Multimodal visual stimulation and intelligent self-adaption combined myopia prevention and control system based on AR glasses

Abstract

According to the multi-mode visual stimulation and intelligent self-adaption combined myopia prevention and control system based on the AR glasses, all-weather, personalized and full-scene myopia suppression is realized through multi-module cooperation of sensory visual stimulation, visual function training, AI scene dynamic recognition and directional intervention, self-adaption closed-loop feedback, cloud / offline deployment and the like; through multi-dimensional visual stimulation and real-time physiological monitoring, eye axis growth is accurately regulated and controlled, myopia prevention and control precision is improved, out-of-focus and contrast setting are automatically optimized based on immediate refraction and adjustment feedback, personalized intervention is enhanced, lightweight AI and cloud pre-calculation are introduced, the endurance of equipment is effectively prolonged, an existing AR platform is compatible, the development process is simplified, and the development efficiency is improved. And the user compliance is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of myopia prevention and control, and specifically to a multimodal visual stimulation and intelligent adaptive combined myopia prevention and control system based on AR glasses. Background Art

[0002] Peripheral defocus refers to the process of defocusing light in the peripheral area of ​​the retina through glasses or other devices, thereby reducing the growth of the eye axis and inhibiting the progression of myopia. Peripheral defocus glasses stimulate changes in the eye's growth mechanism by generating defocus signals in the peripheral area of ​​the retina, thereby delaying the progression of myopia. Existing studies have shown that peripheral defocus glasses (such as multi-zone optical positive defocus lenses, referred to as DIMS lenses) have a certain effect on slowing the progression of myopia, but their effect is not effective for all people. For example, Liu et al. found in "Liu J, Lu Y, Huang D, et al. Ophthalmology 2023;130(5):542-550" that within 2 years of wearing DIMS lenses, the average increase in myopia was only 0.35D lower than that of single-focus glasses, but 12% of DIMS lens wearers had an increase in refractive power of more than 1.5D within 2 years. Similarly, Lam et al. (LamCSY, Tang WC, Tse DY, et al. Br J Ophthalmol 2020;104:363–368) found that 13% of DIMS lens wearers experienced a refractive gain of more than 1 D. This suggests that the effectiveness of peripheral defocus glasses is influenced by individual differences, the refractive power of the peripheral retinal region, and the structural differences of the cornea and axial length. Individual differences may be a key factor contributing to the inconsistent peripheral defocus effects across different populations.

[0003] In addition to peripheral defocus glasses, researchers have also begun to explore augmented reality (AR) glasses as a potential tool for myopia prevention and control in recent years. AR glasses enhance information by superimposing virtual images in the wearer's field of view. Recent studies have shown that AR technology can provide a "defocus" signal when working at close range, which is expected to slow down the thinning of choroidal thickness and blood flow changes caused by long-term close-range eye use. Considering that AR glasses are an emerging optical technology, they have broad application prospects in myopia prevention and control. Existing myopia prevention and control methods include peripheral positive defocus soft lenses, OK lenses and AR systems based on single defocus. Most of them lack coordinated regulation and dynamic adaptive optimization of central and peripheral visual pathways, cannot reproduce outdoor natural lighting and spatial characteristics in indoor environments, and do not fully utilize AI for real-time signal processing and interactive optimization. Summary of the Invention

[0004] In order to address the deficiencies in the prior art, the present invention provides a multimodal visual stimulation and intelligent adaptive combined myopia prevention and control system based on AR glasses.

[0005] The technical solution adopted by the present invention is: a multimodal visual stimulation and intelligent adaptive combined myopia prevention and control system based on AR glasses, including: Visual stimulation module: Leveraging the optical projection capabilities of AR glasses, it dynamically generates personalized stimulation signals within a 10°–30° peripheral field of view. Stimulation parameters are adjusted in real time based on ambient illumination, eye movement characteristics, and usage scenarios, simulating outdoor visual experience and enhancing system load control. Vision Training Module: The central visual field area enhances visual convergence and gaze stabilization by presenting dynamic visual tracking tasks, binocular fusion targets, and contrast sensitivity tests. The visual training module's system design features a "central-peripheral" visual feedback chain: when central vision training achieves the preset effect, it automatically and synchronously triggers the visual stimulation module to increase the intensity and range of peripheral defocus stimulation, stimulating a stronger peripheral perception response, thereby achieving functional synergy. AI scene dynamic recognition and targeted intervention module: The system integrates a lightweight semantic recognition model to perform real-time image acquisition and intelligent classification of the environment. It also comprehensively assesses eye risks based on light intensity, eye distance, and eye movement characteristics, and automatically initiates targeted intervention strategies for scenarios with different risk levels. Adaptive closed-loop feedback module: By real-time collection of key physiological parameters of the user, such as blinking frequency, pupil diameter changes, and gaze stability, the system comprehensively judges the degree of visual fatigue and regulatory load status. Based on the feedback information, the system dynamically fine-tunes the stimulation intensity, frequency, and duration of the three modules: the pre-visual stimulation module, the visual training module, and the directional intervention module. It also sends prompts to the user through voice, graphics, or vibration to establish closed-loop control.

