Intelligent teaching method and system for road test training

Abstract

The invention provides an intelligent teaching method and system for road test training, and relates to the technical field of driving training, and the method comprises the steps: obtaining real-time driving information, obtaining real-time environment information, inputting the real-time driving information and the real-time environment information into a driving risk degree prediction model, and obtaining a real-time prediction risk degree; and judging whether the real-time predicted risk degree is in a preset risk degree threshold, acquiring a real-time driving operation video through a vehicle-mounted camera, analyzing the real-time driving operation video to generate a real-time teaching decision, and performing dynamic teaching optimization on the student according to the real-time teaching decision. The technical problem that a road test training mode lacks real-time and accurate data support and targeted teaching optimization in the prior art is solved. The technical effects of comprehensively evaluating the driving behavior of the trainee in real time, performing targeted teaching optimization and improving the driving skill of the trainee by combining the real-time driving information and the environment data are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of driving training, and in particular to an intelligent teaching method and system for road test training. Background Art

[0002] Existing road test training usually relies on traditional teaching methods, including students undergoing driving training under the guidance of a coach, and the coach providing verbal guidance and corrections based on the student's performance. However, this method has some limitations. First, the coach's teaching experience and subjective judgment have a great impact on the student's guidance effect, which may lead to differences in teaching effects between different coaches and students. Secondly, traditional road test training cannot monitor the student's driving behavior and surrounding environment in real time and comprehensively, making it difficult to detect and correct potential safety hazards in a timely manner. Moreover, during the road test training process, students can only rely on the coach's verbal feedback or post-test performance evaluation to understand their shortcomings in driving skills, which lacks sufficient timeliness and accuracy.

[0003] The existing road test training model lacks real-time, accurate data support and technical problems of targeted teaching optimization. Summary of the invention

[0004] The present application provides an intelligent teaching method and system for road test training, which is used to solve the technical problem that the road test training model in the prior art lacks real-time, accurate data support and targeted teaching optimization.

[0005] In view of the above problems, the present application provides an intelligent teaching method and system for road test training.

[0006] In a first aspect of the present application, an intelligent teaching method for road test training is provided, the method comprising: obtaining real-time driving information, the real-time driving information refers to vehicle driving information obtained by dynamically monitoring the training vehicle through a running sensor device mounted on the training vehicle; obtaining real-time environmental information, the real-time environmental information refers to environmental information obtained by dynamically monitoring the training vehicle through an environmental sensor device mounted on the training vehicle; activating a driving hazard prediction model, and inputting the real-time driving information and the real-time environmental information into the driving hazard prediction model to obtain a real-time predicted hazard; determining whether the real-time predicted hazard is within a predetermined hazard threshold; if it is not within the predetermined hazard threshold, linking an on-board camera on the training vehicle, and obtaining a real-time driving operation video through the on-board camera, wherein the real-time driving operation video refers to a monitoring video of the driving vehicle operation of a trainee on the training vehicle; analyzing the real-time driving operation video to generate a real-time teaching decision, and dynamically optimizing the teaching for the trainee according to the real-time teaching decision.

[0007] According to a second aspect of the present application, an intelligent teaching system for road test training is provided, the system comprising: a driving information acquisition module, for acquiring real-time driving information, wherein the real-time driving information refers to vehicle driving information obtained by dynamically monitoring the training vehicle through a running sensor device mounted on the training vehicle; an environmental information acquisition module, for acquiring real-time environmental information, wherein the real-time environmental information refers to environmental information obtained by dynamically monitoring the training vehicle through an environmental sensor device mounted on the training vehicle; a prediction model activation module, for activating a driving risk prediction model, and inputting the real-time driving information and the real-time environmental information into the driving risk prediction model to obtain a real-time predicted risk; a predicted risk judgment module, for judging whether the real-time predicted risk is within a predetermined risk threshold; a monitoring video acquisition module, for judging if it is not within the predetermined risk threshold, linking the on-board camera of the training vehicle, and acquiring a real-time driving operation video through the on-board camera, wherein the real-time driving operation video refers to a monitoring video of the driving vehicle operation of the trainee on the training vehicle; and a teaching decision generation module, for analyzing the real-time driving operation video to generate a real-time teaching decision, and dynamically optimizing the teaching of the trainee according to the real-time teaching decision.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The method provided in the embodiment of the present application obtains real-time driving information, obtains real-time environmental information, activates a driving danger prediction model, and inputs the real-time driving information and the real-time environmental information into the driving danger prediction model to obtain a real-time predicted danger, judges whether the real-time predicted danger is within a predetermined danger threshold, links the on-board camera on the training vehicle, and obtains a real-time driving operation video through the on-board camera, wherein the real-time driving operation video refers to a monitoring video of the driving vehicle operation of the trainee on the training vehicle, analyzes the real-time driving operation video to generate a real-time teaching decision, and dynamically optimizes the teaching of the trainee according to the real-time teaching decision. The technical effect of combining real-time driving information and environmental data, comprehensively and in real time evaluating the trainee's driving behavior and conducting targeted teaching optimization, thereby improving the trainee's driving skills is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A flowchart of the intelligent teaching method for road test training provided in this application;

[0012] Figure 2 A schematic diagram of the structure of the intelligent teaching system for road test training provided in this application.

