Intelligent visual perception training method, system, medium, program product and terminal based on micro visual field and Gabor visual target

Abstract

The invention provides an intelligent visual perception training method and system based on a micro-view and a Gabor sighting mark, a medium, a program product and a terminal, and the method can generate personalized initial training regions and training sighting marks for different patients through importing a micro-view inspection result and combining with the positioning of a residual function region and micro-view sensitivity, thereby improving the training efficiency. Therefore, the training effect is obviously improved. Meanwhile, stimulation parameters are dynamically adjusted according to patient performance, so that the training content is always matched with the visual ability level of the patient. The characteristics of controllable spatial frequency, direction, contrast ratio and the like of the Gabor sighting target are utilized to construct a multi-level task from easy to difficult, and the diversity and suitability of training are improved. The data-driven weight mechanism not only enhances the scientificity of training, but also provides visual rehabilitation progress reference for clinicians. According to the method, the precise positioning capability of the micro-view and the multi-dimensional stimulation advantage of the Gabor visual target are fully utilized, and the rehabilitation effect and compliance of the low-vision patient are remarkably improved by combining the precise positioning capability with the multi-dimensional stimulation advantage of the Gabor visual target.

Description

Technical Field

[0001] This application relates to the field of visual perception training technology, and in particular to intelligent visual perception training methods, systems, media, program products and terminals based on microfields and Gabor targets. Background Technology

[0002] With the aging population and the increasing incidence of eye diseases such as diabetic retinopathy, macular degeneration, and glaucoma, the number of patients with low vision is constantly increasing. In the field of visual function rehabilitation training, existing technologies mainly rely on standardized optotype presentation and fixed training procedures. These technologies typically display static or simple dynamic optotypes through electronic screens or specialized training instruments, requiring patients to complete preset tasks such as optotype recognition and contrast discrimination. However, this standardized and centralized training method has obvious limitations.

[0003] First, there are significant differences in the residual functional areas among patients with low vision. Especially when macular degeneration or glaucoma causes a central scotoma, patients often need to rely on the peripheral retina to establish new training areas. However, existing training programs are mostly based on the central fixation assumption, and most of them present stimuli in the central area. It is difficult to combine the distribution characteristics of the individual's residual visual field for precise positioning and personalized training, resulting in a large number of stimuli falling into blind spots or non-functional areas, and low training efficiency.

[0004] Secondly, existing visual rehabilitation systems generally lack real-time gaze monitoring and feedback mechanisms, making it impossible to ensure that stimuli are truly applied to the target retinal area. At the same time, most systems also lack adaptive adjustment capabilities, making it difficult to dynamically adjust training parameters such as stimulus location, contrast, spatial frequency, or task difficulty based on the patient's immediate performance, thereby reducing training effectiveness and compliance.

[0005] In terms of stimulus design, traditional training often uses single static light spots or simple graphics, lacking multi-dimensional control over spatial frequency, direction, and contrast, making it difficult to fully activate the neuroplasticity of the brain's visual cortex. Existing research has shown that Gabor targets, due to their controllable spatial frequency, direction, and contrast characteristics, are widely used in visual science research and amblyopia rehabilitation training, effectively mobilizing specific neuronal groups in the primary visual cortex. However, current Gabor training is usually limited to central fixation tasks, failing to consider the actual residual visual field of low-vision patients, and thus unable to achieve truly personalized rehabilitation.

[0006] On the other hand, micro-field examination technology can precisely correlate functional test results with retinal structure through fundus tracking, thereby discovering and locating the patient's micro-field sensitivity. Micro-field-guided biofeedback training has been used in many areas of visual impairment rehabilitation for at least 20 years, such as amblyopia, strabismus, and nystagmus. Multiple studies have shown that biofeedback training based on micro-field sensitivity can improve fixation stability and some visual function indicators. However, most existing micro-field training is limited to improving fixation stability, with limited training content and a lack of systematic enhancement of higher visual functions.

[0007] Furthermore, most current rehabilitation training methods require a high-quality training environment, such as a dark room or special lighting conditions, making them unsuitable for widespread application in everyday settings. At the same time, the lack of collection and analysis of physiological data during training (such as pupillary response and fixation stability) makes it difficult to provide doctors with comprehensive evidence for evaluating treatment effectiveness.

[0008] In summary, current technologies cannot organically combine the precise positioning capabilities of micro-fields with the multi-dimensional stimulation advantages of Gabor targets, nor can they achieve individualized, adaptive, and real-time monitoring of visual function training. Summary of the Invention

[0009] In view of the shortcomings of the prior art described above, the purpose of this application is to provide an intelligent visual perception training method, system, medium, program product and terminal based on microfield and Gabor targets, to solve the problem that the prior art cannot organically combine the precise positioning capability of microfield with the multi-dimensional stimulation advantage of Gabor targets, and also fails to achieve individualized, adaptive and real-time monitoring visual function training.

