A lightweight brain function state evaluation device, method and system

Abstract

The present specification provides a lightweight brain function state evaluation device, method and system, wherein the device comprises: a portable head-mounted device provided with a detection electrode group corresponding to the prefrontal lobe, central region, parietal lobe and occipital lobe of the brain; a processing unit configured to determine a four-parameter feature set from a multi-channel electroencephalogram signal, the four-parameter feature set comprising a peak alpha frequency, a 1 / f spectrum slope, an alpha wave relative power and a theta wave relative power; and calculate a brain function state quantitative index value based on a preset mapping relationship according to the four-parameter feature set, the mapping relationship being such that when the four-parameter feature set is the same, a unique brain function state quantitative index value is output. The present scheme can simplify the device structure, simplify the device usage, reduce the device cost, and more scientifically, accurately and reliably evaluate the brain function state, thereby being more suitable for the needs of scenarios such as daily brain function detection and personal daily health management at home.

Description

Technical Field

[0001] This application relates to the field of health management technology, and in particular to a lightweight brain function status assessment device, method and system. Background Technology

[0002] Brain function status is one of the core indicators reflecting human health, and its accurate assessment is of great significance for health management, early screening of neurological diseases, and early warning of cognitive decline. Brain function status assessment not only provides healthy individuals with a quantitative reference for their brain health, helping them develop scientific brain health and protection plans, but also provides auxiliary evidence for the early diagnosis of neurological diseases such as Alzheimer's and Parkinson's, enabling early detection and intervention. Furthermore, it provides strong technical support for monitoring brain development in children and adolescents and maintaining brain health in the elderly. Electroencephalography (EEG) signals are widely used in brain function status detection technology due to their advantages such as convenient acquisition, real-time performance, and direct reflection of neuronal activity in the brain.

[0003] In existing technologies, brain function status assessment schemes based on EEG signals typically employ a 10-20 system, which sets electrodes at numerous locations on the head to collect multi-channel EEG signals, and then assesses brain function status based on these channels of EEG signals. Figure 1 This is a lateral view schematic diagram of the EEG electrode distribution in the 10-20 system. Figure 2 This is a top-down view of the EEG electrode distribution in the 10-20 system. Fp represents the frontal pole, F represents the frontal lobe, C represents the central region, T represents the temporal lobe, P represents the parietal lobe, O represents the occipital lobe, and A represents the auricular pole (reference electrode). Odd numbers (1, 3, 5) represent the left brain region, even numbers (2, 4, 6) represent the right brain region, and z represents the midline position. The EEG electrodes of the 10-20 system can be divided into midline region electrodes (Fpz, Fz, Cz, Pz, Oz), left brain region electrodes, and right brain region electrodes. The left brain region electrodes include the left prefrontal cortex (Fp1, F3, F7), left central-parietal cortex, and left occipital cortex (O1). The left central-parietal cortex includes C3, T3 (T7), P3, and T5 (P7). The right brain region electrodes are strictly symmetrical to the left.

[0004] When detecting EEG signals, the scalp needs to be cleaned first to ensure good contact between the electrodes and the skin. The electrodes are then attached to the corresponding positions on the head according to their placement.

[0005] While the aforementioned professional-grade EEG testing methods can collect relatively rich EEG signals, they require numerous electrodes (16-64) and extensive preparation work before electrode attachment. Therefore, existing EEG functional state detection methods are costly in terms of electrode cost, complex EEG signal processing algorithms, and high R&D costs. Furthermore, the wearing process is complicated, requiring professional operation and adjustment, and necessitates shaving almost all of the hair. Based on these factors, these EEG testing methods are not suitable for routine home-based brain function monitoring or personal health management.

[0006] Currently, consumer-grade products based on electroencephalogram (EEG) signals have emerged on the market, such as devices for meditation monitoring and sleep quality assessment. While these consumer products offer advantages like ease of wear and affordability, their core algorithms are primarily designed for specific scenarios like meditation state recognition and sleep stage segmentation. They lack dedicated algorithm models specifically for assessing brain function, resulting in brain function assessment results that lack sufficient scientific rigor and accuracy, failing to meet the demand for precise brain function assessment.

[0007] In summary, there is an urgent need for a lightweight brain function assessment solution to address the issues of high cost and complex operation of professional-grade brain function assessment solutions, and the lack of scientific rigor and accuracy in consumer-grade products. This would meet the needs of families for daily brain function monitoring and personal health management. Summary of the Invention

[0008] This manual provides a lightweight brain function status assessment device, method, and system to address the issues of high cost and complex operation of professional-grade brain function status assessment solutions, and the lack of scientific rigor and accuracy in consumer-grade products. This allows the device to meet the needs of families for daily brain function status monitoring and personal health management.

[0009] To address the aforementioned technical problems, this specification provides a lightweight brain function state assessment device, comprising: a portable head-mounted device with lightweight detection electrode sets corresponding to the prefrontal, central, parietal, and occipital lobes of the brain for acquiring multi-channel electroencephalogram (EEG) signals; a processing unit disposed within or communicatively connected to the portable head-mounted device; the processing unit being configured to perform the following operations: determining a lightweight four-parameter feature set from the multi-channel EEG signals, the four-parameter feature set including the following four feature parameters: peak alpha frequency, 1 / f spectral slope, alpha wave relative power, and theta wave relative power; calculating a brain function state quantitative index value based on the lightweight four-parameter feature set and a preset mapping relationship; wherein the mapping relationship is determined through training on a sample dataset, and the mapping relationship ensures that when the input four-parameter feature sets are the same, a unique brain function state quantitative index value is output; and an output unit for outputting the brain function state quantitative index value.

[0010] In some embodiments, the processing unit calculates the peak α frequency based on the EEG signals detected by the detection electrodes corresponding to the parietal and occipital lobes in the lightweight detection electrode group. Specifically, this includes: preprocessing the EEG signals detected by the detection electrodes corresponding to the parietal and occipital lobes, and then calculating the power spectrum corresponding to each detection electrode based on the preprocessed EEG signals; extracting the EEG signals of the first frequency band corresponding to each detection electrode based on the power spectrum; selecting the peak frequency corresponding to each detection electrode from the extracted EEG signals, wherein the peak frequency is the frequency value corresponding to the maximum power; and calculating the average value of the peak frequencies corresponding to each detection electrode, and using the average value as the peak α frequency in the four-parameter feature set.

[0011] In some embodiments, the processing unit calculates the 1 / f spectral slope based on the EEG signals detected by the detection electrodes corresponding to the prefrontal, central, parietal, and occipital lobes of the brain in the lightweight detection electrode group. Specifically, this includes: preprocessing the EEG signals detected by the detection electrodes corresponding to the prefrontal, central, parietal, and occipital lobes of the brain; calculating the power spectral density corresponding to each detection electrode based on the preprocessed EEG signals; selecting the power spectral density in a second frequency band range; performing a logarithmic transformation on the selected data; performing linear fitting on the power spectral density in a double logarithmic coordinate system; determining the slope of the fitted line corresponding to each detection electrode based on the fitting result; calculating the average value of the slope of the fitted line corresponding to each detection electrode; and using the average value as the 1 / f spectral slope in the four-parameter feature set.

[0012] In some embodiments, the processing unit calculates the relative power of alpha waves based on the EEG signals detected by the detection electrodes corresponding to the parietal and occipital lobes in the lightweight detection electrode group. Specifically, this includes: preprocessing the EEG signals detected by the detection electrodes corresponding to the parietal and occipital lobes, and then calculating the power spectral density corresponding to each detection electrode based on the preprocessed EEG signals; selecting the power spectral density corresponding to a first frequency band, and calculating the first power of the first frequency band based on the power spectral density; selecting the power spectral density corresponding to a second frequency band, and calculating the second power of the second frequency band based on the power spectral density; and calculating the ratio of the first power to the second power as the relative power of alpha waves in the four-parameter feature set.

