Multi-scene switching driving simulator control method and device and storage medium

Abstract

The invention provides a multi-scene switching driving simulator control method and device and a storage medium, and relates to the technical field of driving training, and the method comprises the steps: collecting historical training data of multiple training scenes of a target student in historical time; according to the historical training data, analyzing a plurality of training difficulties of the target student on the plurality of training scenes; according to the multiple training difficulties, training parameters of the multiple training scenes are optimized for the target trainee, and multiple optimal scene training parameters are obtained; and adopting the plurality of optimal scene training parameters to configure training parameters of the plurality of training scenes in the driving simulator, and performing training control on the target trainee. The technical problems that the training process of an existing driving simulator lacks pertinence and the training process cannot be adjusted according to specific expressions of trainees in different scenes are solved, the personalized level and pertinence of driving training are improved, and then the efficiency and overall quality of driving training are improved.

Description

Technical Field

[0001] The present application relates to the field of driving training technology, and in particular to a driving simulator control method, device and storage medium for multi-scene switching. Background Art

[0002] As an efficient and safe training tool, driving simulators can simulate various real driving scenarios, such as urban roads, highways, bad weather, etc., providing students with a safe and controllable training environment. They have been widely used in driving schools and professional training.

[0003] Existing driving simulator control methods usually use preset training scenarios and fixed training parameters. The difficulty and settings of the training scenarios are unified and cannot be dynamically adjusted according to the different skill levels and learning progress of the trainees. This stereotyped training method ignores the individual differences of trainees during the training process and lacks personalized considerations. For example, for trainees with poor foundations, fixed training parameters may be too difficult and affect the training effect; while for trainees with good foundations, fixed parameters may be too simple and cannot effectively improve skills. In addition, this training process lacks sufficient analysis and feedback on the specific performance of trainees in different scenarios, and it is difficult to optimize training parameters according to the actual situation of the trainees. Therefore, during the training process, trainees cannot obtain personalized guidance and targeted training, resulting in repetitiveness and incompatibility of training content, reducing learning motivation and effect. Summary of the invention

[0004] The present application provides a multi-scene switching driving simulator control method, device and storage medium, which solves the technical problem that the prior art ignores the individual differences of students and is unable to adjust the training process according to the specific performance of students in different scenarios, resulting in a lack of targeted driving training and affecting the training efficiency and training effect. The application achieves the technical effect of improving the personalization level and targetedness of driving training, thereby improving the efficiency and overall quality of driving training.

[0005] In view of the above problems, on the one hand, the present application provides a driving simulator control method for multi-scene switching, the method comprising: collecting historical training data of a target student within a historical time, wherein the historical training data includes training data of multiple training scenes; based on the historical training data, analyzing multiple training difficulties of the target student for the multiple training scenes; based on the multiple training difficulties, optimizing the training parameters of the target student for the multiple training scenes to obtain multiple optimal scene training parameters; using the multiple optimal scene training parameters, configuring the training parameters of the multiple training scenes in the driving simulator, and performing training control on the target student.

[0006] In a second aspect, the present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above-mentioned multi-scene switching driving simulator control method when executing the computer program.

[0007] In a third aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-mentioned multi-scene switching driving simulator control method.

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

[0009] Collect historical training data of target students in multiple training scenarios in historical time. These data can reflect the students' past training in different scenarios and provide a basis for subsequent analysis of the students' training difficulty and ability. Based on historical training data, analyze the students' performance in various training scenarios and evaluate their adaptability and difficulty to different training scenarios. This analysis process helps identify the strengths and weaknesses of students, understand the challenges and difficulties they encounter in various scenarios, and lay the foundation for personalized adjustment of training plans. According to the analysis results, optimize the parameters of the training scenarios to ensure that the difficulty of each training scenario matches the students' abilities, and generate multiple optimal scenario training parameters. By adjusting the training difficulty and settings, the training is made more targeted and personalized, avoiding difficulty mismatches during the training process. Use the optimized training parameters to configure the simulator's training scenarios so that students can train at the appropriate difficulty. Through this personalized training control method, the simulator's training content and difficulty can be dynamically adjusted to ensure maximum training effect.