[0010] To achieve the above and other related objectives, a first aspect of this application provides an intelligent visual perception training method based on microfield and Gabor targets, comprising: obtaining a patient's visual ability data through a microfield meter; generating a visual assessment result based on the visual ability data and the patient's physiological indicators; analyzing the visual assessment result using a contrast recognition algorithm to obtain an initial training region; generating initial training parameters corresponding to the initial training region based on the visual ability data, and generating visual function training targets based on the initial training parameters; performing visual function training on the patient based on the initial training region and the corresponding visual function training targets, and collecting the patient's visual training feedback data in real time; analyzing the visual training feedback data to generate a real-time assessment result; updating the initial training parameters corresponding to the initial training region in real time based on the real-time assessment result, and updating the visual function training targets based on the updated initial training parameters corresponding to the initial training region; updating the initial training region after the visual function training is completed; and continuing to perform visual function training based on the updated initial training region and the updated visual function training targets.

[0011] In some embodiments of the first aspect of this application, the visual assessment results include: visual acuity, visual field range, micro-visual field sensitivity, fixation point distribution, and fixation stability.

[0012] In some embodiments of the first aspect of this application, the process of analyzing the visual assessment results using a contrast recognition algorithm to obtain an initial training region includes: comparing micro-field sensitivity with a preset sensitivity threshold, and obtaining the patient's residual functional area based on the comparison result; dividing the patient's residual functional area into regions based on micro-field sensitivity to obtain multiple sub-residual functional areas; and filtering based on the micro-field sensitivity and fixation stability corresponding to the multiple sub-residual functional areas to obtain an initial training region.

[0013] In some embodiments of the first aspect of this application, the initial training parameters include: target size, contrast, spatial frequency, orientation angle, presentation duration, appearance position, color mode, and training distance.

[0014] In some embodiments of the first aspect of this application, the process of real-time acquisition of the patient's visual training feedback data includes: real-time tracking of the patient's eye movement status information during visual function training using an eye-tracking device; the eye movement status information includes eye movement trajectory, fixation point coordinates, fixation duration, and pupil diameter; and real-time acquisition of the patient's training judgment results based on the current visual function training target during visual function training.

[0015] In some embodiments of the first aspect of this application, the process of updating the initial training parameters corresponding to the initial training region in real time based on the real-time evaluation results includes: obtaining the target size, spatial frequency, and microfield sensitivity of the current visual function training target; generating initial weight values ​​based on the target size, spatial frequency, and microfield sensitivity using a preset linear weighting function; modifying the initial weight values ​​according to the real-time response results of the current visual function training target in the real-time evaluation results to obtain the final weight values; and performing weighted calculations based on the final weight values ​​to update the initial training parameters corresponding to the initial training region.

[0016] To achieve the above and other related objectives, a second aspect of this application provides an intelligent visual perception training system based on microfield and Gabor targets, comprising: a region generation module: obtaining visual ability data of a patient through a microfield meter, generating a visual assessment result based on the visual ability data and the patient's physiological indicators, and analyzing the visual assessment result using a contrast recognition algorithm to obtain an initial training region; a target generation module: generating initial training parameters corresponding to the initial training region based on the visual ability data, and generating visual function training targets based on the initial training parameters; and an execution module: executing visual function training of the patient based on the initial training region and the corresponding visual function training targets, and collecting the patient's visual training feedback data in real time; and analyzing the visual training feedback data to generate a real-time assessment result.

[0017] Analysis module: Based on the real-time evaluation results, it updates the initial training parameters corresponding to the initial training region in real time, and updates the visual function training targets based on the updated initial training parameters; it also updates the initial training region after visual function training is completed. Update module: It continues to perform visual function training based on the updated initial training region and the updated visual function training targets.

[0018] To achieve the above and other related objectives, a third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent visual perception training method based on microfield and Gabor targets.

[0019] To achieve the above and other related objectives, a fourth aspect of this application provides a computer program product comprising computer program code that, when executed on a computer, enables the computer to implement the intelligent visual perception training method based on microfield and Gabor targets.

[0020] To achieve the above and other related objectives, a fifth aspect of this application provides an electronic terminal, including a memory, a processor, and a computer program stored in the memory; the processor executes the computer program to implement the intelligent visual perception training method based on microfield and Gabor targets.

[0021] As described above, this application has the following beneficial effects: By importing micro-field examination results and combining the localization of residual functional areas and micro-field sensitivity, personalized initial training areas and training targets can be generated for different patients, thereby significantly improving training effectiveness. Eye tracking is introduced during training to collect fixation point data in real time and generate real-time evaluation results, ensuring that training stimuli truly act on the target area and avoiding ineffective training; simultaneously, stimulation parameters are dynamically adjusted according to patient performance, ensuring that the training content always matches the patient's visual ability level. Utilizing the controllable spatial frequency, direction, and contrast characteristics of Gabor targets, multi-level tasks from easy to difficult are constructed, enhancing the diversity and adaptability of training. This data-driven weighting mechanism not only enhances the scientific nature of training but also provides clinicians with intuitive references for rehabilitation progress. This scheme fully utilizes the precise localization capabilities of micro-fields and the multi-dimensional stimulation advantages of Gabor targets, significantly improving the rehabilitation effect and compliance of low vision patients. Attached Figure Description

[0022] Figure 1 The diagram shown is a flowchart illustrating an intelligent visual perception training method based on microfield and Gabor targets in one embodiment of this application.