[0013] Explanation of the reference numerals: driving information acquisition module 11 , environmental information acquisition module 12 , prediction model activation module 13 , prediction risk judgment module 4 , monitoring video acquisition module 15 , teaching decision generation module 16 . DETAILED DESCRIPTION

[0014] This application provides an intelligent teaching method and system for road test training, which is used to solve the technical problem that the road test training model in the prior art lacks real-time, accurate data support and targeted teaching optimization. It achieves the technical effect of combining real-time driving information and environmental data, evaluating the driving behavior of students in real time and performing targeted teaching optimization, thereby improving the driving skills of students.

[0015] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides an intelligent teaching method for road test training, the method comprising:

[0017] Step S100, obtaining real-time driving information, wherein the real-time driving information refers to vehicle driving information obtained by dynamically monitoring the training vehicle through a running sensor device mounted on the training vehicle.

[0018] Specifically, a series of operation sensing devices are installed on the road test training vehicle, and the operation sensing devices can monitor the dynamic driving state of the vehicle in an all-round and high-precision manner. The operation sensing devices include the vehicle's wheel speed sensor, acceleration sensor, gyroscope sensor, steering angle sensor, etc. Each sensor works together to capture the motion state and driving trajectory of the training vehicle in real time. Furthermore, based on the real-time monitoring of the motion state and driving trajectory of the training vehicle by the operation sensing devices mounted on the training vehicle, the real-time driving information of the vehicle is formed. The real-time driving information, such as the current speed, acceleration, steering angle, lane deviation, braking condition, etc. of the vehicle, reflects the driver's operation behavior of the vehicle. By using the operation sensing equipment to monitor the dynamic driving of the vehicle, the real-time vehicle driving information of the training vehicle in the driving environment can be obtained, providing comprehensive and accurate basic data support for the intelligent teaching method, helping students to promptly discover and correct driving errors, thereby effectively improving the efficiency and effectiveness of road test training.

[0019] Step S200, acquiring real-time environmental information, wherein the real-time environmental information refers to environmental information obtained by dynamically monitoring the environment of the training vehicle through an environmental sensor device mounted on the training vehicle.

[0020] Specifically, while obtaining the real-time driving information of the training vehicle, the environmental sensing equipment deployed on the training vehicle is used to dynamically monitor and collect data related to the training vehicle's driving environment. Environmental sensing equipment refers to a variety of sensors and monitoring equipment used to collect real-time information about the environment around the training vehicle, such as temperature and humidity sensors, tire pressure sensors, light intensity sensors, etc. Through environmental sensing equipment, the dynamic environmental information of the training vehicle is monitored and collected to form real-time environmental information. The real-time environmental information includes environmental factors such as road conditions, weather changes, traffic density, and surrounding obstacles. By obtaining real-time environmental information, more comprehensive and accurate data support is provided for road test training, so that teaching decisions can provide accurate guidance to students based on real-time data, helping students make correct judgments and decisions in complex and changing driving environments, thereby effectively improving students' driving skills and ability to deal with emergencies.

[0021] Step S300, activating a driving risk prediction model, and inputting the real-time driving information and the real-time environmental information into the driving risk prediction model to obtain a real-time predicted risk.

[0022] Specifically, the driving danger prediction model is a model built based on big data and machine learning algorithms. It is obtained by deep learning and training historical road test training record data, and can identify and predict the degree of danger in various driving environments. After collecting real-time driving information and real-time environmental information, the pre-trained driving danger prediction model is activated, and the real-time driving information and the real-time environmental information are used as input data and input into the driving danger prediction model for processing. The driving danger prediction model takes into account the changes in the student's driving behavior and the external environment according to the pre-trained rules, and outputs the real-time predicted danger. The real-time predicted danger is a numerical indicator that reflects the safety risk level under the current driving behavior and environmental conditions. The higher the real-time predicted danger, the greater the risk of the current driving. For example, if the driving danger prediction model finds that the current student is driving at too fast a speed, and the surrounding traffic environment is congested, or there are dangerous factors such as water accumulation or ice and snow on the road, a higher danger will be calculated, indicating that the driving behavior has a higher risk. On the contrary, if the student drives more steadily and the external environment is good, the danger will be relatively low. By inputting real-time driving information and real-time environmental information into the driving hazard prediction model, the current driving hazard can be assessed quickly and accurately, providing intelligent support for subsequent teaching decisions and safety interventions, thereby improving road safety and teaching effectiveness.

[0023] Step S400, determining whether the real-time predicted risk level is within a predetermined risk level threshold.

[0024] Step S500, if it is not within the predetermined danger level threshold, the vehicle-mounted camera on the training vehicle is linked to obtain a real-time driving operation video through the vehicle-mounted camera, wherein the real-time driving operation video refers to the driving vehicle operation monitoring video of the trainee on the training vehicle.

