Intelligent management platform for driving school

Abstract

The invention discloses an intelligent management platform for a driving school. The platform comprises a data acquisition module, a data preprocessing module and a reservation time prediction module. The data acquisition module is used for acquiring coach information, vehicle information and student information, the data preprocessing module is used for extracting first coach data features, first vehicle data features and first student data features, and the reservation time prediction module is used for realizing the steps of the reservation time prediction method. The method comprises the steps of performing reservation time prediction according to a first coach data feature, a first vehicle data feature and a first student data feature to obtain a prediction result, and updating student reservation time according to the prediction result. According to the number of vehicles and the vehicle following conditions of coaches and trainees, the reservation time prediction model is utilized to update and sort the reservation time of the trainees in real time and output the reservation time table, so that resources of driving schools are reasonably allocated and utilized, resource waste of the driving schools is reduced, and more flexible time arrangement is provided for the trainees.

Description

Technical Field

[0001] The present invention relates to the technical field of driving school management, and in particular to an intelligent management platform for driving schools. Background Art

[0002] At present, with the number of cars increasing year by year, the number of students in driving schools is also increasing. With too many students, how to scientifically and reasonably manage multiple students, coaches and training vehicles is an urgent problem that needs to be solved.

[0003] In the prior art, students' appointments are generally made by manual registration or app appointments. Although the app appointment method greatly facilitates students, the appointment time periods on the app are fixed. For example, students with different progress have different requirements for vehicles and whether they need a coach to accompany the car. If a fixed time period on the app is used, it is easy to cause the coach to be idle when the training students do not need a coach to accompany the car, while the appointment time for students who need a coach to accompany the car is relatively late. Furthermore, when the coach is idle, students who need a coach to accompany the car cannot receive training immediately, resulting in unreasonable allocation and utilization of resources, a huge waste of driving school resources, increased difficulty in driving school management, and students cannot make reasonable use of their time. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent management platform for driving schools in response to the above-mentioned problems. The present invention uses an appointment time prediction model to update and sort the students' appointment times in real time according to the number of vehicles and the following conditions of coaches and students, and outputs an appointment schedule, so as to reasonably allocate and utilize driving school resources, reduce the waste of driving school resources, and provide students with more flexible time arrangements.

[0005] In order to achieve the above-mentioned invention object, the technical solution adopted by the present invention is as follows:

[0006] According to one aspect of the present invention, there is provided a driving school intelligent management platform, including a data acquisition module, a data preprocessing module and an appointment time prediction module;

[0007] The data collection module is used to collect information about the coach, vehicle information about the vehicle bound to the coach, and student information about the student bound to the coach;

[0008] The data preprocessing module is used to extract the first coach data feature from the coach information, extract the first vehicle data feature from the vehicle information, and extract the first student data feature from the student information;

[0009] The appointment time prediction module is used to implement an appointment time prediction method step, the method steps comprising:

[0010] According to the first coach data feature, the first vehicle data feature and the first student data feature, an appointment time prediction is performed to obtain a prediction result, and the student appointment time is updated according to the prediction result.

[0011] Wherein, the appointment time prediction includes:

[0012] Inputting the first coach data feature, the first vehicle data feature and the first trainee data feature into the appointment time prediction model to predict the appointment time, and outputting the appointment time;

[0013] The appointment time prediction model is obtained through the following model training steps:

[0014] Construct an appointment time prediction model, obtain the second coach data feature, the second vehicle data feature and the second student data feature, and input the second coach data feature, the second vehicle data feature and the second student data feature into the appointment time model for model training.

[0015] Preferably, the coach information includes the coach name, coach vehicle information and coach work and rest time information, and the coach vehicle information is the first coach data feature or the second coach data feature.

[0016] Preferably, the vehicle information includes a vehicle number, vehicle operation information and a vehicle health status, and the vehicle operation information is the first vehicle data feature or the second vehicle data feature.

[0017] Preferably, the student information includes the student name, appointment time information, student vehicle-following information and student progress information, and the appointment time information, student vehicle-following information and student progress information are the first student data features or the second student data features.

[0018] Preferably, the coach's vehicle-following information and the student's vehicle-following information are acquired by a monitoring device, and the monitoring device comprises a camera, and the camera is fixed in the vehicle for monitoring the coach and the student.

