Driving skill training method based on diversified virtual examination room

Abstract

The application discloses a driving skill training method based on a diversified virtual examination room construction, and relates to the technical field of data processing.The method comprises the following steps: constructing a virtual examination room scene based on a diversified virtual examination room construction system, training a user in driving, outputting a driving behavior data set in real time for scoring, analyzing data according to the driving score, and generating a personalized training path in combination with historical data when the driving score does not meet the standard, so that the user trains step by step according to the training path until a preset skill score target is achieved.The application solves the technical problem that the conventional driving training method in the prior art cannot dynamically adjust the training path to meet the actual skill needs of students, resulting in lack of pertinence of training content and low efficiency, achieves the technical effects of improving the individualization and pertinence of driving skill training, ensuring that the training content is highly matched with the actual skill needs of students, and improving the training efficiency and effect.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically to a driving skills training method based on the construction of diversified virtual test sites. Background Technology

[0002] With the rapid development of virtual reality (VR) and artificial intelligence (AI) technologies, traditional driver skills training methods are gradually shifting towards intelligent and personalized approaches. Traditional driver training typically relies on actual vehicles and physical training grounds, which is not only limited by objective conditions such as venue, equipment, and weather, but also suffers from high costs and inherent risks. Furthermore, traditional methods struggle to provide personalized guidance to address the specific weaknesses of individual learners, resulting in a relatively one-dimensional training outcome that fails to fully meet the needs of learners at different skill levels, exhibiting a lack of personalization and dynamic adjustment capabilities. Summary of the Invention

[0003] This application provides a driving skills training method based on the construction of diversified virtual test sites, which is used to solve the technical problem that traditional driving training methods in the prior art cannot dynamically adjust the training path to meet the actual skill needs of trainees, resulting in a lack of targeted training content and low efficiency.

[0004] This application provides a driving skills training method based on the construction of diversified virtual test rooms. The method includes: acquiring virtual test room scenarios based on a diversified virtual test room construction system; training users logging into the diversified virtual test room construction system, driving based on the virtual test room scenarios, and outputting real-time driving behavior datasets; scoring the real-time driving behavior datasets and outputting driving scores; if the driving scores of the real-time driving behavior datasets are less than a preset score, acquiring the training user's historical driving behavior datasets; inputting the real-time driving behavior datasets and the historical driving behavior datasets into a driving path generation model, and obtaining a first driving training path according to the driving path generation model, wherein the first driving training path includes multiple path nodes, each path node corresponding to a driving training scenario; and the training user performing driving training according to the first driving training path until the preset score is met.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] This application provides a driving skills training method based on the construction of a diversified virtual testing room, which relates to the field of data processing technology. It acquires scenarios through a virtual testing room system, allows users to conduct driving training, and generates a driving behavior dataset in real time to evaluate user performance. When the score is below the target, a personalized training path is generated by combining historical data. This path consists of multiple training scenarios, and users train step-by-step according to the training path until they reach the preset scoring target. This solves the technical problem in existing traditional driving training methods that cannot dynamically adjust training paths to meet the actual skill needs of trainees, resulting in a lack of targeted training content and low efficiency. It achieves the technical effect of improving the personalization and targeting of driving skills training, ensuring that the training content is highly matched with the actual skill needs of trainees, and improving training efficiency and effectiveness. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 A schematic diagram of a driving skills training method based on the construction of a diversified virtual examination room, provided for an embodiment of this application;

[0009] Figure 2 This is a schematic diagram of the process for obtaining the first driving training path in the driving skills training method based on the construction of a diversified virtual test site provided in the embodiments of this application. Detailed Implementation

[0010] This application provides a driving skills training method based on the construction of diversified virtual test sites, which is used to solve the technical problem that traditional driving training methods in the prior art cannot dynamically adjust the training path to meet the actual skill needs of trainees, resulting in a lack of targeted training content and low efficiency.

