle AVM function based on the vehicle status data. The vehicle data acquisition module is used to acquire image monitoring data and radar ranging data every second preset time if the vehicle AVM function is enabled, and to obtain the collision intensity based on the image monitoring data and the radar ranging data. The collision detection module is used to determine whether the collision intensity is greater than a first preset intensity threshold. The driving behavior recognition module is used to retrieve the vehicle's trajectory within a third preset time before the collision occurs if the collision intensity is greater than a first preset intensity threshold, and generate at least one behavior type and a driver behavior score corresponding to the at least one behavior type based on the vehicle's trajectory. The accident determination module is used to calculate a final score based on the behavior type and the driver behavior score, and output the responsibility determination result based on the final score.

[0013] Thirdly, this application also provides a readable storage medium that stores one or more programs that, when executed, implement the traffic accident liability determination method described above.

[0014] Fourthly, this application also provides a computer device, the computer device including a memory and a processor, wherein: The memory is used to store computer programs; When the processor executes the computer program stored in the memory, it implements the traffic accident liability determination method described above.

[0015] Compared with the prior art, this application has the following advantages: 1. This application acquires vehicle status data at preset intervals after the vehicle is powered on to determine whether the onboard AVM function is activated. Once activated, it rapidly acquires image monitoring data and radar ranging data to calculate the collision intensity. If the collision intensity exceeds a threshold, it immediately retrieves the vehicle's pre-collision trajectory and generates a behavior type and driver behavior score, thereby quickly calculating the final score and outputting the liability determination result. Compared to existing technologies that mainly rely on traffic police and involve cumbersome processes such as on-site investigation, data collection and processing, and manual analysis and judgment, this application significantly shortens accident handling time by utilizing automated vehicle data collection and intelligent analysis, while also preventing accident vehicles from remaining at the scene for extended periods and thus preventing traffic congestion.

[0016] 2. This application, through multi-source data fusion and intelligent analysis methods, can more comprehensively and objectively reflect the true situation of the accident, fully considering various factors in the accident, thereby greatly improving the accuracy and fairness of accident liability determination. Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by means of embodiments thereof. Attached Figure Description

[0017] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart illustrating a method for determining liability in a traffic accident according to an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a traffic accident liability determination system according to an embodiment of this application.

[0018] The following detailed description, in conjunction with the accompanying drawings, will further illustrate this application. Detailed Implementation

[0019] The present application will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0020] The following detailed descriptions are exemplary and intended to provide further detailed explanation of this application. Unless otherwise specified, all technical terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application.

[0021] like Figure 1 As shown, one embodiment of this application proposes a method for determining liability in a traffic accident, the method including steps S101 to S104, wherein: Step S101: After the vehicle is powered on, vehicle status data is acquired every first preset time interval, and the vehicle status data is used to determine whether to enable the vehicle AVM function. It should be noted that after the vehicle is started (powered on), the system enters the self-test and initialization phase, at which time it begins to periodically collect vehicle status data to determine whether the on-board AVM function should be enabled.

[0022] Specifically, in some embodiments, the vehicle status data includes the vehicle battery voltage and the current vehicle speed. In actual driving scenarios, it is necessary to determine whether the vehicle battery voltage is within a first preset voltage range and whether the current vehicle speed is within a first preset speed range. If the vehicle battery voltage is within the first preset voltage range and the current vehicle speed is within the first preset speed range, then the vehicle AVM function is activated. In addition, if the vehicle AVM function is already activated at this time, then the function remains activated.

[0023] Conversely, if the vehicle battery voltage is not within the first preset voltage range, and / or the current vehicle speed is not within the first preset speed range, the vehicle AVM function will not be activated. In addition, if the vehicle AVM function is already activated at this time, the function will be deactivated.

[0024] It should be noted that in the actual judgment process, you can first check whether the vehicle battery voltage meets the conditions, and then check whether the current vehicle speed meets the conditions; or you can first check whether the current vehicle speed meets the conditions, and then check whether the vehicle battery voltage meets the conditions.

[0025] For example, if the battery voltage is between 6V and 16V and the vehicle speed is 30km / h, the AVM function is activated; otherwise, the AVM function is not activated.

[0026] In summary, by clearly defining the specific conditions for activating the in-vehicle AVM function and by judging the vehicle battery voltage and current vehicle speed, we can ensure that the AVM function is activated when the vehicle condition is suitable.

[0027] Step S102: If the vehicle AVM function is enabled, image monitoring data and radar ranging data are acquired every second preset time interval, and the collision intensity is obtained based on the image monitoring data and the radar ranging data. Once the vehicle-mounted AVM function is confirmed to be enabled, it begins to acquire image monitoring data obtained by the AVM function, while simultaneously calling up radar ranging data and unifying these two types of data to the same time reference.