[0010] In summary, this application controls the driving simulator through the above steps, so that the driving simulator can automatically adjust the difficulty and parameters of the training scene according to the historical performance and ability differences of the trainees, and realize highly personalized training control. Through in-depth analysis of training data and optimization of training parameters, trainees can obtain challenges and guidance that match their abilities during training, thereby improving training efficiency and the overall quality of training.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flowchart of a multi-scenario switching driving simulator control method provided in an embodiment of the present application.

[0013] Figure 2 A flowchart of analyzing multiple training difficulties of a target student for multiple training scenarios based on historical training data in a multi-scenario switching driving simulator control method provided in an embodiment of the present application.

[0014] Figure 3 A schematic diagram of a flow chart for obtaining multiple optimal scenario training parameters in a multi-scenario switching driving simulator control method provided in an embodiment of the present application.

[0015] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present application.

[0016] Description of the reference numerals: bus 300 , receiver 301 , processor 302 , transmitter 303 , memory 304 , bus interface 305 . DETAILED DESCRIPTION

[0017] The embodiments of the present application provide a driving simulator control method, device and storage medium for multi-scenario switching, collect historical training data of students, analyze the training difficulty under different scenarios, and then optimize the training parameters and apply them to the training control of the driving simulator. This solves the technical problem that the prior art ignores the individual differences of students and is unable to adjust the training process according to the specific performance of students in different scenarios, resulting in a lack of targetedness in driving training and affecting the training efficiency and training effect. This achieves the technical effect of improving the personalization level and targetedness of driving training, thereby improving the efficiency and overall quality of driving training.

[0018] Embodiment 1, as Figure 1 As shown, an embodiment of the present application provides a driving simulator control method for multi-scene switching, the method comprising:

[0019] Step S1: Collect historical training data of the target trainee within a historical period of time, wherein the historical training data includes training data of multiple training scenarios.

[0020] Specifically, the target student refers to the student who is receiving driving training. The historical time is a specific time range set when extracting the student's training data, which can usually be the total training time that the student has experienced from the beginning of training to the present. The historical training data is all the training records of the student in the driving simulator during the historical time, including the specific training conditions, student performance and training content in multiple training scenarios. These training scenarios can be various simulation situations or tasks such as urban driving, night driving, and driving in bad weather.

[0021] The driving simulator itself has a data collection function. During the training of the target trainee, the driving simulator will automatically record various data related to the trainee's operation. These data cover the trainee's operation in different training scenarios, such as the trainee's reaction time to traffic lights, the strength of brake and accelerator operation in urban street scenarios, and the trainee's steering operation and speed control in mountain road scenarios. The data collection system of the interactive driving simulator obtains the historical training data of the target trainee in the past period of time, and classifies and organizes these historical data according to specific training scenarios. These historical training data provide a comprehensive data basis for the subsequent analysis of the trainee's training in different scenarios, which helps to gain a deeper understanding of the trainee's driving habits and performance in different scenarios.

[0022] Step S2: Analyze the multiple training difficulties of the target trainee for the multiple training scenarios based on the historical training data.

[0023] Specifically, we analyze the collected historical training data, and collect statistics and evaluations on the various operational data of the trainees in each training scenario. For example, we calculate the operational error rate and average reaction time of the trainees in a specific scenario, so as to determine the training difficulty of each training scenario for the trainee. By analyzing the historical data, we can understand the performance of the trainees in different scenarios, so as to accurately identify the weak links of the trainees in different training scenarios, and provide a clear direction for the subsequent optimization of training parameters.

[0024] Step S3: According to the multiple training difficulties, the training parameters of the target students for the multiple training scenarios are optimized to obtain multiple optimal scenario training parameters.

[0025] Specifically, the optimal scenario training parameters refer to optimizing the training parameters of each training scenario according to the training difficulty of the training scenario, and determining the driving simulator setting parameters that are most suitable for the training difficulty of students in the current scenario.

[0026] Based on the training difficulty of each training scenario for the trainee obtained from the previous step, the machine learning algorithm is used to optimize the training parameters of each training scenario one by one according to the historical scenario training parameters and training difficulty, and determine multiple optimal scenario training parameters corresponding to multiple training scenarios. Through the optimization of training parameters, targeted difficulty adjustment can be achieved, making the training process more in line with the actual ability of the trainee, ensuring that the training of the trainee in different scenarios is both challenging and can improve the trainee's driving skills, thereby improving the effectiveness and efficiency of training.