[0011] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0012] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0013] Example 1, as Figure 1 As shown, this application provides a driving skills training method based on the construction of a diversified virtual testing environment, the method comprising:

[0014] P10: Based on a diversified virtual examination room construction system, obtain virtual examination room scenarios.

[0015] The diversified virtual examination room construction system includes multiple construction components, including a scene type construction component, a difficulty level construction component, a scene task distribution component, and an environment simulation component; the virtual examination room scene is obtained by collaborative construction based on the multiple construction components.

[0016] Optionally, a diversified virtual test center construction system can be used to obtain virtual test center scenarios. This system comprises multiple construction components that work together to generate the virtual test center scenarios. Specifically, the scenario type construction component selects different types of driving scenarios from a pre-defined scenario library, such as urban roads, highways, mountain roads, and extreme weather scenarios, ensuring scenario diversity to meet various driving training needs. The scenario type refers to the specific category of the virtual scenario, which directly determines the driver's simulated environment, such as traffic signals and road condition complexity.

[0017] The difficulty level construction component dynamically adjusts the training intensity of the scenario based on the driving skill level, such as increasing traffic flow, introducing dynamic obstacles, or simulating complex emergencies. The difficulty level is a standard for grading the training requirements of the virtual testing environment, used to adapt to the different needs of beginners and advanced drivers. This component dynamically adjusts parameters based on algorithms to ensure that learners can improve their skills through reasonable challenges.

[0018] The scenario-based task assignment component is used to embed specific driving tasks into the scenario, such as straight driving, reversing into a parking space, and emergency braking, to help trainees practice their skills in a targeted manner within the scenario. Task assignment here refers to distributing pre-set operational objectives into the scenario, similar to the task points specified in a real driving test.

[0019] The environment simulation component is responsible for introducing environmental variables, such as lighting conditions, rain and snow, wind speed, and road surface slippage, and uses a physics engine to recreate the real driving environment. Environment simulation is key to virtual reality technology; through accurate modeling and real-time rendering, it allows drivers to experience a near-realistic driving experience.

[0020] Through the collaborative operation of the aforementioned building components, combined with input parameters and user needs, a virtual test scenario that meets training requirements is ultimately generated. Data interaction between components is completed through a unified communication interface, ensuring the efficiency and flexibility of the scenario construction process. This modular design-based construction method not only enhances the richness and accuracy of the virtual test scenario but also provides strong technical support for personalized driver training.

[0021] P20: Train users to log in to the diversified virtual test room construction system, drive based on the virtual test room scenario, and output a real-time driving behavior dataset.

[0022] Furthermore, step P20 in this embodiment of the application also includes:

[0023] P21: The diversified virtual examination room construction system includes a virtual reality operating device. The training user performs a perception sensitivity test using the virtual reality operating device and outputs a perception test dataset. P22: When the perception test dataset meets the preset perception sensitivity, the device configuration parameters are obtained. P23: A connection is established between the virtual reality operating device and the training user according to the device configuration parameters.

[0024] It should be understood that training users to log in to the diversified virtual test room construction system, drive based on the virtual test room scenario, and output real-time driving behavior datasets. Simultaneously, the user's immersive experience can be enhanced through virtual reality operating devices, ensuring the accuracy and consistency of data collection.

[0025] Specifically, before users practice driving, a perception sensitivity test is first performed. This test assesses response time and accuracy to multimodal feedback, including visual, auditory, and tactile feedback, generating a perception test dataset. Perception sensitivity refers to a user's ability to react to sensory stimuli in a virtual driving environment, such as the speed of visual recognition of road signs, the auditory reaction time to emergency alarms, and the sensitivity to tactile feedback from steering wheel vibrations. This test is conducted using sensors in the virtual reality device (such as gyroscopes and accelerometers) and external monitoring devices (such as eye trackers).

[0026] After the test is completed, the perception test dataset is compared with the preset perception sensitivity. The preset perception sensitivity can be generated based on statistical analysis of user big data. If the dataset meets the preset perception sensitivity threshold, the system will obtain device configuration parameters based on the user's test performance. Device configuration parameters include the display refresh rate, control sensitivity, feedback intensity, etc. of the virtual reality device. Dynamic adjustment of these parameters can ensure that the user's operation and feedback are highly synchronized in the driving scenario, reducing latency or discomfort.