[0023] Figure 2 The diagram shown is a schematic representation of the visual field test results in one embodiment of this application.

[0024] Figure 3 The diagram shows a flowchart of repeatedly performing visual function training in one embodiment of this application.

[0025] Figure 4 The diagram shown is a structural schematic of an intelligent visual perception training system based on microfield and Gabor targets in one embodiment of this application.

[0026] Figure 5 The diagram shown is a structural schematic of an electronic terminal according to an embodiment of this application. Detailed Implementation

[0027] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0028] Before providing a further detailed description of the present invention, the nouns and terms used in the embodiments of the present invention are explained, and the nouns and terms used in the embodiments of the present invention are subject to the following interpretations:

[0029] <1> Microperimetry: A technology that combines fundus imaging and functional detection, which tracks the eye's gaze position in real time and maps visual acuity threshold results to retinal structures.

[0030] <2> Gabor Patch: A visual stimulus formed by superimposing sinusoidal stripes and a Gaussian window function. It has the characteristics of adjustable direction, spatial frequency and contrast, and is often used in research on visual cortex function.

[0031] <3> Eye-tracking devices: a technology that captures a user's visual attention location and behavior by detecting eye movements and fixation points, used to study visual attention, interface interaction, and cognitive processes.

[0032] <4> Linear weighted function: A method of calculating a weighted average by multiplying each element by its corresponding weight and then summing the results, used to adjust the contribution of each element to the result according to its importance.

[0033] To facilitate understanding of the embodiments of this application, firstly, in conjunction with Figure 1 Detailed explanation. Figure 1 This document illustrates a flowchart of an intelligent visual perception training method based on microfields and Gabor targets, as described in an embodiment of the present invention. The intelligent visual perception training method based on microfields and Gabor targets in this embodiment mainly includes the following steps:

[0034] Step S11: Obtain the patient's visual ability data through microperimeter detection, generate visual assessment results based on the visual ability data and the patient's physiological indicators, and analyze the visual assessment results using a contrast recognition algorithm to obtain an initial training area.

[0035] In one embodiment of this application, the patient's visual ability data includes visual acuity, visual field range, initial microperimeter sensitivity, and fixation stability. Visual acuity is obtained using a Snellen visual acuity chart or an ETDRS visual acuity chart, used for measuring visual acuity at long and near distances, respectively; visual field range is detected using a microperimeter or a Humphrey perimeter to obtain the sensitivity distribution of the central and peripheral visual fields; fixation stability is recorded by the fundus tracking function of the microperimeter or an eye-tracking device, recording the distribution range and offset of the fixation point.

[0036] Furthermore, initial micro-field sensitivity is obtained through micro-perimeter measurement to assess the patient's visual resolution ability in low-contrast environments. The specific process includes: obtaining the patient's visual ability data through micro-perimeter measurement of the micro-field sensitivity, and generating visualized visual field examination results from the visual ability data, such as... Figure 2As shown, the visual field test results include: eccentricity, meridian, minimum threshold, and maximum threshold. Eccentricity refers to the angle by which the test stimulus point deviates from the eye's fixation point. It determines the corresponding position of the stimulus point on the retina and is a key parameter describing the spatial position of the visual field. Meridian refers to an imaginary line passing through the optical axis of the eyeball, used to determine the range or direction of the visual field test. Statuses include undefined, not started, increasing, decreasing, completed, and failed, used to determine the patient's testing status at a specific retinal position. Minimum threshold refers to the minimum stimulus intensity that the patient can detect at a specific visual position. It reflects the sensitivity of the retinal photoreceptor cells at that location and is a core indicator for quantitative visual field analysis. Maximum threshold refers to the highest recorded stimulus intensity level, serving as a reference benchmark for calculating relative sensitivity. The above data is stored in a dedicated data file (e.g., MPD format). By parsing the data file, the specific area of ​​the eye is first spatially located based on the eccentricity and meridian data. Then, the original observation values ​​such as the minimum threshold and maximum threshold are transformed into an initial set of micro-field sensitivity values ​​that can be used for further analysis, thus establishing a reliable and consistent data foundation for subsequent statistical analysis, defect judgment, and disease tracking.

[0037] After acquiring visual ability data, the micro-field sensitivity is calculated by combining real-time recorded eye movement trajectories, fixation point distribution, and pupil diameter changes using eye-tracking technology, along with the initial micro-field sensitivity from the visual ability data and the fixation point distribution of the physiological indicators. The calculation of micro-field sensitivity is shown below:

[0038] ;(Formula 1)

[0039] By combining visual ability data with patients' physiological indicators, we can enhance visual field sensitivity and patient fit, thereby achieving accurate quantitative assessment of visual ability.