[0013] In some embodiments, the processing unit calculates the relative power of theta waves based on the EEG signals detected by the detection electrodes corresponding to the prefrontal and central regions in the lightweight detection electrode group. Specifically, this includes: preprocessing the EEG signals detected by the detection electrodes corresponding to the prefrontal and central regions, and calculating the power spectral density corresponding to each detection electrode based on the preprocessed EEG signals; selecting the power spectral density corresponding to a third frequency band, and calculating the third power of the third frequency band based on the power spectral density; selecting the power spectral density corresponding to a second frequency band, and calculating the second power of the second frequency band based on the power spectral density; and calculating the ratio of the third power to the second power as the relative power of theta waves in the four-parameter feature set.

[0014] In some embodiments, the detection electrodes on the portable head-mounted device are symmetrically distributed in the frontal and central regions, and distributed along the midline in the parietal and occipital lobes.

[0015] In some embodiments, the portable head-mounted device includes a first fixing part and a second fixing part for setting detection electrodes. The first fixing part is an annular fixing part corresponding to the circumference of the head, and the second fixing part is a fixing part corresponding to the midline position of the head. The circumferential length of the first fixing part is adjustable, and the fixing position on at least one side of the second fixing part is detachable and adjustable.

[0016] In some embodiments, the second fixing part is rotatably fixed to the first fixing part; when the portable head-mounted device is in a stored state, the second fixing part rotates to overlap with the first fixing part.

[0017] In some embodiments, the output unit further includes: a presentation device for presenting to the user a quantitative index value of brain functional state, and at least one of the following: a radar chart of four feature parameters, a trend of change of the quantitative index value of brain functional state, and personalized suggestions based on the evaluation results of the quantitative index value of brain functional state.

[0018] The second aspect of this specification provides a lightweight method for assessing brain functional status, comprising: detecting multi-channel electroencephalogram (EEG) signals from the prefrontal, central, parietal, and occipital lobes of the brain using a portable head-mounted device; determining a lightweight four-parameter feature set from the multi-channel EEG signals, the four-parameter feature set including the following four feature parameters: peak alpha frequency, 1 / f spectral slope, alpha wave relative power, and theta wave relative power; calculating a quantitative index value of brain functional status based on the lightweight four-parameter feature set and a preset mapping relationship; wherein the mapping relationship is determined through training on a sample dataset, and the mapping relationship ensures that when the input four-parameter feature set is the same, a unique quantitative index value of brain functional status is output; and outputting the quantitative index value of brain functional status.

[0019] In some embodiments, outputting the quantitative index value of brain function status includes: presenting the quantitative index value of brain function status to the user, and at least one of the following: a radar chart of four feature parameters, a trend of change of the quantitative index value of brain function status, and personalized suggestions based on the evaluation results of the quantitative index value of brain function status.

[0020] A third aspect of this specification provides a health status assessment system, a lightweight brain function status assessment device according to any one of claims 1 to 9; a central processing unit; wherein the central processing unit is configured to: receive brain function status assessment indicators from the lightweight brain function status assessment device and fuse them with data from at least one other type of physiological parameter monitoring device to generate a comprehensive health status assessment report.

[0021] This specification provides an electronic device in a fourth aspect, comprising: a memory and a processor, wherein the processor and the memory are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to implement the lightweight brain functional state assessment method described in any of the second aspects.

[0022] The fifth aspect of this specification provides a computer storage medium storing computer program instructions that, when executed, implement the lightweight brain functional state assessment method described in any of the second aspects.

[0023] The sixth aspect of this specification provides a computer program product comprising a computer program that, when executed by a processor, implements the lightweight brain functional state assessment method described in any of the second aspects.

[0024] The lightweight brain function assessment device, method, and system provided in this manual, through the special selection of detection electrodes and characteristic parameters, enables a more scientific, accurate, and reliable assessment of brain function status while simplifying the device structure, simplifying the device's use, and reducing the device cost. This makes it more suitable for the needs of daily brain function testing at home and personal daily health management. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0026] Figure 1 A lateral view of the EEG electrode distribution in the 10-20 system; Figure 2 A top-view schematic diagram of the EEG electrode distribution in the 10-20 system; Figure 3 A schematic diagram of a lightweight brain function assessment device provided in this specification; Figure 4 A three-dimensional structural diagram of the portable head-mounted device provided in this specification. Figure 5 This is a top view of the portable head-mounted device provided in this specification. Figure 6 This is a schematic diagram showing the portable head-mounted device provided in this instruction manual in a stowed state. Figure 7 This is a schematic diagram for calculating the peak α frequency provided in this specification. Figure 8 This is a schematic diagram illustrating the calculation of the 1 / f spectral slope provided in this specification. Figure 9 This is a schematic diagram for calculating the relative power of the α wave provided in this specification; Figure 10 This is a schematic diagram for calculating the relative power of the theta wave provided in this specification; Figure 11 A schematic diagram of a user interface for presenting a device; Figure 12 This specification provides a flowchart illustrating a lightweight method for assessing brain function. Figure 13 This is a schematic diagram of the electronic device provided in this specification. Detailed Implementation

[0027] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0028] Current brain function assessment algorithms suffer from a paradoxical incompatibility: professional-grade assessments employ complex, multi-parameter models with extremely high computational demands, requiring high-performance processors and making them unsuitable for the low-power, low-computational-consumption hardware environments of portable head-mounted devices, thus hindering real-time assessment. Meanwhile, consumer-grade products use simplified linear models, which, while adaptable to low-computational-power hardware, cannot achieve stable and accurate quantitative assessments in low-data-volume (4-8 channels) or unshielded home environments, resulting in significant errors. Currently, there is no dedicated quantization mapping solution that simultaneously adapts to low-computational-power consumer hardware, lightweight 4-8 channel data acquisition, high interference resistance in home settings, and professional-grade assessment accuracy.

[0029] In scenarios such as daily brain function monitoring at home and personal health management, users' routine activities encompass work, study, and rest. Monitoring a user's brain function requires not only real-time assessment but also long-term health monitoring. The applicant categorizes the brain function they need to focus on into the following five dimensions: 1. Arousal Level and Energy State. This dimension focuses on the brain's alertness and basic vitality, which directly affects daytime mental state, reaction speed, and task performance. It is key to determining whether one is sleepy and whether one can quickly enter a working / study state.

[0030] 2. Cognitive Load and Attention Concentration Ability. This dimension focuses on the intensity of the brain's workload and concentration when processing tasks, which is related to learning efficiency and work focus. It is especially applicable to the state management of students and working professionals (such as those who work long hours or prepare for exams).

[0031] 3. Relaxation and Stress Regulation Ability. This dimension focuses on the brain's ability to switch from tension to relaxation and the quality of rest. This dimension affects sleep quality and emotional stability, and is an important indicator for relieving stress and avoiding anxiety, especially applicable to people under high pressure and those with poor sleep.

[0032] 4. Stability of neural rhythms and network coordination. This dimension focuses on the regularity of brain activity and the efficiency of coordination between different areas, reflecting the overall health foundation of the brain. It is related to the fluency of thinking and the efficiency of information processing, and is a core monitoring dimension for long-term brain health.

[0033] 5. Memory processing and cognitive reserve capacity. This dimension focuses on the brain's basic ability to retrieve and store memories and its cognitive potential. It is related to learning outcomes (such as knowledge memorization) and daily task processing (such as remembering passwords and to-do items), and is a core function that needs attention at all ages.

[0034] For ease of daily use, devices for "daily monitoring" of brain function should be lightweight for easy storage and portability. Furthermore, the device's electrodes must cover the five dimensions of functional status mentioned above to ensure the scientific rigor of the assessment.

