Driving school data management method for driving training contract management

Abstract

The invention discloses a driving school data management method for driving training contract management, and relates to the technical field of machine learning, and the method comprises the following steps: data collection and student information input; making a training plan according to the student information; performing course tracking and adjustment according to the training plan; performing contract validity period prediction according to the training performance data; fee payment and fee refund management are carried out by using contract validity period prediction data; trainee compliance detection is carried out through contract and payment data; performing contract renewal according to a detection result; and generating an optimization management decision report based on the renewal result. According to the innovative compliance detection method based on the weighted logistic regression model, the model parameters are adjusted in real time, and the weights of the features are optimized, so that a driving school can monitor the compliance of trainees more accurately, potential default behaviors are found in time, the management efficiency is improved, and the default risk is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of machine learning, and specifically provides a driving school data management method for driving training contract management. Background Art

[0002] With the rapid development of intelligent and digital technologies, the operation and management of driving schools have gradually become automated and intelligent. Especially in the process of student training and contract management, the application of data management and analysis technologies is becoming more and more extensive.

[0003] Most existing driving school data management systems rely on traditional manual operations or simple rule-based systems, making it difficult to comprehensively and real-time reflect multi-dimensional information such as the training progress, compliance status, and course profitability of students, resulting in problems such as low management efficiency, lagging decision-making, and inaccurate information. To improve management efficiency and decision-making accuracy, modern driving school data management systems have gradually adopted machine learning technologies such as deep learning and logistic regression models to assist decision-making and automate processing. Especially in student compliance detection and operation decision support, combining big data analysis and intelligent models has become a trend.

[0004] The deficiencies of the existing logistic regression model in analyzing student compliance. The logistic regression models in the existing technologies usually only perform binary classification analysis based on fixed input features (such as the payment history and learning progress of students) to determine whether students are compliant. The traditional logistic regression model uses fixed weights during the training process and does not consider dynamic change factors such as the historical behavior and time sensitivity of students. The prediction results of the model lack flexibility and cannot accurately capture the timely changes of student behavior and the relationships between multi-dimensional factors. The traditional model rarely considers the compliance history of students and lacks effective tracking and dynamic adjustment for students who have had default behaviors, resulting in a decline in the accuracy of the model. Summary of the Invention

[0005] In view of the deficiencies of the existing technology, the present invention provides a driving school data management method for driving training contract management to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides a driving school data management method for driving training contract management, including the following steps: S1. Data collection and student information entry; Collect the basic information of students through an online platform or a mobile terminal and enter it into the management system; S2. Training plan formulation according to student information; The system formulates a training plan according to the basic information of students; S3. Conduct course tracking and adjustment according to the training plan; The system conducts real-time tracking of the training of trainees according to the training plan and generates training performance data; S4. Predict the contract validity period based on the training performance data; The system determines the time for trainees to complete the entire training course and whether they can pass the exam on time based on the training performance data to obtain contract validity period prediction data; S5. Use the contract validity period prediction data for fee payment and refund management; The system manages the fee payment of trainees in combination with the contract validity prediction data to obtain contract and payment data; S6. Conduct trainee compliance detection through the contract and payment data; The system checks whether trainees have completed the corresponding courses as agreed in the contract and determines whether all fees have been paid through a logistic regression model to obtain the detection results; S7. Renew the contract according to the detection results; The system decides whether to recommend renewing the contract based on the detection results to obtain the renewal results; S8. Generate an optimized management decision report based on the renewal results; Based on the results of all the previous steps, the system generates an optimized management decision report through data visualization.

[0007] To further optimize this technical solution, the trainee information in step S1 includes: Trainee background: age, gender, driving experience; Learning objectives: driving skills that the trainee hopes to improve; Physical conditions: eyesight, reaction speed; Time arrangement: free time for training.

[0008] To further optimize this technical solution, the training plan in step S2 includes: Training content: For beginners, start with basic driving operations; for trainees with driving experience, start with traffic environment simulation training; Training time: Determine the training time according to the time arrangement and learning objectives in the trainee information. The training time for beginners should be longer than that for trainees with driving experience.

