Vehicle-mounted traffic accident rapid judgment system

Abstract

The invention discloses a vehicle-mounted traffic accident rapid determination system, and relates to the technical field of traffic management, and the system comprises a construction module which is used for determining vehicle information, collecting vehicle driving environment information in real time based on a sensor, and carrying out information fusion based on the driving environment information to construct an environment model in real time; the judgment module is connected with the construction module and is used for judging whether an accident occurs on the environment model based on machine learning and obtaining accident information when the accident occurs; and a determination module connected with the determination module and used for performing a claim settlement process according to the accident information to complete accident determination. According to the method, the distinguishing information of the comparison result is issued to the image configuration cloud at the corresponding position through the cloud server, the corresponding color blocks are changed through the image configuration cloud, updating of the color blocks is completed, then the updated fixed model is obtained, environment information can be constructed and updated better and quickly, and the user experience is improved. And subsequent analysis and judgment of vehicle accidents are facilitated.

Description

Technical Field

[0001] The invention relates to the technical field of traffic management, and in particular to a vehicle-mounted traffic accident rapid determination system. Background Art

[0002] With the rapid development of science and technology, various new technologies have been widely used in vehicle accident judgment; for example, intelligent transportation systems, vehicle-mounted sensors, image recognition technology, etc. At present, the construction of high-precision virtual environment models requires rapid processing and analysis of large amounts of complex data; existing computing platforms and algorithms often face performance bottlenecks when processing large-scale, high-dimensional data, resulting in a long model construction process and difficulty meeting real-time requirements. At the same time, the accuracy of model construction is also restricted by multiple factors such as data quality and algorithm complexity. It is difficult to maintain stable performance in complex and changing road environments, and it is difficult to quickly judge vehicle accidents based on vehicle driving conditions. Summary of the invention

[0003] The purpose of the present invention is to provide a vehicle-mounted traffic accident rapid judgment system to solve the shortcomings of the background technology.

[0004] In order to achieve the above object, the present invention provides the following technical solution: a vehicle-mounted traffic accident rapid determination system, comprising: A construction module is used to determine vehicle information, collect vehicle driving environment information in real time based on sensors, and build an environment model in real time based on information fusion based on the driving environment information; The judgment module is connected to the construction module and is used to judge whether an accident has occurred based on the environmental model based on machine learning, and obtain accident information when an accident has occurred; The determination module is connected with the judgment module and is used to complete the accident determination according to the claim settlement process based on the accident information.

[0005] In a preferred embodiment, the building blocks include: A collection unit, used to determine vehicle type information and vehicle identity information as vehicle information; A driving information collection unit, used to collect driving environment information of the vehicle in real time through sensors built into the vehicle, wherein the driving environment information includes the vehicle's surrounding environment information and the vehicle's own driving parameter information; The model building unit is used to fuse the driving environment information to build the environment model in real time, and to bind the environment model with the corresponding vehicle information.

[0006] In a preferred embodiment, the model building unit comprises: An information determination unit, used to determine the driving jurisdiction, collect fixed environment information within the driving jurisdiction, and construct a fixed model based on the fixed environment information; An updating unit, used for punctuating the fixed model to obtain fixed model points, and updating the fixed model with the vehicle surrounding environment information based on the fixed model points to obtain an updated model; The fusion unit is used to construct a vehicle model according to the vehicle's own driving parameter information, build the vehicle model in the update model to complete the fusion of driving environment information to obtain an environmental model, and bind the environmental model with the corresponding vehicle information.

[0007] In a preferred embodiment, the updating unit includes: A division unit is used to divide the range in the fixed model to obtain multiple management ranges, punctuate the multiple management ranges as range points, configure cloud servers for the range points in the multiple management ranges, and establish communication connections between the cloud servers in the multiple management ranges; A setting unit is used to respectively obtain the number of environmental subjects and the images corresponding to the environmental subjects within the multiple management ranges, set update points in the environmental subjects in the fixed model, and connect the update points to the cloud servers corresponding to the range points within the management ranges; A management unit, used to use the management range after the update point in the fixed model is connected to the cloud server corresponding to the range point as the fixed model point; The model updating unit is used to extract images from the vehicle's surrounding environment information to obtain multiple images corresponding to current environmental subjects, compare the images corresponding to the multiple current environmental subjects with the images corresponding to the environmental subjects in the corresponding fixed model to obtain a comparison result, and update the fixed model with the images corresponding to the current environmental subjects corresponding to the comparison results that do not meet preset conditions to obtain an updated model.