[0006] The personalized stimulation signal includes a defocused grating with variable adjustable intensity, a low-contrast disturbance pattern and a spatial frequency stripe.

[0007] The stimulation parameters in the visual stimulation module include defocus intensity, contrast, and spatial frequency.

[0008] The AI ​​scene dynamic recognition and targeted intervention module automatically initiates targeted intervention strategies for scenarios with different risk levels, including: improving display contrast in low-contrast environments; enhancing defocus signals and spatial frequency regulation during continuous gaze at close range; and adapting high-frequency stimulation compensation in tasks dominated by low-frequency visual stimulation.

[0009] The adaptive closed-loop feedback module sends prompts to the user, including rest suggestions, sitting posture adjustment suggestions, and long-distance viewing suggestions.

[0010] The personalized stimulation signal is in the form of concentric rings or radial gradients.

[0011] The peripheral visual field in the visual stimulation module also includes three sections: a central visual field of 0°-10°, a mid-peripheral visual field of 10°-20°, and a far peripheral visual field of 20°-30°.

[0012] The contrast gradients of 5%–20% and 20%–50% are set for the middle peripheral visual field and the far peripheral visual field, respectively, to differentially activate the ON / OFF pathways.

[0013] The visual stimulation module dynamically generates personalized stimulation signals in the peripheral visual field 10°-30° area by superimposing a +0.5D to +4.5D positive defocus or -0.5D to -4.5D negative defocus pattern in the peripheral visual field 10°-30° area according to the current refractive power.

[0014] It also includes a cloud / offline deployment module, which uploads multimodal data to the server in real time and uses a distributed AI model for batch calculation and analysis; periodically generates individual and group reports and pushes the latest parameters to the device; and locally stores data and synchronizes it regularly to avoid data loss.

[0015] The beneficial effects of the present invention are: a multimodal visual stimulation and intelligent adaptive joint myopia prevention and control system based on AR glasses, which realizes all-weather, personalized, and full-scene myopia suppression through multi-module collaboration such as sensory visual stimulation, visual function training, AI scene dynamic recognition and directional intervention, adaptive closed-loop feedback, and cloud / offline deployment. Through multi-dimensional visual stimulation and real-time physiological monitoring, it accurately regulates axial growth and improves the accuracy of myopia prevention and control. It automatically optimizes defocus and contrast settings based on instant refractive and accommodation feedback to enhance personalized intervention. It introduces lightweight AI and cloud pre-calculation to effectively extend device life, is compatible with existing AR platforms, simplifies the development process, and enhances user compliance. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The results show the changes in choroidal thickness after close work with AR on or off.

[0017] Figure 2 These are the changes in choroidal vascular index after close work with AR on or off.

[0018] Figure 3 This is the change in axial length after close work with AR on or off. DETAILED DESCRIPTION

[0019] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] The present invention achieves all-weather, personalized, and full-scenario myopia intervention through the collaboration of multiple modules such as sensory visual stimulation, visual function training, AI scene dynamic recognition and directional intervention, adaptive closed-loop feedback, and cloud / offline deployment.

[0021] Visual stimulation module Relying on the optical projection capabilities of AR glasses, personalized stimulation signals are dynamically generated in the 10°–30° peripheral field of view. The stimulation parameters are adjusted in real time based on the ambient illumination, eye movement characteristics, and usage scenarios to simulate the outdoor visual experience and enhance the load regulation of the adjustment system.