[0009] To further optimize this technical solution, the course adjustment in step S3 includes: During the real-time tracking of the training of trainees, the management system identifies that trainees do not operate according to the steps required by the exam or the coach during the process of learning the driving course. The system will remind the coach to change the training plan and remind the operation steps that need to be strengthened or emphasized and record the number of reminders.

[0010] Further optimize this technical solution. The contract validity period prediction in step S4 includes: The management system will change the end date of the contract according to the training performance data of the trainees; for trainees with a reminder count of 0 for training performance data, shorten the end date of the contract, and for trainees with a reminder count of more than 3 for training performance data, extend the end date of the contract.

[0011] Further optimize this technical solution. The fee payment and refund management in step S5 includes: The management system calculates based on the contract validity period prediction data and the charging standard of the driving school to obtain the charging data; for trainees who complete the courses in advance, reduce the fees to be paid, and for trainees who complete the courses late, increase the fees to be paid.

[0012] Further optimize this technical solution. The logistic regression model in step S6 includes: Define the compliance prediction label ; The value range of is between 0 and 1, and the value of this label represents whether the trainee is compliant; When it is 1, the trainee is compliant; When it is 0, the trainee is non-compliant; Construct the probability calculation formula of the prediction label : ; ; Among them, z represents a parameter; represents the learning progress of the trainee and is assigned a value according to the number of completed courses: ; represents the payment history of the trainee, 1 for on-time payment and 0 for late payment; represents the contract performance of the trainee, 1 for compliance with the contract and 0 for non-compliance; represents the category of the trainee, 0 for beginners and 1 for trainees who have already taken courses; represents the urgency of the trainee's feedback, which is calculated based on the time sensitivity of the trainee's feedback, and its formula is: ; Among them: is the difference between the time when the trainee submits the feedback and the current time, indicating the time since the trainee's feedback was submitted; is a constant that adjusts the decay rate, ; represents the compliance history of the trainee, indicating whether there were any violations before this training. This value is quantified based on the trainee's past compliance behavior records; Its calculation method is: ; wherein, the number of defaults is the number of the trainee's past violation records; is the impact coefficient of the default record. Its value is 1 for the first default, 2 for the second, and so on; when the default record is 0, ; n = 6; is the eigenvector; represents the probability of the trainee's compliance; Manually set a threshold m, whose value range is between 0 and 1. Compare the value of with the value of m. If is greater than m, then it is determined that the trainee is compliant; otherwise, the trainee is non - compliant.

[0013] To further optimize this technical solution, the calculation formula of the said is: ; wherein, represents the basic compliance score, which is manually set; represents the weights of various data, which are assigned by the driving school according to the actual situation. The values with greater influence are larger than those with smaller influence.

[0014] To further optimize this technical solution, the determination criterion for whether to recommend renewing the contract in step S7 is: When the trainee has completed all the learning courses and the of this trainee is greater than the threshold m, the management system will recommend that the trainee renew the contract and provide new intensive courses.

[0015] To further optimize this technical solution, in step S8, by means of data visualization, the generated optimized management decision report includes: The management system generates a visual table based on the student's background, learning objectives, physical conditions, time arrangements, training plans, training performance data, contract validity data, and renewal results, lists the above contents and provides written explanations, and presents them to the decision-makers for decision-making.

[0016] In a second aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program instructions are executed by the processor, the steps of a driving training contract management-based driving school data management method as described in the first aspect of the present invention are implemented.

[0017] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program instructions are executed by the processor, the steps of a driving training contract management-based driving school data management method as described in the first aspect of the present invention are implemented.

