L2 + level intelligent driving evaluation analysis method, device and equipment and storage medium

Abstract

The invention discloses an L2 + level intelligent driving evaluation analysis method, device and equipment and a storage medium, and the method comprises the steps: carrying out the testing and screening of intelligent driving evaluation personnel according to the driving experience and identity labels of the intelligent driving evaluation personnel of an L2 + level intelligent driving system, obtaining target evaluation personnel, and pushing an evaluation test table to the target evaluation personnel; starting a system test of the L2 + level intelligent driving system, receiving an evaluation test result fed back by the target evaluation personnel, and performing data validity judgment on the evaluation test result to obtain effective evaluation data; and analyzing the effective evaluation data to obtain an intelligent driving comprehensive evaluation result, so that the evaluation results of different evaluation personnel can be integrated, the verification time is shortened, the effectiveness of the evaluation data is ensured, the accuracy of the test data is improved, the consistency of the data in the test process is ensured, and the speed and efficiency of L2 + level intelligent driving evaluation analysis are improved.

Description

Technical Field

[0001] The present invention relates to the field of electric vehicle technology, and in particular to an L2+ level intelligent driving evaluation and analysis method, device, equipment and storage medium. Background Art

[0002] The existing driving automation classification standard divides the driving automation level of automobiles into 6 levels, namely L0 (emergency assistance), L1 (partial driving assistance), L2 (combined driving assistance), L3 (conditional autonomous driving), L4 (highly autonomous driving), and L5 (fully autonomous driving).

[0003] At present, L0 and L1 systems are relatively mature, and L2 combined driving assistance functions have also been implemented on a large scale. More manufacturers have invested a lot of energy in the L2 and above markets. In order to make autonomous driving landed faster, the concept of L2+ has been proposed and is receiving more and more attention. While opening up a larger operating range, the driver always needs to be in the loop. There is still and will be a long time in the future for the L2 and L3 driving automation systems to be difficult to cross.

[0004] At present, few testing organizations at home and abroad have conducted systematic subjective testing and evaluation on the popular L2+ level intelligent driving system. At the same time, some organizations predict that cars with combined driving assistance functions (L2 level) and conditional automatic driving functions (L3 level) will account for more than 70% of new car production.

[0005] However, at present, these L2+ level intelligent driving systems often require a large number of objective test cases to verify their functions. The methods involved are complex, time-consuming, and the results are discontinuously distributed. For consumers, the objective data is not intuitive and has little reference value.

[0006] Moreover, when there are many models that need to be evaluated, evaluating multiple models at one time is inefficient and time-consuming. In reality, one model is often tested at intervals, which leads to the problem of inconsistent data results. Summary of the Invention

[0007] The main purpose of the present invention is to provide an L2+ level intelligent driving evaluation and analysis method, device, equipment and storage medium, aiming to solve the technical problems in the existing technology that the functional verification of the L2+ level intelligent driving system requires reliance on a large number of objective tests, has complex verification methods, high time costs, inaccurate test data, low test efficiency, and inconsistent data results.

[0008] In a first aspect, the present invention provides an L2+ intelligent driving evaluation and analysis method, the L2+ intelligent driving evaluation and analysis method comprising the following steps: Perform a test screening on the intelligent driving evaluators of the L2+ intelligent driving system based on their driving experience and identity tags, obtain target evaluators, and push the evaluation test form to the target evaluators; Initiate system testing of the L2+ intelligent driving system, receive evaluation test results fed back by the target evaluators, perform data validity judgment on the evaluation test results, and obtain valid evaluation data; Analyze the effective evaluation data to obtain a comprehensive evaluation result of intelligent driving.

[0009] Optionally, the testing and screening of intelligent driving evaluators of the L2+ intelligent driving system based on their driving experience and identity tags to obtain target evaluators, and pushing an evaluation test form to the target evaluators, includes: Obtaining the driving experience of intelligent driving evaluators of L2+ intelligent driving systems, screening the intelligent driving evaluators based on the driving experience, and obtaining experienced testers; Obtaining identity tags of the experienced testers, and classifying the experienced testers according to the identity tags to obtain professional evaluation testers, consumer users, and skilled drivers, where the skilled drivers do not overlap with the consumer users; The professional evaluation testers, consumer users and experienced drivers are used as testers in each category; According to the preset evaluation group composition ratio, corresponding testers are randomly selected from testers of each category as target evaluators, and the evaluation test form is pushed to the target evaluators.

[0010] Optionally, the step of selecting corresponding testers from testers of each category as target evaluators according to a preset evaluation group composition ratio, and pushing the evaluation test form to the target evaluators, includes: Obtain the current number of evaluators required, and select a corresponding proportion of testers from each category of testers as target evaluators based on the current number of evaluators required and the preset evaluation group composition ratio; Obtaining basic items, functional items, and overall images of different functions of the L2+ intelligent driving system, and generating an evaluation test table based on the basic items, functional items, and overall images; The evaluation test form is pushed to the target evaluator.

[0011] Optionally, obtaining basic items, functional items, and overall images of different functions of the L2+ intelligent driving system, and generating an evaluation test table based on the basic items, functional items, and overall images, includes: Obtaining a vehicle key parameter table and an equipment installation parameter table of the vehicle to be tested, and establishing a vehicle database based on the vehicle key parameter table and the equipment installation parameter table; Obtaining basic items, functional items, and overall images of different functions of the L2+ level intelligent driving system based on the vehicle database; Determine the activation mode, deactivation mode, activation mode, deactivation mode and display mode of the L2+ intelligent driving system from the basic items; Determine, from the function items, the success rate of function activation in different scenarios, the user experience during function activation, and the completeness of the display after function completion or after exiting the function; Determining the image scores of each judge for different functions from the overall image; An evaluation test table is generated according to the opening method, the closing method, the activation method, the deactivation method, the display method, the function activation success rate, the experience, the display completeness and the image score.

[0012] Optionally, starting the system test of the L2+ intelligent driving system, receiving the evaluation test results fed back by the target evaluator, and performing data validity judgment on the evaluation test results to obtain valid evaluation data include: Obtaining the perception thresholds of the target evaluators under different test environments; Obtaining test values ​​of the target evaluator in different test scenarios and at different time periods according to the perception threshold, and taking an average of the test values ​​as the expected value of the target evaluator; Initiate system testing of the L2+ intelligent driving system, receive evaluation test results fed back by the target evaluators, and obtain scoring results for each function from the evaluation test results; The scoring results of each function are compared with the corresponding expected values, and the data validity of the evaluation test results is judged based on the comparison results to obtain valid evaluation data.

[0013] Optionally, comparing the scoring results of each function with the corresponding expected values, and judging the data validity of the evaluation test results based on the comparison results to obtain valid evaluation data, includes: Compare the scoring results of each function with the corresponding expected value to obtain the comparison results; When the comparison result shows that the difference is greater than the preset difference threshold, determining that the test data of the current function is invalid; When the comparison result shows that the difference is not greater than the preset difference threshold, determining that the test data of the current function is valid; Gather all the test data of each function with valid data to generate valid evaluation data.