[0035] Based on the above, this specification proposes to use detection electrodes to acquire EEG signals from the prefrontal, central, parietal, and occipital lobes of the brain, and to calculate four characteristic parameters based on these EEG signals: peak alpha frequency, 1 / f spectral slope, alpha wave relative power, and theta wave relative power. The mapping relationship between these four characteristic parameters and brain functional state is then established.

[0036] Compared to professional-grade EEG testing methods, the lightweight brain function assessment method provided in this manual not only reduces the number of testing electrodes but also simplifies the characteristic parameters used to assess brain function. The simplified testing electrodes and characteristic parameters offer the following technical advantages: 1. A one-to-one correspondence between detection electrodes and feature parameters creates a closed loop with no spatial redundancy. The detection electrodes and feature parameters form a precise mapping of "brain region function - rhythmic features - quantitative parameters," eliminating the need for redundant detection electrodes or feature parameters. Specifically, the "prefrontal + central area electrodes" correspond to the relative power of theta waves, where the signal is most significant. Dedicated electrodes can directly capture rhythms related to cognitive load and memory processing, avoiding interference from irrelevant signals in other brain regions such as the occipital lobe, eliminating the need for redundant electrodes in the temporal lobe. The "parietal + occipital lobe electrodes" correspond to peak alpha frequency and relative alpha wave power, where alpha waves are dominant. Electrodes in this region can accurately capture core rhythms reflecting "awake level and relaxation state," obtaining stable features without requiring full brain coverage, reducing the hardware burden caused by ineffective electrodes. The whole-brain (four brain regions) electrodes correspond to the 1 / f spectrum slope. These four brain regions cover the core functional areas of the brain, and their synchronous signal acquisition can reflect the synergy of the whole-brain neuronal network, meeting fitting requirements without expanding to more channels, avoiding increased computational complexity due to channel redundancy.

[0037] 2. The four feature parameters are complementary and non-redundant, fully covering the five core assessment dimensions of brain function status defined by the applicant. The assessment logic between parameters is non-overlapping and non-redundant, and the signal sources of each parameter are highly consistent with the physiological functions of the brain regions covered by the detection electrodes. This achieves the lightweight design goal of "completing a full-chain scientific assessment of the five dimensions with the fewest core parameters." Specifically, peak alpha frequency (collected by electrodes corresponding to the parietal and occipital lobes): quantifies the frequency stability and inherent rhythmic characteristics of the core alpha wave rhythm, accurately corresponding to the dimensions of arousal level and energy state. It directly reflects the brain's alertness, basic vitality, and information processing efficiency, and is a core quantitative indicator for judging the subject's energy state and ability to quickly enter a work / study state; alpha wave relative power (collected by electrodes corresponding to the parietal and occipital lobes): quantifies the power proportion of the alpha wave rhythm across the entire effective frequency band, accurately corresponding to the dimensions of relaxation state and stress regulation ability. It directly reflects the brain's ability to switch from tension to relaxation and the quality of resting state, and is a core quantitative indicator for assessing the subject's stress level, emotional stability, and sleep adaptation state; theta wave relative power (collected by electrodes corresponding to the prefrontal and central regions): The theta wave rhythm is quantified to determine its power proportion across the entire effective frequency band, precisely corresponding to two dimensions: cognitive load and attention concentration, and memory processing and cognitive reserve. This directly reflects the brain's workload, focus, and learning efficiency during task processing, and also quantifies the brain's basic memory storage and retrieval capabilities and cognitive potential, meeting the daily state management and cognitive ability monitoring needs of people of all ages. The 1 / f spectral slope (collected by electrodes corresponding to four areas of the whole brain): quantifies the power spectrum attenuation pattern and global rhythm distribution characteristics of EEG signals across the entire frequency band, precisely corresponding to the dimensions of neural rhythm and network coordination stability. It directly reflects the regularity of neural activity across the entire brain region, the efficiency of multi-brain region coordination, and the overall health foundation, serving as a core global quantitative indicator for long-term brain health trend monitoring. The evaluation dimensions of the above four characteristic parameters are non-overlapping, with no redundant designs that quantify the same attribute (e.g., uniquely quantifying rhythm frequency characteristics only through the peak α frequency, with no duplicate parameters of the same attribute). These four core parameters comprehensively cover the entire chain of brain functions: "basic health reserve → real-time state regulation → task execution ability," meeting the core design requirements of lightweight home devices that are "portable, easy to operate, and scientifically comprehensive in assessment."

[0038] 3. A balance between lightweight design and evaluation accuracy, suitable for portable scenarios. Specifically: (1) Advantage of simplified detection electrodes: 4–8 channels only cover the core brain region. Compared with the professional-grade 16–64 channel solution, the size, weight and power consumption of the device are greatly reduced. The electrode layout is symmetrical and simple, and it is easy to wear, meeting the engineering implementation requirements of portable devices. (2) Advantage of simplified parameters: The four-parameter calculation logic is simple (FFT, linear regression, power integration), without the need for complex nonlinear feature extraction. It is compatible with the computing power of consumer-grade microprocessors and can realize real-time evaluation (response time ≤ 1 second). (3) Uncompromising accuracy: Due to the accurate correspondence between "detection electrodes and feature parameters" and the absence of redundant signal interference, the evaluation accuracy is on par with multi-channel and multi-parameter solutions (brain function state quantification error ≤ 5%), solving the pain point of "difficulty in balancing lightweight and scientific accuracy" in the industry.

[0039] 4. Enhanced anti-interference capability and improved assessment stability. Specifically: (1) Spatial anti-interference: Electrodes avoid high-interference areas such as the lower temporal lobe and periauricular region, and each parameter only depends on its own brain region signal, reducing the influence of artifacts such as electromyography and electrooculography on non-target parameters (e.g., the theta wave parameter is not affected by the occipital lobe α wave); (2) Feature anti-interference: Frequency features (peak α frequency, 1 / f spectral slope) and power features (α / θ relative power) are cross-validated with each other. Frequency features are less affected by transient artifacts, which can correct short-term fluctuations in power features and improve the stability of assessment results in complex environments such as home and office.

[0040] 5. Strong cross-scenario versatility, suitable for daily monitoring of the entire population. Specifically: (1) Brain region coverage adapts to full-function assessment: prefrontal cortex + central area support cognitive load monitoring (workplace / student scenario), occipital-parietal cortex support relaxation state assessment (high-pressure population / sleep management scenario), whole brain region support network synergy monitoring (elderly health early warning scenario); (2) No population adaptation barrier for parameters: the age correlation of the four parameters is clear (e.g., children have a high proportion of theta waves, and the slope of the 1 / f spectrum is steeper in the elderly), and there is no need to adjust the electrode layout or parameter combination for specific populations such as children, adults, and the elderly, which is highly versatile; in long-term monitoring, health risk early warning can be achieved through parameter trend changes (e.g., the slope of the 1 / f spectrum becomes steeper year by year).

[0041] Based on the above technical concept, this specification provides a lightweight brain function state assessment device, such as... Figure 3 As shown, it includes a portable head-mounted device 10, a processing unit 20, and an output unit 30.

[0042] The portable head-mounted device 10 is provided with a lightweight detection electrode assembly corresponding to the prefrontal cortex, central region, parietal lobe, and occipital lobe of the brain for acquiring multi-channel electroencephalogram (EEG) signals. In some embodiments, the lightweight detection electrode assembly may include only electrodes corresponding to the prefrontal cortex, central region, parietal lobe, and occipital lobe of the brain, and exclude electrodes corresponding to other regions.

[0043] In some embodiments, the detection electrodes on the portable head-mounted device are symmetrically distributed in the frontal and central regions, and distributed along the midline in the parietal and occipital lobes. Specifically, the positions of the detection electrodes correspond to... Figure 1 and Figure 2 The F3 and F4 (prefrontal lobe), C3 and C4 (central area), Pz (midline of parietal lobe), and Oz (midline of occipital lobe) are all located in the frontal lobe.