[0019] Preferably, the step of inputting the second coach data feature, the second vehicle data feature and the second trainee data feature into the appointment time prediction model for model training specifically includes:

[0020] Collecting the running time of the second vehicle data feature of all vehicles to obtain running time data, and performing maximum value downsampling processing and arrangement processing on the running time data in sequence to obtain a plurality of first data;

[0021] Inputting the first data into the appointment time prediction model for a first training process;

[0022] The step of inputting the first data into the appointment time prediction model for the first training process comprises: after the first data is input into the appointment time prediction model for processing, the second trainer data feature is input into the appointment time prediction model for processing to obtain the first feature result, and it is judged whether the first feature result is that the trainer follows the car, if the trainer follows the car, the appointment times of all trainees who need the trainer to follow the car are arranged in sequence, and the first appointment schedule is output; if the trainer does not follow the car, the second trainee data feature is input into the appointment time prediction model for processing to obtain the second feature result, and it is judged whether the second feature result is that the trainee follows the car, if the trainee follows the car, the appointment times of all trainees who do not need the trainer to follow the car are arranged in sequence, and the second appointment schedule is output;

[0023] The first training process step is repeatedly performed until all the first data have been trained and processed.

[0024] Preferably, the first appointment schedule includes the names of all students who need a coach to follow them and the first appointment time period.

[0025] Preferably, the second appointment schedule includes the names of all students who do not need a coach to accompany them and the second appointment time period.

[0026] Preferably, the method further includes an empty vehicle detection step, wherein the empty vehicle detection step includes:

[0027] Obtain vehicle operation information and determine whether the vehicle is in operation. If the vehicle is in operation, immediately execute the first training processing step and continue to detect the next vehicle. If the vehicle is not in operation, assign the vehicle to the student with the most advanced time and detect the next vehicle. Repeat the above steps until all vehicle inspections are completed.

[0028] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0029] The present invention uses an appointment time prediction model to update and sort students' appointment times in real time according to the number of vehicles and the following conditions of coaches and students, and outputs an appointment schedule, so as to reasonably allocate and utilize driving school resources, reduce the waste of driving school resources, and provide students with more flexible time arrangements. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a structural block diagram of the present invention. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and preferred embodiments. However, it should be noted that many details listed in the specification are only for the purpose of enabling the reader to have a thorough understanding of one or more aspects of the invention, and these aspects of the present invention can be realized even without these specific details.

[0032] See also Figure 1 The present invention provides a driving school intelligent management platform, and the technical solution is as follows:

[0033] A driving school intelligent management platform includes a data acquisition module, a data preprocessing module and an appointment time prediction module. The data acquisition module is used to collect coach information, vehicle information of vehicles bound to coaches and student information of students bound to coaches. Coach information includes coach name, coach vehicle information and coach work and rest time information. Vehicle information includes vehicle number, vehicle operation information and vehicle health status. Student information includes student name, appointment time information, student vehicle information and student progress information. The coach name, vehicle number and student name are all obtained from the registration information entered into the platform. For example, in the platform, the coach name is A, then coach A is bound to vehicles 1, 2 and 3, and students 1, 2 and 3. The coach vehicle information and student vehicle information are obtained by a monitoring device, and the monitoring device includes a camera, which is fixed in each vehicle, and the camera can be used to detect coaches and students. For example, if there are coach A and student 1 in vehicle 1, the camera in vehicle 1 detects coach A and student 1, and transmits the detected signal data to the platform for calling. The coach work and rest time information is directly obtained from the information entered into the platform. The appointment time information and student progress information in the student information are obtained from the information entered into the platform. The appointment time information can be selected by the student on the student side of the platform. The student progress information is entered by the coach on the coach side. The vehicle operation information and vehicle health status are monitored by the vehicle system, which is connected to the platform data. The vehicle system detects the vehicle status information and transmits the vehicle status information to the platform.

[0034] The data preprocessing module is used to extract the first coach data feature from the coach information, and the first coach data feature is the coach following vehicle information. The first vehicle data feature is extracted from the vehicle information, and the first vehicle data feature is the vehicle operation information. The first student data feature is extracted from the student information, and the first student data feature is the appointment time information, the student following vehicle information, and the student progress information.

