Modularized head ring glasses device combining brain wave monitoring and intelligent feedback

Abstract

The invention discloses a brain wave monitoring and intelligent feedback combined modularized head ring glasses device, and relates to the technical field of brain wave sensing and adjusting equipment.According to the device, brain electrical activities, eye movement behaviors, eye fatigue states, wearing fitness of the head ring glasses device, environmental noise interference and use situations of a user are monitored in real time; the brain wave fitting quality index is calculated through the pressure variance, the EEG signal-to-noise ratio and the historical template fitting degree, and self-adaptive compensation adjustment is carried out when the brain wave fitting quality index is unqualified; combining electroencephalogram and eye movement characteristics to calculate a brain-eye collaborative concentration index, and generating a comprehensive adjustment strategy when the brain-eye collaborative concentration index does not reach the standard; and calculating an emotional scene switching index according to the brain wave emotional characteristics, the situation parameters and the historical trend, and triggering personalized emotional regulation when the emotional scene switching index is not matched with the situation parameters. The device can quantify the brain wave and behavior state of the user in real time, realizes intelligent concentration and emotion management, and improves the reliability and individual suitability of electroencephalogram monitoring.

Description

Technical Field

[0001] This invention relates to the field of brainwave sensing and modulation equipment technology, specifically a modular headband glasses device that combines brainwave monitoring and intelligent feedback. Background Technology

[0002] With the development of wearable devices and brain-computer interface technology, EEG-based brainwave monitoring devices and smart glasses combined with visual terminals have gradually become research and industrialization hotspots. Existing related products and research mainly focus on single-form head-mounted or glasses-style acquisition devices, single-channel or multi-channel EEG acquisition and simple physiological parameter monitoring, and basic state recognition and feedback control based on cloud or local algorithms. These devices are widely used in applications such as stress detection, focus training, meditation assistance, sleep monitoring, and health management, enabling monitoring and simple intervention of users' mental states to a certain extent.

[0003] However, existing technologies still have several shortcomings, limiting the reliability, comfort, and intelligence level of the equipment in practical applications. The main problems include:

[0004] EEG signal quality is easily affected by the fit of the wearer. Traditional dry electrode structures rely on a fixed pressing method to achieve contact between the electrode and the skin. However, different users have different head shapes, which can easily lead to uneven contact pressure, local detachment, and contact impedance fluctuations during long-term wear. This results in unstable EEG signal energy distribution and severe noise mixing, which in turn affects recognition accuracy.

[0005] Existing systems generally use a single channel or simple filtering algorithm to process EEG and eye movement signals, which have weak anti-interference capabilities. In multi-scenario environments such as noise, changes in lighting, or head movements, EEG signals may be mixed with multi-source interference such as EMG, motion artifacts, and light flicker noise. However, most devices lack the synchronous acquisition of multi-modal environmental parameters, making it difficult to achieve dynamic modeling and real-time suppression of complex interference.

[0006] There is a lack of systematic modeling of the synergistic relationship between EEG and eye movement. Existing products generally only use a single indicator such as EEG or EOG to judge focus. They also lack the correlation analysis between blink frequency, saccade speed and visual fatigue signals, and cannot effectively establish the coupling relationship between brain cognitive state and eye behavior, resulting in limited accuracy of focus judgment.

[0007] Existing smart glasses and brainwave feedback systems generally adopt static rules or simple prompts, lacking adaptive feedback capabilities based on context and historical templates. The devices usually do not have the ability to understand multi-dimensional contextual information such as user emotional trends, usage scenarios, time periods, and visual load, nor do they have the ability to perform long-term tracking and trend judgment based on historical brainwave templates. Therefore, they cannot form an effective personalized feedback loop. Summary of the Invention

[0008] To address the shortcomings of existing technologies, this invention provides a modular headband glasses device that combines brainwave monitoring and intelligent feedback, thereby solving the problems mentioned in the background art.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a modular headband glasses device combining brainwave monitoring and intelligent feedback, comprising:

[0010] A multi-dimensional data acquisition module is used to monitor the user's brain activity in real time, acquiring delta-wave EEG energy parameter sequences EEGδ(t), theta-wave EEG energy parameter sequences EEGθ(t), alpha-wave EEG energy parameter sequences EEGα(t), and beta-wave EEG energy parameter sequences EEGβ(t); to monitor the user's eye movement behavior and eye fatigue status in real time, acquiring blink frequency Blink(t), saccade velocity Sacc(t), and eye fatigue index Efat(t); to monitor the fit of the headband glasses device, environmental noise interference, and usage context in real time; and to acquire scene index parameter G(t), time period parameter Td(t), and historical template parameter HEEG(t).

[0011] The neural state quantification module is used to extract multi-source brain-pressure synergistic features, including pressure variance. EEG signal-to-noise ratio Fit to historical templates The brainwave fit quality index (BQI) is calculated and compared with the fit quality threshold (Bth) to determine whether the EEG fit quality is qualified. If it is not qualified, adaptive compensation adjustment is performed.

[0012] The dual-modal collaborative recognition module is used to extract the alpha wave EEG energy parameter sequence EEGα(t) and the beta wave EEG energy parameter sequence EEGβ(t), and combine them with the blink frequency Blink(t), eye saccade velocity Sacc(t) and eye fatigue index Efat(t) to calculate the brain-eye coordination focus index FCI, and compare it with the coordination focus threshold Fth to determine whether the user's brain-eye coordination meets the standard. If it does not meet the standard, a comprehensive adjustment strategy is implemented.

[0013] The emotion-context adaptive adjustment module is used to extract contextualized brainwave features, including the emotion brainwave index MoodEEG(t), context feature parameter Ctx(t), and historical brainwave trend parameter HEEGtrend(t). It calculates and obtains the emotion scenario switching index ESC and compares it with the emotion scenario switching threshold Eth to determine whether the user's current brainwave emotion features are suitable for the external context. If they are not suitable, an emotion scenario switching strategy is implemented.

[0014] Preferably, the multi-dimensional data acquisition module includes an electroencephalogram (EEG) signal acquisition unit, an eye movement micro-expression acquisition unit, and a wearing fit environment interference acquisition unit;

[0015] The EEG signal acquisition unit is used to monitor the user's brain activity in real time. A multi-channel dry electrode EEG acquisition device is installed in the inner headband contact area of ​​the headband glasses device to acquire raw EEG signals of δ, θ, α and β respectively. Multi-band spectral analysis technology and short-time Fourier transform (STFT) method are used to denoise, divide the frequency and extract the energy envelope of the raw EEG signals of δ, θ, α and β to obtain the δ wave EEG energy parameter sequence EEGδ(t), the θ wave EEG energy parameter sequence EEGθ(t), the α wave EEG energy parameter sequence EEGα(t) and the β wave EEG energy parameter sequence EEGβ(t).