[0008] In a preferred embodiment, the setting unit includes: A range division unit is used to extract edge lines of the image corresponding to the environment subject, define an image frame of the image corresponding to the environment subject based on the edge lines, divide the image corresponding to the environment subject into multiple color blocks, and correspond each color block to an image configuration cloud; An image configuration unit, which is used for multiple color blocks of a single environmental subject and the image configuration cloud corresponding to the color blocks as a single update point; The connection unit is used to connect the update point with the cloud server corresponding to the scope point within the management scope.

[0009] In a preferred embodiment, the judgment module includes: A training unit is used to collect historical accident information, wherein the historical accident information includes historical driving environment information and historical accident information, and train the deep learning model through the historical accident information to obtain a trained learning model; The determination unit is used to bind the trained learning model with the environmental model, input the driving environment information in the environmental model into the trained learning model, and output the accident information of the current vehicle.

[0010] In a preferred embodiment, the determination module includes: The process setting unit is used to set up the claims process library and select the corresponding claims process according to the accident information of the current vehicle; The determination application unit is used to apply for determination of the accident information according to the claim settlement process, and store the accident information and the vehicle information corresponding to the claim settlement process.

[0011] In a preferred embodiment, the process setting unit includes: A database setting unit, used to set a claim settlement process and corresponding accident information as a claim settlement process library, wherein the claim settlement process includes a responsible party claim settlement process and a non-responsible party claim settlement process; The selection unit is used to select the corresponding claim settlement process according to the accident information of the current vehicle.

