Vision rehabilitation training collaborative control method and device, storage medium and equipment

Abstract

The application discloses a vision rehabilitation training cooperative control method and device, a storage medium and equipment, and relates to the technical field of vision rehabilitation. The method comprises the following steps: determining a target training subject based on a user vision detection result; querying a first, a second and a third trajectory parameter set associated with the subject; controlling a seat and a training table to perform cooperative physical movement based on the first and the second trajectory parameter set, and controlling a visual stimulation object to move on a display unit of the training table based on the third trajectory parameter set, so as to constitute a three-dimensional dynamic training environment; acquiring user performance index data in a training process; and updating the third trajectory parameter set and adjusting the movement of the visual stimulation object based on the difference between the data and a threshold value. Through the cooperation of multi-degree-of-freedom physical movement and dynamic visual stimulation, the application realizes the simulation of a real visual scene, can adaptively adjust the training difficulty, and effectively improves the effect and adaptability of vision rehabilitation training.

Description

Technical Field

[0001] This application relates to the field of vision rehabilitation technology, and in particular to a collaborative control method, device, storage medium and equipment for vision rehabilitation training. Background Technology

[0002] Traditional vision rehabilitation equipment typically uses a fixed display screen, with users sitting statically in front of it for training. The training content relies on the movement and changes of graphics or symbols within the two-dimensional plane of the screen. Because both the equipment and the user's position are fixed, current technology cannot provide a realistic representation of the visual target in three-dimensional space, nor can it simulate the complex visual stimuli generated when the user moves or interacts with the moving environment. Therefore, the training scenario differs from a real dynamic visual environment, limiting the transferability of training effects. Summary of the Invention

[0003] This application provides a collaborative control method, device, storage medium, and equipment for vision rehabilitation training, which can solve the technical problems in the prior art where the use of a fixed display mode results in a single training scenario and insufficient transferability of effects. The technical solution is as follows: In a first aspect, embodiments of this application provide a collaborative control method for vision rehabilitation training, the method comprising: Based on the user's vision test results, the corresponding target training subject is determined from a set of preset training subjects; Query the first trajectory parameter set of the multi-degree-of-freedom seat, the second trajectory parameter set of the multi-degree-of-freedom training table, and the third trajectory parameter set of the visual stimulus object associated with the target training subject; The multi-degree-of-freedom seat is controlled to move based on the first set of trajectory parameters, the multi-degree-of-freedom training platform is controlled to move based on the second set of trajectory parameters, and the visual stimulus object is controlled to move on the display unit of the multi-degree-of-freedom training platform based on the third set of trajectory parameters, so as to form a coordinated training exercise. During the execution of the collaborative training exercise, the user's performance index data for the visual stimulus object is acquired; The third trajectory parameter set is updated based on the difference between the performance index data and the target index data corresponding to the target training subject; and The visual stimulus object is moved on the display unit according to the updated third trajectory parameter set.

[0004] Secondly, embodiments of this application provide a collaborative control device for vision rehabilitation training, the device comprising: The determination module is used to determine the corresponding target training subject from a set of preset training subjects based on the user's vision test results; The query module is used to query the first trajectory parameter set of the multi-degree-of-freedom seat, the second trajectory parameter set of the multi-degree-of-freedom training table, and the third trajectory parameter set of the visual stimulus object associated with the target training subject; The control module is used to control the multi-degree-of-freedom seat to move based on the first trajectory parameter set, control the multi-degree-of-freedom training platform to move based on the second trajectory parameter set, and control the visual stimulus object to move on the display unit of the multi-degree-of-freedom training platform based on the third trajectory parameter set, so as to form a coordinated training exercise. The acquisition module is used to acquire the user's performance index data for the visual stimulus object during the execution of the collaborative training exercise. The update module is used to update the third trajectory parameter set based on the difference data between the performance index data and the target index data corresponding to the target training subject; and A driving module is used to control the movement of the visual stimulus object on the display unit according to the updated third trajectory parameter set.

[0005] Thirdly, embodiments of this application provide a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the above-described method steps.

[0006] Fourthly, embodiments of this application provide a vision rehabilitation device, which may include: a processor and a memory; wherein the memory stores a computer program, the computer program being adapted to be loaded by the processor and to execute the above-described method steps.

[0007] The beneficial effects of the technical solutions provided in some embodiments of this application include at least the following: By controlling the coordinated movement of a multi-degree-of-freedom seat and a multi-degree-of-freedom training platform according to a preset trajectory parameter set, and simultaneously controlling the corresponding movement of the visual stimulus object on the display unit of the mobile platform, a three-dimensional dynamic training environment integrating vestibular, proprioceptive, and visual stimuli is constructed. This core feature directly solves the problem of the limited training scenarios in the background technology, which cannot simulate real spatial changes. The beneficial effects are twofold: first, through the spatiotemporal coordination of the physical motion platform and visual stimuli, a highly realistic dynamic visual task scenario is created for the user, enhancing the realism and challenge of the training; second, based on the user's real-time performance data, the trajectory parameter set of the visual stimulus is dynamically updated, enabling adaptive adjustment of training difficulty, thereby ensuring the personalization and effectiveness of the training process. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a schematic diagram of the network architecture provided in the embodiments of this application; Figure 2 This is a block diagram of the vision rehabilitation device provided in the embodiments of this application; Figure 3 This is a flowchart illustrating the collaborative control method for vision rehabilitation training provided in this application embodiment; Figure 4 This is a flowchart illustrating the control method for a multi-degree-of-freedom seat provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a collaborative control device for vision rehabilitation training provided in this application; Figure 6 This is a schematic diagram of a computer storage medium provided in this application; Figure 7 This is a schematic diagram of the hardware structure of a vision rehabilitation device provided in this application. Detailed Implementation

[0010] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0011] It should be noted that the collaborative control method for vision rehabilitation training provided in this application is generally executed by a collaborative control device for vision rehabilitation training, and correspondingly, the collaborative control device for vision rehabilitation training is generally installed in vision rehabilitation equipment.

[0012] Figure 1 An exemplary network architecture is shown that can be applied to the collaborative control method or collaborative control device for vision rehabilitation training in this application.

[0013] like Figure 1 As shown, the network architecture may include: vision rehabilitation device 1 and server 2. Vision rehabilitation device 101 and server 2 can communicate with each other via the network, which serves as the medium for providing communication links between the various units. The network may include various types of wired or wireless communication links, such as: wired communication links including fiber optic cables, twisted-pair cables, or coaxial cables; and wireless communication links including Bluetooth communication links, Wi-Fi communication links, or microwave communication links.

[0014] See Figure 2 As shown, the vision rehabilitation device 1 includes: a controller 11, a multi-degree-of-freedom training table 14, a lighting module 12, an audio output module 13, a multi-degree-of-freedom seat 15, and a human-computer interaction module 16. The controller 11 may include a processor and a memory.

[0015] The controller 11 is the core processing and control unit of the device, used to execute all training logic algorithms. It is implemented using an embedded computer system with a built-in dedicated control program. The controller 11 is responsible for processing vision detection input data, matching and recalling target training subjects according to pre-stored rules, calculating and generating motion trajectory parameter sets for the multi-degree-of-freedom seat 15 and the multi-degree-of-freedom training platform 14, processing signals uploaded by the physiological monitoring sensor 17 and calculating fatigue levels, controlling the brightness of the lighting module 12 according to the training subject parameters, and sending voice playback commands to the audio output module 13. The controller 11 is connected to all other components via electrical wiring or wireless communication protocols to achieve centralized control and data exchange.

[0016] The multi-degree-of-freedom training platform 14 provides users with a controllable physical motion plane, generating vestibular and proprioceptive stimulation. It is implemented as an electrically powered platform supported by a high-strength frame, beneath which are mounted two sets of orthogonally arranged precision linear slide modules to achieve two degrees of translational motion in the horizontal plane. A servo motor-driven turntable can be integrated at the center of the platform, providing rotational freedom around the vertical axis. The entire platform is precisely positioned and velocitious by the controller 11 based on a second set of trajectory parameters.

