Platform construction method based on driving training teaching platform

Abstract

The invention discloses a platform construction method based on a driving training teaching platform, and relates to the technical field of driving training teaching. Comprising the following steps of performing demand analysis and scene modeling, designing a dynamic training path optimization algorithm, constructing a highly-simulated virtual driving environment, designing a real-time driving behavior monitoring and feedback mechanism, identifying typical error modes of trainees in different driving scenes, constructing a learning map, designing a driving risk prediction model and embedding the driving risk prediction model into a platform. And completing the construction of the platform. According to the platform construction method based on the driving training teaching platform, a dynamic training path optimization algorithm, a multi-dimensional data fusion model and a driving risk prediction model are introduced, so that the problem of insufficient response to individual demands of trainees in a traditional driving training platform is solved. The platform can collect driving operation data, environmental factors and physiological state information of trainees in real time, and generate highly personalized training task paths and immediate feedback in combination with historical behavior data and training tracks of the trainees.

Description

Technical Field

[0001] The present invention relates to the technical field of driving training teaching, and specifically provides a method for constructing a platform based on a driving training teaching platform. Background Art

[0002] With the progress of intelligent driving technology and data collection means, driving training is gradually developing towards data-driven, personalized, and intelligent directions. Traditional driving training platforms mainly rely on coaches' intuitive judgments and simple learning modules for teaching, and there are many deficiencies, such as the singularity of training content, the neglect of students' personalized needs, the lag of the feedback mechanism, etc. Existing technologies usually focus on static task allocation, data analysis, and evaluation, lacking dynamic monitoring and personalized feedback on students' real-time driving behaviors, and also failing to fully consider the influence of students' operation errors and environmental factors in complex driving scenarios.

[0003] Although current driving training platforms can provide certain operation simulations, they mostly rely on basic error statistics and general feedback, lacking in-depth training path optimization and risk prediction functions. Existing path optimization methods are mostly based on simple task difficulty or time arrangement, ignoring the dynamic changes in students' abilities and learning progress. In addition, although some platforms collect driving data through sensors, most applications are limited to recording students' basic operations and do not further deeply integrate multi-dimensional data, resulting in insufficient personalization and pertinence in students' training effects. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the present invention provides a method for constructing a platform based on a driving training teaching platform to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions: In the first aspect, an embodiment of the present invention provides a method for constructing a platform based on a driving training teaching platform, including the following steps: S1. Conduct requirement analysis and scenario modeling; S2. Based on the results of scenario modeling, design a dynamic training path optimization algorithm to provide a personalized learning path; S3. Based on the personalized learning path, construct a highly simulated virtual driving environment; S4. Based on the virtual driving environment, design a real-time driving behavior monitoring and feedback mechanism; S5. Based on the data fed back by the mechanism, identify the typical error patterns of students in different driving scenarios; S6. According to the typical error patterns, construct a learning map; S7. Design a driving risk prediction model and embed it into the platform to complete the construction of the platform.

[0006] Further optimize this technical solution. In step S1: Requirement analysis: By analyzing the characteristics of the driving training industry, extract the common and personalized requirements of the learning paths of trainees, the teaching methods of coaches, and the platform usage requirements of managers. Scenario modeling: Transform the requirements into technical implementation goals, including simulated driving scenarios, real-time learning feedback, and teaching interaction.

[0007] Further optimize this technical solution. In step S2, design a path optimization model to construct a dynamic training path optimization algorithm, and generate a personalized training path by combining the real-time performance, ability level, and learning habits of trainees. In the path optimization model, set that the training path consists of multiple training tasks The path optimization model selects the optimal training task sequence for trainees to maximize the comprehensive learning benefit of trainees; The path optimization model includes a comprehensive learning benefit function, a dynamic weight adjustment formula, and a task sorting formula.

[0008] Further optimize this technical solution. In the path optimization model: The comprehensive learning benefit function is as follows: ; Among them, : The comprehensive benefit value of task ; : The skill matching degree of task , that is, the matching degree between the trainee's current ability and the task difficulty; : The weak point repair value of task , that is, the error frequency of this skill in the trainee's historical data; : The training fatigue value of task , that is, the learning interest attenuation value caused by the similarity between the task and the previous task; : The weight coefficient, which is dynamically adjusted according to the personalized needs of trainees; The dynamic weight adjustment formula is as follows: ; Among them, : The trainee's current ability level vector; : The trainee's historical training record vector; : Weight adjustment function based on the current state and historical data of the trainee; The task sorting formula is as follows: ; The task sorting formula selects a set of training tasks such that the comprehensive learning benefit is maximized.