[0027] Subsequently, based on the device configuration parameters, a connection is established between the virtual reality operating device and the training user. This process is completed through a data transmission protocol, ensuring that all operational information in the virtual testing environment can be synchronized to the user's device in real time and recorded as a real-time driving behavior dataset. For example, when the user operates the steering wheel in the virtual scenario, their steering angle, force, and speed are accurately recorded and transmitted to the system.

[0028] Through perception sensitivity testing and equipment configuration optimization, the diversified virtual test center construction system ensures that each trainee can practice driving in an environment best suited to their individual perception abilities, thereby improving the accuracy of data collection and enhancing training effectiveness. Finally, the system records driving behaviors such as directional control, acceleration / deceleration, and steering as a real-time driving behavior dataset for subsequent evaluation and analysis.

[0029] P30: Perform driving score analysis on the real-time driving behavior dataset and output the driving score.

[0030] Specifically, the real-time driving behavior dataset is scored, and a driving score for the training user is output. The core of this step is to objectively and accurately analyze the driving behavior of the training user to quantify their driving skill level and provide a scientific basis for subsequent training.

[0031] Specifically, real-time driving behavior datasets refer to user operation data collected during driving, including but not limited to steering wheel angle, braking force, throttle control, speed changes, and response time to traffic signals. This data is recorded in real time by high-precision sensors in virtual reality devices and transmitted to the system's evaluation module for analysis.

[0032] First, several key behavioral features are extracted from the real-time driving behavior dataset, including but not limited to vehicle trajectory deviation, acceleration / deceleration smoothness, braking response time, and traffic rule compliance. Here, trajectory deviation refers to the degree of deviation between the vehicle's driving trajectory and the standard path, which is a key indicator for measuring driving accuracy; acceleration / deceleration smoothness reflects the smoothness and comfort of driving operations, and the data comes from changes in the force of the accelerator and brake.

[0033] After feature extraction, the various key behavioral features are input into a preset driving score model for evaluation. This driving score model can be trained using machine learning algorithms and large-scale driving data, enabling adaptability analysis based on different driving scenarios and task requirements. For example, in urban road scenarios, the model focuses more on braking and steering accuracy, while in highway scenarios, it focuses more on speed control and lane keeping ability. For instance, the evaluation process may involve first comparing the user's real-time driving behavior data with a preset standard driving behavior template to calculate the degree of deviation. Simultaneously, weights are assigned according to the importance of each behavioral feature; for example, in complex scenarios, emergency braking has a higher weight than other indicators. Finally, the weighted sum of each individual score is calculated to generate the final driving score.

[0034] The driving score is a quantitative indicator, for example, represented by a score from 0 to 100, reflecting the user's overall driving skill level. The driving score may include a safety score, an operational accuracy score, and a rule compliance score. For example, the safety score can assess the user's ability to respond to potential hazards based on their performance in complex traffic scenarios. The operational accuracy score reflects the user's proficiency in using control devices such as the steering wheel, accelerator, and brakes. The rule compliance score is based on whether the user obeys traffic signals, road markings, and other rules. Furthermore, a visual evaluation report can be generated, highlighting the user's strengths and weaknesses. For example, if the user's acceleration is frequent and inconsistent, the instability of accelerator control can be visually displayed in a chart format, along with relevant suggestions.

[0035] This approach not only enables the precise quantification of driving skills but also provides the necessary input data for subsequent customized training paths, ensuring the relevance and scientific nature of the driving training process.

[0036] P40: If the driving score of the real-time driving behavior dataset is less than the preset score, obtain the historical driving behavior dataset of the training user.

[0037] Optionally, if the driving score in the real-time driving behavior dataset is lower than a preset score, the historical driving behavior dataset of the training user is obtained. The core of this step is to combine historical driving data with real-time performance to analyze the weaknesses in the driving skills of the training user, thereby providing accurate data support for subsequent training.