[0017] The lighting module 12 provides ambient lighting for the working surface of the multi-degree-of-freedom training platform 14, meeting training requirements. It is implemented by uniformly embedding a high-density LED light strip within the perimeter frame of the training platform 14, or by mounting an adjustable-area LED surface light source above it. The module's drive circuit receives a dimming signal from the controller 11 and continuously adjusts the LED's luminous intensity by changing the input current or pulse width modulation duty cycle, thereby controlling the platform illuminance within the lux value range required for the target training subject.

[0018] The audio output module 13 is used to output voice prompts and status feedback to the user. Its implementation includes a speaker integrated within the device housing and a matching audio power amplifier circuit. When training begins, ends, or a reminder is needed, the controller 11 retrieves pre-stored digitized voice segments from its internal memory, converts them to analog-to-digital conversion, and then drives the speaker to emit sound via the module's amplification circuit.

[0019] The multi-degree-of-freedom seat 15 supports the user and can be adjusted independently of the training platform to provide directional vestibular stimulation. It is implemented as a dedicated seat with electric adjustment, featuring a lifting column beneath the seat cushion, a pitch motor at the connection between the backrest and seat cushion, and a rotating mechanism integrated into the seat base. The motors at each joint are independently driven by the controller 11 according to a first set of trajectory parameters, achieving smooth posture changes.

[0020] The human-computer interaction module 16 receives user commands and displays system information, serving as the interface between the user and the device. It is implemented as a touchscreen display embedded in an easily observable location on the device, running graphical user interface software to display subject menus, real-time training data, user performance curves, and system setting options. The module can also be equipped with independent physical emergency stop and start / pause buttons to ensure safe and convenient operation.

[0021] The physiological monitoring sensor 17 is used to non-invasively collect specific physiological signals from the user in real time, providing raw data for fatigue monitoring. Its implementation includes a miniature infrared camera fixed in front of the user to capture images of eyelid movement; a set of dry electrodes that can be fixed to the user's chest with flexible straps to collect single-lead electrocardiogram (ECG) signals; and a portable EEG acquisition patch worn on the forehead region to acquire prefrontal cortex EEG signals. These sensors transmit the digitized signal streams to the controller 11 for processing in real time via cable or Bluetooth.

[0022] It should be understood that Figure 1 The number of vision rehabilitation devices, networks, and servers shown is for illustrative purposes only. The number can be any number, depending on the implementation requirements.

[0023] The following will be combined with the appendix Figure 3 This application provides a detailed description of the collaborative control method for vision rehabilitation training provided in its embodiments. The collaborative control device for vision rehabilitation training in these embodiments may be... Figure 1 The vision rehabilitation equipment shown.

[0024] Please see Figure 3 This is a flowchart illustrating a collaborative control method for vision rehabilitation training, provided in an embodiment of this application. Figure 3 As shown, the method in this application embodiment may include the following steps: S1. Based on the user's vision test results, determine the corresponding target training subject from a set of preset training subjects.

[0025] The vision test results can be input from an external vision testing device or by the user through the interactive interface of the multi-degree-of-freedom training platform; this application makes no limitation on this. The results include at least one parameter quantifying visual function, such as a visual acuity of 0.5, a horizontal visual field of 60 degrees, and an eye-tracking latency of 200 milliseconds. The controller's storage unit pre-stores multiple training subjects, each associated with a numerical range of one or more visual function parameters. The controller compares the parameter values ​​in the vision test results with the numerical ranges associated with each training subject. When a parameter value falls within the associated numerical range of a training subject, the controller identifies that training subject as the target training subject. If multiple parameters match, the most relevant training subject is selected according to a preset priority rule or weighted calculation.

[0026] For example, a vision test shows that the user's horizontal visual field is 55 degrees, while the storage unit contains a training subject called "Peripheral Visual Field Expansion," whose associated visual field range is less than 70 degrees. The controller compares these values ​​and determines that 55 degrees falls within this range, thus identifying "Peripheral Visual Field Expansion" as the target training subject.

[0027] S2. Query the first trajectory parameter set of the multi-degree-of-freedom seat, the second trajectory parameter set of the multi-degree-of-freedom training platform, and the third trajectory parameter set of the visual stimulus object associated with the target training subject.

[0028] The controller performs an index query in the memory database based on the unique identifier of the target training subject. The database is stored in tabular form, with each record associated with a training subject identifier and the storage addresses of its corresponding first, second, and third trajectory parameter sets. The trajectory parameter set is a data set defining the motion sequence, typically including position coordinates, angles, velocities, and acceleration values ​​over time. The controller retrieves the data for the three trajectory parameter sets bound to the target training subject identifier through a query operation.

[0029] For example, the target training subject is "dynamic visual acuity training". The controller queries the database to find the record corresponding to the target training subject, and reads the first trajectory parameter set (e.g., the position command sequence for controlling the seat to pitch and swing at a frequency of 0.5 Hz and an amplitude of 5 degrees), the second trajectory parameter set (e.g., the coordinate command sequence for controlling the training platform to move along a figure-eight trajectory on the horizontal plane), and the third trajectory parameter set (e.g., the coordinate sequence for controlling a letter "E" icon to change direction on the screen with an initial velocity of 1 meter per second).

[0030] It should be noted that the first trajectory parameter set defines the motion patterns of the multi-degree-of-freedom seat. Its determination hinges on configuring appropriate vestibular system physical stimulation parameters for specific training programs. The determination is based primarily on two levels: first, the specific vestibular function or tolerance that the program aims to improve; for example, programs targeting vestibular adaptation training require periodic linear oscillations; second, biomechanical constraints ensuring user safety and comfort. Based on this, by referencing commonly used stimulation patterns and parameter ranges in clinical vestibular rehabilitation, and combining the safety limits of the device's own motion mechanism, specific motion functions for each motion axis of the seat (such as pitch, roll, and rise) are set for each program. These functions are typically expressed as the relationship between time and angle or displacement, including key parameters such as amplitude, frequency, phase, and acceleration characteristics. These parameters are ultimately quantified into discrete position command sequences or continuous function expressions that the controller can directly invoke, and stored as the first trajectory parameter set.

[0031] For example, when determining the first set of trajectory parameters for the "Visual-Motion Reflex Stability Training" subject, based on the subject's goal of strengthening visual and vestibular coordination, a motion pattern of low-speed sinusoidal rotation of the seat around the vertical axis is selected. Referring to clinical data, the rotation amplitude is set to ±15 degrees, and the rotation period is set to 10 seconds to ensure smooth movement. This specific set of function parameters is then calculated and stored as the first set of trajectory parameters for that subject.

[0032] The second trajectory parameter set defines the motion pattern of the multi-degree-of-freedom training platform. Its determination hinges on constructing the necessary proprioceptive input and dynamic visual background for specific training subjects. The determination process must consider its synergistic relationship with the first trajectory parameter set, as both together constitute the complex physical motion environment in which the user is situated. During the design phase, based on the subject objectives, it is determined whether the training platform needs to perform translation, tilting, or a combination of movements. For example, subjects used for training dynamic balance may require slow, irregular planar movements; subjects used to simulate specific motion scenarios may require periodic tilting. Based on relevant research data on human posture stability, the direction, path, speed, and amplitude of the platform's motion are set to ensure it remains within the effective stimulation range and poses no safety hazards. The spatial trajectory and temporal relationship are transformed into precise control coordinate sequence or motion vectors, solidified into the second trajectory parameter set.

[0033] For example, when determining the second trajectory parameter set for the "Visual Tracking in Mobile Scenarios" subject, to simulate the slight undulations during walking, a training platform is set to perform slight periodic pitching around its horizontal axis. Based on typical data of torso undulations in normal gait, the pitch angle is set to ±3 degrees, and the period is set to 2 seconds. This motion pattern, after being parameterized, is stored as the second trajectory parameter set for this subject.

