Lead selection method and device based on traceability and individual differences

Abstract

The application discloses a lead screening method and device based on traceability and individual differences. The method comprises the following steps: acquiring electroencephalogram signals of a target individual collected by each lead point of a multi-lead device; decomposing the electroencephalogram signals into a plurality of independent electroencephalogram signals according to the number of lead points of the multi-lead device; determining effective brain source signals in each independent electroencephalogram signal, and performing spatial arrangement processing on each effective brain source signal according to a preset brain cortex space traceability strategy to obtain spatial position information of the effective brain source signals; calculating electroencephalogram conduction distances of each effective brain source signal to each lead point, and establishing an electroencephalogram conduction distance matrix corresponding to each effective brain source signal based on the electroencephalogram conduction distances of each effective brain source signal to each lead point; and selecting a target lead point from each lead point based on each electroencephalogram conduction distance matrix of the target individual. The method can improve the screening accuracy of the lead points of a single individual.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a lead screening method and device based on traceability and individual differences. BACKGROUND

[0002] The brain-computer interface (BCI) technology based on electroencephalogram (EEG) is a new technology that outputs instructions contained in EEG signals to external actuator devices directly by acquiring EEG signals. The brain-computer interface technology is usually realized through a brain-computer interface device. The EEG signals of each individual are acquired through each lead point in the brain-computer interface device according to a unified preset EEG conduction distance matrix, and the EEG signals are output to external actuator devices. However, the lead points of the traditional brain-computer interface device are too many, and the acquired EEG signals are relatively dispersed, resulting in low accuracy of EEG signal acquisition. Therefore, it has always been a research focus to screen the lead points of the brain-computer interface device to improve the accuracy of EEG signal acquisition.

[0003] The traditional lead screening method is to establish a unified EEG conduction distance matrix by combining the brain skull characteristics of a general population, and to screen each lead point in the brain-computer interface device according to the EEG conduction distance matrix. However, this method does not take into account the differences in the nervous system of individual individuals, resulting in low accuracy of screening the lead points corresponding to individual individuals. SUMMARY

[0004] Therefore, it is necessary to provide a lead screening method and device based on traceability and individual differences, a computer device, a computer readable storage medium and a computer program product in order to solve the above technical problems.

[0005] In a first aspect, the present application provides a lead screening method based on traceability and individual differences.

[0006] The method comprises:

[0007] acquiring EEG signals of a target individual collected by each lead point in a multi-lead device;

[0008] decomposing the EEG signals into a plurality of independent EEG signals according to the number of lead points of the multi-lead device;

[0009] determining effective brain source signals in each of the independent EEG signals, and performing spatial arrangement processing on each of the effective brain source signals according to a preset brain cortex space traceability strategy to obtain spatial position information of the effective brain source signals;

[0010] According to the spatial position information of each of the lead points, the spatial position information of each of the effective brain source signals, and a preset electrical conductivity matrix of each tissue of the brain, the electrical conduction distance of each of the effective brain source signals to each of the lead points is calculated, and a brain electrical conduction distance matrix corresponding to each of the effective brain source signals is established based on the electrical conduction distance of each of the effective brain source signals to each of the lead points.

[0011] Based on each of the brain electrical conduction distance matrices of the target individual, each of the lead points is screened to obtain a plurality of target lead points for the target individual.

[0012] Optionally, the acquiring of the brain electrical signals of the target individual collected by each of the lead points of the multi-lead device comprises:

[0013] The high-dimensional brain electrical signals of the target individual collected by the multi-lead device are acquired.

[0014] The high-dimensional brain electrical signals are processed by dimension reduction to obtain low-dimensional brain electrical signals.

[0015] The low-dimensional brain electrical signals are processed by filtering based on preset filtering parameters to obtain the brain electrical signals of the target individual.

[0016] Optionally, the decomposing of the brain electrical signals into a plurality of independent brain electrical signals according to the number of the lead points of the multi-lead device comprises:

[0017] The brain electrical signals are processed by noise removal to obtain noise-removed brain electrical signals.

[0018] Based on an independent component analysis strategy, the brain electrical signals are decomposed into independent brain electrical signals with the same number as the lead points.

[0019] Optionally, the determining of the effective brain source signals in each of the independent brain electrical signals and the spatial arrangement processing of each of the effective brain source signals according to a preset brain cortex spatial source tracing strategy to obtain the spatial position information of the effective brain source signals comprises:

[0020] In each of the independent brain electrical signals, an effective brain source signal containing brain electrical neural data is selected.

