Intelligent driving function scoring method and device, equipment and storage medium

Abstract

The invention discloses an intelligent driving function scoring method and device, equipment and a storage medium, and the method comprises the steps: obtaining shadow data, carrying out the scene recognition based on the shadow data, and extracting corresponding scene data from the shadow data according to a scene recognition result; determining a target evaluation index of the scene data according to the scene recognition result, and performing partition on the target evaluation index to obtain an index partition result; determining a scene overall score according to the index partition result and a preset index score rate corresponding to the target evaluation index; and determining a scene expected score corresponding to the scene recognition result, comparing the scene expected score with the scene overall score, and feeding back prompt information according to a comparison result. Compared with the prior art, the shadow data of intelligent driving is utilized to perform scene recognition, scoring is performed based on a scene recognition result, and prompt information is fed back, so that the problem that the performance of an intelligent driving function cannot be quantitatively fed back in time after mass production of vehicles is solved by utilizing the shadow data of intelligent driving.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to an intelligent driving function scoring method, device, equipment and storage medium. Background Art

[0002] Smart driving cars, also known as driverless cars and self-driving cars, can obtain environmental information through sensors such as radars and control the vehicle's driving based on the environmental information, reducing the driver's time to control the vehicle. Self-driving cars have advantages such as reducing traffic violations. However, since the driver's time to control the vehicle in the self-driving mode is shorter than the driver's time to control the vehicle in the traditional manual driving mode, there are still many uncertainties in self-driving cars, and existing technologies cannot provide timely quantitative feedback on the performance of the smart driving function after the vehicle is mass-produced.

[0003] In recent years, shadow mode has been widely developed on intelligent driving / autonomous driving domain controllers. Shadow data can record vehicle data before and after the event is triggered, controller debug data, etc., to provide data support for event analysis. However, in most cases during actual application, shadow data is only recorded and not used efficiently.

[0004] Therefore, there is an urgent need for an intelligent driving function scoring method that can use the shadow data of intelligent driving to solve the problem that the performance of the intelligent driving function cannot be quantitatively fed back in a timely manner after the vehicle is mass-produced. Summary of the invention

[0005] The main purpose of the present invention is to provide a method, device, equipment and storage medium for scoring intelligent driving functions, aiming to solve the technical problems in the prior art that the shadow data of intelligent driving is inefficiently utilized and the performance of the intelligent driving function cannot be quantitatively fed back in a timely manner after the mass production of vehicles.

[0006] To achieve the above object, the present invention provides a method for scoring an intelligent driving function, the method comprising the following steps:

[0007] Obtaining shadow data, performing scene recognition based on the shadow data, and extracting corresponding scene data from the shadow data according to the scene recognition result;

[0008] Determining a target evaluation index of the scene data according to the scene recognition result, and assigning points to the target evaluation index to obtain an index assignment result;

[0009] Determine the overall score of the scenario according to the indicator scoring result and the preset indicator score rate corresponding to the target evaluation indicator;

[0010] Determine the expected scene score corresponding to the scene recognition result, compare the expected scene score with the overall scene score, and feed back prompt information based on the comparison result.

[0011] Optionally, the step of acquiring shadow data, performing scene recognition based on the shadow data, and extracting corresponding scene data from the shadow data according to the scene recognition result includes:

[0012] When the shadow mode is triggered by the vehicle-side scene, shadow data is obtained, and data is extracted from the shadow data according to the file name and file type in the shadow data to obtain target data;

[0013] Performing scene recognition based on the target data to obtain multiple scene classification elements, combining the scene classification elements to generate a scene recognition result;

[0014] Corresponding scene data is extracted from the target data according to the scene recognition result.

[0015] Optionally, before the step of determining a target evaluation index of the scene data according to the scene recognition result and assigning a score to the target evaluation index and obtaining the index assignment result, the step further includes:

[0016] Identify the triggering situation of the shadow mode, and determine whether the triggering situation of the shadow mode is a false triggering situation according to the identification result;

[0017] When the triggering condition of the shadow mode is a false triggering condition, the shadow data corresponding to the shadow mode is filtered and an early warning prompt is sent;

[0018] When the triggering situation of the shadow mode is not a false triggering situation, the steps of determining the target evaluation index according to the scene recognition result, assigning points to the target evaluation index, and obtaining the index assignment result are performed.

[0019] Optionally, the step of determining a target evaluation index of the scene data according to the scene recognition result, assigning a score to the target evaluation index, and obtaining an index assignment result includes:

[0020] Determining target evaluation indicators of the scene data according to the scene recognition result, and determining the indicator level and importance of each target evaluation indicator;

[0021] Based on the preset total evaluation score, the indicator level and the degree of importance, each of the target evaluation indicators is scored to obtain an indicator scoring result.

[0022] Optionally, the step of determining the overall score of the scenario according to the indicator scoring result and the preset indicator score rate corresponding to the target evaluation indicator includes:

[0023] Determine the triggering times of the shadow mode in each speed segment and the single item score of the scene in the current scene according to the index scoring result and the preset index score rate corresponding to the target evaluation index;

[0024] Determine the average scene score of each speed segment in the current scene according to the triggering times of the shadow mode of each speed segment in the current scene and the scene single item score;

[0025] Performing weight configuration on the current scene according to each speed segment to obtain a weight configuration result of each speed segment of the current scene;

[0026] The overall scenario score is determined based on the scenario score average and the weight configuration result.

[0027] Optionally, the step of determining a scene expected score corresponding to the scene recognition result, comparing the scene expected score with the scene overall score, and feeding back prompt information according to the comparison result includes:

[0028] Determine the scene expected score corresponding to the scene recognition result by querying the scene expected score table;

[0029] Compare the scenario expected score with the scenario overall score, and determine whether the scenario overall score is less than the scenario expected score based on the comparison result;

[0030] If the overall score of the scenario is less than the expected score of the scenario, a warning prompt message is fed back;

[0031] If the overall score of the scenario is not less than the expected score of the scenario, a safety prompt message is fed back.