[0018] Compared with the prior art, the present invention provides a driving school data management method for driving training contract management, which has the following beneficial effects: The driving school data management method for driving training contract management proposes an innovative compliance detection method based on a weighted logistic regression model. By introducing dynamic feature weight adjustment and student compliance history tracking, the model can dynamically adjust the weights of each feature in real time according to the student's latest behaviors (such as payment history, default records, learning progress, etc.), and combine timeliness factors for more accurate compliance judgment. This method effectively solves the problems of static features and ignoring compliance history in traditional logistic regression models. By adjusting the model parameters and optimizing the weights of features in real time, the driving school can more accurately monitor the compliance of students, timely discover potential default behaviors, improve management efficiency, reduce default risks, and ensure the strict execution of the contracts between students and the driving school. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a flowchart of a driving school data management method for driving training contract management proposed by the present invention; Figure 2 It is a flowchart of compliance detection based on a logistic regression model of a driving school data management method for driving training contract management proposed by the present invention; Figure 3It is a flow chart for predicting the contract validity period of a driving school data management method for driving training contract management proposed by the present invention. Specific Embodiments

[0021] To make the above objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings of the specification.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may be practiced in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0023] Secondly, the so-called "one embodiment" or "embodiment" refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an individual or selectively exclusive embodiment with other embodiments.

[0024] Embodiment 1: Refer to Figures 1 to 3 , which is the first embodiment of the present invention. This embodiment provides a driving school data management method for driving training contract management, including the following steps: S1. Data collection and student information entry.

[0025] Collect the basic information of students through an online platform or a mobile terminal and enter it into the management system.

[0026] Student information includes: Student background: age, gender, driving experience; Learning goals: driving skills that the student hopes to improve; Physical conditions: eyesight, reaction speed; Time arrangement: free time for training.

[0027] In this embodiment, it is also necessary to collect the basic information of students, such as name, ID number, contact information, student category (beginner or advanced student), etc. This information will be used for subsequent student identity verification and data tracking.

[0028] S2. Develop a training plan based on the student information.

[0029] The system develops a training plan based on the basic information of the students.

[0030] The training plan includes: Training content: For beginners, start with basic driving operations; for students with driving experience, start with traffic environment simulation training.

[0031] Training time: Determine the training time according to the time arrangement in the student information and the learning objectives. The training time for beginners should be longer than that for students with driving experience.

[0032] In this embodiment, in this way, the training plan can be flexibly adjusted according to the actual situation of each student to ensure that each student can efficiently complete the learning tasks according to the plan.

[0033] S3. Conduct course tracking and adjustment according to the training plan.

[0034] The system tracks the training of students in real time according to the training plan and generates training performance data.

[0035] Course adjustment includes: When the management system identifies during the real-time tracking of a student's training that the student does not operate according to the steps required by the exam or the coach during the process of learning the driving course, the system will remind the coach to change the training plan and remind the operation steps that need to be strengthened or emphasized and record the number of reminders.

[0036] In this embodiment, if a student fails multiple times during the training of backing into the parking space, the system will recommend increasing the frequency of backing practice until the student can master it proficiently. In this way, the learning quality of the student can be optimized in real time.

[0037] S4. Predict the contract validity period based on the training performance data.

[0038] The system determines the time for the student to complete the entire training course and whether the student can pass the exam on time based on the training performance data to obtain the contract validity period prediction data.

[0039] Contract validity period prediction includes: The management system will change the end date of the contract according to the training performance data of the student; for students with 0 reminder numbers in the training performance data, shorten the end date of the contract, and for students with reminder numbers exceeding 3 times in the training performance data, extend the end date of the contract.

[0040] The contract validity period prediction data is the end date of the student's contract.

[0041] In this embodiment, by analyzing the training performance data of the student, the system will predict the time for the student to complete the entire training course and whether the student can pass the exam on time. This method effectively reduces the problems of manual prediction and inaccurate contract management.

[0042] S5. Use the contract validity period prediction data for fee payment and refund management.

[0043] The system manages the fee payment of trainees by combining contract validity prediction data, and obtains contract and payment data.

[0044] The fee payment and refund management includes: The management system calculates according to the contract validity prediction data and the charging standard of the driving school to obtain the charging data; for trainees who complete the courses in advance, the fees to be paid are reduced, and for trainees who complete the courses late, the fees to be paid are increased.