[0027] Step S4: using the multiple optimal scenario training parameters, configuring the training parameters of the multiple training scenarios in the driving simulator, and performing training control on the target student.

[0028] Specifically, the optimized training parameters are input into the control system of the driving simulator, and the driving simulator reconstructs the training scene according to the new parameters to ensure that the difficulty and challenge of each scene match the trainee's ability. The trainee then trains in this personalized scene. For example, after adjusting the curvature and slope of the curve in the mountain road scene, when the trainee enters the scene for training again, he will face a training environment that is more suitable for his ability. By reconfiguring the training parameters, personalized training control of the trainees is achieved, the training effect of the trainees is improved, and the trainees are helped to master driving skills faster and better.

[0029] Furthermore, step S1 of the embodiment of the present application includes:

[0030] Step S11: collecting the number of times the target trainee has trained the multiple training scenarios in a historical period to obtain multiple historical training times.

[0031] Step S12: Collect the number of training errors made by the target trainee during training of the multiple training scenarios in a historical period to obtain multiple historical numbers of training errors.

[0032] Step S13: Integrate the multiple historical training times and the multiple historical training error times to obtain the historical training data of the target student.

[0033] Specifically, in the process of collecting historical training data, the total number of training sessions of the target trainees in various training scenarios in the historical period is first collected to obtain multiple historical training times. Each historical training number corresponds to a training scenario, which can be labeled in the form of a scenario label to distinguish the data in different training scenarios, so as to facilitate subsequent analysis of different training scenarios one by one. By collecting historical training times, it is possible to accurately count the participation of trainees in each training scenario, understand the training frequency of trainees in different scenarios, and provide data support for subsequent analysis of trainees' familiarity with different scenarios.

[0034] While collecting the number of historical training times, it is also necessary to collect the number of training errors in each training scenario. The scenario labels can also be marked to facilitate subsequent data comparison and calculation. These training errors are the number of times the trainee does not comply with driving specifications or fails to correctly respond to the tasks in the training scenario during the training process of each training scenario. For example, in the highway training scenario, the trainee mistakenly changed lanes 3 times, and these 3 times are the number of training errors in this scenario. During each training process, the driving simulator will make an error judgment on the trainee's operation according to the preset judgment rules, extract the training data of errors in multiple training scenarios, and determine the number of historical training errors corresponding to multiple training scenarios. By obtaining the number of historical training errors, it is possible to clarify where the trainee is prone to problems in different training scenarios, thereby providing a direct basis for analyzing the training difficulty of each scenario for the trainee.

[0035] The historical training times and historical training errors in each training scenario are sorted out, and the historical training times and historical training errors in the same training scenario are correspondingly integrated together to form complete historical training data of the target trainees. The sorting process can use a database management system (such as MySQL, etc.) or spreadsheet software (such as Excel) to complete the data integration, and obtain a historical training data set that comprehensively reflects the training situation of the trainees in various training scenarios, providing a complete data basis for the subsequent analysis of the training difficulty of the trainees in different scenarios.

[0036] Furthermore, step S2 of the embodiment of the present application includes:

[0037] Step S21: Acquire a plurality of sample training data of a plurality of sample students who have been trained in the plurality of training scenarios.

[0038] Step S22: Calculate and analyze, based on the multiple sample training data and the historical training data, to obtain multiple training difficulties for the target trainee for the multiple training scenarios.

[0039] Specifically, sample students refer to students other than the target students, and the training data of these students are used as reference samples for comparative analysis with the data of the target students. For example, among the students using the driving simulator, some other students who are in the same training stage as the target students and have similar driving experience bases are selected as sample students. For these sample students, the sample training data corresponding to each sample student is collected in a manner similar to the aforementioned collection of historical training data of the target students, including information such as the number of trainings and the number of training errors of each sample student in each training scenario, to generate multiple sample training data. The sample training data provides a reference standard for analyzing the training difficulty of the target students, so that the training situation of the target students can be evaluated in the context of a group.