[0022] Among them, in the peripheral field of view (10°–30°), according to the current refractive power, +0.5D to +4.5D positive defocus or –0.5D to –4.5D negative defocus pattern is superimposed to achieve peripheral defocus superposition.

[0023] Reason: A large number of studies have shown that peripheral positive defocus can inhibit axial length growth. By adjusting the defocus according to different refractive states, personalized intervention can be achieved.

[0024] The defocus pattern is designed as concentric rings or radial gradients to ensure visual comfort; reason: concentric rings or gradient patterns can smoothly transition the focus area and reduce visual fatigue and discomfort.

[0025] Segmented contrast adjustment The visual field was divided into three segments: central (0°–10°), mid-peripheral (10°–20°), and far peripheral (20°–30°); Reason: Visual sensitivity varies at different viewing angles, and segmentation can achieve more precise pathway activation.

[0026] Contrast gradients of 5%–20% and 20%–50% were set in the mid-periphery and far-periphery, respectively, to differentially activate ON / OFF pathways; Reason: Differential contrast stimulation can enhance the alternating activation of the ON / OFF pathway, helping to balance accommodation and eliminate visual fatigue.

[0027] Wavelength and spatial frequency compensation Output 460-480nm short-wave blue light, 600-650nm red light and wide-spectrum white light to optimize pupil response; Reason: Short-wavelength blue light can promote retinal dopamine release and inhibit axial length growth; alternating red light and white light can maintain comfort and physiological safety.

[0028] Real-time detection of the spatial frequency distribution of environmental images, superimposition of 0.1–5 c / deg virtual textures on areas lacking high frequency information, and compensation for indoor scenes. Reason: Insufficient high-frequency information in indoor environments may aggravate myopia. Compensation with high-frequency textures can simulate natural depth of field and promote accommodation practice.

[0029] Vision training module The central visual field area enhances visual convergence and gaze stabilization functions by presenting dynamic visual tracking tasks, binocular fusion targets and contrast sensitivity tests. The visual training module is systematically designed with a "central-peripheral" visual feedback chain: when the central visual training achieves the preset effect, the intensity and range of the peripheral defocus stimulation of the visual stimulation module are automatically and synchronously triggered to stimulate a stronger peripheral perception response, thereby achieving functional synergy.

[0030] Adjusting rate and delay training Virtual depth of field switching task: by switching between 1D–4D virtual focal planes, the ciliary muscle accommodation response time is recorded; Rationale: Assessing and improving the responsiveness of the accommodation system can reduce the axial tension stress caused by continuous focus lock.

[0031] Dynamically adjust training difficulty and frequency based on measurement results; Why: Personalized training helps improve regulation over time and avoids one-size-fits-all training programs.

[0032] Gaze stability and fusion ability Central static target recognition: displays 0.5–2 arcmin details and records recognition accuracy; Reason: Poor gaze stability will increase the burden of accommodation. Gaze control can be improved through target recognition tasks. Binocular parallax rendering: Rendering ±10 arcsec parallax targets to improve fusion tolerance; Reason: To enhance binocular fusion function and reduce abnormal changes in eye axis caused by parallax mismatch.

[0033] AI scene dynamic recognition and targeted intervention module The system integrates a lightweight semantic recognition model to perform real-time image acquisition and intelligent classification of the environment, and comprehensively assesses eye risks based on light intensity, eye distance, and eye movement characteristics. It automatically initiates targeted intervention strategies for scenarios with different risk levels.

[0034] Dynamic scene classification Use lightweight semantic segmentation models to recognize scenes such as reading, screens, and outdoor nature in real time; Reason: Accurately distinguishing eye tasks can avoid interference from irrelevant scenes and optimize the logic of myopia prevention and control.

[0035] The scene tag update frequency is ≥1Hz to ensure immediate response to intervention; the high refresh rate can capture scene changes in time to avoid intervention lag.

[0036] Directional Defocus and Contrast Strategy Reading / screen scene: automatically superimpose +1.0D positive defocus and reduce the center contrast by 10%; Reason: The eye axis is easily stretched when reading for a long time or using electronic screens. Positive defocus and reduced contrast can reduce the burden of close-range adjustment.

[0037] Outdoor natural scene: switch to peripheral positive defocus superposition mode; Reason: High outdoor light combined with slight positive defocus helps simulate the protective effect of the natural environment on axial eye growth.