[0021] A skull cavity conductor model of the target individual is acquired; the skull cavity conductor model comprises geometric position information of a three-dimensional structure of brain electrical neural data in the skull cavity and electrode position information of each of the lead points.

[0022] For each effective brain source signal, electrode position information of the effective brain source signal is calculated according to the electrode position information of the electroencephalogram nerve and the effective brain source signal, and spatial position information of the effective brain source signal is determined based on the geometric position information of the three-dimensional structure of the intracranial electroencephalogram nerve and the electrode position information of the effective brain source signal.

[0023] Optionally, the brain electric conduction distance of each effective brain source signal to each lead point is calculated according to the spatial position information of each lead point, the spatial position information of each effective brain source signal, and the preset electrical conductivity matrix of each tissue of the brain, and a brain electric conduction distance matrix corresponding to each effective brain source signal is established based on the brain electric conduction distance of all effective brain source signals to each lead point, including:

[0024] For each effective brain source signal, a spatial distance of the effective brain source signal to each lead point is determined according to the spatial position information of the effective brain source signal and the spatial position information of each lead point.

[0025] For each lead point, a brain electric conduction distance of the effective brain source signal to the lead point is calculated according to the spatial position information of the effective brain source signal, the spatial position information of the lead point, the spatial distance of the effective brain source signal to the lead point, and the preset electrical conductivity matrix of each tissue of the brain.

[0026] A brain electric conduction distance matrix of the effective brain source signal is established based on the brain electric conduction distance of the effective brain source signal to each lead point.

[0027] Optionally, each lead point is screened based on each brain electric conduction distance matrix of the target individual to obtain a plurality of target lead points for the target individual, including:

[0028] For each effective brain source signal, a lead point with the closest brain electric conduction distance to the effective brain source signal is selected as a target lead point from each lead point in the brain electric conduction distance matrix corresponding to the effective brain source signal.

[0029] Optionally, after the lead point with the closest brain electric conduction distance to the effective brain source signal is selected as the target lead point, the method further includes:

[0030] In a case where the number of target lead points does not satisfy a preset lead point number, a lead point satisfying preset lead screening information is selected as a target lead point from each lead point except the target lead points.

[0031] Optionally, the method further includes:

[0032] obtain the electroencephalogram signals corresponding to each of the target electrode points, and take the electroencephalogram signals corresponding to all the target electrode points as the target electroencephalogram signals of the target individual; or

[0033] For each effective brain source signal, the effective brain source signal is inversely transformed by the electroencephalogram conduction distance matrix corresponding to the effective brain source signal, to obtain the electroencephalogram signal corresponding to each of the target electrode points.

[0034] In a second aspect, the present application further provides a lead screening device based on traceability and individual differences. The device comprises:

[0035] An acquisition module is configured to acquire electroencephalogram signals of a target individual collected by each electrode point of a multi-electrode device;

[0036] A decomposition module is configured to decompose the electroencephalogram signals into a plurality of independent electroencephalogram signals according to the number of electrode points of the multi-electrode device;

[0037] A traceability module is configured to determine effective brain source signals from the independent electroencephalogram signals, and perform spatial arrangement processing on each of the effective brain source signals according to a preset spatial traceability strategy of the cerebral cortex, to obtain spatial position information of the effective brain source signals;

[0038] An establishment module is configured to calculate electroencephalogram conduction distances of each of the effective brain source signals to each electrode point according to the spatial position information of each of the electrode points, the spatial position information of each of the effective brain source signals, and a preset electrical conductivity matrix of each tissue of the brain, and establish an electroencephalogram conduction distance matrix corresponding to each of the effective brain source signals based on the electroencephalogram conduction distances of each of the effective brain source signals to each of the electrode points;

[0039] A screening module is configured to screen each of the electrode points based on each of the electroencephalogram conduction distance matrices of the target individual, to obtain a plurality of target electrode points for the target individual.

[0040] Optionally, the acquisition module is specifically configured to:

[0041] Acquire high-dimensional electroencephalogram signals of a target individual collected by a multi-electrode device;

[0042] Perform dimension reduction processing on the high-dimensional electroencephalogram signals to obtain low-dimensional electroencephalogram signals;

[0043] Perform filtering processing on the low-dimensional electroencephalogram signals by using preset filtering parameters, to obtain the electroencephalogram signals of the target individual.

[0044] Optionally, the decomposition module is specifically configured to:

[0045] Perform noise removal processing on the electroencephalogram signals to obtain noise-removed electroencephalogram signals;

[0046] Based on an independent component analysis strategy, the electroencephalogram signal is decomposed into independent electroencephalogram signals same in number as the lead points.