[0012] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention sends the difference information of the comparison results to the image configuration cloud at the corresponding position through the cloud server, changes the corresponding color blocks through the image configuration cloud, completes the update of the color blocks, and then obtains the updated fixed model, which can better and quickly construct and update the environmental information, and facilitates the subsequent analysis and judgment of the vehicle accident. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0014] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] Example 1, please refer to Figure 1 As shown, the vehicle-mounted traffic accident rapid determination system described in this embodiment includes: A construction module is used to determine vehicle information, collect vehicle driving environment information in real time based on sensors, and build an environment model in real time based on information fusion based on the driving environment information; Sensors are devices that interact with the external environment and can capture and transmit multi-dimensional information including road conditions, traffic flow, weather conditions, and the dynamics of other road users. By integrating multiple sensors (such as high-definition cameras, radars, lidars, ultrasonic sensors, etc.), vehicles can build a three-dimensional, comprehensive driving environment perception network, where the driving environment information collected by vehicles can be interconnected, and the collected information can be used together to build an environmental model; The judgment module is connected to the construction module and is used to judge whether an accident has occurred based on the environmental model based on machine learning, and obtain accident information when an accident has occurred; After the vehicle driving environment model is built, machine learning algorithms are introduced to deeply analyze the massive data in these models to intelligently determine whether an accident has occurred. This process not only improves the efficiency of accident judgment, but also significantly enhances the accuracy and objectivity of the judgment. The determination module is connected to the judgment module and is used to complete the accident determination by performing the claim settlement process according to the accident information; The machine learning system accurately extracts accident information from the environmental model, which becomes important information for initiating the claims process. This information not only records the specific details of the accident, but also provides a direct basis for the subsequent division of responsibilities, loss assessment and formulation of compensation plans. The first step in the claims process is to verify and organize the accident information. The claims specialist will carefully review the accident information, including the time and location of the accident, the situation of the parties involved, the degree of vehicle damage, casualties, etc., to ensure the integrity and accuracy of the information. This process may also involve communication with the parties, witnesses and on-site investigators to obtain more supplementary evidence. Then, the responsibility division stage begins. Based on the accident information, traffic rules and laws and regulations, the claims specialist will comprehensively evaluate the responsibilities of all parties and issue a responsibility determination letter. This step is the core of the claims process and is directly related to the allocation of compensation liability and the determination of the compensation amount. After the responsibility is clarified, the loss assessment and compensation calculation stage begins. The claims specialist will quantify the losses caused by the accident based on materials such as vehicle repair quotations, medical expense lists, and property loss certificates, and calculate a reasonable compensation amount based on this. Finally, the compensation plan is formulated and implemented. The claims specialist will formulate a detailed compensation plan based on the loss assessment results and the insurance company's compensation policy, and negotiate and confirm with all parties involved in the accident. Once the compensation plan is approved, the insurance company will quickly initiate the payment process to ensure that the victims can receive the compensation they deserve in a timely manner; It should be noted that with the rapid development of science and technology, various new technologies have been widely used in vehicle accident determination; for example, intelligent transportation systems, vehicle-mounted sensors, image recognition technology, etc., and currently, the construction of high-precision virtual environment models requires rapid processing and analysis of large amounts of complex data; existing computing platforms and algorithms often face performance bottlenecks when processing large-scale, high-dimensional data, resulting in a long model construction process and difficulty meeting real-time requirements. At the same time, the accuracy of model construction is also restricted by multiple factors such as data quality and algorithm complexity. It is difficult to maintain stable performance in a complex and changeable road environment, and it is difficult to quickly determine vehicle accidents based on vehicle driving conditions. In this application, the difference information of the comparison results is sent to the image configuration cloud at the corresponding location through the cloud server, and the corresponding color blocks are changed through the image configuration cloud to complete the update of the color blocks, thereby obtaining an updated fixed model, which can better quickly construct and update environmental information, and facilitate subsequent analysis and determination of vehicle accidents; In one embodiment, the building blocks include: A collection unit, used to determine vehicle type information and vehicle identity information as vehicle information; A driving information collection unit, used to collect driving environment information of the vehicle in real time through sensors built into the vehicle, wherein the driving environment information includes the vehicle's surrounding environment information and the vehicle's own driving parameter information; A model building unit, used to fuse the driving environment information to build an environment model in real time, and to bind the environment model with the corresponding vehicle information; It should be noted that each vehicle has its own vehicle information, which includes vehicle type information and vehicle identity information. The vehicle type information is the vehicle's own mechanical information such as the vehicle brand and model. After the vehicle information is determined, the vehicle's surrounding environment information and the vehicle's own driving parameter information are collected in real time through the vehicle's built-in sensors during the vehicle's driving as driving environment information. The vehicle's built-in sensors include speed sensors and acquisition devices such as radars, lidars, and cameras. For example, when there is relative motion between the radar and the target, the frequency of the echo signal received by the radar will change, and the radar's signal processing system will perform FFT (fast Fourier transform) and other processing on the received signal. The Doppler frequency is extracted and the speed of the target is calculated accordingly. Then, the environmental information around the vehicle is collected based on these collection devices. For example, the environmental information around the vehicle includes the road environment where the vehicle is located, the facilities around the road, and other vehicles and pedestrians around the vehicle. It is also necessary to collect the vehicle's own driving parameter information during driving. For example, the vehicle's own driving parameter information can be information such as the vehicle's driving speed, direction, and vehicle braking status. Multiple information related to the vehicle itself and the surrounding environment during driving can be obtained. Then, the driving environment information is fused, and a real-time environment model is constructed based on the fused driving environment information. Then, the environment model is bound to the corresponding vehicle information. In one embodiment, the model building unit includes: An information determination unit, used to determine the driving jurisdiction, collect fixed environment information within the driving jurisdiction, and construct a fixed model based on the fixed environment information; An updating unit, used for punctuating the fixed model to obtain fixed model points, and updating the fixed model with the vehicle surrounding environment information based on the fixed model points to obtain an updated model; A fusion unit is used to construct a vehicle model according to the vehicle's own driving parameter information, construct the vehicle model in the update model to complete the fusion of driving environment information to obtain an environment model, and bind the environment model with the corresponding vehicle information; It should be noted that the geographical scope for traffic accident determination is determined as the driving jurisdiction, and fixed environmental information within the driving jurisdiction is collected, wherein the fixed environmental information includes road information, road facility information and surrounding building information, which is basically fixed and unchanged. The above are all collected in the form of images, so as a fixed model, the corresponding fixed model is punctuated to obtain the fixed model point position, and the fixed model is updated with the vehicle surrounding environment information based on the fixed model point position during the vehicle driving process to obtain an updated model, which can determine the position of the vehicle and perform local updates to speed up the update efficiency. After that, a vehicle model is constructed according to the vehicle's own driving parameter information. The vehicle model is a virtual model of a vehicle shape. The specific operation is to use 3D modeling software (such as Blender, Maya, 3ds Max, etc.) to create the appearance and shape of the vehicle, including the body, wheels, lights, etc., and generate a vehicle model by defining the parameters of the vehicle (such as length, width, height, wheelbase, etc.) and rules. Then, the model of the vehicle shape is virtually driven according to the vehicle's own driving parameter information and the actual vehicle driving situation. The vehicle model is built in the update model to complete the fusion of the driving environment information to obtain the environment model. The virtually driven vehicle model is invested in the update model to obtain an environment model of virtual driving in a virtual environment. The driving environment information is well integrated through the environment model, and a virtual display can be performed by imitating the actual vehicle driving. Then, the environment model is bound to the corresponding vehicle information, which can facilitate the subsequent determination and analysis of vehicle accidents. In one embodiment, the updating unit comprises: A division unit is used to divide the range in the fixed model to obtain multiple management ranges, punctuate the multiple management ranges as range points, configure cloud servers for the range points in the multiple management ranges, and establish communication connections between the cloud servers in the multiple