[0044] The detection electrodes are symmetrically distributed in the prefrontal and central regions, which can reduce individual differences between the left and right hemispheres and improve representativeness. The detection electrodes are distributed along the midline in the parietal and occipital lobes. The scalp at these midline positions is flat, which can improve the fit between the detection electrodes and the scalp on the skull, thereby improving the signal-to-noise ratio of the collected EEG signals and further improving the accuracy of brain function status assessment.

[0045] In addition to the above distribution pattern, at least one of the prefrontal, central, parietal, and occipital lobes may be symmetrically distributed from left to right, and at least one may be distributed along the midline. The detection electrodes corresponding to the same region may include two detection electrodes that are symmetrically distributed from left to right, or detection electrodes that are distributed along the midline.

[0046] Based on the above distribution pattern, to obtain the peak α frequency, 1 / f spectral slope, α wave relative power and θ wave relative power, a minimum of 4 detection electrodes are required (i.e., the detection electrodes in each region are distributed along the midline). Setting 8 detection electrodes (i.e., the detection electrodes in each region are symmetrically distributed left and right) can obtain more accurate and reliable EEG signals and feature parameter sets, thereby achieving a lightweight device.

[0047] In some embodiments, the detection electrodes on the portable head-mounted device are positioned to avoid the temporal lobe, frontal pole, and periauricular regions. These regions are susceptible to interference from electromyography (chewing, facial movements, etc.) and environmental noise, and the intensity of alpha wave signals detectable in the frontal and temporal lobes is much lower than that in the parietal occipital region. Therefore, acquiring EEG signals from these regions would reduce the overall signal-to-noise ratio of the acquired signals, making it difficult to meet the accuracy requirements for assessing brain function.

[0048] It should be noted that the detection electrodes described in this application are channels for acquiring electroencephalogram (EEG) signals and do not include reference electrodes or ground electrodes. The reference electrode can be placed on the auricle, and the ground electrode can be placed on the midline of the frontal pole.

[0049] Portable head-mounted devices can be designed as helmets or goggles.

[0050] In some embodiments, the portable head-mounted device includes a first fixing part and a second fixing part for setting detection electrodes. The first fixing part is an annular fixing part corresponding to the circumference of the head, and the second fixing part is a fixing part corresponding to the midline of the head. The circumferential length of the first fixing part is adjustable, and the fixing position on at least one side of the second fixing part is detachable and adjustable.

[0051] The portable headband device described above can securely fix the detection electrodes to the head using the first and second fixing parts. The first fixing part can be adjusted to accommodate people with different head circumferences, and the second fixing part can be adjusted to make the detection electrodes on the top of the head fit the scalp better. This makes the portable headband device easy to adapt to the heads of people of all ages, with a wide range of compatibility and high versatility.

[0052] Furthermore, in some embodiments, the second fixing part is rotatably fixed to the first fixing part, and when the portable head-mounted device is in a stored state, the second fixing part rotates to overlap with the first fixing part.

[0053] By rotating the second fixing part to overlap with the first fixing part, the portable head-mounted device can be stored, making its use and storage more convenient and simple. Through the storage method of "rotating the second fixing part to overlap with the first fixing part", the lightweight brain function status assessment device can be stored in a flat shape, which can not only greatly improve the utilization of storage space, but also effectively compress the storage volume, making it more suitable for daily home storage scenarios (such as drawers, small storage boxes), further enhancing the convenience of the device in daily home use.

[0054] Figure 4 This is a three-dimensional structural diagram of the portable head-mounted device provided in this specification. Figure 5 This is a top view schematic diagram of the portable head-mounted device provided in this instruction manual. Figure 6 This is a schematic diagram showing the portable head-mounted device provided in this specification in its stowed state. In the diagram, 11 represents the detection electrode, 12 represents the reference electrode, 13 represents the ground electrode, A represents the first fixing part, and B represents the second fixing part.

[0055] The processing unit 20 is disposed within or communicatively connected to the portable head-mounted device 10. The processing unit 20 is configured to perform the following operations: determine a lightweight four-parameter feature set from the multi-channel EEG signal, the four-parameter feature set including the following four feature parameters: peak alpha frequency, 1 / f spectral slope, alpha wave relative power, and theta wave relative power; and calculate a quantitative index value of brain functional state based on a preset mapping relationship according to the lightweight four-parameter feature set.

[0056] The mapping relationship ensures that when the four input parameter feature sets are the same, a unique quantitative index value of brain functional state is output.

[0057] The "mapping relationship that outputs a unique quantitative index value of brain functional state when the four input parameter feature sets are the same" mentioned in this application refers to the fact that under ideal technical conditions, such as no data processing errors, the detection equipment being in a standard working environment and rated working state, and no external uncontrollable interference factors, the mapping relationship itself has the uniqueness of the output result. This is the core technical characteristic and design goal of the mapping relationship, and also the key feature of the technical solution protected by this application.

[0058] In practical applications, due to objective, non-intentional, minor data processing errors in data acquisition, transmission, and calculation processes, or unavoidable technical factors such as slight fluctuations in the detection environment or minor parameter deviations in normal equipment operation, the quantitative index values ​​of brain functional status may exhibit minor fluctuations within a reasonable range when the same four-parameter feature set is input. This situation is a normal technical phenomenon in the implementation of the technical solution of this application, does not change the unique design feature of the mapping relationship itself, and does not deviate from the scope of the core technical solution defined by this application.

[0059] In other words, the final output quantitative index value of brain functional state is determined only by four EEG characteristic parameters: peak alpha frequency, 1 / f spectral slope, alpha wave relative power, and theta wave relative power, and has no direct determining relationship with other EEG characteristic parameters.

[0060] The above mapping relationship is an engineering quantification model specifically developed for the four-parameter feature set, 4-8 channel lightweight head-mounted devices, consumer-grade low-computing-power microprocessors, and home daily use scenarios specified in this application. Its form can be a lightweight, pruned and optimized artificial intelligence network model, or a nonlinear regression function adapted to low-computing-power hardware.

[0061] This mapping relationship is not a universal mathematical model or data processing rule. Its training, pruning, optimization, and deployment are all completed around three core engineering goals: "adapting to the low computing power environment of portable devices, achieving a real-time response of ≤1 second for a single frame of data, and maintaining an evaluation error of ≤5% in an unshielded home environment." After the model completes basic training with massive labeled samples (including four-parameter feature sets and gold standard labels for quantitative indicators of brain functional state), it needs to be further optimized for lightweighting through engineering methods such as model fixed-point quantization, operator simplification, and redundant layer pruning. This ensures that it can be directly deployed in the consumer-grade microprocessor of portable head-mounted devices, complete local real-time inference without cloud computing power support, and achieve a computation response time of ≤1 second for a single frame of EEG data, which is fully adapted to the real-time evaluation needs in daily home scenarios.

[0062] Artificial intelligence network models can specifically be machine learning (such as random forest, support vector regression SVR), deep learning (such as CNN, LSTM), and other model types.

[0063] The core role of artificial intelligence network models is to establish a mapping relationship (which may be a complex nonlinear mapping relationship) between four-parameter features and brain functional state, thus solving the problems of strong subjectivity and difficulty in quantification in human assessment.

[0064] Multiple sample users can be set up, and portable head-mounted devices can be worn by each sample user to collect lightweight four-parameter feature sets corresponding to each sample user. The quantitative index values ​​of brain function status of each sample user can be determined by other methods (such as professional-grade EEG signal detection equipment and brain function status assessment methods, or more cumbersome methods such as long-term observation and questionnaire surveys). The lightweight four-parameter feature set and the quantitative index value of brain function status corresponding to each sample user can be used as training data, and the above-mentioned artificial intelligence network model can be trained using these training data.