[0047] Optionally, the tracing module is specifically configured to:

[0048] In each of the independent electroencephalogram signals, an effective brain source signal containing electroencephalogram neural data is selected;

[0049] An intracranial conductor model of the target individual is acquired; the intracranial conductor model includes geometric position information of a three-dimensional structure of the intracranial electroencephalogram neural data and electrode position information of each of the lead points;

[0050] For each effective brain source signal, electrode position information of the effective brain source signal is calculated according to the electrode position information of the electroencephalogram neural data and the effective brain source signal, and spatial position information of the effective brain source signal is determined based on the geometric position information of the three-dimensional structure of the intracranial electroencephalogram neural data and the electrode position information of the effective brain source signal.

[0051] Optionally, the establishing module is specifically configured to:

[0052] For each effective brain source signal, spatial distance of the effective brain source signal to each lead point is determined according to the spatial position information of the effective brain source signal and the spatial position information of each of the lead points;

[0053] For each lead point, electroencephalogram conduction distance of the effective brain source signal to the lead point is calculated according to the spatial position information of the effective brain source signal, the spatial position information of the lead point, the spatial distance of the effective brain source signal to the lead point, and the preset electrical conductivity matrix of each tissue of the brain.

[0054] Based on the electroencephalogram conduction distance of the effective brain source signal to each lead point, an electroencephalogram conduction distance matrix of the effective brain source signal is established.

[0055] Optionally, the screening module is specifically configured to:

[0056] For each effective brain source signal, a lead point closest to the effective brain source signal in the electroencephalogram conduction distance matrix corresponding to the effective brain source signal is selected as a target lead point.

[0057] Optionally, the device further includes:

[0058] A re-screening module is configured to, in a case where the number of target lead points does not satisfy the preset number of lead points, select a lead point satisfying preset lead screening information as a target lead point from each of the lead points except the target lead points.

[0059] Optionally, the device further comprises:

[0060] a first electroencephalogram signal acquisition module, configured to acquire electroencephalogram signals corresponding to each of the target electrode points, and take the electroencephalogram signals corresponding to all the target electrode points as target electroencephalogram signals of the target individual; or

[0061] a second electroencephalogram signal acquisition module, configured to, for each effective brain source signal, perform inverse transform processing on the effective brain source signal through an electroencephalogram conduction distance matrix corresponding to the effective brain source signal, to obtain electroencephalogram signals corresponding to each of the target electrode points.

[0062] In a third aspect, the present application provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method of any one of the first aspect when executing the computer program.

[0063] In a fourth aspect, the present application provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program implements the steps of the method of any one of the first aspect when executed by a processor.

[0064] In a fifth aspect, the present application provides a computer program product. The computer program product comprises a computer program, and the computer program implements the steps of the method of any one of the first aspect when executed by a processor.

[0065] The lead screening method and device based on the traceability and individual differences, by acquiring the EEG signals of a target individual collected by each lead point of a multi-lead device, decomposes the EEG signals into multiple independent EEG signals according to the number of lead points of the multi-lead device, determines effective brain source signals in each independent EEG signal, and performs spatial arrangement processing on each effective brain source signal according to a preset brain cortex space traceability strategy to obtain spatial position information of the effective brain source signals, calculates the EEG conduction distance of each effective brain source signal to each lead point according to the spatial position information of each lead point, the spatial position information of each effective brain source signal, and a preset electrical conductivity matrix of each brain tissue, and establishes an EEG conduction distance matrix corresponding to each effective brain source signal based on the EEG conduction distance of each effective brain source signal to each lead point, and screens each lead point based on each EEG conduction distance matrix of the target individual to obtain multiple target lead points for the target individual. By determining each effective brain source signal in the EEG signals of the target individual, establishing the EEG conduction distance matrix corresponding to each effective brain source signal of the target individual, and screening the target lead points corresponding to the target individual from each lead point based on the EEG conduction distance matrix corresponding to each effective brain source signal of the target individual, the accuracy of screening the target lead points corresponding to a single individual is improved. The technical solutions of the present application are described in further detail below with reference to the drawings and embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0066] Figure 1 An application environment diagram of the lead screening method based on traceability and individual differences in one embodiment;

[0067] Figure 2 A two-dimensional style diagram of all lead points of the multi-lead device in one embodiment;

[0068] Figure 3 A flowchart of the step of constructing the EEG conduction distance matrix in one embodiment;

[0069] Figure 4 A two-dimensional style diagram of the multi-lead device containing the target lead points in another embodiment;