[0009] To further optimize this technical solution, when the path optimization model is used, it includes: Input data; Calculation steps: Calculate skill matching degree, calculate weak point repair value, calculate training fatigue value, comprehensive benefit calculation and sorting; Output result; Dynamic adjustment.

[0010] To further optimize this technical solution, in step S4, the real-time driving behavior monitoring and feedback mechanism captures the trainee's driving operations and physiological states through sensors, and designs a multi-dimensional data fusion model to judge whether their performance meets the expectations; The driving operations include steering wheel angle, braking force, and throttle pressure; The physiological states include heart rate, pupil diameter, and eye movement trajectory.

[0011] To further optimize this technical solution, in the multi-dimensional data fusion model, the set multi-dimensional data includes: Driving operation data , including steering wheel angle, braking force, and throttle pressure; Environmental data , including road type, weather conditions, and traffic flow; Physiological state data , including heart rate, pupil diameter, and eye movement trajectory.

[0012] To further optimize this technical solution, the multi-dimensional data fusion model includes a fusion weight calculation formula, a data fusion formula, a performance deviation detection formula, and a real-time feedback generation formula; The fusion weight calculation formula is used to represent the contribution degree of different dimension data to driving behavior; The data fusion formula is used to comprehensively measure the driving behavior performance of the trainee; The performance deviation detection formula is used to measure the deviation degree between the current behavior and the ideal behavior; The real-time feedback generation formula is used to generate feedback.

[0013] To further optimize this technical solution, in step S6, constructing a learning map includes: Dynamically reorganize the knowledge point structure of driving training, and divide the driving knowledge points into three levels: basic operation category, scenario application category, and complex task category; Represent the knowledge mastery path of the trainee through a graph structure, where the nodes represent knowledge points and the edges represent learning logical relationships.

[0014] Further optimize the technical solution. In step S7, the driving risk prediction model uses time series analysis method to predict the possible risk points in the future driving of the trainee, generates a risk report after each training, and puts forward improvement suggestions.

[0015] In a second aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program instructions are executed by the processor, the steps of a platform construction method based on a driving training teaching platform as described in the first aspect of the present invention are implemented.

[0016] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program instructions are executed by the processor, the steps of a platform construction method based on a driving training teaching platform as described in the first aspect of the present invention are implemented.

[0017] Compared with the prior art, the present invention provides a platform construction method based on a driving training teaching platform, belonging to the technical fields of intelligent transportation Internet of Things application services and customer interaction services, and having the following beneficial effects: The platform construction method based on the driving training teaching platform overcomes the problem of insufficient response to the personalized needs of trainees in traditional driving training platforms by introducing a dynamic training path optimization algorithm, a multi-dimensional data fusion model, and a driving risk prediction model. The platform can collect the driving operation data, environmental factors, and physiological state information of trainees in real time, and generate a highly personalized training task path and instant feedback in combination with the historical behavior data and training trajectories of trainees. By dynamically adjusting the training content in real time, the system can accurately identify the weak points and potential risks of trainees, so as to provide more targeted training guidance, significantly improve the efficiency and safety of driving training. This data-driven intelligent teaching method can not only improve the operation skills of trainees, but also enhance their ability to cope with complex driving environments, thus effectively reducing driving risks and promoting the development of driving training towards a more scientific and intelligent direction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic flow chart of a platform construction method based on a driving training teaching platform proposed by the present invention; Figure 2 It is a specific composition schematic diagram of a multi-dimensional data fusion model in a platform construction method based on a driving training teaching platform proposed by the present invention. Detailed implementation manners

[0020] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the detailed implementation manners of the present invention with reference to the accompanying drawings of the specification.

[0021] In the following description, many specific details are set forth to facilitate a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0022] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The "in one embodiment" appearing in different places in this specification does not all refer to the same embodiment, nor is it an embodiment that is separate or selectively mutually exclusive with other embodiments.