[0014] Optionally, analyzing the valid evaluation data to obtain a comprehensive intelligent driving evaluation result includes: The following formula is used to obtain the primary indicator weight corresponding to each test function of the L2+ level intelligent driving system and the secondary indicator weight corresponding to each auxiliary evaluation factor:

[0015]

[0016] in, is the first-level indicator weight, For the The average rating of the tested features, is the total number of test functions, is the secondary indicator weight, For the The average score of the auxiliary evaluation factors, is the total number of auxiliary evaluation factors; When there are weight tendency correlation coefficients of different evaluators among the target evaluators within a preset correlation range, the first-level indicator weight and the second-level indicator weight are recalculated according to the weight tendency value; The effective evaluation data is analyzed and the comprehensive evaluation result of intelligent driving is obtained by the following calculation formula:

[0017]

[0018] in, This is the comprehensive evaluation result of intelligent driving. For the The first-level indicator weight of each test function, For the The evaluation results of the test functions, For the The secondary indicator weights of the auxiliary evaluation factors, For each evaluator The scoring value of the auxiliary evaluation factors, is the total number of test functions, is the total number of auxiliary evaluation factors.

[0019] In a second aspect, to achieve the above-mentioned objectives, the present invention further proposes an L2+ intelligent driving evaluation and analysis device, the L2+ intelligent driving evaluation and analysis device comprising: A personnel screening module is used to test and screen intelligent driving evaluators of the L2+ intelligent driving system based on their driving experience and identity tags, obtain target evaluators, and push the evaluation test form to the target evaluators; A validity verification module is used to start the system test of the L2+ intelligent driving system, receive the evaluation test results fed back by the target evaluator, perform data validity judgment on the evaluation test results, and obtain valid evaluation data; The analysis and evaluation module is used to analyze the effective evaluation data to obtain a comprehensive evaluation result of intelligent driving.

[0020] On the third aspect, in order to achieve the above-mentioned purpose, the present invention also proposes an L2+ level intelligent driving evaluation and analysis device, which includes: a memory, a processor, and an L2+ level intelligent driving evaluation and analysis program stored on the memory and runnable on the processor, and the L2+ level intelligent driving evaluation and analysis program is configured to implement the steps of the L2+ level intelligent driving evaluation and analysis method described above.

[0021] Fourthly, in order to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which an L2+ level intelligent driving evaluation and analysis program is stored. When the L2+ level intelligent driving evaluation and analysis program is executed by a processor, the steps of the L2+ level intelligent driving evaluation and analysis method described above are implemented.

[0022] The L2+ level intelligent driving evaluation and analysis method proposed in the present invention tests and screens the intelligent driving evaluators of the L2+ level intelligent driving system according to their driving experience and identity tags, obtains target evaluators, and pushes an evaluation test form to the target evaluators; starts the system test of the L2+ level intelligent driving system, receives the evaluation test results fed back by the target evaluators, performs data validity judgment on the evaluation test results, and obtains valid evaluation data; analyzes the valid evaluation data to obtain a comprehensive intelligent driving evaluation result, which can integrate the evaluation results of different evaluators, shorten the verification time, ensure the validity of the evaluation data, improve the accuracy of the test data, ensure the consistency of the test process data, and improve the speed and efficiency of the L2+ level intelligent driving evaluation analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention; Figure 2 This is a flowchart of the first embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention; Figure 3 This is a flow chart of the second embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention; Figure 4 This is a flowchart of the third embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention; Figure 5This is a flowchart of the fourth embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention; Figure 6 This is a functional module diagram of the first embodiment of the L2+ level intelligent driving evaluation and analysis device of the present invention.

[0024] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0025] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0026] The solution of the embodiment of the present invention is mainly: by testing and screening the intelligent driving evaluators of the L2+ level intelligent driving system according to their driving experience and identity tags, the target evaluators are obtained, and the evaluation test form is pushed to the target evaluators; the system test of the L2+ level intelligent driving system is started, the evaluation test results fed back by the target evaluators are received, and the data validity judgment of the evaluation test results is performed to obtain valid evaluation data; the valid evaluation data is analyzed to obtain a comprehensive intelligent driving evaluation result, which can integrate the evaluation results of different evaluators, shorten the verification time, ensure the validity of the evaluation data, improve the accuracy of the test data, ensure the consistency of the test process data, and improve the speed and efficiency of the L2+ level intelligent driving evaluation analysis, and solve the technical problems in the existing technology that the functional verification of the L2+ level intelligent driving system needs to rely on a large number of objective tests, and there are complex verification methods, high time costs, inaccurate test data, low test efficiency, and inconsistent data results.

[0027] Reference Figure 1 , Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention.

[0028] like Figure 1 As shown, the device may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement communication between these components. The user interface 1003 may include a display and an input unit such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory, such as a disk storage. The memory 1005 may also be a storage device independent of the processor 1001.

[0029] Those skilled in the art will understand that Figure 1 The device structure shown in the figure does not constitute a limitation of the device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0030] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating device, a network communication module, a user interface module, and an L2+ level intelligent driving evaluation and analysis program.

[0031] The device of the present invention calls the L2+ level intelligent driving evaluation and analysis program stored in the memory 1005 through the processor 1001 and performs the following operations: Perform a test screening on the intelligent driving evaluators of the L2+ intelligent driving system based on their driving experience and identity tags, obtain target evaluators, and push the evaluation test form to the target evaluators; Initiate system testing of the L2+ intelligent driving system, receive evaluation test results fed back by the target evaluators, perform data validity judgment on the evaluation test results, and obtain valid evaluation data; Analyze the effective evaluation data to obtain a comprehensive evaluation result of intelligent driving.

[0032] The device of the present invention calls the L2+ level intelligent driving evaluation and analysis program stored in the memory 1005 through the processor 1001, and further performs the following operations: Obtaining the driving experience of intelligent driving evaluators of L2+ intelligent driving systems, screening the intelligent driving evaluators based on the driving experience, and obtaining experienced testers; Obtaining identity tags of the experienced testers, and classifying the experienced testers according to the identity tags to obtain professional evaluation testers, consumer users, and skilled drivers, where the skilled drivers do not overlap with the consumer users; The professional evaluation testers, consumer users and experienced drivers are used as testers in each category; According to the preset evaluation group composition ratio, corresponding testers are randomly selected from testers of each category as target evaluators, and the evaluation test form is pushed to the target evaluators.

[0033] The device of the present invention calls the L2+ level intelligent driving evaluation and analysis program stored in the memory 1005 through the processor 1001, and further performs the following operations: Obtain the current number of evaluators required, and select a corresponding proportion of testers from each category of testers as target evaluators based on the current number of evaluators required and the preset evaluation group composition ratio; Obtaining basic items, functional items, and overall images of different functions of the L2+ intelligent driving system, and generating an evaluation test table based on the basic items, functional items, and overall images; The evaluation test form is pushed to the target evaluator.