[0040] Compare the data differences between the target students and the sample students in each training scenario, and use statistical analysis methods to determine the target students' performance and training difficulty in different training scenarios. For example, if the target student's performance in the night driving scenario is significantly different from that of other sample students, it indicates that the scenario is more difficult for the target student. By calculating and analyzing the differences between the sample training data and the target student's historical training data, the training difficulty of the target student in each training scenario can be objectively and accurately determined, providing an important basis for the subsequent optimization of training parameters for the target student.

[0041] Further, such as Figure 2 As shown, step S22 includes:

[0042] Step S221: extracting and obtaining a plurality of sets of sample training times and a plurality of sets of sample training error times of the plurality of training scenarios according to the plurality of sample training data.

[0043] Step S222: respectively calculating the ratios of the multiple sample training times sets to the multiple sample training error times sets to obtain multiple sample error rate sets, and calculating the mean to obtain multiple average error rates of the multiple training scenarios.

[0044] Step S223: Calculate the ratios of the multiple historical training error times to the multiple historical training times respectively, and obtain multiple error rates of the multiple training scenarios.

[0045] Step S224: Calculate the ratios of the multiple error rates to the multiple average error rates respectively to obtain multiple basic training difficulties.

[0046] Step S225: respectively calculating the mean values ​​of the plurality of sample training times sets to obtain a plurality of average training times.

[0047] Step S226: Calculate the ratios of the multiple historical training times to the multiple average training times respectively, obtain multiple times correction coefficients, multiply them by the multiple basic training difficulties respectively, complete the correction calculation, and obtain multiple training difficulties.

[0048] Specifically, when conducting a training difficulty analysis for target students, since the difficulty of different training scenarios is not the same, it is necessary not only to consider the performance of the target students themselves, but also to compare with the performance of other students in order to accurately and objectively evaluate the training difficulty of the target students.

[0049] First, the number of sample training times and the number of sample training errors of each sample student in each training scenario are extracted from multiple sample training data to generate multiple sets of sample training times and multiple sets of sample training errors for multiple training scenarios. Among them, the sample training times set includes the set of training times of all sample students in a specific training scenario. The sample training error times set includes the set of training errors of all sample students in a specific training scenario. In the process of extracting sample data, the corresponding sample student number and training scenario label can be added to each data to indicate the source of the data, which is convenient for subsequent comparison and data calculation.

[0050] For each training scenario, divide each element in the sample training error number set by the element in the corresponding sample training number set to obtain the sample error rate set. For example, in the urban road scenario, sample student A has trained 10 times, made 2 mistakes, and has an error rate of 20%; sample student B has trained 15 times, made 3 mistakes, and has an error rate of 20%. Similarly, calculate the error rates of all sample students in this scenario to form a sample error rate set. Then, calculate the average of the sample error rate set to obtain the average error rate for this scenario. Use the same method to process the sample training data of other training scenarios to obtain multiple average error rates for multiple training scenarios. The average error rate represents the average error level of the sample students in the corresponding training scenario, and provides a reference standard for the subsequent evaluation of the training difficulty of the target students.

[0051] For the target student, multiple error rates for multiple training scenarios are calculated in the same way as for the sample students. That is, the target student's historical training error count in each training scenario is divided by the historical training count to obtain the error rate in that scenario. For example, the target student has 8 historical training times and 3 errors in the urban road scenario, and his error rate is 37.5%. The error rate of the target student reflects his actual error situation in each training scenario.

[0052] Divide the target student's error rate in each training scenario by the corresponding average error rate to obtain the basic training difficulty. The larger the ratio of the error rate to the average error rate, the greater the basic training difficulty, indicating that the training scenario is more difficult for the target student. When the target student's error rate is greater than the average error rate of multiple sample students, the basic training difficulty is greater than 1, otherwise it is less than or equal to 1. For example, in the urban road scenario, the target student's error rate is 37.5% and the average error rate is 20%, then the basic training difficulty is 37.5% / 20%=1.875. This means that the training difficulty of the target student in this scenario is 87.5% higher than the average level of the sample students.