[0038] Outdoor mode silent: turns off central visual stimulation and only provides defocus signals for the periphery (10°–30°); Reason: In real outdoor or simulated outdoor scenes, avoid interference from central content, make peripheral out-of-focus signals more focused, and improve intervention effects.

[0039] Adaptive closed-loop feedback module By collecting the user's key physiological parameters such as blinking frequency, pupil diameter changes, and gaze stability in real time, the system comprehensively judges the degree of visual fatigue and regulatory load status. Based on the feedback information, the system dynamically fine-tunes the stimulation intensity, frequency, and duration of the three modules: the pre-visual stimulation module, the visual training module, and the directional intervention module. It also sends prompts to the user through voice, graphics, or vibration to establish a closed-loop control.

[0040] Multimodal physiological monitoring Eye movement and pupil: sampling frequency ≥ 120 Hz, extracting saccades, fixations, and pupil diameter changes; Reason: High-frequency monitoring can capture subtle physiological changes and provide feedback to adjust training effects and fatigue levels.

[0041] Online strategy optimization Reinforcement learning algorithms automatically fine-tune the defocus intensity and distribution based on short-term feedback (regulation accuracy, fatigue indicators); Reason: Reinforcement learning can explore optimal intervention strategies and achieve personalized dynamic adjustment.

[0042] Long Short-Term Memory (LSTM) predicts myopia progression and triggers long-term parameter adjustments or expert recommendations. Rationale: Time series forecasting can detect abnormal progression in advance and support proactive intervention.

[0043] Dynamically adjust the defocus pattern, contrast distribution, and training task difficulty based on real-time collected eye parameters (such as instantaneous accommodation response, pupil diameter changes, and refractive power fluctuations); Reason: Direct feedback of physiological parameters can further optimize the stimulation effect and improve the accuracy and comfort of prevention and control.

[0044] Automatically select the optimal defocus strategy and mode (positive defocus / negative defocus or mixed mode) based on the real-time monitoring of refractive status and accommodation hysteresis indicators, and switch instantly when the scene changes; Rationale: Precisely matching individual refractive characteristics and accommodation ability can maximize the effect of inhibiting axial length growth.

[0045] Abnormal warning and eye load adaptive mechanism Eye load assessment: The load level is determined by combining the distance, duration, and scene mode (e.g., if the distance is less than 20 cm and the user is using the device for more than 20 minutes continuously in a gaming scenario, the load is considered high); Reason: Closer distances, longer durations, and high-interaction scenarios significantly increase the regulatory burden and require stronger intervention.

[0046] Increase intervention intensity during high workload: When entering a high workload state, the defocus range in the peripheral field of view is automatically expanded (for example, +0.5D increases to +1.5D) and the contrast adjustment area is expanded to 0°–30°; Reason: By enhancing visual stimulation under high load, the elongation of the eye axis can be more effectively inhibited.

[0047] If you use your eyes for more than 30 minutes under high load, the system will automatically switch to the virtual depth of field task. Reason: Prolonged continuous use of the eyes can lead to visual fatigue and constant accommodation. The virtual depth of field switching task is used for assessment and training, relaxes the ciliary muscles, and relieves accommodation tension.

[0048] Cloud / offline deployment module Upload multimodal data to the server in real time, use distributed AI models for batch calculation and analysis; periodically generate individual and group reports and push the latest parameters to devices; store data locally and synchronize regularly to avoid data loss.

[0049] Cloud Batch Optimization Upload multimodal data to the server in real time and use distributed AI models for batch calculation and analysis; Reason: The powerful computing power of the cloud can conduct in-depth mining and model training on large-scale data.

[0050] Generate individual and group reports periodically and push the latest parameters to the device; Rationale: Reports help parents and clinical staff understand the effectiveness of interventions and make informed decisions.

[0051] Offline real-time inference Locally embed lightweight neural networks and databases, supporting ≥90% of functions without a network connection; Reason: To ensure that the system can still provide personalized intervention in the event of a network outage.

[0052] The latest 30 days of data are stored locally and synchronized regularly to avoid data loss.

[0053] Reasoning: Local storage and delayed synchronization mechanisms prevent data loss and protect user privacy.

[0054] System hardware architecture It includes a high-brightness microdisplay, a diffraction grating waveguide, a wide-spectrum LED supplemental light source, a binocular camera and eye-pupil tracking sensor, a high-performance AI processor, and a power management and cooling system to support the efficient operation of the above functional modules.