[0028] Furthermore, in some embodiments, convolutional neural networks (CNNs) are used to analyze the images. CNNs, through multi-layer convolution and pooling operations, can automatically learn local and global features in image monitoring data. In vehicle collision scenarios, CNNs can identify changes in vehicle contours, displacement of body parts, etc., thereby quantifying the degree of vehicle deformation. For example, by comparing the shape changes of key vehicle parts (such as doors, hoods, etc.) before and after a collision. Furthermore, by using a CNN model, debris in the image monitoring data is detected and segmented. Using object detection algorithms (such as anchor-based methods or instance segmentation methods), debris in the image is identified, and its location and extent are determined. Then, based on the distribution of debris in the image, indicators such as the area of ​​debris scattering and the distance from the vehicle body are calculated to characterize the extent of debris scattering. This completes the extraction of the degree of vehicle deformation and the extent of parts scattering from the image monitoring data.

[0029] Furthermore, in some embodiments, since the vehicle-mounted radar continuously transmits and receives signals, the changes in signal reflection during the collision can be determined by analyzing the time-series data of the radar signals (radar ranging data). When a vehicle collides, the reflection pattern of the radar signal changes; by detecting the start and end times of this change, the collision duration can be calculated. Simultaneously, the vehicle's motion state can be deduced using the radar ranging data. According to the Doppler effect, the frequency change of the radar signal is related to the vehicle's speed. By analyzing the frequency of the radar signal, the vehicle's speed change curve is obtained, and the vehicle's deceleration can be calculated. During the collision, a peak value appears in the deceleration; by finding the maximum value in the deceleration curve, the deceleration peak value is determined. This completes the extraction of the collision duration and deceleration peak value from the radar ranging data.

[0030] More specifically, in some embodiments, the collision intensity is calculated according to the following formula: ; in, For collision intensity, , , , All are weighting coefficients. The degree of vehicle deformation, The area where the parts were scattered. For the duration of the collision, This represents the peak deceleration.

[0031] In summary, by comprehensively considering multiple factors such as the degree of vehicle deformation, the range of parts scattered, the duration of the collision, and the peak deceleration, the intensity of the collision can be assessed more comprehensively and accurately, providing a more reliable basis for subsequent liability determination.

[0032] Furthermore, in real-world driving scenarios, different collision types (such as rear-end collisions, side impacts, and angled collisions) exhibit varying degrees of damage and impact intensity to vehicles. For instance, a side impact may cause more severe structural damage than a rear-end collision, thus the correction factor for side impacts may be relatively larger. Moreover, different vehicle models have varying structural stiffness; greater stiffness allows the vehicle to withstand greater impact forces during a collision. Therefore, to ensure more accurate collision intensity assessments that adapt to different collision types and vehicle structures, in some embodiments, the collision intensity needs to be corrected according to the following formula: ; in, The corrected collision strength. The correction factor corresponds to the collision type, which includes side impact, rear-end collision, and angled impact. This is the vehicle structural stiffness coefficient.

[0033] By introducing a collision type correction factor and a vehicle structural stiffness coefficient, the collision intensity is corrected so that the final collision intensity can more accurately reflect the actual collision situation.

[0034] Step S103: Determine whether the collision intensity is greater than a first preset intensity threshold; It should be noted that if the collision intensity is less than or equal to the first preset intensity threshold, it means that no collision has occurred.

[0035] Step S104: If the collision intensity is greater than the first preset intensity threshold, retrieve the vehicle movement trajectory within a third preset time before the collision occurs, and generate at least one behavior type and a driver behavior score corresponding to the at least one behavior type based on the vehicle movement trajectory. In this step, the vehicle trajectory is first defined as time-series data. ,in, , , The data points are the motion data at the 1st, 2nd, and nth time points, respectively. Each data point includes the acceleration and turning angle at the corresponding time. The average acceleration, average steering angle, acceleration standard deviation, and steering angle standard deviation are calculated from the time series data. The average acceleration, average steering angle, acceleration standard deviation, and steering angle standard deviation are then input into a pre-trained LSTM model to obtain at least one behavior type and a driver behavior score corresponding to the at least one behavior type.

[0036] The pre-trained LSTM model is trained based on multiple historical motion trajectories. Before training, the historical motion trajectories need to be labeled with behavior type and behavior score.

[0037] In addition, in some embodiments, the behavior type is for two objects: the driver and the other party. The behavior includes speeding, changing lanes, reversing, running a red light, normal braking, emergency braking, U-turn, etc. Any combination of behavior and object constitutes the behavior type.