[0038] Specifically, the driving score is a quantitative evaluation of a trainee's current driving performance, typically calculated by weighting multiple assessment indicators, such as safety score, rule compliance score, and operational accuracy score. The preset score is the minimum passing grade set by the system, based on driving skills training goals and standards, used to assess whether the user has reached the required driving level.

[0039] When the real-time driving score falls below the preset score, the system automatically triggers the data retrieval module to obtain the historical driving behavior dataset from the user's profile. The historical driving behavior dataset is a complete record of data collected from the user's previous driving practice, including operating habits, skill improvement trajectories, and past evaluation results. It provides crucial information for identifying the user's driving weaknesses and operating patterns.

[0040] During data retrieval, historical records related to the current task are quickly located using data indexing and classification techniques. For example, when a user performs poorly in a complex turning scenario, the system will prioritize retrieving historical data related to steering control and speed adjustment. By combining real-time data with historical data for comparative analysis, the system can delve deeper into the user's operational characteristics, such as repetitive errors and reaction delays.

[0041] To ensure the comprehensiveness and efficiency of data analysis, historical data is processed based on driving behavior feature extraction algorithms. Feature extraction refers to extracting key information from raw data that reflects the user's operating habits and skill level. For example, the system can extract the user's average braking reaction time and steering wheel operation smoothness index from past practice to help pinpoint the sources of deviations in current performance.

[0042] By acquiring historical driving behavior datasets, the system can construct a complete profile of a user's driving skills. This not only provides data support for the design of subsequent training paths but also identifies the user's skill growth trends, thereby adjusting training objectives and strategies to ultimately achieve targeted and effective improvement in driving skills.

[0043] P50: Input the real-time driving behavior dataset and the historical driving behavior dataset into the driving path generation model, and obtain the first driving training path according to the driving path generation model. The first driving training path includes multiple path nodes, and each path node corresponds to a driving training scenario.

[0044] Furthermore, such as Figure 2As shown, step P50 in this embodiment further includes:

[0045] P51: The driving path generation model extracts features of driving evaluation items based on the real-time driving behavior dataset and the historical driving behavior dataset to obtain evaluation indicators corresponding to each driving evaluation item; P52: Based on the evaluation indicators corresponding to each driving evaluation item, the skill items to be improved are determined, wherein each driving evaluation item includes at least braking evaluation item, speed control evaluation item, steering operation evaluation item, environmental adaptability evaluation item, and emergency response capability evaluation item; P53: A virtual test room scenario library is constructed; P54: Scenario matching is performed in the virtual test room scenario library based on the skill items to be improved to generate the first driving training path.

[0046] It should be understood that the real-time driving behavior dataset and the historical driving behavior dataset are input into the driving path generation model, and a first driving training path is obtained based on the driving path generation model. This step generates a personalized training path by combining the user's current driving performance and historical skill data, so as to effectively strengthen the training of the user's weak points. The specific implementation process is as follows.

[0047] First, the driving path generation model performs multi-dimensional analysis and feature extraction based on the input real-time driving behavior dataset and historical driving behavior dataset. Feature extraction refers to extracting core information reflecting driving skills and behavioral patterns from the raw data, such as operational smoothness, response latency, and rule compliance. During this process, the model generates corresponding evaluation indicators based on different driving evaluation items (such as braking evaluation items and speed control evaluation items). These indicators quantify the user's specific performance in each skill.

[0048] Based on the above evaluation indicators, by comparing preset standards and individual performance, the skill items that users need to improve are identified, i.e., the skill items to be improved. These skill items refer to specific abilities that the user performs poorly in during driving and require further training, such as delayed braking response or unstable steering. The evaluation dimensions cover multiple key skill areas, including but not limited to braking evaluation, used to assess whether the timing and force of the user's braking are appropriate; speed control evaluation, used to check whether the user's speed adjustments meet road conditions and task requirements; steering operation evaluation, used to assess the accuracy and smoothness of steering operations; environmental adaptability evaluation, used to measure the user's performance under different lighting, weather, and road conditions; and emergency response capability evaluation, used to analyze the user's decision-making speed and operational accuracy in dealing with emergencies.