[0035] The appointment time prediction module is used to implement an appointment time prediction method step, which includes the following steps:

[0036] First, an appointment time prediction model is constructed, and the second coach data feature, the second vehicle data feature, and the second student data feature are obtained. The second coach data feature, the second vehicle data feature, and the second student data feature are input into the appointment time model for model training. The appointment time prediction model includes an input layer, a hidden layer, and an output layer. The second coach data feature is the coach following vehicle information. The second vehicle data feature is the vehicle operation information. The second student data feature is the appointment time information, the student following vehicle information, and the student progress information.

[0037] Specifically, the coach following vehicle information, vehicle operation information, student appointment time information, student following vehicle information and student progress information are input into the appointment time prediction model for model training, which is specifically as follows:

[0038] Collect the running time of all vehicles bound to the coach, and the running time>0. Obtain the running time data of all vehicles, and perform maximum downsampling and sorting processing on the running time data of all vehicles in turn to obtain multiple first data. For example, coach A is bound to vehicle 1, vehicle 2, and vehicle 3, the running time of vehicle 1 is 30 minutes, the running time of vehicle 2 is 60 minutes, and the running time of vehicle 3 is 15 minutes. After maximum sampling processing and sorting, the order of the vehicles is: vehicle 2, vehicle 1, vehicle 3. Corresponding to the first data of vehicle 2, the first data of vehicle 1, and the first data of vehicle 3.

[0039] According to the above arrangement, the first data is input into the reservation time prediction model for the first training process. According to the above arrangement, the first data of vehicle 2 is first input into the reservation time prediction model for processing.

[0040] The first data is input into the appointment time prediction model for a first training process, which is specifically:

[0041] After the first data is input into the appointment time prediction model for processing, the second coach data feature is input into the appointment time prediction model for processing to obtain the first feature result, and it is determined whether the first feature result is a coach following the car. If the coach follows the car, the appointment times of all students who need the coach to follow the car are arranged in sequence, and the first appointment schedule is output; if the coach does not follow the car, the second student data feature is input into the appointment time prediction model for processing to obtain the second feature result, and it is determined whether the second feature result is a student following the car. If the student follows the car, the appointment times of all students who do not need the coach to follow the car are arranged in sequence, and the second appointment schedule is output, wherein the first appointment schedule includes the names of all students who need the coach to follow the car and the first appointment time period. The second appointment schedule includes the names of all students who do not need the coach to follow the car and the second appointment time period.

[0042] For example, the first data of vehicle 2 is input into the appointment time prediction model, and then the coach follow-up information of coach A is input into the appointment time prediction model to obtain the first feature result, and judge whether coach A follows the car. If coach A follows the car, the student progress information and the student appointment time information of all students are detected. The student progress information contains information on whether the student needs a coach to follow the car, and the appointment time of all students who need a coach to follow the car is extracted. The appointment time of all students who need a coach to follow the car is arranged in sequence, and the first appointment schedule is output. For example, the appointment time of student 1 is 8:30-9:30, the appointment time of student 2 is 9:30-10:30, and the appointment time of student 3 is 10:30-11:30. Both students 1 and 3 need a coach to follow the car, but student 2 does not need a coach to follow the car. Then, students 1 and 3 are sorted, and the first appointment schedule output is: the appointment time of student 1 is 8:30-9:30, and the appointment time of student 3 is 9:30-10:30. If the instructor does not follow the car, the second student data feature is input into the appointment time prediction model for processing to obtain the second feature result, and judge whether the student follows the car. If the student follows the car, the appointment times of all students who do not need the instructor to follow the car are arranged in sequence, and the second appointment schedule is output. For example, here includes student 4, student 4 does not need the instructor to follow the car, and the appointment time of student 4 is 11:30-12:30, then the second appointment schedule is: the appointment time of student 2 is 9:30-10:30, and the appointment time of student 4 is 10:30-11:30.

[0043] Then, the first training process step is repeatedly performed until all the first data have been trained and processed, thereby completing the training of the appointment time prediction model.

[0044] Finally, the first coach data feature, the first vehicle data feature and the first student data feature are input into the appointment time prediction model to predict the appointment time, and the predicted appointment schedule is output. The student appointment time is updated according to the predicted appointment schedule.

