Dynamic visual function training method and device based on VR, medium, program product and terminal

Abstract

The invention provides a VR-based dynamic visual function training method and device, a medium, a program product and a terminal. An initial training task type and configuration parameters are generated according to a visual evaluation result of a patient, a sighting mark and a stimulation signal for visual function training are constructed, and training is executed through a VR unit. In the training process, feedback data of a patient is collected in real time, a real-time evaluation result is analyzed and generated, task types, configuration parameters and sighting marks are dynamically adjusted, and new stimulation signals are generated to continue training, so that dynamic optimization of training content is achieved. Through real-time evaluation and dynamic adjustment, the problem that the training content is not matched with the requirements of the patient is solved, the defects of a traditional method in the aspects of individuation and adaptability are overcome, the training effect is remarkably improved, the requirements of the patient are better met, the training time is shortened, and the efficiency is improved. The device is especially suitable for rehabilitation training of various visual function defects, and has remarkable advantages in the aspect of dynamic visual function recovery.

Description

Technical Field

[0001] This application relates to the field of electronic data processing, and in particular, to a method, device, medium, program product, and terminal for dynamic visual function training based on VR. Background Art

[0002] In the field of visual function training, existing technologies mainly rely on standardized training tasks and fixed training programs. These technologies usually present visual stimuli through a computer screen or a dedicated device, and require patients to complete a series of preset tasks, such as identifying specific visual targets or completing contrast discrimination tasks. However, this standardized method has obvious limitations.

[0003] Firstly, due to the significant differences in the visual conditions and attention levels of patients, fixed training programs are difficult to adapt to individual needs, resulting in uneven training effects. Secondly, existing technologies lack real-time monitoring and evaluation of patients' compliance during the training process, and cannot dynamically adjust the training difficulty or provide personalized feedback, which further limits the effectiveness of training and patients' participation. In addition, existing visual training technologies usually adopt a single visual stimulus mode, making it difficult to simulate complex real-world scenarios, resulting in a gap between the training effect and the actual life needs. For example, traditional training tasks are often limited to static or simple dynamic visual targets, unable to provide an immersive training environment, thus making it difficult to effectively improve patients' comprehensive visual abilities. At the same time, existing technologies lack the ability to collect and analyze patients' physiological data in real time, unable to comprehensively evaluate the changes in visual function during the training process, and restricting the optimization and personalized adjustment of training programs. Summary of the Invention

[0004] In view of the above-mentioned disadvantages of the existing technologies, the purpose of this application is to provide a method, device, medium, program product, and terminal for dynamic visual function training based on VR, which is used to solve the problems that the existing technologies have significant deficiencies in the personalization of training tasks, real-time feedback mechanisms, and immersive training environments, and are difficult to meet the diverse visual function training needs of patients. These defects directly affect the training effect and patients' long-term compliance.

[0005] To achieve the above and other related objectives, the first aspect of the present application provides a VR-based dynamic visual function training method, including: obtaining the visual assessment results of a patient, and generating an initial training task type based on the visual assessment results; generating corresponding initial training configuration parameters according to the training task type, and generating visual function training visual targets based on the initial training configuration parameters; generating a stimulation signal based on the visual function training visual targets, and sending the stimulation signal to a VR unit to perform visual function training; during the visual function training process, collecting the patient's visual feedback data in real time; analyzing the visual feedback data to generate a real-time assessment result; according to the real-time assessment result, updating the training task type and the corresponding training configuration parameters; based on the updated training configuration parameters, updating the visual function training visual targets, and generating a new stimulation signal according to the updated visual function training visual targets, and continuing to perform visual function training.

[0006] In some embodiments of the first aspect of the present application, the method includes: calculating a dependency parameter between each preset training task type and the visual assessment result and / or the real-time assessment result.

[0007] In some embodiments of the first aspect of the present application, the process of generating an initial training task type based on the visual assessment result includes: calculating a dependency parameter between each preset training task type and the visual assessment result; extracting the task type with the highest dependency parameter as the initial training task type.

[0008] In some embodiments of the first aspect of the present application, the process of updating the training task type and the corresponding training configuration parameters according to the real-time assessment result includes: calculating a dependency parameter between each preset training task type and the real-time assessment result; extracting the task type with the highest dependency parameter as the updated task type; calculating and updating the training configuration parameters according to the updated task type and the dependency parameter.

[0009] In some embodiments of the first aspect of the present application, the process of updating the visual function training visual targets based on the updated training configuration parameters includes one or more of the following: updating the visual target size, visual target contrast, visual target color combination, visual target shape combination, visual target movement trajectory, and visual target movement speed of the visual function training visual targets.

[0010] In some embodiments of the first aspect of the present application, the training task type includes one or more of the following: static visual target recognition training, contrast training, target localization training, dynamic target tracking training, interference background target recognition, depth perception training, blind area recovery training, adaptive dynamic training, and contour shape detection training.

[0011] To achieve the above and other related objectives, the second aspect of the present application provides a VR-based dynamic visual function training device, including: an initialization module: used to obtain the visual assessment result of the patient and generate an initial training task type based on the visual assessment result; a training configuration module: used to generate corresponding initial training configuration parameters according to the training task type and generate a visual function training target based on the initial training configuration parameters; a stimulation signal generation module: used to generate a stimulation signal based on the visual function training target, send the stimulation signal to the VR unit to perform visual function training; a real-time feedback module: used to collect the visual feedback data of the patient in real time during the visual function training process; analyze the visual feedback data to generate a real-time assessment result; according to the real-time assessment result, adjust the training task type and the corresponding training configuration parameters; based on the adjusted training configuration parameters, update the visual function training target and generate a new stimulation signal according to the updated visual function training target, and continue to perform visual function training; a VR unit: used to perform corresponding visual function training according to the stimulation signal.