[0065] Since the four feature parameters in the lightweight four-parameter feature set are specially selected, representative, and have less interference, inputting the lightweight four-parameter feature set into the artificial intelligence model can obtain quantitative index values ​​of brain functional state more accurately.

[0066] The processing unit 20 may include analog signal processing units such as signal amplifiers, bandpass filters, and notch filters, and may also include a data processor. The data processor is used to extract four feature parameters from the signal after analog-to-digital conversion to form a four-parameter feature set.

[0067] The four feature parameter set can consist of only four feature parameters: peak α frequency, 1 / f spectral slope, α wave relative power, and θ wave relative power. Alternatively, it can include other feature parameters based on these four feature parameters. These feature parameters can be calculated from the EEG signals detected by the detection electrodes in four brain regions: the prefrontal cortex, central cortex, parietal cortex, and occipital cortex.

[0068] The above four characteristic parameters, approached from three core technical dimensions—rhythmic characteristics, power distribution, and network coordination—form a non-redundant and highly complementary scientific evaluation system. This avoids the one-sidedness and limitations of single-parameter evaluation, and the evaluation results of each technical dimension accurately correspond to the five core evaluation dimensions of brain functional status defined by the applicant. Specifically, peak alpha frequency focuses on arousal level and energy state, corely characterizing the inherent stability of brain neural rhythms, and is a core rhythmic characteristic indicator reflecting brain alertness and basic vitality; alpha wave relative power quantifies relaxation state and stress regulation ability, reflecting the balance of resting-activated brain resource allocation through power ratio, and is a core power distribution indicator for assessing stress regulation and resting quality; theta wave relative power assesses cognitive load and attention concentration ability, memory processing and cognitive reserve ability, reflecting the load intensity and memory processing activity of the brain during task processing through power ratio, and is a core power distribution indicator suitable for all age groups; 1 / f spectrum slope characterizes the stability of neural rhythm and network coordination, accurately reflecting the complexity of whole-brain neuronal network coordination and the basic health status of brain development and aging, and is a core network coordination indicator for monitoring long-term brain health.

[0069] These four characteristic parameters, when combined, comprehensively cover the entire chain of brain function from "basic health → dynamic state → task processing," enabling both real-time assessment (such as current focus or fatigue) and monitoring long-term health trends (such as cognitive decline risk and developmental maturity), achieving a "three-dimensional assessment" rather than a "single-point judgment." This addresses the core pain points of existing technologies while achieving a balance between professionalism and practicality.

[0070] The combination of the above four characteristic parameters follows the principle of necessity and sufficiency, and can meet the needs of portable home use.

[0071] The method of assessing brain functional status by using a combination of four feature parameters has the following advantages: 1. High computational efficiency: It does not require complex nonlinear feature extraction (such as multi-scale entropy and higher-order statistics), and can be calculated using only FFT, linear regression, and power integral, which has low requirements for device computing power (consumer-grade microprocessors can support it), enabling real-time assessment; 2. Low data requirements: It only requires 4-8 channels of data, eliminating the need for 16-64 channels of whole-brain coverage in professional-grade equipment, reducing the size, weight, and cost of the device, and meeting the portability needs of daily monitoring for families and individuals; 3. Avoidance of redundant interference: It does not introduce parameters that are weakly correlated with brain function (such as absolute power of delta waves and instantaneous amplitude of a single brain region), reducing the interference of irrelevant factors on the assessment results and solving the pain points of "redundant feature parameters and unstable accuracy" in existing technologies.

[0072] The evaluation results using four characteristic parameters can be directly applied to different usage scenarios, satisfying both the daily status management needs of ordinary people and providing effective references for health monitoring. Specifically: 1. Daily scenarios: α / θ relative power determines whether it is suitable for work, study, or rest, and peak α frequency assesses energy status, enabling personalized time management (e.g., breaking down tasks when α waves are too high, and meditating when α waves are too low); 2. Health monitoring scenarios: Long-term trends in 1 / f spectrum slope monitor the risk of cognitive decline (e.g., a persistently steep slope in the elderly) and the developmental maturity of children (a gradually flattening slope in adolescents); abnormal combinations of peak α frequency and θ wave relative power provide early warning of attention deficit disorders, mild cognitive impairment, and other problems; 3. Cross-population adaptability: Applicable to different populations such as children and adolescents (developmental monitoring), adults (work efficiency management), and the elderly (brain health maintenance), without the need to adjust parameter combinations for specific populations, making it highly versatile.

[0073] The proprietary quantization mapping relationship in this application forms a one-to-one closed-loop technical solution with the four-parameter feature set and the 4-8 channel lightweight hardware structure, which is irreplaceable. The core of this solution is reflected in the following two aspects: 1. Without this mapping relationship, it is impossible to achieve a balance between lightweight hardware and professional-grade precision.

[0074] If the proprietary quantization mapping relationship of this application is not adopted, there are only two alternative solutions in the prior art, neither of which can meet the core inventive purpose of this application.

[0075] The two alternatives are: (1) Using a professional-grade full-band multi-parameter complex model: This type of model requires input of more than 10 EEG feature parameters and more than 16 channels of whole-brain EEG data, which has extremely high computing power requirements. The calculation time for a single frame of data is ≥4.8 seconds, which cannot achieve real-time evaluation on the consumer-grade low-computing-power microprocessor of this application, and is completely inconsistent with the lightweight design goal of portable devices; (2) Using a conventional simplified linear regression model: Although this type of model can be adapted to low-computing-power hardware, under the condition of 4-8 channels and four parameters of the small amount of data input in this application, it cannot fit the nonlinear relationship between the four parameters and the brain functional state. The relative error of the evaluation in the home unshielded environment is ≥22%, which cannot meet the core requirements of accurate evaluation.

[0076] Only the proprietary quantization mapping relationship of this application can achieve an evaluation relative error of ≤5% comparable to that of professional-grade 64-channel devices, while meeting the real-time response requirement of ≤1 second, under the premise of only inputting a four-parameter feature set and adapting to consumer-grade low-computing-power hardware. This is an irreplaceable core technology in the lightweight solution of this application.

[0077] 2. Without this mapping relationship, it is impossible to achieve a full-dimensional evaluation of the value of the four-parameter combination.

[0078] The four-parameter feature set of this application corresponds to the five core assessment dimensions of brain functional state. There is a non-linear complementary relationship between the parameters, rather than a simple linear superposition relationship. Conventional general-purpose algorithm models cannot specifically fit the complementary characteristics of the four parameters, resulting in either dimensional redundancy or dimensional missingness, failing to fully cover the five assessment dimensions. In contrast, the proprietary quantitative mapping relationship of this application is specifically trained and optimized based on the complementary characteristics of the four parameters and the correspondence of the five assessment dimensions. It can accurately fit the non-linear relationship between the four parameters and brain functional state, achieving the core invention objective of "completing accurate assessment of all dimensions with the fewest parameters," forming an inseparable technical whole with the four-parameter feature set.

[0079] In some embodiments, the processing unit 20 calculates the peak α frequency based on the electroencephalogram (EEG) signals detected by the detection electrodes corresponding to the parietal and occipital lobes in the lightweight detection electrode group, such as... Figure 7 As shown, it specifically includes SA1 to SA4.

[0080] SA1: After preprocessing the EEG signals detected by the detection electrodes corresponding to the parietal and occipital lobes, Fourier transform is performed on the preprocessed EEG signals to obtain the power spectrum corresponding to each detection electrode.

[0081] Alpha waves are most prominent in the occipital and parietal lobes, particularly at locations O1, O2, P3, and P4. Therefore, EEG signals at locations O1, O2, P3, and P4 can be acquired using detection electrodes on a portable head-mounted device and subjected to Fourier transform.

[0082] With the detection electrodes on the portable head-mounted device distributed along the midline in the parietal and occipital lobes, EEG signals at the Pz (parietal midline) and Oz (occipital midline) positions can be obtained through the detection electrodes on the portable head-mounted device and subjected to Fourier transform.