[0025] Specifically, the real-time predicted danger level of the current driving process is obtained through the driving danger level prediction model, and on this basis, the real-time predicted danger level is compared with the preset danger level threshold. The preset danger level threshold is a value determined based on factors such as safety standards, historical data, and training objectives. It represents the tolerance range of driving behavior under specific driving conditions and is used to distinguish between safe driving states and potentially dangerous driving states. If the real-time predicted danger level is lower than the preset danger level threshold, it is considered that the student's driving behavior meets the safety standards and no further intervention is required, and the teaching process continues. If the real-time predicted danger level is not within the preset danger level threshold, that is, the real-time predicted danger level is equal to or higher than the preset danger level threshold, it means that the current driving behavior has a high safety risk and potential danger, and intervention and optimization are required.

[0026] Furthermore, when the real-time predicted danger level is equal to or higher than the predetermined danger level threshold, the on-board camera on the training vehicle is automatically linked. The on-board camera is installed in the training vehicle and is responsible for recording the trainee's driving operation process, such as hand and foot operation, steering wheel rotation, accelerator and brake movements, etc. The real-time driving operation monitoring video of the trainee on the training vehicle is obtained through the on-board camera. The real-time driving operation video refers to the video record of the whole process of monitoring the driving operation of the trainee on the training vehicle, which has real-time and high precision. Real-time means that the video is recorded in real time during the driving process to ensure that it can truly reflect the driving behavior of the trainee. High precision means that the on-board camera has high resolution and can clearly capture the specific operations of the trainee, ensuring the reliability and analyzability of the video data, providing comprehensive and intuitive feedback on the trainee's driving behavior for the coach or evaluator, thereby helping the trainee to timely discover and correct improper behavior in the real driving environment, improve the pertinence and effectiveness of teaching, and ensure that the trainee can complete the training under safe and efficient conditions.

[0027] Step S600: Analyze the real-time driving operation video to generate a real-time teaching decision, and dynamically optimize the teaching for the student according to the real-time teaching decision.

[0028] Specifically, after obtaining the real-time driving operation video, the real-time driving operation video is analyzed in detail through video processing algorithms and image recognition technology to identify key driving actions and obtain the driving operation video analysis results. For example, through image recognition, it is detected whether the trainee has improper speed control when turning, whether there is overspeeding or sudden braking, or whether the lane is deviated. And based on the analysis results of the driving operation video, a real-time teaching decision is generated. When generating the teaching decision, the student's behavior will be compared to find out its potential errors or deficiencies. For example, through comparison, it is found that the student did not slow down in time when approaching the intersection. At this time, a teaching decision will be generated to remind the student to slow down and brake in advance. Dynamic teaching optimization is carried out according to the real-time teaching decision, so as to adjust the teaching content and strategy, which can better help students improve their driving skills and enhance safety awareness. Through the teaching mode based on real-time data and dynamic feedback, not only the learning efficiency of the students is improved, but also the problems that the students may encounter in the actual road test training driving can be solved in a targeted manner, which helps to improve the driving skills of the students and ensure the safety and effectiveness of the training process.

[0029] Further, step S100, obtaining real-time driving information, the real-time driving information refers to vehicle driving information obtained by dynamically monitoring the training vehicle through a running sensor device mounted on the training vehicle, and also includes:

[0030] In step S110, the operation sensing device includes one or more of a wheel speed sensor, an acceleration sensor, a gyroscope sensor, a steering angle sensor, a lateral acceleration sensor, a longitudinal acceleration sensor, a yaw rate sensor, an air pressure sensor, a liquid level sensor, a temperature sensor and an oil pressure sensor.

[0031] Specifically, the running sensor equipment is used to monitor and collect various motion state information of the vehicle in real time, and provide basic data support for the driving risk prediction model. Among them, the running sensor equipment includes multiple types of sensors, each of which is responsible for collecting different types of vehicle running data, so as to ensure that the dynamic state of the vehicle can be comprehensively and accurately evaluated. The running sensor equipment includes one or more of the wheel speed sensor, acceleration sensor, gyroscope sensor, steering angle sensor, lateral acceleration sensor, longitudinal acceleration sensor, yaw rate sensor, air pressure sensor, liquid level sensor, temperature sensor and oil pressure sensor. The wheel speed sensor is used to measure the rotation speed of each wheel of the vehicle. By monitoring the rotation speed of each tire, the actual driving speed of the vehicle can be obtained to determine whether the vehicle is speeding or driving smoothly; the acceleration sensor is used to measure the acceleration of the vehicle in different directions; the gyroscope sensor is responsible for measuring the rotation angular velocity of the vehicle to monitor the rotation change of the vehicle during driving; the steering angle sensor is used to measure the rotation angle of the vehicle steering wheel to reflect the driver's steering operation; the lateral acceleration sensor is used to monitor the lateral force of the vehicle when turning to determine whether there is a risk of rollover, and the longitudinal acceleration sensor is mainly used to detect the change in longitudinal acceleration when the vehicle accelerates or brakes; the yaw rate sensor is used to measure the rotation rate of the vehicle around the vertical axis, also called the yaw angular velocity, to determine whether the vehicle has oversteered or deviated from the driving trajectory during driving; the air pressure sensor is mainly used to detect the air pressure state of the vehicle; the liquid level sensor is used to monitor the level change of the vehicle fuel or other liquids; the temperature sensor is used to monitor the temperature of key parts of the vehicle in real time, such as engine temperature, brake system temperature, etc.; the oil pressure sensor is responsible for monitoring the oil pressure state of the vehicle, especially the oil pressure of the engine and oil circuit. By collecting the vehicle's operating status data in real time through the operation sensor equipment on the training vehicle, the vehicle's operating status can be accurately judged, thereby providing comprehensive driving data support for the driving hazard prediction model.