[0070] Figure 5 A flowchart of the lead screening example based on traceability and individual differences in one embodiment;

[0071] Figure 6 A structural block diagram of the lead screening device based on traceability and individual differences in one embodiment;

[0072] Figure 7 An internal structure diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0073] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0074] The lead screening method based on traceability and individual differences provided by the embodiments of the present application can be applied to a terminal, a server, a system including a terminal and a server, and is realized through the interaction of the terminal and the server. The terminal can include, but is not limited to, various personal computers, notebook computers, tablet computers, etc. The terminal improves the accuracy of individual lead point screening by respectively establishing an electroencephalogram conduction distance matrix corresponding to each electroencephalogram for the electroencephalogram conduction distance matrix to obtain a target electroencephalogram corresponding to the electroencephalogram.

[0075] In one embodiment, as shown in Figure 1 A lead screening method based on traceability and individual differences is provided. The method is described by taking the terminal as an example, which includes the following steps:

[0076] Step S101: Obtain the electroencephalogram of a target individual collected by each lead point of a multi-lead device.

[0077] In this embodiment, the terminal obtains the electroencephalogram of the target individual through the sampling strategy of the multi-lead device. The multi-lead device is a brain-computer interface device for collecting the electroencephalogram of the target individual. The sampling strategy of the multi-lead device is any electroencephalogram sampling method of the brain-computer interface device that can realize the above steps. The target individual can be, but is not limited to, a living being that can be collected by the multi-lead device, such as a human, a simian, a gorilla, a dolphin, etc. The multi-lead device includes multiple lead points (as shown in Figure 2 Specifically, the multi-lead device clusters and aggregates the sub-electroencephalogram information obtained by each lead point to obtain the electroencephalogram information of the target individual.

[0078] Step S102: Decompose the electroencephalogram into multiple independent electroencephalograms according to the number of lead points of the multi-lead device.

[0079] In this embodiment, the terminal decomposes the electroencephalogram into multiple independent electroencephalograms according to the number of lead points of the multi-lead device through an independent component analysis strategy. The specific decomposition process will be described in detail later.

[0080] Step S103: Determine the effective brain source signals in each independent electroencephalogram, and perform spatial arrangement processing on each effective brain source signal according to a preset brain cortex space traceability strategy to obtain the spatial position information of the effective brain source signals.

[0081] In this embodiment, the terminal screens effective brain source signals from the independent electroencephalogram signals of each lead information. For each effective brain source signal, the terminal locates the spatial position information of the effective brain source signal according to the effective brain source signal and the spatial position information of each lead point through a brain cortex spatial tracing strategy. Similarly, the terminal obtains the spatial position information corresponding to each effective brain source signal through the above steps. The effective brain source signal is an electroencephalogram signal transmitted by an electroencephalogram signal emission source in the brain tissue of the target individual. The process of calculating the spatial position information of the effective brain source signal will be described in detail later.

[0082] In step S104, the terminal calculates the electroencephalogram conduction distance of each effective brain source signal to each lead point according to the spatial position information of each lead point, the spatial position information of each effective brain source signal, and the preset electrical conductivity matrix of each brain tissue, and establishes the electroencephalogram conduction distance matrix corresponding to each effective brain source signal based on the electroencephalogram conduction distance of each effective brain source signal to each lead point.

[0083] In this embodiment, the terminal calculates the electroencephalogram conduction distance of each effective brain source signal to each lead point according to the spatial position information of the effective brain source signal and the spatial position information of each lead point, and calculates the electroencephalogram conduction distance of the effective brain source signal to each lead point according to the brain tissue electrical conductivity matrix of the effective brain source signal to each lead point, and establishes the electroencephalogram conduction distance matrix corresponding to the effective brain source signal according to the electroencephalogram conduction distance of the effective brain source signal to each lead point. The electroencephalogram conduction distance is the electrical conduction distance of the electroencephalogram signal from one spatial position point to another spatial position point. Because the electrical characteristics of the brain skull cavity at different positions are not the same, two points that are close in spatial distance may be very far in conduction distance, and the influencing factor of the electroencephalogram conduction distance is determined by the electrical conductivity of the brain skull cavity tissue between the two different spatial position points. The specific process of establishing the electroencephalogram conduction distance matrix will be described in detail later.

[0084] In step S105, the terminal screens each lead point based on each electroencephalogram conduction distance matrix of the target individual, and obtains a plurality of target lead points for the target individual.

