A biometric analysis method and apparatus, an electronic device, and a storage medium

Abstract

The application discloses a biological feature analysis method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an electroencephalogram signal and a cerebral oximetry signal of a target; performing feature extraction on the electroencephalogram signal to obtain an electroencephalogram feature, and performing feature extraction on the cerebral oximetry signal to obtain a cerebral oximetry feature; and analyzing the electroencephalogram feature and the cerebral oximetry feature to obtain a biological feature, wherein the biological feature comprises a neurovascular coupling relationship between the electroencephalogram signal and the cerebral oximetry signal and a comprehensive brain function connection feature of the target. The technical scheme of the embodiment of the application is aimed at the electroencephalogram signal and the cerebral oximetry signal collected by a multi-modal fNIRS-EEG neuroimaging acquisition technology, and the electroencephalogram signal and the cerebral oximetry signal are respectively subjected to feature extraction, and the biological feature obtained by analyzing the electroencephalogram feature and the cerebral oximetry feature has more complete information in time and space, thereby providing better diagnosis and treatment basis for medical staff.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a biometric analysis method, apparatus, electronic device, and storage medium. Background Technology

[0002] With social and economic development and the continuous improvement of medical technology, how to better analyze the biological characteristics of the brain has always been a key focus of human attention.

[0003] However, the biometric analysis methods currently used have missing information in terms of time and space, which makes it impossible for medical staff to provide a good basis for diagnosis and treatment. Summary of the Invention

[0004] One technical problem that this invention aims to solve is that the analyzed biometric features have missing information in terms of time and space.

[0005] According to one aspect of the present invention, a biometric analysis method is provided, which may include:

[0006] Acquire the target's electroencephalogram (EEG) signals and cerebral blood oxygenation signals;

[0007] Feature extraction is performed on the electroencephalogram (EEG) signal to obtain EEG features, and feature extraction is performed on the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features;

[0008] Based on EEG and cerebral blood oxygenation characteristics, biological features are obtained through analysis. These biological features include the neurovascular coupling relationship between EEG and cerebral blood oxygenation signals and the comprehensive brain functional connectivity characteristics of the target.

[0009] According to another aspect of the present invention, a biometric analysis device is provided, which may include:

[0010] The signal acquisition module is used to acquire the target's electroencephalogram (EEG) signals and cerebral blood oxygenation signals.

[0011] The feature extraction module is used to extract features from EEG signals to obtain EEG features, and to extract features from cerebral blood oxygenation signals to obtain cerebral blood oxygenation features.

[0012] The feature analysis module is used to analyze and obtain biological features based on EEG features and cerebral blood oxygenation features. The biological features include the neurovascular coupling relationship between EEG signals and cerebral blood oxygenation signals, as well as the comprehensive brain functional connectivity features of the target.

[0013] According to another aspect of the present invention, an electronic device is provided, which may include:

[0014] At least one processor; and

[0015] A memory that is communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, such that when the at least one processor executes the program, it implements the biometric analysis method provided in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided having computer instructions stored thereon for causing a processor to execute and implement the biometric analysis method provided in any embodiment of the present invention.

[0018] The technical solution of this invention involves acquiring the target's electroencephalogram (EEG) signal and cerebral blood oxygenation signal; extracting features from the EEG signal to obtain EEG features, and extracting features from the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features; and then analyzing these features to obtain biological characteristics, including the neurovascular coupling relationship between the EEG and cerebral blood oxygenation signals and the target's comprehensive brain functional connectivity characteristics. This technical solution, targeting the EEG and cerebral blood oxygenation signals acquired through multimodal fNIRS-EEG neuroimaging technology, extracts features from both, and then analyzes the resulting EEG and cerebral blood oxygenation features to obtain biological characteristics. These biological characteristics possess relatively complete information in both time and space, thus providing medical personnel with better diagnostic and treatment basis.

[0019] It should be understood that the description in this section is not intended to identify key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description.

[0020] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0021] The accompanying drawings, which form part of this specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0022] The invention will be more clearly understood with reference to the accompanying drawings and the following detailed description, wherein:

[0023] Figure 1 This is a schematic diagram of the acquisition channels for electroencephalogram (EEG) signals and cerebral blood oxygenation signals in a biometric analysis method provided by an embodiment of the present invention;

[0024] Figure 2 This is a flowchart of a biometric analysis method provided according to an embodiment of the present invention;

[0025] Figure 3This is a schematic diagram of the preprocessing process of electroencephalogram (EEG) signals and cerebral blood oxygenation signals in a biometric analysis method provided by an embodiment of the present invention;

[0026] Figure 4 This is a flowchart of an optional example of a biometric analysis method provided according to an embodiment of the present invention;

[0027] Figure 5 This is a flowchart of another biometric analysis method provided according to an embodiment of the present invention;

[0028] Figure 6 This is a flowchart of the neurovascular coupling relationship analysis process in another biometric analysis method provided by an embodiment of the present invention;

[0029] Figure 7 This is a flowchart of another biometric analysis method provided according to an embodiment of the present invention;

[0030] Figure 8 This is a flowchart of the comprehensive brain functional connectivity feature analysis process in another biometric analysis method provided by an embodiment of the present invention;

[0031] Figure 9 This is a flowchart of another biometric analysis method provided according to an embodiment of the present invention;

[0032] Figure 10 This is a schematic diagram of a brain atlas obtained by brain imaging reconstruction in another biometric analysis method provided by an embodiment of the present invention;

[0033] Figure 11 This is a flowchart of an optional example of another biometric analysis method provided according to an embodiment of the present invention;

[0034] Figure 12 This is a structural block diagram of a biometric analysis device provided according to an embodiment of the present invention;

[0035] Figure 13 This is a structural block diagram of an electronic device that implements the biometric analysis method of this invention. Detailed Implementation

[0036] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0037] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0038] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0039] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0040] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0041] Embodiments of this invention can be applied to computer systems / servers that can operate with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known computing systems, environments, and / or configurations suitable for use with computer systems / servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments that include any of the above systems, etc.