[0034] The device of the present invention calls the L2+ level intelligent driving evaluation and analysis program stored in the memory 1005 through the processor 1001, and further performs the following operations: Obtaining a vehicle key parameter table and an equipment installation parameter table of the vehicle to be tested, and establishing a vehicle database based on the vehicle key parameter table and the equipment installation parameter table; Obtaining basic items, functional items, and overall images of different functions of the L2+ level intelligent driving system based on the vehicle database; Determine the activation mode, deactivation mode, activation mode, deactivation mode and display mode of the L2+ intelligent driving system from the basic items; Determine, from the function items, the success rate of function activation in different scenarios, the user experience during function activation, and the completeness of the display after function completion or after exiting the function; Determining the image scores of each judge for different functions from the overall image; An evaluation test table is generated according to the opening method, the closing method, the activation method, the deactivation method, the display method, the function activation success rate, the experience, the display completeness and the image score.

[0035] The device of the present invention calls the L2+ level intelligent driving evaluation and analysis program stored in the memory 1005 through the processor 1001, and further performs the following operations: Obtaining the perception thresholds of the target evaluators under different test environments; Obtaining test values ​​of the target evaluator in different test scenarios and at different time periods according to the perception threshold, and taking an average of the test values ​​as the expected value of the target evaluator; Initiate system testing of the L2+ intelligent driving system, receive evaluation test results fed back by the target evaluators, and obtain scoring results for each function from the evaluation test results; The scoring results of each function are compared with the corresponding expected values, and the data validity of the evaluation test results is judged based on the comparison results to obtain valid evaluation data.

[0036] The device of the present invention calls the L2+ level intelligent driving evaluation and analysis program stored in the memory 1005 through the processor 1001, and further performs the following operations: Compare the scoring results of each function with the corresponding expected value to obtain the comparison results; When the comparison result shows that the difference is greater than the preset difference threshold, determining that the test data of the current function is invalid; When the comparison result shows that the difference is not greater than the preset difference threshold, determining that the test data of the current function is valid; Gather all the test data of each function with valid data to generate valid evaluation data.

[0037] The device of the present invention calls the L2+ level intelligent driving evaluation and analysis program stored in the memory 1005 through the processor 1001, and further performs the following operations: The following formula is used to obtain the primary indicator weight corresponding to each test function of the L2+ level intelligent driving system and the secondary indicator weight corresponding to each auxiliary evaluation factor:

[0038]

[0039] in, is the first-level indicator weight, For the The average rating of the tested features, is the total number of test functions, is the secondary indicator weight, For the The average score of the auxiliary evaluation factors, is the total number of auxiliary evaluation factors; When there are weight tendency correlation coefficients of different evaluators among the target evaluators within a preset correlation range, the first-level indicator weight and the second-level indicator weight are recalculated according to the weight tendency value; The effective evaluation data is analyzed and the comprehensive evaluation result of intelligent driving is obtained by the following calculation formula:

[0040]

[0041] in, This is the comprehensive evaluation result of intelligent driving. For the The first-level indicator weight of each test function, For the The evaluation results of the test functions, For the The secondary indicator weights of the auxiliary evaluation factors, For each evaluator The scoring value of the auxiliary evaluation factors, is the total number of test functions, is the total number of auxiliary evaluation factors.

[0042] Through the above-mentioned scheme, this embodiment tests and screens the intelligent driving evaluators of the L2+ level intelligent driving system according to their driving experience and identity tags, obtains target evaluators, and pushes an evaluation test form to the target evaluators; starts the system test of the L2+ level intelligent driving system, receives the evaluation test results fed back by the target evaluators, judges the data validity of the evaluation test results, and obtains valid evaluation data; analyzes the valid evaluation data to obtain a comprehensive intelligent driving evaluation result, which can integrate the evaluation results of different evaluators, shorten the verification time, ensure the validity of the evaluation data, improve the accuracy of the test data, ensure the consistency of the test process data, and improve the speed and efficiency of the L2+ level intelligent driving evaluation analysis.

[0043] Based on the above hardware structure, an embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention is proposed.

[0044] Reference Figure 2 , Figure 2 This is a flow chart of the first embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention.

[0045] In a first embodiment, the L2+ level intelligent driving evaluation and analysis method includes the following steps: Step S10: Test and screen the intelligent driving evaluators of the L2+ level intelligent driving system based on their driving experience and identity tags, obtain target evaluators, and push the evaluation test form to the target evaluators.

[0046] It should be noted that by testing and screening the intelligent driving evaluators of the L2+ level intelligent driving system based on their driving experience and identity tags, evaluators who meet the requirements can be obtained as target evaluators, and then the evaluation test form can be pushed to the target evaluators.

[0047] Step S20: Start the system test of the L2+ level intelligent driving system, receive the evaluation test results fed back by the target evaluator, perform data validity judgment on the evaluation test results, and obtain valid evaluation data.

[0048] It should be understood that after the evaluation test form is pushed to the target evaluator, the system test of the L2+ level intelligent driving system can be started, the evaluation test results fed back by the target evaluator can be received, and then the data validity of the evaluation test results can be judged to obtain valid evaluation data.

[0049] Step S30: Analyze the valid evaluation data to obtain a comprehensive intelligent driving evaluation result.

[0050] It can be understood that after analyzing the effective evaluation data, a comprehensive evaluation result of intelligent driving can be obtained.

[0051] Furthermore, the step S30 specifically includes the following steps: The following formula is used to obtain the primary indicator weight corresponding to each test function of the L2+ level intelligent driving system and the secondary indicator weight corresponding to each auxiliary evaluation factor:

[0052]

[0053] in, is the first-level indicator weight, For the The average score of the tested features, is the total number of test functions, is the secondary indicator weight, For the The average score of the auxiliary evaluation factors, is the total number of auxiliary evaluation factors; When there are weight tendency correlation coefficients of different evaluators among the target evaluators within a preset correlation range, the first-level indicator weight and the second-level indicator weight are recalculated according to the weight tendency value; The effective evaluation data is analyzed and the comprehensive evaluation result of intelligent driving is obtained by the following calculation formula:

[0054]

[0055] in, This is the comprehensive evaluation result of intelligent driving. For the The first-level indicator weight of each test function, For the The evaluation results of the test functions, For the The secondary indicator weights of the auxiliary evaluation factors, For each evaluator The scoring value of the auxiliary evaluation factors, is the total number of test functions, is the total number of auxiliary evaluation factors.

[0056] It can be understood that by screening evaluators, testing and evaluating the evaluators' own driving habits and driving needs, and then comparing the evaluators' evaluation results of the intelligent driving system with their own driving habits, we can obtain the relatively objective subjective evaluation results of the person, and statistically process the evaluation results of multiple evaluators of different types to obtain the evaluation results of the intelligent driving system.