[0040] In one embodiment of this application, the visual assessment results include: visual acuity, visual field range, micro-visual field sensitivity, fixation point distribution, and fixation stability.

[0041] Within the field of view, the area is divided into multiple sub-blocks according to a preset sub-block size. Each sub-block corresponds to a micro-field sensitivity. The micro-field sensitivity in the visual evaluation result includes the set of micro-field sensitivity thresholds for all sub-blocks within the field of view.

[0042] In one embodiment of this application, the process of using the contrast recognition algorithm to analyze the visual assessment results to obtain an initial training region includes: comparing micro-field sensitivity with a preset sensitivity threshold, setting the set of sub-blocks within the field of view whose micro-field sensitivity is greater than the preset sensitivity threshold as residual functional areas; further dividing the patient's residual functional areas based on micro-field sensitivity to obtain multiple sub-residual functional areas; and filtering based on the micro-field sensitivity and fixation stability corresponding to the multiple sub-residual functional areas to obtain the initial training region.

[0043] Specifically, within the visual field, micro-visual field sensitivity is compared with a preset sensitivity threshold, and areas with micro-visual field sensitivity greater than the preset threshold are selected as the patient's residual functional area. For example, areas with micro-visual field sensitivity higher than 10dB within the visual field are selected as residual functional areas. Then, the residual functional area is further divided into three sub-residual functional areas: 10-15dB, 15-20dB, and greater than 20dB. Areas within the sub-residual functional area greater than 20dB that are greater than the preset fixation stability threshold are selected as the first training area; areas within the sub-residual functional area of ​​15-20dB that are greater than the preset fixation stability threshold are selected as the second training area; and areas within the sub-residual functional area of ​​10-15dB that are greater than the preset fixation stability threshold are selected as the third training area. The preset first, second, and third training areas together constitute the initial training area. Finding a suitable initial training area for the current patient is to address the lack of sensitivity in the central visual field. In order to efficiently carry out visual rehabilitation training, traditional methods fix the visual rehabilitation training in the visual center. By finding a suitable initial training area, the effect of visual rehabilitation training can be maximized, avoiding the problem of poor training effect when the patient's visual center is diseased or sensitivity is reduced.

[0044] Step S12: Generate initial training parameters corresponding to the initial training region based on the visual ability data, and generate visual function training targets based on the initial training parameters.

[0045] In one embodiment of this application, the initial training parameters include: target size, contrast, spatial frequency, orientation angle, presentation duration, position distribution pattern, color mode, and training distance.

[0046] Specifically, after determining the initial training area, the initial training parameters suitable for the current patient's visual ability are configured based on the corresponding visual ability data within the initial training area. Preferably, in order to provide the patients participating in the training with an adaptation training process, the initial training parameters will be maintained at a low level of difficulty. That is, the overall training process follows the principle of "from easy to difficult". In the initial stage, the stimulation is repeatedly strengthened near the minimum difficulty to improve neural plasticity.

[0047] For example, the size of the optotype is divided into 6 levels: 32, 24, 16, 11, 8, and 6 units, with larger optotypes indicating lower difficulty; contrast ratio refers to the contrast ratio of the optotype, ranging from 0 to 100, with higher contrast indicating higher difficulty; spatial frequency indicates the number of times the optotype is repeated in each cycle, ranging from 0.5 to 6 cycles per degree (cpd), with higher frequency indicating higher difficulty; directional angles include multiple directions such as 0°, 45°, 90°, and 135°, with higher slope indicating higher difficulty, and vertical and parallel angles having the lowest difficulty; presentation duration ranges from 300 to 1000 ms, with shorter presentation durations indicating higher difficulty; positional distribution pattern indicates the positional pattern of the optotype in the initial training area during training, including fixed patterns, semi-random patterns, and random patterns, with stronger randomness indicating higher difficulty; the color mode initially uses black and white Gabor optotypes, and color Gabor optotypes can be implemented in subsequent expansions to test color vision-related functions; the initial training distance is 45 cm between the patient and the screen.

[0048] Fixed pattern means the appearance of the target within the training area follows certain rules; semi-random pattern means the appearance of the target within the training area follows certain rules but also has a degree of randomness. Common semi-random patterns include partitioned randomness, rule-based randomness, and fixed-interval randomness; random pattern means the appearance position of the target changes randomly. Common random patterns include completely random, random sequence, and local randomness. No specific restrictions are placed on the specific random or semi-random pattern here; choose the appropriate one according to your needs.

[0049] It should be noted that the range of difficulty for the initial training parameters in the above example is determined by the patient's visual ability data. Different visual ability data correspond to different ranges of initial training parameters. That is, the minimum difficulty corresponds to the lowest initial training parameter that the current patient can tolerate, and the maximum difficulty corresponds to the highest initial training parameter that the current patient can tolerate.

