Brain-computer interface smart zoom glasses and visual adaptive adjustment system

Abstract

This invention discloses a brain-computer interface (BCI) smart zoom glasses and a visual adaptive adjustment system, relating to the field of smart glasses technology. It includes an EEG signal acquisition module that attaches to the user's head to collect signals, extracts feature vectors after noise reduction, and transmits them to a core control module; a visual environment perception module that collects target and environmental data, generates structured data packets, and transmits them synchronously; a core control module that integrates multi-source data, identifies visual intent, and decides on adjustment parameters; a smart zoom execution module that adjusts the lens focal length and provides closed-loop feedback to calibrate accuracy; a visual adaptive adjustment module that adjusts lens parameters based on the environment and fatigue state; a human-computer interaction module that supports manual operation, status display, and vibration feedback; and a data storage and update module that stores data and iteratively optimizes the model. This invention achieves accurate visual intent recognition through brain-computer interaction; personalized modeling adapts to different user needs, meeting the product development and application requirements of the wearable smart device manufacturing field.

Description

Technical Field

[0001] This invention relates to the field of smart glasses technology, and more particularly to brain-computer interface smart zoom glasses and a visual adaptive adjustment system. Background Technology

[0002] With the development of brain-computer interfaces and smart wearable technologies, smart zoom glasses, as one of the products in the wearable smart device manufacturing field, are gradually becoming important devices for improving visual experience and adapting to diverse visual needs, and are widely used in daily travel, work and study, medical rehabilitation and other scenarios. Currently, most smart zoom glasses rely on manual touch or voice commands to trigger zooming, which is cumbersome to operate and has a slow response time, failing to accurately match the user's real-time visual intent. The introduction of brain-computer interface technology has made contactless control possible, but existing products in the wearable smart device manufacturing field have insufficient accuracy in acquiring EEG signals, are susceptible to power frequency interference and environmental noise, have limited feature extraction leading to low accuracy in visual intent recognition, and have poor anti-interference capabilities in complex scenarios, making it difficult to meet practical usage needs.

[0003] The lack of adaptability in zoom adjustment mechanisms is a core issue limiting user experience. Existing devices often use fixed preset zoom parameters or simple distance-sensing adjustments, failing to fully integrate multi-dimensional data such as ambient light, target sharpness, and user visual characteristics. This results in an uneven zooming process, easily causing visual dizziness. Furthermore, there is a lack of adjustment strategies for different usage scenarios. In special scenarios such as driving, outdoor sports, and nighttime observation, it is impossible to balance dynamic target tracking accuracy, anti-glare effects, and low-light sharpness, limiting its adaptability. In addition, visual fatigue monitoring and relief functions are inadequate, judging fatigue solely based on usage time without integrating objective physiological indicators such as EEG signals and eye movement parameters. This leads to delayed warnings and limited relief measures, potentially exacerbating visual strain with prolonged use.

[0004] Insufficient low-power management and personalized adaptation capabilities further limit the widespread adoption of these devices. Smart glasses are limited by size and battery capacity, and existing power control strategies are simplistic. The continuous high-load operation of core modules results in short battery life, failing to meet all-day usage needs. Regarding personalized adjustments, only basic parameters such as refractive power are considered, without integrating multi-dimensional data such as user visual preferences, usage habits, and ocular physiological characteristics. Universal adjustment solutions struggle to adapt to the differentiated needs of different groups, such as teenagers, the elderly, and people with myopia. These issues lead to significant shortcomings in the current smart zoom glasses in terms of ease of interaction, adjustment accuracy, scene adaptability, and user comfort. They fail to fully leverage the empowering role of smart technology in visual adjustment, hindering the industrial upgrading and widespread application of smart glasses technology. Summary of the Invention

[0005] The present invention proposes brain-computer interface intelligent zoom glasses and a visual adaptive adjustment system to solve the problems mentioned in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a brain-computer interface intelligent zoom glasses and a visual adaptive adjustment system, comprising the following modules:

[0007] The EEG signal acquisition module is equipped with a flexible EEG electrode array, signal amplification circuit, filtering module and feature extraction unit. It fits the user's forehead and temporal region to acquire visual attention-related EEG signals, and extracts relevant feature vectors after amplification and filtering.

[0008] The visual environment perception module integrates a miniature wide-angle camera, a laser distance sensor, a light sensor, and a color sensor to collect relevant features in real time. It separates the target from the background through an image segmentation algorithm and generates a structured visual environment data package, which is then synchronously transmitted to the core control module.

[0009] The core control module, with its built-in embedded processor and machine learning model, receives EEG signal feature vectors and visual environment data. Through multi-source data fusion algorithm correlation analysis, it identifies visual intentions and combines environmental data to determine zoom and visual adjustment parameters.

[0010] The intelligent zoom execution module includes an electronically controlled liquid crystal zoom lens, a micro drive motor, a displacement sensor and a closed-loop feedback unit. After receiving the zoom command, it adjusts the curvature or spacing of the lens to change the focal length and monitors the adjustment amount through the displacement sensor.

[0011] The visual adaptive adjustment module is equipped with a light feedback adjustment circuit and a parameter optimization unit. It adjusts the lens transmittance, display contrast and blue light protection coefficient according to the ambient light intensity and color temperature, and optimizes the adjustment parameters in combination with the visual fatigue state reflected by the user's EEG signal.

[0012] The human-computer interaction module is equipped with a touch operation panel, a miniature OLED display, and a vibration feedback unit. It supports users to manually switch modes, set the default focal length and adjust the sensitivity, and displays the current focal length, environmental parameters and device status in real time.

[0013] The data storage and update module adopts a dual mode of flash storage and cloud backup, categorizes and stores relevant data, and supports receiving algorithm model update packages via wireless communication.

[0014] Furthermore, it also includes an EEG intention recognition module, which constructs a multi-dimensional EEG feature fusion model, using formulas... Generate a visual intent confidence vector, where For visual intent confidence vector For event-related potential weighting coefficients, The weighting coefficients for brainwave rhythm characteristics. For context-related weight coefficients and + + =1, This is the event-related potential feature matrix. This is the feature vector of brain electrical rhythm. This refers to the matrix dot product operation. For the feature gradient vector, It is a visual context association factor.