[0032] Optionally, after the step of feeding back warning prompt information if the overall score of the scenario is less than the expected score of the scenario, the step further includes:

[0033] Performing data analysis based on the relevant data of the overall score of the scenario, optimizing and upgrading the current intelligent driving system according to the data analysis results, and obtaining an upgraded intelligent driving system;

[0034] The upgraded intelligent driving system is used for verification to generate a comparison result between the current intelligent driving system and the upgraded intelligent driving system.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also proposes an intelligent driving function scoring device, the device comprising:

[0036] A scene recognition module, used to obtain shadow data, perform scene recognition based on the shadow data, and extract corresponding scene data from the shadow data according to the scene recognition result;

[0037] An indicator scoring module is used to determine the target evaluation indicator of the scene data according to the scene recognition result, and to score the target evaluation indicator to obtain the indicator scoring result;

[0038] A scenario scoring module is used to determine the overall scenario score based on the indicator scoring result and the preset indicator score rate corresponding to the target evaluation indicator;

[0039] The information feedback module is used to determine the scene expected score corresponding to the scene recognition result, compare the scene expected score with the scene overall score, and feedback prompt information according to the comparison result.

[0040] In addition, to achieve the above-mentioned purpose, the present invention also proposes an intelligent driving function scoring device, which includes: a memory, a processor, and an intelligent driving function scoring program stored in the memory and executable on the processor, and the intelligent driving function scoring program is configured to implement the steps of the intelligent driving function scoring method described above.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which an intelligent driving function scoring program is stored. When the intelligent driving function scoring program is executed by a processor, the steps of the intelligent driving function scoring method described above are implemented.

[0042] The present invention discloses obtaining shadow data, and performing scene recognition based on the shadow data, extracting corresponding scene data from the shadow data according to the scene recognition result; determining the target evaluation index of the scene data according to the scene recognition result, and assigning points to the target evaluation index to obtain the index assignment result; determining the overall score of the scene according to the index assignment result and the preset index score rate corresponding to the target evaluation index; determining the expected score of the scene corresponding to the scene recognition result, and comparing the expected score of the scene with the overall score of the scene, and feeding back prompt information according to the comparison result. Since the present invention performs scene recognition based on shadow data, determines the target evaluation index of the scene data in the shadow data according to the scene recognition result, and then determines the overall score of the scene according to the assignment result of the target evaluation index and the preset index score rate corresponding to the target evaluation index, and finally feeds back prompt information according to the comparison result of the overall score of the scene with the expected score of the scene, compared with the prior art, the present invention uses the shadow data of intelligent driving to solve the problem that the performance of the intelligent driving function cannot be quantitatively fed back in time after the mass production of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of a first embodiment of the intelligent driving function scoring method of the present invention;

[0044] Figure 2 A schematic diagram of an AEB stationary vehicle target scene in the intelligent driving function scoring method of the present invention;

[0045] Figure 3 This is a flowchart of automatic scoring and score warning in the intelligent driving function scoring method of the present invention;

[0046] Figure 4 This is a flow chart of a second embodiment of the intelligent driving function scoring method of the present invention;

[0047] Figure 5 This is a flow chart of a third embodiment of the intelligent driving function scoring method of the present invention;

[0048] Figure 6 This is a diagram showing the architecture of the shadow data closed-loop application technology solution in the intelligent driving function scoring method of the present invention;

[0049] Figure 7 This is a schematic diagram showing the score comparison before and after optimization of the scene of a stationary vehicle on a straight road in a suburban area during the day in the intelligent driving function scoring method of the present invention;

[0050] Figure 8 This is a structural block diagram of the first embodiment of the intelligent driving function scoring device of the present invention;

[0051] Fig. 9 It is a structural diagram of an intelligent driving function scoring device in a hardware operating environment involved in an embodiment of the present invention.

[0052] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0054] The embodiment of the present invention provides a method for scoring intelligent driving functions, referring to Figure 1 , Figure 1 Schematic diagram of the flow chart of the first embodiment of the intelligent driving function scoring method of the present invention.

[0055] In this embodiment, the intelligent driving function scoring method includes steps S10 to S40:

[0056] Step S10: Obtain shadow data, perform scene recognition based on the shadow data, and extract corresponding scene data from the shadow data according to the scene recognition result.

[0057] It should be noted that the execution subject of this embodiment can be a computer server device with data processing, network communication and program running functions used in the intelligent driving function evaluation scenario, such as a server, a tablet computer, a smart phone, a vehicle-mounted mobile device, etc., or an electronic device capable of realizing the above functions, an intelligent driving function scoring device, etc. The following takes a system including an intelligent driving function scoring device (hereinafter referred to as the system) as an example to illustrate this embodiment and the following embodiments.

[0058] It should be understood that the above-mentioned shadow data is the data obtained when the shadow mode is triggered by the vehicle-side scene. In the field of intelligent driving / autonomous driving, the shadow mode can collect vehicle-side data and send it to the cloud for management and storage when safety-related functions such as automatic emergency braking are triggered or when there is inconsistency between the driver's driving behavior and the intelligent / autonomous driving decision, to support the algorithm and software optimization and iteration mode.

[0059] In shadow mode, the autonomous driving system will record the vehicle's driving trajectory, sensor data, simulated control instructions and other information in real time. These data will be compared and analyzed with the driver's actual operation data to evaluate the performance and safety of the autonomous driving system. These recorded and analyzed data can be regarded as shadow data in the field of intelligent driving.

[0060] In a specific implementation, in order to improve the data processing efficiency and the accuracy of scene recognition, step S10 includes steps S101 to S103:

[0061] Step S101: When the shadow mode is triggered in the vehicle-side scene, shadow data is obtained, and data is extracted from the shadow data according to the file name and file type in the shadow data to obtain target data.