management ranges; A setting unit is used to respectively obtain the number of environmental subjects and the images corresponding to the environmental subjects within the multiple management ranges, set update points in the environmental subjects in the fixed model, and connect the update points to the cloud servers corresponding to the range points within the management ranges; A management unit, used to use the management range after the update point in the fixed model is connected to the cloud server corresponding to the range point as the fixed model point; A model updating unit is used to extract images from the vehicle surrounding environment information to obtain multiple images corresponding to current environment subjects, compare the images corresponding to the multiple current environment subjects with the images corresponding to the environment subjects in the corresponding fixed model to obtain a comparison result, and update the fixed model with the images corresponding to the current environment subjects corresponding to the comparison results that do not meet the preset conditions to obtain an updated model; It should be noted that in the entire driving jurisdiction, it is necessary to construct a block model. There are multiple vehicles traveling on a road. Therefore, updating the fixed model through vehicle collection is convenient for all vehicles passing through the road to use the updated model and analyze and determine subsequent accidents. The block analysis of the driving jurisdiction also requires range division in the fixed model. After dividing the fixed model, multiple management ranges of the fixed model are obtained. Then, punctuation points are used as range points in multiple management ranges. The range points here are used to manage the fixed environmental information within the management range. Then, the cloud servers are configured for the corresponding range points, and then the cloud servers are connected to communicate with each other, so that multiple management ranges can be interconnected to form a complete fixed model. Then, the environmental subject data within multiple management ranges and the corresponding images of the environmental subjects are obtained respectively. The environmental subject is the type of object in the environment, for example, the road in the fixed environmental information, the equipment around the road and other different subject types, then the corresponding image of the environmental subject can be obtained. Therefore, it is necessary to be responsible for the environmental subject within the management range through the update point, which is used for the subsequent update of the environmental subject, and then the update of the fixed model is completed. The connection between the point and the cloud server corresponding to the range point within the management range can be used to receive the part of the model that needs to be updated issued by the subsequent cloud server. Then, the management range after the update point in the fixed model is connected to the cloud server corresponding to the range point is used as the fixed model point. After setting the fixed model point, the image of the current environment subject can be extracted from the image of the vehicle's surrounding environment information actually collected by the vehicle. Then, the images corresponding to multiple current environment subjects are compared with the images corresponding to the corresponding fixed model environment subjects to obtain the comparison results. Through SIFT (scale-invariant feature transform), SURF (accelerated robust feature) and other algorithms, the images corresponding to multiple current environment subjects and the images corresponding to the corresponding fixed model environment subjects are extracted (such as edges, corners, textures, etc.), and feature matching is performed to evaluate the similarity of the images. Then, the images corresponding to the current environment subjects corresponding to the comparison results that do not meet the preset conditions are updated to the fixed model to obtain an updated model, which can better complete the update of the model. When a vehicle has an accident, the mode and characteristics of the accident can be analyzed according to the updated model, which is convenient for the judgment of the accident, making the judgment of the accident more accurate and fast; In one embodiment, the setting unit includes: A range division unit is used to extract edge lines of the image corresponding to the environment subject, define an image frame of the image corresponding to the environment subject based on the edge lines, divide the image corresponding to the environment subject into multiple color blocks, and correspond each color block to an image configuration cloud; An image configuration unit, which is used for multiple color blocks of a single environmental subject and the image configuration cloud corresponding to the color blocks as a single update point; A connection unit, used to connect the update point with a cloud server corresponding to a range point within the management range; It should be noted that the edge line of the image corresponding to the environmental subject is used as the image frame. Under the image frame, the image corresponding to the environmental subject is divided into regions to obtain multiple color blocks. One color block corresponds to an image configuration cloud, where the image configuration cloud is an image parameter library. For example, in subsequent operations, if the color block is a completely white picture and the purpose is to update it to red, then the image configuration cloud will update the corresponding color block from white to red. The multiple color blocks of a single environmental subject and the image configuration cloud corresponding to the color block are used as a single update point. There are multiple environmental subjects in a single management range of a fixed model, so there are multiple update points in a management range. Then, the update point is connected to the cloud server corresponding to the range point within the management range to receive the image update of the environmental subject corresponding to the update point by the cloud server corresponding to the subsequent range point, thereby completing the subsequent fixed model. The update module is obtained by updating the model. In the model update unit, the image in the vehicle surrounding environment information is extracted to obtain multiple images corresponding to the current environment subjects, and the images corresponding to the multiple current environment subjects are compared with the images corresponding to the environment subjects in the corresponding fixed model to obtain the comparison result, wherein the comparison result includes the difference information and the occupation range of the difference information in the actual environment, and the image corresponding to the current environment subject corresponding to the comparison result that does not meet the preset conditions is used to update the fixed model, and the preset conditions include the preset occupation range. The update method here is: the difference information of the comparison result is sent to the image configuration cloud at the corresponding position through the cloud server, and the corresponding color block is changed through the image configuration cloud to complete the update of the color block, thereby obtaining an updated fixed model, which can better quickly construct and update the environmental information, and facilitate the subsequent analysis and judgment of the vehicle accident; In one embodiment, the determination module includes: A training unit is used to collect historical accident information, wherein the historical accident information includes historical driving environment information and historical accident information, and train the deep learning model through the historical accident information to obtain a trained learning model; A determination unit, used to bind the trained learning model with the environment model, input the driving environment information in the environment model into the trained learning model, and output the accident information of the current vehicle; It should be noted that the historical accident information of all vehicles is collected, and the historical accident information includes the historical driving environment information and the historical accident information. The historical accident information includes the historical accident type and the historical accident responsibility division. The historical accident information is cleaned, the noise data, duplicate data and incomplete data are removed, and the non-numeric data is converted into numerical data, such as converting text data into numerical codes. Finally, the data is standardized or normalized to obtain the processed historical accident information. The processed data and labeled information are input into the deep learning model for training, and the hyperparameters of the model (such as learning rate, batch size, number of iterations, etc.) are tuned to obtain the trained The learning model is used to bind the trained learning model with the environment model, and the driving environment information in the environment model is input into the trained learning model to output the accident information of the current vehicle. The accident information is the accident feature information, where the accident feature information is the accident type and the accident responsibility division. The accident responsibility division is further divided into the responsible party and the non-responsible party. The damage of the vehicle can also be collected. According to the vehicle damage valuation database, the accident repair information including the valuation and maintenance cycle can be obtained. The learning model and the environment model can be combined and bound to quickly determine the vehicle accident, thereby improving the efficiency of handling vehicle accidents. In one embodiment, the determination module includes: The process setting unit is used to set up the claims process library and select the corresponding claims process according to the accident information of the current vehicle; A determination application unit is used to apply for determination of accident information according to the claim settlement process, and store the accident information and vehicle information corresponding to the claim settlement process; In one embodiment, the process setting unit includes: A database setting unit, used to set a claim settlement process and corresponding accident information as a claim settlement process library, wherein the claim settlement process includes a responsible party claim settlement process and a non-responsible party claim settlement process; A selection unit, used to select a corresponding claim settlement process according to the accident information of the current vehicle; It should be noted that this library is divided into two core parts: the responsible party claims process and the non-responsible party claims process, which aims to cover all possible accident scenarios under different liability attribution situations; the responsible party claims process focuses on guiding those car owners or insurance companies identified as the responsible party for the accident, submitting them to the insurance company for review, and then calculating and negotiating the compensation according to the insurance terms, and finally completing the compensation procedures; the non-responsible party claims process provides clear guidance for those car owners who are not involved in the accident or only bear secondary liability.