[0042] Computer systems / servers can be described in the general context of computer system executable instructions (such as program modules) executed by the computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are performed by remote processing devices linked through a communication network. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0043] Before introducing the embodiments of the present invention, the application scenarios of the embodiments of the present invention will be described by way of example. Electroencephalogram (EEG) technology, used to acquire brain signals from a target, has high temporal resolution but low spatial resolution; functional near-infrared spectroscopy (fNIRS) technology, used to acquire brain oxygenation signals from a target, has high spatial resolution but low temporal resolution. Specific comparative data are shown in Table 1. Therefore, when detecting physiological data of patients with mental illnesses, a single neuroimaging modality (i.e., EEG or fNIRS) may, due to its inherent technical limitations, result in a lack of spatiotemporal physiological data (i.e., information), ultimately failing to provide medical personnel with a good basis for diagnosis and treatment.

[0044] Table 1 Comparison of EEG and fNIRS in terms of temporal and spatial resolution.

[0045]

[0046]

[0047] To address the aforementioned problems, the inventors, based on a thorough study of existing technologies, proposed combining EEG technology with fNIRS technology to achieve multimodal analysis of the target. For this purpose, an exemplary configuration of the multimodal fNIRS-EEG acquisition channel is as follows: Figure 1 As shown. Specifically, Figure 1 This diagram illustrates the configuration of fNIRS-EEG multimodal acquisition channels based on the international 10-20 configuration system and with Fpz as the reference center. These channels are distributed across two functional regions of the target (prefrontal and temporal lobes), comprising 16 fNIRS detectors, 16 fNIRS light sources, and 29 EEG electrodes. The channels formed between the fNIRS detectors and fNIRS light sources constitute the cerebral oxygenation signal acquisition channels (36 in total), while the channels formed between two EEG electrodes are the EEG acquisition channels. Of course, acquisition channels can be configured using other methods; no specific limitations are specified here.

[0048] Figure 2 This is a flowchart of a biometric analysis method provided in an embodiment of the present invention. This embodiment is applicable to situations where EEG and fNIRS are combined to obtain complete spatiotemporal biometric information through multimodal analysis. The method can be executed by the biometric analysis device provided in this embodiment of the present invention. This device can be implemented in software and / or hardware and can be integrated into an electronic device, which can be various user terminals or servers.

[0049] See Figure 2 The method of this invention specifically includes the following steps:

[0050] S110. Acquire the target's electroencephalogram (EEG) signal and cerebral blood oxygenation signal.

[0051] This includes acquiring electroencephalogram (EEG) signals and cerebral oxygenation (COS) signals from the target using fNIRS technology. The system can analyze the actual EEG and COS signals (referred to as the two signals) of the target. For example, it can analyze the two signals acquired in real-time, or analyze signals that have already been acquired. It can also analyze simulated signals from the target, which can be derived from the actual acquired signals and can reflect the target's true condition to some extent, thus providing more analytical data. These are not specifically limited here.

[0052] In practical applications, optionally, the raw signals such as directly acquired EEG signals and cerebral blood oxygenation signals can be preprocessed. For example, see... Figure 3 For electroencephalogram (EEG) signals, Independent Component Correlation Algorithm (ICA) can be used to process them. Specifically, this involves using source signal statistics and other methods to meet prior conditions and reconstruct unobservable source signal components from the mixed signal. Eye movement noise can also be removed from the EEG signal. Other techniques can also be used for processing the EEG signal, without specific limitations. For cerebral oxygenation (COS) signals, at least one of the following operations can be used for preprocessing: 1) conversion from light intensity to density; 2) channel-to-channel analysis; 3) artifact detection and correction; 4) signal filtering, such as wavelet processing, median filtering, or deep learning filtering; 5) conversion from optical density to oxygen concentration; 6) block averaging; etc., without specific limitations.

[0053] S120. Extract features from the electroencephalogram (EEG) signal to obtain EEG features, and extract features from the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features.

[0054] The process involves feature extraction from electroencephalogram (EEG) signals to obtain EEG features. For example, specific feature extraction methods may include at least one of the following: short-time Fourier transform (STFT), wavelet filtering algorithm, support vector machine (SVM), linear discriminant analysis (LDA), deep neural networks (DNN), and convolutional neural network (CNN). In addition, feature extraction is performed on cerebral blood oxygenation signals to obtain cerebral blood oxygenation features. The feature extraction method used here may be the same as or different from the feature extraction method used for EEG signals; no specific limitation is made here.

[0055] S130. Based on EEG characteristics and cerebral blood oxygenation characteristics, biological characteristics are obtained through analysis. Among them, biological characteristics include the neurovascular coupling relationship of EEG signals and cerebral blood oxygenation signals and the comprehensive brain functional connectivity characteristics of the target.

[0056] Among these, electroencephalogram (EEG) features provide more complete temporal information, and cerebral oxygenation features provide more complete spatial information. Therefore, multimodal analysis can be performed based on these two features, resulting in biomarkers with relatively complete information in both time and space. It should be noted that the analyzed biomarkers can include the neurovascular coupling relationship between EEG signals and cerebral oxygenation signals, as well as the comprehensive brain functional connectivity features of the target. Of course, other types of biomarkers may also be included, without specific limitations. In conjunction with the application scenarios that may be involved in the embodiments of this invention, the physiological data of patients with mental illnesses can be detected based on the above scheme, thereby analyzing their biomarkers.