[0049] Next, with the support of a virtual test scenario library, customized training scenarios are created for users. This library is a collection of diverse driving scenarios, covering various driving environments from urban roads to extreme weather. These scenarios are constructed using highly realistic virtual reality technology, supporting real-time dynamic loading and scenario adjustments.

[0050] Finally, based on the skill to be improved, a scenario is matched from the virtual test scenario library to generate the first driving training path. Scenario matching refers to selecting the appropriate driving training scenario from the scenario library according to the specific skill the user needs to improve. For example, for users with unstable steering operation, the system may select a complex curve driving scenario as the training focus; for users with slow reaction to sudden events, an emergency avoidance scenario involving the sudden appearance of obstacles may be designed.

[0051] The generated first driving training path consists of multiple path nodes, each corresponding to a specific driving training scenario. These path nodes are arranged in a logical order, gradually guiding users to complete training goals ranging from basic skill enhancement to comprehensive ability improvement. Through these steps, the training path can be personalized and targeted, ensuring that each user can efficiently improve their driving skills in a scientific training process, laying the foundation for ultimately achieving the preset driving score target.

[0052] Furthermore, step P53 in this embodiment of the application also includes:

[0053] P53-1: Set up multiple virtual test room scenario samples; P53-2: Collect driving behavior sample data of training users based on each virtual test room scenario sample; P53-3: Upload the driving behavior sample data of each virtual test room scenario sample to the cloud platform, analyze the driving behavior sample data of each virtual test room scenario sample on the cloud platform, and determine the skill improvement tag of each virtual test room scenario sample; P53-4: Identify the multiple virtual test room scenario samples according to the skill improvement tag to generate a virtual test room scenario library.

[0054] Optionally, to achieve accurate adaptation and scientific configuration of virtual test room scenarios, a systematic virtual test room scenario library is generated by setting scenario samples, collecting user data, analyzing skill improvement effects, and identifying scenarios, ultimately supporting the generation of targeted driving training paths. The specific process is as follows:

[0055] First, multiple virtual test scenario samples were created, covering different driving environments and task requirements, such as urban traffic, mountain roads, highways, rainy / snowy weather, and nighttime driving. These virtual test scenario samples serve as simulated test units for different driving environments, used to evaluate learner driving performance under various conditions. Each sample is carefully designed, emphasizing environmental diversity and alignment with training objectives.

[0056] After trainees complete the driving exercises in the aforementioned scenario samples, the system collects their driving behavior data in real time. This data includes the trainee's operational records in each scenario, such as braking force, acceleration time, steering wheel turning angle, and response time to unexpected events. Through large-scale data collection, not only can individual performance be reflected, but the overall performance trends of the trainee group in specific scenarios can also be analyzed.

[0057] All driving behavior sample data is uploaded to a cloud platform and processed using efficient big data analytics. The cloud platform uses feature extraction and clustering algorithms to identify key features of learner behavior data in various scenarios, analyzing which types of scenarios are most helpful in improving driving safety and which scenarios can effectively improve reaction speed. For example, certain complex road conditions (such as multi-way intersections) may significantly improve learners' rule compliance, while sudden obstacle scenarios have a greater effect on improving reaction time.

[0058] Skill enhancement tags are a key outcome of data analysis; they are quantitative or qualitative descriptions of how each scenario sample improves a learner's specific skill. For example, a "driving safety improvement tag" might be associated with complex traffic scenarios, while a "reaction speed improvement tag" might correspond to emergency scenarios. Through these tags, the system can intuitively understand the training value of each scenario.

[0059] Next, based on the analysis results, each virtual test scenario sample is assigned a corresponding skill enhancement tag, and a standardized scenario library is generated. The virtual test scenario library is a structured database that stores all analyzed and tagged scenario samples, categorized and indexed according to skill enhancement goals. For example, scenarios aimed at improving reaction speed can be separately tagged as "emergency event reinforcement training scenarios," while scenarios aimed at improving driving safety might be categorized as "rule compliance reinforcement scenarios."