[0017] When a vehicle accident occurs, the system will quickly respond with intelligent matching and select the most suitable claims process to ensure the accuracy and efficiency of the claims process selection; the system will guide users to apply for and determine the accident information step by step according to the selected claims process, and the system will automatically or with the assistance of manual review, conduct a comprehensive assessment of the authenticity of the accident, the extent of the loss and the attribution of responsibility; in order to ensure the transparency and traceability of the claims process, all accident information and its corresponding claims process records, as well as key information involving the vehicle (such as vehicle identification code, insurance policy number, owner information, etc.) will be securely stored in the system database, building a claims process library that includes the claims processes of responsible and non-responsible parties, and realizing the application, judgment and storage of accident information through intelligent matching and guidance mechanisms, which not only improves the efficiency and accuracy of claims processing, but also provides customers with a more convenient and transparent claims service experience.

[0018] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The vehicle-mounted traffic accident rapid judgment system is characterized by: include: A construction module is used to determine vehicle information, collect vehicle driving environment information in real time based on sensors, and build an environment model in real time based on information fusion based on the driving environment information; The judgment module is connected to the construction module and is used to judge whether an accident has occurred based on the environmental model based on machine learning, and obtain accident information when an accident has occurred; The determination module is connected with the judgment module and is used to complete the accident determination according to the claim settlement process based on the accident information.