[0038] By defining vehicle trajectory as time series data and using an LSTM model to deeply analyze various features in the time series data, it is possible to more accurately generate behavior types and driver behavior scores, thereby improving the accuracy of driver behavior assessment.

[0039] Step S105: Calculate the final score based on the behavior type and the driver behavior score, and output the liability determination result based on the final score. Before calculating the final score, a database was pre-built, which assigned a weight to each behavior type. Subsequently, the required weights can be retrieved based on the behavior types obtained from the actual analysis.

[0040] Specifically, the weights corresponding to each behavior type are retrieved from a pre-set database, and the final score is calculated according to the following formula: ; in, For the final score, The number of behavior types, The weight of the i-th behavior type, Rate the driver's behavior for the i-th behavior type.

[0041] By comprehensively considering the impact of different types of behavior on accident liability, the final score calculation is more scientific and reasonable, and can more accurately reflect the driver's degree of responsibility in the accident.

[0042] Furthermore, in some embodiments, the process for outputting the responsibility determination result based on the final score is as follows: If the final score is greater than the first threshold, the driver is deemed fully responsible. If the final score is greater than the second threshold and less than or equal to the first threshold, then the driver is deemed primarily responsible. If the final score is greater than the third threshold and less than or equal to the second threshold, then the driver is deemed to be secondarily responsible. If the final score is less than the third threshold, the driver is deemed not at fault.

[0043] Furthermore, it should be noted that setting the first preset time and the second preset time is for real-time continuous monitoring of the current vehicle, setting the first preset intensity threshold is for determining whether a collision has occurred, and setting the first threshold, the second threshold, etc., is for accurately defining the rules for determining responsibility. The above thresholds are all related to the specific use case and are not limited in detail in this embodiment.

[0044] In summary, this application acquires vehicle status data at preset intervals after the vehicle is powered on to determine whether the onboard AVM function is activated. Once activated, it rapidly acquires image monitoring data and radar ranging data to calculate the collision intensity. If the collision intensity exceeds a threshold, it immediately retrieves the vehicle's pre-collision trajectory and generates a behavior type and driver behavior score, thereby quickly calculating the final score and outputting the liability determination result. Compared to existing technologies that mainly rely on traffic police and involve cumbersome processes such as on-site investigation, data collection and processing, and manual analysis and judgment, this application significantly shortens accident handling time by utilizing automated vehicle data collection and intelligent analysis, while also preventing accident vehicles from remaining at the scene for extended periods and thus preventing traffic congestion.

[0045] like Figure 2 As shown, one embodiment of this application proposes a system for determining liability in traffic accidents, the system comprising: The image function detection module 10 is used to acquire vehicle status data every first preset time after the vehicle is powered on, and to determine whether to enable the vehicle AVM function based on the vehicle status data. The vehicle data acquisition module 20 is used to acquire image monitoring data and radar ranging data every second preset time if the vehicle AVM function is enabled, and to obtain the collision intensity based on the image monitoring data and the radar ranging data. The collision detection module 30 is used to determine whether the collision intensity is greater than a first preset intensity threshold. The driving behavior recognition module 40 is used to retrieve the vehicle movement trajectory within a third preset time before the collision occurs if the collision intensity is greater than a first preset intensity threshold, and generate at least one behavior type and a driver behavior score corresponding to the at least one behavior type based on the vehicle movement trajectory. The accident determination module 50 is used to calculate a final score based on the behavior type and the driver behavior score, and output the responsibility determination result based on the final score.

[0046] This application also proposes a readable storage medium having one or more programs stored thereon, which, when executed by a processor, implement the aforementioned method for determining liability in traffic accidents.

[0047] This application also proposes a computer device, including a memory and a processor, wherein the memory is used to store computer programs and the processor is used to execute the computer programs stored in the memory to implement the above-mentioned method for determining liability in traffic accidents.

[0048] As is known from common technical knowledge, this application can be implemented through other embodiments that do not depart from its spirit or essential characteristics. Therefore, the disclosed embodiments described above are merely illustrative in all respects and are not the only ones. All modifications within the scope of this application or equivalent to this application are included in this application.

[0049] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0050] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0051] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0052] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and not to limit them. Although this application has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of this application. Any modifications or equivalent substitutions that do not depart from the spirit and scope of this application should be covered within the protection scope of the claims of this application.

Claims

1. A method for determining liability in a traffic accident, characterized in that, The method includes: When the vehicle is powered on, vehicle status data is acquired every first preset time interval, and the vehicle status data is used to determine whether to enable the vehicle AVM function. If the vehicle AVM function is enabled, image monitoring data and radar ranging data will be acquired every second preset time interval, and the collision intensity will be obtained based on the image monitoring data and the radar ranging data. Determine whether the collision intensity is greater than a first preset intensity threshold; If the collision intensity is greater than the first preset intensity threshold, the vehicle movement trajectory within a third preset time before the collision occurs is retrieved, and at least one behavior type and a driver behavior score corresponding to the at least one behavior type are generated based on the vehicle movement trajectory. The final score is calculated based on the behavior type and the driver behavior score, and the liability determination result is output based on the final score.