[0034] The third trajectory parameter set defines the motion and presentation characteristics of the visual stimulus, directly corresponding to the core visual task and difficulty level of the target training subject. The determination process strictly follows the classic paradigm of visual cognition and eye-tracking training. For example, for subjects involving smooth tracking, the stimulus needs to move in a straight line or curve at a constant speed or with uniform acceleration; for subjects involving saccades, the stimulus needs to make instantaneous jumps between different positions. The parameter settings reference commonly used values ​​in standard visual inspection and training tools, such as viewing angle, movement speed, and contrast, and take into account the spatiotemporal coordination with the physical movement of the seat and training platform to create tasks that match or challenge the user's integration abilities. All these rules regarding the stimulus's path, speed, appearance, and appearance logic are encoded into specific coordinate sequences, state variables, and triggering conditions, forming the third trajectory parameter set.

[0035] For example, when determining the third trajectory parameter set for the "Horizontal Smooth Tracking Training" subject, based on the optimal stimulus velocity range for smooth eye tracking, a circular cursor is set to move horizontally back and forth on the screen at a constant angular velocity of 15 degrees / second, with a range of motion of 20 degrees to the left and right of the center of the screen. This path and velocity rule, after being parameterized, is stored as the third trajectory parameter set for this subject.

[0036] S3. Control the multi-degree-of-freedom seat to move based on the first trajectory parameter set, control the multi-degree-of-freedom training platform to move based on the second trajectory parameter set, and control the visual stimulus object to move on the display unit of the multi-degree-of-freedom training platform based on the third trajectory parameter set, so as to form a coordinated training motion.

[0037] Specifically, the data from the first and second trajectory parameter sets are processed according to their time sequence using a digital-to-analog converter and amplification circuit to generate control signals for the motors driving each joint of the multi-degree-of-freedom seat and for the linear or rotary actuators of the multi-degree-of-freedom training platform. Simultaneously, the controller, through a graphics rendering module, combines the coordinate data from the third trajectory parameter set with the refresh rate of the display unit to generate image frame signals that continuously render the visual stimulus at corresponding positions on the screen. The controller ensures the timing of these three control processes is synchronized, allowing the physical movement of the seat, the physical movement of the training platform, and the movement of the visual stimulus on the screen to occur simultaneously according to a predetermined spatiotemporal relationship, thus creating a collaborative, multi-sensory integrated training environment.

[0038] For example, based on the first set of trajectory parameters, the controller outputs a signal in the first second to tilt the seat forward by 3 degrees; based on the second set of trajectory parameters, it outputs a signal at the same moment to move the training platform 2 centimeters to the right; simultaneously, based on the third set of trajectory parameters, the graphics rendering module renders the visual stimulus (a light spot) 10 pixels to the right of the center of the screen in the first second. The synchronized movement of these three components simulates a complex vestibular and visual stimulus scenario.

[0039] S4. During the execution of collaborative training exercises, acquire the user's performance index data for visual stimuli.

[0040] The controller has a data acquisition interface that receives user response data in real time from one or more human-computer interaction modules. These modules include, but are not limited to, infrared eye trackers, manual response buttons, electroencephalogram (EEG) electrodes, or electromyography (EMG) sensors. The controller preprocesses the received raw data, for example, by using a low-pass filter to remove high-frequency noise from the eye movement signal, or by calculating the difference between the timestamp of the manual response and the timestamp of the visual stimulus event. The preprocessed data, which quantifies user performance, is the performance metric data. For example, the root mean square error between the eye movement trajectory and the trajectory of the visual stimulus is 15 pixels, or the average reaction time from the appearance of the stimulus to pressing the button is 450 milliseconds. The controller temporarily stores this performance metric data in a designated memory area.

[0041] For example, during the movement of the visual stimulus, the infrared eye tracker sends the user's gaze coordinates to the controller at a frequency of 60 Hz. The controller continuously records 60 gaze coordinates within one second and calculates them with 60 coordinates of the visual stimulus within the same time period to obtain the average tracking error within that one second, which is used as a performance indicator.

[0042] S5. Update the third trajectory parameter set based on the difference between the performance index data and the target index data corresponding to the target training subject.

[0043] The controller reads target performance data set in the target training subjects from memory, such as a target tracking error of 10 pixels or a target reaction time of 400 milliseconds. Then, it performs subtraction or division operations between the performance data obtained in step S4 and the target performance data to obtain difference data, such as an error exceeding 5 pixels or a reaction delay of 50 milliseconds. The controller has a pre-set parameter adjustment rule table, which defines the mapping relationship between different types of difference data and the adjustment amount of specific parameters in the third trajectory parameter set. Based on the calculated difference data, the controller queries the adjustment rule table to determine the adjustment instructions for the third trajectory parameter set, such as reducing the movement speed by 20% or increasing the radius of curvature of the motion path by 30%. Subsequently, the controller modifies the data values ​​of the third trajectory parameter set in its working memory according to the adjustment instructions, generating an updated third trajectory parameter set.

[0044] For example, the current target tracking error is 10 pixels, while the actual performance data shows 18 pixels, resulting in a difference of 8 pixels. The parameter adjustment rule table is consulted, which stipulates that for every 2 pixels the error exceeds, the movement speed of the visual stimulus should be reduced by 5%. Based on this, the controller calculates that the speed needs to be reduced by 20%, and updates the speed parameter value defined in the third trajectory parameter set from 100 pixels per second to 80 pixels per second.

[0045] S6. Control the visual stimulus object to move on the display unit according to the updated third trajectory parameter set.

[0046] In this system, the controller inputs the updated third trajectory parameter set into the graphics rendering module at the next control cycle or at a preset update time. Based on the new trajectory parameter sequence, the graphics rendering module recalculates and generates the position of the visual stimulus object in each frame of the display unit, altering the movement characteristics of the visual stimulus object—for example, controlling its movement to be slower or its path to be straighter. The update process does not require stopping the movement of the multi-degree-of-freedom seat and training platform, enabling online dynamic adaptation of training difficulty and forming a closed-loop training system based on performance feedback.

[0047] For example, after updating the velocity parameters in step S5, the controller immediately uses the new velocity value of 80 pixels per second to calculate the position of the visual stimulus when rendering the next frame. The user will then see a visual stimulus moving at a slower speed, which helps them track it more accurately and may reduce performance differences in the next evaluation.

[0048] This application executes the above process through a controller, achieving highly automated and personalized visual-vestibular coordination training. Training content is automatically matched based on objective vision test results, and an immersive training environment is created using the synchronized movement of multi-degree-of-freedom devices and dynamic visual stimuli. The difficulty parameters of the visual stimuli are dynamically adjusted based on the user's real-time training performance, forming a closed-loop adaptive control. This effectively solves the problems of fixed content, lack of immediate feedback, and personalized adaptation in traditional training methods, improving the safety and efficiency of training.

[0049] In one embodiment, see Figure 4 , Figure 4 This is a flowchart illustrating a control method for a multi-degree-of-freedom seat, including the following steps: A1. During the execution of collaborative training exercises, the user's fatigue level is detected based on the user's physiological state data.

[0050] In step A1, the controller continuously collects the user's physiological state data using one or more physiological monitoring sensors. These sensors include an infrared camera for capturing facial video, electrode pads attached to the skin to collect electrocardiogram (ECG) signals, and a sensor for measuring skin conductivity. The controller processes the raw physiological state data, using filtering algorithms to remove noise and extract key feature indicators. For example, it calculates the average number of blinks per unit time from the video stream, analyzes the standard deviation of adjacent heartbeat intervals from the ECG signal to obtain heart rate variability, and calculates the average conductivity level from the skin conduction signal. The controller compares the extracted feature indicators with fatigue assessment parameters pre-stored in memory. These fatigue assessment parameters define fatigue level scores corresponding to different feature indicator ranges; for example, a blink frequency exceeding 20 times per minute and a heart rate variability below 50 milliseconds corresponds to a fatigue level score of 7. The controller uses a lookup table or weighted calculation method to synthesize the various feature values ​​and derive a specific fatigue level number.

[0051] For example, during training, an infrared camera detected that the user blinked 25 times in the past minute, and an electrocardiogram sensor measured a heart rate variability of 45 milliseconds. Based on a pre-stored parameter table, the controller determined that the blink frequency index fell into the "high frequency" range, corresponding to a score of 2, and the heart rate variability index fell into the "low variability" range, corresponding to a score of 5. The weighted sum was then used to determine the current fatigue level as 7.