[0016] The eye movement micro-expression acquisition unit is used to monitor the user's eye movement behavior and eye fatigue status in real time. By installing an EOG electrode array in the nose bridge support area inside the frame of the headband glasses device, the raw EOG signals of blink frequency, saccade velocity, and eye fatigue potential sequence are acquired. Using eye potential difference analysis technology and eye movement trajectory model reconstruction method, peak detection, displacement calculation, and potential sequence filtering are performed on the raw EOG signals to obtain blink frequency Blink(t), saccade velocity Sacc(t), and eye fatigue index Efat(t).

[0017] The wearing fit environmental interference acquisition unit is used to monitor the wearing fit, environmental noise interference, and usage scenarios of the headband glasses device in real time. It collects contact pressure data by deploying a DACO miniature contact pressure sensor array inside the headband and at the temple joints of the headband glasses device. Contact pressure field gradient analysis technology is used to perform distribution modeling and dynamic fit reconstruction of the pressure data to obtain the contact pressure distribution. By installing a noise detection microphone, a light sensor, and a miniature inertial measurement unit (IMU) on the outside of the glasses frame, ambient noise dB(t), light intensity Lux(t), and head micro-movement sequence Mv(t) are collected. By connecting GPS and time management components to the communication device of the headband glasses, GPS scene G(t) and usage time period Td(t) are collected, and the user's historical brainwave template is synchronized from the cloud. The context recognition and template matching analysis methods are used to perform pattern modeling and context analysis to obtain the scene index parameter G(t), time period parameter Td(t), and historical template parameter HEEG(t).

[0018] Preferably, the neural state quantification module includes a multi-source brain-pressure collaborative feature extraction unit, a first calculation unit, and a first analysis unit;

[0019] The multi-source brain-pressure collaborative feature extraction unit is used to extract features based on the acquired contact pressure distribution. Contact pressure field variance analysis technology was used to perform dynamic statistics and stability reconstruction on pressure distribution data to obtain pressure variance. Based on the acquired delta-wave EEG energy parameter sequences (EEGδ(t), theta-wave EEGθ(t), alpha-wave EEGα(t), and beta-wave EEGβ(t), a signal-to-noise ratio (SNR) estimation method and a multi-channel noise stripping algorithm were used. After normalization, energy calculation and noise modeling were performed on the signals in each frequency band to obtain the EEG SNR. Based on the collected historical template parameters HEEG(t) from users, template matching correlation analysis is used to compare the similarity and calculate the matching degree of the current EEG spectral features, thereby obtaining the historical template fitting degree. .

[0020] Preferably, the first calculation unit is used to extract the pressure variance. EEG signal-to-noise ratio Fit to historical templates After dimensionless processing, the brainwave fit quality index (BQI) is calculated and obtained.

[0021] Preferably, the first analysis unit is used to obtain a first evaluation result by comparing the EEG fit quality index (BQI) with the fit quality threshold (Bth) through a preset fit quality threshold (Bth):

[0022] When the EEG fit quality index BQI is greater than or equal to the fit quality threshold Bth, it indicates that the EEG fit quality is qualified, the signal is stable, and continuous monitoring is possible.

[0023] When the EEG fit quality index (BQI) is less than the fit quality threshold (Bth), it indicates that the EEG fit quality is substandard, posing a risk of unstable contact, noise drift, or signal attenuation. This triggers the first warning instruction and generates the first strategy: based on contact pressure distribution. By employing contact pressure field gradient analysis and DACO deformation compensation control methods, the local damping coefficient and micro-deformation of the DAO magnetorheological microstructure are adjusted in real time. This compensates for the local pressure in the weak pressure zone and appropriately releases the pressure in the strong pressure zone, thereby improving the uniformity of contact pressure distribution and reducing the fluctuation amplitude of Var(Pt). The real-time EEG signal-to-noise ratio is continuously monitored. If within a consecutive 2-second time window, If there is no improvement trend, it is determined that the DCO adjustment cannot effectively improve the fit, and the user is automatically prompted to "slightly adjust the wearing position" to prompt manual correction of the contact impedance and fit structure. Based on the collected noise and context data, including ambient noise dB(t), light intensity Lux(t), head micro-movement sequence Mv(t), GPS scene G(t), usage time Td(t), and user historical template parameter HEEG(t), the ambient noise dB(t), light intensity Lux(t), and head micro-movement sequence Mv(t) are spectrally estimated and interference mode decomposed using the environmental interference adaptive filtering method ANC-LMS / RLS to form the environmental noise prediction component N̂(t). Using the context recognition and template matching method, the expected template waveform EEGtemplate(t) of the EEG in the current scene is obtained based on the GPS scene G(t), usage time Td(t), and user historical template parameter HEEG(t). The noise deviation ΔN(t) is further generated: adaptive compensation adjustment is performed based on the noise deviation ΔN(t).

[0024] Preferably, the dual-modal collaborative recognition module includes a second computing unit and a second analysis unit;

[0025] The second calculation unit is used to extract the α-wave EEG energy parameter sequence EEGα(t) and the β-wave EEG energy parameter sequence EEGβ(t), and combine them with the blink frequency Blink(t), eye saccade velocity Sacc(t) and eye fatigue index Efat(t), and then use a weighted combination algorithm to calculate the brain-eye coordination focus index FCI after dimensionless processing.

[0026] Preferably, the second analysis unit is used to obtain a second evaluation result by comparing the brain-eye coordination focus index (FCI) with the preset coordination focus threshold (Fth) and the coordination focus threshold (Fth):

[0027] When the Brain-Eye Coordination Attention Index (FCI) is greater than or equal to the Coordination Attention Thres (Fth), it indicates that the user's brain-eye coordination has met the standard and the user is in a stable state of focus, which will be continuously monitored.

[0028] When the Brain-Eye Coordination Attention Index (FCI) is less than the Coordination Attention Threshold (Fth), it indicates that the user's brain-eye coordination has not met the standard, and the user is at risk of decreased attention or emotional fluctuations. This triggers a second warning instruction and generates a second strategy: A brain-eye coordination regulation method is used to comprehensively adjust the feedback channels, prompting mechanisms, and contextual guidance interface of the headband glasses device. This involves activating a coordination feedback mode oriented towards attention maintenance, prioritizing the response of attention-related channels on the brainwave side, and constructing an individualized attention support sequence based on the user's current eye movement state. Through behavioral segment alignment, feature association calculation, and pattern modeling methods, a brain-eye behavioral coupling relationship is generated. Furthermore, a targeted attention maintenance plan is generated, including comprehensive adjustment of the user's visual load, task status, and environmental interference, guiding the user to restore stable focus in the current usage context. Simultaneously, a matching analysis of the causes of this attention decline is performed to generate real-time attention improvement feedback.