[0023] Embodiment 1: Refer to Figures 1 to 2 , which is the first embodiment of the present invention. This embodiment provides a platform construction method based on a driving training teaching platform, including the following steps: S1. Conduct requirement analysis and scenario modeling.

[0024] In this embodiment, for requirement analysis, by analyzing the characteristics of the driving training industry, the common and personalized requirements of the learning paths of trainees, the teaching methods of coaches, and the platform usage requirements of managers are refined; For scenario modeling, the requirements are transformed into technical implementation goals, including simulated driving scenarios, real-time learning feedback, and teaching interactions.

[0025] Meanwhile, in the modeling, it is also necessary to determine the core functional modules of the platform and their interaction logics to ensure the systematicness and forward-looking of subsequent designs.

[0026] S2. Based on the results of scenario modeling, design a dynamic training path optimization algorithm to provide personalized learning paths.

[0027] In this embodiment, a path optimization model is designed to construct a dynamic training path optimization algorithm, and combined with the real-time performance, ability level, and learning habits of trainees, a personalized training path is generated; In the path optimization model, it is set that the training path consists of multiple training tasks The path optimization model selects the optimal training task sequence for the trainee to maximize the comprehensive learning benefit of the trainee; The path optimization model includes a comprehensive learning benefit function, a dynamic weight adjustment formula, and a task sorting formula.

[0028] Furthermore, in the path optimization model: The comprehensive learning benefit function is as follows: ; Wherein, : The comprehensive benefit value of task ; : The skill matching degree of task , that is, the matching degree between the trainee's current ability and the task attributes; : The weak point repair value of task , that is, the error frequency of this skill in the trainee's historical data; : The training fatigue value of task , that is, the learning interest attenuation value caused by the similarity between the task and the previous task; : The weight coefficient, which is dynamically adjusted according to the trainee's personalized needs.

[0029] The dynamic weight adjustment formula is as follows: ; Wherein, : The trainee's current ability level vector; In this embodiment, for example, the following ability level vectors can be set: Emergency acceleration control ability : 80 points (full score 100), indicating that the trainee performs well in emergency acceleration control; Emergency braking control ability : 70 points, indicating that the trainee has certain deficiencies in emergency braking operations; Cornering driving skill : 60 points, indicating obvious technical short - boards in sharp - corner driving; Complex road condition response ability : 85 points, indicating a relatively rapid response to complex environments.

[0030] : The trainee's historical training record vector; In this embodiment, for example, the following historical training record vectors can be set: Historical performance of rapid acceleration control : 7 out of 10 trainings are qualified, that is, 0.7; Historical performance of emergency braking control : 15 out of 20 trainings are qualified, that is, 0.75; Historical performance of cornering driving skills : 18 out of 30 trainings are qualified, that is, 0.6; Historical performance of response ability in complex road conditions : 22 out of 25 trainings are qualified, that is, 0.88.

[0031] : The weight adjustment function based on the current state and historical data of the trainee dynamically generates , , 's weight coefficients, reflecting the importance and reliability of skills in different tasks. The weight adjustment function usually calculates weights through weighted average, linear combination or non-linear mapping, enabling it to flexibly adapt to the skill differences and training accumulations of trainees, ensuring more accurate and personalized prediction and evaluation results.

[0032] The task sorting formula is as follows: ; The task sorting formula selects a set of training tasks such that the comprehensive learning benefit is maximized.

[0033] Furthermore, when the path optimization model is used, it includes: Input data: The current ability level of the trainee and historical records ; The task set and its attributes (such as task difficulty, corresponding skill points, etc.); The limiting conditions of the trainee's learning path (such as time limit, scenario constraints).

[0034] Calculation steps: Calculate the skill matching degree , and calculate the skill matching degree according to the matching degree between the trainee's ability level and the task attributes. For example, if the trainee has strong ability in cornering driving, the matching degree of this type of task will be lower and the priority will decrease: ; Among them and are the values of the trainee and the task at the skill point respectively. represents the maximum value in the current ability level vector of the trainee, that is, the ability value with the strongest performance of the trainee at all skill points.

[0035] Calculate the weak point repair value , extract the error frequency of the trainee at a certain skill point according to the historical record , and assign high priority to the weak tasks: ; Among them represents all tasks in the task set . In the formula, is used to represent the sum of the error frequencies of all tasks in the task set . Therefore, is mainly used to calculate the proportion of the error rate of task in the total error rate of all tasks.