[0057] The technical solution of this invention involves acquiring the target's electroencephalogram (EEG) signal and cerebral blood oxygenation signal; extracting features from the EEG signal to obtain EEG features, and extracting features from the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features; and then analyzing these features to obtain biological characteristics, including the neurovascular coupling relationship between the EEG and cerebral blood oxygenation signals and the target's comprehensive brain functional connectivity characteristics. This technical solution, targeting the EEG and cerebral blood oxygenation signals acquired through multimodal fNIRS-EEG neuroimaging technology, extracts features from both, and then analyzes the resulting EEG and cerebral blood oxygenation features to obtain biological characteristics. These biological characteristics possess relatively complete information in both time and space, thus providing medical personnel with better diagnostic and treatment basis.

[0058] An optional technical solution involves feature extraction from electroencephalogram (EEG) signals to obtain EEG features. This can include: acquiring a pre-set time window and sliding the window across the EEG signal to obtain at least two EEG signals; extracting features from the at least two EEG signals to obtain cortical activity information of the target in the time domain, and using the cortical activity information as the EEG features. In conjunction with potential application scenarios of this invention, spatiotemporal functional magnetic resonance imaging (fMRI) constrained EEG source imaging (i.e., dynamic brain migration networks) can be used to perform source tracing analysis, where a sliding window method is used to analyze each EEG period. Specifically, the EEG time window is selected as t milliseconds (depending on the test duration), where the dynamic time window can be designed with 50% overlap, which helps to provide a suitable temporal resolution for evoked response potential studies. Thus, cortical activity information of each region of interest in the target in the time domain can be extracted by averaging voxel activity within the region. The above technical solution, by employing a sliding window scheme, achieves effective extraction of EEG features.

[0059] Another optional technical solution involves feature extraction from the cerebral oxygenation signal to obtain cerebral oxygenation features. This may include: statistically analyzing the channel signals acquired under the same acquisition channel using a generalized linear model to obtain a channel activation map; and obtaining a scalp activation map of the target based on the channel activation maps corresponding to each acquisition channel, using the scalp activation map as a cerebral oxygenation feature. Considering the application scenarios that may be involved in the embodiments of this invention, the classic generalized linear model (GLM) can be used to perform statistical analysis on the cerebral oxygenation signal of each target, and then obtain the channel activation map of the acquisition channel by comparing the encoding task with the baseline, which can also be called a significant activation map. Based on this, a cluster-based method can be used to correct multiple comparisons to limit the multiple comparison error rate to within 0.05. Acquisition channels with acquisition channel values ​​in fNIRS higher than the p_value threshold (p-correction > 0.05) can be considered as negligible acquisition channels with minimal impact, thus ensuring that only statistically significant acquisition channel values ​​can be used for subsequent source imaging operations. The scalp activation maps of fNIRS are typically projected and interpolated onto the cortical layer, thus visually representing the activation status of relevant brain regions. In short, firstly, the position of each acquisition channel (midpoint between the light source and detector) of fNIRS is marked on the scalp; further, according to the method described, the fNIRS scalp positions are projected onto the cortical layer; finally, the fNIRS activation values ​​of each acquisition channel are applied and interpolated onto the cortical source using the method described. In this embodiment of the invention, the channel activation map of a single acquisition channel can be divided into multiple sub-maps based on adjacent locations and cortical functional region clusters, allowing greater spatial flexibility when using fNIRS information as a constraint. More specifically, connected component labeling techniques (e.g., decomposition algorithms, such as Dulmage Mendelsohn) are used to group activation voxels into multiple subsets, and then each cortical activation block is divided into smaller blocks according to a predefined brain atlas, thereby ensuring that a single region does not cover multiple functional brain regions. The above technical solution, by employing GLM analysis of cerebral blood oxygenation signals, achieves effective extraction of cerebral blood oxygenation features.

[0060] Based on this, in order to better understand the various technical solutions mentioned above as a whole, specific examples will be provided below for illustrative purposes. For example, such as... Figure 4As shown, the acquired EEG and cerebral oxygenation signals are preprocessed, and the signals are updated based on the preprocessing results. Furthermore, a sliding window scheme is used to perform EEG source analysis to obtain EEG features, and GLM-based feature extraction is used to extract cerebral oxygenation features. Of course, other schemes can also be used for feature extraction; no specific limitation is made here. Finally, the neurovascular coupling relationship and comprehensive brain functional connectivity features can be obtained by combining the EEG and cerebral oxygenation features.

[0061] Before introducing the embodiments of the present invention, the application scenarios of the embodiments of the present invention will be described by way of example. The neurovascular coupling relationship can be understood as the relationship between local neural activity and subsequent changes in cerebral blood flow (CBF). The magnitude and spatial location of blood flow changes are closely related to changes in neural activity through a complex sequence of coordinated events involving neurons, glial cells, and vascular cells. Many vascular-based functional brain imaging techniques, such as fMRI and fNIRS, rely on this neurovascular coupling relationship to infer the patterns of neural activity changes.

[0062] Figure 5 This is a flowchart of another biometric analysis method provided in this embodiment of the invention. This embodiment is based on the above-mentioned technical solutions and optimized. In this embodiment, optionally, feature extraction of EEG signals to obtain EEG features may include: standardizing the potential signals of at least one band in the time dimension of the EEG signal in the amplitude dimension; orthogonalizing the standardized potential signals of each band to obtain orthogonalization results; convolving the orthogonalization results with a hemodynamic function, and using the regression value of the EEG signal obtained after convolution in a generalized linear model as the EEG feature. Alternatively, feature extraction of cerebral oxygenation signals to obtain cerebral oxygenation features may include: feature extraction of cerebral oxygenation signals acquired in a first channel to obtain a first oxygenation feature, and feature extraction of cerebral oxygenation signals acquired in a second channel to obtain a second oxygenation feature, wherein the channel length of the first channel is longer than that of the second channel; using the regression values ​​of the first oxygenation feature and the second oxygenation feature in the generalized linear model as cerebral oxygenation features. The explanations of terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0063] See Figure 5 The method in this embodiment may specifically include the following steps:

[0064] S210. Acquire the target's electroencephalogram (EEG) signal and cerebral blood oxygenation signal.