[0029] Preferably, the emotion-context adaptive regulation module includes a contextualized brainwave feature extraction unit, a third calculation unit, and a third analysis unit;

[0030] The contextualized EEG feature extraction unit is used to perform multi-band energy ratio analysis based on the delta-wave EEG energy parameter sequence EEGδ(t), the theta-wave EEG energy parameter sequence EEGθ(t), the alpha-wave EEG energy parameter sequence EEGα(t), and the beta-wave EEG energy parameter sequence EEGβ(t). It then extracts immediate emotional features using a short-time energy sliding window model to obtain the emotional EEG index MoodEEG(t). Based on the scene index parameter G(t) and the time period parameter Td(t), it uses a context recognition and template matching analysis method to generate the context feature parameter Ctx(t) through scene index matching and time period pattern modeling. Based on the historical template parameter HEEG(t), it uses historical template fitting trend analysis technology to perform difference calculation and trend regression on the change direction of the current EEG energy pattern and the historical template to obtain the historical EEG trend parameter HEEGtrend(t).

[0031] Preferably, the third calculation unit is used to calculate the Emotional Scene Switching Index (ESC) by using a weighted combination algorithm after dimensionless processing of the acquired MoodEEG(t), Situational Feature Parameter Ctx(t), and Historical Brainwave Trend Parameter HEEGtrend(t).

[0032] Preferably, the third analysis unit is used to obtain a third evaluation result by comparing the emotional scene switching index ESC with the emotional scene switching threshold Eth through a preset emotional scene switching threshold Eth:

[0033] When the emotional scene switching index ESC < the emotional scene switching threshold Eth, it indicates that the user's current brainwave emotional characteristics are adequately adapted to the external situation, and continuous monitoring is required.

[0034] When the Emotional Scene Switching Index (ESC) is greater than or equal to the Emotional Scene Switching Threshold (Eth), it indicates that the user's current brainwave emotional characteristics are not well-suited to the external context, posing a risk of emotional fluctuations or mismatch with the context. This triggers a third warning instruction and generates a third strategy: activating the Emotional Scene Switching Mode, automatically selecting an emotion regulation path based on the current GPS scene G(t), time period Td(t), multi-band EEG energy ratio characteristics, and the brain-eye coordination assessment results output by the second analysis unit; constructing an individualized emotion-soothing sequence through the synergistic effect of audio relaxation guidance, local micro-vibration relaxation devices, visual brightness softening interface, and environmental noise adaptive filtering mechanism; dynamically adjusting the feedback rhythm based on the historical brainwave trend parameter HEEGtrend(t) to gradually return the user to a stable emotional state in the current context; and writing the results of this emotion regulation into the historical template HEEG(t) through a chain update method, forming a continuously looping emotional scene adaptation closed loop.

[0035] This invention provides a modular headband glasses device that combines brainwave monitoring with intelligent feedback. It has the following beneficial effects:

[0036] (1) This modular headband glasses device that combines brainwave monitoring and intelligent feedback achieves comprehensive real-time monitoring of the user's brain-eye activity and wearing status through multi-dimensional data collection of EEG signals, eye movement micro-expressions, and wearing fit and environmental interference, ensuring the accuracy and continuity of brainwave signals and providing a reliable data foundation for subsequent intelligent analysis.

[0037] (2) This modular headband glasses device that combines brainwave monitoring and intelligent feedback, through multi-source brain-pressure collaborative feature extraction and brainwave fit quality index (BQI) evaluation, can dynamically adjust the local damping coefficient of the DACO microstructure and perform adaptive compensation for environmental interference, effectively improving the stability and fit of EEG signals and reducing the risk of unstable contact, noise drift or signal attenuation.

[0038] (3) This modular headband glasses device that combines brainwave monitoring and intelligent feedback. This invention calculates the brain-eye coordination focus index (FCI) by combining the energy of brainwave α and β waves and eye movement behavior characteristics. It can judge the user's attention state in real time, and when the coordination focus is not up to standard, it can achieve individualized attention maintenance and focus recovery by comprehensively adjusting the feedback channel and situational guidance, thereby improving the user's focus and operation efficiency.

[0039] (4) This modular headband glasses device that combines brainwave monitoring and intelligent feedback calculates the emotional scene switching index ESC through the fusion analysis of the emotional brainwave index MoodEEG, the situational feature parameter Ctx and the historical brainwave trend HEEGtrend, so as to realize the matching assessment of brainwave emotional features and external situation; when an incompatibility is detected, an individualized emotion regulation strategy is automatically generated to improve the user's emotional state and improve the comfort and experience adaptability. Attached Figure Description

[0040] Figure 1 This is a block diagram and flowchart of a modular headband glasses device combining brainwave monitoring and intelligent feedback according to the present invention. Detailed Implementation

[0041] 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.

[0042] Example 1

[0043] Please see Figure 1 This invention provides a modular headband glasses device that combines brainwave monitoring and intelligent feedback, comprising:

[0044] A multi-dimensional data acquisition module is used to monitor the user's brain activity in real time, acquiring delta-wave EEG energy parameter sequences EEGδ(t), theta-wave EEG energy parameter sequences EEGθ(t), alpha-wave EEG energy parameter sequences EEGα(t), and beta-wave EEG energy parameter sequences EEGβ(t); to monitor the user's eye movement behavior and eye fatigue status in real time, acquiring blink frequency Blink(t), saccade velocity Sacc(t), and eye fatigue index Efat(t); to monitor the fit of the headband glasses device, environmental noise interference, and usage context in real time; and to acquire scene index parameter G(t), time period parameter Td(t), and historical template parameter HEEG(t).

[0045] The neural state quantification module is used to extract multi-source brain-pressure synergistic features, including pressure variance. EEG signal-to-noise ratio Fit to historical templates The brainwave fit quality index (BQI) is calculated and compared with the fit quality threshold (Bth) to determine whether the EEG fit quality is qualified. If it is not qualified, adaptive compensation adjustment is performed.

[0046] The dual-modal collaborative recognition module is used to extract the alpha wave EEG energy parameter sequence EEGα(t) and the beta wave EEG energy parameter sequence EEGβ(t), and combine them with the blink frequency Blink(t), eye saccade velocity Sacc(t) and eye fatigue index Efat(t) to calculate the brain-eye coordination focus index FCI, and compare it with the coordination focus threshold Fth to determine whether the user's brain-eye coordination meets the standard. If it does not meet the standard, a comprehensive adjustment strategy is implemented.

[0047] The emotion-context adaptive adjustment module is used to extract contextualized brainwave features, including the emotion brainwave index MoodEEG(t), context feature parameter Ctx(t), and historical brainwave trend parameter HEEGtrend(t). It calculates and obtains the emotion scenario switching index ESC and compares it with the emotion scenario switching threshold Eth to determine whether the user's current brainwave emotion features are suitable for the external context. If they are not suitable, an emotion scenario switching strategy is implemented.