[0062] It should be noted that when the shadow mode is triggered in the vehicle-side scene, the shadow data can be collected by the intelligent driving domain controller, and then the shadow data is extracted according to the file name and file type in the shadow data to obtain the target data. The target data may include vehicle bus data; debug data of algorithms, functions, and software; perception data and image / video data of visual sensors; perception data of radar sensors; and fusion data.

[0063] Step S102: performing scene recognition based on the target data to obtain a plurality of scene classification elements, combining the scene classification elements to generate a scene recognition result.

[0064] It should be noted that after the intelligent driving controller completes data collection, it can be sent to the vehicle-side TBOX through Ethernet communication, and then sent to the cloud through the network by TBOX. The cloud can automatically identify the type of shadow mode trigger through the vehicle bus data and function debug data, and automatically identify the scene and accurately classify it by combining the type of shadow mode trigger, fusion data, and image / video data provided by the visual sensor; the scene element classification method is summarized in Table 1:

[0065] Table 1 Classification of scene elements

[0066]

[0067] It needs to be explained that the above-mentioned AEB stands for automatic emergency braking function, ELK stands for emergency lane keeping function and EMA stands for emergency steering assist function.

[0068] It should be noted that, during the scene recognition process, the bus data in the shadow data packet can be extracted according to the file name and file type in the shadow data, and the functional status signal can be parsed according to the parsing file (DBC, xml, etc.), such as AEB_State, ELK_State, etc. When it is parsed that a specific functional state is activated when the shadow mode is triggered, it is clear that the shadow data is the shadow data of a specific function. For example, when the shadow mode is triggered, AEB_State is activated, then the shadow data is judged to be the shadow data of AEB.

[0069] The bus data and image / video data in the shadow data packet can be extracted according to the file name and file type in the shadow data, and the date, time, longitude and latitude can be parsed according to the bus data parsing file (DBC, xml, etc.), and the illumination value can be parsed according to the forward-looking perception data parsing file. For example, the time is 10:30 on January 1, 2024, Beijing time, 116° east longitude, 30° north latitude, which is determined as daytime, and 20:30 on January 1, 2024, Beijing time, 116° east longitude, 30° north latitude is determined as nighttime. For the judgment of early morning and evening, it is necessary to combine the image / video data input based on the time and longitude and latitude to give it to the visual detection network model, and the visual detection network model recognizes daytime, night, early morning, and evening and then outputs.

[0070] The bus data in the shadow data packet can be extracted according to the file name and file type in the shadow data, and the navigation information can be parsed according to the bus data parsing file (DBC, xml, etc.). According to the navigation area and road grade, highways, elevated roads, urban areas, suburbs, rural areas, etc. can be distinguished.

[0071] The forward-looking perception data in the shadow data packet can be extracted according to the file name and file type in the shadow data, and the lane line curvature analysis can be performed according to the forward-looking perception analysis file. The lane attribute can be judged as a straight road or a curve according to the lane line curvature. For example, a road curvature ≤ 0.0005 is classified as a straight road, and a road curvature > 0.0005 is classified as a curve.

[0072] It is understandable that after the scene classification elements are clearly distinguished, the specific scene of the shadow data (i.e., the scene recognition result) can be obtained by combining the scene classification elements, such as: AEB function, daytime, suburbs, straight roads, pedestrians, and crossing scenes.

[0073] Step S103: extracting corresponding scene data from the target data according to the scene recognition result.

[0074] It should be noted that, for example, for AEB function, daytime, suburban, straight road, pedestrian, and crossing scenarios, scene data such as vehicle speed, deceleration, collision speed, alarm, and TTC value during braking are extracted from the target data.

[0075] Step S20: determining a target evaluation index of the scene data according to the scene recognition result, and assigning points to the target evaluation index to obtain an index assignment result.

[0076] In a specific implementation, the target evaluation index of the scene data can be determined based on the scene recognition result, and the indicator level and importance of each target evaluation index can be determined; each target evaluation index can be scored based on the preset total evaluation score, the indicator level and the importance to obtain the indicator scoring result.

[0077] It should be understood that the importance of the above-mentioned target evaluation indicators may be the degree of concern of the corresponding scenario for safety, comfort, efficiency, and human-computer interaction.

[0078] For example, based on the scene recognition results, the target evaluation indicators are located, and each target evaluation indicator is scored according to the preset total evaluation score of 10 points. The weights are assigned according to the different levels of concern for safety, comfort, efficiency, and human-computer interaction in the corresponding scene and the different levels of indicators. First, the first and second level indicators are assigned different weights, and then the third and fourth level indicators are assigned different weights. The indicator classification reference is shown in Table 2:

[0079] Table 2 Example table of indicator allocation

[0080]

[0081] It should be understood that the total score of the secondary indicators is equal to the total score of the primary indicators, the total score of the tertiary indicators is equal to the total score of the secondary indicators, and the total score of the quaternary indicators is equal to the total score of the tertiary indicators. For example, the adequacy and timeliness of the alarm / prompt are assigned 2 points, of which the form of the alarm / prompt can be assigned 1 point, and the timing of the alarm / prompt can be assigned 1 point. It should be understood that only some indicators are described in Table 2, and the remaining indicators can be customized according to specific scenarios, which will not be repeated in this embodiment.

[0082] For example, the first-level indicators may include technical indicators, the second-level indicators may refer to the safety performance indicators, comfort performance indicators and efficiency indicators included in the technical indicators, the third-level indicators included in the safety performance indicators may include the adequacy and timeliness of alarms / prompts, speed boundaries (driving), takeover frequency and risk avoidance performance, etc., and the fourth-level indicators included in the adequacy and timeliness of alarms / prompts may include the form of alarms / prompts (optical, sound, vibration, etc.) and the timing of alarms / prompts (TTC, TTLC, etc.), etc.