[0083] SA2: Based on the power spectrum, extract the EEG signal corresponding to the first frequency band range of each detection electrode.

[0084] The first frequency band can specifically be 8-13Hz, and the waves in this frequency band are alpha waves.

[0085] SA3: Select the peak frequency corresponding to each detection electrode from the extracted EEG signals. The peak frequency is the frequency value corresponding to the maximum power.

[0086] SA4: Calculate the average value of the peak frequencies corresponding to each detection electrode, and use the average value as the peak α frequency in the four-parameter feature set.

[0087] In some embodiments, the processing unit 20 calculates the 1 / f spectral slope based on the electroencephalogram (EEG) signals detected by the detection electrodes corresponding to the prefrontal, central, parietal, and occipital lobes of the lightweight detection electrode group, such as... Figure 8 As shown, it specifically includes SC1 to SC5 as follows.

[0088] SC1: Preprocesses the EEG signals detected by the detection electrodes corresponding to the prefrontal, central, parietal, and occipital lobes of the brain, and calculates the power spectral density corresponding to each detection electrode based on the preprocessed EEG signals.

[0089] The detection electrodes correspond to the prefrontal cortex, central area, parietal lobe, and occipital lobe of the brain, specifically eight detection electrodes: F3, F4, C3, C4, P3, P4, O1, and O2. In this manual, each detection electrode is referred to as a channel.

[0090] In portable head-mounted devices, the detection electrodes are symmetrically distributed in the prefrontal and central regions. In the case where the electrodes are distributed along the midline in the parietal and occipital lobes, the detection electrodes corresponding to the prefrontal, central, parietal, and occipital lobes of the brain can specifically be six detection electrodes: F3, F4, C3, C4, Pz, and Oz.

[0091] The 1 / f spectral slope describes the shape and energy distribution of the entire spectrum. It is a global feature across frequency bands and reflects the balance between randomness and order in brain activity. It is not a wave, but a mathematical parameter that describes the energy decay pattern of all frequencies (from low to high). It focuses on the characteristics of the background signal.

[0092] SC2: Filter out the power spectral density in the second frequency band range.

[0093] The second frequency band can be 1-30Hz.

[0094] SC3: Perform logarithmic transformation on the filtered data.

[0095] SC4: In a double logarithmic coordinate system, the power spectral density is linearly fitted, and the slope of the fitted line corresponding to each detection electrode is determined based on the fitting results.

[0096] In a log-log coordinate system, the horizontal axis is log (frequency) and the vertical axis is log (power). In a log-log coordinate system, the power spectral density of an EEG signal is usually approximated as a descending straight line, and the slope of this line is the 1 / f spectral slope.

[0097] SC5: Calculate the average value of the slope of the fitted straight line corresponding to each detection electrode, and use the average value as the 1 / f spectral slope in the four-parameter feature set.

[0098] In some embodiments, the processing unit 20 calculates the relative power of the alpha wave based on the electroencephalogram (EEG) signals detected by the detection electrodes corresponding to the parietal and occipital lobes in the lightweight detection electrode group, such as... Figure 9 As shown, it specifically includes SD1 to SD4.

[0099] SD1: After preprocessing the EEG signals detected by the detection electrodes corresponding to the parietal and occipital lobes, the power spectral density corresponding to each detection electrode is calculated based on the preprocessed EEG signals.

[0100] Alpha waves are most prominent in the occipital and parietal lobes, particularly at locations O1, O2, P3, and P4. Therefore, EEG signals at locations O1, O2, P3, and P4 can be acquired using detection electrodes on a portable head-mounted device and subjected to Fourier transform.

[0101] With the detection electrodes on the portable head-mounted device distributed along the midline in the parietal and occipital lobes, EEG signals at the Pz (parietal midline) and Oz (occipital midline) positions can be obtained through the detection electrodes on the portable head-mounted device and subjected to Fourier transform.

[0102] SD2: Filter out the power spectral density corresponding to the first frequency band range, and calculate the first power of the first frequency band range based on the power spectral density.

[0103] The first frequency band can specifically be 8-13Hz, and the waves in this frequency band are alpha waves.

[0104] The first power can be calculated by integrating the power spectral density corresponding to the first frequency band.

[0105] SD3: Filter out the power spectral density corresponding to the second frequency band range, and calculate the second power of the second frequency band range based on the power spectral density.

[0106] The second frequency band can specifically be 1-30Hz, and the waves in this frequency band are the effective frequency bands for the whole brain.

[0107] The second power can be calculated by integrating the power spectral density corresponding to the second frequency band.

[0108] SD4: Calculate the ratio of the first power to the second power as the α-wave relative power in the four-parameter feature set.

[0109] In some embodiments, the processing unit 20 calculates the relative power of theta waves based on the electroencephalogram (EEG) signals detected by the detection electrodes corresponding to the prefrontal and central regions in the lightweight detection electrode group, such as... Figure 10 As shown, it specifically includes SE1 to SE4.

[0110] SE1: After preprocessing the EEG signals detected by the detection electrodes corresponding to the prefrontal cortex and central region, the power spectral density corresponding to each detection electrode is calculated based on the preprocessed EEG signals.

[0111] The detection electrodes corresponding to the prefrontal cortex and the central area can specifically be four electrodes: F3, F4, C3, and C4.

[0112] In portable head-mounted devices, when the detection electrodes are distributed along the midline in the prefrontal cortex and central region, the detection electrodes corresponding to the prefrontal cortex and central region can specifically be two detection electrodes, Fz and Cz.

[0113] SE2: Filter out the power spectral density corresponding to the third frequency band range, and calculate the third power of the third frequency band range based on the power spectral density.

[0114] SE3: Filter out the power spectral density corresponding to the second frequency band range, and calculate the second power of the second frequency band range based on the power spectral density.

[0115] SE4: Calculate the ratio of the third power to the second power as the θ-wave relative power in the four-parameter feature set.

[0116] The output unit 30 is used to output quantitative index values ​​of brain functional state. Specifically, the output unit 30 can be a user-visualized presentation device such as a display screen or a voice player, or it can be a code segment used to transmit the quantitative index values ​​of brain functional state to the user-visualized presentation device.

[0117] The lightweight brain function assessment device provided in this manual, through the special selection of detection electrodes and characteristic parameters, simplifies the device structure, simplifies the use of the device, and reduces the cost of the device, while also enabling a more scientific, accurate, and reliable assessment of brain function status. This makes it more suitable for the needs of daily brain function testing at home and personal daily health management.

[0118] In some embodiments, the lightweight brain function state assessment device further includes a presentation device for presenting to a user a quantitative index value of brain function state, and at least one of the following: a radar chart of four feature parameters, a trend of change of the quantitative index value of brain function state, and personalized suggestions based on the assessment results of the quantitative index value of brain function state.

[0119] In this scheme, the quantitative index value of brain functional state can be represented by various concrete forms. Brain age assessment value, as an optional embodiment of this quantitative index, is constructed based on the inherent correlation between human brain functional state and the EEG characteristics of healthy people at different actual age stages, and is an effective form of intuitive quantitative representation of brain functional state.

[0120] As an optional embodiment, the core technological advantage of brain age assessment lies in transforming the abstract state of brain function into a quantitative value corresponding to actual age and its difference. By comparing it with the EEG characteristic benchmark of healthy individuals, a quantitative and concrete representation of brain function is achieved, effectively solving the problem of abstract representation and difficulty in intuitive perception in existing EEG assessment technologies. The brain age assessment value of this scheme does not simply correspond to actual age, but is calculated using a four-parameter feature set consisting of peak alpha frequency, 1 / f spectral slope, alpha wave relative power, and theta wave relative power as the sole input, and is obtained through a nonlinear regression mapping relationship determined by training with EEG sample datasets of healthy individuals at different actual age stages. The sample dataset covers the four-parameter EEG characteristics of healthy individuals of different ages and genders, ensuring a strong correlation between brain age assessment value and brain function state, while also giving brain age assessment value universality across populations.