[0048] In this embodiment, through the synergistic effect of a multi-dimensional data acquisition module, a neural state quantification module, a dual-modal collaborative recognition module, and an emotion-situation adaptive adjustment module, real-time monitoring and comprehensive analysis of the user's brainwave activity, eye movement behavior, wearing fit, and environmental context are achieved. It can dynamically evaluate the quality of brainwave fit, brain-eye coordination and focus, and emotion-situation adaptability. When unqualified or incompatible conditions are detected, it automatically performs adaptive compensation, focus recovery, and emotional scene switching adjustment, thereby improving the accuracy of brainwave signal acquisition, user focus, and emotional comfort, and optimizing the user experience and intelligent feedback effect of the headband glasses device.

[0049] Example 2

[0050] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the multi-dimensional data acquisition module includes an electroencephalogram (EEG) signal acquisition unit, an eye movement micro-expression acquisition unit, and a wearing fit environment interference acquisition unit.

[0051] The EEG signal acquisition unit is used to monitor the user's brain activity in real time. A multi-channel dry electrode EEG acquisition device is installed in the inner headband contact area of ​​the headband glasses device to acquire raw EEG signals of δ, θ, α and β respectively. Multi-band spectral analysis technology and short-time Fourier transform (STFT) method are used to denoise, divide the frequency and extract the energy envelope of the raw EEG signals of δ, θ, α and β to obtain the δ wave EEG energy parameter sequence EEGδ(t), the θ wave EEG energy parameter sequence EEGθ(t), the α wave EEG energy parameter sequence EEGα(t) and the β wave EEG energy parameter sequence EEGβ(t).

[0052] The eye movement micro-expression acquisition unit is used to monitor the user's eye movement behavior and eye fatigue status in real time. By installing an EOG electrode array in the nose bridge support area inside the frame of the headband glasses device, the raw EOG signals of blink frequency, saccade velocity, and eye fatigue potential sequence are acquired. Using eye potential difference analysis technology and eye movement trajectory model reconstruction method, peak detection, displacement calculation, and potential sequence filtering are performed on the raw EOG signals to obtain blink frequency Blink(t), saccade velocity Sacc(t), and eye fatigue index Efat(t).

[0053] The wearing fit environmental interference acquisition unit is used to monitor the wearing fit, environmental noise interference, and usage scenarios of the headband glasses device in real time. It collects contact pressure data by deploying a DACO miniature contact pressure sensor array inside the headband and at the temple joints of the headband glasses device. Contact pressure field gradient analysis technology is used to perform distribution modeling and dynamic fit reconstruction of the pressure data to obtain the contact pressure distribution. By installing a noise detection microphone, a light sensor, and a miniature inertial measurement unit (IMU) on the outside of the glasses frame, ambient noise dB(t), light intensity Lux(t), and head micro-movement sequence Mv(t) are collected. By connecting GPS and time management components to the communication device of the headband glasses, GPS scene G(t) and usage time period Td(t) are collected, and the user's historical brainwave template is synchronized from the cloud. The context recognition and template matching analysis methods are used to perform pattern modeling and context analysis to obtain the scene index parameter G(t), time period parameter Td(t), and historical template parameter HEEG(t).

[0054] In this embodiment, a multi-dimensional data acquisition module is used to monitor and analyze the user's EEG signals, eye movement micro-expressions, wearing fit, and environmental interference in real time. This enables the synchronous acquisition and feature extraction of EEG energy, eye movement state, and wearing environment, providing an accurate and reliable data foundation for subsequent EEG fit quality assessment, brain-eye coordination analysis, and emotion-situation adaptive adjustment, thereby improving the intelligent perception capability and user experience of the headband glasses device.

[0055] Example 3

[0056] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the neural state quantification module includes a multi-source brain-pressure collaborative feature extraction unit, a first calculation unit, and a first analysis unit;

[0057] The multi-source brain-pressure collaborative feature extraction unit is used to extract features based on the acquired contact pressure distribution. Contact pressure field variance analysis technology was used to perform dynamic statistics and stability reconstruction on pressure distribution data to obtain pressure variance. Based on the acquired delta-wave EEG energy parameter sequences (EEGδ(t), theta-wave EEGθ(t), alpha-wave EEGα(t), and beta-wave EEGβ(t), a signal-to-noise ratio (SNR) estimation method and a multi-channel noise stripping algorithm were used. After normalization, energy calculation and noise modeling were performed on the signals in each frequency band to obtain the EEG SNR. Based on the collected historical template parameters HEEG(t) from users, template matching correlation analysis is used to compare the similarity and calculate the matching degree of the current EEG spectral features, thereby obtaining the historical template fitting degree. .

[0058] In this embodiment, the joint analysis of the user's EEG signal and contact pressure is achieved through the multi-source brain-pressure synergistic feature extraction in the neural state quantification module. This enables the simultaneous acquisition of pressure variance, EEG signal-to-noise ratio, and historical template fitting degree, providing multi-dimensional and quantitative reference indicators for EEG fit quality assessment. This effectively improves the accuracy and stability of EEG monitoring and ensures the signal reliability of the headband glasses device during wear.

[0059] Example 4

[0060] This embodiment is an explanation based on Embodiment 3. Please refer to it. Figure 1 Specifically, the first calculation unit is used to extract the pressure variance. EEG signal-to-noise ratio Fit to historical templates After dimensionless processing, the Brainwave Attachment Quality Index (BQI) is calculated using the following formula:

[0061]

[0062] In the formula, w1, w2 and w3 represent weighting coefficients.

[0063] Characterizing the variance of pressure The impact on EEG fit quality has a high weight and is a key indicator, reflecting the contribution of the uniformity of the contact pressure distribution and the local fit stability of the headband glasses device to the quality of EEG signal acquisition.

[0064] Characterizing the signal-to-noise ratio of EEG The impact on the quality of brainwave fit has the second highest weight, reflecting the role of the noise suppression degree and signal effectiveness of the EEG signal in fit judgment;

[0065] Characterizing the goodness of fit of historical templates The impact on EEG fit quality has a medium weight, reflecting the contribution of the degree of matching between the user's historical EEG characteristics and the current signal to fit stability.

[0066] By weighted fusion of pressure uniformity, signal clarity, and historical matching, the brainwave fit quality (BQI) is quantified, allowing influencing factors from different sources to be reflected under the same evaluation scale through dimensionless weighted combination.

[0067] In this embodiment, the pressure variance, EEG signal-to-noise ratio, and historical template fitting degree are processed dimensionlessly and weighted by the first calculation unit to form the Brainwave Fit Quality Index (BQI). This enables a quantitative assessment of the quality of EEG signals while the headband glasses device is being worn, thereby accurately judging the fit of the EEG signal and improving the reliability and real-time performance of the monitoring.