[0083] Step S30: Determine the overall score of the scenario according to the indicator scoring result and the preset indicator score rate corresponding to the target evaluation indicator.

[0084] In a specific implementation, step S30 may include steps S301 to S304:

[0085] Step S301: Determine the triggering times of the shadow mode in each speed segment and the single item score of the scene in the current scene according to the indicator scoring result and the preset indicator score rate corresponding to the target evaluation indicator.

[0086] It should be explained that the above-mentioned preset index score rate can be customized according to the specific scenario, and this embodiment does not limit this. In this embodiment, the preset index score rate can refer to Table 3:

[0087] Table 3 Index score rate reference table

[0088]

[0089] It should be understood that Table 3 only describes the score rates of some indicators, and the score rates of other indicators can be customized according to specific scenarios, which will not be described in detail in this embodiment.

[0090] Step S302: determining the average scene score of each speed segment in the current scene according to the triggering times of the shadow mode of each speed segment in the current scene and the scene single item score.

[0091] Step S303: weighting the current scene according to each speed segment to obtain weighting results for each speed segment of the current scene.

[0092] Step S304: Determine the overall scenario score based on the scenario score average and the weight configuration result.

[0093] It should be noted that the single scene score = scene-related index score * cumulative sum of score rate; if a single scene triggers the shadow mode multiple times, the multiple scene items are summed and averaged. The scene is weighted according to different vehicle speed ranges. The weight is comprehensively evaluated by considering factors such as the commonness of the speed range, the impact on safety, and the impact on comfort. The weight coefficient can be 0-3. The overall scene score can be obtained by the single scene score * the cumulative sum of the single scene weights / the cumulative sum of the single scene weights.

[0094] For example, refer to Figure 2 , Figure 2 The figure is a schematic diagram of the AEB stationary vehicle target scenario in the intelligent driving function scoring method of the present invention. The figure shows the scenario in which AEB brakes a stationary target to avoid / reduce the risk of collision. The vehicle on the left side of the schematic diagram is the host vehicle, and the vehicle on the right side is the stationary target vehicle. The implementation process of the system in this scenario is as follows:

[0095] 1. When the TTC (i.e., the remaining collision time with the target) in this scenario is less than the threshold for AEB triggering, the AEB function state changes from the inactive state to the active state, and the data for a period of time before and after the AEB activation is triggered is collected and uploaded to the cloud; then, based on the AEB function state signal in the vehicle bus data and the signal triggering the shadow mode in the debug data, it is determined that AEB is activated, and the shadow data is comprehensively determined to be AEB function data; the time zone, time, and illumination information fed back by the camera at the location of the vehicle in the shadow data are used to distinguish it as daytime; the road attribute of the vehicle is distinguished as suburban through the road section information provided by the map; the lane attribute is distinguished as a straight road through the lane line curvature of the lane where the vehicle is located; the target type of the functional scene is distinguished as a vehicle through the main target type in the debug data of the shadow data; the kinematic attribute of the target is distinguished as stationary through the longitudinal and lateral speeds and accelerations of the main target; in summary, the scene recognition results are AEB, daytime, suburban, straight road, and stationary vehicle scenes; finally, based on the scene recognition results, the parameters such as TTC, vehicle speed, Vimpact collision speed, and self-vehicle deceleration value after the function is triggered are extracted to support automatic scoring.

[0096] 2. Based on the scene recognition result: AEB is triggered on a stationary vehicle target, and the system assigns points to the indicators. Points are assigned: 8 points for safety indicator_risk avoidance performance, 2 points for human-machine interaction indicator_sufficiency and timeliness of alarm / prompt, including 1 point for sufficiency of alarm / prompt and 1 point for timeliness of alarm / prompt.

[0097] 3. Determine the score rate of the corresponding indicator, safety indicator_risk avoidance performance, and the scoring reference mechanism is shown in Table 4:

[0098] Table 4 Safety index_risk avoidance performance score table

[0099] Safety Indicator_Risk Hedging Performance Scoring rate Vimpact≤0 100％ 0<Vimpact≤20 80％ 20<Vimpact≤30 60％ 30<Vimpact≤45 40％ 45<Vimpact≤60 20％ Vimpact>60 0％

[0100] It should be noted that Vimpact in the above table represents the collision speed. For example, when the vehicle is traveling at 80 kph, AEB is triggered on a stationary vehicle target and the vehicle cannot be completely stopped to avoid the risk. When the vehicle cannot be completely stopped, the collision speed is between 5 and 10 kph, and the safety index_risk avoidance performance score is 80%.

[0101] Human-computer interaction index_alarm / prompt adequacy and timeliness, the scoring reference mechanism is shown in Table 5:

[0102] Table 5 Human-computer interaction index_Alarm / prompt adequacy and timeliness score table

[0103] Human-computer interaction index_alarm / prompt adequacy Scoring rate There are 2 or more alarms / prompts 100％ There is 1 type of alarm / prompt 50％ No alarm / prompt 0％ Human-computer interaction indicators_alarm / prompt timeliness Scoring rate 1.7≤TTC≤2.3 100％ 1.3<TTC<1.7 70％ 1.0≤TTC≤1.3 30％ TTC<1.0 0％

[0104] It should be noted that the TTC in the above table represents the remaining collision time with the target. For example, the alarm has two forms, acoustic and optical, and the alarm TTC is stable at 1.8s. The human-computer interaction indicator_alarm / prompt adequacy and timeliness is stable and gets 2 points.

[0105] As shown in the example above, the scene individual score for a single AEB triggering scenario on a stationary vehicle target is 8*80%+1*100%+1*100% to 8*100%+1*100%+1*100%, which is 8.4 points.