[0036] Calculate the training fatigue value . If the skill points of the current task and the previous task overlap too much, resulting in a decrease in interest and an increase in fatigue value: ; Among them, : the similarity between task and the previous task . This value reflects the overlap degree of the current task and the previous task in terms of skill points or operation types. The higher the similarity between tasks, the more fatigued the trainee may feel because the task content is too repetitive.

[0037] : the maximum possible similarity value between all tasks in the task set, used as a normalization benchmark to convert the similarity value into a proportion of the fatigue value. Usually, is a preset constant representing the maximum possible value of task similarity.

[0038] This formula is used to measure the relationship between the similarity of the current task and the previous task. If the similarity is too high, the trainee may feel fatigued due to lack of freshness.

[0039] Comprehensive benefit calculation and sorting: Combine calculate the benefit value of each task and sort to generate the optimal path .

[0040] Output result: The system generates a personalized training path for the trainee , and recommends the next task in real time.

[0041] Dynamic adjustment: Update according to the real-time feedback of the trainees and weights , and realize the dynamic optimization of the training path. For example, when a certain ability point of a trainee improves, the priority of the tasks related to this ability will be automatically reduced.

[0042] S3. Based on the personalized learning path, construct a highly realistic virtual driving environment.

[0043] In this embodiment, constructing a highly realistic virtual driving environment is the key to realizing immersive teaching. By introducing physical engine and graphics rendering technology, the real restoration of roads, weather, vehicles and traffic rules is realized. Different from the traditional static driving simulation system, the virtual environment here has high dynamic adaptability and can automatically load relevant scenarios according to the training path selected by the trainees. For example, a simulation scenario of driving at high speed on a rainy night is generated in real time, and the dynamics of the vehicle and the behavior of traffic participants are controlled by algorithms, so as to better match the training goals of the trainees.

[0044] S4. Based on the virtual driving environment, design a real-time driving behavior monitoring and feedback mechanism.

[0045] In this embodiment, the real-time driving behavior monitoring and feedback mechanism captures the driving operations, environment and physiological states of the trainees through sensors, and designs a multi-dimensional data fusion model to judge whether their performance meets the expectations; Furthermore, in the multi-dimensional data fusion model, it is set that the multi-dimensional data includes: Driving operation data , including steering wheel angle, braking force, throttle pressure; Environmental data , including road type, weather conditions, traffic flow; Physiological state data , including heart rate, pupil diameter, eye movement trajectory.

[0046] The multi-dimensional data fusion model includes a fusion weight calculation formula, a data fusion formula, a performance deviation detection formula, and a real-time feedback generation formula.

[0047] Fusion weight calculation formula: Define the fusion weight indicating the contribution degree of data in different dimensions to driving behavior, and calculate it through the following formula: ; where represents the variance of the data dimension, reflecting the impact of its fluctuation on the overall performance.

[0048] Data fusion formula: The fused data is expressed as , used to comprehensively measure students' Driving behavior performance: ; in: It is a data mapping function used to normalize and nonlinearly map different data dimensions to a unified standard; For students at time Real-time operational data, environmental data and physiological status data.

[0049] Performance Deviation Detection Formula: Defining the Deviation Function Measure how much current behavior deviates from ideal behavior: ; in, It is the expected ideal driving behavior, which is derived from a preset driving behavior model or high-level driving data.

[0050] Real-time feedback generation formula: Generate feedback , based on the deviation value and fused data :

[0051] in, is the deviation tolerance threshold.

[0052] When using the multidimensional data fusion model, it includes: Real-time collection of driving operation data , environmental data and physiological status data , and complete normalization preprocessing.

[0053] Dynamically calculate weights based on data fluctuations (variance) , to reflect the importance of each dimension of data in the current scenario. For example, in a complex traffic environment, the weight of environmental data Will be higher.

[0054] Generate comprehensive evaluation value This value comprehensively reflects whether the student's current driving behavior is consistent with expectations.

[0055] Compare With ideal performance , measurement deviation. If If it is large, it means that the student’s current performance deviates from expectations and needs to be corrected in time.

[0056] Through the feedback formula Generate personalized prompts. For example, when occurs, the system will trigger a voice prompt "The current vehicle speed is too fast. Please decelerate immediately."