[0057] In the specific implementation, each score is scored based on the rating scale recommended by SAE J1441_201609 for the subjective evaluation of vehicle driving and handling, with applicable changes made. Through the use of positive and negative scores, evaluators can more simply and directly judge the gap between each scoring point and their own expectations.

[0058]

[0059] Before the test officially begins, the test evaluates the evaluator's perception threshold. Without turning on any functions, the evaluator is asked to drive by himself. Dynamic data detection equipment is used to measure each evaluator's driving comfort following distance, target response distance, braking deceleration and braking distance, deceleration of the vehicle after the front vehicle cuts in, acceleration of the vehicle after the front vehicle cuts out, driving speed in response to speed limit signs, lateral acceleration, vehicle neutrality, speed on speed bumps, obstacle handling strategy and lateral acceleration, parking speed, number of steering wheel turns on the spot and number of steering wheel rubbing. These data include natural language descriptions and objective data. The correspondence between the simplified functions and evaluation factors is shown in Table 1.

[0060] Table 1 Correspondence between functions and evaluation factors

[0061] Due to the particularity of the L2+ intelligent driving system, functions and scenarios are combined, and continuous scenarios are built based on the functions. Different from the intelligent driving system tests below the L2+ level, the continuous scenario test is comprehensive and is generally divided into two major functions: driving and parking, corresponding to the two major scenarios of roads and parking lots, as shown in Table 2.

[0062] Table 2 Correspondence between functions and test scenarios

[0063] The scenario contains a variety of scenario elements. Important scenario elements are selected to correspond to the functional test scenarios, as shown in Table 3.

[0064] Table 3 Correspondence between scenes and scene elements

[0065] It should be noted that AEB (Autonomous Emergency Braking) is an active automotive safety technology that uses the vehicle's sensors to monitor road conditions ahead. When a possible collision is detected, the system automatically triggers the brakes to reduce or avoid the severity of the collision.

[0066] ACC: Adaptive Cruise Control; this system can automatically adjust the vehicle's speed according to the speed and distance of the vehicle in front, maintain a safe following distance, realize automatic following driving, and reduce the driver's fatigue during long-distance driving or traffic jams.

[0067] LCC: Lane Centering Control; it can identify lane lines through cameras, sensors and other equipment, automatically control the vehicle to drive in the center of the lane, keep the vehicle at an equal distance from the lane lines on both sides, and improve driving safety and comfort.

[0068] TJA&ICA: TJA stands for Traffic Jam Assist. It generally operates in the 0-60km / h speed range and provides the driver with longitudinal and lateral assistance in traffic jams. Longitudinal assistance is provided by the ACC system, while lateral assistance keeps the vehicle within the lane when there are lane markings, and moves laterally with the vehicle ahead when there are no lane markings.

[0069] ICA: Integrated Cruise Assist; operates at speeds above 60 km / h, providing the driver with longitudinal and lateral assistance. Longitudinal assistance is also provided by the ACC system, while lateral assistance always keeps the vehicle near the center of the lane and does not have the function of following a vehicle when there are no lane lines.

[0070] NOA: Navigate on Autopilot, urban navigation-assisted driving; it is the application of intelligent driving technology in urban road environments. Based on the navigation route, it realizes automatic lane changing, following vehicles, passing intersections and other functions on urban roads, providing users with a more convenient driving experience.

[0071] APA&RCP: APA: Analytic Process Automation; it revolves around three elements: data, processes, and people. It integrates different data sources, operations, and business knowledge into an end-to-end automation platform, focusing on realizing business value. It can perform overall optimization for different business scenarios such as customer profiling and audit processes to improve enterprise operating efficiency.

[0072] Rapid Control Prototyping is a technology that verifies and optimizes control algorithms by quickly building prototypes of control systems. It can use simulation tools and rapid prototyping platforms to quickly implement control logic before actual hardware system development, shortening the development cycle and reducing costs.

[0073] AVP: Automated Valet Parking; the vehicle can autonomously find a parking space and complete the parking process in an environment such as a parking lot without the need for direct driver operation.

[0074] In the specific implementation, the expert database assigns weights to each function, i.e., the first-level indicator, and the evaluation factor, i.e., the second-level indicator. The maximum score for each indicator is 10 points, and the minimum score is accurate to 0.1 points. Experts need to score based on the importance of the indicator and the degree of expected achievement, so as to obtain the weights of the function (first-level indicator) and the evaluation factor (second-level indicator). The average score of the expert database for the first-level indicator and the second-level indicator is calculated to obtain 、 Assuming that there are m first-level indicators and n second-level indicators, the weight of each first-level indicator is k. Similarly, the weight of each second-level indicator is As the above formula.

[0075] After determining the basic weights of the primary and secondary indicators, we make minor adjustments based on the number of users in each test. Users also use a 10-point scale, with a minimum accuracy of 0.1 points, to score the primary and secondary indicators. Each test will yield five groups of user weight tendency values. The expert database weight tendency value is set as x, and the user group weight tendency value is set as y. The correlation coefficient is used to calculate the correlation between the expert weight tendency and the user weight tendency: Correlation coefficient:

[0076] If the correlation coefficient is 0.8≤|r|≤1, it is considered a strong correlation. Then the user group weight tendency value is added to the expert group weight tendency value, and k and q are recalculated to obtain a new weight distribution. For the The expert database weight tendency value of the test, For the The user group weight tendency value of the test, is the mean weighted tendency value of the expert database, is the mean weighted propensity value of the user group.

[0077] Through the above-mentioned scheme, this embodiment tests and screens the intelligent driving evaluators of the L2+ level intelligent driving system according to their driving experience and identity tags, obtains target evaluators, and pushes an evaluation test form to the target evaluators; starts the system test of the L2+ level intelligent driving system, receives the evaluation test results fed back by the target evaluators, judges the data validity of the evaluation test results, and obtains valid evaluation data; analyzes the valid evaluation data to obtain a comprehensive intelligent driving evaluation result, which can integrate the evaluation results of different evaluators, shorten the verification time, ensure the validity of the evaluation data, improve the accuracy of the test data, ensure the consistency of the test process data, and improve the speed and efficiency of the L2+ level intelligent driving evaluation analysis.

[0078] Furthermore, Figure 3 This is a flow chart of the second embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention. Figure 3 As shown, a second embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention is proposed based on the first embodiment. In this embodiment, step S10 specifically includes the following steps: Step S11: Obtain the driving experience of intelligent driving evaluators of the L2+ level intelligent driving system, and screen the intelligent driving evaluators based on the driving experience to obtain experienced testers.

[0079] It should be noted that after obtaining the driving experience of the intelligent driving evaluators of the L2+ level intelligent driving system, the intelligent driving evaluators can be screened based on the driving experience, and experienced testers can be selected from the intelligent driving evaluators.

[0080] In the specific implementation, the testers' driving experience is taken into consideration and the drivers are divided into "experienced testers", "key testers", "certain testers", "most testers" and "all testers" (the affiliation is from the front to the back).