[0012] To achieve the above and other related objectives, the third aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the VR-based dynamic visual function training method is implemented.

[0013] To achieve the above and other related objectives, the fourth aspect of the present application provides a computer program product, which includes computer program code, and when the computer program code runs on a computer, the computer is enabled to implement the VR-based dynamic visual function training method.

[0014] To achieve the above and other related objectives, the fifth aspect of the present application provides an electronic terminal, including a memory, a processor, and a computer program stored on the memory; the processor executes the computer program to implement the VR-based dynamic visual function training method.

[0015] As described above, the VR-based dynamic visual function training method, device, medium, program product, and terminal of the present application have the following beneficial effects: By collecting the visual feedback data of patients in real time and generating real-time evaluation results, the training task type and configuration parameters are dynamically adjusted to ensure that the training content always matches the visual ability level of the patients, thereby significantly improving the training effect. Based on the visual evaluation results and real-time evaluation results, an initial training task type is generated, and the task selection and configuration are optimized by calculating the dependency parameters to provide a personalized training plan. By updating parameters such as the size, contrast, color combination, shape combination, motion trajectory, and speed of the visual function training visual targets, the training content is enriched, and the diversity and adaptability of the training are improved. Multiple training task types (such as static visual target recognition, dynamic target tracking, depth perception training, etc.) are provided to meet the rehabilitation needs of different visual function impairments. Combining VR technology, a stimulation signal is generated and visual function training is executed to provide an immersive training environment, enhancing the realism and accuracy of the training. Through real-time feedback and dynamic adjustment, a closed-loop optimization system is formed to ensure the efficiency and scientific nature of the training process. This solution significantly improves the effect of visual function training and the user experience, and has broad application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Shows a schematic flowchart of an embodiment of the VR-based dynamic visual function training method of the present application.

[0017] Figure 2 Shows a schematic structural diagram of an embodiment of the VR-based dynamic visual function training device of the present application.

[0018] Figure 3 Shows a schematic structural diagram of an embodiment of the VR-based dynamic visual function training terminal of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The following specific examples illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0020] Before further elaborating on the present invention, the nouns and terms involved in the embodiments of the present invention are described. The nouns and terms involved in the embodiments of the present invention are applicable to the following explanations:

[0021] <1>VR (Virtual Reality): A three-dimensional environment simulated and generated by computer technology, allowing users to interact with this virtual environment through specific devices.

[0022] <2>Dynamic visual function training: Through specially designed activities, it enhances an individual's visual processing ability in a dynamic environment, including aspects such as reaction speed, object tracking, and spatial perception.

[0023] <3>Visual assessment results: Refer to the comprehensive determination of a patient's visual ability, including the assessment results of indicators such as visual acuity, visual field range, and contrast sensitivity, which are used for the generation of personalized training tasks.

[0024] <4>Dependency parameter: Used to quantify the correlation between a specific training task type and the visual ability assessment results of a patient, calculated through statistical methods to confirm the most suitable training task.

[0025] <5>Stimulus signal: An electronic signal used to control the display of visual content on VR or display devices, carrying the specific visual stimulus information required in visual training.

[0026] <6>Gabor visual target: A stimulus pattern used in visual research, usually composed of a Gaussian function modulated by a sine wave, forming a specific texture pattern. It is widely used in psychology and vision science to study the human visual system's perception ability of spatial frequency, orientation, and contrast. Gabor visual targets help researchers analyze related mechanisms such as visual recognition, edge detection, and image processing.

[0027] <7>Multimodal feedback mechanism: A system that combines different types of data sources (such as eye movement tracking and task performance data) for evaluation, used to enhance the real-time feedback and adjustment ability of training.

[0028] <8>Eye movement tracking technology: A technology that monitors visual attention and preferences by recording and analyzing eye movements, usually using an infrared camera to obtain high-precision eye movement data.

[0029] <9>Dynamic adjustment curve: A strategy for gradually adjusting the difficulty or type of training tasks based on real-time assessment results to ensure that the training process always adapts to the changes in the patient's visual ability.

[0030] <10>Humphrey perimeter: A device used to measure the visual field of the eye, which evaluates visual function and diagnoses visual field defects by testing a patient's ability to perceive light points in different directions and at different brightness levels. This device is widely used in ophthalmology and optometry, especially in the examination of glaucoma and other optic nerve diseases.

[0031] <11>Pelli-Robson contrast sensitivity test: A test method used to evaluate the contrast sensitivity of the visual system. It shows a series of letters or patterns with different contrasts and asks the subjects to identify the characters to determine their visual ability at different contrasts. This test is commonly used in clinics to evaluate the sensitivity of visual acuity and visual function, especially when studying visual-related diseases or conditions.

[0032] To facilitate the understanding of the embodiments of this application, first, in combination with Figure 1 it is described in detail. Figure 1 The flowchart of a VR-based dynamic visual function training method in an embodiment of the present invention is shown. The VR-based dynamic visual function training method in this embodiment mainly includes the following steps:

[0033] Step S11: Obtain the visual assessment result of the patient, generate an initial training task type based on the visual assessment result; generate corresponding initial training configuration parameters according to the training task type, and generate visual function training visual targets based on the initial training configuration parameters.