[0068] Example 5

[0069] This embodiment is an explanation based on Embodiment 3. Please refer to it. Figure 1 Specifically, the first analysis unit is used to obtain a first evaluation result by comparing the EEG fit quality index (BQI) with the fit quality threshold (Bth) through a preset fit quality threshold (Bth):

[0070] When the EEG fit quality index BQI is greater than or equal to the fit quality threshold Bth, it indicates that the EEG fit quality is qualified, the signal is stable, and continuous monitoring is possible.

[0071] When the EEG fit quality index (BQI) is less than the fit quality threshold (Bth), it indicates that the EEG fit quality is substandard, posing a risk of unstable contact, noise drift, or signal attenuation. This triggers the first warning instruction and generates the first strategy: based on contact pressure distribution. By employing contact pressure field gradient analysis and DACO deformation compensation control methods, the local damping coefficient and micro-deformation of the DAO magnetorheological microstructure are adjusted in real time. This compensates for the local pressure in the weak pressure zone and appropriately releases the pressure in the strong pressure zone, thereby improving the uniformity of contact pressure distribution and reducing the fluctuation amplitude of Var(Pt). The real-time EEG signal-to-noise ratio is continuously monitored. If within a consecutive 2-second time window, If there is no improvement trend, it is determined that the DCO adjustment cannot effectively improve the fit, and the user is automatically prompted to "slightly adjust the wearing position" to prompt manual correction of the contact impedance and fit structure. Based on the collected noise and context data, including ambient noise dB(t), light intensity Lux(t), head micro-movement sequence Mv(t), GPS scene G(t), usage time Td(t), and user historical template parameter HEEG(t), the ambient noise dB(t), light intensity Lux(t), and head micro-movement sequence Mv(t) are spectrally estimated and interference mode decomposed using the environmental interference adaptive filtering method ANC-LMS / RLS to form the environmental noise prediction component N̂(t). Using the context recognition and template matching method, the expected template waveform EEGtemplate(t) of the EEG in the current scene is obtained based on the GPS scene G(t), usage time Td(t), and user historical template parameter HEEG(t). The noise deviation ΔN(t) is further generated: adaptive compensation adjustment is performed based on the noise deviation ΔN(t).

[0072] The method for obtaining the fit quality threshold Bth: Statistical analysis was conducted on a large number of users' EEG signal quality, contact pressure distribution, and historical template fit data under different wearing conditions. The distribution range of the EEG fit quality index (BQI) under stable signal and unstable contact states was extracted. Combined with the experience of professional technicians regarding the comfort of the headband glasses and the quality of EEG signal acquisition, a reasonable threshold was determined. Referencing the EEG device's instruction manual, ergonomic design standards, and signal acquisition reliability specifications, these documents typically provide reasonable fit or signal stability judgment ranges. This threshold is used to effectively distinguish between qualified and unqualified wearing states of the headband glasses device, ensuring the stability and reliability of EEG signal acquisition.

[0073] In this embodiment, the first analysis unit compares the brainwave fit quality index (BQI) with a preset threshold (Bth) to determine the fit status of the EEG signal in real time. When the fit is unqualified, the system can automatically perform DACO deformation compensation, adaptive filtering of environmental interference, and wearing guidance prompts to achieve dynamic optimization and adjustment of signal quality, thereby significantly improving the accuracy and stability of EEG monitoring and ensuring the reliable execution of subsequent neural state assessment and feedback strategies.

[0074] Example 6

[0075] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the dual-modal collaborative recognition module includes a second computing unit and a second analysis unit;

[0076] The second calculation unit is used to extract the alpha wave EEG energy parameter sequence EEGα(t) and the beta wave EEG energy parameter sequence EEGβ(t), combine them with blink frequency (Blink(t), saccade velocity (Sacc(t)) and eye fatigue index (Efat(t)), and calculate the brain-eye coordination focus index (FCI) using a weighted combination algorithm after dimensionless processing. The formula is as follows:

[0077]

[0078] In the formula, a1, a2, a3 and a4 represent weighting coefficients.

[0079] The ratio of alpha wave EEG energy parameter sequence EEGα(t) to beta wave EEG energy parameter sequence EEGβ(t) represents the influence of the user's attention state and has a high weight, reflecting the direct correlation between high-frequency beta wave enhancement and alpha wave inhibition and attention level.

[0080] : Characterizes the impact of blink frequency Blink(t) on the user's focus state, with a moderate weight, reflecting the contribution of visual behavior stability and attention maintenance;

[0081] The second highest weighting represents the impact of saccade velocity Sacc(t) on the user's attention state, reflecting the effect of rapid eye movement on cognitive load and attention distraction.

[0082] The Efat(t) index, which characterizes eye fatigue, has a minor weight in terms of its impact on users' concentration. It reflects the effect of visual fatigue on decreased attention.

[0083] By weighting and combining EEG signal features with eye movement behavior indicators and processing them dimensionlessly, the Comprehensive Focus Index (FCI) is obtained, which can quantify the brain-eye coordination state and achieve real-time assessment of the user's attention level.

[0084] In this embodiment, the brain-eye coordination focus index (FCI) is calculated by combining the alpha and beta wave energy of EEG and eye movement indicators through a dual-modal collaborative recognition module, thereby achieving real-time quantitative assessment of the user's attention state. This method can comprehensively reflect the level of brain-eye coordination, providing an objective basis for judging the user's focus state, thus effectively improving the accuracy and response speed of focus monitoring.

[0085] Example 7

[0086] This embodiment is an explanation based on Embodiment 6. Please refer to it. Figure 1 Specifically, the second analysis unit is used to obtain a second evaluation result by comparing the brain-eye coordination focus index (FCI) with the preset coordination focus threshold (Fth) and the coordination focus threshold (Fth).

[0087] When the Brain-Eye Coordination Attention Index (FCI) is greater than or equal to the Coordination Attention Thres (Fth), it indicates that the user's brain-eye coordination has met the standard and the user is in a stable state of focus, which will be continuously monitored.

[0088] When the Brain-Eye Coordination Attention Index (FCI) is less than the Coordination Attention Threshold (Fth), it indicates that the user's brain-eye coordination has not met the standard, and the user is at risk of decreased attention or emotional fluctuations. This triggers a second warning instruction and generates a second strategy: A brain-eye coordination regulation method is used to comprehensively adjust the feedback channels, prompting mechanisms, and contextual guidance interface of the headband glasses device. This involves activating a coordination feedback mode oriented towards attention maintenance, prioritizing the response of attention-related channels on the brainwave side, and constructing an individualized attention support sequence based on the user's current eye movement state. Through behavioral segment alignment, feature association calculation, and pattern modeling methods, a brain-eye behavioral coupling relationship is generated. Furthermore, a targeted attention maintenance plan is generated, including comprehensive adjustment of the user's visual load, task status, and environmental interference, guiding the user to restore stable focus in the current usage context. Simultaneously, a matching analysis of the causes of this attention decline is performed to generate real-time attention improvement feedback.