[0081] Step S12: obtaining identity tags of the experienced testers, classifying the experienced testers according to the identity tags, and obtaining professional evaluation testers, consumer users and skilled drivers, wherein the skilled drivers do not overlap with the consumer users.

[0082] It can be understood that the experienced testers have identity tags corresponding to different tester identities. According to the identity tags, the experienced testers can be classified to obtain professional evaluation testers, consumer users and skilled drivers, and the skilled drivers do not overlap with the consumer users.

[0083] Step S13: The professional evaluation testers, consumer users and skilled drivers are used as testers in different categories.

[0084] It should be understood that after obtaining various types of testers, the professional evaluation testers, consumer users and skilled drivers can be used as testers in each category.

[0085] In specific implementation, evaluators can be divided into three categories. The first category is professionals, namely professional evaluation testers. The evaluation criteria are that they have studied the intelligent connected industry for at least 3 years and have evaluated at least 10 intelligent connected vehicles. The second category is users, namely consumer users. Three types of users are selected: consumers who already have intelligent connected vehicles, potential consumers who have purchasing intentions for intelligent connected vehicles, and car bloggers who have a better understanding of intelligent connected vehicles. The third category is skilled drivers. Considering the correlation between driving experience and traffic accidents, drivers with at least 3 years of actual driving experience are selected. This type of personnel does not overlap with the second category of evaluators.

[0086] Step S14: Select corresponding testers from each category of testers as target evaluators according to the preset evaluation group composition ratio, and push the evaluation test form to the target evaluators.

[0087] It should be noted that, by using the pre-set evaluation group composition ratio, corresponding testers can be selected from each category of testers as target evaluators, and then the evaluation test form can be pushed to the target evaluators.

[0088] In specific implementation, after obtaining professionals, an expert database can be established, and 5 people are randomly selected from the expert database each time. However, the experts selected in each round of testing must participate in at least 2 subjective evaluations of smart driving cars. For consumers who have purchased the vehicle to be evaluated, questionnaires are sent out for investigation to avoid insensitivity to vehicle performance caused by being too familiar with the vehicle, and questionnaires are used only for key issues. Taking a 10-person evaluation group as an example, three types of evaluators can be used to form a 10-person evaluation group, consisting of 5 professionals, 3 users, and 2 skilled drivers.

[0089] Through the above scheme, this embodiment obtains the driving experience of the intelligent driving evaluators of the L2+ level intelligent driving system, screens the intelligent driving evaluators according to the driving experience, and obtains experienced testers; obtains the identity tags of the experienced testers, classifies the experienced testers according to the identity tags, and obtains professional evaluation testers, consumer users and skilled drivers, and the skilled drivers do not overlap with the consumer users; the professional evaluation testers, consumer users and skilled drivers are used as testers of each category; according to the preset evaluation group composition ratio, corresponding testers are selected from the testers of each category as target evaluators, and the evaluation test form is pushed to the target evaluators, which can quickly determine the target evaluators, improve the accuracy of the test data, and improve the speed and efficiency of the L2+ level intelligent driving evaluation analysis.

[0090] Furthermore, Figure 4 This is a flow chart of the third embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention. Figure 4 As shown, a third embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention is proposed based on the second embodiment. In this embodiment, step S14 specifically includes the following steps: Step S141: Obtain the current number of evaluators required, and select a corresponding proportion of testers from each category of testers as target evaluators based on the current number of evaluators required and the preset evaluation group composition ratio.

[0091] It should be noted that different requirements correspond to different total number of testers. After obtaining the current number of testers required, a corresponding proportion of testers can be selected from each category of testers as target evaluators based on the current number of testers required and the preset evaluation group composition ratio.

[0092] In specific implementation, the evaluation levels can be divided into "acceptable" (6 to 10 points), "critical value" (5 points) and "unacceptable" (1 to 4 points), and the maximum standard principle can be adopted to screen the evaluators through this method, and the test results can be assigned corresponding scores to form the final test results.

[0093] Step S142: Obtain the basic items, functional items, and overall images of different functions of the L2+ level intelligent driving system, and generate an evaluation test table based on the basic items, functional items, and overall images.

[0094] It can be understood that the evaluation test table can be divided according to different functions. Different functions correspond to basic items, functional items and overall images, and the evaluation test table is generated according to the basic items, functional items and overall images.

[0095] Furthermore, the step S142 specifically includes the following steps: Obtaining a vehicle key parameter table and an equipment installation parameter table of the vehicle to be tested, and establishing a vehicle database based on the vehicle key parameter table and the equipment installation parameter table; Obtaining basic items, functional items, and overall images of different functions of the L2+ level intelligent driving system based on the vehicle database; Determine the activation mode, deactivation mode, activation mode, deactivation mode and display mode of the L2+ intelligent driving system from the basic items; Determine, from the function items, the success rate of function activation in different scenarios, the user experience during function activation, and the completeness of the display after function completion or after exiting the function; Determining the image scores of each judge for different functions from the overall image; An evaluation test table is generated according to the opening method, the closing method, the activation method, the deactivation method, the display method, the function activation success rate, the experience, the display completeness and the image score.

[0096] It should be noted that the vehicle key parameter table and equipment installation parameter table can be queried and filled in before each vehicle model test. For the vehicle database and the equipment installation for objective testing, the equipment installation position for each scenario test remains consistent. Generally, the relative position of the equipment used (inertial navigation system, camera, etc.) is filled in and confirmed before the test.

[0097] It can be understood that the table content of each function is divided according to different functions and is composed of basic items + functional items + overall impression.

[0098] In specific implementation, the main examination points of the basic items are: the system's opening, closing, activation, and deactivation methods, and the display method. The evaluation focus of each system in the functional items is different, which can be basically summarized as the function activation success rate in different scenarios, the experience during function activation (including human-computer interaction experience and driving experience), and the display completeness after the function is completed or exited. The overall impression score is the judges' overall impression of the function.

[0099] Step S143: Push the evaluation test form to the target evaluator.

[0100] It should be understood that after the target evaluators are determined, the evaluation test form can be pushed.

[0101] Through the above scheme, this embodiment obtains the current number of evaluators required, and selects a corresponding proportion of testers from each category of testers as target evaluators according to the current number of evaluators required and the preset evaluation group composition ratio; obtains the basic items, functional items and overall images of different functions of the L2+ level intelligent driving system, and generates an evaluation test form based on the basic items, functional items and overall image; pushes the evaluation test form to the target evaluators; can quickly determine the target evaluators, improve the accuracy of the test data, and improve the speed and efficiency of the L2+ level intelligent driving evaluation analysis.

[0102] Furthermore, Figure 5 This is a flow chart of the fourth embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention. Figure 5 As shown, a fourth embodiment of the L2+ level intelligent driving evaluation and analysis method of the present invention is proposed based on the first embodiment. In this embodiment, step S20 specifically includes the following steps: Step S21: Obtain the perception threshold of the target evaluator under different test environments.

[0103] It should be noted that the perception thresholds of the target evaluators in different test environments were obtained. The same intensity in different environments may not necessarily result in the perception of the same stimulus, and different testers have different perception thresholds.