[0034] In an embodiment of the present application, visual ability data of the patient is obtained, including key indicators such as visual acuity, visual field range, and contrast sensitivity. Among them, visual acuity is collected through a Snellen visual acuity chart. This test quantifies the patient's distance and near visual acuity levels by asking the patient to identify letters or symbols of different sizes; the visual field range is collected through a Humphrey visual field analyzer, and through static or dynamic visual field test methods, the visual field boundary of the patient is detected and the visual field defect area is identified; contrast sensitivity is collected through a Pelli-Robson contrast sensitivity test chart. By asking the patient to identify letters or patterns with different contrasts, the patient's visual discrimination ability in a low-contrast environment is evaluated; eye movement behavior data is collected through eye tracking technology. Specifically, by using an infrared camera to record physiological indicators such as the patient's eye movement trajectory, fixation point distribution, and pupil diameter change, dynamic data support is provided for visual assessment.

[0035] In an embodiment of the present application, visual ability data of a patient is collected through standardized tests (such as Humphrey visual field analyzer and Pelli-Robson contrast sensitivity test chart, etc.), including key indicators such as visual acuity, visual field range, and contrast sensitivity. Combining physiological indicators such as the fixation point distribution and pupil diameter changes recorded by the eye tracking technology (Eye Tracking Technology), a comprehensive visual assessment result is formed. Based on the assessment result, the type and severity of the patient's visual defects are analyzed through a preset algorithm, and the initial training task type is automatically generated. For example, if the patient has a visual field defect, the Gabor stimulus detection task is preferentially selected; if the contrast sensitivity is low, a contrast discrimination task is generated. Subsequently, initial training configuration parameters are generated according to the task type, including the size, color, contrast, spatial frequency, etc. of the stimulus. These parameters are dynamically adjusted based on the patient's visual ability to ensure the suitability and effectiveness of the training task. Finally, visual function training stimuli (such as Gabor stimuli, compound gratings, or motion direction images) are generated according to the configuration parameters and presented to the patient through a high-resolution display screen or a VR device.

[0036] In this embodiment, through data-driven intelligent design, the personalization and precision of the visual rehabilitation training plan are realized. First, the combination of standardized tests and eye tracking technology provides multi-dimensional visual ability data, laying a scientific foundation for subsequent analysis. The preset algorithm can accurately identify the type and severity of the patient's visual defects by analyzing these data and automatically generate targeted training task types. For example, the Gabor stimulus detection task is for visual field defects, while the contrast discrimination task is for patients with insufficient contrast sensitivity. In addition, the algorithm dynamically adjusts the training configuration parameters (such as stimulus size, color, contrast, etc.) according to the patient's visual ability to ensure that the training task is both challenging and within the patient's tolerance. Finally, presenting the training stimuli through a high-resolution display screen or a VR device further enhances the immersion and effect of the training. This process not only improves the scientificity and efficiency of visual rehabilitation but also provides personalized rehabilitation support for patients.

[0037] In an embodiment of the present application, the method includes: for each preset training task type, calculating the dependency parameter between it and the visual assessment result and / or the real-time assessment result.

[0038] In an embodiment of the present application, the process of generating the initial training task type based on the visual assessment result includes: for each preset training task type, calculating the dependency parameter between it and the visual assessment result; extracting the task type with the highest dependency parameter as the initial training task type.

[0039] In this embodiment, the dependency parameter is used to quantify the correlation between the training task type and the patient's visual ability, ensuring the scientificity and pertinence of the training task. Specifically, the calculation of the dependency parameter includes, but is not limited to: based on the static indicators in the visual assessment results (such as visual acuity, visual field range, contrast sensitivity, etc.), calculating the correlation between the training task type and these indicators through the Pearson correlation coefficient; and / or based on the dynamic data in the real-time assessment results (such as eye movement trajectory, reaction time, correct rate, etc.), calculating the association between the training task type and the dynamic data through mutual information.

[0040] Further, the two calculation methods respectively generate corresponding dependency parameters, and finally obtain the comprehensive dependency parameter through weighted summation. Among them, the calculation process of the dependency parameter is shown in Formula 1, where α is the weight coefficient of the static indicator, and the value range is from 0 to 1, which is used to balance the influence of static and dynamic indicators. By setting the value of the weight α, the contribution ratio of static and dynamic indicators can be flexibly adjusted.

[0041] Exemplarily, when α = 1, the comprehensive dependency parameter is calculated only based on the static dependency parameter, completely ignoring the influence of dynamic indicators; when α = 0, the comprehensive dependency parameter is calculated only based on the dynamic dependency parameter, completely ignoring the influence of static indicators; when 0 < α < 1, the comprehensive dependency parameter is the weighted sum of static and dynamic dependency parameters, achieving a balanced consideration of both. This design enables the system to flexibly select a single parameter or a comprehensive parameter for calculation according to actual needs or data availability, enhancing the adaptability and practicality of the method.

[0042] Dependency parameter = α × Static dependency parameter + (1 - α) × Dynamic dependency parameter (Formula 1)

[0043] Among them, the static dependency parameter represents the correlation between the training task type and the static visual indicators (visual assessment results), and the dynamic dependency parameter (implementation assessment results) represents the association between the training task type and the dynamic behavior data. The static dependency parameter is shown in Formula 2. X i represents the value of the i-th static visual indicator (such as visual acuity, visual field range, etc.), X represents the mean value of the static visual indicators, Y i represents the performance value of the i-th training task type (such as task completion rate, reaction time, etc.), Y represents the mean value of the training task type performance, and n represents the number of static visual indicators. The Pearson correlation coefficient is used to measure the linear correlation between X and Y, and the value range is from -1 to 1. The closer the value is to 1, the stronger the correlation.

