Attention distribution training equipment

Abstract

The invention discloses attention distribution training equipment, and relates to the technical field of attention training, and the equipment comprises an adjusting module which is responsible for adjusting a camera body according to different students; the training demand input module is responsible for setting different training plans according to different trainees; the route generation and display module is responsible for generating different training routes according to different input requirements and displaying the different training routes on a display screen; the eye tracking module is responsible for tracking and recording the eye movement track of the student in real time; when different students carry out attention training, the threaded rod and the first rotating shaft are driven to rotate through the adjusting module, the height and angle of the camera body can be adjusted, the camera body can be reasonably adjusted to detect the positions of the eyes of the students, it is ensured that the eye changes of the students can be accurately captured, and the training efficiency is improved. Accuracy of acquiring trainee training data by the camera body is ensured, and training effect is improved for trainees.

Description

Technical Field

[0001] The present invention relates to the technical field of attention training, and in particular to an attention allocation training device. Background Art

[0002] When performing various flight missions, pilots need to monitor a large amount of information at the same time, which requires them to have efficient visual attention allocation capabilities. The pilot's attention allocation ability directly affects flight safety. Through effective attention allocation training, the risk of misjudgment and operational errors caused by distracted attention during flight can be reduced.

[0003] After searching, the Chinese patent number CN220340816U discloses an auxiliary training device for recording the attention distribution of flight trainees, including a bottom plate, a base fixedly connected to one side of the top of the bottom plate, a slide groove provided on the base, and a seat provided on the slide groove for supporting the flight trainees; a visual component, which is arranged on the other side of the top of the bottom plate through a multifunctional bracket, and is used to provide visual and sound feedback to the flight trainees; a simulation component, which is arranged on the multifunctional bracket and located between the seat and the visual component, and is used to simulate the flight function for the flight trainees; a detection component, which is arranged corresponding to the simulation component and is worn on the eyes of the flight trainees, and is used to monitor the eye movement trajectory of the flight trainees. This patent is small in size and light in weight, so that pilots can perform eye movements more naturally during the mission, thereby improving the precision and accuracy of the recorded data, and improving the training quality and flight safety of pilots. The Chinese patent number CN220340816U solves the problems of existing simulator equipment, which are high cost and poor scalability. Eye tracker technology mostly uses head-mounted or desktop devices, which are large in size, heavy in weight, not natural and convenient enough, and it is difficult to ensure the natural eye movement state of pilots when performing tasks.

[0004] However, in the actual use of the above-mentioned device, the attention load capacity of different flight trainees varies greatly. It is difficult for the training equipment to carry out personalized training, and it is difficult to adjust and optimize according to the specific needs and skill levels of each trainee, which may lead to unsatisfactory training results. Therefore, it is necessary to propose an attention allocation training device. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art that the attention load capacity of different flight trainees varies greatly, the training equipment is difficult to carry out personalized training, and it is difficult to adjust and optimize according to the specific needs and skill level of each trainee, which may lead to unsatisfactory training results. An attention allocation training device is proposed to solve the problems in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An attention allocation training device, comprising:

[0008] Adjustment module: responsible for adjusting the camera body according to different students;

[0009] Training demand input module: responsible for setting different training plans according to different trainees;

[0010] Route generation and display module: responsible for generating different training routes according to different input requirements and displaying them on the display screen;

[0011] Eye tracking module: responsible for real-time tracking and recording of students’ eye movement trajectories;

[0012] Attention analysis module: responsible for analyzing students’ eye movement trajectories and determining whether students follow the correct attention allocation;

[0013] Feedback and Guidance Module: Responsible for providing timely feedback and guidance to students based on the results of the attention analysis module;

[0014] The adjustment module is arranged on the outside of the training base plate, the outside of the training base plate is fixedly connected to a support frame, the outside of the support frame is fixedly connected to a display screen, the outside of the support frame is fixedly connected to an eye detection platform, the outside of the eye detection platform is rotatably connected to a threaded rod, the outside of the threaded rod is threadedly connected to a slider, the inside of the slider is rotatably connected to a rotating screw, the outside of the rotating screw is symmetrically slidably connected to a fixed plate, the outside of the fixed plate is fixedly connected to a first rotating shaft, the outside of the rotating screw is meshedly connected to a gear, the outside of the gear is fixedly connected to a third rotating shaft, the outside of the third rotating shaft is fixedly installed with a camera body, the adjustment module facilitates personalized adjustment of the camera body according to different students to ensure accurate capture of eye changes of different students.

