Vehicle driving license hierarchical management and control method and device and storage medium

Abstract

The invention discloses a vehicle driving license grading control method and device and a storage medium, and relates to the technical field of automatic driving safety certification, and the method comprises the steps: carrying out the grading test of a target vehicle according to a pre-constructed test scene library, obtaining the passing result of each scene, and calculating an original total score, the test scene library is constructed based on the real traffic characteristic data set; and when the total score reaches a qualified threshold value, determining a driving license grade and a road permission, generating an electronic driving license, binding the electronic driving license with a physical license plate, and synchronizing the electronic driving license to a traffic management platform to realize traffic management and control. According to the scheme, the vehicles are subjected to grading test through the test scene library constructed based on the real traffic characteristic data set, so that the scene coverage capability is improved; furthermore, safety capability quantification and grading are realized through total score grading, and the comprehensiveness of safety verification of the automatic driving vehicle and the precision of an evaluation result are remarkably improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving safety certification technology, and in particular to methods, equipment and storage media for vehicle driver's license classification and management. Background Technology

[0002] With the rapid development of autonomous driving technology, Robotaxi (driverless taxis) are gradually moving from the laboratory to public urban roads, and verifying their operational safety has become a core bottleneck for industrial implementation. Currently, mainstream safety verification mainly relies on scenario-based testing in closed environments (such as the scenarios recommended by ISO 21448). However, such testing lacks the challenge of combining complex dynamic elements, such as extreme situations involving temporary malfunctions, severe weather, and the simultaneous presence of malicious road users.

[0003] At the same time, existing safety certification systems (such as new vehicle evaluation procedures) have revealed their shortcomings when applied to Robotaxi, due to their reliance on a single evaluation system. These systems typically only provide a "pass / fail" conclusion, failing to quantify the vehicle's safety capability level. This results in vehicles that perform well in low-risk, high-frequency scenarios being treated the same as those that barely meet the standards in high-risk, complex scenarios, making it impossible to effectively distinguish their true safety level.

[0004] Therefore, there is an urgent need to build a new assessment and control system that can comprehensively cover complex traffic risks and achieve quantifiable and graded safety capabilities. Summary of the Invention

[0005] The main purpose of this application is to provide a method, device and storage medium for vehicle driver's license classification and management, which aims to solve the technical problems of incomplete scenario coverage and insufficient accuracy of evaluation results in the existing safety verification of autonomous vehicles.

[0006] To achieve the above objectives, this application proposes a method for graded management of vehicle driver's licenses, which includes: Based on a pre-built test scenario library, the target vehicle is subjected to graded tests to obtain the pass results of the target vehicle in each test scenario. The test scenario library is constructed based on a real traffic feature dataset. Based on the pass results of each test scenario, the original total score of the target vehicle is calculated; When the original total score reaches the preset qualification threshold, the driver's license level and road access rights of the target vehicle are determined based on the original total score; Based on the original total score, the driver's license level, and the road access rights, a corresponding electronic driver's license is generated; The electronic driver's license is bound to the physical license plate of the target vehicle, and the binding relationship is synchronized to the traffic management platform so that the traffic management platform can control the road traffic of the target vehicle.

[0007] In one embodiment, the step of performing graded tests on the target vehicle based on a pre-built test scenario library to obtain the pass results of the target vehicle in each test scenario includes: The test scenarios in the pre-built test scenario library are divided into different difficulty levels; According to the preset level progression rules and the difficulty level, the target vehicle is tested in stages to obtain the performance data of the target vehicle in each test scenario. Based on the performance data, a weighted scoring method is used to calculate the single score for each test scenario; If multiple tests are performed on the same test scenario, and at least one single score meets the preset scenario passing conditions, then the target vehicle is determined to have passed the test in the test scenario.

[0008] In one embodiment, before the step of performing graded testing on the target vehicle based on a pre-built test scenario library to obtain the test score corresponding to the target vehicle, the method further includes: Based on the accident database, meteorological model, attack vector library, and traffic flow model, basic traffic scenarios are extracted. By combining meteorological conditions and attack vectors, the basic traffic scenario is reconstructed in a multi-dimensional coupling manner through a scenario combination algorithm to generate a test scenario library.

[0009] In one embodiment, after the step of generating a test scenario library by multi-dimensional coupling reconstruction of the basic traffic scenario using a scenario combination algorithm, the method further includes: The test scenario library is updated according to a preset annual update rate.

[0010] In one embodiment, the step of calculating the target vehicle's original total score using a weighted scoring mechanism based on the pass results of each test scenario is as follows: Based on the number of test scenarios passed by the target vehicle at each difficulty level, and combined with the preset level weight coefficient, the number of scenarios passed is weighted and summed to obtain the original total score of the target vehicle.

[0011] In one embodiment, the step of determining the driver's license level and road access rights of the target vehicle based on the original total score when the original total score reaches a preset qualification threshold includes: When the original total score reaches the preset passing threshold, the target vehicle is determined to have passed the safety capability assessment, and the corresponding driver's license level is determined according to the preset score range into which the original total score falls. Based on the driver's license level, corresponding road access permissions are generated.

[0012] In one embodiment, after the step of calculating the original total score of the target vehicle based on the pass results of each test scenario, the method further includes: If the original total score does not meet the preset qualification threshold, the target vehicle is determined to have failed the safety capability assessment, and a prohibition order is generated to prohibit the target vehicle from operating on public roads.

[0013] In one embodiment, the step of binding the electronic driver's license to the physical license plate of the target vehicle and synchronizing the binding relationship with the traffic management platform so that the traffic management platform can control the road traffic of the target vehicle includes: Obtain the physical license plate and digital fingerprint of the target vehicle; Based on the physical license plate and the digital fingerprint, a vehicle identity binding record is generated, and the electronic driver's license is associated with the vehicle identity binding record; The electronic driver's license, the vehicle identity binding record, and their associations are synchronized to the traffic management platform so that the traffic management platform can allocate road rights and monitor the operating status of the target vehicle based on the vehicle identity binding record and the driver's license level and road access permissions contained in the electronic driver's license.