[0032] Further, step S200, obtaining real-time environmental information, the real-time environmental information refers to environmental information obtained by dynamically monitoring the environment of the training vehicle through an environmental sensor device mounted on the training vehicle, and further includes:

[0033] In step S210, the environmental sensing device includes one or more of a rain sensor, a humidity sensor, a temperature sensor, a tire pressure sensor, a road friction coefficient sensor, a light intensity sensor, a fog light sensor, a radar sensor, an image sensor, an ultrasonic sensor, a millimeter wave radar, a lidar, and an air quality sensor.

[0034] Specifically, the environmental sensing device is used to monitor the changes in the vehicle's surrounding environment in real time to provide comprehensive environmental information. The environmental sensing device includes one or more of a rain sensor, a humidity sensor, a temperature sensor, a tire pressure sensor, a road friction coefficient sensor, a light intensity sensor, a fog light sensor, a radar sensor, an image sensor, an ultrasonic sensor, a millimeter wave radar, a lidar, and an air quality sensor. The rain sensor is used to detect the amount of rainfall around the vehicle, monitor the intensity of the rain, and determine whether the current weather conditions affect the slippery road surface, thereby increasing the risk of the vehicle skidding; the humidity sensor is used to measure the humidity of the surrounding air, especially when the temperature is low, higher humidity may cause ice or slipping on the road; the temperature sensor is used to monitor the temperature of the surrounding environment in real time. In cold weather, too low a temperature may cause ice on the road surface, increasing the risk of loss of control; the tire pressure sensor is used to monitor the air pressure status of the vehicle's tires; the road friction coefficient sensor is used to detect the friction of the current road surface. A low friction coefficient indicates that there may be oil, water stains, ice and snow on the road surface, which may cause the vehicle to slip; the light intensity sensor is used to monitor the light intensity in the current environment, and determine whether the road surface is wet or slippery. The fog light sensor is mainly used to determine whether the fog light is in the correct state of use; the radar sensor is used to detect objects or obstacles in front and around through electromagnetic waves, make up for the problem of insufficient sight distance, and identify potential obstacles in time; the image sensor is used to capture images of the surrounding environment, identify road markings, traffic signs, traffic lights, pedestrians, other vehicles, etc., and judge the complexity of the current traffic environment; the ultrasonic sensor is used to detect obstacles around the vehicle at close range; the millimeter wave radar and laser radar are two high-precision sensing devices that scan the surrounding environment through high-frequency electromagnetic waves and laser beams respectively, and are used to accurately identify surrounding obstacles, lane boundaries and other important landmarks; the air quality sensor monitors the degree of pollution in the surrounding air. The environmental sensing equipment can comprehensively evaluate the current driving environment by collecting multi-dimensional data of the surrounding environment in real time, including precipitation, humidity, temperature, tire pressure, road friction, light intensity, air quality, etc., and provide students with timely and accurate driving guidance to ensure that students can drive safely under changing environmental conditions.

[0035] Furthermore, in step S300, before activating the driving risk prediction model and inputting the real-time driving information and the real-time environmental information into the driving risk prediction model to obtain the real-time predicted risk, the method includes:

[0036] Step S301, obtaining historical road test training records based on big data, wherein the historical road test training records include a first historical record;

[0037] Step S302, comparing the first historical driving information in the first historical record with the predetermined driving information to obtain a first comparison result;

[0038] Step S303, performing weighted calculation on the first comparison result after normalization to obtain a first comparison deviation index, and recording the first comparison deviation index as a first historical risk degree;

[0039] Step S304, extracting the first historical environment information from the first historical record, and forming a first data group with the first historical driving information and the first historical risk level;

[0040] Step S305: training the first data set based on the neural network principle to obtain the driving risk prediction model.