2. The method for determining liability in a traffic accident according to claim 1, characterized in that, The step of acquiring vehicle status data every first preset time interval after the vehicle is powered on, and determining whether to enable the in-vehicle AVM function based on the vehicle status data, includes: The vehicle status data includes the vehicle battery voltage and current vehicle speed; Determine whether the vehicle battery voltage is within a first preset voltage range and whether the current vehicle speed is within a first preset speed range; If the vehicle battery voltage is within a first preset voltage range and the current vehicle speed is within a first preset speed range, then the in-vehicle AVM function is activated.

3. The method for determining liability in a traffic accident according to claim 1, characterized in that, If the vehicle-mounted AVM function is enabled, image monitoring data and radar ranging data are acquired every second preset time interval, and the collision intensity is obtained based on the image monitoring data and the radar ranging data; including: The degree of vehicle deformation and the range of parts scattered are extracted from the image monitoring data, and the collision duration and peak deceleration are extracted from the radar ranging data; The collision intensity is calculated using the following formula: ； in, For collision intensity, , , , All are weighting coefficients. The degree of vehicle deformation, The area where the parts were scattered. For the duration of the collision, This represents the peak deceleration.

4. The method for determining liability in a traffic accident according to claim 3, characterized in that, The method further includes: The collision intensity is corrected according to the following formula: ； in, The corrected collision strength. The correction factor corresponds to the collision type, which includes side impact, rear-end collision, and angled impact. This is the vehicle structural stiffness coefficient.

5. The method for determining liability in a traffic accident according to claim 1, characterized in that, The step of generating at least one behavior type and a driver behavior score corresponding one-to-one with the at least one behavior type based on the vehicle's movement trajectory includes: The vehicle trajectory is defined as time series data. ,in, , , The data points are the motion data at the 1st, 2nd, and nth time points, respectively. Each data point includes the acceleration and turning angle at the corresponding time. The average acceleration, average steering angle, acceleration standard deviation, and steering angle standard deviation are calculated from the time series data. The average acceleration, average steering angle, acceleration standard deviation, and steering angle standard deviation are then input into a pre-trained LSTM model to obtain at least one behavior type and a driver behavior score corresponding to the at least one behavior type.

6. The method for determining liability in a traffic accident according to claim 5, characterized in that, The final score is calculated based on the behavior type and the driver behavior score, including: The weights corresponding to each behavior type are retrieved from the preset database, and the final score is calculated according to the following formula: ； in, For the final score, The number of behavior types, The weight of the i-th behavior type, Rate the driver's behavior for the i-th behavior type.

7. The method for determining liability in a traffic accident according to claim 1, characterized in that, The step of outputting a responsibility determination result based on the final score includes: If the final score is greater than the first threshold, the driver is deemed fully responsible. If the final score is greater than the second threshold and less than or equal to the first threshold, then the driver is deemed primarily responsible. If the final score is greater than the third threshold and less than or equal to the second threshold, then the driver is deemed to be secondarily responsible. If the final score is less than the third threshold, the driver is deemed not at fault.

8. A system for determining liability in traffic accidents, characterized in that, The system includes: The image function detection module is used to acquire vehicle status data every first preset time after the vehicle is powered on, and to determine whether to enable the vehicle AVM function based on the vehicle status data. The vehicle data acquisition module is used to acquire image monitoring data and radar ranging data every second preset time if the vehicle AVM function is enabled, and to obtain the collision intensity based on the image monitoring data and the radar ranging data. The collision detection module is used to determine whether the collision intensity is greater than a first preset intensity threshold. The driving behavior recognition module is used to retrieve the vehicle's trajectory within a third preset time before the collision occurs if the collision intensity is greater than a first preset intensity threshold, and generate at least one behavior type and a driver behavior score corresponding to the at least one behavior type based on the vehicle's trajectory. The accident determination module is used to calculate a final score based on the behavior type and the driver behavior score, and output the responsibility determination result based on the final score.

9. A readable storage medium, characterized in that, include: The readable storage medium stores one or more programs that, when executed by a processor, implement the method for determining liability in a traffic accident as described in any one of claims 1-7.

10. An electronic device, characterized in that, The electronic device includes a memory and a processor, wherein: The memory is used to store computer programs; When the processor executes the computer program stored in the memory, it implements the wireless communication method for distributed scenarios as described in any one of claims 1-7.

Images