[0045] In this embodiment, when signing a training contract, a trainee pays a certain fee according to the number and cycle of training courses. If a trainee completes the courses in advance, the system recalculates the fees according to the number of courses and makes a refund. On the contrary, if a trainee delays the training end date, the system will charge a late fee according to the remaining training courses and the extra time.

[0046] S6. Conduct trainee compliance detection through contract and payment data; The system uses a logistic regression model to check whether a trainee has completed the corresponding courses as agreed in the contract and determines whether all fees have been paid, and obtains the detection result.

[0047] The logistic regression model includes: Define the compliance prediction label ; The value range of is between 0 and 1, and the value of this label represents whether the trainee is compliant; When is 1, the trainee is compliant; When is 0, the trainee is non-compliant; Construct the probability calculation formula of the prediction label : ; ; Among them, z represents a parameter; represents the learning progress of the trainee, and is assigned according to the number of completed courses: ; represents the payment history of the trainee, 1 for on-time payment and 0 for non-on-time payment; represents the contract performance of the trainee, 1 for observing the contract and 0 for not observing; represents the category of the trainee, 0 for beginners and 1 for trainees who have already taken courses; Indicates the urgency of the trainee's feedback, which is calculated based on the time sensitivity of the trainee's feedback. The formula is as follows: ; Where: is the difference between the time when the trainee submitted the feedback and the current time, representing the time since the trainee's feedback was submitted; is a constant that adjusts the attenuation rate, ; represents the trainee's compliance history, indicating whether there were any violations before this training. This value is quantified based on the trainee's past compliance records; Its calculation method is: ; Where, The number of defaults is the number of the trainee's past violation records; is the impact coefficient of the default record. Its value is 1 for the first default, 2 for the second, and so on; When the default record is 0, ; n = 6; is the eigenvector; represents the probability of the trainee's compliance; Manually set a threshold m, whose value range is between 0 and 1, and compare the value of with the value of m. If is greater than m, it is determined that the trainee is compliant; otherwise, the trainee is non-compliant.

[0048] The formula for the above-mentioned is: ; Where, represents the basic compliance score, which is set manually; represents the weights of various data, which are assigned by the driving school according to the actual situation, and the values with greater influence are larger than those with smaller influence.

[0049] In this embodiment, the following steps are required to use this model: Feature collection: Collect the trainee's feature data from the trainee management system, including: name, learning progress, payment history, contract fulfillment status, trainee category, compliance history. Generate an input vector through these features .

[0050] Model Training: Use historical data to train the model to ensure that the weights of each feature conform to the values assigned by the driving school according to the actual situation. If they are different, changes need to be made. This process usually optimizes the parameters through maximum likelihood estimation (MLE) or gradient descent method.

[0051] The process of optimizing parameters through the maximum likelihood method includes: Likelihood function, the probability of the observed data given the model parameters. If we have a sample set , the likelihood function can be expressed as: ; where represents the model parameters.

[0052] Logarithmic function model: Since the product of the likelihood function may encounter underflow problems in numerical calculations, the log-likelihood function is usually used, which converts the product into a sum: ; Maximum likelihood estimation: The goal of maximum likelihood estimation is to find the parameter value that maximizes the log-likelihood function. This is usually achieved by solving the following optimization problem: ; The solution methods include analytical methods and numerical methods.

[0053] Analytical method: If the log-likelihood function is differentiable, the maximum value can be found by taking the derivative and setting the derivative to zero.

[0054] Numerical method: If the log-likelihood function is too complex to be solved analytically, numerical optimization algorithms such as gradient descent can be used.

[0055] Properties of MLE: Under certain conditions, MLE is consistent, that is, as the sample size increases, the estimated value converges to the true parameter value.

[0056] MLE has asymptotic normality, that is, when the sample size is large enough, the distribution of MLE is approximately normal.

[0057] MLE has the smallest variance among all unbiased estimators, that is, it is efficient.

[0058] In logistic regression, MLE is used to estimate the model parameters to maximize the likelihood between the probability predicted by the model and the actual observed labels (such as compliant or non-compliant). In this way, the model parameters that can best explain the data can be found.