[0015] Furthermore, it also includes a dynamic zoom parameter optimization module, which, based on visual environment data and user visual characteristics, uses formulas to optimize zoom parameters. Calculate the optimal zoom parameters, where The optimal zoom parameters include focal length and adjustment rate. This is the distance influence coefficient. The target sharpness coefficient, For user visual characteristic coefficients, The coefficient is the dynamic variation coefficient. For the target distance, For ambient light intensity, As an evaluation metric for target clarity, For user visual characteristic parameters, The rate of change of the target distance.

[0016] Furthermore, it also includes an eye-tracking assistance module, integrating a miniature infrared eye-tracking sensor and a pupil monitoring unit to collect real-time data on the user's eye movement trajectory, pupil diameter changes, fixation point position, and blink frequency. It analyzes the user's visual attention area through fixation point heatmap analysis, and performs spatiotemporal fusion of eye-tracking data and EEG signals. It optimizes visual intent recognition through a multi-source feature association algorithm; dynamically adjusts the intent recognition threshold based on pupil diameter changes; judges the target movement trend through eye-tracking trajectory to predict zoom needs in advance; and assists in judging the degree of visual fatigue based on blink frequency and fixation stability.

[0017] Furthermore, it also includes a low-power intelligent management module, which adopts a module-level power consumption classification strategy to divide the system into three power consumption levels: core working level, standby level, and hibernation level. The current monitoring unit monitors the working current and energy consumption ratio of each module in real time. The core control module dynamically switches the power consumption level according to the activity level of EEG signals and the frequency of changes in the visual environment. When the user has no visual intention input and the environmental parameters are stable for more than a preset time, the system automatically switches to the hibernation level. When EEG signal fluctuations or environmental changes are detected, it quickly wakes up to the core working level. It integrates a micro energy recovery unit, which uses the user's head movement to drive a micro electromagnetic induction device to generate auxiliary power to supplement battery life. At the same time, it optimizes the energy consumption control of the drive motor and zoom lens, and uses pulse width modulation technology to adjust the motor drive current.

[0018] Furthermore, it includes a multi-scenario adaptive switching module, which presets six typical usage scenarios: long-distance observation, close-range reading, dynamic tracking, driving, outdoor sports, and nighttime observation. It constructs a scenario feature library to store adjustment parameter templates for various scenarios. Through the visual environment perception module, it collects target movement speed, ambient light changes, background complexity, and EEG intention features, and performs multi-dimensional fusion to automatically identify the current usage scenario using a decision tree algorithm. It optimizes adjustment strategies for different scenarios. It supports users to customize scenario parameters and store them in the scenario feature library. The system iteratively optimizes scenario templates based on user usage frequency and satisfaction scores.

[0019] Furthermore, it includes a visual fatigue early warning and relief module, constructing a multi-dimensional fatigue assessment model that integrates four major fatigue indicators from EEG signals: alpha wave proportion, pupil blinking frequency, fixation stability, and ocular muscle electroencephalography (EEG). A fatigue index is calculated through weighted summation, classifying fatigue into mild, moderate, and severe levels. For mild fatigue, the system automatically optimizes visual accommodation parameters to reduce visual load. For moderate fatigue, a miniature OLED display prompts the user to perform eye relaxation exercises, simultaneously adjusting lens transmittance and auxiliary light. For severe fatigue, the system automatically reduces zoom adjustment frequency and limits continuous use. A fatigue trend prediction model is established based on the user's historical fatigue data to predict fatigue occurrence points and initiate intervention measures in advance. Simultaneously, relief plans are optimized by combining user vision data and age characteristics.

[0020] Furthermore, it includes a wireless communication and data sharing module, supporting wireless transmission mode and enabling interconnection with terminal devices; users can view detailed usage data through a dedicated APP, customize adjustment parameters and scene modes, and support remote control functions, allowing doctors or professionals to remotely adjust device parameters with authorization; it also works in conjunction with smartwatches to monitor user physiological data and assist in assessing visual fatigue; the system automatically generates periodic visual health reports, analyzes vision change trends based on historical data, provides visual charts and improvement suggestions, and supports anonymous community sharing.

[0021] Furthermore, it includes a fault self-diagnosis and protection module, with built-in multi-channel sensors to monitor the working status of each module in real time; it adopts a graded fault handling mechanism: in case of minor faults, the system automatically starts a calibration program to adjust the sensor position and sensitivity; in case of moderate faults, it switches to a backup drive scheme or enables default parameters to maintain basic functions; in case of severe faults, it immediately cuts off the power to non-essential modules, switches to a safe mode, displays fault codes on the screen, and triggers a high-frequency vibration alarm; it has a fault tracing function, generates a fault analysis report, and stores it in the data module; it supports remote fault diagnosis, allowing users to upload fault codes and reports via an APP, and the cloud server analyzes the data to provide solutions or repair guidance, while also incorporating a built-in hardware protection mechanism.

[0022] Furthermore, it includes a user personalization modeling module that collects multi-dimensional personalized data from users, covering ocular physiological data, visual preference data, and usage habit data, to build a dynamically updated personalized visual model. The core control module dynamically adjusts zoom accuracy, adjustment rate, and visual parameter optimization direction based on this model. For teenagers, parameters are updated in real time as their vision changes. For elderly users, zoom response speed and ease of operation are optimized. For myopic individuals, the focal length is adjusted based on their refractive error. Multi-user switching is supported. The system continuously iterates and optimizes the model based on user usage data and vision change trends, automatically updating parameter configurations every cycle, while also supporting manual fine-tuning of model parameters by users.

[0023] Compared with existing technologies, the beneficial effects of this invention are:

[0024] The brain-computer interface smart zoom glasses and visual adaptive adjustment system of this invention comprehensively break through the bottlenecks of existing technologies, with significant core advantages, greatly improving the convenience of interaction, adjustment accuracy, and user comfort of smart glasses. At the brain-computer interface level, through a flexible electrode array and a multi-dimensional feature fusion model, the accuracy of EEG signal acquisition and anti-interference ability are improved, the mapping relationship between visual intent and EEG signals is strengthened, and accurate recognition and rapid response of visual intent are achieved. This eliminates the cumbersome process of traditional manual or voice control, achieving a contactless and intelligent control experience.