[0065] S220. For the potential signal of at least one band in the time dimension of the EEG signal, the potential signal of each band is standardized in the amplitude dimension.

[0066] At least one band can be at least one of the theta, alpha, and beta bands, but other bands are not specifically limited here. The signal of at least one band in the time dimension of the EEG signal is taken as the potential signal, and the potential signals of each band are standardized in the amplitude dimension.

[0067] S230. Orthogonalize the normalized potential signals of each band to obtain the orthogonalization result.

[0068] In this process, the potential signals of each band after standardization are orthogonalized. Considering the possible application scenarios involved in the embodiments of this invention, the Schmidt-Gram orthogonalization scheme can be adopted here. This scheme solves for the orthogonal basis (i.e., normalization) of each band in Euclidean space to obtain the orthogonalization result.

[0069] S240. Convolve the orthogonalization result with the hemodynamic function, and use the regression of the EEG signal obtained after convolution in the generalized linear model as the EEG feature.

[0070] In this process, the orthogonalization result is convolved with the hemodynamic response function (HRF) to obtain the regression value of the EEG signal in the GLM. Alternatively, this step can be understood as convolving the orthogonalization result with brain oxygenation dynamics to obtain a model of the expected change in hemoglobin concentration after EEG activity in a resting state, resulting in a regression value based on EEG in the GLM. This regression value is then used as the EEG feature.

[0071] S250. Perform feature extraction on the cerebral blood oxygenation signal acquired on the first channel to obtain the first blood oxygenation feature, and perform feature extraction on the cerebral blood oxygenation signal acquired on the second channel to obtain the second blood oxygenation feature, wherein the channel length of the first channel is longer than that of the second channel.

[0072] In this step, the first channel can be understood as a long channel, and the second channel as a short channel; these terms are relative. Feature extraction is performed on the cerebral blood oxygenation signals acquired from different acquisition channels to obtain their respective blood oxygenation features: the first blood oxygenation feature corresponding to the first channel and the second blood oxygenation feature corresponding to the second channel. In practical applications, optionally, the first stage of the first blood oxygenation feature can be standardized. Depending on the application scenarios that may be involved in this embodiment, standardization can be achieved using the Z-score.

[0073] S260. The regression values ​​of the first blood oxygenation feature in the generalized linear model and the regression values ​​of the second blood oxygenation feature in the generalized linear model are used as brain blood oxygenation features.

[0074] Among them, the regression values ​​of the first blood oxygenation feature in GLM and the regression values ​​of the second blood oxygenation feature in GLM are used as brain blood oxygenation features.

[0075] S270. Based on EEG characteristics and cerebral blood oxygenation characteristics, biological characteristics are obtained through analysis. Among them, biological characteristics include the neurovascular coupling relationship of EEG signals and cerebral blood oxygenation signals and the comprehensive brain functional connectivity characteristics of the target.

[0076] The technical solution of this invention standardizes the potential signals of each band in the time dimension of the EEG signal in the amplitude dimension, then orthogonalizes the standardized potential signals of each band, and convolves the orthogonalization result with the HRF. The regression value of the EEG signal obtained after convolution in the GLM is used as the EEG feature, thereby achieving effective extraction of EEG features; and / or, feature extraction is performed on the cerebral blood oxygenation signals acquired in the short channel and long channel respectively to obtain the corresponding first blood oxygenation feature and second blood oxygenation feature. The regression values ​​of the first blood oxygenation feature and the second blood oxygenation feature in the GLM are used as the cerebral blood oxygenation feature, thereby achieving effective extraction of cerebral blood oxygenation features.

[0077] Based on this, an optional technical solution, which analyzes and obtains biomarkers based on EEG and cerebral blood oxygenation characteristics, may include: fusing EEG and cerebral blood oxygenation characteristics to obtain a first fused feature; analyzing the first fused feature based on a generalized linear model (GLM), and using the obtained neurovascular coupling relationship as a biomarker. Specifically, to fully utilize the advantages of both EEG and cerebral blood oxygenation characteristics, these two can be fused to obtain the first fused feature, and then analyzed based on a GLM to obtain the neurovascular coupling relationship, thereby achieving effective analysis of this biomarker. In practical applications, the fusion of EEG and cerebral oxygenation features can be achieved in various ways, such as based on attention mechanisms or wavelet transform; or by using the Joint Mutual Information (JMI) criterion to optimize the combination of EEG and cerebral oxygenation features; or by analyzing brain information from preset perspectives through different decision paths and then using Independent Decision Path Fusion (IDPF); or by converting the combination of EEG and cerebral oxygenation features in the time series into a third-order tensor through tensor mapping; of course, other methods can also be used to achieve the fusion process, which will not be elaborated here.

[0078] To better understand the various technical solutions described in the embodiments of the present invention, specific examples are provided below for illustrative purposes. For example, see [link to example description]. Figure 6 To estimate the physiological (neuronal) indices of patients with mental illness, the neurovascular coupling relationship based on fNIRS convolution of signal features can be analyzed. Specifically, during EEG signal processing, the potential signals of the θ, α, and β bands for each patient with mental illness are extracted from single trials to multiple trials (i.e., the time dimension), and these signals are standardized in the amplitude dimension. Schmidt-Gram orthogonalization is performed by solving for the orthogonal basis (normalization) of each band in Euclidean space; this is then convolved with the HRF to obtain the regression value based on EEG in GLM. During cerebral oxygenation signal processing, the first stage of the first oxygenation feature in the long channel and the first stage of the second oxygenation feature in the short channel are z-score processed. Finally, their regression values ​​are combined with the EEG regression values ​​for GLM analysis, thereby obtaining the neurovascular coupling relationship between EEG signals and cerebral oxygenation signals.