[0104] Step S22: obtaining the test values ​​of the target evaluator in different test scenarios and different time periods according to the perception threshold, and taking the average of the test values ​​as the expected value of the target evaluator.

[0105] It is understandable that, based on the perception threshold, the test values ​​of the target evaluator in different test scenarios and different time periods can be obtained, and then the average of the test values ​​can be used as the expected value of the target evaluator.

[0106] Step S23: Start the system test of the L2+ level intelligent driving system, receive the evaluation test results fed back by the target evaluator, and obtain the scoring results of each function from the evaluation test results.

[0107] It should be understood that after the system test of the L2+ level intelligent driving system is started, the evaluation test results fed back by the target evaluators can be received, and then the scoring results of each function can be obtained from the evaluation test results.

[0108] Step S24: Compare the scoring results of each function with the corresponding expected values, and perform data validity judgment on the evaluation test results based on the comparison results to obtain valid evaluation data.

[0109] It is understandable that after comparing the scoring results of each function with the corresponding expected value, the data validity of the evaluation test results can be determined based on the comparison results to obtain valid evaluation data.

[0110] In specific implementation, before testing each vehicle, the evaluator can be tested first to obtain his or her perception threshold in a fixed test environment (perception threshold: the same intensity in different environments may not necessarily result in the perception of the same stimulus, and different testers have different perception thresholds), such as following distance, emergency deceleration, etc. In the same scenario, multiple tests are conducted in different time periods (morning, noon, and afternoon) and the average is taken as the evaluator's expected value; the subsequent score given by the evaluator to the vehicle is compared with his or her expected value under this parameter to confirm the accuracy of the score.

[0111] Furthermore, the step S24 specifically includes the following steps: Compare the scoring results of each function with the corresponding expected value to obtain the comparison results; When the comparison result shows that the difference is greater than the preset difference threshold, determining that the test data of the current function is invalid; When the comparison result shows that the difference is not greater than the preset difference threshold, determining that the test data of the current function is valid; Gather all the test data of each function with valid data to generate valid evaluation data.

[0112] It should be understood that by comparing the scoring results of each function with the corresponding expected value, when the comparison result is that the difference between the two is greater than the preset difference threshold, it can be determined that the test data of the current function is invalid; when the comparison result is that the difference is not greater than the preset difference threshold, it can be determined that the test data of the current function is valid, and then the test data of all functions with valid data are summarized to generate valid evaluation data.

[0113] In the specific implementation, the key scoring indicators are compared with the perception values ​​of each tester obtained from the test. In the objective data, if the indicator values ​​are similar but the score is lower than +2 points, the scoring result is considered inaccurate. If the indicator values ​​are far apart but the score is higher than +2 points, the result is also considered inaccurate. In the natural language description, if the vehicle behavior and the tester behavior appear consistent but the score is lower than +2 points, the scoring result is considered inaccurate. If they are inconsistent, the vehicle behavior and the human driver behavior are considered to have similarities and differences, and the data is considered valid. If the tester has additional explanations for the scoring results, the validity judgment in 1) can be skipped, and the entire group of testers will discuss and confirm whether to retain the data.

[0114] This embodiment adopts the above scheme, by obtaining the perception threshold of the target evaluator in different test environments; obtaining the test values ​​of the target evaluator in different test scenarios and different time periods according to the perception threshold, and taking the average of the test values ​​as the expected value of the target evaluator; starting the system test of the L2+ level intelligent driving system, receiving the evaluation test results fed back by the target evaluator, and obtaining the scoring results of each function from the evaluation test results; comparing the scoring results of each function with the corresponding expected value, and judging the data validity of the evaluation test results according to the comparison results to obtain valid evaluation data; being able to quickly obtain valid evaluation data, shortening the verification time, ensuring the validity of the evaluation data, improving the accuracy of the test data, and improving the speed and efficiency of the L2+ level intelligent driving evaluation analysis.

[0115] Accordingly, the present invention further provides an L2+ level intelligent driving evaluation and analysis device.

[0116] Reference Figure 6 , Figure 6 This is a functional module diagram of the first embodiment of the L2+ level intelligent driving evaluation and analysis device of the present invention.

[0117] In a first embodiment of the L2+ intelligent driving evaluation and analysis device of the present invention, the L2+ intelligent driving evaluation and analysis device includes: The personnel screening module 10 is used to test and screen the intelligent driving evaluators of the L2+ level intelligent driving system based on their driving experience and identity tags, obtain target evaluators, and push the evaluation test form to the target evaluators.

[0118] The validity verification module 20 is used to start the system test of the L2+ level intelligent driving system, receive the evaluation test results fed back by the target evaluator, perform data validity judgment on the evaluation test results, and obtain valid evaluation data.

[0119] The analysis and evaluation module 30 is used to analyze the effective evaluation data to obtain a comprehensive evaluation result of intelligent driving.

[0120] The personnel screening module 10 is also used to obtain the driving experience of the intelligent driving evaluators of the L2+ level intelligent driving system, screen the intelligent driving evaluators according to the driving experience, and obtain experienced testers; obtain the identity tags of the experienced testers, classify the experienced testers according to the identity tags, and obtain professional evaluation testers, consumer users and skilled drivers, and the skilled drivers do not overlap with the consumer users; the professional evaluation testers, consumer users and skilled drivers are regarded as testers of each category; according to the preset evaluation group composition ratio, corresponding testers are selected from the testers of each category as target evaluators, and the evaluation test form is pushed to the target evaluators.

[0121] The personnel screening module 10 is also used to obtain the current number of evaluators required, and select a corresponding proportion of testers from each category of testers as target evaluators based on the current number of evaluators required and the preset evaluation group composition ratio; obtain the basic items, functional items and overall images of different functions of the L2+ level intelligent driving system, and generate an evaluation test form based on the basic items, functional items and overall image; and push the evaluation test form to the target evaluators.

[0122] The personnel screening module 10 is also used to obtain the vehicle key parameter table and the equipment installation parameter table of the vehicle to be tested, and establish a vehicle database based on the vehicle key parameter table and the equipment installation parameter table; obtain the basic items, functional items and overall image of different functions of the L2+ level intelligent driving system based on the vehicle database; determine the opening method, closing method, activation method, failure method and display method of the L2+ level intelligent driving system from the basic items; determine the function activation success rate in different scenarios, the experience during function activation, and the display completeness after the function is completed or exited from the functional items; determine the image score of each judge for different functions from the overall image; generate an evaluation test table based on the opening method, the closing method, the activation method, the failure method, the display method, the function activation success rate, the experience, the display completeness and the image score.

[0123] The validity verification module 20 is also used to obtain the perception threshold of the target evaluator in different test environments; obtain the test values ​​of the target evaluator in different test scenarios and different time periods based on the perception threshold, and use the average of the test values ​​as the expected value of the target evaluator; start the system test of the L2+ level intelligent driving system, receive the evaluation test results fed back by the target evaluator, and obtain the scoring results of each function from the evaluation test results; compare the scoring results of each function with the corresponding expected value, and judge the data validity of the evaluation test results based on the comparison results to obtain valid evaluation data.