[0106] It should be noted that in order to improve the accuracy of the intelligent driving function scoring, the scores of different speed ranges in a scene can be averaged, for example:

[0107] AEB, daytime, suburban, straight road, stationary, vehicle: if the shadow mode is triggered 3 times in the speed range of 0-40 kph (kilometers per hour), and all 3 scores are 10 points, the average score of the scene is 10 points;

[0108] AEB, daytime, suburban, straight road, stationary, vehicle: Shadow mode is triggered twice in the speed range of 40-60kph, and both scores are 10 points, then the average score of the scene is 10 points;

[0109] AEB, daytime, suburban, straight road, stationary, vehicle: The shadow mode was triggered twice in the speed range of 60-80kph, with 1 score of 10 points and 1 score of 8.4 points, so the average score of the scene was 9.2 points.

[0110] Furthermore, the scenarios are weighted according to different vehicle speed ranges, and the weights are evaluated comprehensively based on factors such as the commonness of the speed range, the impact on safety, and the impact on comfort. The weight coefficient can be 0-3. For example: AEB, daytime, suburban, straight road, stationary, vehicle: 0-40kph, weight configuration 2; 40-60kph, weight configuration 3; 60-80kph, weight configuration 2.

[0111] The overall scene score is obtained by the cumulative sum of the scene individual scores * the cumulative sum of the scene individual weights / the cumulative sum of the scene individual weights; taking the above assumption as an example, the overall scene score of the AEB stationary vehicle target scene is: (10*2+10*3+9.2*2) / (2+3+2)=9.771.

[0112] It should be added that the scene score calculation is performed only after the shadow mode is triggered, and the speed segment scores and weight values ​​without shadow data records are not included in the calculation.

[0113] Step S40: determining the expected scene score corresponding to the scene recognition result, comparing the expected scene score with the overall scene score, and feeding back prompt information according to the comparison result.

[0114] In a specific implementation, step S40 may include: steps S401 to S404:

[0115] Step S401: determining the scene expected score corresponding to the scene recognition result by querying the scene expected score table.

[0116] It should be noted that the scenario expected score table can be shown as follows:

[0117] Table 6 Scenario Expected Score Table

[0118]

[0119] It should be understood that the scene expected score in the scene expected score table can be a custom setting. According to the scene recognition result, by searching the scene expected score table, the corresponding scene expected score is obtained. According to the scene score expected table, the scene expected score of AEB, daytime, suburbs, straight road, stationary, and the vehicle is 9.8 points.

[0120] Step S402: Compare the scenario expected score with the scenario overall score, and determine whether the scenario overall score is less than the scenario expected score based on the comparison result.

[0121] Step S403: If the overall score of the scenario is less than the expected score of the scenario, a warning prompt message is fed back.

[0122] Step S404: If the overall score of the scenario is not less than the expected score of the scenario, a safety prompt message is fed back.

[0123] It should be understood that the above-mentioned AEB overall scene score for the stationary vehicle target scene is 9.771 points - the expected scene score of AEB for the stationary vehicle target scene is 9.8 points < 0, thus triggering the score warning, feeding back the warning prompt information, and reminding engineers to optimize the software.

[0124] In a specific implementation, if the overall score of the scenario is not less than the expected score of the scenario, safety prompt information is fed back.

[0125] For example, refer to Figure 3 , Figure 3 This is a flowchart of automatic scoring and score warning in the intelligent driving function scoring method of the present invention. In the figure, the vehicle-side scene triggers the shadow mode, collects and uploads data (i.e., collects shadow data); extracts the shadow mode trigger type video data, environmental information, target, lane line information, etc., performs scene recognition and classification, and refines the scene data; obtains the scene classification (i.e., scene recognition result), and assigns indicators according to the scene classification; obtains the scene data to calculate the indicator score rate, and further calculates the single score of the scene at that time. Take the average value of multiple triggers of the same scene, and multiply the cumulative sum of multiple scene scores by the weight value to obtain the comprehensive scene score, i.e., the overall scene score. According to the scene classification, i.e., the scene recognition result, the overall expected score of the corresponding classified scene, i.e., the scene expected score, is found in the scene overall expected score table. If the calculated score (scene overall score)-expected score (scene expected score) is less than 0, the score warning is triggered; after the scene optimized software is OTA, the shadow mode of the same scene is triggered again, the optimized scene overall score is calculated, and the score comparison before and after optimization is implemented to verify the optimization effect.

[0126] This embodiment discloses obtaining shadow data, and performing scene recognition based on the shadow data, extracting corresponding scene data from the shadow data according to the scene recognition result; determining the target evaluation index of the scene data according to the scene recognition result, and assigning points to the target evaluation index to obtain the index assignment result; determining the overall score of the scene according to the index assignment result and the preset index score rate corresponding to the target evaluation index; determining the expected score of the scene corresponding to the scene recognition result, and comparing the expected score of the scene with the overall score of the scene, and feeding back prompt information according to the comparison result. Since this embodiment performs scene recognition based on shadow data, determines the target evaluation index of the scene data in the shadow data according to the scene recognition result, and then determines the overall score of the scene according to the assignment result of the target evaluation index and the preset index score rate corresponding to the target evaluation index, and finally feeds back prompt information according to the comparison result of the overall score of the scene with the expected score of the scene, compared with the prior art, this embodiment uses the shadow data of intelligent driving to solve the problem that the performance of the intelligent driving function cannot be quantitatively fed back in a timely manner after the mass production of the vehicle.

[0127] refer to Figure 4 , Figure 4 Schematic diagram of the flow chart of the second embodiment of the intelligent driving function scoring method of the present invention.

[0128] Based on the first embodiment described above, in this embodiment, before step S20, steps S104 to S106 are further included:

[0129] Step S104: Identify the triggering condition of the shadow mode, and determine whether the triggering condition of the shadow mode is a false triggering condition according to the identification result.