[0079] Figure 7 This is a flowchart of another biometric analysis method provided in this embodiment of the invention. This embodiment is an optimization based on the above-mentioned technical solutions. In this embodiment, optionally, feature extraction is performed on the electroencephalogram (EEG) signal to obtain EEG features, including: analyzing the EEG signal to obtain a first brain functional connectivity feature, and using the first brain functional connectivity feature as the EEG feature; feature extraction is performed on the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features, including: analyzing the cerebral blood oxygenation signal to obtain a second brain functional connectivity feature, and using the second brain functional connectivity feature as the cerebral blood oxygenation feature; based on the EEG features and cerebral blood oxygenation features, biometric features are analyzed and obtained, which may include: comparing the EEG features and cerebral blood oxygenation features to obtain a comprehensive brain functional connectivity feature, and using the comprehensive brain functional connectivity feature as the biometric feature. The explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here.

[0080] See Figure 7 The method in this embodiment may specifically include the following steps:

[0081] S310. Acquire the target's electroencephalogram (EEG) signal and cerebral blood oxygenation signal.

[0082] S320. Analyze the EEG signals to obtain the first brain functional connectivity features, and use the first brain functional connectivity features as EEG features.

[0083] S330. Analyze the cerebral blood oxygenation signal to obtain the second brain functional connectivity feature, and use the second brain functional connectivity feature as the cerebral blood oxygenation feature.

[0084] S340. Compare the EEG characteristics and cerebral blood oxygenation characteristics to obtain the comprehensive brain functional connectivity characteristics of the target, and use the comprehensive brain functional connectivity characteristics as biological characteristics.

[0085] Specifically, EEG signals and cerebral blood oxygenation signals can be analyzed separately to obtain their respective brain functional connectivity features, such as the first brain functional connectivity feature corresponding to the EEG signal and the second brain functional connectivity feature corresponding to the cerebral blood oxygenation signal. Furthermore, these two brain functional connectivity features are compared to obtain the comprehensive brain functional connectivity features of the target. In practical applications, the analysis process for the first and second brain functional connectivity features can optionally be the same or different; no specific limitations are imposed here.

[0086] The technical solution of this invention analyzes electroencephalogram (EEG) signals and cerebral blood oxygenation signals, and then compares the first brain functional connectivity features corresponding to the EEG signals and the second brain functional connectivity features corresponding to the cerebral blood oxygenation signals to effectively obtain comprehensive brain functional connectivity features.

[0087] Based on this, an optional technical solution involves analyzing cerebral oxygenation signals to obtain second brain functional connectivity features. This can include: calculating the Pearson correlation coefficient between the reference signal located on the reference channel and the remaining signals located on the other channels in each acquisition channel, based on the reference signal and the remaining signals; and obtaining the second brain functional connectivity features based on the Pearson correlation coefficient. In practical applications, optionally, assuming the reference channel is the i-th acquisition channel and the remaining channels are the j-th acquisition channels, the Pearson correlation coefficient r between these two acquisition channels can be expressed by the following formula:

[0088]

[0089] Where ρ is the correlation coefficient of the Pearson function, and y i Let y represent the n-point time series of the i-th acquisition channel. j Let represent the n-point time series of the j-th channel, with the functional connectivity quantized as r for the channel configuration. The above technical solution effectively obtains the second brain functional connectivity features through the calculated Pearson correlation coefficient.

[0090] Another optional technical solution, based on the Pearson correlation coefficient, to obtain the second brain functional connectivity feature may include: transforming each of the at least two calculated Pearson correlation coefficients according to a preset transformation strategy to obtain a transformed brain functional connectivity map, wherein the preset transformation strategy is used to achieve nonlinear correction; averaging the transformed brain functional connectivity maps to obtain an average brain functional connectivity map; and performing a reverse transformation on the average brain functional connectivity map based on the inverse transformation strategy corresponding to the preset transformation strategy to obtain the second brain functional connectivity feature. In practical applications, optionally, the preset transformation strategy can be a pre-set strategy for transforming the Pearson correlation coefficient to achieve nonlinear correction, such as the Fisher transformation; then the inverse transformation strategy can be the inverse Fisher transformation. The Fisher transformation is expressed by the following formula:

[0091]

[0092] Here, z represents the z-value obtained after Fisher transform, and a transformed brain functional connectivity map can be obtained based on the z-value. The above technical solution can accurately obtain the second brain functional connectivity features.

[0093] To better understand the various technical solutions described in the embodiments of the present invention, specific examples are provided below for illustrative purposes. For example,... Figure 8 As shown, brain functional connectivity analysis can be understood as follows: A sampling channel from a functional region of interest is selected as the basic seed (i.e., the baseline channel) to calculate the correlation coefficient (r) between the basic seed and all other channels (i.e., the remaining channels). At least two basic seeds are used to calculate r for each region of interest in each cortical area. Specifically, firstly, trials representing time-series hemodynamic response signals during the detection phase are selected from the overall trial to represent task-related responses. Then, r between the i-th and j-th sampling channels is calculated using the formula mentioned above. Each new calculation of r can be called a run. Then, the Fisher transform is used to convert the r values ​​to z values ​​to obtain a set of functional connectivity maps (i.e., transformed brain functional connectivity maps), and the z values ​​during the runs of each sampling channel are averaged to obtain the average brain functional connectivity map. Finally, the brain functional connectivity presented in the r map (i.e., the second brain functional connectivity feature) is obtained through the inverse Fisher transform. Based on this, to further analyze the brain functional connectivity maps corresponding to the second brain functional connectivity feature, statistical analysis can be used to compare significant differences in brain functional connectivity between frontal and temporal cortical regions.

[0094] Before introducing the embodiments of the present invention, the application scenarios of the embodiments of the present invention will be described exemplarily. From the perspective of locating the target region within a target, EEG currently has difficulty locating the target region, while fNIRS has a much higher localization performance than EEG. By analyzing the target's cerebral blood oxygenation signal, damaged or abnormal areas under the cerebral cortex can be reconstructed through algorithms and can be identified relatively well by the naked eye. However, it still lacks the accuracy of fMRI. Therefore, in order to improve the accuracy of target region localization, the inventors have proposed the following technical solution.