[0044]

[0045] The dynamic dependency parameter is shown in Equation 3. X represents a set of dynamic behavior data (such as eye movement trajectories, reaction times, etc.), Y represents a set of training task types, p(x,y) represents the joint probability distribution of X and Y, and p(x) and p(y) represent the marginal probability distributions of X and Y respectively. Mutual information is used to measure the statistical independence between X and Y, and the larger the value, the stronger the correlation between the two.

[0046]

[0047] After the calculation is completed, the task type with the highest comprehensive dependency parameter is extracted as the initial training task type. Exemplarily, if the comprehensive dependency parameter of the Gabor visual target detection task is the highest, then this task is preferentially selected as the initial training task type. This process ensures a high degree of matching between the training task and the patient's visual ability through data-driven intelligent design.

[0048] In an embodiment of the present application, the training task types include, according to difficulty and complexity: low-level tasks, intermediate tasks, and high-level tasks. Low-level tasks are usually designed as simple basic training, suitable for patients with relatively weak visual abilities, such as basic visual stimulus recognition tasks, aiming to help patients recover basic visual perception abilities. Intermediate tasks increase complexity on the basis of low-level tasks, such as introducing multi-dimensional visual stimuli or dynamically changing tasks, suitable for patients with a certain degree of visual ability recovery, aiming to further improve their visual functions. High-level tasks are designed as complex comprehensive training, such as multi-task combinations or high-difficulty visual discrimination tasks, suitable for patients with visual abilities close to normal or in need of further strengthening, aiming to optimize their visual performance and adaptability.

[0049] It should be noted that in this embodiment, through the calculation of the dependency parameter, not only can the correlation between the task type and the patient's visual ability be evaluated, but also the appropriate task difficulty can be automatically matched according to the patient's current visual level. For example, for patients with relatively weak visual abilities, low-level tasks may be preferentially selected as the initial training tasks; while for patients with stronger visual abilities, intermediate or high-level tasks may be selected. This hierarchical task design combined with a data-driven decision-making mechanism ensures the scientific nature and personalization of the training tasks, providing comprehensive support for the visual rehabilitation of patients.

[0050] In an embodiment of the present application, the training task types include one or more of the following: static visual target recognition training, contrast training, target localization training, dynamic target tracking training, interference background target recognition, depth perception training, blind area recovery training, adaptive dynamic training, contour shape detection training.

[0051] In this embodiment, a variety of different training task types are designed according to the different visual defects and rehabilitation needs of patients. Specifically, static visual target recognition training requires patients to recognize static visual stimuli (such as dots, lines, graphics, etc.) to improve basic visual perception ability and is suitable for patients with relatively poor eyesight or those whose visual function is just recovering. By recognizing simple static visual targets, patients can gradually recover their perception ability of basic visual information; contrast training requires patients to recognize targets against backgrounds with different contrasts to enhance contrast sensitivity and is suitable for patients with visual function impairment caused by decreased contrast sensitivity. It helps patients distinguish targets more clearly in low-contrast environments; target localization training requires patients to quickly locate targets within a specific area to improve spatial attention and visual search ability and is suitable for patients with visual field defects or scattered attention. By quickly locating targets, patients can improve their visual search efficiency and spatial perception ability; dynamic target tracking training requires patients to track moving targets to enhance dynamic visual function and eye movement coordination ability and is suitable for patients with insufficient dynamic visual ability. It helps improve patients' ability to capture and track moving targets; recognition of targets in a distracting background requires patients to recognize targets in a complex or distracting background to enhance visual discrimination ability and anti-interference ability and is suitable for patients with relatively weak visual information processing ability. It helps patients extract target information more effectively in complex environments; depth perception training requires patients to judge the depth or distance of targets to improve stereoscopic vision and spatial perception ability and is suitable for patients with insufficient depth perception ability. By judging the depth of targets, patients can better understand three-dimensional spatial relationships; blind spot recovery training requires patients to restore the function of the blind spot through specific visual stimuli to improve visual field defects or blind spot problems and is suitable for patients with visual function limitations caused by visual field defects. It aims to activate the visual perception ability within the blind spot; adaptive dynamic training requires patients to adjust their responses according to dynamically changing visual stimuli to enhance visual adaptation ability and dynamic response ability and is suitable for patients who need to improve dynamic visual adaptability. It helps patients better cope with rapidly changing visual environments; contour and shape detection training requires patients to recognize and distinguish the contours and shapes of targets to enhance shape perception ability and visual discrimination ability and is suitable for patients with insufficient shape perception ability. By recognizing different contours and shapes, patients can enhance their ability to process complex visual information.

[0052] Further, the training task module is divided into low-level training tasks, intermediate training tasks, and high-level training tasks according to difficulty and complexity. Low-level training tasks include Gabor visual target detection, contrast discrimination (color contrast), orientation discrimination, noise environment discrimination, spatial frequency discrimination, phase shift discrimination, and hyperacuity visual discrimination, etc., to help patients improve their basic visual abilities. Intermediate training tasks such as Gabor composite grating discrimination, texture discrimination, depth discrimination, motion direction discrimination, etc., add interference factors to further exercise the patient's visual discrimination ability and attention. High-level training tasks combine real-world scenarios, including contour discrimination, object discrimination, shelf item retrieval, etc., aiming to improve the patient's visual recognition and processing abilities in complex environments.