[0052] A2. When the fatigue level exceeds the fatigue threshold, pause the coordinated training exercise and record the current posture data of the multi-degree-of-freedom seat and multi-degree-of-freedom training platform.

[0053] The memory stores a fatigue threshold, which can be set according to the intensity of the training subject or the user's personal profile, for example, set to fatigue level 6. The controller compares the fatigue level calculated in real time in step A1 with the fatigue threshold. When the fatigue level exceeds the preset fatigue threshold, a pause command is generated and sent to the multi-degree-of-freedom seat and the multi-degree-of-freedom training platform. The transient command simultaneously reaches the motor driver of the multi-degree-of-freedom seat, the platform controller of the multi-degree-of-freedom training platform, and the graphics rendering processor, instructing all movements to stop smoothly immediately, and the visual stimulus on the display unit to freeze or fade out. While issuing the pause command, the controller reads the current posture data of the multi-degree-of-freedom seat and the multi-degree-of-freedom training platform. For example, for the multi-degree-of-freedom seat, the controller reads and records the specific values ​​of parameters such as backrest tilt angle, seat rotation angle, and seat height adjustment through the angle encoders or position sensors built into each joint. For the multi-degree-of-freedom training platform, the controller reads and records the specific values ​​of parameters such as the X and Y coordinates of the training platform in the horizontal plane and the tilt angle of the platform around each axis through its platform displacement sensor and tilt sensor. The controller defines the set of spatial pose values ​​obtained from the seat and training platform at the moment of pause as the current attitude data, integrates them into a data packet, and stores it in non-volatile memory.

[0054] Example: The preset fatigue threshold is level 6. When the controller calculates a real-time fatigue level of 7, it immediately sends a pause command. After all movement stops, the controller synchronously reads and records the following data: data from the seat sensor: backrest tilt angle 120 degrees, base rotation angle 15 degrees; data from the training platform sensor: platform X-axis coordinate 150 mm, Y-axis coordinate -50 mm, roll angle 2 degrees. This set of data constitutes the current posture data packet and is saved.

[0055] For example, the preset fatigue threshold is 6, and the current calculated fatigue level is 7. The controller determines that level 7 exceeds the threshold of 6 and immediately sends a pause command to all execution units. After the training exercise stops, the controller reads and stores the values ​​from the seat back tilt sensor (120 degrees), the base rotary encoder (15 degrees), and the column position sensor (750 mm) as the current posture data.

[0056] A3. Control the multi-degree-of-freedom seat to switch to preset relaxation posture data.

[0057] After recording the current posture, the controller retrieves a set of preset relaxation posture data from memory. This relaxation posture data consists of a set of optimal comfort position coordinates pre-defined through experimentation or configuration, such as defining the backrest tilt angle as 150 degrees, the leg rest elevation angle as 20 degrees, and the seat lowered to its lowest position. Based on these target parameters, the controller calculates a safe motion trajectory from the recorded current posture to the target relaxation posture. This trajectory includes speed and acceleration curves for each joint motor to ensure smooth movement. Subsequently, the controller generates drive signals based on this trajectory, controlling the coordinated movement of each motor in the multi-degree-of-freedom seat, automatically adjusting the seat from the posture at the end of training to the preset relaxation posture.

[0058] For example, the preset relaxation posture data is a backrest angle of 150 degrees, a leg support angle of 20 degrees, and a height of 650 mm. The controller plans a movement trajectory that takes 10 seconds, driving the seat to gradually and smoothly move from the recorded backrest angle of 120 degrees and height of 750 mm to a backrest angle of 150 degrees and a height of 650 mm, allowing the user to enter a more reclined and elevated resting posture.

[0059] A4. After pausing for a preset duration, resume collaborative training motion based on the current posture data.

[0060] The controller starts an internal timer when training is paused. The target duration of the internal timer is a preset duration, such as 180 seconds. When the timer reaches 180 seconds, the controller triggers the recovery process. The first step of the recovery process is to control the multi-degree-of-freedom seat to return from a relaxed posture. The controller reads the previously stored current posture data, uses it as the target position, plans a motion trajectory to return from the relaxed posture, and controls the seat to move along the trajectory, restoring the spatial posture recorded at the time of the pause. After the seat returns to its original position, the controller immediately sends a restart command to the motion control module and the graphics rendering module. This command instructs the system to start from the trajectory sequence point where the previous co-training motion was interrupted or the next logical starting point, and continue to drive the multi-degree-of-freedom seat, multi-degree-of-freedom training platform, and visual stimulus object to continue performing co-training motion according to the original first trajectory parameter set, second trajectory parameter set, and possibly updated third trajectory parameter set.

[0061] For example, after a 180-second pause, the timer is triggered. The controller first moves the seat from a relaxed posture at a 150-degree tilt angle and a height of 650 mm back to the stored current posture at a 120-degree tilt angle and a height of 750 mm. Once the seat is confirmed to be in position, the controller sends a start command, and the training platform continues its original trajectory. The visual stimulus on the screen also resumes its movement along the preset trajectory from its paused position, thus seamlessly resuming the collaborative training.

[0062] This application quantifies user fatigue levels and automatically interrupts training when fatigue exceeds safe limits, effectively mitigating the risk of physical discomfort or decreased efficiency due to overtraining. By automatically recording and restoring training postures and providing standardized relaxation positions during interruptions, it achieves controllable pausing and precise resumption of the training process, ensuring the integrity of the training plan and the consistency of the user experience.

[0063] In one possible embodiment, A11, detecting the user's fatigue level based on the user's physiological state data, includes: A111. Collect the user's physiological state data, including: eye state parameters, electrocardiogram signal parameters, and electroencephalogram signal parameters.

[0064] The controller synchronously collects the user's physiological state data through one or more physiological sensors. For example, an infrared eye tracker or camera continuously captures images of the user's facial eye area to collect eye state parameters. Contact electrode pads are attached to specific locations on the user's chest to detect electrical signals generated by heart activity, and an EEG cap or head-mounted electrode array is placed on the user's scalp to detect electrical activity of neurons in the cerebral cortex. The controller acquires images at a preset sampling frequency, such as 30 frames per second, 250 sampling points per second for ECG signals, and 500 sampling points per second for EEG signals, and then converts the acquired continuous raw analog signals into digital physiological state data signals.

[0065] For example, during training, the controller simultaneously receives data streams from three sensors: a video sequence of eyelid opening and closing from an infrared camera, a millivolt-level voltage fluctuation sequence from ECG electrodes, and a microvolt-level voltage fluctuation sequence from EEG electrodes located in the forehead area. The controller then uses these raw data streams to acquire eye state parameters, ECG signal parameters, and EEG signal parameters, all of which are related to the user's level of fatigue.

[0066] A112. Normalize the eye state parameters, electrocardiogram signal parameters, and electroencephalogram signal parameters.

[0067] The eye state parameters include blink rate per minute and average eyelid closure speed. ECG signal parameters include heart rate and heart rate variability. EEG signal parameters include the power ratio of specific frequency bands, such as the Theta wave to Beta wave. Subsequently, the controller calls a pre-stored normalization mapping function to convert each extracted parameter value into a unified dimensionless numerical range. This mapping function is pre-calibrated based on a large amount of sample data; for example, it linearly maps the historical minimum to maximum blink frequency to a range of 0 to 1.

[0068] For example, the controller calculates the current blink rate as 25 times per minute, heart rate as 75 beats per minute, and EEG Theta / Beta power ratio as 2.5. Based on pre-stored normalization rules, the blink rate of 25 is mapped to 0.7, the heart rate of 75 is mapped to 0.5, and the power ratio of 2.5 is mapped to 0.8. These normalized values ​​eliminate the dimensional differences between the various parameters, facilitating subsequent comprehensive calculations.

[0069] A113. Calculate the normalized parameters according to the preset weight model to obtain a comprehensive fatigue metric value.