[0041] Specifically, historical road test training records are obtained from the road test training big data platform. The historical road test training records include a large number of past training data of trainees. The training data include the trainees' driving information and environmental information. A first historical record is selected from the historical road test training records. The first historical record contains the trainees' driving behaviors and environmental condition information for different environments and road conditions during the historical training process. Then, the first historical driving information is compared with the predetermined driving information. The predetermined driving information refers to the preset driving behavior representing the ideal or standard driving state, such as the driving speed, steering angle and acceleration under specific road conditions. By comparing the trainees' historical driving information and the predetermined driving information, a first comparison result can be obtained, that is, the degree to which the trainees' driving behavior in training deviates from the predetermined standard. For example, the trainees may drive at too fast a speed in a certain section of the journey, or fail to smoothly control the steering wheel when turning. Then, the first comparison result is normalized and converted into a unified scale, and the normalized first comparison result is weighted. According to historical experience and expert experience, different weights are assigned to each comparison result according to its impact on driving safety. For example, excessive speed may be more important than slight steering instability, so speed-related deviations will have a higher weight. Through weighted calculation, a first comparative deviation index is obtained. The first comparative deviation index refers to the degree of deviation between the student's driving behavior and the predetermined driving information, which is used to reflect the current driving danger. After obtaining the first historical danger, the first historical environmental information in the first historical record is extracted, and the first historical environmental information is combined with the first historical driving information and the first historical danger to form a complete first data group. The first data group provides comprehensive training data for neural network training, including the student's driving behavior and external environmental conditions and their corresponding driving danger information. Finally, the first data group is trained based on the principle of neural network. The neural network is a computing model that simulates the working principle of human brain neurons and can learn and extract features from a large amount of data to make predictions. In this process, through training, the neural network can learn the relationship between different types of driving information, environmental information and danger, and automatically adjust the weights and parameters of the network, and finally generate a model that can predict driving danger, that is, a driving danger prediction model. The driving risk prediction model can accurately predict the current driving risk of the trainee based on new inputs, such as real-time driving information and environmental data, to help the trainee identify potential dangerous behaviors in a timely manner, and provide a scientific basis for subsequent dynamic teaching optimization and safety intervention.

[0042] Furthermore, step S302, before comparing the first historical driving information in the first historical record with the predetermined driving information to obtain a first comparison result, includes:

[0043] Step S302-1, reading the scheduled road test constraints;

[0044] Step S302-2, the instructor drives the training vehicle under the predetermined road test constraints to obtain instructor driving information;

[0045] Step S302-3: Analyze the instructor driving information to determine the predetermined driving information.

[0046] Specifically, the predetermined road test constraints are read and parsed. The predetermined road test constraints define the driving rules and conditions that students must abide by during the road driving skills and safe and civilized driving common sense test or training process. The predetermined road test constraints include: speed limit, driving path, safety distance, steering angle and acceleration and deceleration requirements. Then, the instructor uses the training vehicle for actual driving under the predetermined road test constraints to ensure that the teaching process meets the prescribed driving standards and safety requirements. In this process, the instructor will perform driving operations according to the predetermined route, speed, steering angle and other requirements, and at the same time, obtain the instructor's driving information through the running sensor equipment mounted on the training vehicle. After the instructor completes the driving and generates the instructor's driving information, the instructor's driving information is analyzed to extract the predetermined driving information that meets the predetermined road test constraints, such as standard vehicle speed, steering method, braking timing and other key indicators, etc. The predetermined driving information represents the most ideal driving behavior under specific constraints. By analyzing the instructor's driving information under the predetermined road test constraints, the instructor's driving behavior is ensured as a benchmark in the subsequent teaching process, helping students understand and follow the correct road test driving operations, and improving the safety and efficiency of road test driving.

[0047] Furthermore, step S600, analyzing the real-time driving operation video to generate a real-time teaching decision, and dynamically optimizing the teaching for the student according to the real-time teaching decision, further includes:

[0048] Step S610, extracting a first operation video of a first point in the real-time driving operation video, wherein the first point has an identifier of a first associated driving indicator;

[0049] Step S620, matching the first correlation indicator comparison result corresponding to the first correlation driving indicator in the first comparison result;

[0050] Step S630, performing weighted calculation on the normalized first correlation index comparison result to obtain a first correlation comparison deviation index, and recording it as a first correlation risk degree;

[0051] Step S640, determining whether the first associated risk level is within the predetermined risk level threshold;

[0052] Step S650: if the vehicle is not within the predetermined risk threshold, retrieve the driving operation video of the instructor, and extract the first standard operation video of the first point in the driving operation video;

[0053] Step S660: using the first standard operation video as the real-time teaching decision.