[0130] Step S105: When the triggering condition of the shadow mode is a false triggering condition, the shadow data corresponding to the shadow mode is filtered and an early warning prompt is sent.

[0131] Step S106: When the triggering condition of the shadow mode is not a false triggering condition, the step of determining the target evaluation index according to the scene recognition result, assigning points to the target evaluation index, and obtaining the index assignment result is executed.

[0132] It should be noted that in order to improve the accuracy of the calculation of the overall score of the scene, before determining the target evaluation index of the scene data based on the scene recognition result and allocating the target evaluation index, and obtaining the index scoring result, the triggering of the shadow mode can be identified, and it can be determined whether the triggering of the shadow mode is a false trigger based on the identification result.

[0133] It should be explained that the recognition of false triggering of shadow mode requires cloud-based algorithms / models to support recognition at the perception level, the test bench replays the image / video, and uses the visual detection network model for re-recognition. The false triggering is judged based on whether the recognition of the visual detection network model is consistent with the recognition of the real vehicle shadow mode (whether the target is recognized, and whether the position, speed, acceleration and other parameters of the target are out of tolerance). If the recognition of the test bench visual detection network model is inconsistent with the recognition of the real vehicle shadow mode or the difference in the position, speed and acceleration of the target exceeds the threshold, it is judged as a false trigger; otherwise, it is judged as a positive trigger, that is, the triggering of the shadow mode is not a false trigger.

[0134] The present embodiment discloses identifying the triggering situation of the shadow mode, judging whether the triggering situation of the shadow mode is a false triggering situation according to the recognition result; when the triggering situation of the shadow mode is a false triggering situation, filtering the shadow data corresponding to the shadow mode at that time, and sending a warning prompt; when the triggering situation of the shadow mode is not a false triggering situation, executing the steps of determining the target evaluation index according to the scene recognition result, assigning points to the target evaluation index, and obtaining the index assignment result. Because the present embodiment identifies the triggering situation of the shadow mode before the shadow data participates in the automatic scoring, judging whether the triggering situation of the shadow mode is a false triggering situation according to the recognition result, and if it is a false triggering situation, filtering the shadow data corresponding to the shadow mode at that time, and sending a warning prompt, compared with the prior art, the present embodiment effectively improves the accuracy of the calculation of the overall score of the scene.

[0135] refer to Figure 5 , Figure 5 4 is a flow chart of a third embodiment of the intelligent driving function scoring method of the present invention.

[0136] Based on the above embodiments, in this embodiment, after step S403, steps S50 to S60 are further included:

[0137] Step S50: performing data analysis based on the relevant data of the overall score of the scenario, optimizing and upgrading the current intelligent driving system according to the data analysis results, and obtaining an upgraded intelligent driving system.

[0138] Step S60: Utilize the upgraded intelligent driving system for verification, and generate a comparison result between the current intelligent driving system and the upgraded intelligent driving system.

[0139] For example, refer to Figure 6 , Figure 6This is the architecture diagram of the shadow data closed-loop application technology solution in the intelligent driving function scoring method of the present invention. In the figure, the vehicle triggers the shadow mode, and the shadow data is collected and uploaded; the cloud scene management combines the shadow trigger type and data to perform scene recognition classification and scene data extraction; the function automatic scoring system calculates the score based on the scene recognition results and data, and the score is warned; software optimization and simulation evaluation are performed based on the situation, scene, and shadow data of the automatic function scoring; OTA upgrade and real vehicle verification, after the OTA upgrade, the corresponding scene is verified, and the scene data is collected through shadow triggering and sent to the cloud for upgraded function scoring, so as to realize the comparative analysis of the corresponding scene scores of the previous and later versions and the confirmation of the optimization effect.

[0140] It should be noted that the above-mentioned AEB overall scene score for the stationary vehicle target scene is 9.771 points - the expected scene score of AEB for the stationary vehicle target scene is 9.8 points < 0, thus triggering the score warning and feeding back the warning prompt information to remind engineers to optimize the software.

[0141] Based on data analysis of the overall scenario score, it was determined that the main point-loss scenario is the 60-80kph speed range, and the focus was on optimizing this speed range. For example, the TTC value and maximum deceleration limit triggered by AEB in this speed range can be optimized to reduce the collision risk and collision speed in this scenario.

[0142] It is understandable that after system software optimization iterations and OTA upgrades, scene recognition and function score calculations are performed again after the shadow mode is triggered. Assuming that the score of the 60-80kph speed segment is 10 points after optimization, and the comprehensive scene score is 10 points, the score warning prompt for the scene will be lifted.

[0143] Synchronous can use the automatic scoring system to compare the scores of the previous and next versions. For example, the system software versions before and after optimization are S3.2.0 and S3.3.0 respectively. For example, refer to Figure 7 , Figure 7 This is a schematic diagram comparing the scores before and after optimization of the scene of a stationary vehicle on a straight road in the suburbs during the day in the intelligent driving function scoring method of the present invention. In the figure, the horizontal axis represents the version number, and the vertical axis represents the overall score of the scene. By comparing different versions of the scene scores of a stationary vehicle on a straight road in the suburbs during the day, the optimization effect can be quickly verified and confirmed.

[0144] This embodiment discloses obtaining shadow data, and performing scene recognition based on the shadow data, extracting corresponding scene data from the shadow data according to the scene recognition result; determining the target evaluation index of the scene data according to the scene recognition result, and assigning points to the target evaluation index to obtain the index assignment result; determining the overall score of the scene according to the index assignment result and the preset index score rate corresponding to the target evaluation index; determining the expected score of the scene corresponding to the scene recognition result, and comparing the expected score of the scene with the overall score of the scene, and if the overall score of the scene is less than the expected score of the scene, then feedback warning prompt information; performing data analysis based on the relevant data of the overall score of the scene, optimizing and upgrading the current intelligent driving system according to the data analysis result, and obtaining the upgraded intelligent driving system; using the upgraded intelligent driving system for verification, and generating the comparison result of the current intelligent driving system and the upgraded intelligent driving system. Compared with the prior art, this embodiment uses the upgraded intelligent driving system for verification, generates the comparison result of the current intelligent driving system and the upgraded intelligent driving system, which is conducive to evaluating the upgrade effect, and then guiding the iterative optimization of the subsequent system in a targeted manner.