[0053] In an embodiment of the present application, the process of generating visual function training visual targets based on the initial training configuration parameters includes: extracting the visual function evaluation results of the patient to obtain the initial training configuration parameters, which include various types of data such as the patient's visual field defect area, visual sensitivity threshold, contrast requirement, and spatial frequency adaptability. Based on the initial training configuration parameters, determine the basic attributes of the visual target, such as the shape, size, color, contrast, spatial frequency, and motion characteristics of the visual target, to ensure that the visual target can adapt to the individual needs of the patient and effectively stimulate visual perception during training. Finally, using the visual target generation algorithm, dynamically adjust the presentation method of the visual target according to the patient's visual function status to ensure that the brightness and recognition of the visual target are optimized in different environments (such as low contrast or complex background).

[0054] Step S12: Generate a stimulation signal based on the visual function training visual target, and send the stimulation signal to the VR unit to perform visual function training; during the visual function training process, collect the patient's visual feedback data in real time.

[0055] In an embodiment of the present application, in generating a stimulation signal based on the visual function training visual target, the stimulation signal is an electronic signal used to control the visual content presented on a display device (such as a VR headset or a monitor). The electronic signal includes but is not limited to the display time, size, color, contrast, and other visual parameters of the visual target, ensuring that the visual stimulation during the training process matches the patient's needs.

[0056] In an embodiment of the present application, the VR unit refers to a virtual reality device used to present three-dimensional images and environments, allowing users to immerse themselves in an interactive virtual world. The stimulation signal generated in this embodiment is transmitted to the VR unit, enabling it to adjust the visual output according to the electronic signal. The VR unit communicates with the computer device for performing the VR-based dynamic visual function training method through a data transmission protocol, which includes but is not limited to Bluetooth, Wi-Fi, or wired connection, etc., to ensure fast and efficient signal transmission.

[0057] In one embodiment of the present application, to perform visual function training, the visual content represented by the stimulation signal is displayed through the VR unit. During visual function training, the patient needs to complete a series of visual tasks, including but not limited to: recognition, discrimination, tracking, etc. of visual targets, to help the patient improve their visual ability.

[0058] In one embodiment of the present application, visual feedback data of the patient is collected in real time through the visual assessment and eye movement tracking module. The visual feedback data includes but is not limited to: fixation duration, pupil diameter change, eye movement trajectory offset, reaction time, and accuracy rate. The fixation duration refers to the attention time of the patient on a specific visual target, reflecting visual attention and task completion efficiency. The pupil diameter change refers to evaluating the relationship between the visual stimulation intensity and the patient's perceptual sensitivity by recording the pupil reaction. The eye movement trajectory offset refers to calculating the offset between the actual fixation point of the patient and the target stimulation point, which is used to judge the effect of visual training. The reaction time and accuracy rate refer to recording the reaction speed and accuracy of the user in the training task to determine the performance level of the patient in completing the task.

[0059] Step S13: Analyze the visual feedback data to generate a real-time evaluation result; according to the real-time evaluation result, update the training task type and the corresponding training configuration parameters; based on the updated training configuration parameters, update the visual function training visual targets, and generate a new stimulation signal according to the updated visual function training visual targets, and continue to perform visual function training.

[0060] In one embodiment of the present application, the process of analyzing the visual feedback data to generate a real-time evaluation result includes: integrating eye movement tracking data (such as fixation duration, pupil diameter change, eye movement trajectory offset) and task performance data (such as reaction time, accuracy rate, task completion rate) through a multi-modal feedback mechanism and data modeling technology, and combining mathematical modeling methods (such as Weibull psychometric function or machine learning algorithms) to generate a multi-dimensional real-time evaluation result. The evaluation result includes performance indicators (task completion rate, accuracy rate, reaction time, etc.), training difficulty level (dynamic adjustment curve), and visual function improvement trend (time series analysis). Through the above analysis, the training effect is monitored in real time, the parameters are adjusted dynamically, and the pertinence and effectiveness of the training are maximized.

[0061] In an embodiment of the present application, the process of updating the training task type includes: updating the training task type based on the training accuracy rate. Specifically, if the evaluation result shows that the patient has mastered the current task proficiently (such as the accuracy rate reaches 75% or higher, and at the same time the reaction time continues to decrease), the type of the training task is automatically upgraded. For example, it transitions from a low-level training task (such as Gabor visual target detection, contrast discrimination, etc.) to a medium-level task (such as texture discrimination, depth discrimination, complex grating discrimination, etc.), or is upgraded from a medium-level task to a high-level task (such as contour discrimination, shelf picking, etc.). This process is completed through dynamic parameter adjustment. If the evaluation data indicates that the current task is too difficult (such as the accuracy rate is lower than 50% or there is a long-term stagnation), the task difficulty will be reduced or switched to a more basic training task to help the patient adapt gradually.

[0062] In an embodiment of the present application, the process of updating the training configuration parameters includes the following steps: adjusting the training configuration parameters according to the patient's performance monitored in real time to achieve personalized training stimuli. The training configuration parameters include but are not limited to visual target contrast, spatial frequency, color mode, and noise complexity.

[0063] In an embodiment of the present application, the process of updating the training task type and the corresponding training configuration parameters according to the real-time evaluation result includes: calculating the dependence parameter between each preset training task type and the real-time evaluation result; extracting the task type with the highest dependence parameter as the updated task type; calculating and updating the training configuration parameters according to the updated task type and the dependence parameter.

[0064] In an embodiment of the present application, the process of updating the visual function training visual target based on the updated training configuration parameters includes one or more of the following: updating the visual target size, visual target contrast, visual target color combination, visual target shape combination, visual target movement trajectory, and visual target movement speed of the visual function training visual target.