[0085] In this embodiment, the terminal selects the lead point closest to the effective brain source signal from each lead point in each electroencephalogram conduction distance matrix as the target lead point of the electroencephalogram conduction distance matrix. Similarly, all target lead points are obtained through the above method. The target lead point can be used to collect the electroencephalogram signal corresponding to the target individual, or a target brain-computer interface device corresponding to the target individual can be established for the target individual. The target brain-computer interface device can accurately obtain the electroencephalogram signal of the target individual.

[0086] Based on the above scheme, by determining each effective brain source signal in the electroencephalogram signal of the target individual, an electroencephalogram conduction distance matrix corresponding to each effective brain source signal of the target individual is established, and based on the electroencephalogram conduction distance matrix corresponding to each effective brain source signal of the target individual, a target lead point corresponding to the target individual is screened out among the lead points, thereby improving the accuracy of screening the target lead point corresponding to a single individual.

[0087] Optionally, the electroencephalogram signal of the target individual collected by each lead point of the multi-lead device includes: acquiring the high-dimensional electroencephalogram signal of the target individual collected by the multi-lead device; performing dimensionality reduction processing on the high-dimensional electroencephalogram signal to obtain a low-dimensional electroencephalogram signal; and performing filtering processing on the low-dimensional electroencephalogram signal by using a preset filtering parameter to obtain the electroencephalogram signal of the target individual.

[0088] In this embodiment, the terminal acquires the high-dimensional electroencephalogram signal of the target individual based on the sampling strategy of the multi-lead device. The terminal performs downsampling processing on the high-dimensional electroencephalogram signal, and performs dimensionality reduction operation on the high sampling rate to obtain the low-dimensional electroencephalogram signal of the target individual. The terminal presets a filtering parameter, and screens the electroencephalogram signal that meets the filtering parameter from the low-dimensional electroencephalogram signal according to the filtering parameter to obtain the electroencephalogram signal of the target individual. Before acquiring the electroencephalogram signal of the target individual, the terminal determines the invalid lead points in the multi-lead device, and after obtaining the electroencephalogram signal of the target individual, the terminal deletes the electroencephalogram signal corresponding to the invalid lead points in each electroencephalogram signal to obtain the electroencephalogram signal of the target individual after impurity removal.

[0089] The dimensionality reduction operation is to reduce the original high sampling rate of the electroencephalogram signal to 200 Hz or 256 Hz sampling rate. The filtering parameter can be but is not limited to a sampling rate of 1 Hz-45 Hz, which is used to remove the primary slow wave interference and high-frequency noise existing in the electroencephalogram signal.

[0090] Based on the above scheme, by performing dimensionality reduction and impurity removal processing on the electroencephalogram signal of the target individual, the electroencephalogram signal with high signal-to-noise ratio is obtained, which provides a data basis for subsequent establishment of the electroencephalogram conduction distance matrix.

[0091] Optionally, the electroencephalogram signal is decomposed into a plurality of independent electroencephalogram signals according to the number of lead points of the multi-lead device, including: performing noise removal processing on the electroencephalogram signal to obtain the noise-removed electroencephalogram signal; and decomposing the electroencephalogram signal into independent electroencephalogram signals with the same number of lead points based on an independent component analysis strategy.

[0092] In this embodiment, the terminal performs noise removal processing on the acquired electroencephalogram signal to obtain a denoised electroencephalogram signal. The terminal decomposes the electroencephalogram signal into a plurality of independent electroencephalogram signals according to the number of lead points based on an independent component analysis strategy. The independent component analysis strategy is an ICA (Independent Component Correlation Algorithm) signal decomposition technology. The noise removal processing is used to remove noise signals such as electromyographic noise, electrooculographic noise, environmental noise, and electrode noise in the electroencephalogram signal. The noise removal technology can be, but is not limited to, any electroencephalogram signal noise removal technology that can achieve the above steps.

[0093] Based on the above scheme, by decomposing the brain source signal into effective brain source signals corresponding to each lead point, the accuracy of determining the brain source signal is improved.

[0094] Optionally, as shown in Figure 3 The effective brain source signals in each independent electroencephalogram signal are determined, and the spatial arrangement processing is performed on each effective brain source signal according to a preset brain cortex space source tracing strategy to obtain spatial position information of the effective brain source signals, including:

[0095] In step S301, the effective brain source signals containing electroencephalogram neural data are selected from each independent electroencephalogram signal.

[0096] In this embodiment, the terminal extracts neural data related to electroencephalogram neural data in each neural data of each independent electroencephalogram signal by a neural data analysis strategy, and takes each electroencephalogram neural data as an effective brain source signal. The neural data analysis strategy can be, but is not limited to, an ICLabel label-based neural analysis technology. Each independent electroencephalogram signal contains a plurality of neural data, such as electrooculographic neural data and electromyographic neural data.