[0145] In addition, an embodiment of the present invention further proposes a storage medium, on which an intelligent driving function scoring program is stored. When the intelligent driving function scoring program is executed by a processor, the steps of the intelligent driving function scoring method described above are implemented.

[0146] Reference Figure 8 , Figure 8 This is a structural block diagram of the first embodiment of the intelligent driving function scoring device of the present invention.

[0147] like Figure 8 As shown, the intelligent driving function scoring device proposed in the embodiment of the present invention includes: a scene recognition module 801, an indicator scoring module 802, a scene scoring module 803 and an information feedback module 804.

[0148] The scene recognition module 801 is used to obtain shadow data, perform scene recognition based on the shadow data, and extract corresponding scene data from the shadow data according to the scene recognition result.

[0149] The indicator scoring module 802 is used to determine the target evaluation indicator of the scene data according to the scene recognition result, and to score the target evaluation indicator to obtain the indicator scoring result.

[0150] The scenario scoring module 803 is used to determine the overall scenario score according to the indicator scoring result and the preset indicator score rate corresponding to the target evaluation indicator.

[0151] The information feedback module 804 is used to determine the scene expected score corresponding to the scene recognition result, compare the scene expected score with the scene overall score, and feed back prompt information according to the comparison result.

[0152] The scene recognition module 801 is also used to obtain shadow data when the vehicle-side scene triggers the shadow mode, and extract data from the shadow data according to the file name and file type in the shadow data to obtain target data; perform scene recognition based on the target data to obtain multiple scene classification elements, combine each of the scene classification elements to generate a scene recognition result; and extract corresponding scene data from the target data according to the scene recognition result.

[0153] The indicator scoring module 802 is also used to determine the target evaluation indicator of the scene data based on the scene recognition result, and determine the indicator level and importance of each target evaluation indicator; based on the preset total evaluation score, the indicator level and the importance, each target evaluation indicator is scored to obtain the indicator scoring result.

[0154] The scene scoring module 803 is also used to determine the number of triggering times of the shadow mode of each speed segment in the current scene and the scene single score according to the indicator scoring result and the preset indicator score rate corresponding to the target evaluation indicator; determine the average scene score of each speed segment in the current scene through the number of triggering times of the shadow mode of each speed segment in the current scene and the scene single score; perform weight configuration on the current scene according to each speed segment to obtain the weight configuration result of each speed segment in the current scene; and determine the overall scene score based on the scene score average value and the weight configuration result.

[0155] The information feedback module 804 is further used to determine the scene expected score corresponding to the scene recognition result by querying the scene expected score table; compare the scene expected score with the scene overall score, and determine whether the scene overall score is less than the scene expected score based on the comparison result; if the scene overall score is less than the scene expected score, then feedback warning prompt information; if the scene overall score is not less than the scene expected score, then feedback safety prompt information.

[0156] The embodiment of the present device discloses obtaining shadow data, and performing scene recognition based on the shadow data, extracting corresponding scene data from the shadow data according to the scene recognition result; determining the target evaluation index of the scene data according to the scene recognition result, and assigning points to the target evaluation index to obtain the index assignment result; determining the overall score of the scene according to the index assignment result and the preset index score rate corresponding to the target evaluation index; determining the expected score of the scene corresponding to the scene recognition result, and comparing the expected score of the scene with the overall score of the scene, and feeding back prompt information according to the comparison result. Since the embodiment of the present device performs scene recognition based on shadow data, determines the target evaluation index of the scene data in the shadow data according to the scene recognition result, and then determines the overall score of the scene according to the assignment result of the target evaluation index and the preset index score rate corresponding to the target evaluation index, and finally feeds back prompt information according to the comparison result of the overall score of the scene with the expected score of the scene, compared with the prior art, the embodiment of the present device uses the shadow data of intelligent driving to solve the problem that the performance of the intelligent driving function after the mass production of the vehicle cannot be quantitatively fed back in time.

[0157] Based on the first embodiment of the intelligent driving function scoring device of the present invention, a second embodiment of the intelligent driving function scoring device of the present invention is proposed.

[0158] In this embodiment, the indicator scoring module 802 is also used to identify the triggering situation of the shadow mode, and determine whether the triggering situation of the shadow mode is a false triggering situation according to the identification result; when the triggering situation of the shadow mode is a false triggering situation, the shadow data corresponding to the shadow mode at that time is filtered, and an early warning prompt is sent; when the triggering situation of the shadow mode is not a false triggering situation, the step of determining the target evaluation indicator based on the scene recognition result, and scoring the target evaluation indicator to obtain the indicator scoring result is executed.

[0159] Other embodiments or specific implementations of the intelligent driving function scoring device of the present invention can refer to the above-mentioned method embodiments and will not be described in detail here.

[0160] The present application provides an intelligent driving function scoring 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 so that the at least one processor can execute the intelligent driving function scoring method in the above-mentioned embodiment one.