[0014] Furthermore, to achieve the above objectives, this application also proposes a vehicle driver's license classification and control system, which includes: The testing module is used to perform graded tests on the target vehicle based on a pre-built test scenario library, and obtain the pass results of the target vehicle in each test scenario; The calculation module is used to calculate the original total score of the target vehicle based on the pass results of each test scenario; The rating module is used to determine the driver's license level and road access rights of the target vehicle based on the original total score when the original total score reaches a preset qualification threshold. The generation module is used to generate a corresponding electronic driver's license based on the original total score, the driver's license level, and the road access rights; The synchronization module is used to bind the electronic driver's license to the physical license plate of the target vehicle and synchronize the binding relationship to the traffic management platform so that the traffic management platform can control the road traffic of the target vehicle.

[0015] In addition, to achieve the above objectives, this application also proposes a vehicle driver's license classification and control device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle driver's license classification and control method described above.

[0016] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the vehicle driver's license classification and control method described above.

[0017] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the vehicle driver's license classification and control method described above.

[0018] This application proposes a method, device, and storage medium for vehicle driver's license hierarchical management. The method includes: conducting hierarchical tests on a target vehicle based on a pre-built test scenario library to obtain the target vehicle's pass results in each test scenario, wherein the test scenario library is constructed based on a real traffic feature dataset; calculating the target vehicle's original total score based on the pass results of each test scenario; determining the target vehicle's driver's license level and road access based on the original total score when the original total score reaches a preset qualification threshold; generating a corresponding electronic driver's license based on the original total score, driver's license level, and road access; binding the electronic driver's license to the target vehicle's physical license plate, and synchronizing the binding relationship to a traffic management platform for the traffic management platform to manage the target vehicle's road access. This solution improves scenario coverage by conducting hierarchical tests on vehicles using a test scenario library constructed based on a real traffic feature dataset; furthermore, it quantifies and classifies safety capabilities through total score-based classification, significantly improving the comprehensiveness of safety verification and the accuracy of evaluation results for autonomous vehicles. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the first embodiment of the vehicle driver's license classification and control method in this application. Figure 2 This is a flowchart illustrating the interaction between the target vehicle and the testing platform provided in Embodiment 1 of this application. Figure 3 This is a schematic diagram of the electronic driver's license on-chain evidence storage process provided in Embodiment 1 of this application; Figure 4 This is a schematic diagram of the vehicle locking process provided in Embodiment 1 of this application; Figure 5 This is a flowchart illustrating the second embodiment of the vehicle driver's license classification and control method in this application. Figure 6 Flowchart for constructing the test scenario library provided in Embodiment 2 of this application; Figure 7 A simplified flowchart illustrating the vehicle driver's license classification and control method provided in Embodiment 2 of this application; Figure 8 This is a schematic diagram of the module structure of the vehicle driver's license hierarchical management system according to an embodiment of this application; Figure 9 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the vehicle driver's license hierarchical management method in this application embodiment.

[0022] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0023] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0024] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0025] The main solution of this application embodiment is as follows: Based on a pre-built test scenario library, the target vehicle is subjected to graded testing to obtain the pass results of the target vehicle in each test scenario. The test scenario library is constructed based on a real traffic feature dataset. Based on the pass results of each test scenario, the original total score of the target vehicle is calculated. When the original total score reaches a preset passing threshold, the driver's license level and road access rights of the target vehicle are determined based on the original total score. Based on the original total score, driver's license level, and road access rights, a corresponding electronic driver's license is generated. The electronic driver's license is bound to the physical license plate of the target vehicle, and the binding relationship is synchronized to the traffic management platform for the traffic management platform to control the road traffic of the target vehicle.

[0026] In this embodiment, for ease of description, the vehicle driver's license hierarchical management system will be used as the implementing entity for the following description.

[0027] The current Robotaxi security verification system has three major flaws: 1. Insufficient scenario coverage: Traditional closed-site testing mainly focuses on fixed scenarios (such as the scenarios recommended by ISO 21448), lacking challenges involving a combination of complex dynamic elements (such as temporary roadblocks, severe weather, and the simultaneous appearance of malicious traffic participants). 2. Limited Evaluation System: Existing certification systems (such as NCAP) only provide a "pass / fail" conclusion, failing to quantify vehicle safety capability levels. This leads to vehicles scoring high in low-risk scenarios being lumped together with vehicles barely meeting standards in high-risk scenarios. 3. Lagging timeliness: The driver's license test question bank has a long update cycle (usually >3 years) and cannot be updated in a timely manner to include new risk scenarios (such as drone interference and new traffic sign fraud attacks).

[0028] Furthermore, there is currently no similar solution in the industry to address the aforementioned issues.

[0029] This application provides a solution that systematically and hierarchically tests target vehicles by pre-constructing a scenario library containing multi-level test scenarios, obtaining pass results for each scenario, effectively improving the breadth and depth of test coverage, and solving the problem of insufficient scenario coverage. Simultaneously, the dynamic update mechanism of the test scenario library allows for the timely inclusion of new risk scenarios, improving the timeliness of safety verification. Furthermore, based on the pass results of each test scenario, a raw total score is calculated, and a weighted scoring mechanism is used to quantitatively assess the vehicle's safety capabilities, avoiding a "one-size-fits-all" evaluation and solving the problem of a single evaluation system. When the raw total score reaches a preset passing threshold, the corresponding driver's license level and road access rights are determined according to the preset score range into which the total score falls, achieving hierarchical mapping of capabilities and providing a basis for differentiated management. Subsequently, an electronic driver's license containing the raw total score, driver's license level, and road access rights is generated and bound to the target vehicle's physical license plate. This binding relationship is synchronized to the traffic management platform, enabling the platform to dynamically allocate road rights, monitor operation, and intercept violations based on the electronic driver's license information.

[0030] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device, vehicle-mounted computing unit, cloud server, or edge computing server capable of performing the above functions. The following description uses a cloud server deployed in an autonomous driving evaluation center as an example to illustrate this embodiment and the subsequent embodiments.