[0050] Furthermore, each sub-block within the field of vision has independent initial training parameters. Based on the initial training parameters of each sub-block within the initial training area, Gabor targets corresponding to each sub-block are generated. Multiple Gabor targets constitute the visual function training targets for the patient.

[0051] S13: Perform visual function training on the patient based on the initial training area and the corresponding visual function training targets, and collect the patient's visual training feedback data in real time; analyze the visual training feedback data to generate real-time evaluation results.

[0052] Specifically, the visual function training targets generated by S12 are converted into pixel-driving signals recognizable by the display unit and presented as Gabor targets within the initial training area. The display unit is a device used to display visual stimuli; common devices include liquid crystal displays (LCDs), organic light-emitting diode displays (OLEDs), projectors, virtual reality (VR) displays, holographic displays, and head-mounted displays. LCDs and OLEDs are used to display static or dynamic patterns, helping to improve visual perception; projectors are suitable for large-scale visual training, such as field-of-view expansion training; VR headsets provide an immersive experience for depth perception and spatial vision training; holographic displays and head-mounted displays are often used for stereoscopic vision or motion vision training, improving spatial perception and dynamic response capabilities. The selection of different devices depends on training needs and specific goals, and is not limited here.

[0053] Furthermore, the patient maintains a training distance from the display screen, corresponding to approximately 5° of visual angle, which helps ensure the correspondence between the initial training area and micro-field sensitivity. The patient's training distance is monitored and calibrated in real time using a camera or laser rangefinder to avoid stimulation distortion caused by distance deviations.

[0054] In one embodiment of this application, the process of collecting patient visual training feedback data in real time includes: tracking the patient's eye movement status information in real time during visual function training using an eye-tracking device; the eye movement status information includes eye movement trajectory, fixation point coordinates, fixation duration, and pupil diameter; and collecting the patient's training judgment results based on the current visual function training target during visual function training in real time.

[0055] Specifically, when visual function training begins, the Gabor targets corresponding to one or more sub-blocks are first displayed based on the positional distribution patterns in the initial training parameters. Then, the displayed Gabor targets are configured according to the initial training parameters and projected onto the display unit. During training, when the patient sees the current Gabor target, they input the direction or contrast of the seen Gabor target into the input device. The training judgment result is collected, comparing the patient's input Gabor target direction or contrast with the actual direction or contrast of the current Gabor target. This training judgment includes the patient's response time and the correctness of their answer. Simultaneously, each time the display device displays a Gabor target, the eye-tracking device records the patient's current eye movement status in real time. Then, based on the positional distribution patterns, the appearance position and number of Gabor targets are reset, and the training judgment results and eye movement status information are accumulated and recorded. The specific process is not detailed here, continuing until the training is completed.

[0056] The input device can be a keyboard, touchscreen, or gamepad, or any other device capable of recording data. The eye-tracking device is a technological device used to monitor and record eye movements, widely applied in fields such as psychology, neuroscience, medicine, education, and user experience research. Its main function is to track the eye's fixation point, eye movement trajectory, and various dynamic eye responses, helping researchers and clinicians better understand an individual's performance in visual attention, eye movement control, and visual cognition. Specific examples include optical eye-tracking devices and video eye-tracking devices, etc., without further specific limitations here.

[0057] Before analyzing the visual training feedback data to generate real-time evaluation results, abnormal samples caused by abnormal behaviors such as blinking or head movement are screened out and removed. Based on the screened visual training feedback data, the effective fixation rate, fixation deviation rate, response accuracy rate, and reaction time are calculated.

[0058] Among them, the effective fixation rate refers to the duration of effective fixation continuously updated by the system when the eye's fixation area is within the effective training range. By calculating the proportion of effective fixation time in the total time, the system analyzes whether the training quality meets the standards. The fixation deviation rate refers to the action captured and recorded by the system when the eye's fixation area enters and exits the effective training range, which is used to analyze the level of attention concentration during the training. The response accuracy rate refers to the system recording the response status each time, which is used to analyze whether the training difficulty is suitable for the patient's current state. The reaction time refers to the time recorded in each training session, starting from the appearance of the training icon and ending after the response, and the time is summed up. This indicator, combined with the response accuracy rate, is used to analyze the patient's behavioral characteristics during the training process to determine whether the training is within the scope of effective training.

[0059] It should be noted that the training environment does not require a dark room; the system can operate in a normal bright room. To ensure the visibility of the stimuli, the display unit automatically adjusts the brightness and contrast based on the illuminance information collected by the ambient light sensor, ensuring that patients with low light sensitivity, such as those with glaucoma or low vision, can complete the training under comfortable conditions.

[0060] S14: Based on the real-time evaluation results, update the initial training parameters corresponding to the initial training region in real time, and update the visual function training targets based on the updated initial training parameters corresponding to the initial training region; update the initial training region after the visual function training is completed.