[0045] Furthermore, in order to improve the appointment schedule and make the appointment time more accurate, in this embodiment, an empty vehicle detection step is also included, and the empty vehicle detection step includes:

[0046] Obtain vehicle operation information and determine whether the vehicle is in operation. If the vehicle is in operation, immediately execute the first training processing step and continue to detect the next vehicle. If the vehicle is not in operation, assign the vehicle to the student with the most advanced time and detect the next vehicle. Repeat the above steps until all vehicle inspections are completed.

[0047] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A driving school intelligent management platform, characterized in that: It includes data collection module, data preprocessing module and appointment time prediction module; The data collection module is used to collect information about the coach, vehicle information about the vehicle bound to the coach, and student information about the student bound to the coach; The data preprocessing module is used to extract the first coach data feature from the coach information, extract the first vehicle data feature from the vehicle information, and extract the first student data feature from the student information; The appointment time prediction module is used to implement an appointment time prediction method step, the method steps comprising: According to the first coach data feature, the first vehicle data feature and the first student data feature, an appointment time prediction is performed to obtain a prediction result, and the student appointment time is updated according to the prediction result. Wherein, the appointment time prediction includes: Inputting the first coach data feature, the first vehicle data feature and the first trainee data feature into the appointment time prediction model to predict the appointment time, and outputting the appointment time; The appointment time prediction model is obtained through the following model training steps: Construct an appointment time prediction model, obtain the second coach data feature, the second vehicle data feature and the second student data feature, and input the second coach data feature, the second vehicle data feature and the second student data feature into the appointment time model for model training.

2. The driving school intelligent management platform according to claim 1, characterized in that: The coach information includes the coach name, coach following vehicle information and coach work and rest time information, and the coach following vehicle information is the first coach data feature or the second coach data feature.

3. The driving school intelligent management platform according to claim 1, characterized in that: The vehicle information includes a vehicle number, vehicle operation information and a vehicle health status, and the vehicle operation information is the first vehicle data feature or the second vehicle data feature.

4. The driving school intelligent management platform according to claim 1, characterized in that: The student information includes the student's name, appointment time information, student vehicle-following information and student progress information, and the appointment time information, student vehicle-following information and student progress information are the first student data features or the second student data features.

5. The driving school intelligent management platform according to claim 2, characterized in that: The coach's vehicle-following information and the student's vehicle-following information are acquired by a monitoring device, and the monitoring device includes a camera, which is fixed in the vehicle and is used to monitor the coach and the student.

6. The driving school intelligent management platform according to claim 1, characterized in that: The step of inputting the second coach data feature, the second vehicle data feature and the second trainee data feature into the appointment time prediction model for model training specifically includes: Collecting the running time of the second vehicle data feature of all vehicles to obtain running time data, and performing maximum value downsampling processing and arrangement processing on the running time data in sequence to obtain a plurality of first data; Inputting the first data into the appointment time prediction model for a first training process; The step of inputting the first data into the appointment time prediction model for the first training process comprises: after the first data is input into the appointment time prediction model for processing, the second trainer data feature is input into the appointment time prediction model for processing to obtain the first feature result, and it is judged whether the first feature result is that the trainer follows the car, if the trainer follows the car, the appointment times of all trainees who need the trainer to follow the car are arranged in sequence, and the first appointment schedule is output; if the trainer does not follow the car, the second trainee data feature is input into the appointment time prediction model for processing to obtain the second feature result, and it is judged whether the second feature result is that the trainee follows the car, if the trainee follows the car, the appointment times of all trainees who do not need the trainer to follow the car are arranged in sequence, and the second appointment schedule is output; The first training process step is repeatedly performed until all the first data have been trained and processed.

7. The driving school intelligent management platform according to claim 6, characterized in that: The first appointment schedule includes the names of all students who need a coach to follow them and the first appointment time period.

8. The driving school intelligent management platform according to claim 6, characterized in that: The second reservation schedule includes the names of all students who do not need a coach to accompany them and the second reservation time period.

9. The driving school intelligent management platform according to claim 6, characterized in that: The method further includes an empty vehicle detection step, wherein the empty vehicle detection step includes: Obtain vehicle operation information and determine whether the vehicle is in operation. If the vehicle is in operation, immediately execute the first training processing step and continue to detect the next vehicle. If the vehicle is not in operation, assign the vehicle to the student with the most advanced time and detect the next vehicle. Repeat the above steps until all vehicle inspections are completed.

Images