[0065] In an embodiment of the present application, by obtaining the patient's eye movement tracking data in real time (including fixation dwell time and pupil diameter change), and combining the spatial frequency and contrast coupling algorithm, Gabor visual targets with multiple parameters are dynamically generated. The parameters include contrast, color, direction, spatial frequency, phase, and noise, etc.

[0066] Exemplarily, first, the range of the contrast is set between 0.001 and 1 using formula 4 to quantify the strength of the brightness difference in the visual stimulus. The color parameters use two colors, red (#FF0000) and green (#00FF00), and the directions select four directions of 0°, 45°, 90°, and 135° to cover visual stimuli at different angles.

[0067]

[0068] Secondly, set the range of spatial frequency to 1 to 36 Cycles Per Degree (cpd), and calculate the corresponding spatial frequency through Formula 5. F is the spatial frequency, and λ represents the optical wavelength. The phase value range of the light wave is from 0 to 4, representing the initial phase shift of the visual stimulus. Among them, cpd is the unit used to describe the spatial frequency, indicating that in the visual stimulus, the number of grating cycles contained within each degree of visual angle. 1 cpd means there is 1 cycle (i.e., 1 pair of black and white stripes) within each degree of visual angle. 10 cpd means there are 10 cycles within each degree of visual angle, meaning the stripes are finer and the details are richer. 36 cpd is a very high spatial frequency, indicating that the stripes are extremely fine, approaching the limit of the human eye's resolution ability.

[0069]

[0070] Finally, preset the noise to be generated based on 2×2 pixels, with the noise contrast range from 0.4 to 1, and generate standard Gaussian distribution random numbers through the Box-Muller transform and convert them to the required range. Thus, it can be dynamically adjusted according to the patient's real-time performance to ensure the suitability and effectiveness of the training task.

[0071] Introduce the preset noise in the current visual training task to simulate the complex background in the real environment. The preset noise is generated based on small squares of 2×2 pixels. Each small square represents a noise unit, and its contrast range is set from 0.4 to 1, indicating that the intensity of the brightness change of the noise is within this range. As shown in Formula 6, generate the corresponding noise random numbers through the Box-Muller transform. This method can convert two uniformly distributed random numbers (range between 0 and 1) into random numbers that conform to the standard Gaussian distribution (normal distribution). Among them, U1 and U2 are uniformly distributed random numbers between (0, 1), and Z0 and Z1 are standard normal distribution random numbers.

[0072]

[0073] Convert the random numbers generated in Formula 6 into a normal distribution with a specified mean and standard deviation through Formula 7, so as to ensure that the intensity and distribution of the noise meet the training requirements. In particular, the intensity and distribution of the noise can be dynamically adjusted according to the patient's real-time performance. Exemplarily, if the patient performs well, the contrast or complexity of the noise can be increased to improve the training difficulty; if the patient performs poorly, the contrast or complexity of the noise can be reduced to make the task easier to complete.

[0074] X = Z·σ + μ (Formula 7)

[0075] In an embodiment of the present application, the visual function training visual targets include multiple types, aiming to improve the neural plasticity stimulation efficiency, activate the nerve cells of the visual system, and promote visual information processing and transmission through diverse visual stimulus designs combined with a dynamic adaptive mechanism.

[0076] In this embodiment, when the visual function training visual target is a hyper-acute vision target, the visual target is constructed based on a double-line structure with orthogonal arrangement. Among them, the baseline length is 8 - 12 arc minutes, the line width is 2 - 3 arc minutes, the brightness contrast ≥ 90%, and the offset gradient is 0.5 - 5 arc seconds. This visual target design enables the trainer to distinguish a small displacement of 1 - 4 arc seconds. The training adaptively adjusts the offset using the random staircase method (QUEST algorithm) and conducts task interaction based on the two-alternative forced-choice paradigm (2AFC). The data is fitted with a Weibull psychometric function, and the offset corresponding to 75% correct rate is calculated as the threshold to ensure the scientificity and effectiveness of the training effect.

[0077] Furthermore, for the complex grating generation task, a complex grating pattern is generated by superimposing two sine wave gratings with different frequencies and orthogonal directions. The grating included angle is set to 90° ± 0.5°, and the frequency difference Δf gradient is 0.1 to 2.0 cpd. During the training, the observer determines whether two groups of grating patterns are the same, thereby enhancing the complexity of the visual stimulus and improving the observer's visual discrimination ability.

[0078] In this embodiment, in the texture image generation task, the target array consists of peripheral targets and background textures, and the background texture direction is different from the target texture. The masking array is a 19×19 randomly oriented "v"-shaped array. During the training process, the observer is made to fixate on the target array and determine the direction of the peripheral targets. The discrimination threshold is estimated by fitting the measurement data with a Weibull psychophysical function to quantify the observer's performance, thereby optimizing the training difficulty and effect. The Weibull psychophysical function is as shown in Equation 8.

[0079]

[0080] Among them, P(t) is the correct response probability, t is the stimulus interval time (in milliseconds), T is the discrimination threshold (i.e., the stimulus interval time corresponding to 75% correct rate), β is the slope of the psychophysical function, and f e is the finger error parameter (indicating the possibility of random errors, with a value range of 0 to 1). The discrimination threshold T is obtained by fitting the data to quantify the observer's performance, thereby optimizing the training difficulty and effect.