[0061] In one embodiment of this application, during the training process, each time the position of the Gabor target is reset, the real-time evaluation result is also updated synchronously in real time. After each real-time update during training, based on the generated real-time evaluation result, subsequent training will adjust the difficulty according to the current real-time evaluation result, ensuring that the training difficulty remains at the most suitable level for the patient. For example, when the effective fixation rate is ≤70% or the fixation deviation rate is ≥10%, the patient is judged to be "not focused during training"; when the fixation deviation rate is ≤20% and the accuracy rate is ≥80%, the patient is judged to be "suitable for the current task"; if the fixation deviation rate is ≤20% and the accuracy rate is ≤80%, a feedback message "training parameters need to be reduced" is generated, etc. Specific limiting conditions can be set as needed and are not limited here. When the patient is judged to be "not focused during training," the initial training parameters are not updated, and the current initial training parameters are repeated; when the patient is judged to be "suitable for the current task," the difficulty of the current initial training parameters is increased; when the patient is judged to "need to reduce training parameters," the difficulty of the current initial training parameters is reduced.

[0062] In one embodiment of this application, the process of updating the initial training parameters corresponding to the initial training region in real time based on the real-time evaluation results includes: obtaining the target size, spatial frequency, and microfield sensitivity of the current visual function training target; generating initial weight values ​​based on the target size, spatial frequency, and microfield sensitivity using a preset linear weighting function; modifying the initial weight values ​​according to the real-time response results of the current visual function training target in the real-time evaluation results to obtain the final weight values; and performing weighted calculations based on the final weight values ​​to update the initial training parameters corresponding to the initial training region.

[0063] Taking the need to reduce the difficulty of the current initial training parameters as an example, when it is determined that the patient "needs to reduce the training parameters", the target size of the current Gabor target, the spatial frequency of the current Gabor target, and the micro-field sensitivity of the sub-region where the current Gabor target appears are first obtained. Then, the initial weight values ​​are generated according to the linear weighting function, which is shown in Formula 2:

[0064] ;(Formula 2)

[0065] in These are the coefficients corresponding to target size, spatial frequency, and microfield sensitivity.

[0066] Then, based on the real-time response results of the current Gabor beacon, the current initial weight value is modified to the final weight value, and Formula 3 is modified as follows:

[0067] ;(Formula 3)

[0068] When the real-time response result of the current Gabor target is correct, M is a value greater than 1; when the real-time response result of the current Gabor target is incorrect, M is a value between 0 and 1.

[0069] The final weight values ​​are added to each initial training parameter, and the modified initial training parameters complete one real-time parameter update. This process is repeated until the current training ends.

[0070] It should be noted that, The corresponding values ​​are related to the target size, spatial frequency, and micro-field sensitivity range, respectively. Specific settings should be selected based on actual needs; this embodiment does not impose any limitations. M is used to adjust the degree of difficulty adjustment, but M does not change the current overall trend of difficulty adjustment. Specific parameters can be set based on the patient's overall visual ability level and historical training data; no specific limitations are imposed here.

[0071] In this embodiment, Gabor targets are generated in the first training region, the second training region, and the third training region according to the positional distribution pattern in the initial training parameters. Furthermore, the number of Gabor targets in each training region follows a descending trend. For example, during the training process, the number of Gabor targets appearing in the first training region accounts for 50% of the number of Gabor targets in the initial training region, the number of Gabor targets appearing in the second training region accounts for 30% of the number of Gabor targets in the initial training region, and the number of Gabor targets appearing in the third training region accounts for 20% of the number of Gabor targets in the initial training region. The specific percentage can be selected according to the training situation and is not specifically limited here.

[0072] During training, the Gabor targets are arranged from highest to lowest quantity. The first training region is the primary training region, while the second and third are secondary training regions. Each of the three regions executes the positional distribution rules from the initial training parameters. The generation of training targets according to the corresponding positional distribution rules in the three regions can be performed sequentially or alternately, without specific limitations. By dividing the training regions into primary and secondary regions and executing their respective positional distribution rules, the efficiency of training can be reduced due to visual fatigue caused by unchanging Gabor target positions, while also allowing for dynamic expansion of the training regions.

[0073] After training, the micro-field sensitivity within the field of view is re-acquired to match the field of view ranges of the first training region, the second training region, and the third alternative training region, thus completing the update of the initial training region.

[0074] Specifically, after the current training ends, the micro-field sensitivity within the patient's visual field changes. After re-collecting the micro-field sensitivity within the visual field, the first training region, the second training region, and the third training region are re-selected based on the micro-field sensitivity within the patient's visual field. For example, the first training region has a micro-field sensitivity greater than 20dB, the second training region has a micro-field sensitivity of 15-20dB, and the third training region has a micro-field sensitivity of 10-15dB. After the selection is completed, the initial training region is updated.

[0075] S15: Continue visual function training based on the updated initial training area and the updated visual function training targets.