[0031] Based on this, the embodiments of this application provide a method for graded management of vehicle driver's licenses, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the vehicle driver's license classification and control method of this application.

[0032] In this embodiment, the vehicle driver's license classification and control method includes steps S10 to S50: Step S10: According to the pre-built test scenario library, the target vehicle is subjected to graded tests to obtain the passing results of the target vehicle in each test scenario. The test scenario library is constructed based on real traffic feature datasets. It should be noted that the test scenario library is a multi-level set of scenarios dynamically generated based on a real event library and attack models.

[0033] Understandably, traditional closed-site testing relies solely on static, fixed scenario templates, which are insufficient to cover the complex and ever-changing coupled risks in real traffic. This results in test results that fail to accurately reflect the vehicle's safety capabilities. Therefore, step S10 can avoid misjudgments of capabilities due to a single or outdated scenario, thereby improving the comprehensiveness, challenge, and real-world relevance of the test, and ensuring that the evaluation results effectively reflect the actual operational safety of the target vehicle in an open road environment.

[0034] In one feasible implementation, step S10 may include steps S11 to S14: Step S11: Divide the test scenarios in the pre-built test scenario library into different difficulty levels; It should be noted that the difficulty levels include basic, intermediate, and expert levels. The basic level test scenarios are designed for known but ambiguous single-factor dominant risks, with low complexity, few entities (1 to 3), and low uncertainty. They mainly cover the basic risk avoidance scenarios required by regulations and typical system failure modes, with a weighting coefficient of 1.0. Examples include sudden deceleration of the vehicle in front, sudden crossing of a pedestrian (visible), and brief instantaneous reporting by sensors. The advanced-level test scenarios focus on the known extreme multi-factor coupling risks of the system, with moderate complexity, moderate number of entities (3-5), and moderate uncertainty. They involve complex accident scenarios or known attack patterns, with a weighting coefficient of 1.2. Examples include "ghost peeking" (pedestrians rushing out from behind an obstruction), a vehicle skidding due to leakage on a highway, and identifying construction areas in rainy or foggy weather. The expert-level test scenarios are designed for extremely rare or undefined unknown-insecure scenarios. They are highly complex, involve a large number of entities (≥5), and have high uncertainty. They cover edge cases, novel attacks, and the coupled risks of multiple heterogeneous failures, with a weighting coefficient of 1.5. Examples include "triple threats" (high-speed tire blowout + backlight glare + GPS spoofing) or "perception paradox" (lidar misidentifying guardrail shadows as obstacles in dense fog, leading to false braking).

[0035] Specifically, this embodiment adopts a tiered examination model to structurally organize a pre-built test scenario library based on the risk level and technical level of the test scenarios. All test scenarios in the library are divided into three difficulty levels: Basic (B), Advanced (A), and Senior (S), and a standardized assessment question bank of 100 test levels is constructed. The Basic level has 60 questions, the Advanced level has 30 questions, and the Senior level has 10 questions, with each question worth 1 point, forming a broad-coverage, progressive, and challenging test architecture. The test scenarios cover different lighting conditions during the day (54 questions) and at night (46 questions) to ensure a comprehensive evaluation of the target vehicle's perception, decision-making, and control capabilities in all-weather operating environments.

[0036] Step S12: According to the preset level progression rules and the difficulty level, the target vehicle is tested in stages to obtain the performance data of the target vehicle in each test scenario. It should be noted that this embodiment configures the scoring logic and weighting rules through the implementation scoring module in the testing platform, and pre-loads a graded scene library containing 100 test levels. Please refer to... Figure 2 , Figure 2 This is a flowchart illustrating the interaction between the target vehicle and the test platform.

[0037] In this embodiment, the testing platform organizes the testing process according to a preset progressive ranking rule. The target vehicle must first complete 60 basic-level test stages and pass each test before proceeding to the advanced-level 30-stage test. If it needs to tackle the 10 highly challenging expert-level scenarios, it must have already passed all 90 tests in the first two levels. This mechanism ensures that vehicle capability assessment is logically progressive and rigorous, preventing low-capability vehicles from being directly exposed to extremely complex scenarios.

[0038] During the test, the test platform receives raw sensor data (such as camera, lidar, millimeter-wave radar) and execution command feedback from the vehicle in real time through the interface, and issues control commands or trigger events (such as simulated pedestrian intrusion, road construction, severe weather, etc.) to the target vehicle. It comprehensively collects the target vehicle's operational behavior data in various test scenarios, including key indicators such as whether a collision occurs, response delay, trajectory deviation, and takeover request time, forming a complete performance dataset.

[0039] Step S13: Based on the performance data, calculate the single score for each test scenario using a weighted scoring method; Specifically, the testing platform quantifies the results of each test based on a pre-set three-dimensional scoring system: Passability (weight 50%~70%): If the vehicle is involved in a collision, serious violation, or loss of control, the score for that test will be 0, triggering a "veto"; otherwise, the test will proceed to the next dimension for scoring. Response timeliness (weight 20%~30%): the lead time from the triggering of a dangerous event to the system issuing a takeover request. ≥10 seconds is full marks, and less than 10 seconds will be deducted in a linear proportion. Trajectory smoothness (weight 10%~20%): Based on the deviation between the actual driving path of the vehicle and the preset safe path calculated by the trajectory analyzer, the smaller the deviation, the higher the score.

[0040] Different difficulty levels correspond to different weight allocations, as shown in Table 1:

[0041] Table 1 Based on the above allocation of different difficulty levels and weights, the formula for calculating the score per test is as follows: Single score = Passability score × weight + Response timeliness score × weight + Trajectory smoothness score × weight; Each score is normalized and takes a value in the range [0,1], with the final score being a decimal between 0 and 1.

[0042] Step S14: Perform multiple tests on the same test scenario. If at least one single score meets the preset scenario passing conditions, then the target vehicle is determined to have passed the test in the test scenario.