[0015] The above technical solution further includes:

[0016] The training demand input module is convenient for setting up personalized training plans according to trainees' needs, and its specific steps are as follows:

[0017] Initialization settings: When the trainee starts using the training device, the training demand adjustment input module will first display the initial training settings and parameters;

[0018] Training parameter input: according to the actual needs of different students, new training requirement parameters are input through the controller;

[0019] Parameter verification: The device will verify the input training parameters to ensure their legitimacy and validity;

[0020] Parameter adjustment: Ensure that the input training parameters are legal and valid. The device will adjust its internal settings and configurations based on the parameters.

[0021] The eye tracking module is used to track and analyze the trainee's line of sight, and the specific steps are as follows:

[0022] Image capture and preprocessing: Capture the student's eye image through the camera and convert the color image into a grayscale image;

[0023] Pupil area detection: Apply thresholding method to convert grayscale image into binary image and highlight the pupil area;

[0024] Pupil center positioning: In a binary image, the pupil appears as a dark connected area. The pupil center can be determined by calculating the centroid of the connected area. The centroid calculation formula is:

[0025] (C_x=\frac{\sum_{i=1}{n}x_i*I(x_i,y_i)}{\sum_{i=1}{n}I(x_i,y_i)})

[0026] (C_y=\frac{\sum_{i=1}{n}y_i*I(x_i,y_i)}{\sum_{i=1}{n}I(x_i,y_i)})where ((x_i,y_i)) is the coordinate of each pixel in the pupil area;

[0027] (I(x_i,y_i)) is the grayscale value of the pixel.

[0028] The attention analysis module uses a convolutional neural network algorithm for analysis, and the specific steps are as follows:

[0029] Input data representation: Assume that the input data is a multidimensional array, denoted as X, where the dimensions of X are batch size, number of channels, height, and width, which represent the number of input samples, number of channels, image height, and image width, respectively;

[0030] Convolution operation: Perform sliding window convolution operation on the input data through the convolution kernel to extract the features in the input data. Assuming that the dimensions of the convolution kernel are the number of channels, the height of the convolution kernel, and the width of the convolution kernel, recorded as W, the convolution operation can be expressed by the following formula:

[0031] Z[i,j]=sum(sum(sum(X[:,:,i:i+h,j:j+w]*W)))+b

[0032] Among them, Z(i,j) is the value of the output feature map Z at (i,j), i and j represent the position of the feature map, h and w represent the height and width of the convolution kernel respectively, and b is the bias term;

[0033] Activation function: After the convolution operation, ReLU is applied to perform nonlinear transformation on the feature map to increase the network's expressive power. The formula of the ReLU function is: [f(x)=\max(0,x)]

[0034] Among them, x is the output value after the convolution operation;

[0035] Pooling operation: By selecting the average value in the local perception area as the pooling result, the spatial dimension of the feature map is reduced and important feature information is retained;

[0036] Fully connected operation: After multiple convolution and pooling operations, the feature map is expanded into a one-dimensional vector and passed through a fully connected layer for classification or regression tasks. Each neuron in the fully connected layer is connected to all neurons in the previous layer, and the mapping relationship between input and output is established by learning weights and biases.

[0037] Loss function: In the convolutional neural network model, the cross entropy loss function is used to measure the gap between the model's prediction results and the true label;

[0038] Back propagation algorithm: Use the back propagation algorithm to calculate the gradient of the loss function with respect to the model parameters, and use gradient descent to update the model parameters to continuously optimize the performance of the model.

[0039] The first rotating shaft is rotationally connected to the eye detection platform, the third rotating shaft is rotationally connected to the slider, the outside of the eye detection platform is fixedly connected with a fixing rod, and the fixing rod is slidingly connected to the slider.

[0040] A first motor is fixedly installed on the outside of the eye detection platform, and the output end of the first motor is fixedly connected to the threaded rod. A second motor is fixedly installed on the outside of the eye detection platform, and the output end of the second motor is fixedly connected to the first rotating shaft.

[0041] The outside of the support frame is rotatably connected to a second rotating shaft, the outside of the second rotating shaft is fixedly connected to a second telescopic rod, and a side of the second telescopic rod away from the second rotating shaft is fixedly connected to a rudder.