[0076] In one embodiment of this application, as Figure 3 As shown, based on the initial training parameters updated last before the end of training and the initial training region updated after training, the next visual function training continues, and the patient's visual training feedback data is collected in real time. This visual training feedback data is analyzed to generate new real-time evaluation results. Based on these new real-time evaluation results, the initial training parameters corresponding to the initial training region are updated in real time. Based on the updated initial training parameters, the visual function training targets are updated. The initial training region is updated after the visual function training ends. The training process is then repeated based on the updated initial training region and the initial training parameters updated last time.

[0077] It should be noted that the difficulty of the repeatedly updated initial training parameters will be continuously adjusted during the previous training process, and the difficulty may increase or decrease. The repeatedly updated initial training area will gradually expand as training progresses, thereby achieving the recovery of the patient's visual ability.

[0078] Furthermore, if any one of the following conditions is met during multiple rounds of training—that the accuracy and fixation stability both reach the set thresholds, the training duration reaches the preset value (e.g., 30 minutes), or the micro-field re-examination shows stable improvement in the functional area—then the patient's visual function training can be considered complete.

[0079] In the embodiments of this application, the terms "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect, without limiting their order. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" do not necessarily imply that they are different.

[0080] It should be noted that, in the embodiments of this application, the words "exemplary" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0081] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0082] like Figure 4 The diagram shows a schematic of the structure of an intelligent visual perception training system based on microfield and Gabor targets in an embodiment of the present invention. The visual perception training system 400 in this embodiment includes the following modules: region generation module 401, target generation module 402, execution module 403, analysis module 404, and update module 405.

[0083] It should be understood that the specific process of each module performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0084] The region generation module 401 is used to obtain the patient's visual ability data through microperimeter detection, generate visual assessment results based on the visual ability data and the patient's physiological indicators, and analyze the visual assessment results using a contrast recognition algorithm to obtain an initial training region.

[0085] The optotype generation module 402 is used to generate initial training parameters corresponding to the initial training region based on the visual ability data, and to generate visual function training optotypes based on the initial training parameters.

[0086] The execution module 403 is used to perform visual function training on the patient based on the initial training area and the corresponding visual function training targets, and to collect the patient's visual training feedback data in real time; and to analyze the visual training feedback data to generate real-time evaluation results.

[0087] The analysis module 404 is used to update the initial training parameters corresponding to the initial training region in real time based on the real-time evaluation results, update the visual function training targets based on the updated initial training parameters corresponding to the initial training region, and update the initial training region after the visual function training is completed.

[0088] The update module 405 is used to continue visual function training based on the updated initial training area and the updated visual function training targets.

[0089] It should also be understood that the module division in the embodiments of this application is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0090] Figure 5 This is a schematic block diagram of the electronic terminal provided in the embodiments of this application. Figure 5 As shown, the computer device includes at least one processor 501, a memory 502, at least one network interface 503, and a user interface 505. The various components in the device are coupled together via a bus system 504. It is understood that the bus system 504 is used to implement communication between these components. In addition to a data bus, the bus system 504 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 5 The general will label all buses as bus systems.

[0091] The user interface 505 may include a monitor, keyboard, mouse, trackball, clicker, button, touchpad, or touch screen.

[0092] It is understood that memory 502 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM) or programmable read-only memory (PROM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memory.

[0093] In this embodiment of the invention, the memory 502 is used to store various types of data to support the operation of the electronic terminal 500. Examples of this data include: any executable program for operation on the electronic terminal 500, such as the operating system 5021 and application programs 5022; the operating system 5021 contains various system programs, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and handling hardware-based tasks. The application program 5022 may contain various applications, such as a media player, browser, etc., for implementing various application services. The intelligent visual perception training method based on micro-field of view and Gabor targets provided in this embodiment of the invention can be included in the application program 5022.

[0094] The methods disclosed in the above embodiments of the present invention can be applied to processor 501, or implemented by processor 501. Processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 501 or by instructions in the form of software. The processor 501 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. Processor 501 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. General-purpose processor 501 may be a microprocessor or any conventional processor, etc. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly reflected as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in memory. The processor reads the information in the memory and combines it with its hardware to complete the steps of the aforementioned method.

[0095] In an exemplary embodiment, the electronic terminal 500 may be used by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs) to execute the aforementioned method.

[0096] According to the method provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute an intelligent visual perception training method based on microfield and Gabor targets according to any of the embodiments shown.

[0097] According to the method provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code. When the program code is run on a computer, it causes the computer to execute an intelligent visual perception training method based on microfield and Gabor targets according to any of the embodiments shown.

[0098] As used in this specification, the terms "component," "module," "system," etc., are used to refer to 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. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0099] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0100] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0102] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0103] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0104] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs, DVDs), or semiconductor media (e.g., solid-state disks, SSDs, etc.).