[0070] The system includes a pre-stored weighting model. This model defines the weighting coefficient for each normalized physiological parameter's impact on fatigue. These weighting coefficients can be obtained by analyzing historical training data or by calibration based on expert experience. The controller multiplies the normalized parameter values ​​obtained in step A112 by their corresponding preset weighting coefficients, then sums all the weighted values ​​to calculate a single quantitative value representing the overall fatigue level. The weighting model can be switched according to different training modes to adjust the importance of different physiological parameters in fatigue assessment.

[0071] For example: The preset weighting model specifies that the weighting coefficient for normalized blink frequency is 0.4, the weighting coefficient for normalized heart rate is 0.3, and the weighting coefficient for normalized EEG power ratio is 0.3. The controller multiplies 0.7 by 0.4 to get 0.28, multiplies 0.5 by 0.3 to get 0.15, and multiplies 0.8 by 0.3 to get 0.24. Adding 0.28, 0.15, and 0.24 yields a comprehensive fatigue measurement value of 0.67.

[0072] A114. Determine the user's fatigue level based on the target value range to which the fatigue measurement value belongs among multiple preset numerical ranges.

[0073] The memory contains a pre-set fatigue level mapping table. This table divides the numerical range of 0 to 1 into several consecutive and non-overlapping numerical intervals, each interval corresponding to a discrete fatigue level. For example, 0 to 0.3 corresponds to level 1, indicating alertness; 0.3 to 0.6 corresponds to level 2, indicating mild fatigue, and so on. The controller sequentially compares the quantified fatigue value calculated in step A113 with the boundaries of each numerical interval in the mapping table. When the quantified fatigue value falls into a specific numerical interval, the controller determines the fatigue level corresponding to that interval as the user's final fatigue level.

[0074] For example: The preset mapping table specifies that a quantified value between 0.6 and 0.8 corresponds to fatigue level 3, representing moderate fatigue. The controller calculates a comprehensive fatigue quantified value of 0.67. Comparing this to 0.8, 0.67 is greater than or equal to 0.6 and less than 0.8; therefore, the controller determines the user's current fatigue level to be level 3.

[0075] In this way, this application overcomes the shortcomings of single-parameter evaluation being susceptible to interference, significantly improving the accuracy and robustness of fatigue state detection. By mapping the quantified comprehensive fatigue value to a preset interval, different fatigue levels can be distinguished, providing a precise and reliable decision-making basis for implementing graded safety interventions. This enhances the intelligence and personalization of the entire training system while ensuring user training safety.

[0076] In one embodiment, S5, updating the third trajectory parameter set based on the difference data between performance indicator data and target indicator data corresponding to the target training subject, includes: S51. Obtain tracking error and response delay from performance indicator data.

[0077] The controller acquires user performance metrics data across multiple dimensions. For tracking error, the controller receives coordinate data streams from the eye-tracking device. The eye-tracking device monitors the user's gaze point position on the display screen at a fixed frequency. The controller compares the coordinates of each gaze point acquired within a preset time window with the preset center coordinates of the visual stimulus at that moment, calculating the straight-line distance between the two points. The controller performs statistical processing on all instantaneous distance values ​​obtained within this time window, such as calculating their arithmetic mean, ultimately obtaining a tracking error value representing the average deviation within that time period, typically in pixels. For reaction delay, the controller can be triggered manually by a user, such as a button or touchscreen. The controller internally records the precise moment of occurrence of a specific visual stimulus event, which is a clear signal requiring a user response. The controller continuously monitors the input status of the manual trigger device. When a user response is detected, the controller records the precise moment of the action. The time difference between the stimulus event and the user's response is calculated, yielding the reaction delay value, typically in milliseconds.

[0078] For example, the controller analyzes 120 fixation points reported by the eye tracker in the last 2 seconds, calculates the deviation of each point from the position of the visual stimulus, and obtains an average deviation of 18 pixels, which is the current tracking error. In a training exercise requiring the user to respond to a color change of an image, if the controller receives a button signal 350 milliseconds after the stimulus signal is emitted, this 350 milliseconds is recorded as the current reaction delay.

[0079] S52. Obtain a target tracking error threshold corresponding to the target training subject.

[0080] Among them, the target tracking error threshold represents the maximum average error that the user's tracking performance can be regarded as qualified under the current subject difficulty. The target tracking error threshold is in pixels and is pre-stored in the database of the memory, mapped to a specific target training subject identifier. The controller uses the target training subject identifier currently in operation as a query key to access the database and obtain the numerical value of the matching target tracking error threshold.

[0081] For example, when the currently executed subject is the "High-speed Horizontal Saccade Training" subject, the controller uses this subject identifier to query the database and obtains the preset target tracking error threshold for this subject as 12 pixels.

[0082] S53. Obtain a reaction delay error threshold corresponding to the target training subject.

[0083] Among them, similar to the method of obtaining the target tracking error threshold, the controller queries the corresponding data item, that is, the target reaction delay threshold, from the database using the same target training subject identifier. The target reaction delay threshold defines the longest delay time that the user's reaction speed can be regarded as qualified under the current subject, in milliseconds.

[0084] For example, for the above "High-speed Horizontal Saccade Training" subject, the controller obtains its preset target reaction delay threshold as 280 milliseconds from the database.

[0085] S54. If the tracking error is greater than the target tracking error threshold, reduce the movement speed of the visual stimulus object based on the difference between the tracking error and the target tracking error threshold; Among them, the controller compares the calculated tracking error with the obtained target tracking error threshold. When the comparison result indicates that the current tracking error is greater than the target tracking error threshold, the controller determines that the user's tracking accuracy does not meet the standard. The controller calculates the difference between the two, that is, the excess amount of the tracking error. According to the speed adjustment rule preset in the controller, the controller calculates the specific ratio or absolute value by which the movement speed of the visual stimulus object needs to be reduced according to the size of the difference. The speed adjustment rule can be a clear mathematical relationship, for example: the speed reduction ratio is equal to the difference divided by a fixed base number; it can also be a pre-set query table, which directly maps different differences to different speed adjustment amounts. After calculating the new speed value, the controller directly modifies the parameter item used to control the movement speed in the third trajectory parameter set and uses the new value to overwrite the old value.

[0086] For example, the current tracking error is 18 pixels, the target tracking error threshold is 12 pixels, and the excess is 6 pixels. The preset speed adjustment rule stipulates that for every 3-pixel difference, the motion speed decreases by 10%. According to this rule, a 6-pixel difference corresponds to a 20% speed reduction. If the current motion speed parameter in the third trajectory parameter set is 200 pixels per second, then the updated speed parameter should be set to 160 pixels per second. The controller updates the parameter set accordingly.

[0087] S55. If the reaction delay is greater than the target reaction delay threshold, the motion path complexity of the visual stimulus is reduced based on the difference between the reaction delay and the target reaction delay threshold.

[0088] The controller calculates the reaction delay and compares it with a target reaction delay threshold obtained from the database. When the comparison indicates that the current reaction delay exceeds the target threshold, the controller determines that the user's reaction speed has not met the requirement. The controller calculates the difference between the two to obtain the excess reaction delay. Motion path complexity is a comprehensive parameter, and its reduction is specifically reflected in the adjustment of a series of sub-parameters in the third trajectory parameter set. These sub-parameters collectively determine the path's tortuosity, frequency of direction changes, and randomness. Based on preset path simplification rules and the excess reaction delay, the controller determines how to adjust these sub-parameters. For example, it can increase the duration of straight-line motion segments in the path, decrease the maximum allowed number of path direction changes per unit time, or lower the upper limit of the change amplitude in the path random generation algorithm. The controller calculates new sub-parameter values ​​according to the rules and updates the third trajectory parameter set accordingly.

[0089] For example, the current reaction delay is 350 milliseconds, the target reaction delay threshold is 280 milliseconds, and the excess is 70 milliseconds. The preset path simplification rule stipulates that for every 35 milliseconds of excess, the "maximum number of direction changes per second" parameter is reduced by one. According to this rule, a 70-millisecond excess corresponds to a reduction of this parameter by two. If the original value of this parameter was 5 times per second, the updated value should be 3 times per second. The controller then modifies the corresponding parameter in the third trajectory parameter set accordingly.