[0095] Figure 9 This is a flowchart of another biometric analysis method provided in this embodiment of the invention. This embodiment is an optimization based on the above-described technical solutions. Optionally, in this embodiment, the above-described biometric analysis method may further include: fusing electroencephalogram (EEG) features and cerebral blood oxygenation features to obtain a second fused feature; and performing brain imaging reconstruction based on the second fused feature to obtain a brain atlas. The explanations of terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0096] See Figure 9 The method in this embodiment may specifically include the following steps:

[0097] S410. Acquire the target's electroencephalogram (EEG) signal and cerebral blood oxygenation signal.

[0098] S420. Extract features from the electroencephalogram (EEG) signal to obtain EEG features, and extract features from the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features.

[0099] S430. Based on EEG characteristics and cerebral blood oxygenation characteristics, biological characteristics are obtained through analysis. Among them, biological characteristics include the neurovascular coupling relationship of EEG signals and cerebral blood oxygenation signals and the comprehensive brain functional connectivity characteristics of the target.

[0100] S440. The EEG characteristics and cerebral blood oxygenation characteristics are fused to obtain the second fused characteristic.

[0101] Among them, the second fusion feature has relatively complete information in both time and space.

[0102] S450. Brain imaging reconstruction is performed based on the second fusion feature to obtain a brain atlas.

[0103] The brain atlas obtained after brain imaging reconstruction based on the second fusion feature can be understood as a brain atlas generated under multimodal data fusion. Such a brain atlas is more helpful for automatically or manually locating target regions. For example, see Figure 10The brain atlas shown typically contains multiple functional areas within the target area. Target areas for different diseases may be located in the same or different functional areas. In the diagram, A and B represent two different diseases. Taking A as an example, its two straight lines point to different functional areas, which are darker in color. The darker the color, the greater the likelihood that the functional area is the target area, thus improving the accuracy of target area localization. The located target area can be used as a physical stimulation target, such as transcranial alternating-current stimulation (tACS), transcranial direct current stimulation (tDCS), and transcranial magnetic stimulation (tMS).

[0104] The technical solution of this invention involves fusing EEG features and cerebral blood oxygenation features to obtain a second fused feature, and then performing brain imaging reconstruction based on the second fused feature to obtain a brain atlas. This processing method can capture more complete information in time and space, thereby improving the localization accuracy of the target area.

[0105] To better understand the various technical solutions described above, specific examples are provided below for illustration. For examples, see [link to example]. Figure 11 Specifically:

[0106] Step 1: Collect EEG and cerebral oxygenation signals from the target patient with mental illness;

[0107] Step 2: Preprocess and filter the EEG signal and cerebral blood oxygenation signal respectively;

[0108] Step 3: Extract features from the EEG signal and cerebral blood oxygenation signal respectively, such as short-time Fourier transform, wavelet algorithm or deep learning algorithm, etc.

[0109] Step 4: Fuse the extracted EEG features and cerebral blood oxygenation features so that they can be integrated into data on the same dimension;

[0110] Step 5: Multidimensional data analysis: 1) Neurovascular coupling analysis; 2) Brain atlas analysis; 3) Brain functional connectivity analysis;

[0111] Step 6: The results of multi-dimensional data analysis can provide medical staff with a basis for diagnosis and treatment.

[0112] The above technical solution integrates and couples fNIRS and EEG data in multiple dimensions to capture the biological characteristics of patients with mental illness to the greatest extent. In addition, based on the spatial localization of fNIRS, the brain imaging reconstruction algorithm under multimodal data can accurately locate the target area of ​​patients with mental illness.

[0113] Figure 12 This is a structural block diagram of a biometric analysis device provided in an embodiment of the present invention. This device is used to execute the biometric analysis method provided in any of the above embodiments. This device and the biometric analysis methods of the above embodiments belong to the same inventive concept. Details not described in detail in the embodiments of the biometric analysis device can be found in the embodiments of the above biometric analysis methods. See also... Figure 12 The device may specifically include: a signal acquisition module 510, a feature extraction module 520, and a feature analysis module 530. Among them,

[0114] The signal acquisition module 510 is used to acquire the target's electroencephalogram (EEG) signal and cerebral blood oxygenation signal;

[0115] The feature extraction module 520 is used to extract features from electroencephalogram (EEG) signals to obtain EEG features, and to extract features from cerebral blood oxygenation signals to obtain cerebral blood oxygenation features.

[0116] The feature analysis module 530 is used to analyze and obtain biological features based on EEG features and cerebral blood oxygenation features. The biological features include the neurovascular coupling relationship of EEG signals and cerebral blood oxygenation signals, as well as the comprehensive brain functional connectivity features of the target.

[0117] Optionally, the feature extraction module 520 may include:

[0118] The potential signal standardization unit is used to standardize the potential signals of each band in the amplitude dimension for at least one band in the time dimension of the electroencephalogram (EEG) signal.

[0119] The potential signal orthogonalization unit is used to orthogonalize the normalized potential signals of each band to obtain the orthogonalization result;

[0120] The first unit for obtaining EEG features is used to convolve the orthogonalization result with the hemodynamic function, and the regression value of the EEG signal obtained after convolution in the generalized linear model is used as the EEG feature.

[0121] Optionally, the feature extraction module 520 may include:

[0122] The blood oxygen feature extraction unit is used to extract features from the brain blood oxygen signal acquired in the first channel to obtain the first blood oxygen feature, and to extract features from the brain blood oxygen signal acquired in the second channel to obtain the second blood oxygen feature, wherein the channel length of the first channel is longer than that of the second channel.