[0097] Specifically, the terminal first removes the electrode noise data in the independent electroencephalogram signal by noise removal operation to obtain a noise-free independent electroencephalogram signal. The terminal extracts non-electrooculographic neural data and electromyographic neural data from each neural data by ICLabel technology to obtain the effective brain source signal of the independent electroencephalogram signal, and obtains the effective brain source signal corresponding to each lead point.

[0098] In step S302, a skull cavity conductor model of a target individual is acquired.

[0099] The skull cavity conductor model includes geometric position information of a three-dimensional structure of electroencephalogram neural in the skull cavity and electrode position information of each lead point.

[0100] In this embodiment, the terminal obtains the geometric position information of the three-dimensional structure of the intracranial brain electrical nerve of the target individual and the electrode position information of each lead point of the multi-lead device based on the target individual and the multi-lead device. The terminal constructs the cranial cavity conductor model of the target individual by the geometric position information of the three-dimensional structure of the intracranial brain electrical nerve of the target individual and the electrode position information of each brain electrical nerve. The terminal can obtain the data information for constructing the cranial cavity conductor model by scanning the structure of each tissue in the cranial cavity of the target individual through the MRI (Magnetic Resonance Imaging) technology. The geometric position information of the three-dimensional structure of the intracranial brain electrical nerve of the target individual is the geometric position information of the three-dimensional structure of each brain tissue in the cranial cavity of the target individual and the theoretical electrode position information of each lead point when the target individual wears the multi-lead device. The electrode position information of each lead point is the position information of the spatial arrangement of the multi-lead device, and the electrode position information of each lead point can be directly obtained through the multi-lead device.

[0101] In step S303, for each effective brain source signal, the electrode position information of the effective brain source signal is calculated according to the electrode position information of each lead point and the effective brain source signal, and the spatial position information of the effective brain source signal is determined based on the geometric position information of the three-dimensional structure of the intracranial brain electrical nerve and the electrode position information of the effective brain source signal.

[0102] In this embodiment, the terminal calculates the electrode position information of each effective brain source signal according to the electrode position information of each lead point through the boundary element algorithm. The terminal arranges the spatial position of the effective brain source signal in the geometric position information of the three-dimensional structure of the intracranial brain electrical nerve based on the electrode position information of the effective brain source signal, and obtains the spatial position information of the effective brain source signal.

[0103] Specifically, according to the obtained brain source signal and the existing electrode position coordinates, the accurate single dipole positioning of each brain source component can be performed. Here, the boundary element method is used to estimate the conductive matrix in combination with the general MRI (Magnetic Resonance Imaging) fine structure data. In order to obtain source positioning, it is first assumed that the brain electrical observation signal and the source signal satisfy the following equation:

[0104] E=LS+ε

[0105] In the formula, E is the collected electroencephalogram observation signal, S is a theoretical source signal containing all information of the dipole, such as direction, position, intensity, and the like, ε is noise information that cannot be avoided, L is a lead field matrix, after the fine structure of each tissue and the conductivity matrix thereof are known, the lead field matrix L can be solved by using a boundary element method, and the observation space signal is converted into a source space signal, since the source calculation itself is a highly underdetermined problem, therefore, a least square method of L2 norm is used to give a constraint:

[0106] min s ||LS+ε|| 2 +λ||WS|| 2

[0107] Wherein W is a conduction weight matrix, which represents the amplitude of the source signal, and λ is a regularization coefficient. In order to further solve W, a weighted minimum norm estimation method is used to obtain the estimation of W in the case that the source distribution can be generated and the least square error measurement value is fitted and the power is minimum:

[0108] W=BL T (LBL T +λN) -1

[0109] Wherein N is a noise covariance matrix, and B is a construction matrix, which is usually selected as B=1 or a diagonal matrix according to experience.

[0110] Based on the above scheme, the spatial position information of the effective brain source signal is obtained, which provides a data basis for subsequent calculation of the transmission distance of each effective brain source signal to each lead point.

[0111] Optionally, according to the spatial position information of each lead point, the spatial position information of each effective brain source signal, and the preset conductivity matrix of each tissue of the brain, the electroencephalogram transmission distance of each effective brain source signal to each lead point is calculated, and based on the electroencephalogram transmission distance of all effective brain source signals to each lead point, an electroencephalogram transmission distance matrix corresponding to each effective brain source signal is established, including: for each effective brain source signal, according to the spatial position information of the effective brain source signal and the spatial position information of each lead point, the spatial distance of the effective brain source signal to each lead point is determined; for each lead point, according to the spatial position information of the effective brain source signal, the spatial position information of the lead point, the spatial distance of the effective brain source signal to the lead point, and the preset conductivity matrix of each tissue of the brain, the electroencephalogram transmission distance of the effective brain source signal to the lead point is calculated; based on the electroencephalogram transmission distance of the effective brain source signal to each lead point, the electroencephalogram transmission distance matrix of the effective brain source signal is established.