[0090] It should be noted that if the user's performance metrics all meet the standards, the third trajectory parameter set of the visual stimulus object remains unchanged.

[0091] In this way, this application can specifically reduce the difficulty of the visual stimulus task in the corresponding dimension when the user's performance in any dimension fails to meet the standard. For example, it can reduce the speed to adapt to insufficient tracking ability, or simplify the path to adapt to insufficient information processing speed. This closed-loop adjustment mechanism based on two-dimensional performance feedback ensures that the training task is always matched with the user's real-time ability, effectively maintaining the optimal challenge of training, thereby maximizing the effect and efficiency of personalized training while protecting the user's training enthusiasm.

[0092] In one possible embodiment, S1, determining the corresponding target training subject from a set of preset training subjects based on the user's vision test results, includes: S11. Obtain the user's vision test results, which include: refractive error parameters and corrected visual acuity values.

[0093] The controller receives digital vision test reports from standard automated refractometers or comprehensive refractometers via wired or wireless data interfaces. These reports should include at least spherical, cylindrical, and axis data in diopters, as well as corrected visual acuity values ​​expressed using a standard logarithmic visual acuity chart or decimal notation. The controller parses the report, extracts the diopter parameters and corrected visual acuity values, and stores them as internally processable data structures. For example, it can create a data object for each user containing two sets of diopter data for the left and right eyes, along with a corrected visual acuity value.

[0094] S12. Determine the user's refractive error level based on refractive power parameters, and calculate the user's visual function deficit index based on corrected visual acuity values.

[0095] The controller calculates the refractive error level from the stored refractive parameters. The processing rules are based on recognized clinical classification standards, primarily using the absolute value of the spherical power. For example, a preset rule might be defined as follows: 0.25D or less is Level 0 (normal); greater than 0.25D and less than or equal to 3.00D is Level 1 (mild abnormality); greater than 3.00D and less than or equal to 6.00D is Level 2 (moderate abnormality); and greater than 6.00D is Level 3 (severe abnormality). The controller applies this rule to the spherical power of the user's left and right eyes respectively, selecting the higher level value from the two eyes as the user's final refractive error level. Simultaneously, the controller calculates the visual impairment index based on corrected visual acuity. The calculation uses a predefined quantitative formula, for example: Visual Impairment Index = (Standard Corrected Visual Acuity Reference Value - User's Corrected Visual Acuity Value) / Standard Corrected Visual Acuity Reference Value. The standard corrected visual acuity reference value is typically set to 1.0 (or logarithmic visual acuity of 5.0). This formula converts the difference in visual acuity into a dimensionless index between 0 and 1, with a larger value indicating a more significant defect.

[0096] For example, a user's right eye spherical lens power is -2.50D, with an absolute value of 2.50D. According to the rules, this falls within the range of "greater than 0.25D and less than or equal to 3.00D," corresponding to level 1. The left eye also corresponds to level 1. Therefore, the user's refractive error level is determined to be level 1. The user's corrected visual acuity is 0.8, and the standard reference value is 1.0. Substituting these values ​​into the formula, we get: (1.0 - 0.8) / 1.0 = 0.2. The user's visual impairment index is 0.2.

[0097] S13. Match the refractive error type and visual impairment index in the preset mapping relationship.

[0098] The system stores a pre-defined subject matching table (i.e., mapping relationship). This table exists as a two-dimensional matrix or database table, with row indices corresponding to different refractive error levels and column indices corresponding to predefined visual impairment index ranges. Each cell defined by the intersection of a row and column contains a unique identifier for one or more recommended training subjects. The controller uses the refractive error level (e.g., level 1) and visual impairment index (e.g., 0.2) calculated in step S12 as query input. First, it locates the corresponding row based on the refractive error level. Then, it determines which pre-defined numerical range the visual impairment index falls into (e.g., range 1: 0 ≤ index < 0.1; range 2: 0.1 ≤ index < 0.3; range 3: index ≥ 0.3), thereby locating the corresponding column. The intersection of the row and column determines the final matching position.

[0099] For example, a user has a refractive error level of 1 and a visual impairment index of 0.2. The controller queries the relationship table and finds the interval to which the index 0.2 belongs in the row corresponding to level 1. Assume that 0.2 falls into the interval "0.1 ≤ index < 0.3", which corresponds to a specific column. The subject identification codes stored in the cells at the intersection of the row and column are "TM_A01" and "TM_B03".

[0100] S14. Based on the matching results, obtain at least one target training subject.

[0101] In this process, the controller reads all training subject identifier codes stored in the cell matched in step S13. The training subject identifier code is the key to access the database. Based on the training subject identifier code, the controller retrieves the corresponding target training subject record containing complete training parameter definitions from the database. These target training subject records constitute the set of target training subjects recommended personally to the user. If multiple subjects are matched, they can be arranged according to a preset sorting rule (such as identifier code order or subject basic difficulty order) to determine the initial training order.

[0102] For example, the controller obtains subject identification codes "TM_A01" and "TM_B03". Then, the controller retrieves the record with identification code "TM_A01" from the subject database, which represents "Dynamic Visual Tracking Training (Basic Version)"; and the record with identification code "TM_B03", which represents "Contrast Perception Enhancement Training". These two specific training subjects are then identified as the user's target training subjects.

[0103] In this way, this application automatically converts the original vision test results into standardized refractive error levels and quantified visual function impairment indices. Using a pre-defined scientific mapping table, it performs precise matching, achieving automated, standardized, and personalized training subject recommendations. This method eliminates the subjectivity and inconsistency of traditional methods that rely on human experience, ensuring the scientific and efficient matching of the most suitable training subjects to users with different vision conditions.

[0104] In one embodiment, it also includes: Voice prompts are issued via the voice output module at the beginning and end of the collaborative training exercise.

[0105] The memory pre-stores at least two specific digital audio data segments, corresponding to the training start and training end prompts, respectively. After the controller completes the loading of the target training subject, parameter set query, and equipment readiness check according to the process, it generates a training start flag before issuing the first set of coordinated motion control commands to the multi-degree-of-freedom seat, multi-degree-of-freedom training platform, and display unit. This flag triggers the controller's audio output function. The controller reads the corresponding "start" audio data from its internal memory, converts it into an analog audio signal, and sends it to the audio output module connected to the controller circuitry. This audio output module converts the electrical signal into sound and plays it, thus issuing the training start audio prompt. Correspondingly, when the coordinated training motion is completed as planned, or the user interrupts the training via the emergency stop device, the controller generates a training end flag after completing the safety stop procedures for all moving parts. This flag triggers the controller to read the corresponding "end" audio data and drive the audio output module to play the training end audio prompt through the same path.

[0106] For example, after the user starts the system and selects a subject, the controller completes all initialization. Just as the seat is about to begin moving, the controller triggers voice output, playing a message that reads, "Training begins, please concentrate and follow the target." After a preset 15-minute training session, the training process automatically ends. Once the seat and training platform are back in place and the display screen is off, the controller triggers another message that reads, "Training complete, please relax and rest."

[0107] Thus, by automatically playing voice prompts at the beginning and end of the training process, this application can improve the clarity of human-computer interaction and the integrity of the user experience. The start prompt serves as a clear instruction and preparation, helping users quickly switch their attention to the training state; the end prompt provides a clear signal of task completion and guides users through a relaxation transition.

[0108] In one embodiment, the multi-degree-of-freedom training platform is equipped with a lighting module; The method of this application also includes: Obtain the target lighting intensity associated with the target training subject; The luminous power of the lighting module is controlled based on the target lighting intensity.

[0109] When the controller queries the trajectory parameter set of the target training subject from memory, it simultaneously queries the lighting configuration parameters associated with that subject's identifier. The lighting configuration parameters include a target lighting intensity value, in lux, defining the optimal lighting level for the visual environment of the training platform when performing that subject. The target lighting intensity values ​​for different training subjects are pre-determined through experimental or clinical experience and stored in the subject configuration database. The controller accesses this database, using the unique identifier of the current target training subject as an index, to retrieve and obtain the target lighting intensity associated with it.