[0123] The first unit for obtaining brain blood oxygenation features is used to take the regression values ​​of the first blood oxygenation feature in the generalized linear model and the regression values ​​of the second blood oxygenation feature in the generalized linear model as brain blood oxygenation features.

[0124] Based on this, the optional feature analysis module 530 may include:

[0125] The first fusion feature obtaining unit is used to fuse EEG features and cerebral blood oxygenation features to obtain the first fusion feature;

[0126] The neurovascular coupling analysis unit is used to analyze the first fusion feature based on a generalized linear model, and the obtained neurovascular coupling relationship is used as a biological feature.

[0127] Optionally, the feature extraction module 520 may include:

[0128] The second EEG feature acquisition unit is used to analyze the EEG signal to obtain the first brain functional connectivity feature, and uses the first brain functional connectivity feature as the EEG feature.

[0129] The second brain blood oxygenation feature acquisition unit is used to analyze brain blood oxygenation signals, obtain second brain functional connectivity features, and use the second brain functional connectivity features as brain blood oxygenation features.

[0130] Feature analysis module 530 may include:

[0131] The integrated brain functional connectivity feature analysis unit is used to compare EEG features and cerebral blood oxygenation features to obtain integrated brain functional connectivity features, and uses integrated brain functional connectivity features as biological characteristics.

[0132] Based on this, the optional second unit for obtaining cerebral blood oxygenation characteristics may include:

[0133] The Pearson correlation coefficient calculation subunit is used to calculate the Pearson correlation coefficient between the reference signal located on the reference channel and the other signals located on the other channels in each acquisition channel, based on the reference signal and the other signals.

[0134] The sub-units for obtaining second brain functional connectivity features are used to obtain second brain functional connectivity features based on the Pearson correlation coefficient.

[0135] Based on this, optional sub-units for obtaining second brain functional connectivity features are specifically used for:

[0136] For each of the at least two calculated Pearson correlation coefficients, the Pearson correlation coefficients are transformed based on a preset transformation strategy to obtain a transformed brain functional connectivity map, wherein the preset transformation strategy is used to achieve nonlinear correction;

[0137] The average brain functional connectivity maps of each transformation are averaged to obtain the average brain functional connectivity map.

[0138] Based on the inverse transformation strategy corresponding to the preset transformation strategy, the average brain functional connectivity map is transformed inversely to obtain the second brain functional connectivity features.

[0139] Optionally, the above-mentioned biometric analysis device may further include:

[0140] The second fusion feature acquisition module is used to fuse EEG features and cerebral blood oxygenation features to obtain the second fusion feature;

[0141] The brain atlas reconstruction module is used to reconstruct brain images based on the second fusion feature to obtain a brain atlas.

[0142] Optionally, the feature extraction module 520 may include:

[0143] The brain electronic signal acquisition unit is used to acquire a pre-set time window and slide on the brain electronic signal based on the time window to obtain at least two brain electronic signals.

[0144] The cortical activity information acquisition unit is used to extract features from at least two brain electrical signals to obtain the cortical activity information of the target in the time domain, and to use the cortical activity information as EEG features.

[0145] Optionally, the feature extraction module 520 may include:

[0146] The channel activation map is obtained by statistically analyzing the channel signals acquired under the same acquisition channel in the brain blood oxygenation signal based on a generalized linear model to obtain the channel activation map.

[0147] The scalp activation map acquisition unit is used to obtain the target's scalp activation map based on the activation maps corresponding to each acquisition channel, and to use the scalp activation map as a feature of cerebral blood oxygenation.

[0148] The biometric analysis device provided in this invention acquires the target's electroencephalogram (EEG) signals and cerebral oxygenation (COS) signals through a signal acquisition module; it extracts features from the EEG signals to obtain EEG features, and extracts features from the COS signals to obtain COS features; then, based on the EEG and COS features, the feature analysis module analyzes and obtains biometric features, which include the neurovascular coupling relationship between the EEG and COS signals and the target's comprehensive brain functional connectivity features. This device, for EEG and COS signals acquired through multimodal fNIRS-EEG neuroimaging technology, extracts features from both, and analyzes the resulting biometric features, providing relatively complete information in both time and space, thus offering better diagnostic and treatment basis for medical personnel.

[0149] The biometric analysis device provided in the embodiments of the present invention can execute the biometric analysis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0150] It is worth noting that in the embodiments of the above-mentioned biometric analysis device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0151] Figure 13 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0152] like Figure 13As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0153] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0154] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as biometric analysis methods.

[0155] In some embodiments, the biometric analysis method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the biometric analysis method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the biometric analysis method by any other suitable means (e.g., by means of firmware).

[0156] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0157] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0158] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0159] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0160] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0161] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0162] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0163] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system embodiments, since they largely correspond to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0164] The methods and systems of the present invention may be implemented in many ways. For example, they may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order of steps for the methods is for illustrative purposes only, and the steps of the methods of the present invention are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the present invention may also be implemented as a program recorded on a recording medium, the program comprising machine-readable instructions for implementing the methods according to the present invention. Thus, the present invention also covers recording media storing programs for performing the methods according to the present invention.

[0165] The description of this invention is given for illustrative and descriptive purposes only and is not intended to be exhaustive or to limit the invention to the forms disclosed. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to better illustrate the principles and practical application of the invention and to enable those skilled in the art to understand the invention and to design various embodiments with various modifications suitable for a particular purpose.