[0060] Through the above steps, the virtual examination scenario library has achieved scientific and personalized processing, providing a wealth of choices and precise matching support for the generation of subsequent training paths.

[0061] Furthermore, step P54 in this embodiment of the application also includes:

[0062] P54-1: Based on the driving path generation model, obtain multiple driving training scenarios; P54-2: Mark the difficulty of the multiple driving training scenarios and output multiple difficulty labels, with the multiple driving training scenarios corresponding to the multiple difficulty labels; P54-3: Based on the multiple difficulty labels, connect the multiple driving training scenarios sequentially from smallest to largest to generate the first driving training path.

[0063] In one possible embodiment of this application, to ensure the logicality and relevance of the training path, this step is further refined by constructing a complete driving training path through the generation of scenarios, difficulty markers, and sequential connections. The specific description is as follows:

[0064] First, based on the driving path generation model, and combining the user's real-time and historical driving behavior data, scenario samples that best match the skills to be improved are selected from the virtual testing scenario library. These scenarios are designed as specific task units for driving training, such as simulated sharp turns, sudden obstacle avoidance training, or complex traffic rule scenarios. Driving training scenarios are a set of specific driving tasks provided to trainees in the virtual testing environment, covering multiple skill areas.

[0065] To ensure the progressiveness of the training path, the generated driving training scenarios are labeled with difficulty. The difficulty label is assigned based on a comprehensive evaluation of the scenario's operational complexity, dynamic environmental changes, and task requirements. For example, a scenario simulating straight-line driving might be labeled "beginner difficulty," while a scenario containing complex curves and unexpected events might be labeled "advanced difficulty." The difficulty labels are generated by analyzing historical completion rates, student success rates, and the distribution of key behavioral data, ensuring their scientific validity and rationality.

[0066] Based on the difficulty level, the system sorts multiple driving training scenarios and connects them sequentially from easy to difficult to form a complete first driving training path. This sorting strategy helps trainees gradually adapt to and master the skills. For example, the initial stage of the path may include simple braking and starting practice scenarios, while subsequent stages gradually transition to handling complex traffic situations and training in advanced operating skills.

[0067] Each driving training scenario is defined as a path node in the training path, and trainees need to complete the training tasks of each node in sequence. Path nodes are logically connected; for example, after completing a beginner-level straight-line driving task, the system will automatically load the next intermediate-level cornering driving task. This design ensures the smoothness and continuity of the training.

[0068] Through the above steps, a scientific and progressive driving training path has been successfully constructed. This first driving training path not only covers all the key aspects of the skills to be improved, but also enhances learners' confidence and learning outcomes through a gradient of difficulty. Ultimately, the sequential connection of the path provides crucial technical support for achieving efficient and precise improvement of driving skills.

[0069] P60: The training user performs driving training according to the first driving training path until the preset score is met.

[0070] Specifically, the trainee follows the first driving training path until the preset score is met. The core of this step is to guide the trainee to gradually improve their driving skills through a personalized training path, while utilizing real-time feedback and dynamic adjustment mechanisms to ensure the training effect meets expectations.

[0071] At the start of training, the system loads the first driving training path, with each node in the path corresponding to a specific driving training scenario. These scenarios are arranged in progressive difficulty, covering various aspects from basic skills to complex operations. For example, users may start with basic braking and acceleration control exercises and gradually transition to advanced skills training such as cornering and handling unexpected events.

[0072] In each scenario, the real-time driving behavior acquisition module records the trainee's operational behaviors, such as steering wheel angle, braking force, and accelerator timing. This operational data is transmitted in real time to the driving behavior analysis engine, compared with a preset optimal operating model, and generates immediate operational feedback for the trainee. This feedback evaluates the user's current behavior, including whether the operation is accurate and conforms to driving rules. For example, if the user's steering control is unstable while driving on a curve, the system will issue an immediate warning and provide corrective suggestions via visual or voice means.