[0059] Compliance prediction: Input the new trainee data into the trained model to calculate the compliance probability.

[0060] If it is higher than the set threshold (e.g., 0.7), then it is determined that the trainee is compliant; if it is lower than the threshold, then it is determined that the trainee is non-compliant.

[0061] Real-time feedback mechanism: Through the real-time feedback mechanism, apply the output result of the model to trainee management. For example, if a trainee fails to pay the fees on time, the system will generate a notice to remind the trainee to make up the payment; if the compliance of a trainee is low, the system will mark the trainee and provide optimization suggestions.

[0062] S7. Renew the contract according to the detection result.

[0063] The system decides whether to recommend renewing the contract according to the detection result to obtain the renewal result.

[0064] The criteria for determining whether to recommend renewing the contract are as follows: When the trainee has completed all the learning courses and the is greater than the threshold m, the management system will recommend that the trainee renew the contract and provide new intensive courses.

[0065] In this embodiment, the new intensive courses can be courses other than the subjects required for the exam. For example, the concept of safe driving (being familiar with traffic rule changes), defensive driving (emphasizing predictability and initiative, predicting the behavior of other drivers and reacting quickly to avoid accidents), and basic motor vehicle knowledge (vehicle structure, main safety devices, vehicle inspection and maintenance).

[0066] S8. Generate an optimized management decision report based on the renewal result; According to the results of all the previous steps, the system generates an optimized management decision report in a data visualization manner.

[0067] The optimized management decision report includes: The management system generates a visual table based on the trainee's background, learning objectives, physical conditions, time arrangements, training plans, training performance data, contract validity period data, and renewal results, lists the above contents and gives a written description, and presents it to the decision maker for decision-making.

[0068] In this embodiment, the system will use a method that combines deep learning and data visualization to generate multi-dimensional management reports, which helps driving school managers make decisions. The system can not only display basic information such as the training progress of students, fee payment status, contract compliance, etc., but also discover potential problems and optimization directions through data analysis. For example, the report can show information such as which courses are the most popular and the passing rates of students in certain courses. Based on this information, managers can identify weak links in the operation of the driving school and further optimize the course content and service quality. This visual report not only provides an instant display of data, but also generates personalized reports according to the needs of students and management goals, greatly improving management efficiency and decision-making support capabilities.

[0069] Deep learning and data visualization include: Multi-task deep neural network model: Set the output of the model to contain target variables for multiple tasks , where each represents the result of a prediction task, such as the prediction of the training progress of students, the prediction of course profitability, etc.

[0070] Task 1: Prediction of students' training progress .

[0071] Task 2: Prediction of course profitability .

[0072] The goal of the constructed deep neural network model is to solve these two tasks simultaneously through shared underlying feature learning. The output of the model consists of multiple prediction values, and the model optimizes each task through different loss functions.

[0073] ; Among them, , ; are all vectors. represents the multi-dimensional data required for Task 1 (learning progress, assigned according to the number of completed courses; contract fulfillment status: 1 for compliance, 0 for non-compliance; represents the category of students, 0 for beginners, 1 for students who have taken courses, n = 3), represents the multi-dimensional data required for Task 2 (contract fulfillment status: 1 for compliance, 0 for non-compliance; students' payment history: 1 for on-time payment, 0 for non-on-time payment; comparison of students' payment and learning costs: 1 for profit, 0 for loss, n = 3).

[0074] are the parameters corresponding to each task and are optimized for different tasks respectively. The value of this parameter is finally determined by the system after multiple repeated calculations.

[0075] The deep neural network model combines the losses of each task: ; Among them, is the loss function of task such as mean squared error, etc., and is the weight of the task, used to balance the influence of different tasks. Through this multi-task learning method, the model can simultaneously learn the common features between multiple tasks and improve the overall prediction performance.

[0076] The mean squared error is a commonly used regression loss function, which calculates the average of the squares of the differences between the predicted values and the true values of all samples.