[0161] Reference below Fig. 9, which shows a schematic diagram of the structure of an intelligent driving function scoring device suitable for implementing an embodiment of the present application. The intelligent driving function scoring device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig. 9 The intelligent driving function scoring device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0162] like Fig. 9 As shown, the intelligent driving function scoring device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the intelligent driving function scoring device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the intelligent driving function scoring device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows an intelligent driving function scoring device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0163] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0164] The intelligent driving function scoring device provided by the present application adopts the intelligent driving function scoring method in the above embodiment, which can solve the technical problems in the prior art that the shadow data of intelligent driving is inefficiently utilized and the performance of the intelligent driving function after the mass production of the vehicle cannot be quantitatively fed back in a timely manner. Compared with the prior art, the beneficial effects of the intelligent driving function scoring device provided by the present application are the same as the beneficial effects of the intelligent driving function scoring method provided by the above embodiment, and the other technical features in the intelligent driving function scoring device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0165] It should be understood that the various parts disclosed in this application can be implemented by 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 one or more embodiments or examples in a suitable manner.

[0166] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0167] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0168] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0169] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0170] 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 specification 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 method for scoring intelligent driving functions, characterized in that: The method comprises: Obtaining shadow data, performing scene recognition based on the shadow data, and extracting corresponding scene data from the shadow data according to the scene recognition result; Determining a target evaluation index of the scene data according to the scene recognition result, and assigning points to the target evaluation index to obtain an index assignment result; Determine the overall score of the scenario according to the indicator scoring result and the preset indicator score rate corresponding to the target evaluation indicator; Determine the expected scene score corresponding to the scene recognition result, compare the expected scene score with the overall scene score, and feed back prompt information based on the comparison result.

2. The intelligent driving function scoring method according to claim 1, characterized in that: The step of obtaining shadow data, performing scene recognition based on the shadow data, and extracting corresponding scene data from the shadow data according to the scene recognition result includes: When the shadow mode is triggered by the vehicle-side scene, shadow data is obtained, and data is extracted from the shadow data according to the file name and file type in the shadow data to obtain target data; Performing scene recognition based on the target data to obtain multiple scene classification elements, combining the scene classification elements to generate a scene recognition result; Corresponding scene data is extracted from the target data according to the scene recognition result.

3. The intelligent driving function scoring method according to claim 2, characterized in that: Before the step of determining the target evaluation index of the scene data according to the scene recognition result and assigning points to the target evaluation index and obtaining the index assignment result, the step further includes: Identify the triggering situation of the shadow mode, and determine whether the triggering situation of the shadow mode is a false triggering situation according to the identification result; When the triggering condition of the shadow mode is a false triggering condition, the shadow data corresponding to the shadow mode is filtered and an early warning prompt is sent; When the triggering situation of the shadow mode is not a false triggering situation, the steps of determining the target evaluation index according to the scene recognition result, assigning points to the target evaluation index, and obtaining the index assignment result are performed.

4. The intelligent driving function scoring method according to claim 1, characterized in that: The step of determining the target evaluation index of the scene data according to the scene recognition result, assigning points to the target evaluation index, and obtaining the index assignment result includes: Determining target evaluation indicators of the scene data according to the scene recognition result, and determining the indicator level and importance of each target evaluation indicator; Based on the preset total evaluation score, the indicator level and the degree of importance, each of the target evaluation indicators is scored to obtain an indicator scoring result.

5. The intelligent driving function scoring method according to claim 1, characterized in that: The step of determining the overall score of the scenario according to the indicator scoring result and the preset indicator score rate corresponding to the target evaluation indicator includes: Determine the triggering times of the shadow mode in each speed segment and the single item score of the scene in the current scene according to the index scoring result and the preset index score rate corresponding to the target evaluation index; Determine the average scene score of each speed segment in the current scene according to the triggering times of the shadow mode of each speed segment in the current scene and the scene single item score; Performing weight configuration on the current scene according to each speed segment to obtain a weight configuration result of each speed segment of the current scene; The overall scenario score is determined based on the scenario score average and the weight configuration result.

6. The intelligent driving function scoring method according to claim 1, characterized in that: The step of determining the expected scene score corresponding to the scene recognition result, comparing the expected scene score with the overall scene score, and feeding back prompt information according to the comparison result includes: Determine the scene expected score corresponding to the scene recognition result by querying the scene expected score table; Compare the scenario expected score with the scenario overall score, and determine whether the scenario overall score is less than the scenario expected score based on the comparison result; If the overall score of the scenario is less than the expected score of the scenario, a warning prompt message is fed back; If the overall score of the scenario is not less than the expected score of the scenario, a safety prompt message is fed back.

7. The intelligent driving function scoring method according to claim 6, characterized in that: After the step of feeding back warning information if the overall score of the scenario is less than the expected score of the scenario, the method further includes: Performing data analysis based on the relevant data of the overall score of the scenario, optimizing and upgrading the current intelligent driving system according to the data analysis results, and obtaining an upgraded intelligent driving system; The upgraded intelligent driving system is used for verification to generate a comparison result between the current intelligent driving system and the upgraded intelligent driving system.

8. An intelligent driving function scoring device, characterized in that: The device comprises: A scene recognition module, used to obtain shadow data, perform scene recognition based on the shadow data, and extract corresponding scene data from the shadow data according to the scene recognition result; An indicator scoring module is used to determine the target evaluation indicator of the scene data according to the scene recognition result, and to score the target evaluation indicator to obtain the indicator scoring result; A scenario scoring module is used to determine the overall scenario score based on the indicator scoring result and the preset indicator score rate corresponding to the target evaluation indicator; The information feedback module is used to determine the scene expected score corresponding to the scene recognition result, compare the scene expected score with the scene overall score, and feedback prompt information according to the comparison result.

9. An intelligent driving function scoring device, characterized in that: The device comprises: a memory, a processor, and an intelligent driving function scoring program stored in the memory and executable on the processor, wherein the intelligent driving function scoring program is configured to implement the steps of the intelligent driving function scoring method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores an intelligent driving function scoring program, and when the intelligent driving function scoring program is executed by the processor, the steps of the intelligent driving function scoring method according to any one of claims 1 to 7 are implemented.

Images