[0089] The method for obtaining the brain-eye coordination attention threshold Fth is as follows: Statistical analysis was conducted on a large number of users under different task loads and visual behavioral states, analyzing alpha and beta wave energy parameters, blink frequency, saccade velocity, and eye fatigue indicators. The distribution range of the brain-eye coordination attention index (FCI) under stable attention and attention decline states was extracted. Combined with the experience and judgment of psychology and cognitive behavior experts, a reasonable threshold was determined. Reference was made to cognitive load assessment standards, attention measurement experimental results, and brain-eye coordination research literature, which typically provide a range for judging a user's attention level. This threshold is used to effectively distinguish between a user's attention-achieving state and attention decline state, ensuring the accuracy of brain-eye coordination assessment.

[0090] In this embodiment, the second analysis unit performs threshold comparison and intelligent assessment of the Brain-Eye Coordination Attention Index (FCI), which can identify the risk of decreased user attention or emotional fluctuations in real time. Based on the brain-eye coordination regulation method, a personalized attention maintenance plan is generated, thereby realizing dynamic intervention and timely recovery of the user's attention state and improving the effectiveness and stability of attention maintenance during use.

[0091] Example 8

[0092] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically, the emotion-context adaptive regulation module includes a contextualized brainwave feature extraction unit, a third calculation unit, and a third analysis unit;

[0093] The contextualized EEG feature extraction unit is used to perform multi-band energy ratio analysis based on the delta-wave EEG energy parameter sequence EEGδ(t), the theta-wave EEG energy parameter sequence EEGθ(t), the alpha-wave EEG energy parameter sequence EEGα(t), and the beta-wave EEG energy parameter sequence EEGβ(t). It then extracts immediate emotional features using a short-time energy sliding window model to obtain the emotional EEG index MoodEEG(t). Based on the scene index parameter G(t) and the time period parameter Td(t), it uses a context recognition and template matching analysis method to generate the context feature parameter Ctx(t) through scene index matching and time period pattern modeling. Based on the historical template parameter HEEG(t), it uses historical template fitting trend analysis technology to perform difference calculation and trend regression on the change direction of the current EEG energy pattern and the historical template to obtain the historical EEG trend parameter HEEGtrend(t).

[0094] In this embodiment, the emotion-situation adaptive adjustment module extracts the user's real-time emotional brainwave features, usage scenario features, and historical brainwave trends, enabling a comprehensive analysis of the user's emotional state and external environmental context. This provides a precise basis for subsequent emotional scenario switching strategies, thereby improving the emotional adaptability and personalized adjustment effect of the headband glasses device in different usage scenarios.

[0095] Example 9

[0096] This embodiment is an explanation based on Embodiment 8. Please refer to it. Figure 1 Specifically, the third calculation unit is used to calculate the Emotional Scene Switching Index (ESC) by using the acquired MoodEEG(t), situational feature parameter Ctx(t), and historical brainwave trend parameter HEEGtrend(t) after dimensionless processing, and employing a weighted combination algorithm. The formula is as follows:

[0097]

[0098] In the formula, s1, s2 and s3 represent weighting coefficients.

[0099] The MoodEEG(t) index, which characterizes the impact of emotional brainwaves on the switching of emotional scenarios, has a high weight and reflects the direct correlation between the user's real-time brainwave emotional characteristics and the adaptability to the external situation.

[0100] The second highest weighting represents the influence of the contextual feature parameter Ctx(t) on the switching of emotional scenes, reflecting the contribution of contextual factors such as environmental scene and time period to the user's emotion regulation.

[0101] The HEEGtrend(t) parameter, which characterizes the historical brainwave trend, has a high weighting and reflects the reference value of historical brainwave patterns in predicting and adapting to the current emotional state.

[0102] By weightedly integrating emotional brainwave characteristics, situational factors, and historical trends, the Emotional Scene Switching Index (ESC) is calculated, enabling a quantitative evaluation of the matching between user brainwave emotional characteristics and environmental situations, and providing a scientific basis for triggering emotion regulation strategies.

[0103] In this embodiment, the third calculation unit performs weighted combination calculations on the emotional brainwave index, situational feature parameters, and historical brainwave trend parameters to obtain the emotional scene switching index (ESC). This enables quantitative assessment and dynamic monitoring of the user's emotional state, providing accurate decision-making basis for emotion regulation strategies, thereby effectively improving the user's emotional adaptability and comfort experience in different usage scenarios.

[0104] Example 10

[0105] This embodiment is an explanation based on Embodiment 8. Please refer to it. Figure 1 Specifically, the third analysis unit is used to obtain a third evaluation result by comparing the emotional scene switching index ESC with the emotional scene switching threshold Eth through a preset emotional scene switching threshold Eth:

[0106] When the emotional scene switching index ESC < the emotional scene switching threshold Eth, it indicates that the user's current brainwave emotional characteristics are adequately adapted to the external situation, and continuous monitoring is required.

[0107] When the Emotional Scene Switching Index (ESC) is greater than or equal to the Emotional Scene Switching Threshold (Eth), it indicates that the user's current brainwave emotional characteristics are not well-suited to the external context, posing a risk of emotional fluctuations or mismatch with the context. This triggers a third warning instruction and generates a third strategy: activating the Emotional Scene Switching Mode, automatically selecting an emotion regulation path based on the current GPS scene G(t), time period Td(t), multi-band EEG energy ratio characteristics, and the brain-eye coordination assessment results output by the second analysis unit; constructing an individualized emotion-soothing sequence through the synergistic effect of audio relaxation guidance, local micro-vibration relaxation devices, visual brightness softening interface, and environmental noise adaptive filtering mechanism; dynamically adjusting the feedback rhythm based on the historical brainwave trend parameter HEEGtrend(t) to gradually return the user to a stable emotional state in the current context; and writing the results of this emotion regulation into the historical template HEEG(t) through a chain update method, forming a continuously looping emotional scene adaptation closed loop.

[0108] The method for obtaining the emotion scene switching threshold Eth is as follows: Statistical analysis is conducted on a large number of users' EEG energy ratios, historical EEG trends, and emotional EEG index data under different situations, lighting conditions, noise levels, and time periods. The distribution range of the Emotion Scene Switching Index (ESC) under stable and fluctuating emotional states is extracted. Combined with the experience of emotion psychology experts regarding the matching relationship between brainwaves and emotions, a reasonable threshold is determined. Referencing EEG emotion recognition standards, emotion regulation research results, and environmental adaptability analysis specifications, these materials typically provide an emotion suitability judgment range. This threshold is used to effectively distinguish between user brainwave emotions matching and not matching external situations, ensuring the effectiveness of emotion regulation strategies.