[0112] In this embodiment, the terminal determines, for each effective brain source signal, a spatial distance from the effective brain source signal to each electrode point according to the spatial position information of the effective brain source signal and the spatial position information of each electrode point. Then, the terminal calculates, for each electrode point, an EEG conduction distance from the effective brain source signal to the electrode point according to the spatial position information of the effective brain source signal, the spatial position information of the electrode point, the spatial distance from the effective brain source signal to the electrode point, and the preset conductivity matrix of each tissue of the brain. Similarly, the EEG conduction distance from the effective brain source signal to each electrode point is obtained through the above scheme, and the terminal establishes an EEG conduction distance matrix of the effective brain source signal based on the EEG conduction distance from the effective brain source signal to each electrode point. Similarly, through the above steps, the terminal obtains the EEG conduction distance from all effective brain source signals to each electrode point.

[0113] Specifically, after obtaining the three-dimensional coordinates of the dipole (i.e., the spatial position information of the effective brain source signal) and the source signal (i.e., the effective brain source signal), it is necessary to exclude the scalp electrodes based on the pure signal. Here, the screening criteria need to be solved first. In order to facilitate batch processing, the distance dist(o, c) is selected as the screening basis here, where c is the electrode reference and o refers to the dipole. For each dipole with known three-dimensional coordinates, combined with the known spatial coordinates of the scalp electrodes (i.e., the spatial position information of each electrode point) and the skull cavity tissue conductivity matrix, the conduction distance matrix D ∈ R O×C of each dipole corresponding to each electrode can be obtained, where any element dist i，j is the conduction distance from the dipole o i to the electrode c j .

[0114] Based on the above scheme, by calculating the conduction distance from each effective brain source signal to each electrode point, the EEG conduction matrix corresponding to the effective brain source signal is established, which improves the accuracy of establishing the EEG conduction distance matrix.

[0115] Optionally, each electrode point is screened based on the EEG conduction distance matrix of the target individual to obtain a plurality of target electrode points for the target individual, including: for each effective brain source signal, selecting, in the EEG conduction distance matrix of the effective brain source signal, the electrode point with the closest EEG conduction distance to the effective brain source signal as the target electrode point.

[0116] In this embodiment, the terminal selects, for each effective brain source signal, in the EEG conduction distance matrix corresponding to the effective brain source signal, the electrode point with the closest EEG conduction distance to the effective brain source signal as the target electrode point. Similarly, through the above scheme, the terminal obtains a plurality of target electrode points through the EEG conduction distance matrix corresponding to each effective brain source signal.

[0117] Based on the above scheme, the target lead points are screened by using the EEG conduction distance matrix of the target individual, which improves the accuracy of screening the target lead points corresponding to the target individual.

[0118] Optionally, after selecting the lead point closest to the effective brain source signal's EEG conduction distance as the target lead point, the following steps are also included:

[0119] If the number of target lead points does not meet the preset number of lead points, then among all lead points other than the target lead points, lead points that meet the preset lead filtering information are selected as target lead points.

[0120] In this embodiment, the terminal presets the number of lead points and lead filtering information. If the number of target lead points obtained through the above steps does not meet the preset number of lead points, the terminal selects lead points that meet the lead filtering information from among the lead points other than the target lead points as target lead points. The preset number of lead points is adjusted based on the task corresponding to the target individual's EEG signal. Through the above steps, the terminal obtains all target lead points for the target individual (e.g., ...). Figure 4 (As shown). The lead selection information is a lead selection strategy obtained based on the individual differences of the target or the task relevance of the EEG signals. For example, if the total number of target lead points with the closest EEG conduction distance to each effective brain source signal is 24, and the target individual is a female human with a physiological age of 16, the lead selection information shows that the number of target lead points is 32. Then, the terminal calculates the EEG conduction distance between each lead point and each effective brain source signal, excluding the target lead point with the closest EEG conduction distance to each effective brain source signal, and further selects the 8 lead points with the closest EEG conduction distance to each effective brain source signal from the above lead points as the target lead points for this target individual.