[0105] If a function is implemented as 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 the 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0107] In summary, this application provides an intelligent visual perception training method, system, medium, program product, and terminal based on microfield and Gabor targets. This application collects patients' visual ability data through standardized testing combined with a microfield perimeter, and calculates the zone training complexity, fixation stability index, and sensitive fixation point using eye-tracking technology to form a multi-dimensional visual assessment result. It configures the corresponding initial training area, configures the initial training parameters of the Gabor targets, generates the corresponding initial training task, generates real-time assessment results during the training process, and dynamically adjusts and optimizes the initial training parameters and initial training area. This achieves an organic combination of the precise positioning capability of the microfield and the multi-dimensional stimulation advantages of the Gabor targets, thereby significantly improving the rehabilitation effect and compliance of low vision patients.

[0108] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. An intelligent visual perception training method based on microfields and Gabor targets, characterized in that, include: Visual ability data of patients is obtained by microperimeter detection. Visual assessment results are generated based on the visual ability data and the patient's physiological indicators. A contrast recognition algorithm is used to analyze the visual assessment results to obtain an initial training area. Based on the visual ability data, initial training parameters corresponding to the initial training area are generated, and visual function training targets for the patient are generated based on the initial training parameters. Visual function training for patients is performed based on the initial training area and the corresponding visual function training targets, and visual training feedback data of patients is collected in real time. The visual training feedback data is analyzed to generate real-time evaluation results; Based on the real-time evaluation results, the initial training parameters corresponding to the initial training region are updated in real time, and the visual function training targets are updated based on the updated initial training parameters corresponding to the initial training region. Update the initial training region after visual function training is completed; Visual function training continues based on the updated initial training area and the updated visual function training targets.

2. The intelligent visual perception training method based on microfield and Gabor targets according to claim 1, characterized in that, The visual assessment results include: visual acuity, visual field range, micro-visual field sensitivity, fixation point distribution, and fixation stability.

3. The intelligent visual perception training method based on microfield and Gabor targets according to claim 2, characterized in that, The process of analyzing the visual evaluation results using a contrast recognition algorithm to obtain the initial training region includes: The residual functional area of ​​the patient is obtained by comparing the micro-field sensitivity with a preset sensitivity threshold. The patient's residual functional area is divided into multiple sub-residual functional areas based on micro-field sensitivity. The initial training region is obtained by screening based on the micro-field sensitivity and gaze stability corresponding to multiple sub-residual functional areas.

4. The intelligent visual perception training method based on microfield and Gabor targets according to claim 1, characterized in that, The initial training parameters include: target size, contrast, spatial frequency, orientation angle, presentation duration, appearance position, color mode, and training distance.

5. The intelligent visual perception training method based on microfield and Gabor targets according to claim 1, characterized in that, The process of collecting patients' visual training feedback data in real time includes: The eye movement status information of the patient during visual function training is tracked in real time using an eye-tracking device; the eye movement status information includes eye movement trajectory, fixation point coordinates, fixation duration, and pupil diameter; Real-time acquisition of the patient's training judgment results based on the current visual function training target during visual function training.

6. The intelligent visual perception training method based on microfield and Gabor targets according to claim 1, characterized in that, Based on the real-time evaluation results, the process of updating the initial training parameters corresponding to the initial training region in real time includes: Obtain the target size, spatial frequency, and microfield sensitivity of the current visual function training target, and generate initial weight values ​​based on the target size, spatial frequency, and microfield sensitivity using a preset linear weighting function; The initial weight values ​​are modified based on the real-time response results of the current visual function training target in the real-time evaluation results to obtain the final weight values; The initial training parameters corresponding to the initial training region are updated by performing a weighted calculation based on the final weight values.

7. An intelligent visual perception training system based on microfields and Gabor targets, characterized in that, include: Region generation module: Obtains the patient's visual ability data through microperimeter detection, generates visual assessment results based on the visual ability data and the patient's physiological indicators, and analyzes the visual assessment results using a contrast recognition algorithm to obtain the initial training region; Optical target generation module: Generates initial training parameters corresponding to the initial training region based on the visual ability data, and generates visual function training optical targets based on the initial training parameters; Execution module: Performs visual function training on the patient based on the initial training area and the corresponding visual function training targets, and collects the patient's visual training feedback data in real time; The visual training feedback data is analyzed to generate real-time evaluation results; Analysis module: Based on the real-time evaluation results, update the initial training parameters corresponding to the initial training region in real time, and update the visual function training targets based on the updated initial training parameters corresponding to the initial training region. Update the initial training region after visual function training is completed; Update module: Continue visual function training based on the updated initial training area and the updated visual function training targets.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the intelligent visual perception training method based on microfield and Gabor targets as described in any one of claims 1 to 6.

9. A computer program product, characterized in that, The computer program product includes computer program code, which, when run on a computer, enables the computer to implement the intelligent visual perception training method based on microfield and Gabor targets as described in any one of claims 1 to 6.

10. An electronic terminal, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the intelligent visual perception training method based on microfield and Gabor targets as described in any one of claims 1 to 6.

Images