[0043] In this embodiment, each test scenario is executed three times, and the system calculates the score for each of the three tests. If any score is greater than or equal to a preset passing threshold (e.g., ≥ 0.8), the scenario is considered passed and scored as 1 point; otherwise, it is considered failed and scored as 0 points. This mechanism effectively reduces the impact of accidental factors (such as instantaneous sensor interference and communication delays) on the test results, improving the stability and fairness of the evaluation. For example, in the scenario of "identifying a construction area in rainy or foggy weather," a vehicle scores 0.7, 0.85, and 0.65 in three tests, respectively. Since there is one score ≥ 0.8, it is considered to have passed and scores 1 point for this question.

[0044] Through the above steps, a systematic, quantifiable, and interference-resistant capability assessment of the target vehicle under multiple levels, environments, and rounds is achieved, providing a solid data foundation for subsequent total score calculation and driver's license level assessment. At the same time, the test scenario library is dynamically updated according to a preset annual increase of 30%, which can promptly incorporate new risk scenarios and improve the timeliness of the autonomous driving certification system.

[0045] Step S20: Calculate the original total score of the target vehicle based on the pass results of each test scenario; It should be noted that the original total score refers to the weighted cumulative score of the target vehicle across all 100 test stages, based on the number of scenarios. It reflects the vehicle's comprehensive safety capability level under scenarios of different complexity and risk levels.

[0046] Understandably, since the existing safety certification system only provides a binary conclusion of "pass / fail", it cannot distinguish the actual performance differences of vehicles in different complexity scenarios. This leads to vehicles with strong capabilities being treated the same as those that barely meet the standards. Therefore, executing step S20 can avoid the ambiguity and flattening of safety capabilities by traditional evaluation methods, thereby improving the quantitative accuracy and distinguishability of the safety level of autonomous vehicles and providing objective and comparable data support for subsequent driver's license level classification and road access permission allocation.

[0047] In one feasible embodiment, step S20 may include step S21: Step S21: Based on the number of test scenarios passed by the target vehicle at each difficulty level, and combined with the preset level weight coefficient, the number of passed scenarios is weighted and summed to obtain the original total score of the target vehicle.

[0048] It should be noted that the grade weighting coefficient refers to a weighting factor set according to the technical challenge and security risk of test scenarios at different difficulty levels, which is used to reflect the higher contribution of high-complexity scenarios to the overall score.

[0049] In this embodiment, firstly, the weighting coefficient for the basic level is assigned as 1.0, for the advanced level as 1.2, and for the expert level as 1.5. Then, the number of test scenarios actually passed by the target vehicle at each difficulty level is counted.

[0050] Based on the number of test scenarios actually passed by the target vehicle at each difficulty level and the corresponding level weight coefficient, the original total score of the target vehicle is calculated: The target vehicle's original total score = 1 * number of basic level scenarios cleared + 1.2 * number of intermediate level scenarios cleared + 1.5 * number of expert level scenarios cleared; For example, if a target vehicle passes 50 basic level, 25 advanced level, and 8 expert level scenarios, its original total score is: 50×1.0+25×1.2+8×1.5=92.

[0051] Through the above steps, based on the number of test scenarios passed by the target vehicle at each difficulty level, and combined with preset level weighting coefficients for weighted summation, the true safety performance of vehicles at different capability levels can be effectively distinguished. Compared to a simple scoring method that accumulates the number of passed scenarios, this weighting mechanism assigns higher weight to expert-level and advanced-level scenarios, highlighting the technical value of a vehicle's stable operation in highly complex, multi-factor coupled risk scenarios, and avoiding misjudgments of capability caused by relying solely on a large number of low-difficulty test scores at the basic level to "inflate the total score." Therefore, the original total score more realistically and fairly reflects the target vehicle's comprehensive coping capabilities in actual open road environments, providing a differentiated and guiding quantitative basis for subsequent driver's license level classification and road access permission configuration.

[0052] Step S30: When the original total score reaches the preset qualification threshold, determine the driver's license level and road access rights of the target vehicle based on the original total score; It should be noted that, in this embodiment, the driver's license level refers to the autonomous driving safety capability level divided based on the target vehicle's original total score, which is used to characterize its comprehensive operational capability in complex traffic environments.

[0053] The road access rights refer to the legal travel range and operating conditions of a target vehicle on actual roads, granted according to its driver's license level. These include the types of roads allowed to travel (such as ordinary urban roads, elevated roads, tunnels, and expressways), weather conditions (such as sunny days, rain, and fog), time periods (such as daytime and nighttime), traffic density levels, and specific control strategies such as whether passenger transport is permitted.

[0054] Understandably, the existing safety certification system only provides a binary result of "whether it meets the standard" and cannot reflect the differences in vehicle capabilities. This leads to vehicles operating stably in low-risk scenarios being treated the same as those operating stably in high-risk scenarios, resulting in safety hazards and lax management. Therefore, implementing step S30 can avoid resource misallocation and safety risks caused by "one-size-fits-all" management, thereby achieving refined control of capability-based authorization and graded access, and improving the safety, manageability, and road resource utilization efficiency of autonomous vehicle operation.

[0055] In one feasible embodiment, step S30 may include steps S31-S32: Step S31: When the original total score reaches the preset qualification threshold, it is determined that the target vehicle has passed the safety capability assessment, and the corresponding driver's license level is determined according to the preset score range into which the original total score falls. Specifically, this embodiment determines whether the target vehicle's original total score reaches a preset qualification threshold (e.g., 60 points). If it does, a driver's license is issued to the target vehicle, and the original total score is further mapped to a preset score range to determine its corresponding driver's license level. This embodiment divides driver's license levels into five levels, representing the actual operational capabilities of Robotaxi. Depending on the original total score and the driver's license level, the corresponding road permissions also differ.

[0056] In this embodiment, driver's license levels are divided into five levels, including: Level B (Basic): 60-70 points, possesses basic risk avoidance capabilities and can cope with common traffic scenarios; A+ level (advanced): 71–80 points, with strong environmental adaptability and able to handle multi-factor coupled scenarios; A++ level (high-order): 81–90 points, with high reliability and stable performance under complex traffic and severe weather conditions; S-level (Expert): 91–99 points, capable of handling extreme edge scenarios and operating close to all working conditions; SS-level (Excellent): 100 points, possessing the ability to operate safely and continuously in highly dynamic and uncertain environments.