[0025] The zoom adjustment performance has achieved a qualitative leap. The dynamic zoom parameter optimization module integrates multi-dimensional data such as target distance, ambient light, target sharpness, and user visual characteristics. Through collaborative calculation, it generates optimal zoom parameters, ensuring the smoothness and adaptability of the zoom process and reducing the risk of visual dizziness. The multi-scene adaptive switching mechanism achieves precise adaptation to different usage scenarios through scene feature library matching and dynamic adjustment strategy optimization. It takes into account diverse needs such as dynamic target tracking, anti-glare, and low-light sharpness, expanding the applicability of the device.

[0026] The comprehensive visual fatigue management system integrates objective indicators such as EEG signals and eye movement parameters into a multi-dimensional fatigue assessment model. This accurately determines the fatigue level and triggers tiered relief measures, forming a full-process fatigue management mechanism that effectively reduces visual load and protects visual health. The low-power intelligent management strategy significantly extends the device's single-charge battery life through tiered power control, energy recovery, and power prediction optimization, meeting all-day usage needs.

[0027] The personalization capability has been significantly improved. The user personalization modeling module integrates ocular physiological data, visual preferences, and usage habits to build a dynamically updated personalized visual model. This upgrades the system from general adaptation to precise personalized adjustment, catering to the differentiated needs of users of different ages and vision conditions, aligning with the personalized development trend in the wearable smart device manufacturing industry. Simultaneously, robust fault self-diagnosis and data security mechanisms ensure device operational safety and user privacy. Wireless communication and data sharing functions support visual health monitoring and remote guidance, comprehensively promoting the intelligent and user-friendly upgrade of smart glasses technology in the wearable smart device manufacturing industry, and providing users with a higher-quality, safer, and more convenient visual adjustment solution. Attached Figure Description

[0028] Figure 1 This is a schematic block diagram of the brain-computer interface smart zoom glasses and visual adaptive adjustment system proposed in this invention.

[0029] Figure 2 Bar chart showing the accuracy of intent recognition under different EEG feature fusion methods;

[0030] Figure 3 A line graph showing how zoom adjustment response speed changes with usage scenarios;

[0031] Figure 4 A pie chart showing the power consumption percentage of each module in the system. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0034] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified. Furthermore, the terms "installed," "connected," and "linked" should be interpreted broadly; for example, they may refer to a fixed connection, a detachable connection, or an integral connection; they may refer to a mechanical connection or an electrical connection; they may refer to a direct connection or an indirect connection through an intermediate medium; and they may refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. The invention will now be described in further detail with reference to the accompanying drawings.

[0035] Reference Figures 1 to 4 A brain-computer interface smart zoom glasses and visual adaptive adjustment system, comprising the following modules:

[0036] The EEG signal acquisition module is equipped with a flexible EEG electrode array, signal amplification circuit, filtering module and feature extraction unit. It is fitted to the user's forehead and temporal region to acquire visual attention-related EEG signals. The microvolt-level EEG signals are amplified by differential amplifier circuit, and power frequency interference and environmental noise are removed by bandpass filtering and notch filtering. Event-related potentials, EEG rhythm features and visual intention feature vectors are extracted and transmitted to the core control module at a preset frequency.

[0037] The visual environment perception module integrates a miniature wide-angle camera, a laser distance sensor, a light sensor, and a color sensor. It collects the size information, spatial distance, ambient light intensity, color temperature, contrast, and background texture features of the observed target in real time. It separates the target from the background through an image segmentation algorithm, calculates the target clarity evaluation index, and generates a structured visual environment data package, which is synchronously transmitted to the core control module.

[0038] The core control module, with its built-in embedded processor and machine learning model, receives EEG signal feature vectors and visual environment data. Through multi-source data fusion algorithms, it performs correlation analysis to identify the user's visual intentions, including long-distance observation, near-distance reading, and dynamic tracking. It combines environmental data to dynamically determine zoom parameters and visual adjustment parameters, and generates precise control commands to be sent to the execution module.

[0039] The intelligent zoom execution module includes an electronically controlled LCD zoom lens, a micro drive motor, a displacement sensor, and a closed-loop feedback unit. It receives zoom commands from the core control module, adjusts the curvature or spacing of the zoom lens through the drive motor to change the focal length, monitors the lens adjustment amount in real time through the displacement sensor, and compares and calibrates the actual focal length with the target focal length to ensure that the zoom accuracy meets visual requirements.

[0040] The visual adaptive adjustment module is equipped with a light-sensing feedback adjustment circuit and a parameter optimization unit. It dynamically adjusts the lens transmittance, display contrast and blue light protection coefficient according to the ambient light intensity and color temperature. It enhances the light blocking effect in strong light environment and improves the transmittance and supplements soft auxiliary light in weak light environment. It also optimizes the adjustment parameters based on the visual fatigue state reflected by the user's EEG signal.

[0041] The human-computer interaction module is equipped with a touch operation panel, a miniature OLED display screen and a vibration feedback unit. It supports users to manually switch modes, set the default focal length and adjust the sensitivity. The display screen shows the current focal length, environmental parameters and device status in real time. The vibration feedback unit provides tactile prompts when zooming is completed, parameters are optimized or the device malfunctions.

[0042] The data storage and update module adopts a dual mode of flash storage and cloud backup. It categorizes and stores user EEG feature templates, commonly used adjustment parameters, historical visual environment data, and device operation logs. It supports receiving algorithm model update packages via wireless communication, and iteratively optimizes the machine learning model based on user data to improve the accuracy of intent recognition and adjustment adaptability.

[0043] This invention also includes a precise EEG intention recognition module, which constructs a multi-dimensional EEG feature fusion model and uses formulas... Generate a visual intent confidence vector, where For visual intent confidence vector For event-related potential weighting coefficients, The weighting coefficients for brainwave rhythm characteristics. For context-related weight coefficients and + + =1, This is the event-related potential feature matrix. This is the feature vector of brain electrical rhythm. This refers to the matrix dot product operation. For the feature gradient vector, As a visual context association factor, it strengthens the mapping relationship between visual intent and EEG signals through multi-dimensional feature fusion, thereby improving the accuracy and anti-interference ability of intent recognition in complex scenarios.

[0044] This invention also includes a dynamic zoom parameter optimization module, which optimizes zoom parameters based on visual environment data and user visual characteristics using formulas. Calculate the optimal zoom parameters, where The optimal zoom parameters include focal length and adjustment rate. This is the distance influence coefficient. The target sharpness coefficient, For user visual characteristic coefficients, The coefficient is the dynamic variation coefficient. For the target distance, For ambient light intensity, As an evaluation metric for target clarity, For user visual characteristic parameters, including diopter and accommodation sensitivity, To improve the smoothness and adaptability of the zoom process by using multi-factor collaborative calculations to target the rate of change of distance, and reduce visual dizziness caused by rapid zooming.