[0042] A cylinder is fixedly installed on the outside of the training base plate, and a seat body is provided at the output end of the cylinder. A first telescopic rod is fixedly connected to the outside of the seat body, and a side of the first telescopic rod away from the seat body is fixedly connected to the training base plate.

[0043] The present invention has the following beneficial effects:

[0044] 1. In the present invention, when different students are conducting attention training, the height and angle of the camera body can be adjusted by driving the threaded rod and the first rotating shaft to rotate through the adjustment module, so as to reasonably adjust the position of the camera body to detect the eyes of the students, ensure that the changes of the students' eyes can be accurately captured, ensure the accuracy of the camera body in acquiring the students' training data, and improve the training effect for the students.

[0045] 2. In the present invention, by inputting different training data into the route generation and display module, personalized training plans can be provided for different students. The eye tracking module can then track the students' glasses in real time. The attention analysis module can analyze the students' eye movement trajectories. The feedback and guidance module is convenient for providing training suggestions to students based on the analysis results, thereby improving the students' attention training effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of the structure of an attention allocation training device proposed by the present invention;

[0047] Figure 2 It is a schematic diagram of the first structure in the present invention;

[0048] Figure 3 It is a second structural schematic diagram of the present invention;

[0049] Figure 4 for Figure 1 A schematic diagram of the structure enlargement in the middle;

[0050] Figure 5 for Figure 3 A magnified schematic diagram of the structure at B in the middle;

[0051] Figure 6 It is a system block diagram of the present invention.

[0052] In the figure: 1. training base plate; 2. cylinder; 3. first telescopic rod; 4. seat body; 5. support frame; 6. display screen; 7. eye detection platform; 8. first motor; 9. second motor; 10. fixed rod; 11. threaded rod; 12. first rotating axis; 13. camera body; 14. slider; 15. second rotating axis; 16. second telescopic rod; 17. rudder; 18. fixed plate; 19. rotating screw; 20. gear; 21. third rotating axis. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] like Figure 1-Figure 6 As shown, an attention allocation training device comprises:

[0055] Adjustment module: responsible for adjusting the camera body 13 according to different students;

[0056] Training demand input module: responsible for setting different training plans according to different trainees;

[0057] Route generation and display module: responsible for generating different training routes according to different input requirements and displaying them on the display screen 6;

[0058] Eye tracking module: responsible for real-time tracking and recording of students’ eye movement trajectories;

[0059] Attention analysis module: responsible for analyzing students’ eye movement trajectories and determining whether students follow the correct attention allocation;

[0060] Feedback and Guidance Module: Responsible for providing timely feedback and guidance to students based on the results of the attention analysis module;

[0061] The adjustment module is arranged on the outside of the training base plate 1, the outside of the training base plate 1 is fixedly connected to a support frame 5, the outside of the support frame 5 is fixedly connected to a display screen 6, the outside of the support frame 5 is fixedly connected to an eye detection platform 7, the outside of the eye detection platform 7 is rotatably connected to a threaded rod 11, the outside of the threaded rod 11 is threadedly connected to a slider 14, the inside of the slider 14 is rotatably connected to a rotating screw 19, the outside of the rotating screw 19 is symmetrically slidably connected to a fixed plate 18, the outside of the fixed plate 18 is fixedly connected to a first rotating shaft 12, the outside of the rotating screw 19 is meshingly connected to a gear 20, the outside of the gear 20 is fixedly connected to a third rotating shaft 21, the outside of the third rotating shaft 21 is fixedly installed with a camera body 13, the adjustment module facilitates personalized adjustment of the camera body 13 according to different students to ensure accurate capture of eye changes of different students.

[0062] The working principle of the attention allocation training device proposed by the present invention is that the training demand input module is convenient for inputting different training parameters according to the actual needs of different students, the route generation and display module is convenient for generating different training plans based on the input training parameters, such as different training routes, different difficulty levels and different training durations, and the generated plans are displayed to the students through the display screen 6, the changing routes of the students' eyes are tracked and collected through the camera body 13, and the attention analysis module can analyze the attention analysis process of the students, and finally the feedback and guidance module can provide training suggestions for the students;