2. The vehicle-mounted traffic accident rapid determination system according to claim 1 is characterized in that: The building blocks include: A collection unit, used to determine vehicle type information and vehicle identity information as vehicle information; A driving information collection unit, used to collect driving environment information of the vehicle in real time through sensors built into the vehicle, wherein the driving environment information includes the vehicle's surrounding environment information and the vehicle's own driving parameter information; The model building unit is used to fuse the driving environment information to build the environment model in real time, and to bind the environment model with the corresponding vehicle information.

3. The vehicle-mounted traffic accident rapid determination system according to claim 2 is characterized in that: The model building unit comprises: An information determination unit, used to determine the driving jurisdiction, collect fixed environment information within the driving jurisdiction, and construct a fixed model based on the fixed environment information; An updating unit, used for punctuating the fixed model to obtain fixed model points, and updating the fixed model with the vehicle surrounding environment information based on the fixed model points to obtain an updated model; The fusion unit is used to construct a vehicle model according to the vehicle's own driving parameter information, build the vehicle model in the update model to complete the fusion of driving environment information to obtain an environmental model, and bind the environmental model with the corresponding vehicle information.

4. The vehicle-mounted traffic accident rapid determination system according to claim 3 is characterized in that: The updating unit comprises: A division unit is used to divide the range in the fixed model to obtain multiple management ranges, punctuate the multiple management ranges as range points, configure cloud servers for the range points in the multiple management ranges, and establish communication connections between the cloud servers in the multiple management ranges; A setting unit is used to respectively obtain the number of environmental subjects and the images corresponding to the environmental subjects within the multiple management ranges, set update points in the environmental subjects in the fixed model, and connect the update points to the cloud servers corresponding to the range points within the management ranges; A management unit, used to use the management range after the update point in the fixed model is connected to the cloud server corresponding to the range point as the fixed model point; The model updating unit is used to extract images from the vehicle's surrounding environment information to obtain multiple images corresponding to current environmental subjects, compare the images corresponding to the multiple current environmental subjects with the images corresponding to the environmental subjects in the corresponding fixed model to obtain a comparison result, and update the fixed model with the images corresponding to the current environmental subjects corresponding to the comparison results that do not meet preset conditions to obtain an updated model.

5. The vehicle-mounted traffic accident rapid determination system according to claim 4 is characterized in that: The setting unit comprises: A range division unit is used to extract edge lines of the image corresponding to the environment subject, define an image frame of the image corresponding to the environment subject based on the edge lines, divide the image corresponding to the environment subject into multiple color blocks, and correspond each color block to an image configuration cloud; An image configuration unit, for multiple color blocks of a single environmental subject and the image configuration cloud corresponding to the color blocks as a single update point; The connection unit is used to connect the update point with the cloud server corresponding to the scope point within the management scope.

6. The vehicle-mounted traffic accident rapid determination system according to claim 1 is characterized in that: The judging module comprises: A training unit is used to collect historical accident information, wherein the historical accident information includes historical driving environment information and historical accident information, and train the deep learning model through the historical accident information to obtain a trained learning model; The determination unit is used to bind the trained learning model with the environmental model, input the driving environment information in the environmental model into the trained learning model, and output the accident information of the current vehicle.

7. The vehicle-mounted traffic accident rapid determination system according to claim 1 is characterized in that: The determination module comprises: The process setting unit is used to set up the claims process library and select the corresponding claims process according to the accident information of the current vehicle; The determination application unit is used to apply for determination of the accident information according to the claim settlement process, and store the accident information and the vehicle information corresponding to the claim settlement process.

8. The vehicle-mounted traffic accident rapid determination system according to claim 1 is characterized in that: The process setting unit includes: A database setting unit, used to set a claim settlement process and corresponding accident information as a claim settlement process library, wherein the claim settlement process includes a responsible party claim settlement process and a non-responsible party claim settlement process; The selection unit is used to select the corresponding claim settlement process according to the accident information of the current vehicle.

Images