[0121] In this solution, the output format of the brain age assessment value can be adapted to the application scenario of the portable acquisition device. This includes directly outputting the quantitative brain age value, outputting the difference between the brain age value and the user's actual age, or outputting a long-term trend curve of the brain age assessment value based on continuously acquired EEG data. Simultaneously, reasonable numerical ranges can be set for the brain age difference, with different ranges corresponding to different visualization methods, such as using different color labels and numerical highlighting. This design is suitable for both the miniature, lightweight display unit of portable head-mounted devices and the display interface of external smart terminals, achieving a clear and intuitive display of brain age assessment values, meeting the lightweight and convenient technical design requirements of portable EEG assessment devices.

[0122] It should be clearly pointed out that this application uses brain age assessment as an optional embodiment of quantitative indicators of brain functional state, and does not limit the scope of protection of such quantitative indicators. Based on the four-parameter feature set and preset mapping relationship defined in this application, other quantitative indicators for characterizing brain functional state, such as brain vitality index, cognitive load, and relaxation depth, can also be output. All the above-mentioned quantitative indicators of brain functional state calculated using the four-parameter feature set as input and the mapping relationship defined in this application fall within the scope of protection of this application. This application selects brain age assessment as an optional embodiment because it achieves a unity of quantification, intuitiveness, and universality in the characterization of brain functional state at the technical level.

[0123] Figure 11 This is a schematic diagram of a user interface for presenting the device, in which the quantitative index value of brain functional state is represented as the brain age assessment value, and the user interface displays the brain age difference (the brain age difference represents the difference between the brain age assessment value and the actual age), a radar chart of four characteristic parameters, optimization suggestions, and a brain age trend chart.

[0124] The aforementioned brain function assessment device is not used for disease diagnosis, but only to provide non-diagnostic electroencephalogram (EEG) signal reference data. That is, the quantitative indicators of brain function are not used for disease diagnosis.

[0125] This specification provides a lightweight method for assessing brain function, which can be implemented using the aforementioned lightweight brain function assessment device. For example... Figure 12 As shown, it includes the following steps S10 to S40.

[0126] S10: Detects multi-channel EEG signals from the prefrontal, central, parietal, and occipital lobes of the brain using a portable head-mounted device.

[0127] S20: Determine a lightweight four-parameter feature set from the multi-channel EEG signal. The four-parameter feature set includes the following four feature parameters: peak α frequency, 1 / f spectral slope, α wave relative power, and θ wave relative power.

[0128] In some embodiments, the above-described S20 includes Figures 7 to 10 The method described by any one of them.

[0129] S30: Calculate the quantitative index value of brain functional state based on the lightweight four-parameter feature set and a preset mapping relationship; wherein the mapping relationship is determined by training through a sample dataset, and the mapping relationship ensures that when the input four-parameter feature set is the same, a unique quantitative index value of brain functional state is output.

[0130] S40: Output the quantitative index value of the brain functional state.

[0131] In some embodiments, S40 includes: presenting the user with a quantitative index value of brain function status, and at least one of the following: a radar chart of four feature parameters, a trend of change of the quantitative index value of brain function status, and personalized suggestions based on the assessment results of the quantitative index value of brain function status.

[0132] The aforementioned lightweight brain function assessment method can be understood by referring to the aforementioned lightweight brain function assessment device, and will not be elaborated here.

[0133] This specification also provides a health status assessment system, which includes any of the above-mentioned lightweight brain function status assessment devices and a central processing device; wherein, the central processing device is configured to: receive brain function status assessment indicators from the lightweight brain function status assessment device, and fuse them with data from at least one other type of physiological parameter monitoring device to generate a comprehensive health status assessment report.

[0134] "Other types of physiological parameter monitoring devices" can include wearable devices such as smart bracelets and smart glasses, as well as blood pressure monitors, blood glucose meters, body composition scales, etc.

[0135] The brain function status assessment indicators from the lightweight brain function status assessment device can be used as subsystem scores of the nervous system or cognitive system. The comprehensive health status assessment includes scores of multiple body subsystems, with the nervous system or cognitive system being one of them.

[0136] This application also provides an electronic device, such as... Figure 13 As shown, the electronic device may include a processor 1301 and a memory 1302, wherein the processor 1301 and the memory 1302 may be connected via a bus or other means. Figure 13 Taking the example of a connection between China and Israel via a bus.

[0137] Processor 1301 may be a central processing unit (CPU). Processor 1301 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof.

[0138] The memory 1302, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the lightweight brain functional state assessment method in the embodiments of this application. The processor 1301 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory 1302, thereby realizing the lightweight brain functional state assessment method in the above method embodiments.

[0139] The memory 1302 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor 1301, etc. Furthermore, the memory 1302 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 1302 may optionally include memory remotely located relative to the processor 1301, and these remote memories may be connected to the processor 1301 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0140] The one or more modules are stored in the memory 1302 and, when executed by the processor 1301, perform the aforementioned lightweight brain function state assessment method.

[0141] The specific details of the above-mentioned electronic device can be understood by referring to the relevant descriptions and effects in the method embodiments, and will not be repeated here.

[0142] This specification also provides a computer storage medium storing computer program instructions that, when executed, implement the aforementioned lightweight brain function state assessment method.

[0143] This specification also provides a computer program product comprising a computer program that, when executed by a processor, implements the aforementioned lightweight brain function state assessment method.

[0144] To further verify the technical advantages of the four-parameter combination of this application, this embodiment completes the performance comparison through a large-sample human trial. The specific test plan and results are as follows: Subjects: 120 healthy participants aged 6-75 years were recruited, including children, adolescents, young adults, and the elderly. Participants with a history of neurological diseases, mental illnesses, or head injuries were excluded.

[0145] Experimental equipment: The 4-channel lightweight head-mounted device (electrode positions Fz, Cz, Pz, Oz) of this application and the internationally recognized 64-channel professional-grade EEG device (as the gold standard for evaluation) were used.

[0146] Experimental scenario: Simulating an unshielded daily home environment, without electromagnetic shielding or professional operation, 3-minute EEG signals were collected from subjects under three core daily scenarios: resting relaxation, mild cognitive load (two-digit continuous addition and subtraction calculation), and meditation relaxation.

[0147] Comparison schemes: The same batch of EEG data was quantitatively assessed using the four-parameter combination of this application and three conventional combinations (Combination 1: peak α frequency + α wave relative power, two-parameter combination; Combination 2: θ / β power ratio + 1 / f spectral slope, two-parameter combination; Combination 3: δ+θ+α+β+γ full-band relative power + peak α frequency + 1 / f spectral slope, professional-grade conventional full-band multi-parameter combination with 7 or more parameters). The assessment results of a professional-grade 64-channel device were used as the gold standard to compare the core performance indicators of each scheme. The results are shown in Table 1 below.

[0148] Table 1 Comparison of core performance indicators of each scheme

[0149] The results of this experiment clearly demonstrate that the four-parameter combination of this application is not a simple superposition of conventional indicators in the field, but rather achieves a balance of four core technical objectives through precise screening and design: (1) In terms of evaluation accuracy, with 4-channel lightweight hardware, it achieves the same evaluation accuracy as professional-grade 16-channel or higher full-band multi-parameter solutions, with a relative error of ≤5%; (2) In terms of anti-interference capability, it is far superior to conventional β-wave correlation combinations and full-band multi-parameter combinations in the field, and is suitable for daily use in unshielded home environments; (3) In terms of lightweight adaptability, the computing power requirement is extremely low, and real-time evaluation can be achieved on consumer-grade microprocessors. Ordinary users can complete the wearing and use within 1 minute, which is fully suitable for daily home scenarios; (4) In terms of evaluation comprehensiveness, it fully covers the five core dimensions of brain functional status, and at the same time has the ability to monitor long-term brain health trends, solving the core defects of conventional simplified combination dimensions.