[0077] Self-attention mechanism: To further improve the model's ability to focus on important features in the input data, the self-attention mechanism is introduced, enabling the model to dynamically adjust its weights when processing different features and focus on the features that are most valuable for the current task.

[0078] The formula of the self-attention mechanism is as follows: ; Among them, Q: Query matrix, representing the goal of the current task.

[0079] K: Key matrix, representing the representation of the input features, which usually comes from the same input sequence as the query matrix.

[0080] V: Value matrix, representing the weighted output of the input features.

[0081] : is the dimension of the key, used for scaling.

[0082] Softmax function: Let ; According to the calculation formula, it is not difficult to see that Z is a matrix, which must contain k elements, where k is a positive integer. Then the matrix Z can be expressed as, ; ; Among them, is the exponential function of the i-th element in the vector Z.

[0083] The denominator is the sum of all , where j represents the index of the elements in the vector Z, from 1 to k, ensuring that the sum of all elements of the output vector is 1.

[0084] The self-attention mechanism allows the model to weight the input features according to different tasks, thereby enhancing the sensitivity to important features.

[0085] Adaptive data visualization: Automatically adjust the displayed visualization content according to different management requirements. For example, if the manager is concerned about the compliance and payment status of trainees, the system will give priority to displaying the compliance score and payment progress charts; if the manager is concerned about course profitability, the system will display the profit margin, cost-benefit comparison charts of each course.

[0086] The process of adaptive data visualization is as follows: Input data: Obtain the prediction results of multiple tasks from the deep learning model, such as trainee compliance, training progress, course profitability, etc.

[0087] Task weights: Dynamically adjust the visualization weights of different tasks according to the manager's preferences and concerns.

[0088] Visualization display: Use forms such as dynamic charts, heat maps, radar charts, etc. to display the results of different tasks, and automatically adjust the chart layout and content.

[0089] Instructions for using the multi-task deep neural network model Feature collection: Collect multi-dimensional data from the trainee management system, such as learning progress, payment records, course selections, compliance history, etc.

[0090] Model training: Use a deep neural network for multi-task learning to train, optimize the prediction performance of each task, and at the same time enhance the ability to identify the importance of features through the self-attention mechanism.

[0091] Model prediction: After the real-time data of the trainee is input, the model predicts the task results such as trainee compliance and training progress, and generates relevant reports for the manager.

[0092] Data visualization: Dynamically adjust the data display content according to the prediction results to help the manager make decisions.

[0093] Embodiment 2: This embodiment also provides a computer device, applicable to the situation of a driving school data management method for driving training contract management, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement a driving school data management method for driving training contract management as proposed in the above embodiment.

[0094] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by the processor, it implements a driving school data management method for driving training contract management as proposed in the above embodiment.

[0095] The computer device can be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0096] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., which are various media that can store program codes.

[0097] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0098] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which a program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing it in a suitable manner if necessary, and then storing it in a computer memory.

[0099] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0100] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A driving school data management method for driving training contract management, characterized in that: The following steps are involved: S1, data collection and student information entry; Collect students' basic information through online platforms or mobile terminals and enter it into the management system; S2. Formulate training plans based on trainee information; The system formulates a training plan based on the basic information of the trainees; S3. Track and adjust courses according to the training plan; The system tracks the trainees’ training in real time according to the training plan and generates training performance data; S4. Predict the contract validity period based on training performance data; The system uses the training performance data to determine the time it takes for trainees to complete the entire training course and whether they can pass the exam on time to obtain contract validity forecast data; S5. Use contract validity period forecast data to manage payment and refund; The system manages the payment of students' fees in combination with the effective forecast data of the contract and obtains the contract and payment data; S6. Conduct student compliance checks through contract and payment data; The system uses a logistic regression model to check whether the students have completed the corresponding courses as agreed in the contract and whether they have paid all fees to obtain the test results; S7. Renew the contract based on the test results; The system decides whether to recommend contract renewal based on the test results and obtains the contract renewal result; S8. Generate an optimization management decision report based on the renewal results; Based on the results of all previous steps, the system generates an optimization management decision report through data visualization.