[0054] Specifically, first, the real-time driving operation video of the trainee on the training vehicle is analyzed, and a specific segment in the video is extracted, which is called the first operation video of the first point. The first point refers to the specific moment or position of the trainee's operation during the driving process, which is the time point when the key driving action occurs, such as entering an intersection, turning, braking, etc. Each point is associated with its specific first associated driving index, such as turning speed, parking distance or acceleration performance. For example, during the trainee's driving process, a key point is marked, such as the start time of braking. The operation at this moment can be identified by the first associated driving index, which represents the trainee's driving behavior at this moment. Then, the first associated driving index at this moment is compared and matched with the first comparison result to obtain the first associated index comparison result, which reflects the degree of difference between the trainee's driving behavior and the standard behavior. Then, the first associated index comparison result is normalized to convert all comparison results to a unified scale. And the normalized first associated index comparison result is weighted, that is, a certain weight is assigned to each comparison result, and weighted according to its impact on driving safety. Through weighted calculation, the first correlation comparison deviation index is obtained. The first correlation comparison deviation index represents the danger level of the trainee at the specific operation point, which is recorded as the first correlation danger. The first correlation danger reflects the gap between the trainee's driving behavior at the operation point and the safety standard. Then, the first correlation danger is compared with the predetermined danger threshold to determine whether the first correlation danger is within the predetermined danger threshold. If it is lower than the threshold, it means that the trainee's operation meets the safety requirements. If the danger caused by the trainee's driving behavior is equal to or higher than the predetermined threshold, that is, the first correlation danger is not within the predetermined danger threshold, it means that the behavior has a greater safety risk, and the instructor's driving operation video is retrieved. The instructor's driving operation video refers to the standard operation video of the instructor driving the training vehicle under the predetermined road test constraints, which shows how the instructor can operate safely and accurately in the same situation. After retrieving the instructor's driving operation video, the first standard operation video at the same first point in the driving operation video is extracted. This standard operation video shows the instructor's standardized operation at this point. Finally, the first standard operation video is used as a real-time teaching decision to provide clear guidance to the trainees. For example, if a student makes an improper braking operation, the instructor's standard braking operation video will be played to demonstrate how to perform the braking operation correctly. By analyzing the student's driving behavior in detail based on the real-time driving operation video, generating real-time teaching decisions, and dynamically optimizing teaching based on these decisions, it can provide students with accurate and personalized teaching feedback, help students discover and correct improper driving behaviors in a timely manner, and improve driving safety and skill levels.

[0055] Furthermore, in step S640, after determining whether the first associated risk level is within the predetermined risk level threshold, the method further includes:

[0056] Step S641, if the first associated risk level is within the predetermined risk level threshold, extracting a second operation video of a second point in the real-time driving operation video, wherein the second point has an identifier of a second associated driving indicator;

[0057] Step S642, matching the second associated indicator comparison result corresponding to the second associated driving indicator in the first comparison result;

[0058] Step S643, performing weighted calculation on the normalized second correlation index comparison result to obtain a second correlation comparison deviation index, and recording it as a second correlation risk degree;

[0059] Step S644, determining whether the second associated risk level is within the predetermined risk level threshold;

[0060] Step S645: if the vehicle is not within the predetermined risk threshold, retrieve the driving operation video of the instructor, and extract the second standard operation video of the second point in the driving operation video;

[0061] Step S646, using the second standard operation video as the real-time teaching decision.

[0062] Specifically, when the first associated risk level is within the predetermined risk level threshold, it means that the first associated risk level is within the safe range, and then the driving behavior of the trainee is further analyzed, and more operation points are gradually evaluated. At this stage, the next key point is entered, that is, the second operation video of the second point is extracted. The second point represents another key moment or behavior node in the trainee's driving process, such as a moment of turning, sudden braking, changing lanes, etc. during driving. Each operation point will generate a corresponding second associated driving index according to the trainee's behavior and road conditions. Similarly, in the first comparison result, the second associated driving index of the trainee's driving behavior at the second point is matched, and the second associated index comparison result is generated by comparing the trainee's actual driving behavior with the predetermined standard driving behavior, that is, whether the trainee deviates from the standard behavior at the second point. For example, if the trainee does not decelerate appropriately when turning, the deviation of the vehicle speed being too high will be recorded. The second associated index comparison result is normalized to ensure that the dimensions of different indicators are consistent. After normalization, weighted calculation is performed according to the safety importance of each indicator, that is, the impact of key behaviors is highlighted by assigning different weights. For example, overspeeding during a turn may be more dangerous than a slight lane deviation, so a speed deviation during a turn will be given a higher weight. After weighted calculation, the second correlation comparison deviation index is obtained, which reflects the difference between the student's driving behavior and the standard at that moment, and generates the second correlation risk. Then, the second correlation risk is compared with the predetermined risk threshold. If the second correlation risk is not within the predetermined risk threshold, it means that the student is in a certain danger at this operation point. The instructor's driving operation video is retrieved, and the second standard operation video of the second point in the driving operation video is extracted. The second standard operation video shows the instructor's standard operation in the same situation, provides clear guidance to the students, helps the students understand the correct driving method, and uses the second standard operation video as the real-time teaching decision to provide personalized teaching intervention. Through continuous behavior comparison, risk calculation and standard operation demonstration, it is ensured that students can perform dynamic teaching optimization at each key point, gradually improve driving skills, reduce the risk of accidents, thereby realizing intelligent and refined driving training and improving students' driving skills.

[0063] To sum up, the intelligent teaching method for road test training provided in the embodiment of the present application includes at least the following technical effects, which achieves the combination of real-time driving information and environmental data, real-time evaluation of students' driving behavior and targeted teaching optimization, thereby improving students' driving skills and safety.