[0109] In this embodiment, the third analysis unit compares the Emotion Scene Switching Index (ESC) with the threshold Eth, which can identify in real time the abnormal adaptation between the user's brainwave emotions and the external situation and trigger the emotion scene switching mode. Combined with multimodal regulation methods and historical brainwave trends, it dynamically generates an individualized emotion soothing sequence, realizing the user's active regulation and gradual stabilization of emotions. At the same time, it forms a closed-loop feedback mechanism through historical template updates, which significantly improves the user's emotional adaptability and user comfort in complex usage situations.

[0110] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value, it is acceptable.

[0111] The above formulas are all derived from software simulation using a large amount of data and are selected to be close to the actual values. The coefficients in the formulas are set by those skilled in the art according to the actual situation. The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any equivalent substitutions or changes made by those skilled in the art within the technical scope disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the protection scope of the present invention.

Claims

1. A modular headband glasses device combining brainwave monitoring and intelligent feedback, characterized in that, Comprise: A multi-dimensional data acquisition module for real-time monitoring of user brain electrical activity, collecting delta wave EEG energy parameter sequence EEGδ(t), theta wave EEG energy parameter sequence EEGθ(t), alpha wave EEG energy parameter sequence EEGα(t) and beta wave EEG energy parameter sequence EEGβ(t); real-time monitoring of user eye movement behavior and eye fatigue state, collecting blink frequency Blink(t), saccade speed Sacc(t) and eye fatigue index Efat(t); real-time monitoring of the wearing fit of the head ring glasses device, environmental noise interference and use situation; Collect scene index parameter G(t), time period parameter Td(t) and historical template parameter HEEG(t); a neural state quantification module configured to extract multi-source brain-pressure collaborative features including pressure variance , EEG signal-to-noise ratio , and historical template fitting degree , calculate a brain wave fitting quality index BQI, and compare the brain wave fitting quality index BQI with a fitting quality threshold Bth to determine whether the EEG fitting quality is qualified, and if not, perform adaptive compensation adjustment; A dual-mode collaborative recognition module for extracting alpha wave EEG energy parameter sequence EEGα(t) and beta wave EEG energy parameter sequence EEGβ(t), combining blink frequency Blink(t), saccade speed Sacc(t) and eye fatigue index Efat(t), calculating and obtaining brain-eye collaborative concentration index FCI, and comparing with collaborative concentration threshold Fth to determine whether the user's brain-eye collaboration meets the standard, and if not, performing a comprehensive adjustment strategy; An emotion-situation adaptive adjustment module for extracting situational brain wave features, including emotion brain wave index MoodEEG(t), situation feature parameter Ctx(t) and historical brain wave trend parameter HEEGtrend(t), calculating and obtaining emotion scene switching index ESC, and comparing with emotion scene switching threshold Eth to determine whether the user's current brain wave emotion feature and external situation adaptability are qualified, and if not, performing an emotion scene switching strategy.

2. The modular head ring glasses device of claim 1, wherein, The multi-dimensional data acquisition module comprises an electroencephalogram signal acquisition unit, an eye movement micro-expression acquisition unit and a wearing fit environment interference acquisition unit; The electroencephalogram signal acquisition unit is used for real-time monitoring of user brain electrical activity; a multi-channel dry electrode EEG collector is installed on the inner side head ring contact area of the head ring glasses device to collect δ, θ, α and β EEG original signals respectively; multi-band spectral analysis technology and short-time Fourier transform STFT method are used to denoise, frequency divide and energy envelope extract the δ, θ, α and β EEG original signals to obtain the delta wave EEG energy parameter sequence EEGδ(t), theta wave EEG energy parameter sequence EEGθ(t), alpha wave EEG energy parameter sequence EEGα(t) and beta wave EEG energy parameter sequence EEGβ(t); The eye movement micro-expression acquisition unit is used for real-time monitoring of user eye movement behavior and eye fatigue state; an EOG electrode array is installed in the inner side nose bridge support area of the head ring glasses device to collect EOG original signals of blink frequency, saccade speed and eye fatigue potential sequence; eye potential difference analysis technology and eye movement trajectory model reconstruction method are used to perform peak detection, displacement calculation and potential sequence filtering on the EOG original signals to obtain blink frequency Blink(t), saccade speed Sacc(t) and eye fatigue index Efat(t); The wearing fit environment interference collection unit is used for real-time monitoring of wearing fit, environmental noise interference and use situation of the head ring glasses device; DACO micro touch pressure sensor arrays are arranged inside the head ring and at the leg joint of the head ring glasses device to collect contact pressure data; The contact pressure distribution is obtained by using the contact pressure field gradient analysis technology to model the pressure data distribution and dynamically fit the degree of reconstruction ; By installing noise detection microphones, light sensors and miniature inertial measurement components IMU outside the mirror frame, environmental noise dB(t), light intensity Lux(t) and head micro-motion sequence Mv(t) are collected; By accessing GPS and time management components in the communication equipment of the head ring glasses device, GPS scene G(t) and use time period Td(t) are collected, and user historical brain wave templates are synchronized from the cloud; Using context recognition and template matching analysis method, mode modeling and context analysis are carried out to obtain scene index parameters G(t), time period parameters Td(t) and historical template parameters HEEG(t).

3. The modular head ring glasses device of claim 1, wherein, The neural state quantification module comprises a multi-source brain-pressure collaborative feature extraction unit, a first calculation unit and a first analysis unit; The multi-source brain-pressure synergy feature extraction unit is used for based on the collected contact pressure distribution , using contact pressure field variance analysis technology, dynamic statistics and stability reconstruction of pressure distribution data, obtain pressure variance ; based on the collected delta wave EEG energy parameter sequence EEGδ(t), theta wave EEG energy parameter sequence EEGθ(t), alpha wave EEG energy parameter sequence EEGα(t) and beta wave EEG energy parameter sequence EEGβ(t), using signal-to-noise ratio estimation method and multi-channel noise stripping algorithm, after normalization processing, energy calculation and noise modeling are carried out on each frequency band signal, and the EEG signal-to-noise ratio ; based on the collected user historical template parameter HEEG(t), using template matching correlation analysis technology, similarity comparison and matching degree calculation are carried out on the current EEG spectrum feature, and the historical template fitting degree is obtained.

4. The modular head ring glasses device of claim 3, wherein, The first calculation unit is configured to calculate a brain wave fitting quality index BQI by extracting the pressure variance EEG signal-to-noise ratio and historical template fitting degree , and after dimensionless processing.