2. A driving school data management method for driving training contract management according to claim 1, characterized in that: The student information in step S1 includes: Student background: age, gender, driving experience; Learning objectives: Driving skills that you wish to improve; Physical conditions: vision, reaction speed; Time arrangement: Free time for training.

3. A driving school data management method for driving training contract management according to claim 1, characterized in that: The training plan in step S2 includes: Training content: For beginners, start with basic driving operations; for students with driving experience, start with traffic environment simulation training; Training time: Set the training time based on the schedule and learning objectives in the student information. The training time for beginners should be longer than that for students with driving experience.

4. A driving school data management method for driving training contract management according to claim 1, characterized in that: The course adjustment in step S3 includes: When the management system tracks the trainees' training in real time and identifies that the trainees do not follow the steps required by the test or the instructor during the driving course, the system will remind the instructor to change the training plan and remind the instructor of the steps that need to be strengthened or emphasized and record the number of reminders.

5. The driving school data management method for driving training contract management according to claim 1, characterized in that: The contract validity period prediction in step S4 includes: The management system will change the end date of the contract based on the trainee's training performance data; for trainees with 0 training performance data reminders, the end date of the contract will be shortened, and for trainees with more than 3 training performance data reminders, the end date of the contract will be extended.

6. A driving school data management method for driving training contract management according to claim 1, characterized in that: The fee payment and refund management in step S5 includes: The management system calculates the charging data based on the predicted data of the contract validity period and the charging standards of the driving school; for students who complete the course ahead of schedule, the fees they need to pay will be reduced, and for students who complete the course late, the fees they need to pay will be increased.

7. A driving school data management method for driving training contract management according to claim 1, characterized in that: The logistic regression model in step S6 includes: Defining compliance prediction labels ; The value range of is between 0 and 1. The value of this label represents whether the student is compliant; 1, the trainee is compliant; is 0, the student is not compliant; Constructing Prediction Labels The probability calculation formula is: ； ； in, z represents a parameter; Indicates the student's learning progress, which is assigned according to the number of completed courses, as follows: ； Indicates the student’s payment history, with on-time payment being 1 and late payment being 0; Indicates the contract fulfillment status of the trainee, 1 for compliance and 0 for noncompliance; Indicates the category of the students, 0 for beginners and 1 for students who have already taken the course; Indicates the urgency of student feedback, which is calculated based on the time sensitivity of student feedback. The formula is: ; in: It is the difference between the time when the learner submitted the feedback and the current time, indicating the time since the learner submitted the feedback; is a constant that regulates the decay rate, ; Indicates the trainee's compliance history, indicating whether the trainee has violated regulations before this training. This value is quantified based on the trainee's past compliance behavior records; The calculation method is: ； in, The number of violations is the number of violations the student has committed in the past; is the impact coefficient of default record, the value is 1 for the first default, 2 for the second default, and so on; When the default record is 0, ; n=6； is the eigenvector; It indicates the probability of trainees being compliant; Artificially set a threshold m, whose value range is between 0 and 1. The value of is compared with the value of m. If If it is greater than m, the student is judged to be compliant, otherwise he is not compliant.

8. A driving school data management method for driving training contract management according to claim 7, characterized in that: The parameters The calculation formula is: ； in, Indicates the basic compliance score, which is set manually; It represents the weight of each data. The driving school assigns the value according to the actual situation. The value with greater influence is larger than the value with less influence.

9. A driving school data management method for driving training contract management according to claim 1, characterized in that: The criteria for determining whether to recommend contract renewal in step S7 are: When the student has completed all study courses and the student's When it is greater than the threshold m, the management system will recommend that the student renew the contract and provide new intensive courses.

10. A driving school data management method for driving training contract management according to claim 1, characterized in that: In step S8, generating an optimization management decision report by means of data visualization includes: The management system generates a visual table based on the trainee’s background, learning goals, physical condition, schedule, training plan, training performance data, contract validity data, and renewal results, listing the above content and giving text descriptions, and presents it to decision makers for decision-making.

Images