[0055] Experimental data This invention will explore the effects of AR glasses on the choroid and blood flow, and study their potential for controlling myopia progression.

[0056] method: Participants This prospective comparative study recruited adults with myopia at the Eye Hospital of Wenzhou Medical University. The enrollment criteria for participants were as follows: (1) age 18 to 30 years; (2) binocular spherical equivalent (SE) -1.00 D to -5.75 D, astigmatism ≤ 1.00 D, and anisotropy ≤ 1.00 D; (3) best-corrected visual acuity of at least 0.0 logMAR; (4) intraocular pressure (IOP) ≤ 21 mmHg, with an interocular pressure difference ≤ 5 mmHg; (5) no history of eye surgery, organic eye disease, or systemic disease; and (6) patients who could not adapt to contact lens wear, cognitive impairment, neurological or psychiatric diseases, and uncooperative patients were excluded.

[0057] Intervention and experimental procedures In this study, AR glasses were used in the "on" state as the intervention and in the "off" state as the control (INMO, China; 640×400 per eye, binocular display). The order of turning the glasses on or off was randomized. The experiment employed a self-controlled before-after design. All participants underwent two follow-up visits, with their vision fully corrected with contact lenses. Within one week, participants underwent two reading sessions separated by at least 24 hours. During these two reading sessions, the AR glasses were turned on or off according to the randomized results. All testing was completed between 13:00 and 17:00. Participants read different chapters of the same novel on a tablet computer (Huawei, China, resolution 2560×1600) placed 33 cm away from their eyes in real-world space. To prevent the image from interfering with the participants' normal reading, a white screen image was displayed 2 meters above their field of view for 30 minutes while the AR glasses were on.

[0058] Measurement Choroidal thickness (ChT) and choroidal vascular index (CVI) were obtained before and after near work using swept-source optical coherence tomography angiography (SS-OCT, VG200I, Intalight, Henan, China). Axial length (AL) was measured using a Haag-Streit Lenstar LS900 (Haag Streit AG, Kornitz, Switzerland). All measurements were performed in the right eye. Three measurements were performed for each data set, and the average was calculated.

[0059] Choroidal thickness (ChT) is defined as the distance between the Bruch's membrane (BM) and the inner choroidal interface. A 6mm macular scan area is automatically divided into nine zones: a 1mm central zone (C), a 1mm to 3mm nasal zone (N3), a 1mm to 3mm superior zone (S3), a 1mm to 3mm temporal zone (T3), a 1mm to 3mm inferior zone (I3), a 3mm to 6mm nasal zone (N6), a 3mm to 6mm superior zone (S6), a 3mm to 6mm temporal zone (T6), and a 3mm to 6mm inferior zone (I6). The same OCT device (VG200I) was also used to acquire optical coherence tomography angiography (OCTA) images. Images were automatically divided into nine zones, similar to the ChT zone division.

[0060] Statistical analysis Statistical analysis was performed using SPSS 26.0. Normality was tested using the Shapiro-Wilk test. Repeated-measures analysis of variance (RM-ANOVA) was used to analyze differences in choroidal thickness (ChT), choroidal vascular index (CVI), and axial length (AL) after near work with AR glasses in the "on" and "off" states. A P value less than 0.05 was considered statistically significant. Results are presented as mean ± standard error (SE).

[0061] result A total of 21 participants were enrolled, with one excluded due to poor cooperation. There were 8 males and 13 females. The mean age was 24 ± 0.51 years, and the spherical equivalent (SER) was -3.74 ± 0.32 D. There were no significant differences in choroidal thickness (ChT), choroidal vascular index (CVI), and axial length (AL) between the two follow-up visits (p ≥ 0.189).

[0062] Choroidal thickness AR glasses "on" and "off" states had a significant main effect on choroidal thickness changes after near work (F=15.599, p=0.001). Different body locations had no effect on choroidal thickness changes (F=0.527, p=0.584), and the interaction between AR glasses "on" and "off" states and different body locations was not significant (F=1.407, p=0.257).