[0053] The basic training difficulty preliminarily reflects the training difficulty of the target trainees in each training scenario relative to the sample trainees. Theoretically, during the training process, as the number of training times for each scenario increases, the trainees' operational proficiency in that scenario will also increase, and the error rate will decrease. If a trainee still fails the test after multiple trainings in a certain training scenario, it means that the training scenario is more difficult for the trainee. Considering the impact of the number of training times on the training results, after obtaining the basic training difficulty, it needs to be corrected according to the number of training times, so as to more realistically reflect the training difficulty of each training scenario for the target trainees.

[0054] First, the average value of the sample training times set in each training scenario is calculated to obtain the average training times. The average training times reflects the average training input of the sample students in each training scenario, and provides a reference for the subsequent times correction. The ratio of the historical training times of the target students in each training scenario to the average training times is calculated to obtain multiple times correction coefficients. Then, the multiple times correction coefficients are multiplied by the corresponding basic training difficulty to obtain multiple corrected training difficulties. Each training difficulty corresponds to a training scenario. For example, in the urban road scenario, the historical training times of the target students are 8 times, and the average training times are 12 times, then the times correction coefficient is 8 / 12=0.667. The basic training difficulty is 1.875, then the corrected training difficulty is 1.875×0.667=1.247. Through the correction calculation, the training difficulty can be automatically adjusted according to the training times of the students, so as to more accurately reflect the training difficulty of the target students in each training scenario, so that the subsequent training parameter adjustment is more in line with the actual performance of the target students.

[0055] Further, such as Figure 3 As shown, step S3 of the embodiment of the present application includes:

[0056] Step S31: configuring multiple scene weights according to the multiple training difficulties.

[0057] Step S32: Obtain the total training time of the target student for driving simulation training.

[0058] Step S33: randomly allocating the total training time to the multiple training scenes to obtain multiple first scene training times as multiple first scene training parameters.

[0059] Step S34: predicting the training success rate according to the multiple training difficulties and the multiple first scenario training times, and obtaining the multiple first scenario training success rates.

[0060] Step S35: Calculate and obtain the first training fitness of the multiple first scene training parameters according to the multiple scene weights and the multiple first scene training success rates.

[0061] Step S36: Continue to optimize the scene training parameters of the multiple training scenes until convergence, output multiple scene training parameters with the largest training fitness, and obtain the multiple optimal scene training parameters.

[0062] Specifically, scenario weight refers to the relative importance or priority of training difficulty in different training scenarios. According to the difficulty of training, a scenario weight is assigned to each training scenario, and the size of the weight reflects the training difficulty of the scenario or the training value to the target trainees. Training scenarios with higher training difficulty will be assigned larger weights, and relatively longer training time will be configured for the training scenarios later, while scenarios with lower training difficulty will be assigned smaller weights to ensure that the training time is reasonably allocated according to the difficulty of each scenario, thereby optimizing the training effect of the target trainees. The specific weight allocation can be determined based on actual conditions and experience, or it can be optimized through data analysis. For example, the training difficulty is used as input, and the weight is calculated through a linear function or a nonlinear function.

[0063] The total training time refers to the total time the target trainee spends training on the driving simulator. The interactive driving simulator determines the total time the target trainee spends training, i.e. the total training time, based on the trainee’s training needs and plans.

[0064] The first scenario training time refers to the initial training time randomly assigned to each training scenario, which serves as the basis for subsequent training parameter optimization. The total training time of the target trainees is randomly assigned to different training scenarios to obtain multiple first scenario training times corresponding to multiple training scenarios, and the multiple first scenario training times are used as multiple first scenario training parameters. For example, a random number generator can be used to assign an initial training time to each scenario. Randomly assigning training time provides an initial solution space for subsequent optimization.

[0065] The first scenario training success rate refers to the probability of the target trainee achieving success in each scenario, based on the initially allocated training time and training difficulty. Based on the training difficulty and the first scenario training time, a prediction model is trained based on historical data, and the prediction model is used to estimate the first scenario training success rate in each scenario. The prediction model can be trained using statistical models, such as linear regression, logistic regression, etc., or machine learning models, such as decision trees, support vector machines, etc., to predict the training success rate of the target trainee in the corresponding training scenario according to the set first scenario training time. The prediction of the training success rate can help evaluate the rationality of the current training parameter settings.