[0057] In addition, if the target vehicle's original total score is lower than the preset pass threshold, the target vehicle is deemed to have failed the safety capability assessment, and a prohibition order is generated to prohibit the target vehicle from operating on public roads.

[0058] Step S32: Generate corresponding road access permissions based on the driver's license level.

[0059] In this embodiment, the system matches and generates road access permissions commensurate with the target vehicle's safety capabilities based on its driver's license level. These permissions are encapsulated in structured data, containing key elements such as permitted road type, weather conditions, time period, traffic density, and whether passenger transport is permitted. This information is used for subsequent integration with the traffic management platform and real-time control.

[0060] The mapping relationship between driver's license level and road access is shown in Table 2:

[0061] Table 2 As shown in Table 2, vehicles with a Class B driver's license can only operate during the day on roads with low complexity, and are restricted from entering high-risk areas; vehicles with a Class A+ license or above can gradually unlock more complex environments such as nighttime, highways, and severe weather; vehicles that reach Class SS can travel in all scenarios.

[0062] Through the above steps, this application achieves refined and dynamic control over the operating range of autonomous vehicles, ensuring that they always operate within their capability boundaries, effectively reducing the risk of traffic accidents and improving the safety level of public transportation.

[0063] Step S40: Generate the corresponding electronic driver's license based on the original total score, the driver's license level, and the road access rights; In this embodiment, the electronic driver's license serves as a digital authentication credential for the autonomous driving safety capabilities of the target vehicle. It is encapsulated in a structured data format (such as JSON or XML) and supports digital signatures and blockchain storage to ensure its authenticity, integrity, and immutability. The core information fields included in the electronic driver's license include, but are not limited to: vehicle identification information (license plate number, VIN code), assessment result information (original total score, number of passes at each difficulty level, assessment time, etc.), capability level information (driver's license level), road access information, validity period and status, and safety verification information.

[0064] Once the electronic driver's license is generated, it is stored in the government department through a blockchain-based evidence storage system. For example... Figure 3 As shown, Figure 3 This diagram illustrates the process of storing electronic driver's licenses on the blockchain. In this process, the decision-maker (such as an evaluation platform or certification center) packages the generated electronic driver's license data (including License_ID, VIN, issuance time, and permission information) into a transaction request and submits it to the blockchain network. After receiving the transaction, blockchain nodes (such as Node 1 and Node 2) execute a consensus mechanism to verify it. Once the data is confirmed to be legal and valid, it is broadcast and written into a block. Once verification is successful, the blockchain system returns the corresponding blockchain hash value to the decision-maker, serving as the unique proof that the electronic driver's license has been successfully stored on the blockchain.

[0065] Through the above steps, this application achieves the certability, verifiability, and traceability of the safety capabilities of autonomous vehicles, providing a standardized and executable digital carrier for subsequent binding with physical license plates and synchronization with traffic platforms.

[0066] Step S50: Bind the electronic driver's license to the physical license plate of the target vehicle, and synchronize the binding relationship to the traffic management platform so that the traffic management platform can control the road traffic of the target vehicle.

[0067] Understandably, because the evaluation results of autonomous vehicles in the current technology are disconnected from the road supervision system, there are safety hazards such as passing the evaluation but not being subject to constraints on the road or failing to meet the requirements and still violating regulations. Therefore, implementing step S50 can avoid the information gap between evaluation and certification and actual control, and improve the compliance of vehicle operation and the linkage with supervision.

[0068] In one feasible implementation, step S50 may include steps S51 to S53: Step S51: Obtain the physical license plate and digital fingerprint of the target vehicle; The physical license plate of the target vehicle is collected as a unique identifier, and the digital fingerprint of the vehicle is extracted. The digital fingerprint includes unalterable device feature information such as the hardware ID of the on-board computing unit, the serial number of the communication module, and the encrypted record fingerprint, which is used to prevent identity forgery.

[0069] Step S52: Based on the physical license plate and the digital fingerprint, generate a vehicle identity binding record and associate the electronic driver's license with the vehicle identity binding record; The system combines the physical license plate with the digital fingerprint to generate a unique vehicle identity binding record, and binds the electronic driver's license to it through digital signature technology, forming a three-in-one authentication structure of "license plate + device identity + electronic driver's license" to ensure that the electronic driver's license cannot be copied or misused.

[0070] Step S53: Synchronize the electronic driver's license, the vehicle identity binding record, and the associated relationship to the traffic management platform, so that the traffic management platform can allocate road rights and monitor the operation status of the target vehicle based on the vehicle identity binding record and the driver's license level and road access permissions contained in the electronic driver's license.

[0071] Once the electronic driver's license, vehicle identity binding records, and associated relationships are synchronized to the traffic management platform, the platform monitors the operational status of all Robotaxis on the road in real time within a city-wide area. Specifically, the platform dynamically allocates road rights based on the driver's license level in the electronic driver's license. For example, under extreme weather conditions, it automatically restricts lower-level vehicles such as B-level and A+-level vehicles from entering high-risk road sections, ensuring that vehicles only operate within their capabilities.

[0072] The Roadside Unit (RSU) scans a vehicle's physical license plate and digital fingerprint as it passes, combining this information with driver's license authorization information stored on the city's traffic management platform and blockchain, as well as real-time weather and local road conditions, to comprehensively determine whether the vehicle is permitted to pass. If a Robotaxi without a license or with inappropriate authorization is detected, the system will trigger an audible and visual warning, simultaneously deduct points from the vehicle's license, or pursue accountability from the responsible unit and issue a ticket.