[0124] The validity verification module 20 is also used to compare the scoring results of each function with the corresponding expected values ​​to obtain a comparison result; when the comparison result shows that the difference is greater than a preset difference threshold, it is determined that the test data of the current function is invalid; when the comparison result shows that the difference is not greater than the preset difference threshold, it is determined that the test data of the current function is valid; and the test data of all functions with valid data are summarized to generate valid evaluation data.

[0125] The analysis and evaluation module 30 is further configured to obtain the primary indicator weight corresponding to each test function of the L2+ intelligent driving system and the secondary indicator weight corresponding to each auxiliary evaluation factor through the following formula:

[0126]

[0127] in, is the first-level indicator weight, For the The average score of the tested features, is the total number of test functions, is the secondary indicator weight, For the The average score of the auxiliary evaluation factors, is the total number of auxiliary evaluation factors; When there are weight tendency correlation coefficients of different evaluators among the target evaluators within a preset correlation range, the first-level indicator weight and the second-level indicator weight are recalculated according to the weight tendency value; The effective evaluation data is analyzed and the comprehensive evaluation result of intelligent driving is obtained by the following calculation formula:

[0128]

[0129] in, This is the comprehensive evaluation result of intelligent driving. For the The first-level indicator weight of each test function, For the The evaluation results of the test functions, For the The secondary indicator weights of the auxiliary evaluation factors, For each evaluator The scoring value of the auxiliary evaluation factors, is the total number of test functions, is the total number of auxiliary evaluation factors.

[0130] Among them, the steps implemented by each functional module of the L2+ level intelligent driving evaluation and analysis device can refer to the various embodiments of the L2+ level intelligent driving evaluation and analysis method of the present invention, and will not be repeated here.

[0131] In addition, an embodiment of the present invention further provides a storage medium storing an L2+ intelligent driving evaluation and analysis program. When the L2+ intelligent driving evaluation and analysis program is executed by a processor, the following operations are performed: Perform a test screening on the intelligent driving evaluators of the L2+ intelligent driving system based on their driving experience and identity tags, obtain target evaluators, and push the evaluation test form to the target evaluators; Initiate system testing of the L2+ intelligent driving system, receive evaluation test results fed back by the target evaluators, perform data validity judgment on the evaluation test results, and obtain valid evaluation data; Analyze the effective evaluation data to obtain a comprehensive evaluation result of intelligent driving.

[0132] Furthermore, when the processor executes the L2+ intelligent driving evaluation and analysis program, the processor also performs the following operations: Obtaining the driving experience of intelligent driving evaluators of L2+ intelligent driving systems, screening the intelligent driving evaluators based on the driving experience, and obtaining experienced testers; Obtaining identity tags of the experienced testers, and classifying the experienced testers according to the identity tags to obtain professional evaluation testers, consumer users, and skilled drivers, where the skilled drivers do not overlap with the consumer users; The professional evaluation testers, consumer users and experienced drivers are used as testers in each category; According to the preset evaluation group composition ratio, corresponding testers are randomly selected from testers of each category as target evaluators, and the evaluation test form is pushed to the target evaluators.

[0133] Furthermore, when the processor executes the L2+ intelligent driving evaluation and analysis program, the processor also performs the following operations: Obtain the current number of evaluators required, and select a corresponding proportion of testers from each category of testers as target evaluators based on the current number of evaluators required and the preset evaluation group composition ratio; Obtaining basic items, functional items, and overall images of different functions of the L2+ intelligent driving system, and generating an evaluation test table based on the basic items, functional items, and overall images; The evaluation test form is pushed to the target evaluator.

[0134] Furthermore, when the processor executes the L2+ intelligent driving evaluation and analysis program, the processor also performs the following operations: Obtaining a vehicle key parameter table and an equipment installation parameter table of the vehicle to be tested, and establishing a vehicle database based on the vehicle key parameter table and the equipment installation parameter table; Obtaining basic items, functional items, and overall images of different functions of the L2+ level intelligent driving system based on the vehicle database; Determine the activation mode, deactivation mode, activation mode, deactivation mode and display mode of the L2+ intelligent driving system from the basic items; Determine, from the function items, the success rate of function activation in different scenarios, the user experience during function activation, and the completeness of the display after function completion or after exiting the function; Determining the image scores of each judge for different functions from the overall image; An evaluation test table is generated according to the opening method, the closing method, the activation method, the deactivation method, the display method, the function activation success rate, the experience, the display completeness and the image score.

[0135] Furthermore, when the processor executes the L2+ intelligent driving evaluation and analysis program, the processor also performs the following operations: Obtaining the perception thresholds of the target evaluators under different test environments; Obtaining test values ​​of the target evaluator in different test scenarios and at different time periods according to the perception threshold, and taking an average of the test values ​​as the expected value of the target evaluator; Initiate system testing of the L2+ intelligent driving system, receive evaluation test results fed back by the target evaluators, and obtain scoring results for each function from the evaluation test results; The scoring results of each function are compared with the corresponding expected values, and the data validity of the evaluation test results is judged based on the comparison results to obtain valid evaluation data.

[0136] Furthermore, when the processor executes the L2+ intelligent driving evaluation and analysis program, the processor also performs the following operations: Compare the scoring results of each function with the corresponding expected value to obtain the comparison results; When the comparison result shows that the difference is greater than the preset difference threshold, determining that the test data of the current function is invalid; When the comparison result shows that the difference is not greater than the preset difference threshold, determining that the test data of the current function is valid; Gather all the test data of each function with valid data to generate valid evaluation data.

[0137] Furthermore, when the processor executes the L2+ intelligent driving evaluation and analysis program, the processor also performs the following operations: The following formula is used to obtain the primary indicator weight corresponding to each test function of the L2+ level intelligent driving system and the secondary indicator weight corresponding to each auxiliary evaluation factor:

[0138]

[0139] in, is the first-level indicator weight, For the The average rating of the tested features, is the total number of test functions, is the secondary indicator weight, For the The average score of the auxiliary evaluation factors, is the total number of auxiliary evaluation factors; When there are weight tendency correlation coefficients of different evaluators among the target evaluators within a preset correlation range, the first-level indicator weight and the second-level indicator weight are recalculated according to the weight tendency value; The effective evaluation data is analyzed and the comprehensive evaluation result of intelligent driving is obtained by the following calculation formula:

[0140]

[0141] in, This is the comprehensive evaluation result of intelligent driving. For the The first-level indicator weight of each test function, For the The evaluation results of the test functions, For the The secondary indicator weights of the auxiliary evaluation factors, For each evaluator The scoring value of the auxiliary evaluation factors, is the total number of test functions, is the total number of auxiliary evaluation factors.