[0045] This invention also includes an eye-tracking assistance module, integrating a miniature infrared eye-tracking sensor and a pupil monitoring unit. It collects real-time data on the user's eye movement trajectory, pupil diameter changes, fixation point position, and blink frequency. By analyzing the user's visual focus area through a fixation point heatmap, it accurately locates the core area of ​​the observed target. Eye-tracking data is spatiotemporally fused with EEG signals, and a multi-source feature association algorithm optimizes visual intent recognition, reducing the probability of misjudgment from a single signal source. The intent recognition threshold is dynamically adjusted based on pupil diameter changes; recognition sensitivity is improved when the pupil diameter is stable and the fixation point is concentrated, while feature verification strength is enhanced when the pupil fluctuates frequently. The target movement trend is determined by the eye-tracking trajectory, anticipating zoom needs and optimizing zoom response speed. Simultaneously, blink frequency and fixation stability help determine the degree of visual fatigue. When the blink frequency exceeds a set range or the fixation point remains unstable, the zoom adjustment frequency is automatically reduced, and a visual relaxation mode is activated to adjust lens parameters, further improving the system's adjustment accuracy and wearing comfort.

[0046] This invention also includes a low-power intelligent management module, employing a module-level power consumption classification strategy to divide the system into three power consumption levels: core working level, standby level, and hibernation level. A current monitoring unit monitors the operating current and energy consumption ratio of each module in real time. The core control module dynamically switches power consumption levels based on the activity level of EEG signals and the frequency of visual environment changes. When the user does not input visual intent and environmental parameters remain stable for more than a preset time, the system automatically switches to the hibernation level, shutting down unnecessary sensors and the display screen, retaining only the low-sampling-rate monitoring of the EEG signal acquisition module. When fluctuations in EEG signals or environmental changes are detected, the system quickly wakes up to the core working level. An integrated micro energy recovery unit utilizes the user's head movements to drive a micro electromagnetic induction device to generate auxiliary power, supplementing battery life. Simultaneously, it optimizes the energy consumption control of the drive motor and zoom lens, using pulse width modulation technology to adjust the motor drive current and reduce ineffective energy consumption. Through power consumption prediction algorithms, user habits are analyzed, pre-stocking power during high-frequency usage periods and automatically entering energy-saving mode during low-frequency usage periods, significantly extending the device's single-charge runtime.

[0047] This invention also includes a multi-scene adaptive switching module, which presets six typical usage scenarios: long-distance observation, close-range reading, dynamic tracking, driving, outdoor sports, and nighttime observation. A scene feature library is constructed to store optimal adjustment parameter templates for each scenario, including zoom response speed, transmittance range, blue light protection coefficient, and auxiliary light intensity. The system integrates target movement speed, ambient light changes, background complexity, and EEG intent features collected by the visual environment perception module, employing a decision tree algorithm to automatically identify the current usage scenario. When the recognition accuracy falls below a preset threshold, vibration feedback prompts the user for manual confirmation. Adjustment strategies are optimized for different scenarios: in the driving scenario, dynamic target tracking accuracy and anti-glare effects are enhanced; in the outdoor sports scenario, anti-shake capability and fast zoom response are improved; and in the nighttime observation scenario, clarity and auxiliary light softness are optimized in low-light environments. The system supports user-defined scene parameters stored in the scene feature library. Based on user usage frequency and satisfaction ratings, the system iteratively optimizes scene templates, achieving end-to-end scenario-based adjustment from automatic recognition to precise adaptation.

[0048] This invention also includes a visual fatigue early warning and relief module, constructing a multi-dimensional fatigue assessment model that integrates four fatigue indicators from EEG signals: alpha wave proportion, pupil blinking frequency, fixation stability, and ocular muscle electroencephalography (EEG). A fatigue index is calculated through weighted summation, classifying fatigue into mild, moderate, and severe levels. For mild fatigue, the system automatically optimizes visual accommodation parameters to reduce visual load, including fine-tuning focus accuracy and improving contrast. For moderate fatigue, a miniature OLED display prompts the user to perform eye relaxation exercises, simultaneously adjusting lens transmittance and auxiliary light to create a comfortable visual environment. For severe fatigue, the system automatically reduces zoom adjustment frequency, limits continuous use, and triggers vibrations to remind the user to rest. A fatigue trend prediction model is established based on historical user fatigue data to predict fatigue occurrence points and initiate intervention measures. Simultaneously, relief plans are optimized based on user vision data and age characteristics; for adolescent users, the focus is on controlling eye strain intensity, while for elderly users, the focus is on improving visual comfort, forming a comprehensive fatigue management mechanism encompassing monitoring, assessment, early warning, and relief.

[0049] This invention also includes a wireless communication and data sharing module, supporting three wireless transmission modes to achieve interconnection with terminal devices such as smartphones, tablets, and smartwatches. Users can view detailed usage data through a dedicated app, including focus adjustment records, environmental parameter changes, fatigue level statistics, customizable adjustment parameters and scene modes, and remote control functionality. Doctors or professionals can remotely adjust device parameters and provide personalized vision correction suggestions with authorization. It also integrates with smartwatches to monitor users' heart rate, blood oxygen, and other physiological data, assisting in assessing visual fatigue and improving evaluation accuracy. End-to-end encryption algorithms ensure data transmission and storage security, and users can set data access permissions to protect their privacy. The system automatically generates periodic vision health reports, analyzes vision change trends based on historical data, provides visual charts and improvement suggestions, and supports anonymous community sharing. Users can share usage experiences and parameter configurations to help other users optimize usage, while user feedback is collected via the cloud for iterative optimization of system functions.