[0073] For vehicles detected without a driver's license or with serious violations, the system will activate a locking mechanism. (Reference) Figure 4 , Figure 4 This is a diagram illustrating the vehicle locking process. Figure 4As shown, when the city traffic management platform identifies a Robotaxi operating without a license, exceeding its authorized permissions, or committing serious safety violations through roadside units or real-time monitoring systems, the platform will issue a remote locking command to the vehicle. Upon receiving the command, the vehicle enters MRC (Minimal Risk Condition) mode, ensuring that the vehicle stops operating within a safe and controllable range. Subsequently, the control system responds to the command by cutting off power output, causing the power system to stop working, thus physically forcing the vehicle to stop. Simultaneously, the vehicle sends a "lock confirmation" message back to the traffic management platform, completing the closed-loop control.

[0074] Through the above steps, this application achieves a trusted binding of autonomous vehicle identity information and safety capability credentials, constructing an integrated digital identity management system of "vehicle-certificate-rights". By collecting physical license plates and digital fingerprints (such as hardware IDs, encryption keys, and other device characteristics), a unique and tamper-proof vehicle identity binding record is generated, effectively preventing identity forgery and misuse of electronic driver's licenses. The electronic driver's license is associated with this binding record and synchronized to the traffic management platform, enabling the regulatory system to verify vehicle qualifications in real time. Based on this, the platform can implement refined right-of-way allocation and operational monitoring according to driver's license level and road access permissions, combined with dynamic factors such as weather and road conditions, ensuring that vehicles operate compliantly within their safety capabilities. This mechanism provides a trusted data foundation for subsequent remote supervision, violation warnings, automatic interception, and vehicle locking control measures, significantly improving the traceability, authenticability, and manageability of autonomous vehicles operating on the road.

[0075] By employing the methods described above, a scenario library containing multi-level test scenarios is pre-constructed to systematically and hierarchically test the target vehicle, obtaining the pass results for each scenario. This effectively improves the breadth and depth of test coverage, addressing the problem of insufficient scenario coverage. Furthermore, based on the pass results of each test scenario, a raw total score is calculated. A weighted scoring mechanism is used to quantitatively assess the vehicle's safety capabilities, avoiding a "one-size-fits-all" evaluation and resolving the issue of a single evaluation system. When the raw total score reaches a preset passing threshold, the corresponding driver's license level and road access rights are determined based on the preset score range into which the total score falls, achieving hierarchical mapping of capabilities and providing a basis for differentiated management. Subsequently, an electronic driver's license containing the raw total score, driver's license level, and road access rights is generated and bound to the target vehicle's physical license plate. This binding relationship is synchronized to the traffic management platform, enabling the platform to dynamically allocate road rights, monitor operations, and intercept violations based on the electronic driver's license information.

[0076] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 5Before step S10, the vehicle driver's license classification and control method further includes steps S01 to S02: Step S01: Extract basic traffic scenarios based on the accident database, the meteorological model, the attack vector library, and the traffic flow model; Step 02: Combining meteorological conditions and attack vectors, the basic traffic scenario is reconstructed in a multi-dimensional coupling manner using a scenario combination algorithm to generate a test scenario library.

[0077] It should be noted that the real traffic feature dataset in this application includes an accident database, a meteorological model, an attack vector library, and a traffic flow model; Among them, the meteorological model: based on meteorological data provided by various car manufacturers or urban transportation departments, simulates visual and sensor degradation scenarios under environmental conditions such as rain, fog, snow, and strong glare; Attack Vector Library: Covers common attack types from the OWASP TOP10 list of autonomous driving security threats, such as LiDAR spoofing, camera adversarial sample interference, GNSS signal forgery, V2X communication hijacking, etc. Traffic flow model: Based on real road network simulation or historical traffic flow data, construct traffic flow patterns with different densities, speed distributions and interactive behaviors to recreate dynamic environments such as complex intersections and congested road sections.

[0078] Understandably, existing test scenarios are mostly static and single-risk modes, which are difficult to reflect the complex working conditions of multiple factors coupled in real roads and cannot cover new safety threats, resulting in blind spots in the safety verification of autonomous vehicles. Therefore, this embodiment provides a test scenario generation method based on multi-source real data to improve the comprehensiveness and realism of the evaluation system.

[0079] Please refer to Figure 6 , Figure 6 Build a flowchart for the test scenario library. For example... Figure 6 As shown, the construction process of the test scenario library is divided into four core stages: data input layer, risk analysis module, scenario combination algorithm and dynamic question bank output.

[0080] First, at the data input layer, the system integrates real-world traffic feature data from multiple sources, including accident databases (such as C-DAS), meteorological models, attack vector libraries (such as OWASP TOP10 autonomous driving safety threats), and traffic flow models, to extract typical collision scenarios as basic traffic scenarios. These basic traffic scenarios include both publicly available accident cases and the actual operational experience accumulated by automakers, ensuring the authenticity and representativeness of the scenarios.

[0081] Subsequently, the extracted basic traffic scenarios were standardized and risk level assessed through the risk analysis module. Based on the ISO 3450x standard and industry norms, candidate scenarios with high challenge and representativeness were selected.

[0082] Next, a pre-defined scenario combination algorithm is used to couple and reconstruct basic traffic scenarios with external disturbances (such as heavy rain, dense fog, sensor spoofing, and communication hijacking) in multiple dimensions, generating composite test cases. For example, "emergency lane change" is superimposed with "LiDAR spoofing" and "low light" to form a high-order complex scenario, which is used to test the robustness and safety of vehicles under multiple disturbances.

[0083] Ultimately, the system outputs a dynamic question bank that meets the mandatory requirements of L2 / L3 level autonomous driving functions. It contains 100 graded test questions, covering safety challenges from basic to expert level. It supports continuous updates and iterations, forming a scalable, verifiable, and traceable test scenario library, providing scientific, comprehensive, and cutting-edge benchmark support for the graded evaluation of autonomous vehicles.

[0084] In addition, to ensure the innovativeness and leading edge of the tests, this embodiment dynamically updates the test scenario library with a preset annual update rate (e.g., 30%). Every year, some old scenarios are replaced and new risk scenarios generated based on real accident data and new security threats are injected to ensure that the test content continuously covers cutting-edge technological challenges and real road evolution trends, effectively improving the timeliness and foresight of the security verification system.