[0073] During training, the training intensity is dynamically adjusted based on the user's performance. This dynamic adjustment mechanism is a key training technology; by analyzing the user's operational data and current state in real time, the system can adjust the training pace. For example, if a user fails multiple times in a scenario, the system may extend the scenario time or reduce the task difficulty to ensure the user gradually masters the skill; conversely, if the user quickly passes a scenario, the system will automatically jump to a more challenging training node.

[0074] A user's performance in each scenario is quantified into a scenario score, which is then aggregated to generate an overall driving score at the end of the training course. The preset score is a driving skill attainment standard set by the system, and it is dynamically adjusted based on the driving training objectives and the user's individual learning progress. For example, a basic learner's preset score may be relatively low, while advanced learners require a higher score.

[0075] When a user's overall driving score reaches or exceeds a preset score, the system determines that the training objective has been achieved. After training, the system generates a detailed driving training report, which includes the user's training performance, weaknesses in operation, and recommended follow-up training suggestions. If the score does not meet the requirements, the system will regenerate an optimized driving training path based on the training results to guide the user in continuing to strengthen their practice.

[0076] Through this complete training process, users can gradually master driving skills under personalized and scientific guidance, ensuring that they ultimately reach the preset scoring standards, thus laying a solid foundation for actual driving.

[0077] Furthermore, the embodiments of this application also include step P70, which further includes:

[0078] P71: When the training user performs driving training according to the first driving training path, record the new driving behavior dataset of the training user; P72: Input the new driving behavior dataset as incremental data into the driving path generation model for feedback learning, update the first driving training path, and output the second driving path; P73: The training user performs driving training according to the second driving training path.

[0079] Optionally, after completing the first driving training path, this embodiment of the application dynamically optimizes the driving training path through an incremental data feedback learning mechanism to provide users with a more accurate and effective training experience.

[0080] Specifically, during the driving training process following the first driving training path, the system collects new driving behavior data from the user in real time, forming a new driving behavior dataset. This dataset contains records of all new operations performed by the user during the completion of the training path, such as the precision of steering wheel operation, braking reaction time, and changes in speed control. Compared to historical data, the new data better reflects the user's current skill level and training effectiveness.

[0081] Incremental learning is a machine learning technique that uses new data to dynamically optimize a driving path generation model. This involves adjusting model parameters based on new data without retraining the entire model. For example, if new data indicates unstable user operation in complex traffic scenarios, the model will automatically identify this skill weakness and adjust subsequent training paths.

[0082] During the feedback learning process, the model compares and analyzes new data with historical data to identify the user's skill progress and deficiencies. Based on preset skill improvement goals, it recalculates the priority and difficulty allocation of the training path. Through this optimization method, the model generates a second driving training path that is not only more targeted but also further improves the user's training efficiency.

[0083] The trainees will then proceed with driving training according to the updated second driving training path. Compared to the first path, the second path is more closely aligned with the actual needs of users in terms of scenario design and task configuration. For example, for users with slow braking reaction time, the second path may increase the frequency of emergency braking practice; while for users with poor speed control, it may introduce more scenarios involving constant-speed driving.

[0084] This cyclical mechanism ensures that the training path dynamically adapts to the user's skills, keeping training scientific and effective at all times. Through repeated path optimization and training, users can gradually address skill weaknesses and continuously improve their driving skills.

[0085] This step utilizes real-time feedback and dynamic optimization technology based on newly added driving behavior data to achieve adaptive adjustment of the training path. Compared to traditional fixed training methods, this incremental learning and feedback mechanism significantly improves the personalization and accuracy of training results, enabling users to achieve their final driving skill goals through progressive and efficient learning.

[0086] In summary, the embodiments of this application have at least the following technical effects:

[0087] This application acquires virtual test room scenarios through a diversified virtual test room construction system, allows training users to log in to the system for driving training, outputs driving behavior datasets for scoring in real time, analyzes the data based on the driving scores, and generates personalized training paths by combining historical data when the driving scores are not up to standard. These paths consist of multiple training scenario nodes, and training users train step by step according to the paths until they achieve the preset skill score target.