[0050] This invention also includes a fault self-diagnosis and protection module, with built-in multi-channel sensors to monitor the operating status of each module in real time, covering key indicators such as battery voltage, motor operating current, lens adjustment range, sensor signal integrity, and communication link stability. A tiered fault handling mechanism is adopted: for minor faults such as weak sensor signals, the system automatically initiates a calibration program to adjust the sensor position and sensitivity; for moderate faults such as motor jamming or excessive zoom accuracy deviation, it switches to a backup drive scheme or uses default parameters to maintain basic functions; for severe faults such as lens damage or battery overcharging / over-discharging, it immediately cuts off power to unnecessary modules, switches to a safe mode, displays fault codes on the screen, and triggers a high-frequency vibration alarm. It has a fault tracing function, recording environmental data, operating commands, and equipment operating status at the time of the fault, generating a fault analysis report and storing it in the data module. Remote fault diagnosis is supported; users can upload fault codes and reports via an app, and the cloud server analyzes the data to provide solutions or repair guidance. Simultaneously, a built-in hardware protection mechanism automatically cuts off power when the motor is overloaded, and the battery is equipped with overcharge and over-discharge protection circuits to ensure equipment safety and user visual safety.

[0051] This invention also includes a user-personalized modeling module, which collects multi-dimensional personalized data from users, covering ocular physiological data such as refractive error, astigmatism, axial length, and corneal curvature; visual preference data such as color sensitivity, contrast preference, and visual accommodation rate; and usage habit data such as frequency of common scenarios, usage duration, and fatigue tolerance, to construct a dynamically updated personalized visual model. The core control module dynamically adjusts zoom accuracy, accommodation rate, and visual parameter optimization direction based on this model. For adolescent users, parameters are updated in real time as vision changes, slowing down vision decline; for elderly users, zoom response speed and ease of operation are optimized to adapt to physiological response characteristics; for myopic individuals, the focus is precisely adjusted based on refractive error to reduce eye fatigue. Multi-user switching is supported, storing up to five sets of personalized user models, which can be quickly switched via EEG feature recognition or touch operation to meet the needs of family members. The system continuously iterates and optimizes the model based on user usage data and vision change trends, automatically updating parameter configurations each cycle, while also supporting manual fine-tuning of model parameters by users. This upgrade from general adaptation to personalized precision adjustment significantly improves the user experience and visual adaptation effect for different user groups.

[0052] The following two examples further illustrate the specific implementation of this system:

[0053] Example 1: Application of a versatile brain-computer interface smart zoom glasses system for adults in various daily scenarios

[0054] This embodiment is applied to the daily work and life scenarios of adults, covering multiple scenarios such as long-distance observation of road sign recognition during commutes, close-range reading of office documents, dynamic tracking of outdoor fitness and running, and driving. It needs to achieve accurate recognition of visual intent, adaptive adjustment in multiple scenarios, and long-lasting battery life. The specific implementation process is as follows:

[0055] I. Execution of Core Processes and Key Steps

[0056] 1. System Initialization and EEG Signal Acquisition Module Deployment: After system startup, each module automatically completes self-tests. The flexible EEG electrode array of the EEG signal acquisition module is fitted to the user's mid-forehead and bilateral temporal regions, with the electrode-skin contact resistance controlled within 10 kΩ. The differential amplifier circuit amplifies the microvolt-level EEG signal by 1000 times. Bandpass filtering is used to retain effective EEG signals in the 1 Hz to 30 Hz frequency band, and notch filtering is used to specifically remove 50 Hz power frequency interference. The feature extraction unit acquires signals at 100 Hz, extracting the P300 component from event-related potentials and alpha and beta wave features from EEG rhythms, generating a 32-dimensional visual intent feature vector, which is transmitted to the core control module at 50 Hz.

[0057] 2. Visual Environment Perception and Data Acquisition: The visual environment perception module's miniature wide-angle camera acquires real-time images of the field of view at a frame rate of 30 frames per second. A laser distance sensor simultaneously measures the distance to the observed target at a sampling frequency of 10 Hz. A light sensor and a color sensor acquire ambient light intensity, color temperature, and contrast data, respectively, at a sampling frequency of 5 Hz. The target and background are separated using a semantic segmentation model in the image segmentation algorithm. The target sharpness evaluation index is calculated using the variance gradient method, generating a structured data packet containing target size, spatial distance, light intensity, color temperature, and sharpness, which is then synchronously transmitted to the core control module.

[0058] 3. EEG Intent Recognition and Core Decision Making: Activate the precise EEG intent recognition module, construct a multi-dimensional EEG feature fusion model, and set... =0.4 =0.3 =0.3 and satisfies + + =1, This is a 64×32-dimensional event-related potential feature matrix. This is a 32-dimensional EEG rhythm feature vector. It is a 32-dimensional feature gradient vector. This is the visual context association factor generated based on the environmental data from the previous 10 frames. Substituting it into the formula... Calculated The core control module identifies the user's intention as remote observation when the confidence level is 0.85 for remote observation, 0.12 for close-range reading, and 0.03 for dynamic tracking.

[0059] 4. Dynamic zoom parameter calculation and execution: The dynamic zoom parameter optimization module is activated and settings are executed. =0.3 =0.4 =0.2 =0.1, The distance to the target at 50 meters, as collected by the laser sensor. With an ambient light intensity of 500 lux, The target sharpness evaluation index is 0.8. The visual characteristic parameters with a sensitivity of 0.8 are adjusted for a user's refractive error of 1.0D. The target distance change rate is 0.5 meters per second. Substitute into the formula. The calculated optimal zoom parameters for Pzoom are 0.3 meters per second with a focal length of 50 meters. The micro-drive motor of the intelligent zoom execution module adjusts the spacing between the liquid crystal zoom lenses according to the parameters, the displacement sensor provides real-time feedback on the adjustment amount, and the closed-loop feedback unit compares the actual focal length with the target focal length, stopping the adjustment when the deviation is controlled within 0.1 meters.

[0060] 5. Eye Tracking and Multi-Scene Adaptation: The infrared eye-tracking sensor in the eye-tracking auxiliary module collects eye movement trajectories, pupil diameter (3.5 mm), gaze point position, and blink frequency (15 times per minute). It generates a gaze point heatmap to locate the core area of ​​road signs and spatiotemporally fuses eye-tracking data with EEG signals to optimize intent recognition results. The multi-scene adaptive switching module uses features such as target movement speed (0.8 m / s), ambient light change rate (10 lux / s), and background complexity (0.3) to match driving scenarios with EEG intent. It calls scene templates with anti-glare transmittance parameters of 0.6 and zoom response speed of 0.5 m / s, fine-tunes them, and then executes the adjustment.