[0063] When the camera body 13 needs to be adjusted, the threaded rod 11 is rotated. The rotation of the threaded rod 11 will drive the slider 14 connected by the external thread to move on the threaded rod 11. When the threaded rod 11 moves, it will drive the third rotating shaft 21 connected to the external rotation to move. The movement of the third rotating shaft 21 will drive the camera body 13 fixed to the external rotation, that is, the height of the camera body 13 can be adjusted. When the first rotating shaft 12 is rotated, the first rotating shaft 12 will drive the fixed plate 18 symmetrically fixed to the external rotation to rotate. The rotation of the fixed plate 18 will drive the rotating screw 19 connected to the external sliding to rotate. When the rotating screw 19 rotates, the gear 20 meshing with the external rotation will rotate. When the gear 20 rotates, it will drive the third rotating shaft 21 fixed to the external rotation, that is, the inclination angle of the camera body 13 installed outside the third rotating shaft 21 can be changed, so as to ensure that the changes of the students' eyes can be accurately captured.

[0064] In one embodiment, for the above training demand input module, the training demand input module is convenient for setting a personalized training plan according to the needs of the trainees, and the specific steps are:

[0065] Initialization settings: When the trainee starts using the training device, the training demand adjustment input module will first display the initial training settings and parameters;

[0066] Training parameter input: according to the actual needs of different students, new training requirement parameters are input through the controller;

[0067] Parameter verification: The device will verify the input training parameters to ensure their legitimacy and validity;

[0068] Parameter adjustment: Ensure that the input training parameters are legal and valid. The device will adjust its internal settings and configurations based on the parameters.

[0069] In one embodiment, for the above-mentioned eye tracking module, the eye tracking module is used to track and analyze the trainee's line of sight, and the specific steps are:

[0070] Image capture and preprocessing: Capture the student's eye image through the camera and convert the color image into a grayscale image;

[0071] Pupil area detection: Apply thresholding method to convert grayscale image into binary image and highlight the pupil area;

[0072] Pupil center positioning: In a binary image, the pupil appears as a dark connected area. The pupil center can be determined by calculating the centroid of the connected area. The centroid calculation formula is:

[0073] (C_x=\frac{\sum_{i=1}{n}x_i*I(x_i,y_i)}{\sum_{i=1}{n}I(x_i,y_i)})

[0074] (C_y=\frac{\sum_{i=1}{n}y_i*I(x_i,y_i)}{\sum_{i=1}{n}I(x_i,y_i)})where ((x_i,y_i)) is the coordinate of each pixel in the pupil area;

[0075] (I(x_i,y_i)) is the grayscale value of the pixel.

[0076] In one embodiment, for the above-mentioned attention analysis module, the attention analysis module applies a convolutional neural network algorithm for analysis, and the specific steps are:

[0077] Input data representation: Assume that the input data is a multidimensional array, denoted as X, where the dimensions of X are batch size, number of channels, height, and width, which represent the number of input samples, number of channels, image height, and image width, respectively;

[0078] Convolution operation: Perform sliding window convolution operation on the input data through the convolution kernel to extract the features in the input data. Assuming that the dimensions of the convolution kernel are the number of channels, the height of the convolution kernel, and the width of the convolution kernel, recorded as W, the convolution operation can be expressed by the following formula:

[0079] Z[i,j]=sum(sum(sum(X[:,:,i:i+h,j:j+w]*W)))+b

[0080] Among them, Z(i,j) is the value of the output feature map Z at (i,j), i and j represent the position of the feature map, h and w represent the height and width of the convolution kernel respectively, and b is the bias term;

[0081] Activation function: After the convolution operation, ReLU is applied to perform nonlinear transformation on the feature map to increase the network's expressive power. The formula of the ReLU function is: [f(x)=\max(0,x)]

[0082] Among them, x is the output value after the convolution operation;

[0083] Pooling operation: By selecting the average value in the local perception area as the pooling result, the spatial dimension of the feature map is reduced and important feature information is retained;

[0084] Fully connected operation: After multiple convolution and pooling operations, the feature map is expanded into a one-dimensional vector and passed through a fully connected layer for classification or regression tasks. Each neuron in the fully connected layer is connected to all neurons in the previous layer, and the mapping relationship between input and output is established by learning weights and biases.

[0085] Loss function: In the convolutional neural network model, the cross entropy loss function is used to measure the gap between the model's prediction results and the true label;

[0086] Back propagation algorithm: Use the back propagation algorithm to calculate the gradient of the loss function with respect to the model parameters, and use gradient descent to update the model parameters to continuously optimize the performance of the model.