[0063] Significant differences were found in C (0-1mm, 3.967±1.389μm, p=0.010), T3 and T6 (1-3mm and 3-6mm, 4.302±1.032μm and 4.429±1.829μm, p<0.001 and p=0.025, respectively), and I6 (3-6mm, 2.731±0.982μm, p=0.012) between the AR glasses on and off states. Choroidal thickness decreased significantly less when the AR glasses were on than when they were off.

[0064] Choroidal vascularity index and axial length There was no significant main effect of AR glasses on or off on the choroidal vascular index (CVI) (F=11.474, p=0.239). Different body locations had no effect on CVI (F=1.979, p=0.160), and the interaction between AR glasses on or off and body location was not significant (F=1.499, p=0.236). No significant differences were observed in axial length changes (F=0.352, p=0.559).

[0065] discuss The results of the present experimental study showed that when AR glasses were turned on, the simulated defocus effect significantly reduced the thinning of choroidal thickness (ChT) after close reading. Although the choroidal vascular index (CVI) and axial length (AL) did not show statistically significant differences, they showed similar trends to the changes in choroidal thickness, suggesting that AR glasses may have certain potential in controlling changes in ocular structure.

[0066] In selecting the defocus region, this study chose to simulate defocus in the superior retinal region, taking into account visual comfort and safety. This choice was based on previous research, particularly the method proposed by Woodman-Pieterse et al. By simulating the defocus signal in the superior retina, the potential risk of occluding the inferior visual field is avoided, especially during dynamic visual tasks. Studies have shown that choroidal changes are more pronounced in the temporal and inferior regions in response to accommodative stimuli, as these regions are more susceptible to visual stimulation. Barbara et al.'s research indicates that the peripheral retina (6 to 10 degrees) in myopic individuals represents the "sweet spot" for positive defocus signals, which is important for controlling axial length growth and accommodative refractive development. Therefore, this study simulated the peripheral defocus signal, specifically in the 1 to 3 mm and 3 to 6 mm regions, and obtained results consistent with previous studies, showing that significant choroidal changes were primarily concentrated in the temporal and inferior regions. These findings further support the feasibility and effectiveness of AR glasses as an intervention tool.

[0067] However, unlike traditional research methods (such as watching movies at a distance), the task in this study was set as reading at close range, which increases the strain on the eyes. Therefore, the results of this study were more significant in the effect of choroidal thickening, and the defocus effect of AR glasses may therefore be more prominent. Compared with the studies of Sander et al. and Zhu et al. using medications (such as atropine) or orthokeratology lenses, the defocus effect in this study was not only reflected in the central area, but also within a smaller defocus area (such as a 1mm central area), the change in choroidal thickness reached 3.967μm, which means that AR glasses may be superior to other conventional methods in the intensity and effectiveness of simulating defocus signals.

[0068] This study also has certain limitations, especially in the selection of participant groups. The participants in this study were all young adults, and in actual clinical applications, especially in children and adolescents with a high incidence of myopia, the effects of AR glasses may be different. Although young adults respond to defocus signals similarly to children, future studies still need to focus on the differences in responses between children and adolescents. At the same time, although this study has used safety-certified AR glasses, their use and purpose are different from traditional glasses or contact lenses, which may affect the wide applicability of the experimental results. In order to further verify the long-term effects of AR glasses, future studies need to conduct long-term follow-up surveys to observe the continued impact of AR glasses on ocular structures (such as choroidal thickness and axial length).

[0069] In summary, AR glasses hold broad promise for myopia prevention and control, particularly in slowing the progression of myopia. By simulating peripheral defocus signals, AR glasses can, to a certain extent, reduce changes in choroidal thickness after close-up eye use, potentially playing a significant role in myopia management. With technological advancements and further validation of their effectiveness, AR glasses are expected to become an innovative and effective intervention tool, providing new insights and solutions for myopia prevention and control.

[0070] The above is only a preferred embodiment of the present invention, and the scope of protection of the present invention is not limited to the above embodiments and experimental examples. Any technical solution that follows the concept of the present invention is included in the scope of protection of the present invention. It should be emphasized that for ordinary technicians in this technical field, without departing from the purpose and scope of the present invention, any modification or equivalent replacement should be regarded as part of the scope of protection of the present invention.