[0061] 6. Visual Fatigue Management and Low Power Consumption Control: The visual fatigue early warning and relief module integrates indicators such as alpha wave ratio of 0.3, blink frequency of 15 times per minute, fixation stability of 0.9, and eye muscle electrical signal of 0.2. A weighted summation of these indicators calculates a fatigue index of 0.3, indicating mild fatigue. The system automatically fine-tunes focus accuracy and improves contrast to reduce visual load. The low-power intelligent management module operates at the core working level. The current monitoring unit monitors the current of each module. After 5 minutes of no user input and a stable environment, it switches to sleep mode. The EEG acquisition module's sampling rate drops to 20 Hz, the camera and display are turned off, and the integrated micro energy recovery unit generates 0.5 watts of auxiliary power through head movements to supplement battery life.

[0062] 7. Human-Computer Interaction and Data Management: The OLED display of the human-computer interaction module shows the current focal length (50 meters), ambient light level (500 lux), and device battery level (80%) in real time. A vibration feedback unit generates a slight vibration for 200 milliseconds when zooming is complete. The data storage and update module categorizes and stores EEG feature templates, adjustment parameters, and environmental data. It receives algorithm model update packages via Wi-Fi 6 and iteratively optimizes the machine learning model based on usage data. The wireless communication module synchronizes data to a smartphone app, generating daily vision usage reports. A fault self-diagnosis module monitors the status of each module in real time to ensure normal operation.

[0063] II. Data Representation and Interpretation

[0064] Table 1 Performance Comparison in Daily Use Scenarios

[0065]

[0066] Table 1 clearly demonstrates the significant advantages of this invention in various everyday scenarios. Existing smart zoom glasses suffer from insufficient optimization of a single zoom parameter in EEG intent recognition, resulting in an accuracy rate of only 72% and a scene adaptation accuracy rate of 68%, failing to accurately match user needs. This invention, through multi-dimensional EEG feature fusion and multi-source data collaborative optimization, improves both intent recognition and scene adaptation accuracy to over 95%, with excellent zoom smoothness. Mild fatigue relief measures effectively reduce visual load, and low-power management strategies extend battery life to 12 hours, meeting all-day usage needs. Overall performance surpasses existing devices, simultaneously improving interactivity, adjustment accuracy, and user comfort, adapting to diverse daily visual needs.

[0067] Example 2: Application of a Brain-Computer Interactive Smart Zoom Glasses System for Myopia Prevention in Adolescents

[0068] This embodiment is applied to myopia prevention and control scenarios for teenagers aged 10 to 15. It needs to take into account scenarios such as close-range observation during study and reading, distant viewing outdoors, and low-light environments for studying at night. The focus is on achieving personalized visual adjustment, accurate fatigue monitoring, and assistance in myopia prevention and control. The specific implementation process is as follows:

[0069] I. Execution of Core Processes and Key Steps

[0070] 1. Personalized Modeling and System Initialization: The user personalized modeling module collects ocular physiological data of a teenager, including refractive error of 1.5D, astigmatism of 0.5D, axial length of 24.5 mm, and corneal curvature of 43D; visual preference data, including color sensitivity of 0.8, contrast preference of 0.7, and accommodation rate of 0.6; and usage habit data, including 70% for studying and reading, 20% for outdoor use, and 10% for nighttime use. A personalized visual model is then constructed and stored. After system startup, the model is quickly matched using EEG feature recognition to complete the initial parameter configuration.

[0071] 2. EEG Signal Acquisition and Intent Recognition: The lightweight design of the flexible EEG electrode array adapts to the head contours of adolescents, conforming to the forehead and temporal regions. A differential amplifier circuit amplifies microvolt-level EEG signals, and bandpass filtering from 1 Hz to 30 Hz and notch filtering from 50 Hz remove interference. A feature extraction unit extracts event-related potential (ERP) EEG rhythm features to generate a 32-dimensional vector. A precise EEG intent recognition module is also included. =0.45 =0.3 =0.25, substitute 64×32 dimensional matrix 32-dimensional vector 32-dimensional vector Context factors, calculated using a formula The vector indicates that the intended action is close-range reading when the confidence level is 0.9 for close-range reading, 0.08 for distant observation, and 0.02 for dynamic tracking.

[0072] 3. Visual Environment Perception and Zoom Adjustment: The visual environment perception module collects environmental data at a target distance of 0.3 meters, ambient light of 300 lux, color temperature of 4500K, and contrast of 0.6. An image segmentation algorithm separates the document text from the desktop background, calculating a sharpness evaluation index of 0.75. The dynamic zoom parameter optimization module sets... =0.25 =0.45 =0.2 =0.1, The parameter is set to adjust the sensitivity to 0.6 for a refractive power of 1.5D. The distance change rate is 0.1 meters per second. Substituting this into the formula, we get... The parameters are: focal length 0.3 meters, adjustment rate 0.2 meters per second. The intelligent zoom execution module adjusts the lens curvature, the displacement sensor provides feedback on the adjustment amount, and after closed-loop calibration, the focal length deviation is controlled within 0.01 meters.

[0073] 4. Eye Tracking and Fatigue Monitoring: The eye tracking auxiliary module collects eye movement trajectories, pupil diameter (3 mm), fixation point location, and blink frequency (20 times per minute), generating a fixation point heatmap to locate text areas in documents. This data is then fused with EEG signals to optimize intent recognition. The visual fatigue warning and relief module integrates indicators such as alpha wave ratio (0.4), blink frequency (20 times per minute), fixation stability (0.7), and eye muscle electrical signal (0.3). A weighted summation of these indicators yields a fatigue index of 0.6, indicating moderate fatigue. The OLED display provides prompts for eye relaxation training, and the lens transmittance is adjusted to 0.7, while the auxiliary light intensity is adjusted to 0.3 to create a comfortable environment.

[0074] 5. Multi-Scene Adaptation and Low-Power Management: The multi-scene adaptive switching module matches the learning and reading scenarios, calling parameter templates with a zoom response speed of 0.2 meters per second, a blue light protection factor of 0.8, and an auxiliary light color temperature of 4000K. When used outdoors, after identifying the scene through environmental perception, it switches to long-distance observation parameters, increasing light transmittance by 0.9 to enhance anti-shake capabilities. During nighttime learning, it optimizes low-light clarity and reduces auxiliary light intensity to avoid glare. The low-power module predicts usage habits, operating at core working level during learning periods, standby level outdoors, and low-power level at night, with the energy recovery unit supplementing battery life and extending single-use time.