[0087] In one embodiment, for the above-mentioned first rotating shaft 12, the first rotating shaft 12 and the eye detection platform 7 are rotationally connected, the third rotating shaft 21 and the slider 14 are rotationally connected, the outside of the eye detection platform 7 is fixedly connected with a fixed rod 10, and the fixed rod 10 and the slider 14 are slidably connected by a cylinder 2.

[0088] In one embodiment, for the above-mentioned eye detection platform 7, a first motor 8 is fixedly installed on the outside of the eye detection platform 7, and the output end of the first motor 8 is fixedly connected to the threaded rod 11, and a second motor 9 is fixedly installed on the outside of the eye detection platform 7, and the output end of the second motor 9 is fixedly connected to the first rotating shaft 12.

[0089] In one embodiment, for the above-mentioned support frame 5, the outside of the support frame 5 is rotatably connected to the second rotating shaft 15, the outside of the second rotating shaft 15 is fixedly connected to the second telescopic rod 16, and the side of the second telescopic rod 16 away from the second rotating shaft 15 is fixedly connected to the rudder 17.

[0090] In one embodiment, for the above-mentioned training base plate 1, a cylinder 2 is fixedly installed on the outside of the training base plate 1, a seat body 4 is provided at the output end of the cylinder 2, a first telescopic rod 3 is fixedly connected to the outside of the seat body 4, and the side of the first telescopic rod 3 away from the seat body 4 is fixedly connected to the training base plate 1.

[0091] The working principle of the attention allocation training device proposed by the present invention is that the first motor 8 is convenient for driving the threaded rod 11 set at the output end to rotate, the second motor 9 is convenient for driving the first rotating shaft 12 set at the output end to rotate, the fixed rod 10 and the slider 14 are slidably connected, so that the slider 14 can remain stable when moving up and down, the display screen 6 is convenient for showing the correct training route to the trainees, the rudder 17 is convenient for simulating the flight state, the second telescopic rod 16 is convenient for changing the distance between the rudder 17 and the seat body 4, and the cylinder 2 is started. The cylinder 2 will drive the seat body 4 set at the output end to rise and fall, and the multiple first telescopic rods 3 fixedly connected to the outside of the seat body 4 are fixedly connected to the training base plate 1, so that the seat body 4 can remain stable when rising and falling, which is convenient for different trainees to maintain the best training state and improve the attention training effect of the trainees.

[0092] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An attention allocation training device, characterized in that: include: Adjustment module: responsible for adjusting the camera body (13) according to different students; Training demand input module: responsible for setting different training plans according to different trainees; Route generation and display module: responsible for generating different training routes according to different input requirements and displaying them on the display screen (6); Eye tracking module: responsible for real-time tracking and recording of students’ eye movement trajectories; Attention analysis module: responsible for analyzing students’ eye movement trajectories and determining whether students follow the correct attention allocation; Feedback and Guidance Module: Responsible for providing timely feedback and guidance to students based on the results of the attention analysis module; The adjustment module is arranged on the outside of the training base plate (1); the outside of the training base plate (1) is fixedly connected to a support frame (5); the outside of the support frame (5) is fixedly connected to a display screen (6); the outside of the support frame (5) is fixedly connected to an eye detection platform (7); the outside of the eye detection platform (7) is rotatably connected to a threaded rod (11); the outside of the threaded rod (11) is threadably connected to a slider (14); the inside of the slider (14) is rotatably connected to a rotating screw rod (19); the rotating screw rod (19) is rotatably connected to the outside of the eye detection platform (7); 9) is symmetrically slidably connected to a fixed plate (18) on the outside, the fixed plate (18) is fixedly connected to a first rotating shaft (12) on the outside, the rotating screw (19) is meshingly connected to a gear (20) on the outside, the gear (20) is fixedly connected to a third rotating shaft (21) on the outside, and a camera body (13) is fixedly installed on the outside of the third rotating shaft (21), and the adjustment module facilitates personalized adjustment of the camera body (13) according to different students, ensuring accurate capture of eye changes of different students.

2. The attention distribution training device according to claim 1, characterized in that: The training demand input module is convenient for setting up personalized training plans according to trainees' needs, and its specific steps are as follows: Initialization settings: When the trainee starts using the training device, the training demand adjustment input module will first display the initial training settings and parameters; Training parameter input: according to the actual needs of different students, new training requirement parameters are input through the controller; Parameter verification: The device will verify the input training parameters to ensure their legitimacy and validity; Parameter adjustment: Ensure that the input training parameters are legal and valid. The device will adjust its internal settings and configurations based on the parameters.