[0057] S5. Based on the data of mechanism feedback, identify the typical error patterns of the trainee in different driving scenarios.

[0058] In this embodiment, the typical error patterns include braking too early, drifting in curves, etc. Combine data such as error frequency and learning progress for personalized teaching intervention. The intervention mechanism is implemented through augmented reality (AR) and voice guidance. For example, when it is detected that the trainee fails to comply with the right-of-way rules multiple times in simulated city driving, the relevant rule explanations will be automatically played, and the practice frequency of similar scenarios will be increased in the next training, so as to make up for the trainee's knowledge blind spots.

[0059] S6. Build a learning map according to the typical error patterns.

[0060] In this embodiment, building a learning map includes: Dynamically reorganize the knowledge point structure of driving training, and divide the driving knowledge points into three levels: basic operation type, scenario application type, and complex task type; Represent the trainee's knowledge acquisition path through a graph structure, where the nodes represent knowledge points and the edges represent learning logical relationships.

[0061] When the trainee performs excellently in a specific knowledge point, the system can automatically reduce the training volume of the relevant knowledge point, and at the same time strengthen the training of weak links, so as to achieve the optimization of resource allocation.

[0062] S7. Design a driving risk prediction model and embed it into the platform to complete the construction of the platform.

[0063] In this embodiment, the driving risk prediction model uses time series analysis method to predict the possible risk points in the trainee's future driving, generates a risk report after each training, and puts forward improvement suggestions.

[0064] Input the following feature data into the model: Trainee driving habit data (obtained by sorting out typical error patterns) , such as rapid acceleration , rapid braking , number of lane departures , etc.

[0065] Operation error data (obtained by sorting out typical error patterns) , such as the distance of lane departure , the accuracy of steering wheel operation , etc.

[0066] Environmental variable data , such as the reaction time in complex scenarios , weather conditions , etc.

[0067] The model generates an input vector by combining these features: ; Among them, represents the time step of the time series, and the input vector contains all relevant data of the trainee at time moment.

[0068] Through a deep neural network (DNN), we can learn the complex non-linear relationships of the input data and obtain the risk score of the trainee's driving. Suppose there is a neural network with multiple hidden layers, and the output is the driving risk score , and its calculation process can be expressed as: ; Among them, represents the mapping function of the deep neural network. Specifically, the DNN model gradually abstracts the input features through a hierarchical structure and finally predicts the driving risk score of the trainee in a specific scenario.

[0069] To quantify the driving risk of the trainee, we define the risk score as the degree of safe driving risk of the trainee at time . According to the output by the model, the risk index is calculated through the following formula: ; Among them, respectively represent the various risk items output by the model, is the corresponding weight coefficient, reflecting the impact of different risk factors on the overall risk.

[0070] To further accurately quantify the degree of deviation of the trainee's behavior, the risk deviation is introduced to measure the performance deviation of the trainee in the current driving scenario: ; Among them, is the risk score in the ideal driving scenario, representing the expected score in the case of no risk. Through the deviation , the system can judge in real time whether the trainee's driving behavior has excessive risk.

[0071] According to the risk deviation and the driving risk score , personalized feedback is generated: ; Among them, is a set risk threshold. Through this feedback, the trainee can obtain real-time suggestions on driving performance to reduce future risks.

[0072] Based on the above steps, the training teaching construction of the driving training teaching platform is completed.

[0073] Embodiment 2: This embodiment also provides a computer device, applicable to a situation of a platform construction method based on a driving training teaching platform, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement a platform construction method based on a driving training teaching platform as proposed in the above embodiment.

[0074] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements a platform construction method based on a driving training teaching platform as proposed in the above embodiment.

[0075] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0076] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., various media that can store program codes.

[0077] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0078] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), fiber optic devices, and portable compact disc read-only memories (CDROMs). Additionally, a computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0079] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0080] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A method for constructing a platform based on a driving training teaching platform, characterized in that It includes the following steps: S1. Conduct requirement analysis and scenario modeling; S2. Based on the results of scenario modeling, design a dynamic training path optimization algorithm to provide personalized learning paths; S3. Based on the personalized learning paths, construct a highly simulated virtual driving environment; S4. Based on the virtual driving environment, design a real-time driving behavior monitoring and feedback mechanism; S5. Based on the data fed back by the mechanism, identify the typical error patterns of trainees in different driving scenarios; S6. According to the typical error patterns, construct a learning map; S7. Design a driving risk prediction model and embed it into the platform to complete the construction of the platform.