[0075] 6. Data Sharing and Fault Protection: The wireless communication module synchronizes data to the parent's smartphone app via Bluetooth 5.0, generating periodic reports on the teenager's vision usage log, fatigue level statistics, and usage scenario distribution. The fault self-diagnosis module monitors battery voltage, motor current, and lens adjustment range, automatically initiating a calibration program when weak sensor signals are detected to ensure safe device operation. The system supports multi-user switching and can store 5 sets of family member models to meet the needs of family sharing.

[0076] II. Data Representation and Interpretation

[0077] Table 2 Comparison of performance in various scenarios for myopia prevention and control among teenagers

[0078]

[0079] Table 2 highlights the core advantages of this invention in the context of myopia prevention and control among teenagers. Existing smart glasses for teenagers lack comprehensive personalized modeling, have generally poor adaptability, a fatigue recognition accuracy rate of only 65%, poor clarity in low-light environments, and limited blue light protection. This invention achieves excellent personalized adaptation through multi-dimensional personalized data modeling, increasing the fatigue level recognition accuracy to 94% and accurately triggering tiered mitigation measures. Optimized adjustment in low-light environments ensures clarity, significant blue light protection reduces vision damage, and convenient multi-user switching meets the needs of family use. The overall solution aligns with the visual characteristics and usage habits of teenagers, providing effective technical support for myopia prevention and control, and improving user comfort and visual health protection.

[0080] Reference Figure 2This figure visually illustrates the impact of different EEG feature fusion methods on visual intent recognition, reflecting the technical advantages of the multi-dimensional feature fusion model of this invention. The fusion of single event-related potentials (ERPs) and EEG rhythms, due to their limited feature dimensions, achieves recognition accuracies of only 72% and 75%, respectively, failing to effectively cope with interference from complex EEG signals. Feature gradient fusion and context-related fusion, by supplementing feature change trends and environmental information, improve accuracy to 83% and 88%, respectively, but still lack the synergistic effect of multi-dimensional features. The multi-dimensional feature fusion method employed in this invention integrates EEPs, EEG rhythms, feature gradients, and context-related factors, strengthening the mapping relationship between visual intent and EEG signals through weighted combination, achieving an accuracy of 96%. This significantly reduces the misjudgment probability of single-feature fusion, enabling accurate recognition of visual intent in complex scenarios and laying a core technical foundation for contactless control in brain-computer interfaces.

[0081] Reference Figure 3 This figure clearly demonstrates the significant advantage of this invention in zoom adjustment response speed across different scenarios, overcoming the response lag problem of traditional adjustment methods. Traditional adjustment methods use fixed parameters and do not optimize response strategies based on scene characteristics. In outdoor sports scenarios, due to the need for dynamic target tracking, the response speed is only 0.3 seconds, unable to adapt to rapidly changing visual demands; in driving scenarios, the response speed is 0.4 seconds, posing a risk of visual adjustment delay. This invention, through a dynamic zoom parameter optimization module, combined with scene feature library matching and predictive adjustment strategies, controls the response speed in all scenarios to within 0.15 seconds, and even as low as 0.08 seconds in driving scenarios, achieving instant zoom adjustment response. This scenario-based response speed optimization allows the system to accurately match the visual change rhythm of different scenarios, improving visual continuity and comfort during use.

[0082] Reference Figure 4 This diagram clearly illustrates the optimized power distribution and low-power management of this invention, demonstrating the energy efficiency rationality of the module design. The core control module, integrating machine learning models and multi-source data fusion algorithms, accounts for the highest power consumption, reaching 25%. Therefore, this invention reduces ineffective power consumption while ensuring computational accuracy through lightweight algorithms and dynamic computing power allocation. The intelligent zoom execution module, due to motor drive requirements, accounts for 22% of power consumption; pulse width modulation technology is used to optimize motor current and reduce energy consumption. The visual environment perception module and EEG signal acquisition module account for 20% and 15% respectively; intermittent sampling strategies reduce continuous power consumption. The auxiliary function module accounts for 18%, and a sleep-wake mechanism is used for further energy saving. The overall power distribution is balanced. The energy efficiency optimization of the core modules combined with the low-power design of the auxiliary modules allows the system to effectively extend single-charge runtime while achieving complex functions, meeting the needs of all-day use.

[0083] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A brain-computer interface intelligent zoom glasses and a visual adaptive adjustment system, characterized in that, Includes the following modules: The EEG signal acquisition module is equipped with a flexible EEG electrode array, signal amplification circuit, filtering module and feature extraction unit. It fits the user's forehead and temporal region to acquire visual attention-related EEG signals, and extracts relevant feature vectors after amplification and filtering. The visual environment perception module integrates a miniature wide-angle camera, a laser distance sensor, a light sensor, and a color sensor to collect relevant features in real time. It separates the target from the background through an image segmentation algorithm and generates a structured visual environment data package, which is then synchronously transmitted to the core control module. The core control module, with its built-in embedded processor and machine learning model, receives EEG signal feature vectors and visual environment data. Through multi-source data fusion algorithm correlation analysis, it identifies visual intentions and combines environmental data to determine zoom and visual adjustment parameters. The intelligent zoom execution module includes an electronically controlled liquid crystal zoom lens, a micro drive motor, a displacement sensor and a closed-loop feedback unit. After receiving the zoom command, it adjusts the curvature or spacing of the lens to change the focal length and monitors the adjustment amount through the displacement sensor. The visual adaptive adjustment module is equipped with a light feedback adjustment circuit and a parameter optimization unit. It adjusts the lens transmittance, display contrast and blue light protection coefficient according to the ambient light intensity and color temperature, and optimizes the adjustment parameters in combination with the visual fatigue state reflected by the user's EEG signal. The human-computer interaction module is equipped with a touch operation panel, a miniature OLED display, and a vibration feedback unit. It supports users to manually switch modes, set the default focal length and adjust the sensitivity, and displays the current focal length, environmental parameters and device status in real time. The data storage and update module adopts a dual mode of flash storage and cloud backup, categorizes and stores relevant data, and supports receiving algorithm model update packages via wireless communication. The EEG intention recognition module constructs a multi-dimensional EEG feature fusion model, which uses formulas... Generate a visual intent confidence vector, where For visual intent confidence vector For event-related potential weighting coefficients, The weighting coefficients for brainwave rhythm characteristics. For context-related weight coefficients and + + =1, This is the event-related potential feature matrix. This is the feature vector of brain electrical rhythm. This refers to the matrix dot product operation. For the feature gradient vector, Visual contextual factors; The dynamic zoom parameter optimization module, based on visual environment data and user visual characteristics, uses formulas... Calculate the optimal zoom parameters, where The optimal zoom parameters include focal length and adjustment rate. This is the distance influence coefficient. The target sharpness coefficient, For user visual characteristic coefficients, The coefficient is the dynamic variation coefficient. For the target distance, For ambient light intensity, As an evaluation metric for target clarity, For user visual characteristic parameters, The rate of change of the target distance.