[0081] Depth image generation is based on the binocular parallax characteristics of VR devices, and a stereo image pair with a small horizontal displacement is generated through a split screen display of the left and right eyes. The horizontal displacement of the core area is dynamically adjusted according to the user's viewing distance (ranging from 0.1° to 2.0° viewing angle). The interference area uses a randomized filling algorithm to generate a pattern consistent with the background to avoid introducing additional depth clues. During the training process, the displacement amount and interference intensity are dynamically adjusted according to the user's performance to gradually improve the user's depth perception ability.

[0082] In the motion direction image generation task, the interface presents moving random points, where the signal points move at a constant speed in a fixed direction and the noise points move in random directions. The initial signal point to noise point ratio is 7:3, and the randomness of the noise point motion direction is achieved through a full random mode or a constrained random mode. During training, the noise ratio, motion speed, and direction difference are dynamically adjusted according to the user's recognition performance to improve the user's ability to recognize the motion direction.

[0083] Finally, in the contour shape detection task, Gabor sight marks were arranged in a 15×15 grid, and the target area contained Gabor subarrays with consistent directions, forming a closed geometric contour. The directions of Gabor sight marks in the interference stimulus were completely random, and there was no closed contour. The time series was divided into a fixation phase, a blank interval, a stimulus presentation, and a response phase. The time parameters were dynamically adjusted according to the user's performance to optimize the user's contour shape recognition ability.

[0084] In summary, this embodiment not only improves the efficiency of neuroplasticity stimulation, but also activates the nerve cells of the visual system and promotes the processing and transmission of visual information through diversified visual stimulation design combined with a dynamic adaptive mechanism.

[0085] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0086] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects and indicates that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (item)" or similar expressions thereof refer to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0087] Figure 2 is a schematic block diagram of a VR-based dynamic visual function training device 200 provided by an embodiment of the present application. As Figure 2 shown, the device includes an initialization module 201, a training configuration module 202, a stimulation signal generation module 203, a real-time feedback module 204, and a VR unit 205.

[0088] Initialization module 201: It is used to obtain the visual assessment result of the patient and generate an initial training task type based on the visual assessment result.

[0089] Training configuration module 202: It is used to generate corresponding initial training configuration parameters according to the training task type and generate visual function training targets based on the initial training configuration parameters.

[0090] Stimulation signal generation module 203: It is used to generate a stimulation signal based on the visual function training target and send the stimulation signal to the VR unit to perform visual function training.

[0091] Real-time feedback module 204: It is used to collect the visual feedback data of the patient in real time during the visual function training process; analyze the visual feedback data to generate a real-time assessment result; adjust the training task type and corresponding training configuration parameters according to the real-time assessment result; update the visual function training target based on the adjusted training configuration parameters, and generate a new stimulation signal according to the updated visual function training target to continue performing visual function training.

[0092] VR unit 205: It is used to perform corresponding visual function training according to the stimulation signal.

[0093] It should be understood that the specific processes of each module executing the above corresponding steps have been described in detail in the above method embodiments. For the sake of brevity, they will not be repeated here.

[0094] It should also be understood that the division of modules in the embodiments of the present application is illustrative, merely a logical function division, and there may be other division methods in actual implementation. In addition, in each embodiment of the present application, each functional module may be integrated in a processor, may exist separately physically, or two or more modules may be integrated in one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0095] Figure 3 is a schematic block diagram of an electronic terminal provided by an embodiment of the present application. As Figure 3 shown, the electronic terminal includes: at least one processor 301, a memory 302, at least one network interface 303, and a user interface 305. Each component in the device is coupled together through a bus 304. It can be understood that the bus 304 is used to realize the connection and communication between these components. In addition to the data bus, the bus 304 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in Figure 3 all kinds of buses are labeled as buses.

[0096] Among them, the user interface 305 may include a display, a keyboard, a mouse, a trackball, a click gun, a button, a touchpad, or a touch screen, etc.

[0097] It can be understood that the memory 302 may be a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM, Static Random Access Memory), synchronous static random access memory (SSRAM, Synchronous Static Random Access Memory). The memory described in the embodiments of the present invention is intended to include but not be limited to these and any other suitable categories of memory.

[0098] The memory 302 in the embodiments of the present invention is used to store various types of data to support the operation of the electronic terminal 300. Examples of such data include: any executable programs for operating on the electronic terminal 300, such as operation 3021 and application 3022; operation 3021 contains various programs, such as the framework layer, the core library layer, the driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 3022 may include various applications, such as a Media Player, a Browser, etc., for implementing various application services. The method for training the dynamic vision function based on VR provided by the embodiments of the present invention may be included in the application 3022.

[0099] The method disclosed in the above embodiments of the present invention may be applied to the processor 301 or implemented by the processor 301. The processor 301 may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above method may be completed by the integrated logic circuit in the hardware of the processor 301 or instructions in software form. The above-mentioned processor 301 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 301 may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor 301 may be a microprocessor or any conventional processor, etc. Combining the steps of the accessory optimization method provided by the embodiments of the present invention may be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, and this storage medium is located in the memory. The processor reads the information in the memory and combines its hardware to complete the steps of the foregoing method.

[0100] In an exemplary embodiment, the electronic terminal 300 may be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs) for executing the foregoing method.

[0101] According to the method provided by the embodiments of the present application, the present application also provides a computer program product, which includes: computer program code, when the computer program code runs on a computer, causing the computer to execute the method for training the dynamic vision function based on VR in any one of the above embodiments.

[0102] According to the method provided by the embodiments of the present application, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores program codes. When the program codes run on a computer, the computer is caused to execute the VR-based dynamic vision function training method according to any one of the above embodiments.