[0110] For example, if the current target training subject is "dark adaptation training", the controller uses the subject identifier to query the database and obtains the target lighting intensity of 300 lux while obtaining the trajectory parameter set.

[0111] The controller converts the acquired target illumination intensity into control commands for the integrated lighting module on the multi-degree-of-freedom training platform. The lighting module typically consists of a set of LEDs and their driving circuitry. Based on the ratio between the target illumination intensity and the maximum illuminance value corresponding to the lighting module's maximum brightness, the controller calculates the required drive current duty cycle or voltage value. Through its digital or analog output interface, the controller sends corresponding control signals to the lighting module's driving circuitry, adjusting the LEDs' luminous power to stabilize the actual illuminance on the training platform surface near the target illumination intensity. The controller can incorporate a closed-loop light feedback mechanism, using a light sensor to monitor ambient illuminance and fine-tune the output to ensure the accuracy of the illumination intensity.

[0112] For example, the controller acquires a target illumination intensity of 300 lux. The controller has a pre-stored relationship between the illumination module's full-power output and the 500 lux illuminance it can produce. To achieve 300 lux, the controller calculates that the PWM (Pulse Width Modulation) duty cycle of the LED (Light Emitting Diode) driver circuit needs to be set to 60%. The controller then outputs a control signal for this duty cycle to the driver circuit, and the brightness of the illumination module adjusts accordingly until the measured illuminance illuminating the training surface reaches and is maintained at approximately 300 lux.

[0113] Thus, this application achieves personalized and precise control of the training visual environment by treating illumination intensity as a controllable variable associated with the training subject. It can automatically adjust the ambient light level according to the purpose of different training subjects, such as providing a suitable low-light environment during dark adaptation training, or providing sufficient and uniform illumination for training requiring fine discrimination. This ensures that the visual stimulus is always in the optimal light environment that meets the current physiological needs of training, effectively improving the scientific rigor and effectiveness of the training.

[0114] In one possible embodiment, determining the corresponding target training subject from a set of preset training subjects based on the user's vision test results includes: The system collects the user's initial naked-eye vision data, real-time eye movement data, body posture data, and at least one physiological indicator data through a naked-eye vision testing unit, an eye-tracking sensor integrated into the display unit, and a posture monitoring sensor and a physiological signal sensor set on the multi-degree-of-freedom seat. The controller integrates and analyzes the initial uncorrected visual acuity data, real-time eye movement data, body posture data, and physiological index data to generate a personalized combination scheme that includes the target training subject and the physical therapy parameters of the multi-degree-of-freedom seat; wherein, the physical therapy parameters are used to control the multi-degree-of-freedom seat to perform at least one auxiliary therapeutic action, including vibration, heating, or posture maintenance. The method further includes: The target training subjects and / or physical therapy parameters in the personalized combination scheme are periodically adjusted and updated based on newly collected user eye movement data, body posture data, and physiological index data during the collaborative training exercise.

[0115] Specifically, the controller runs an embedded multi-parameter decision model. This model first analyzes initial uncorrected visual acuity data, matching it against preset basic visual acuity thresholds for multiple training subjects to select a set of suitable beginner subjects. Next, combining real-time eye movement data (such as fixation stability and saccade speed) and postural data (such as sitting balance), it further evaluates the user's current motor control and visual function from the beginner set, matching the most suitable individual target training subject. Simultaneously, based on physiological indicators (such as heart rate reflecting tension) and postural data (such as pressure concentration areas caused by prolonged sitting), the model determines the user's relaxation and fatigue state, thereby generating a set of physical therapy parameters for the multi-degree-of-freedom chair. These parameters are translated into specific control commands, such as instructing the chair to periodically perform micro-vibrations of specific amplitude and frequency during training intervals, or to heat a designated area of ​​the chair back at low temperatures, or to automatically adjust the chair posture to correct the user's poor posture.

[0116] For example, based on a naked-eye visual acuity of 0.5, the controller selects two basic subjects: "contrast sensitivity training" and "dynamic tracking training." Combining real-time data, it detects that the user's eye movement speed is slow and their posture is slightly forward-leaning. The decision model prioritizes "dynamic tracking training" and designates it as the target training subject. Simultaneously, physiological data analysis reveals that the user's skin conductivity is low, indicating a need for relaxation. The model generates physical therapy parameters: during each training interval, the chair is controlled to micro-vibrate the lumbar region at a frequency of 40 Hz and an amplitude of 2 mm for 30 seconds.

[0117] Specifically, during training, the controller continuously reassesses the user's state using newly acquired sensor data. A fixed assessment cycle (e.g., every 5 minutes) is set, or it is event-triggered (e.g., completion of a training phase). At each assessment point, the controller compares the new round of eye movement data (e.g., tracking error), posture data (e.g., changes in postural stability), and physiological indicators (e.g., fatigue levels) with the data from the previous cycle and a preset progress threshold. If the analysis indicates that the user's performance in the current subject has stabilized and met the target, the controller updates the target training subject to the next more challenging subject according to a predetermined progression path. If the data shows signs of fatigue or discomfort, such as a significant increase in heart rate or loosening of posture, the controller adjusts the physical therapy parameters accordingly, such as increasing the duration of vibration relaxation or temporarily inserting a seat posture reset. All adjustments and updates are completed automatically and recorded in the user's personal training log.

[0118] For example, after 10 minutes of training, the controller analyzes new data and finds that the user's dynamic tracking error has continuously decreased from 15 pixels to 8 pixels and remained stable, reaching the advanced standard for the current subject. Simultaneously, posture data shows that the user's backward lean angle has increased, potentially indicating inertia. Based on this, the controller updates: switching the target training subject from "Dynamic Tracking Training (Basic)" to "Dynamic Tracking Training (Advanced)"; simultaneously, to correct posture, during the interval between subject switches, the controller performs a standard "upright posture reset" action, adjusting the backrest angle to 90 degrees.

[0119] In this way, by integrating multi-dimensional data such as uncorrected visual acuity, real-time eye movement, posture, and physiology, a fully personalized and automated process is achieved from initial assessment to plan generation and dynamic adjustment. This method not only makes the selection of training subjects more precise, but also achieves real-time intervention and relaxation adjustment of the user's physical and mental state by introducing chair-based physical therapy in synergy with the training process. This enhances the effectiveness of vision rehabilitation training while improving comfort and safety, forming an intelligent closed-loop management system that integrates assessment, training, treatment, and feedback.

[0120] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0121] Please see Figure 5 This illustration shows a schematic diagram of the structure of a collaborative control device for vision rehabilitation training provided in an exemplary embodiment of this application, hereinafter referred to as device 5. Device 5 can be implemented as all or part of a vision rehabilitation device through software, hardware, or a combination of both. Device 5 includes: The determination module 501 is used to determine the corresponding target training subject from a set of preset training subjects based on the user's vision test results; The query module 502 is used to query the first trajectory parameter set of the multi-degree-of-freedom seat, the second trajectory parameter set of the multi-degree-of-freedom training table, and the third trajectory parameter set of the visual stimulus object associated with the target training subject; The control module 503 is used to control the multi-degree-of-freedom seat to move based on the first trajectory parameter set, control the multi-degree-of-freedom training platform to move based on the second trajectory parameter set, and control the visual stimulus object to move on the display unit of the multi-degree-of-freedom training platform based on the third trajectory parameter set, so as to form a coordinated training exercise. The acquisition module 504 is used to acquire the user's performance index data for the visual stimulus object during the execution of the collaborative training exercise. Update module 505 is used to update the third trajectory parameter set based on the difference data between the performance index data and the target index data corresponding to the target training subject; and The driving module 506 is used to control the movement of the visual stimulus object on the display unit according to the updated third trajectory parameter set.

[0122] For further details regarding the implementation of the above-mentioned technical solutions by each module in the collaborative control device for vision rehabilitation training, please refer to the description in the collaborative control method for vision rehabilitation training provided in the above-mentioned embodiments of the invention, which will not be repeated here.

[0123] It should be noted that the above-described embodiment of the device 5, when executing the collaborative control method for vision rehabilitation training, is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the above functions. Furthermore, the collaborative control device for vision rehabilitation training and the collaborative control method embodiment for vision rehabilitation training provided in the above embodiment belong to the same concept, and their implementation process is detailed in the method embodiment, which will not be repeated here.