[0066] Combine the scene weight and the first scene training success rate to calculate the first training fitness of each first scene training parameter. This first training fitness can reflect the quality of the current training parameter settings. The fitness can be calculated using a weighted average method. For example, multiply the training success rate of each scene by its corresponding scene weight, and then sum them up to get the fitness. The calculation of the first training fitness provides an evaluation criterion for subsequent parameter optimization.

[0067] Use optimization algorithms, such as genetic algorithms and particle swarm optimization algorithms, to optimize the parameters of the training scenarios. In each iteration, adjust the allocation of training time according to the fitness until the fitness converges to a stable value. Finally, output multiple scenario training parameters with the largest training fitness as multiple optimal scenario training parameters to provide the most personalized and effective training arrangements for target students.

[0068] The above steps optimize the scene training parameters by setting scene weights and fitness functions, continuously adjust the duration distribution of each training scene, and determine the optimal scene training parameters for each training scene to maximize the training effect.

[0069] Further, step S34 includes:

[0070] Step S341: Based on the historical training data of multiple sample students, multiple sample training difficulty sets and multiple sample scene training time sets of the multiple training scenes are collected, and the percentage of successful training times after training is collected to obtain multiple sample scene training success rate sets.

[0071] Step S342: respectively using the multiple sample training difficulty sets, the multiple sample scene training time sets and the multiple sample scene training success rate sets as multiple supervised training data, training multiple training success prediction branches, and obtaining a training success prediction model.

[0072] Step S343: input the multiple training difficulties and the multiple first scenario training times into the corresponding training success prediction branches respectively, and predict and output to obtain multiple first scenario training success rates.

[0073] Specifically, the sample training difficulty set is a set consisting of the training difficulties of multiple sample students in various training scenarios. For example, for the urban road training scenario, the training difficulty data of all sample students in this scenario form a sample training difficulty set. The sample scenario training time set is a set consisting of the training time of multiple sample students in various training scenarios. The sample scenario training success rate set is a set consisting of the ratio of the number of successful trainings of multiple sample students in various training scenarios to the total number of trainings, reflecting the training success of the sample students in different scenarios. The training success prediction branch is a model branch built for different training scenarios to predict the probability of training success, and each branch specializes in data prediction in a specific scenario. The training success prediction model is an overall model composed of multiple training success prediction branches, which is used to predict the training success rate based on the input training difficulty and training time.

[0074] The historical training data of the sample students are classified and sorted according to the training scenarios. For each training scenario, the training difficulty data of the sample students are extracted to form a sample training difficulty set, and the training time data are extracted to form a sample scenario training time set. At the same time, the proportion of the number of successful training times of each sample student in the training scenario to the total number of training times is counted, and these proportion data are combined into a sample scenario training success rate set. For multiple training scenarios, multiple sample training difficulty sets, multiple sample scenario training time sets, and multiple sample scenario training success rate sets can be obtained accordingly.

[0075] For each training scenario, the corresponding sample training difficulty set, sample scenario training time set, and sample scenario training success rate set are used as a supervised training data. These data are used to train the training success prediction branch for the training scenario. For example, for the urban road scenario, its sample training difficulty set, sample scenario training time set, and sample scenario training success rate set are used to train a branch that specifically predicts the urban road training success rate. The training process can be trained using models such as regression models, neural networks, and decision trees. Multiple training success prediction branches are combined to form a training success prediction model.

[0076] Taking the linear regression model as an example, for each training scenario, its training data includes the sample training difficulty set (set as X1), the sample scenario training time set (set as X2) and the sample scenario training success rate set (set as Y) under the corresponding training scenario. For the training difficulty and training time data, the minimum-maximum normalization method is used for normalization so that its numerical range is within a suitable interval to facilitate model training. The basic form of the linear regression model is y=β0+β1x1+β2x2+e, where y is the predicted training success rate (taken from Y), x1 is the training difficulty (taken from X1), x2 is the training time (taken from X2), β0 is the intercept, β1 and β2 are regression coefficients, and e is the error term. Initialize the regression coefficients β0, β1, and β2 of the linear regression model. Select the mean square error (MSE) as the loss function. Select the gradient descent algorithm as the optimization algorithm to iteratively update the regression coefficients to minimize the loss function. In each iterative training process, the model calculates the predicted value y for the training set sample based on the current regression coefficients β0, β1, and β2. i , then calculate the loss function and update the regression coefficient according to the gradient descent algorithm. Repeat the iteration process until the stopping condition is reached. The stopping condition can be that the maximum number of iterations is reached or the value of the loss function is less than a preset threshold. Output the trained linear regression model at this time, and then use the trained model to predict the test set data. The test set is a part of the data divided in advance from the training data. For each sample in the test set (x 1i , x 2i ), calculate the predicted training success rate y i =β0+β1x 1i +β2x 2i +e. Use the root mean square error as the evaluation indicator to evaluate the prediction results. The smaller the root mean square error value, the better the prediction effect of the model. The model that meets the expected effect is regarded as the successful training prediction branch.