[0085] The above-described method integrates accident databases, meteorological models, attack vector libraries, and traffic flow models to extract real-world typical scenarios, ensuring the breadth and real-world relevance of test sources. It incorporates risk screening based on standards such as ISO 3450x to enhance the representativeness of scenarios and the scientific rigor of assessments. A scenario combination algorithm overlays multi-dimensional disturbances, such as meteorological interference and security attacks, onto the basic scenarios, generating high-order composite test cases like "heavy rain + lidar deception + pedestrian sudden appearance," significantly increasing the complexity and challenge of the tests. Finally, it outputs 100 graded test questions conforming to L2 / L3 mandatory standards, forming a scalable and updatable dynamic question bank. This method not only comprehensively covers extreme conditions in real-world roads, effectively improving the breadth, depth, and timeliness of autonomous vehicle safety verification, but also provides quantifiable and traceable technical support for capability grading assessment, promoting the refinement and intelligence of the autonomous driving certification system. Furthermore, the dynamic update mechanism of the test scenario library allows for the timely inclusion of new risk scenarios, improving the timeliness of safety verification.

[0086] For example, to help understand the implementation process of the vehicle driver's license classification and control method obtained by combining this embodiment with the above embodiment one, please refer to... Figure 7 , Figure 7A simplified flowchart of a vehicle driver's license tiered management method is provided, specifically: like Figure 7 As shown, this embodiment achieves full lifecycle Robotaxi driver's license management, from examination to supervision, through the collaborative work of ten sub-steps, thus solving the core pain points of autonomous driving safety certification. Each sub-step adopts a modular design, supporting independent upgrades and expansions, forming a complete technical closed loop.

[0087] Specifically, based on the accident database, meteorological model, attack vector library and traffic flow model, basic traffic scenarios are extracted, and multi-dimensional coupling reconstruction is performed through scenario combination algorithm to generate a dynamic test question bank containing 100 safety challenge questions.

[0088] Furthermore, the generated test scenarios are categorized into basic, intermediate, and expert levels based on difficulty, and deployed as executable test levels, supporting graded testing of target vehicles in closed venues or simulation environments.

[0089] Furthermore, the target vehicle is connected to the testing system, and its perception, decision-making, and control behavior data are uploaded to achieve real-time interaction with the testing environment.

[0090] Furthermore, based on the vehicle's performance in various test scenarios and in conjunction with preset scoring rules (such as response time, trajectory deviation, and whether a collision occurred), the raw total score is automatically calculated. It is then determined whether the raw total score reaches a passing threshold (e.g., ≥60 points). If it does, the process proceeds to the next step; otherwise, an interception mechanism is triggered.

[0091] Furthermore, key information such as test process data, original total score, and evaluation results will be stored on the blockchain to ensure that the evaluation results are tamper-proof and traceable.

[0092] Furthermore, based on the score range corresponding to the total score, an electronic driver's license is generated, which includes the original total score, driver's license level, and road access rights.

[0093] Furthermore, electronic driver's licenses will be linked to vehicle physical license plates and digital fingerprints, and the linkage will be synchronized to the traffic management platform to achieve unified management of vehicle identity and capability qualifications.

[0094] Furthermore, when a vehicle fails to meet the standards (<60 points) or engages in violations, the system automatically triggers road access interception to prevent high-risk vehicles from entering the road. Simultaneously, for vehicles without a license, using a fake license, or committing serious violations, the traffic management platform issues a remote locking command, putting the vehicle into MRC status and cutting off its power, thus physically forcing it to stop.

[0095] The above-described methods utilize a test scenario library to conduct graded tests on vehicles, improving scenario coverage; the total score-based grading system quantifies and grades safety capabilities, addressing the issue of inadequate evaluation; and the dynamic update mechanism of the test scenario library allows for the timely inclusion of new risk scenarios, enhancing the timeliness of the autonomous driving certification system.

[0096] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the vehicle driver's license classification and control method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0097] This application also provides a vehicle driver's license graded management system; please refer to [reference needed]. Figure 8 The vehicle driver's license hierarchical management system includes: The testing module 10 is used to perform graded tests on the target vehicle according to a pre-built test scenario library, and obtain the pass results of the target vehicle in each test scenario, wherein the test scenario library is constructed based on a real traffic feature dataset. The calculation module 20 is used to calculate the original total score of the target vehicle based on the pass results of each test scenario; The rating module 30 is used to determine the driver's license level and road access rights of the target vehicle based on the original total score when the original total score reaches a preset qualification threshold. The generation module 40 is used to generate a corresponding electronic driver's license based on the original total score, the driver's license level, and the road access rights; The synchronization module 50 is used to bind the electronic driver's license to the physical license plate of the target vehicle and synchronize the binding relationship to the traffic management platform so that the traffic management platform can control the road traffic of the target vehicle.

[0098] The vehicle driver's license classification and control system provided in this application, employing the vehicle driver's license classification and control method in the above embodiments, can solve the technical problem of how to improve the comprehensiveness, quantification level, and timeliness of verification of the safety capabilities of autonomous vehicles. Compared with the prior art, the beneficial effects of the vehicle driver's license classification and control system provided in this application are the same as those of the vehicle driver's license classification and control method provided in the above embodiments, and other technical features of the vehicle driver's license classification and control system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0099] This application provides a vehicle driver's license classification and control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the vehicle driver's license classification and control method in the above embodiment 1.

[0100] The following is for reference. Figure 9 The diagram illustrates a structural schematic suitable for implementing the vehicle driver's license classification and control device in the embodiments of this application. The vehicle driver's license classification and control device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 9 The vehicle driver's license classification and control device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0101] like Figure 9 As shown, the vehicle driver's license classification and control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the vehicle driver's license classification and control device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the vehicle driver's license classification and control equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figures show vehicle driver's license classification and control equipment with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0102] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0103] The vehicle driver's license classification and control device provided in this application, employing the vehicle driver's license classification and control method described in the above embodiments, can solve the technical problem of how to improve the comprehensiveness, quantification level, and timeliness of verification of the safety capabilities of autonomous vehicles. Compared with the prior art, the beneficial effects of the vehicle driver's license classification and control device provided in this application are the same as those of the vehicle driver's license classification and control method provided in the above embodiments, and other technical features in this vehicle driver's license classification and control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0104] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0105] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0106] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the vehicle driver's license classification and control method in the above embodiments.