[0088] This technology has achieved the goal of enhancing the personalization and relevance of driver skills training, ensuring that the training content is highly matched with the actual skill needs of trainees, and improving training efficiency and effectiveness.

[0089] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0090] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0091] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A driving skills training method based on the construction of diversified virtual testing rooms, characterized in that, The method includes: Based on a diversified virtual examination room construction system, virtual examination room scenarios are obtained; Trained users log in to the diversified virtual test room construction system, drive based on the virtual test room scenario, and output real-time driving behavior dataset; The driving behavior dataset is used to generate a driving score, which is then output. If the driving score in the real-time driving behavior dataset is less than the preset score, obtain the historical driving behavior dataset of the training user; The real-time driving behavior dataset and the historical driving behavior dataset are input into the driving path generation model, and a first driving training path is obtained according to the driving path generation model. The first driving training path includes multiple path nodes, and each path node corresponds to a driving training scenario. The training user performs driving training according to the first driving training path until the preset score is met; The method for obtaining the first driving training path based on the driving path generation model includes: The driving path generation model extracts features of driving evaluation items based on the real-time driving behavior dataset and the historical driving behavior dataset, and obtains the evaluation index corresponding to each driving evaluation item. Based on the assessment indicators corresponding to each driving assessment item, the skill items to be improved are determined; Build a virtual examination room scenario library; Based on the skills to be improved, a scenario is matched in the virtual test site scenario library to generate the first driving training path.

2. The method as described in claim 1, characterized in that, Methods for building a virtual examination room scenario library include: Set up multiple virtual examination room scenario samples; Collect driving behavior sample data of training users based on various virtual test site scenarios; The driving behavior sample data of each virtual test room scenario is uploaded to the cloud platform. The driving behavior sample data of each virtual test room scenario is analyzed on the cloud platform to determine the skill improvement tags of each virtual test room scenario. The multiple virtual exam room scene samples are identified according to the skill enhancement tags to generate a virtual exam room scene library.

3. The method as described in claim 1, characterized in that, Based on the skills to be improved, a scenario matching is performed in the virtual test site scenario library to generate the first driving training path, the method including: Based on the aforementioned virtual test site scenario library, multiple driving training scenarios are obtained; The multiple driving training scenarios are labeled with difficulty, and multiple difficulty tags are output, with the multiple driving training scenarios corresponding to the multiple difficulty tags; Based on the multiple difficulty tags, the multiple driving training scenarios are sequentially connected from lowest to highest difficulty to generate the first driving training path.

4. The method as described in claim 1, characterized in that, Based on the evaluation indicators corresponding to each driving evaluation item, the skill items to be improved are determined. Each driving evaluation item includes at least braking evaluation, speed control evaluation, steering operation evaluation, environmental adaptability evaluation, and emergency response capability evaluation.

5. The method as described in claim 1, characterized in that, After the training user completes driving training according to the first driving training path, the method further includes: When the training user performs driving training according to the first driving training path, the newly added driving behavior dataset of the training user is recorded. The newly added driving behavior dataset is input as incremental data into the driving path generation model for feedback learning, the first driving training path is updated, and the second driving training path is output. The training users conduct driving training according to the second driving training path.

6. The method as described in claim 1, characterized in that, The diversified virtual examination room construction system includes multiple construction components, including a scene type construction component, a difficulty level construction component, a scene task distribution component, and an environment simulation component; The virtual examination room scene is obtained by collaboratively building based on the multiple building components.

7. The method as described in claim 1, characterized in that, The diversified virtual examination room construction system includes a virtual reality operating device, and the training user performs a perception sensitivity test based on the virtual reality operating device, and outputs a perception test dataset. When the perception test dataset meets the preset perception sensitivity, obtain the device configuration parameters; Establish a connection between the virtual reality operating device and the training user according to the device configuration parameters.

Images