[0150] In summary, the four-parameter combination of this application resolves the long-standing technical contradiction in the field that "professional-grade equipment cannot be used at home and the evaluation of consumer-grade equipment is unscientific." Its technical effect cannot be easily obtained by those skilled in the art through conventional parameter combinations.

[0151] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0152] The various embodiments in this specification are described in a progressive manner. For the same or similar parts between the various embodiments, please refer to each other. The focus of each embodiment is to describe the differences from other embodiments.

[0153] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions.

[0154] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0155] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute certain parts of the methods of various embodiments of this application.

[0156] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0157] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0158] Although this application has been described through embodiments, those skilled in the art will know that this application has many modifications and variations without departing from the spirit of this application, and it is intended that the appended claims cover such modifications and variations without departing from the spirit of this application.

Claims

1. A lightweight brain function assessment device, characterized in that, include: A portable head-mounted device equipped with detection electrode sets corresponding to the prefrontal cortex, central region, parietal lobe, and occipital lobe of the brain, used to acquire multi-channel electroencephalogram (EEG) signals; A processing unit is disposed within or communicatively connected to the portable head-mounted device; the processing unit is configured to perform the following operations: determine a four-parameter feature set from the multi-channel EEG signal, the four-parameter feature set including the following four feature parameters: peak alpha frequency, 1 / f spectral slope, alpha wave relative power, and theta wave relative power; calculate a quantitative index value of brain functional state based on the four-parameter feature set and a preset mapping relationship; wherein the mapping relationship is determined by training through a sample dataset, and the mapping relationship ensures that when the input four-parameter feature set is the same, a unique quantitative index value of brain functional state is output; The output unit is used to output the quantitative index value of the brain functional state.

2. The apparatus according to claim 1, characterized in that, The processing unit calculates the peak α frequency based on the EEG signals detected by the detection electrodes corresponding to the parietal and occipital lobes in the detection electrode group, specifically including: After preprocessing the EEG signals detected by the detection electrodes corresponding to the parietal and occipital lobes, the power spectrum corresponding to each detection electrode is calculated based on the preprocessed EEG signals. Based on the power spectrum, the electroencephalogram (EEG) signals corresponding to the first frequency band range of each detection electrode are extracted; The peak frequencies corresponding to each detection electrode are selected from the extracted EEG signals, where the peak frequency is the frequency value corresponding to the maximum power. The average value of the peak frequencies corresponding to each detection electrode is used as the peak α frequency in the four-parameter feature set.

3. The apparatus according to claim 1, characterized in that, The processing unit calculates the 1 / f spectral slope based on the EEG signals detected by the detection electrodes corresponding to the prefrontal, central, parietal, and occipital lobes of the brain in the detection electrode group, specifically including: The EEG signals detected by the detection electrodes corresponding to the prefrontal, central, parietal, and occipital lobes of the brain are preprocessed, and the power spectral density corresponding to each detection electrode is calculated based on the preprocessed EEG signals. The power spectral density of the second frequency band is selected; Perform a logarithmic transformation on the selected data; In a double logarithmic coordinate system, the power spectral density is linearly fitted, and the slope of the fitted line corresponding to each detection electrode is determined based on the fitting results. The average value of the slope of the fitted straight line corresponding to each detection electrode is used as the 1 / f spectral slope in the four-parameter feature set.

4. The apparatus according to claim 1, characterized in that, The processing unit calculates the relative power of the alpha wave based on the electroencephalogram (EEG) signals detected by the detection electrodes corresponding to the parietal and occipital lobes in the detection electrode group, specifically including: After preprocessing the EEG signals detected by the detection electrodes corresponding to the parietal and occipital lobes, the power spectral density corresponding to each detection electrode is calculated based on the preprocessed EEG signals. Filter out the power spectral density corresponding to the first frequency band range, and calculate the first power of the first frequency band range based on the power spectral density; Filter out the power spectral density corresponding to the second frequency band range, and calculate the second power of the second frequency band range based on the power spectral density; The ratio of the first power to the second power is calculated as the α-wave relative power in the four-parameter feature set.

5. The apparatus according to claim 1, characterized in that, The processing unit calculates the relative power of theta waves based on the EEG signals detected by the detection electrodes corresponding to the prefrontal and central regions in the detection electrode group, specifically including: After preprocessing the EEG signals detected by the detection electrodes corresponding to the prefrontal cortex and central region, the power spectral density corresponding to each detection electrode is calculated based on the preprocessed EEG signals. The power spectral density corresponding to the third frequency band is selected, and the third power of the third frequency band is calculated based on the power spectral density. Filter out the power spectral density corresponding to the second frequency band range, and calculate the second power of the second frequency band range based on the power spectral density; The ratio of the third power to the second power is calculated as the θ-wave relative power in the four-parameter feature set.

6. The apparatus according to claim 1, characterized in that, The detection electrodes on the portable head-mounted device are symmetrically distributed in the frontal and central regions, and distributed along the midline in the parietal and occipital lobes.

7. The apparatus according to claim 1, characterized in that, The portable head-mounted device includes a first fixing part and a second fixing part for setting detection electrodes. The first fixing part is an annular fixing part corresponding to the circumference of the head, and the second fixing part is a fixing part corresponding to the midline position of the head. The circumferential length of the first fixing part is adjustable, and the fixing position on at least one side of the second fixing part is detachable and adjustable.

8. The apparatus according to claim 7, characterized in that, The second fixing part is rotatably fixed to the first fixing part; When the portable head-mounted device is in the storage state, the second fixing part rotates to overlap with the first fixing part.

9. The apparatus according to claim 1, characterized in that, The output unit includes: A presentation device for presenting to a user quantitative indicators of brain function status, and at least one of the following: a radar chart of four characteristic parameters, a trend of change in the quantitative indicators of brain function status, and personalized suggestions based on the assessment results of the quantitative indicators of brain function status.

10. A lightweight method for assessing brain functional status, characterized in that, include: Multichannel EEG signals from the prefrontal cortex, central region, parietal lobe, and occipital lobe of the brain were detected using a portable head-mounted device; A four-parameter feature set is determined from the multi-channel EEG signal. The four-parameter feature set includes the following four feature parameters: peak α frequency, 1 / f spectral slope, α wave relative power, and θ wave relative power. Based on the four-parameter feature set, a quantitative index value of brain functional state is calculated based on a preset mapping relationship; wherein, the mapping relationship is determined by training through a sample dataset, and the mapping relationship ensures that when the input four-parameter feature set is the same, a unique quantitative index value of brain functional state is output. Output the quantitative index value of the brain functional state.

11. The method according to claim 10, characterized in that, Output the quantitative index values ​​of the brain functional state, including: Present users with quantitative indicators of brain function status, as well as at least one of the following: a radar chart of four characteristic parameters, a trend of changes in the quantitative indicators of brain function status, and personalized suggestions based on the assessment results of the quantitative indicators of brain function status.

12. A health status assessment system, characterized in that, The lightweight brain function assessment device according to any one of claims 1 to 9; Central processing equipment; The central processing unit is configured to receive brain function status assessment indicators from the lightweight brain function status assessment device and fuse them with data from at least one other type of physiological parameter monitoring device to generate a comprehensive health status assessment report.

13. An electronic device, characterized in that, include: The system includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to implement the lightweight brain function state assessment method of claim 10 or 11.

14. A computer storage medium, characterized in that, The computer storage medium stores computer program instructions, which, when executed, implement the lightweight brain function state assessment method of claim 10 or 11.

15. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the lightweight brain functional state assessment method of claim 10 or 11.

Images