2. A platform construction method based on a driving training teaching platform according to claim 1, wherein In the step S1: For requirement analysis, by analyzing the characteristics of the driving training industry, extract the commonalities and personalized requirements of trainees' learning paths, coaches' teaching methods, and managers' platform usage requirements; For scenario modeling, transform the requirements into technical implementation goals, including simulating driving scenarios, providing real-time learning feedback, and facilitating teaching interaction.

3. A method for constructing a platform based on a driving training teaching platform according to claim 1, characterized in that, In the step S2, design a path optimization model to construct a dynamic training path optimization algorithm, and generate personalized training paths by combining trainees' real-time performance, ability levels, and learning habits; In the path optimization model, it is assumed that the training path consists of multiple training tasks and the path optimization model selects the optimal training task sequence for the trainee to maximize the comprehensive learning benefit of the trainee. The path optimization model includes a comprehensive learning benefit function, a dynamic weight adjustment formula, and a task sequencing formula.

4. A platform construction method based on a driving training teaching platform according to claim 3, characterized in that, In the path optimization model: The comprehensive learning benefit function is as follows: ； Where, : Task The comprehensive benefit value of; : Task The skill matching degree, that is, the matching degree between the current ability of the trainee and the task difficulty; : Weakness repair value of the task, that is, the error frequency of this skill in the student's historical data; ​ : Training fatigue value of the task, i.e., the learning interest attenuation value caused by the similarity between the task and the previous task; ​ : Weight coefficient, dynamically adjusted according to the personalized needs of the students; The dynamic weight adjustment formula is as follows: ； Where, : The current ability level vector of the trainee; : The historical training record vector of the trainee; : A weight adjustment function based on the current status and historical data of the trainee; The task sequencing formula is as follows: ； The task sorting formula selects a set of training tasks such that the comprehensive learning benefit is maximized.

5. A method for constructing a platform based on a driving training teaching platform according to claim 4, characterized in that, When the path optimization model is in use, it includes: Input data; Calculation steps: calculate skill matching degree, calculate weak point repair value, calculate training fatigue value, conduct comprehensive benefit calculation and ranking; Output results; Dynamic adjustment.

6. A platform construction method based on a driving training teaching platform according to claim 1, characterized in that In the step S4, the real-time driving behavior monitoring and feedback mechanism captures trainees' driving operations and physiological states through sensors, and designs a multi-dimensional data fusion model to determine whether their performance meets the expectations; Driving operations include steering wheel angle, braking force, and throttle pressure; Physiological states include heart rate, pupil diameter, and eye movement trajectory.

7. A method for constructing a platform based on a driving training teaching platform according to claim 6, characterized in that, In the multi-dimensional data fusion model, the set multi-dimensional data includes: Driving operation data , including steering wheel angle, braking force, and throttle pressure; Environmental data , including road type, weather conditions, and traffic flow; Physiological state data , including heart rate, pupil diameter, and eye movement trajectory.

8. A method for constructing a platform based on a driving training teaching platform according to claim 7, characterized in that, The multi-dimensional data fusion model includes a fusion weight calculation formula, a data fusion formula, a performance deviation detection formula, and a real-time feedback generation formula; The fusion weight calculation formula is used to represent the contribution degree of data in different dimensions to driving behavior; The data fusion formula is used to comprehensively measure trainees' driving behavior performance; The performance deviation detection formula is used to measure the deviation degree between the current behavior and the ideal behavior; The real-time feedback generation formula is used to generate feedback.

9. A method for constructing a platform based on a driving training teaching platform according to claim 1, characterized in that, In the step S6, constructing the learning map includes: Dynamically reorganize the knowledge point structure of driving training, and divide driving knowledge points into three levels: basic operation type, scenario application type, and complex task type; Represent the trainees' knowledge mastery path through a graph structure, where nodes represent knowledge points and edges represent learning logical relationships.

10. A method for constructing a platform based on a driving training teaching platform according to claim 1, characterized in that, In the step S7, the driving risk prediction model uses time series analysis methods to predict possible risk points in trainees' future driving, generates a risk report after each training, and puts forward improvement suggestions.

Images