[0124] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0125] See Figure 6 The diagram shown is a schematic of a computer storage medium provided in an embodiment of this application. The computer storage medium can store multiple instructions (i.e., ... Figure 6 The computer program shown above), the instructions are adapted to be loaded and executed by a processor as described above. Figure 2 The method steps of the illustrated embodiment can be found in the following documentation for detailed execution. Figure 2 The specific details of the illustrated embodiments will not be elaborated here.

[0126] This application also provides a computer program product that stores at least one instruction, which is loaded and executed by the processor to implement the collaborative control method for vision rehabilitation training as described in the above embodiments.

[0127] Please see Figure 7 This document provides a schematic diagram of the hardware structure of a vision rehabilitation device according to an embodiment of this application. Figure 7 As shown, the vision rehabilitation device 700 may include: at least one processor 701, at least one network interface 704, a user interface 703, a memory 705, at least one communication bus 702, multiple vision training units, an illumination module, an audio output module, a visual processing module, and a human-computer interaction module. Figure 7 (Not shown in the drawing).

[0128] The communication bus 702 is used to enable communication between these components.

[0129] The user interface 703 may include input units such as a mouse and keyboard.

[0130] The network interface 704 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0131] The processor 701 may include one or more processing cores. The processor 701 connects to various parts within the vision rehabilitation device 700 using various interfaces and lines. It executes various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 705, and by calling data stored in the memory 705. Optionally, the processor 701 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 701 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the processor 701.

[0132] The memory 705 may include random access memory (RAM) or read-only memory. Optionally, the memory 705 may include a non-transitory computer-readable storage medium. The memory 705 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 705 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 705 may also be at least one storage device located remotely from the aforementioned processor 701. Figure 7As shown, the memory 705, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and application programs.

[0133] exist Figure 7 In the vision rehabilitation device 700 shown, the user interface 703 is mainly used to provide an input interface for the user and to acquire user input data; while the processor 701 can be used to call the application program stored in the memory 705 and specifically execute, such as... Figure 2 The method shown can be referred to for details. Figure 2 As shown, it will not be elaborated further here.

[0134] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0135] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A collaborative control method for vision rehabilitation training, characterized in that, The method includes: Based on the user's vision test results, the corresponding target training subject is determined from a set of preset training subjects; Query the first trajectory parameter set of the multi-degree-of-freedom seat, the second trajectory parameter set of the multi-degree-of-freedom training table, and the third trajectory parameter set of the visual stimulus object associated with the target training subject; The multi-degree-of-freedom seat is controlled to move based on the first set of trajectory parameters, the multi-degree-of-freedom training platform is controlled to move based on the second set of trajectory parameters, and the visual stimulus object is controlled to move on the display unit of the multi-degree-of-freedom training platform based on the third set of trajectory parameters, so as to form a coordinated training exercise. During the execution of the collaborative training exercise, the user's performance index data for the visual stimulus object is acquired; The third trajectory parameter set is updated based on the difference between the performance index data and the target index data corresponding to the target training subject; and The visual stimulus object is moved on the display unit according to the updated third trajectory parameter set.

2. The collaborative control method according to claim 1, characterized in that, Also includes: During the execution of the collaborative training exercise, the user's fatigue level is detected based on the user's physiological state data; When the fatigue level exceeds the fatigue threshold, the collaborative training exercise is paused, and the current posture data of the multi-degree-of-freedom seat is recorded. Control the multi-degree-of-freedom seat to switch to preset relaxation posture data; After a preset pause, the collaborative training motion is resumed based on the current posture data.

3. The cooperative control method according to claim 2, characterized in that, The method of detecting a user's fatigue level based on the user's physiological state data includes: Collect users’ physiological state data, which includes: eye state parameters, electrocardiogram signal parameters and electroencephalogram signal parameters; The eye state parameters, electrocardiogram signal parameters, and electroencephalogram signal parameters are normalized. The normalized parameters are calculated based on the preset weight model to obtain a comprehensive fatigue metric value. The user's fatigue level is determined based on the target value range to which the fatigue quantification value belongs among a preset number range.

4. The collaborative control method according to claim 1, characterized in that, The step of updating the third trajectory parameter set based on the difference data between the performance index data and the target index data corresponding to the target training subject includes: Obtain the tracking error and response delay from the performance index data; Obtain the target tracking error threshold corresponding to the target training subject; Obtain the reaction delay error threshold corresponding to the target training subject; If the tracking error is greater than the target tracking error threshold, then the motion speed of the visual stimulus is reduced based on the difference between the tracking error and the target tracking error threshold; and / or, If the reaction delay is greater than the target reaction delay threshold, the motion path complexity of the visual stimulus is reduced based on the difference between the reaction delay and the target reaction delay threshold.

5. The collaborative control method according to claim 1, characterized in that, The step of determining the corresponding target training subject from a set of preset training subjects based on the user's vision test results includes: Obtain the user's vision test results, which include: refractive parameters and corrected visual acuity values; The user's refractive error level is determined based on the refractive error parameters, and the user's visual impairment index is calculated based on the corrected visual acuity value. The refractive error type level and the visual impairment index are matched according to a preset mapping relationship; Based on the matching results, at least one target training subject is obtained.

6. The cooperative control method according to claim 1, characterized in that, Also includes: At the start and end of the collaborative training exercise, voice prompts are issued via the voice output module.

7. The cooperative control method according to claim 1, characterized in that, The step of determining the corresponding target training subject from a set of preset training subjects based on the user's vision test results includes: The system collects the user's initial naked-eye vision data, real-time eye movement data, body posture data, and at least one physiological indicator data through a naked-eye vision testing unit, an eye-tracking sensor integrated into the display unit, and a posture monitoring sensor and a physiological signal sensor set on the multi-degree-of-freedom seat. The controller integrates and analyzes the initial uncorrected visual acuity data, real-time eye movement data, body posture data, and physiological index data to generate a personalized combination scheme that includes the target training subject and the physical therapy parameters of the multi-degree-of-freedom seat; wherein, the physical therapy parameters are used to control the multi-degree-of-freedom seat to perform at least one auxiliary therapeutic action, including vibration, heating, or posture maintenance. The method further includes: The target training subjects and / or physical therapy parameters in the personalized combination scheme are periodically adjusted and updated based on newly collected user eye movement data, body posture data, and physiological index data during the collaborative training exercise.

8. A collaborative control device for vision rehabilitation training, characterized in that, include: The determination module is used to determine the corresponding target training subject from a set of preset training subjects based on the user's vision test results; The query module is used to query the first trajectory parameter set of the multi-degree-of-freedom seat, the second trajectory parameter set of the multi-degree-of-freedom training table, and the third trajectory parameter set of the visual stimulus object associated with the target training subject; The control module is used to control the multi-degree-of-freedom seat to move based on the first trajectory parameter set, control the multi-degree-of-freedom training platform to move based on the second trajectory parameter set, and control the visual stimulus object to move on the display unit of the multi-degree-of-freedom training platform based on the third trajectory parameter set, so as to form a coordinated training exercise. The acquisition module is used to acquire the user's performance index data for the visual stimulus object during the execution of the collaborative training exercise. The update module is used to update the third trajectory parameter set based on the difference data between the performance index data and the target index data corresponding to the target training subject; as well as A driving module is used to control the movement of the visual stimulus object on the display unit according to the updated third trajectory parameter set.

9. A computer storage medium, characterized in that, The computer storage medium stores multiple instructions adapted for loading by a processor and executing the steps of the collaborative control method for vision rehabilitation training as described in any one of claims 1 to 7.

10. A vision rehabilitation device, characterized in that, include: Processor, memory, multi-DOF seat and multi-DOF training table; The processor is electrically connected to the memory, the multi-degree-of-freedom seat, and the multi-degree-of-freedom training, respectively. The memory stores a computer program adapted to be loaded by the processor and executed by the steps of the collaborative control method for vision rehabilitation training as claimed in any one of claims 1 to 7.

Images