3. The attention distribution training device according to claim 1, characterized in that: The eye tracking module is used to track and analyze the trainee's line of sight, and the specific steps are as follows: Image capture and preprocessing: Capture the student's eye image through the camera and convert the color image into a grayscale image; Pupil area detection: Apply thresholding method to convert grayscale image into binary image and highlight the pupil area; Pupil center positioning: In a binary image, the pupil appears as a dark connected area. The pupil center can be determined by calculating the centroid of the connected area. The centroid calculation formula is: (C_x=\frac{\sum_{i=1}{n}x_i*I(x_i,y_i)}{\sum_{i=1}{n}I(x_i,y_i)})(C_y=\frac{\su m_{i=1}{n}y_i*I(x_i,y_i)}{\sum_{i=1}{n}I(x_i,y_i)}) where ((x_i,y_i)) is the coordinate of each pixel in the pupil area; (I(x_i,y_i)) is the grayscale value of the pixel.

4. The attention distribution training device according to claim 1, characterized in that: The attention analysis module uses a convolutional neural network algorithm for analysis, and the specific steps are as follows: Input data representation: Assume that the input data is a multidimensional array, denoted as X, where the dimensions of X are batch size, number of channels, height, and width, which represent the number of input samples, number of channels, image height, and image width, respectively; Convolution operation: Perform sliding window convolution operation on the input data through the convolution kernel to extract the features in the input data. Assuming that the dimensions of the convolution kernel are the number of channels, the height of the convolution kernel, and the width of the convolution kernel, recorded as W, the convolution operation can be expressed by the following formula: Z[i,j]=sum(sum(sum(X[:,:,i:i+h,j:j+w]*W)))+b Among them, Z(i,j) is the value of the output feature map Z at (i,j), i and j represent the position of the feature map, h and w represent the height and width of the convolution kernel respectively, and b is the bias term; Activation function: After the convolution operation, ReLU is applied to perform nonlinear transformation on the feature map to increase the network's expressive power. The formula of the ReLU function is: [f(x)=\max(0,x)] Among them, x is the output value after the convolution operation; Pooling operation: By selecting the average value in the local perception area as the pooling result, the spatial dimension of the feature map is reduced and important feature information is retained; Fully connected operation: After multiple convolution and pooling operations, the feature map is expanded into a one-dimensional vector and passed through a fully connected layer for classification or regression tasks. Each neuron in the fully connected layer is connected to all neurons in the previous layer, and the mapping relationship between input and output is established by learning weights and biases. Loss function: In the convolutional neural network model, the cross entropy loss function is used to measure the gap between the model's prediction results and the true label; Back propagation algorithm: Use the back propagation algorithm to calculate the gradient of the loss function with respect to the model parameters, and use gradient descent to update the model parameters to continuously optimize the performance of the model.

5. The attention distribution training device according to claim 1, characterized in that: The first rotating shaft (12) is rotationally connected to the eye detection platform (7), the third rotating shaft (21) is rotationally connected to the slider (14), the outside of the eye detection platform (7) is fixedly connected to a fixed rod (10), and the fixed rod (10) is slidably connected to the slider (14).

6. The attention distribution training device according to claim 1, characterized in that: A first motor (8) is fixedly mounted on the outside of the eye detection platform (7), and an output end of the first motor (8) is fixedly connected to a threaded rod (11). A second motor (9) is fixedly mounted on the outside of the eye detection platform (7), and an output end of the second motor (9) is fixedly connected to a first rotating shaft (12).

7. The attention distribution training device according to claim 1, characterized in that: The support frame (5) is rotatably connected to a second rotating shaft (15) on the outside, the second rotating shaft (15) is fixedly connected to a second telescopic rod (16) on the outside, and a rudder (17) is fixedly connected to a side of the second telescopic rod (16) away from the second rotating shaft (15).

8. The attention distribution training device according to claim 1, characterized in that: A cylinder (2) is fixedly mounted on the outside of the training base plate (1); a seat body (4) is provided at the output end of the cylinder (2); a first telescopic rod (3) is fixedly connected to the outside of the seat body (4); and a side of the first telescopic rod (3) away from the seat body (4) is fixedly connected to the training base plate (1).

Images