[0077] The training difficulty and first-scenario training time of each training scenario of the target student are respectively input into the corresponding training success prediction branch in the training success prediction model. For example, the training difficulty and first-scenario training time data of the target student in the urban road scenario are input into the branch that specifically predicts the urban road training success rate. The model predicts and outputs the first-scenario training success rate in this scenario based on the previously learned relationship.

[0078] Through the training success prediction model, the first-scenario training success rate of the target students in various training scenarios can be predicted quickly and accurately, providing data support for the subsequent calculation of the first training fitness, making the allocation of training time and the adjustment of training content more scientific and reasonable, thereby improving the overall training quality.

[0079] Furthermore, the calculation formula in step S35 is as follows: Among them, FCJ is the training fitness, M is the number of multiple training scenarios, and w i is the scene weight of the i-th training scene, K i is the scene training success rate of the i-th training scene.

[0080] Specifically, the training success rates K of the multiple scenarios obtained in step S34 are i and the scene weight w configured for each training scene in step S31 i , and the total number of training scenarios M, substitute into the fitness calculation formula: In the optimization process, the first training fitness of multiple first scene training parameters is calculated. In the whole optimization process, after each iteration, the scene training success rate of each training scene is predicted according to the adjusted scene training parameters, and then the fitness calculation formula is substituted to calculate the training fitness under the corresponding configuration, and the scene training parameter combination with the highest fitness is gradually found, so as to maximize the training efficiency and training quality, and finally improve the training success rate and overall learning effect of the target trainees in multiple training scenes.

[0081] In summary, the multi-scenario switching driving simulator control method provided in the embodiment of the present application has the following technical effects:

[0082] The embodiment of the present application collects the historical training data of the students, analyzes the training difficulty in different scenarios, and then optimizes the training parameters and applies them to the training control of the driving simulator. This method fully takes into account the individual differences of the students, and the optimized training parameters are more in line with the actual situation of the students, so that the students can train under conditions that are more suitable for their own learning progress, which helps the students to master driving skills faster and reduce the training time wasted under parameters that are not suitable for them, thereby improving the efficiency of the entire training process. At the same time, personalized training parameters and scene-specific optimization can allow students to receive more effective training in each training scenario, so that students can better adapt to the driving requirements in different scenarios, comprehensively improve driving skills, and thus improve the overall quality of training.

[0083] Embodiment 2, based on the same inventive concept of the driving simulator control method for multi-scene switching in the aforementioned embodiment 1, the present application also provides a computer device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the method described in the aforementioned embodiment 1.

[0084] like Figure 4As shown, the bus architecture is represented by bus 300, which may include any number of interconnected buses and bridges, and bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, namely a transceiver, providing a unit for communicating with various other devices on a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0085] Embodiment three, based on the same inventive concept of the multi-scene switching driving simulator control method in the aforementioned embodiment one, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned multi-scene switching driving simulator control method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0086] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-scene switching driving simulator control method, characterized in that: The method comprises: Collecting historical training data of the target trainee in a historical period, wherein the historical training data includes training data of multiple training scenarios; Analyzing, based on the historical training data, multiple training difficulties of the target trainee for the multiple training scenarios; According to the multiple training difficulties, optimizing the training parameters of the multiple training scenarios for the target trainee to obtain multiple optimal scenario training parameters; The plurality of optimal scenario training parameters are used to configure the training parameters of the plurality of training scenarios in the driving simulator, and to perform training control on the target trainee.