2. The brain-computer interface intelligent zoom glasses and visual adaptive adjustment system according to claim 1, characterized in that, It also includes an eye-tracking assistance module, which integrates a miniature infrared eye-tracking sensor and a pupil monitoring unit to collect real-time data on the user's eye movement trajectory, pupil diameter changes, fixation point position, and blink frequency. It analyzes the user's visual attention area through fixation point heatmap analysis, and performs spatiotemporal fusion of eye-tracking data and EEG signals. It optimizes visual intent recognition through a multi-source feature association algorithm; dynamically adjusts the intent recognition threshold based on pupil diameter changes; judges the target movement trend through eye-tracking trajectory to predict zoom needs in advance; and assists in judging the degree of visual fatigue based on blink frequency and fixation stability.

3. The brain-computer interface intelligent zoom glasses and visual adaptive adjustment system according to claim 1, characterized in that, It also includes a low-power intelligent management module, which adopts a module-level power consumption classification strategy to divide the system into three power consumption levels: core working level, standby level, and hibernation level. The current monitoring unit monitors the working current and energy consumption ratio of each module in real time. The core control module dynamically switches the power consumption level according to the activity of EEG signals and the frequency of changes in the visual environment. When the user has no visual intention input and the environmental parameters are stable for more than a preset time, the system automatically switches to the hibernation level. When EEG signal fluctuations or environmental changes are detected, it quickly wakes up to the core working level. It integrates a micro energy recovery unit, which uses the user's head movement to drive a micro electromagnetic induction device to generate auxiliary power to supplement battery life. At the same time, it optimizes the energy consumption control of the drive motor and zoom lens, and uses pulse width modulation technology to adjust the motor drive current.

4. The brain-computer interface intelligent zoom glasses and visual adaptive adjustment system according to claim 1, characterized in that, It also includes a multi-scenario adaptive switching module, which presets six typical usage scenarios: long-distance observation, close-range reading, dynamic tracking, driving, outdoor sports, and night observation, and builds a scenario feature library to store adjustment parameter templates for various scenarios; The system integrates target movement speed, ambient lighting changes, background complexity, and EEG intent features collected by the visual environment perception module, and automatically identifies the current usage scenario using a decision tree algorithm; it also optimizes adjustment strategies for different scenarios. The system supports users to customize scene parameters and store them in the scene feature library. The system iteratively optimizes scene templates based on user usage frequency and satisfaction ratings.

5. The brain-computer interface intelligent zoom glasses and visual adaptive adjustment system according to claim 1, characterized in that, It also includes a visual fatigue warning and relief module, which constructs a multi-dimensional fatigue assessment model. It integrates four major fatigue indicators from EEG signals: alpha wave proportion, pupil blinking frequency, fixation stability, and eye muscle electrical signals. By calculating the fatigue index through weighted summation, it classifies fatigue into three levels: mild, moderate, and severe. When fatigue is mild, the system automatically optimizes visual accommodation parameters to reduce visual load. When fatigue is moderate, it prompts the user to perform eye relaxation training through a miniature OLED display and simultaneously adjusts lens transmittance and auxiliary light. When fatigue is severe, it automatically reduces the zoom adjustment frequency and limits continuous use time. A fatigue trend prediction model is established based on users' historical fatigue data to predict fatigue occurrence points in advance and initiate intervention measures. At the same time, the relief plan is optimized by combining users' vision data and age characteristics.

6. The brain-computer interface intelligent zoom glasses and visual adaptive adjustment system according to claim 1, characterized in that, It also includes a wireless communication and data sharing module, which supports wireless transmission mode and completes interconnection with terminal devices; users can view detailed usage data through a dedicated APP, customize and adjust parameters and scene modes, and support remote control functions, allowing doctors or professionals to remotely adjust device parameters with authorization. It can work in conjunction with smartwatches to monitor users' physiological data and help determine visual fatigue levels. The system automatically generates periodic vision health reports, analyzes vision change trends based on historical data, provides visual charts and improvement suggestions, and supports anonymous community sharing.

7. The brain-computer interface intelligent zoom glasses and visual adaptive adjustment system according to claim 1, characterized in that, It also includes a fault self-diagnosis and protection module, with built-in multi-channel sensors to monitor the working status of each module in real time; it adopts a graded fault handling mechanism. In case of minor faults, the system automatically starts a calibration program to adjust the sensor position and sensitivity; in case of moderate faults, it switches to a backup drive scheme or enables default parameters to maintain basic functions; in case of severe faults, it immediately cuts off the power to non-essential modules, switches to a safe mode, displays fault codes on the display screen, and triggers a high-frequency vibration alarm; it has a fault tracing function and generates a fault analysis report which is stored in the data module. It supports remote fault diagnosis. Users can upload fault codes and reports through the APP, and the cloud server will analyze them and provide solutions or maintenance guidance. It also has a built-in hardware protection mechanism.

8. The brain-computer interface intelligent zoom glasses and visual adaptive adjustment system according to claim 1, characterized in that, It also includes a user personalization modeling module, which collects multi-dimensional personalized data of users, covering eye physiological data, visual preference data, and usage habit data, and builds a dynamically updated personalized visual model. The core control module dynamically adjusts zoom accuracy, adjustment rate, and visual parameter optimization direction based on this model. For teenagers, the parameters are updated in real time as their vision changes; for elderly users, the zoom response speed and ease of operation are optimized; and for nearsighted individuals, the focal length is adjusted according to their refractive error. It supports multi-user switching; the system continuously iterates and optimizes the model based on user data and vision change trends, automatically updates parameter configurations every cycle, and also supports users to manually fine-tune model parameters.

Images