[0064] Embodiment 2, based on the same inventive concept as the intelligent teaching method for road test training in the above embodiment, Figure 2 As shown, the present application provides an intelligent teaching system for road test training, wherein the system includes:

[0065] The driving information acquisition module 11 is used to acquire real-time driving information, and the real-time driving information refers to the vehicle driving information obtained by the running sensor equipment mounted on the training vehicle to dynamically monitor the training vehicle; the environmental information acquisition module 12 is used to acquire real-time environmental information, and the real-time environmental information refers to the environmental information obtained by the environmental sensor equipment mounted on the training vehicle to dynamically monitor the training vehicle; the prediction model activation module 13 is used to activate the driving risk prediction model, and input the real-time driving information and the real-time environmental information into the driving risk prediction model to obtain the real-time predicted risk; the predicted risk judgment module 14 is used to judge whether the real-time predicted risk is within the predetermined risk threshold; the monitoring video acquisition module 15 is used to judge if it is not within the predetermined risk threshold, link the vehicle-mounted camera on the training vehicle, and obtain the real-time driving operation video through the vehicle-mounted camera, wherein the real-time driving operation video refers to the vehicle driving operation monitoring video of the trainee on the training vehicle; the teaching decision generation module 16 is used to analyze the real-time driving operation video to generate a real-time teaching decision, and dynamically optimize the teaching for the trainee according to the real-time teaching decision.

[0066] Furthermore, the operation sensing device in the driving information acquisition module 11 includes one or more of a wheel speed sensor, an acceleration sensor, a gyroscope sensor, a steering angle sensor, a lateral acceleration sensor, a longitudinal acceleration sensor, a yaw rate sensor, an air pressure sensor, a liquid level sensor, a temperature sensor and an oil pressure sensor.

[0067] Furthermore, the environmental sensing device in the environmental information acquisition module 12 includes one or more of a rain sensor, a humidity sensor, a temperature sensor, a tire pressure sensor, a road friction coefficient sensor, a light intensity sensor, a fog light sensor, a radar sensor, an image sensor, an ultrasonic sensor, a millimeter wave radar, a lidar and an air quality sensor.

[0068] Furthermore, the prediction model activation module 13 is also used to perform the following steps: obtaining historical road test training records based on big data, the historical road test training records including a first historical record; comparing the first historical driving information in the first historical record with the predetermined driving information to obtain a first comparison result; performing weighted calculation on the normalized first comparison result to obtain a first comparison deviation index, and recording the first comparison deviation index as a first historical hazard level; extracting the first historical environmental information in the first historical record, and forming a first data group with the first historical driving information and the first historical hazard level; training the first data group based on the principle of a neural network to obtain the driving hazard level prediction model.

[0069] Furthermore, the prediction model activation module 13 is also used to perform the following steps: reading the predetermined road test constraints; the instructor drives the training vehicle under the predetermined road test constraints to obtain instructor driving information; and analyzing the instructor driving information to determine the predetermined driving information.

[0070] Furthermore, the teaching decision generation module 16 is also used to perform the following steps: extracting a first operation video of a first point in the real-time driving operation video, wherein the first point has an identification of a first associated driving indicator; matching a first associated indicator comparison result corresponding to the first associated driving indicator in the first comparison result; performing weighted calculation on the normalized first associated indicator comparison result to obtain a first associated comparison deviation index, and recording it as a first associated risk; determining whether the first associated risk is within the predetermined risk threshold; if it is not within the predetermined risk threshold, retrieving the instructor's driving operation video, and extracting a first standard operation video of the first point in the driving operation video; and using the first standard operation video as the real-time teaching decision.

[0071] Furthermore, the teaching decision generation module 16 is also used to perform the following steps: if the first associated risk level is within the predetermined risk level threshold, extract a second operation video of a second point in the real-time driving operation video, wherein the second point has an identifier of a second associated driving indicator; match the second associated indicator comparison result corresponding to the second associated driving indicator in the first comparison result; perform weighted calculation on the normalized second associated indicator comparison result to obtain a second associated comparison deviation index, and record it as a second associated risk level; determine whether the second associated risk level is within the predetermined risk level threshold; if it is not within the predetermined risk level threshold, retrieve the instructor's driving operation video, and extract a second standard operation video of the second point in the driving operation video; and use the second standard operation video as the real-time teaching decision.

[0072] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0073] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An intelligent teaching method for road test training, characterized in that: include: Acquiring real-time driving information, wherein the real-time driving information refers to vehicle driving information obtained by dynamically monitoring the training vehicle through a running sensor device mounted on the training vehicle; Acquiring real-time environmental information, wherein the real-time environmental information refers to environmental information obtained by dynamically monitoring the environment of the training vehicle through an environmental sensor device mounted on the training vehicle; activating a driving risk prediction model, and inputting the real-time driving information and the real-time environmental information into the driving risk prediction model to obtain a real-time predicted risk; Determining whether the real-time predicted risk level is within a predetermined risk level threshold; If the vehicle is not within the predetermined risk threshold, the vehicle camera on the training vehicle is linked to obtain a real-time driving operation video through the vehicle camera, wherein the real-time driving operation video refers to a monitoring video of the driving operation of the trainee on the training vehicle; The real-time driving operation video is analyzed to generate a real-time teaching decision, and the dynamic teaching optimization is performed on the student according to the real-time teaching decision.