[0103] The terms "component", "module", etc. used in this specification are used to represent computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. By way of illustration, an application running on a computing device and the computing device can both be components. One or more components can reside in a process and / or an execution thread, and the components can be located on one computer and / or distributed between two or more computers. In addition, these components can execute from various computer-readable media storing various data structures. The components can communicate, for example, through local and / or remote processes according to signals having one or more data packets (such as data from two components interacting with another component locally, distributively, and / or inter-networkedly, such as through signals interacting with others via the Internet).

[0104] Those of ordinary skill in the art can realize that the various illustrative logical blocks and steps described in combination with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled artisans can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0105] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0106] In several embodiments provided by this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another one, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0107] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0109] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, the processes or functions according to the embodiments of this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server, data center, etc. that contains one or more integrated available media. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, high-density digital video disc (Digital Video Disc, DVD)), or a semiconductor medium (for example, solid state disk (Solid State Disk, SSD), etc.).

[0110] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0111] As described above, the above are only the specific implementation manners of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0112] In summary, this application provides a VR-based dynamic visual function training method, device, medium, program product, and terminal. By generating an initial training task type and configuration parameters based on the visual assessment results of patients, constructing visual targets and stimulation signals for visual function training, and executing the training through a VR unit. During the training process, real-time collection of patient feedback data is performed, real-time assessment results are analyzed and generated, the task type, configuration parameters, and visual targets are dynamically adjusted, and new stimulation signals are generated to continue the training, thereby realizing the dynamic optimization of the training content. Through real-time assessment and dynamic adjustment, the problem that the training content does not match the patient's needs is solved, the deficiencies in personalization and adaptability of the traditional method are overcome, the training effect is significantly improved, it is more in line with the patient's needs, the training time is reduced, and the efficiency is improved. This method is particularly suitable for the rehabilitation training of various visual function defects and has significant advantages in dynamic visual function recovery. Therefore, this application effectively overcomes various disadvantages in the prior art and has high industrial utilization value.

[0113] The above embodiments are only illustrative of the principles and effects of this application and are not used to limit this application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed in this application should still be covered by the claims of this application.

Claims

1. A VR-based dynamic visual function training method, characterized in that, Including: Obtain the visual assessment result of the patient, and generate an initial training task type based on the visual assessment result; Generate corresponding initial training configuration parameters according to the training task type, and generate visual function training visual targets based on the initial training configuration parameters; Generate a stimulation signal based on the visual function training visual target, and send the stimulation signal to the VR unit to perform visual function training; During the visual function training process, collect the visual feedback data of the patient in real time; Analyze the visual feedback data to generate a real-time assessment result; According to the real-time assessment result, update the training task type and the corresponding training configuration parameters; Based on the updated training configuration parameters, update the visual function training visual target, and generate a new stimulation signal according to the updated visual function training visual target, and continue to perform visual function training.

2. The VR-based dynamic vision function training method according to claim 1, wherein The method includes: for each preset training task type, calculate the dependency parameter between it and the visual assessment result and / or the real-time assessment result.

3. The VR-based dynamic vision function training method according to claim 2, wherein The process of generating an initial training task type based on the visual assessment result includes: For each preset training task type, calculate the dependency parameter between it and the visual assessment result; Extract the task type with the highest dependency parameter as the initial training task type.

4. The VR-based dynamic vision function training method according to claim 2, wherein The process of updating the training task type and the corresponding training configuration parameters according to the real-time assessment result includes: For each preset training task type, calculate the dependency parameter between it and the real-time assessment result; Extract the task type with the highest dependency parameter as the updated task type; According to the updated task type and the dependency parameter, calculate and update the training configuration parameters.

5. The VR-based dynamic vision function training method according to claim 1, wherein, The process of updating the visual function training visual target based on the updated training configuration parameters includes one or more of the following: updating the visual target size, visual target contrast, visual target color combination, visual target shape combination, visual target movement trajectory, and visual target movement speed of the visual function training visual target.

6. The VR-based dynamic visual function training method according to claim 1, characterized in that The training task type includes one or more of the following: static visual target recognition training, contrast training, target localization training, dynamic target tracking training, interference background target recognition, depth perception training, blind area recovery training, adaptive dynamic training, and contour shape detection training.

7. A VR-based dynamic vision function training device, characterized in that, Including: Initialization module: used to obtain the visual assessment result of the patient, and generate an initial training task type based on the visual assessment result; Training configuration module: used to generate corresponding initial training configuration parameters according to the training task type, and generate visual function training visual targets based on the initial training configuration parameters; Stimulation signal generation module: used to generate a stimulation signal based on the visual function training visual target, and send the stimulation signal to the VR unit to perform visual function training; Real-time feedback module: used to collect the visual feedback data of the patient in real time during the visual function training process; Analyze the visual feedback data to generate a real-time assessment result; According to the real-time assessment result, adjust the training task type and the corresponding training configuration parameters; Based on the adjusted training configuration parameters, update the visual function training targets, and generate new stimulation signals according to the updated visual function training targets, and continue to perform visual function training; VR unit: configured to perform corresponding visual function training according to the stimulation signal.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the VR-based dynamic visual function training method according to any one of claims 1 to 6.

9. A computer program product, characterized in that, The computer program product includes computer program code, and when the computer program code runs on a computer, the computer is caused to implement the VR-based dynamic visual function training method according to any one of claims 1 to 6.

10. An electronic terminal, comprising a memory, a processor, and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the VR-based dynamic visual function training method according to any one of claims 1 to 6.

Images