Claims

1. A biometric analysis method, characterized in that, include: Acquire the target's electroencephalogram (EEG) signals and cerebral blood oxygenation signals; Feature extraction is performed on the electroencephalogram (EEG) signal to obtain EEG features, and feature extraction is performed on the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features; Based on the electroencephalogram (EEG) characteristics and the brain blood oxygenation characteristics, biometric features are obtained. These biometric features include the neurovascular coupling relationship between the EEG signals and the brain blood oxygenation signals, as well as the comprehensive brain functional connectivity features of the target. The comprehensive brain functional connectivity features are obtained by comparing the EEG characteristics and the brain blood oxygenation characteristics. The step of extracting features from the electroencephalogram (EEG) signal to obtain EEG features includes: The EEG signals are analyzed to obtain the first brain functional connectivity feature, and the first brain functional connectivity feature is used as the EEG feature. The step of extracting features from the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features includes: The brain blood oxygenation signal is analyzed to obtain the second brain functional connectivity feature, and the second brain functional connectivity feature is used as the brain blood oxygenation feature. The biological characteristics obtained by analyzing the electroencephalogram (EEG) features and the cerebral blood oxygenation features include: The EEG characteristics and the cerebral blood oxygenation characteristics are compared to obtain the comprehensive brain functional connectivity characteristics, which are then used as biological characteristics.

2. The method according to claim 1, characterized in that, The step of extracting features from the electroencephalogram (EEG) signal to obtain EEG features includes: For the potential signal of at least one band in the time dimension of the electroencephalogram (EEG) signal, the potential signal of each band is standardized in the amplitude dimension. The normalized potential signals of each band are orthogonalized to obtain the orthogonalization result; The orthogonalization result is convolved with the hemodynamic function, and the regression value of the EEG signal obtained after convolution in the generalized linear model is used as the EEG feature.

3. The method according to claim 1, characterized in that, The step of extracting features from the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features includes: The brain blood oxygenation signal acquired on the first channel is subjected to feature extraction to obtain a first blood oxygenation feature, and the brain blood oxygenation signal acquired on the second channel is subjected to feature extraction to obtain a second blood oxygenation feature, wherein the channel length of the first channel is longer than that of the second channel. The regression values ​​of the first blood oxygenation feature in the generalized linear model and the regression values ​​of the second blood oxygenation feature in the generalized linear model are used as brain blood oxygenation features.

4. The method according to claim 2 or 3, characterized in that, The biological characteristics obtained by analyzing the electroencephalogram (EEG) features and the cerebral blood oxygenation features include: The electroencephalogram (EEG) features and the cerebral blood oxygenation features are fused to obtain the first fused feature; The first fusion feature is analyzed based on the generalized linear model, and the obtained neurovascular coupling relationship is used as a biological feature.

5. The method according to claim 1, characterized in that, The analysis of the cerebral blood oxygenation signal to obtain second brain functional connectivity features includes: For the reference signal located on the reference channel and the other signals located on the other channels in each acquisition channel other than the reference channel in the brain blood oxygenation signal, the Pearson correlation coefficient between the reference channel and the other channels is calculated based on the reference signal and the other signals. Based on the Pearson correlation coefficient, the second brain functional connectivity features are obtained.

6. The method according to claim 5, characterized in that, The second brain functional connectivity feature obtained based on the Pearson correlation coefficient includes: For each of the at least two Pearson correlation coefficients obtained from calculation, the Pearson correlation coefficients are transformed based on a preset transformation strategy to obtain a transformed brain functional connectivity map, wherein the preset transformation strategy is used to achieve nonlinear correction; The average brain functional connectivity maps of each transformation are averaged to obtain the average brain functional connectivity map. Based on the inverse transformation strategy corresponding to the preset transformation strategy, the average brain functional connectivity map is inversely transformed to obtain the second brain functional connectivity feature.

7. The method according to claim 1, characterized in that, Also includes: The electroencephalogram (EEG) features and the cerebral blood oxygenation features are fused to obtain a second fused feature; Brain imaging reconstruction is performed based on the second fusion feature to obtain a brain atlas.

8. The method according to claim 1, characterized in that, The step of extracting features from the electroencephalogram (EEG) signal to obtain EEG features includes: A pre-set time window is obtained, and the EEG signal is slid across the EEG signal based on the time window to obtain at least two EEG signals; Feature extraction is performed on the at least two brain electrical signals to obtain the cortical activity information of the target in the time domain, and the cortical activity information is used as the brain electrical feature.

9. The method according to claim 1, characterized in that, The step of extracting features from the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features includes: For the channel signals acquired under the same acquisition channel in the brain blood oxygenation signal, statistical analysis is performed on the channel signals based on a generalized linear model to obtain a channel activation map; Based on the channel activation maps corresponding to each of the acquisition channels, the scalp activation map of the target is obtained, and the scalp activation map is used as a feature of cerebral blood oxygenation.

10. A biometric analysis device, characterized in that, include: The signal acquisition module is used to acquire the target's electroencephalogram (EEG) signals and cerebral blood oxygenation signals. The feature extraction module is used to extract features from the electroencephalogram (EEG) signal to obtain EEG features, and to extract features from the cerebral blood oxygenation signal to obtain cerebral blood oxygenation features. The feature analysis module is used to analyze and obtain biological features based on the electroencephalogram (EEG) features and the cerebral blood oxygenation features. The biological features include the neurovascular coupling relationship between the EEG signals and the cerebral blood oxygenation signals, as well as the comprehensive brain functional connectivity features of the target. The comprehensive brain functional connectivity features are obtained by comparing the EEG features and the cerebral blood oxygenation features. The feature extraction module includes: The second EEG feature acquisition unit is used to analyze the EEG signal to obtain the first brain functional connectivity feature, and uses the first brain functional connectivity feature as the EEG feature. The second brain blood oxygenation feature acquisition unit is used to analyze brain blood oxygenation signals, obtain second brain functional connectivity features, and use the second brain functional connectivity features as brain blood oxygenation features. The feature analysis module includes: The integrated brain functional connectivity feature analysis unit is used to compare EEG features and cerebral blood oxygenation features to obtain integrated brain functional connectivity features, and uses integrated brain functional connectivity features as biological characteristics.

11. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to cause the at least one processor to perform the biometric analysis method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the biometric analysis method as described in any one of claims 1-9.

Images