5. The modular head ring glasses device of claim 3, wherein, The first analysis unit is used for comparing and analyzing the brain wave fit quality index BQI with the fit quality threshold Bth through the preset fit quality threshold Bth, and obtaining a first evaluation result, which comprises: When the brain wave fit quality index BQI is greater than or equal to the fit quality threshold Bth, it indicates that the EEG fit quality is qualified, the signal is stable, and continuous monitoring is performed. When the brain wave fitting quality index BQI < fitting quality threshold Bth, it indicates that the EEG fitting quality is unqualified, there is a risk of unstable contact, noise drift or signal attenuation, triggers the first early warning instruction, generates the first strategy: based on the contact pressure distribution , using contact pressure field gradient analysis and DACO deformation compensation control method, the local damping coefficient and micro deformation of DACO magnetorheological microstructure are adjusted in real time, so that the local pressure of weak pressure area is compensated, the pressure of strong pressure area is released moderately, the uniformity of contact pressure distribution is improved and the fluctuation amplitude of Var(Pt) is reduced; continuously monitor the real-time EEG signal-to-noise ratio , if in the continuous 2 second time window, There is no lifting trend; it is determined that DACO adjustment cannot effectively improve the fitting, and the user is automatically prompted to "please slightly adjust the wearing position" wearing guidance, prompting the contact impedance and fitting structure to obtain artificial correction; based on the collected noise and context data, including environmental noise dB(t), illumination intensity Lux(t), head micro-motion sequence Mv(t), GPS scene G(t), use time period Td(t) and user historical template parameters HEEG(t); using environmental interference adaptive filtering method ANC-LMS / RLS, the spectrum estimation and interference mode decomposition of environmental noise dB(t), illumination intensity Lux(t) and head micro-motion sequence Mv(t) are carried out, and the environmental noise prediction component N̂(t) is formed; using context recognition and template matching method, based on GPS scene G(t), use time period Td(t) and user historical template parameters HEEG(t), the expected template waveform EEGtemplate(t) of EEG under the current scene is obtained; further generate noise deviation amount ΔN(t): based on noise deviation amount ΔN(t) for adaptive compensation adjustment.

6. The modular head ring eyeglasses device for brainwave monitoring and intelligent feedback combination of claim 1, wherein, The dual-mode collaborative recognition module comprises a second calculation unit and a second analysis unit; The second calculation unit is used for extracting the alpha wave EEG energy parameter sequence EEGa(t) and the beta wave EEG energy parameter sequence EEGβ(t), combining the blink frequency Blink(t), the saccade speed Sacc(t) and the eye fatigue index Efat(t), and calculating the brain-eye collaborative concentration index FCI through a weighted combination algorithm after dimensionless processing.

7. The modular head ring glasses device of claim 6, wherein, The second analysis unit is used for comparing and analyzing the brain-eye collaborative concentration index FCI with the collaborative concentration threshold Fth through the preset collaborative concentration threshold Fth, and obtaining a second evaluation result, which comprises: When the brain-eye collaborative concentration index FCI is greater than or equal to the collaborative concentration threshold Fth, it indicates that the user's brain-eye collaboration is up to standard, and the user is in a stable concentration state, and continuous monitoring is performed. When the brain-eye collaborative concentration index FCI is less than the collaborative concentration threshold Fth, it indicates that the user's brain-eye collaboration is not up to standard, and the user has the risk of attention decline or emotional fluctuation, a second warning instruction is triggered, and a second strategy is generated: a brain-eye collaborative regulation method is used to comprehensively adjust the feedback channel, prompt mechanism and situation guiding interface of the head ring glasses device; a collaborative feedback mode for concentration maintenance is started to make the attention-related channel on the brain wave side respond preferentially, and an individualized concentration support sequence is constructed in combination with the current eye movement state of the user; a brain-eye behavior coupling relationship is generated through behavior segment alignment, feature correlation calculation and pattern modeling method; a targeted attention maintenance scheme is further generated, which comprises comprehensive adjustment of the user's visual load, task state and environmental interference, guiding the user to restore stable concentration in the current use situation; meanwhile, the cause of the current concentration decline is matched and analyzed to generate real-time concentration improvement feedback.

8. The modular head ring glasses device of claim 1, wherein, The emotion-situation adaptive adjustment module comprises a situational brain wave feature extraction unit, a third calculation unit and a third analysis unit; The situational brain wave feature extraction unit is configured to extract an emotional brain wave index MoodEEG(t) based on a delta wave electroencephalogram energy parameter sequence EEGδ(t), a theta wave electroencephalogram energy parameter sequence EEGθ(t), an alpha wave electroencephalogram energy parameter sequence EEGα(t), and a beta wave electroencephalogram energy parameter sequence EEGβ(t), adopt a multi-band energy ratio analysis technique to perform fusion calculation on the energy ratio, and extract an instant emotional feature through a short-time energy sliding window model; based on a scene index parameter G(t) and a time period parameter Td(t), adopt a scene recognition and template matching analysis method to generate a situational feature parameter Ctx(t) through scene index matching and time period mode modeling; and based on a historical template parameter HEEG(t), utilize a historical template fitting trend analysis technique to perform difference calculation and trend regression on a change direction of a current EEG energy mode and the historical template, and obtain a historical brain wave trend parameter HEEGtrend(t).

9. The modular head ring glasses device of claim 8, wherein, The third calculation unit is configured to obtain the emotional brain wave index MoodEEG(t), the situational feature parameter Ctx(t), and the historical brain wave trend parameter HEEGtrend(t), perform dimensionless processing, and calculate an emotional scene switching index ESC by adopting a weighted combination algorithm.

10. The modular head ring glasses device of claim 8, wherein, The third analysis unit is configured to compare the emotional scene switching index ESC with a preset emotional scene switching threshold Eth, and obtain a third evaluation result, including: When the emotional scene switching index ESC is less than the emotional scene switching threshold Eth, it indicates that the current brain wave emotional feature of the user is qualified in terms of adaptation to the external situation, and continuous monitoring is performed; When the emotional scene switching index ESC is greater than or equal to the emotional scene switching threshold Eth, it indicates that the current brain wave emotional feature of the user is unqualified in terms of adaptation to the external situation, and there is a risk of emotional fluctuation or mismatch with the situation, a third warning instruction is triggered, and a third strategy is generated: starting an emotional scene switching mode, automatically selecting an emotional regulation path in combination with the current GPS scene G(t), the time period Td(t), the multi-band electroencephalogram energy ratio feature, and the brain-eye coordination evaluation result output by the second analysis unit; and constructing an individualized emotional relaxation sequence through the synergistic effect of an audio relaxation guide, a local micro-vibration relaxation device, a visual brightness softening interface, and an environmental noise adaptive filtering mechanism; simultaneously, dynamically adjusting a feedback rhythm according to the historical brain wave trend parameter HEEGtrend(t) to make the user gradually return to a stable emotional state in the current situation; and through a chain updating mode, writing the result of this emotional regulation into the historical template HEEG(t) to form a continuous cycle of emotional scene adaptation closed loop.

Images