[0142] Those skilled in the art will understand that all or part of the steps in the above-mentioned implementation methods can be implemented by instructing related hardware through a program. The program is stored in a storage medium and includes a number of instructions for enabling a device (which may be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application; and the aforementioned storage medium is a computer-readable storage medium, including: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0143] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0144] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0145] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A L2+ level intelligent driving evaluation and analysis method, characterized by: The L2+ level intelligent driving evaluation and analysis method includes: Perform a test screening on the intelligent driving evaluators of the L2+ intelligent driving system based on their driving experience and identity tags, obtain target evaluators, and push the evaluation test form to the target evaluators; Initiate system testing of the L2+ intelligent driving system, receive evaluation test results fed back by the target evaluators, perform data validity judgment on the evaluation test results, and obtain valid evaluation data; Analyze the effective evaluation data to obtain a comprehensive evaluation result of intelligent driving.

2. The L2+ level intelligent driving evaluation and analysis method according to claim 1, characterized in that: The method of testing and screening the intelligent driving evaluators according to the driving experience and identity tags of the L2+ intelligent driving system intelligent driving evaluators, obtaining target evaluators, and pushing the evaluation test form to the target evaluators includes: Obtaining the driving experience of intelligent driving evaluators of L2+ intelligent driving systems, screening the intelligent driving evaluators based on the driving experience, and obtaining experienced testers; Obtaining identity tags of the experienced testers, and classifying the experienced testers according to the identity tags to obtain professional evaluation testers, consumer users, and skilled drivers, where the skilled drivers do not overlap with the consumer users; The professional evaluation testers, consumer users and experienced drivers are used as testers in each category; According to the preset evaluation group composition ratio, corresponding testers are randomly selected from testers of each category as target evaluators, and the evaluation test form is pushed to the target evaluators.

3. The L2+ level intelligent driving evaluation and analysis method according to claim 2, characterized in that: The step of selecting corresponding testers from testers of each category as target evaluators according to the preset evaluation group composition ratio and pushing the evaluation test form to the target evaluators includes: Obtain the current number of evaluators required, and select a corresponding proportion of testers from each category of testers as target evaluators based on the current number of evaluators required and the preset evaluation group composition ratio; Obtaining basic items, functional items, and overall images of different functions of the L2+ intelligent driving system, and generating an evaluation test table based on the basic items, functional items, and overall images; The evaluation test form is pushed to the target evaluator.

4. The L2+ level intelligent driving evaluation and analysis method according to claim 3, characterized in that: The obtaining of basic items, functional items, and overall images of different functions of the L2+ intelligent driving system, and generating an evaluation test table based on the basic items, functional items, and overall images, includes: Obtaining a vehicle key parameter table and an equipment installation parameter table of the vehicle to be tested, and establishing a vehicle database based on the vehicle key parameter table and the equipment installation parameter table; Obtaining basic items, functional items, and overall images of different functions of the L2+ level intelligent driving system based on the vehicle database; Determine the activation mode, deactivation mode, activation mode, deactivation mode and display mode of the L2+ intelligent driving system from the basic items; Determine, from the function items, the success rate of function activation in different scenarios, the user experience during function activation, and the completeness of the display after function completion or after exiting the function; Determining the image scores of each judge for different functions from the overall image; An evaluation test table is generated according to the opening method, the closing method, the activation method, the deactivation method, the display method, the function activation success rate, the experience, the display completeness and the image score.

5. The L2+ level intelligent driving evaluation and analysis method according to claim 1, characterized in that: The initiation of the system test of the L2+ intelligent driving system, receiving the evaluation test results fed back by the target evaluator, and performing data validity judgment on the evaluation test results to obtain valid evaluation data include: Obtaining the perception thresholds of the target evaluators under different test environments; Obtaining test values ​​of the target evaluator in different test scenarios and at different time periods according to the perception threshold, and taking an average of the test values ​​as the expected value of the target evaluator; Initiate system testing of the L2+ intelligent driving system, receive evaluation test results fed back by the target evaluators, and obtain scoring results for each function from the evaluation test results; The scoring results of each function are compared with the corresponding expected values, and the data validity of the evaluation test results is judged based on the comparison results to obtain valid evaluation data.

6. The L2+ level intelligent driving evaluation and analysis method according to claim 5, characterized in that: The scoring results of each function are compared with the corresponding expected values, and the data validity of the evaluation test results is judged according to the comparison results to obtain valid evaluation data, including: Compare the scoring results of each function with the corresponding expected value to obtain the comparison results; When the comparison result shows that the difference is greater than the preset difference threshold, determining that the test data of the current function is invalid; When the comparison result shows that the difference is not greater than the preset difference threshold, determining that the test data of the current function is valid; Gather all the test data of each function with valid data to generate valid evaluation data.

7. The L2+ level intelligent driving evaluation and analysis method according to claim 1, characterized in that: The analysis of the effective evaluation data to obtain a comprehensive intelligent driving evaluation result includes: The following formula is used to obtain the primary indicator weight corresponding to each test function of the L2+ level intelligent driving system and the secondary indicator weight corresponding to each auxiliary evaluation factor: in, is the first-level indicator weight, For the The average score of the tested features, is the total number of test functions, is the secondary indicator weight, For the The average score of the auxiliary evaluation factors, is the total number of auxiliary evaluation factors; When there are weight tendency correlation coefficients of different evaluators among the target evaluators within a preset correlation range, the first-level indicator weight and the second-level indicator weight are recalculated according to the weight tendency value; The effective evaluation data is analyzed and the comprehensive evaluation result of intelligent driving is obtained by the following calculation formula: in, This is the comprehensive evaluation result of intelligent driving. For the The first-level indicator weight of each test function, For the The evaluation results of the test functions, For the The secondary indicator weights of the auxiliary evaluation factors, For each evaluator The scoring value of the auxiliary evaluation factors, is the total number of test functions, is the total number of auxiliary evaluation factors.

8. An L2+ level intelligent driving evaluation and analysis device, characterized in that: The L2+ level intelligent driving evaluation and analysis device includes: A personnel screening module is used to test and screen intelligent driving evaluators of the L2+ intelligent driving system based on their driving experience and identity tags, obtain target evaluators, and push the evaluation test form to the target evaluators; A validity verification module is used to start the system test of the L2+ intelligent driving system, receive the evaluation test results fed back by the target evaluator, perform data validity judgment on the evaluation test results, and obtain valid evaluation data; The analysis and evaluation module is used to analyze the effective evaluation data to obtain a comprehensive evaluation result of intelligent driving.

9. An L2+ level intelligent driving evaluation and analysis device, characterized in that: The L2+ level intelligent driving evaluation and analysis device includes: a memory, a processor, and an L2+ level intelligent driving evaluation and analysis program stored in the memory and executable on the processor. The L2+ level intelligent driving evaluation and analysis program is configured to implement the steps of the L2+ level intelligent driving evaluation and analysis method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores an L2+ level intelligent driving evaluation and analysis program, which, when executed by the processor, implements the steps of the L2+ level intelligent driving evaluation and analysis method according to any one of claims 1 to 7.

Images