[0107] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0108] The aforementioned computer-readable storage medium may be included in the vehicle driver's license classification and control device; or it may exist independently and not be installed in the vehicle driver's license classification and control device.

[0109] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the vehicle driver's license classification and control device, the device performs the following actions: 1. Based on a pre-built test scenario library, it conducts classification tests on the target vehicle to obtain the vehicle's pass results in each test scenario, wherein the test scenario library is constructed based on a real traffic feature dataset; 2. Based on the pass results of each test scenario, it calculates the target vehicle's original total score; 3. When the original total score reaches a preset passing threshold, it determines the target vehicle's driver's license level and road access rights based on the original total score; 4. Based on the original total score, driver's license level, and road access rights, it generates a corresponding electronic driver's license; 5. It binds the electronic driver's license to the target vehicle's physical license plate and synchronizes the binding relationship to the traffic management platform for the traffic management platform to manage the target vehicle's road access.

[0110] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0111] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0112] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0113] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-described vehicle driver's license classification and control method. This addresses the technical problem of how to improve the comprehensiveness, quantification level, and timeliness of safety capability verification for autonomous vehicles. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the vehicle driver's license classification and control method provided in the above embodiments, and will not be elaborated upon here.

[0114] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle driver's license classification and control method described above.

[0115] The computer program product provided in this application can solve the technical problem of how to improve the comprehensiveness, quantification level, and timeliness of safety capability verification for autonomous vehicles. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the vehicle driver's license classification and control method provided in the above embodiments, and will not be repeated here.

[0116] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for graded management of vehicle driver's licenses, characterized in that, The vehicle driver's license classification and control method includes: Based on a pre-built test scenario library, the target vehicle is subjected to graded tests to obtain the pass results of the target vehicle in each test scenario. The test scenario library is constructed based on a real traffic feature dataset. Based on the pass results of each test scenario, the original total score of the target vehicle is calculated; When the original total score reaches the preset qualification threshold, the driver's license level and road access rights of the target vehicle are determined based on the original total score; Based on the original total score, the driver's license level, and the road access rights, a corresponding electronic driver's license is generated; The electronic driver's license is bound to the physical license plate of the target vehicle, and the binding relationship is synchronized to the traffic management platform so that the traffic management platform can control the road traffic of the target vehicle.

2. The vehicle driver's license classification and control method as described in claim 1, characterized in that, The step of performing graded tests on the target vehicle based on a pre-built test scenario library to obtain the pass results of the target vehicle in each test scenario includes: The test scenarios in the pre-built test scenario library are divided into different difficulty levels; According to the preset level progression rules and the difficulty level, the target vehicle is tested in stages to obtain the performance data of the target vehicle in each test scenario. Based on the performance data, a weighted scoring method is used to calculate the single score for each test scenario; If multiple tests are performed on the same test scenario, and at least one single score meets the preset scenario passing conditions, then the target vehicle is determined to have passed the test in the test scenario.

3. The vehicle driver's license classification and control method as described in claim 1 or 2, characterized in that, The real traffic feature dataset includes an accident database, a meteorological model, an attack vector library, and a traffic flow model. Before the step of performing graded tests on the target vehicle based on a pre-built test scenario library to obtain the test score corresponding to the target vehicle, the method further includes: Based on the accident database, the meteorological model, the attack vector library, and the traffic flow model, basic traffic scenarios are extracted. By combining meteorological conditions and attack vectors, the basic traffic scenario is reconstructed in a multi-dimensional coupling manner through a scenario combination algorithm to generate a test scenario library.

4. The vehicle driver's license classification and control method as described in claim 3, characterized in that, After the step of generating a test scenario library by multi-dimensional coupling and reconstruction of the basic traffic scenario through a scenario combination algorithm, the method further includes: The test scenario library is updated according to a preset annual update rate.

5. The vehicle driver's license classification and control method as described in claim 2, characterized in that, The step of calculating the original total score of the target vehicle using a weighted scoring mechanism based on the pass results of each test scenario: Based on the number of test scenarios passed by the target vehicle at each difficulty level, and combined with the preset level weight coefficient, the number of scenarios passed is weighted and summed to obtain the original total score of the target vehicle.

6. The vehicle driver's license classification and control method as described in claim 1, characterized in that, The step of determining the driver's license level and road access rights of the target vehicle based on the original total score when the original total score reaches a preset qualification threshold includes: When the original total score reaches the preset passing threshold, the target vehicle is determined to have passed the safety capability assessment, and the corresponding driver's license level is determined according to the preset score range into which the original total score falls. Based on the driver's license level, corresponding road access permissions are generated.

7. The vehicle driver's license classification and control method as described in claim 1, characterized in that, After the step of calculating the original total score of the target vehicle based on the pass results of each test scenario, the method further includes: If the original total score does not meet the preset qualification threshold, the target vehicle is determined to have failed the safety capability assessment, and a prohibition order is generated to prohibit the target vehicle from operating on public roads.

8. The vehicle driver's license classification and control method as described in claim 1, characterized in that, The steps of binding the electronic driver's license to the physical license plate of the target vehicle and synchronizing the binding relationship with the traffic management platform so that the traffic management platform can control the road traffic of the target vehicle include: Obtain the physical license plate and digital fingerprint of the target vehicle; Based on the physical license plate and the digital fingerprint, a vehicle identity binding record is generated, and the electronic driver's license is associated with the vehicle identity binding record; The electronic driver's license, the vehicle identity binding record, and their associations are synchronized to the traffic management platform so that the traffic management platform can allocate road rights and monitor the operating status of the target vehicle based on the vehicle identity binding record and the driver's license level and road access permissions contained in the electronic driver's license.

9. A vehicle driver's license classification and management device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle driver's license classification and control method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the vehicle driver's license classification and control method as described in any one of claims 1 to 8.

Images