Claims

1. A multimodal visual stimulation and intelligent adaptive combined myopia prevention and control system based on AR glasses, characterized by: include: Visual stimulation module: Leveraging the optical projection capabilities of AR glasses, it dynamically generates personalized stimulation signals within a 10°–30° peripheral field of view. Stimulation parameters are adjusted in real time based on ambient illumination, eye movement characteristics, and usage scenarios, simulating outdoor visual experience and enhancing system load control. Vision Training Module: The central visual field area is presented with dynamic visual tracking tasks, binocular fusion targets, and contrast sensitivity tests to enhance visual convergence and gaze stabilization. The visual training module's system design features a "central-peripheral" visual feedback chain: when central vision training achieves the preset effect, the visual stimulation module automatically and synchronously triggers the intensity and range of peripheral defocus stimulation to enhance peripheral perception response, thereby achieving functional synergy. AI scene dynamic recognition and targeted intervention module: The system integrates a lightweight semantic recognition model to perform real-time image acquisition and intelligent classification of the environment. It also comprehensively assesses eye risks based on light intensity, eye distance, and eye movement characteristics, and automatically initiates targeted intervention strategies for scenarios with different risk levels. Adaptive closed-loop feedback module: By real-time collection of the user's key physiological parameters such as blinking frequency, pupil diameter changes, and gaze stability, the system comprehensively judges the degree of visual fatigue and regulatory load status. Based on the feedback information, the system dynamically fine-tunes the stimulation intensity, frequency, and duration of the three modules: the pre-visual stimulation module, the visual training module, and the directional intervention module. It also issues prompts to the user through voice, graphics, or vibration to establish closed-loop control.

2. The multimodal visual stimulation and intelligent adaptive combined myopia prevention and control system based on AR glasses according to claim 1 is characterized in that: The personalized stimulation signal includes a defocused grating with variable adjustable intensity, a low-contrast disturbance pattern and a spatial frequency stripe.

3. The multimodal visual stimulation and intelligent adaptive combined myopia prevention and control system based on AR glasses according to claim 1 is characterized in that: The stimulation parameters in the visual stimulation module include defocus intensity, contrast, and spatial frequency.

4. The multimodal visual stimulation and intelligent adaptive combined myopia prevention and control system based on AR glasses according to claim 1 is characterized in that: The AI ​​scene dynamic recognition and targeted intervention module automatically initiates targeted intervention strategies for scenarios with different risk levels, including: improving display contrast in low-contrast environments; enhancing defocus signals and spatial frequency regulation during continuous gaze at close range; and adapting high-frequency stimulation compensation in tasks dominated by low-frequency visual stimulation.

5. The multimodal visual stimulation and intelligent adaptive combined myopia prevention and control system based on AR glasses according to claim 1 is characterized in that: The adaptive closed-loop feedback module sends prompts to the user, including rest suggestions, sitting posture adjustment suggestions, and long-distance viewing suggestions.

6. The multimodal visual stimulation and intelligent adaptive combined myopia prevention and control system based on AR glasses according to claim 2, characterized in that: The personalized stimulation signal is in the form of concentric rings or radial gradients.

7. The multimodal visual stimulation and intelligent adaptive combined myopia prevention and control system based on AR glasses according to claim 1, characterized in that: The peripheral visual field in the visual stimulation module also includes three sections: a central visual field of 0°-10°, a mid-peripheral visual field of 10°-20°, and a far peripheral visual field of 20°-30°.

8. The multimodal visual stimulation and intelligent self-adaptive combined myopia prevention and control system based on AR glasses according to claim 7, characterized in that: The contrast gradients of 5%–20% and 20%–50% are set for the middle peripheral visual field and the far peripheral visual field, respectively, to differentially activate the ON / OFF pathways.

9. The multimodal visual stimulation and intelligent self-adaptive combined myopia prevention and control system based on AR glasses according to claim 1, characterized in that: The visual stimulation module dynamically generates personalized stimulation signals in the peripheral visual field 10°-30° area by superimposing a +0.5D to +4.5D positive defocus or -0.5D to -4.5D negative defocus pattern in the peripheral visual field 10°-30° area according to the current refractive power.

10. The multimodal visual stimulation and intelligent self-adaptive combined myopia prevention and control system based on AR glasses according to claim 1, characterized in that: It also includes a cloud / offline deployment module, which uploads multimodal data to the server in real time and uses a distributed AI model for batch calculation and analysis; periodically generates individual and group reports and pushes the latest parameters to the device; and locally stores data and synchronizes it regularly to avoid data loss.

Images