2. The multi-scenario switching driving simulator control method according to claim 1, characterized in that: Collect historical training data of target students over a historical period of time, including: Collecting the number of times the target trainee has trained the multiple training scenarios in a historical period to obtain multiple historical training times; Collecting the number of training errors of the target trainee during training of the plurality of training scenarios in a historical period to obtain a plurality of historical numbers of training errors; The multiple historical training times and the multiple historical training error times are integrated to obtain the historical training data of the target student.

3. The multi-scenario switching driving simulator control method according to claim 2, characterized in that: Analyzing the multiple training difficulties of the target trainee for the multiple training scenarios according to the historical training data, including: Acquire a plurality of sample training data of a plurality of sample trainees performing training on the plurality of training scenarios; Based on the multiple sample training data and the historical training data, multiple training difficulties of the target trainee for the multiple training scenarios are obtained through calculation and analysis.

4. The multi-scenario switching driving simulator control method according to claim 3 is characterized in that: Calculating and analyzing the plurality of sample training data and the historical training data to obtain a plurality of training difficulties of the target trainee for the plurality of training scenarios includes: Extracting, based on the plurality of sample training data, a plurality of sample training frequency sets and a plurality of sample training error frequency sets of the plurality of training scenarios; Calculating the ratios of the multiple sample training times sets and the multiple sample training error times sets respectively to obtain multiple sample error rate sets, and calculating the average to obtain multiple average error rates of the multiple training scenarios; Calculating the ratios of the multiple historical training error times to the multiple historical training times respectively, to obtain multiple error rates of the multiple training scenarios; Calculating the ratios of the multiple error rates to the multiple average error rates respectively to obtain multiple basic training difficulties; Calculating the mean values ​​of the plurality of sample training times sets respectively to obtain a plurality of average training times; The ratios of the multiple historical training times and the multiple average training times are calculated respectively to obtain multiple times correction coefficients, which are multiplied by the multiple basic training difficulties respectively to complete the correction calculation and obtain multiple training difficulties.

5. The multi-scenario switching driving simulator control method according to claim 1, characterized in that: According to the multiple training difficulties, the training parameters of the multiple training scenarios for the target trainee are optimized to obtain multiple optimal scenario training parameters, including: According to the multiple training difficulties, configuring multiple scene weights; Obtaining the total training time of the target student for driving simulation training; Randomly allocating the total training time to the multiple training scenes to obtain multiple first scene training times as multiple first scene training parameters; Predicting the training success rate according to the multiple training difficulties and the multiple first scenario training times to obtain the multiple first scenario training success rates; Calculating and obtaining the first training fitness of the plurality of first scene training parameters according to the plurality of scene weights and the plurality of first scene training success rates; Continue to optimize the scene training parameters of the multiple training scenes until convergence, output multiple scene training parameters with the largest training fitness, and obtain the multiple optimal scene training parameters.

6. The multi-scenario switching driving simulator control method according to claim 5, characterized in that: According to the multiple training difficulties and the multiple first scenario training times, a training success rate prediction is performed to obtain multiple first scenario training success rates, including: According to the historical training data of multiple sample students, multiple sample training difficulty sets and multiple sample scenario training time sets of the multiple training scenarios are collected, and the percentage of the number of successful trainings after training is collected to obtain multiple sample scenario training success rate sets; The plurality of sample training difficulty sets, the plurality of sample scene training time sets, and the plurality of sample scene training success rate sets are respectively used as a plurality of supervised training data to train a plurality of training success prediction branches to obtain a training success prediction model; The multiple training difficulties and the multiple first scenario training times are respectively input into corresponding training success prediction branches, and the prediction output obtains multiple first scenario training success rates.

7. The multi-scenario switching driving simulator control method according to claim 5, characterized in that: According to the multiple scene weights and the multiple first scene training success rates, the first training fitness of the multiple first scene training parameters is calculated as follows: Among them, FCJ is the training fitness, M is the number of multiple training scenarios, and w i is the scene weight of the i-th training scene, K i is the scene training success rate of the i-th training scene.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the multi-scene switching driving simulator control method described in any one of claims 1-7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-scene switching driving simulator control method as described in any one of claims 1 to 7 are implemented.

Images