2. The intelligent teaching method for road test training according to claim 1, characterized in that: The operation sensing device includes one or more of a wheel speed sensor, an acceleration sensor, a gyroscope sensor, a steering angle sensor, a lateral acceleration sensor, a longitudinal acceleration sensor, a yaw rate sensor, an air pressure sensor, a liquid level sensor, a temperature sensor and an oil pressure sensor.

3. The intelligent teaching method for road test training according to claim 1 is characterized in that: The environmental sensing device includes one or more of a rain sensor, a humidity sensor, a temperature sensor, a tire pressure sensor, a road friction coefficient sensor, a light intensity sensor, a fog light sensor, a radar sensor, an image sensor, an ultrasonic sensor, a millimeter wave radar, a lidar and an air quality sensor.

4. The intelligent teaching method for road test training according to claim 1, characterized in that: Before activating the driving risk prediction model and inputting the real-time driving information and the real-time environment information into the driving risk prediction model to obtain the real-time predicted risk, the method includes: Acquire historical road test training records based on big data, wherein the historical road test training records include first historical records; Comparing the first historical driving information in the first historical record with the predetermined driving information to obtain a first comparison result; Performing weighted calculation on the first comparison result after normalization to obtain a first comparison deviation index, and recording the first comparison deviation index as a first historical risk degree; Extracting first historical environmental information from the first historical record, and forming a first data group with the first historical driving information and the first historical risk level; The first data group is trained based on the neural network principle to obtain the driving risk prediction model.

5. The intelligent teaching method for road test training according to claim 4 is characterized in that: Before comparing the first historical driving information in the first historical record with the predetermined driving information to obtain a first comparison result, the method includes: Read the scheduled road test constraints; The instructor drives the training vehicle under the predetermined road test constraints to obtain instructor driving information; The instructor driving information is analyzed to determine the predetermined driving information.

6. The intelligent teaching method for road test training according to claim 5, characterized in that: The analyzing the real-time driving operation video to generate a real-time teaching decision, and dynamically optimizing the teaching for the student according to the real-time teaching decision, includes: Extracting a first operation video of a first point in the real-time driving operation video, wherein the first point has an identifier of a first associated driving indicator; matching a first associated indicator comparison result corresponding to the first associated driving indicator in the first comparison result; Performing weighted calculation on the normalized comparison result of the first correlation index to obtain a first correlation comparison deviation index, and recording it as a first correlation risk degree; determining whether the first associated risk level is within the predetermined risk level threshold; If the vehicle is not within the predetermined risk threshold, calling up the driving operation video of the instructor, and extracting a first standard operation video of the first point in the driving operation video; Use the first standard operation video as the real-time teaching decision.

7. The intelligent teaching method for road test training according to claim 6, characterized in that: After determining whether the first associated risk level is within the predetermined risk level threshold, the method further includes: If the first associated risk level is within the predetermined risk level threshold, extracting a second operation video of a second point in the real-time driving operation video, wherein the second point has an identifier of a second associated driving indicator; matching a second associated indicator comparison result corresponding to the second associated driving indicator in the first comparison result; Performing weighted calculation on the normalized second correlation index comparison result to obtain a second correlation comparison deviation index, and recording it as a second correlation risk degree; determining whether the second associated risk level is within the predetermined risk level threshold; If the vehicle is not within the predetermined risk threshold, calling up the driving operation video of the instructor, and extracting a second standard operation video of the second point in the driving operation video; Use the second standard operation video as the real-time teaching decision.

8. An intelligent teaching system for road test training, characterized in that: The intelligent teaching system for road test training is used to execute the steps of any one of the intelligent teaching methods for road test training in claims 1 to 7, and the intelligent teaching system for road test training includes: A driving information acquisition module, used to acquire real-time driving information, wherein the real-time driving information refers to vehicle driving information obtained by dynamically monitoring the training vehicle through a running sensor device mounted on the training vehicle; An environmental information acquisition module, used to acquire real-time environmental information, wherein the real-time environmental information refers to environmental information obtained by dynamically monitoring the environment of the training vehicle through an environmental sensor device mounted on the training vehicle; A prediction model activation module, used for activating the driving risk prediction model, and inputting the real-time driving information and the real-time environmental information into the driving risk prediction model to obtain a real-time predicted risk; A predicted risk level judgment module, used to judge whether the real-time predicted risk level is within a predetermined risk level threshold; A monitoring video acquisition module, used to determine if the vehicle is not within the predetermined risk threshold, link the vehicle-mounted camera on the training vehicle, and acquire a real-time driving operation video through the vehicle-mounted camera, wherein the real-time driving operation video refers to a monitoring video of the driving operation of the trainee on the training vehicle; The teaching decision generation module is used to analyze the real-time driving operation video to generate a real-time teaching decision, and dynamically optimize the teaching for the students according to the real-time teaching decision.

Images