[0121] Based on the above scheme, each lead point is further filtered by lead information threshold, which meets the needs of different target individuals with different EEG signals, thereby improving the accuracy of obtaining the target lead points corresponding to different target individuals.

[0122] Optionally, the method further includes:

[0123] Obtain the EEG signals corresponding to each target lead point, and use the EEG signals corresponding to all target lead points as the target EEG signals for the target individual; or, for each valid brain source signal, perform inverse transformation processing on the valid brain source signal through the EEG conduction distance matrix corresponding to the valid brain source signal to obtain the EEG signals corresponding to each target lead point.

[0124] In this embodiment, the terminal selects the brain electrical signals obtained through all target electrodes from the obtained brain electrical signals of the target individual in the case of knowing the brain electrical signals of the target individual, and takes the brain electrical signals obtained through all electrodes as the target brain electrical signals of the target individual.

[0125] In the case of knowing the set of multiple effective brain source signals of the target individual, the terminal performs inverse transform processing on each effective brain source signal through the brain electrical conduction distance matrix corresponding to the effective brain source signal to obtain the brain electrical signals of each electrode corresponding to the effective brain source signal, and selects the signal of the target electrode corresponding to the effective brain source signal from all electrodes as the target brain electrical signal. Similarly, the signals of the target electrodes corresponding to all effective brain source signals are taken as the target brain electrical signals of the target individual.

[0126] Based on the above scheme, the target brain electrical signals of the target individual are reconstructed based on the brain electrical conduction distance matrix through multiple target brain source signals, which improves the signal-to-noise ratio of the obtained target brain electrical signals.

[0127] The present application also provides a lead screening example based on traceability and individual differences, as shown in Figure 5 The specific processing process includes the following steps:

[0128] Step S501, obtaining the brain electrical signals of the target individual collected by each electrode point in the multi-electrode device.

[0129] Step S502, performing noise removal processing on the brain electrical signals to obtain the denoised brain electrical signals.

[0130] Step S503, based on the independent component analysis strategy, decomposing the brain electrical signals into independent brain electrical signals with the same number of electrode points.

[0131] Step S504, selecting the effective brain source signals containing brain electrical neural data from the independent brain electrical signals.

[0132] Step S505, obtaining the skull cavity conductor model of the target individual.

[0133] Step S506, for each effective brain source signal, calculating the electrode position information of the effective brain source signal according to the electrode position information of the brain electrical neural data and the effective brain source signal, and determining the spatial position information of the effective brain source signal based on the geometric position information of the three-dimensional structure of the intracranial brain electrical neural data and the electrode position information of the effective brain source signal.

[0134] Step S507, for each effective brain source signal, determining the spatial distance from the effective brain source signal to each electrode point according to the spatial position information of the effective brain source signal and the spatial position information of each electrode point.

[0135] Step S508: For each lead point, calculate the EEG conduction distance from the effective brain source signal to the lead point based on the spatial location information of the effective brain source signal, the spatial location information of the lead point, the spatial distance from the effective brain source signal to the lead point, and the preset conductivity matrix of various brain tissues.

[0136] Step S509: Based on the EEG conduction distance from the effective brain source signal to each lead point, establish the EEG conduction distance matrix of the effective brain source signal.

[0137] Step S510: For each valid brain source signal, select the lead point with the closest EEG conduction distance to the valid brain source signal from among the lead points in the EEG conduction distance matrix corresponding to the valid brain source signal, and use it as the target lead point.

[0138] Step S511: If the number of target lead points does not meet the preset number of lead points, select lead points that meet the preset lead filtering information as target lead points from among the lead points other than the target lead points.

[0139] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0140] Based on the same inventive concept, this application also provides a lead screening device based on source tracing and individual differences for implementing the lead screening method based on source tracing and individual differences described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more lead screening device embodiments based on source tracing and individual differences provided below can be found in the limitations of the lead screening method based on source tracing and individual differences described above, and will not be repeated here.

[0141] In one embodiment, such as Figure 6 As shown, a lead screening device based on source tracing and individual differences is provided, including: an acquisition module 610, a decomposition module 620, a source tracing module 630, an establishment module 640, and a screening module 650, wherein:

[0142] The acquisition module 610 is configured to acquire electroencephalogram signals of a target individual collected by lead points of a multi-lead device.

[0143] The decomposition module 620 is configured to decompose the electroencephalogram signals into a plurality of independent electroencephalogram signals according to the number of lead points of the multi-lead device.

[0144] The tracing module 630 is configured to determine effective brain source signals in the independent electroencephalogram signals, and perform spatial arrangement processing on the effective brain source signals according to a preset brain cortex spatial tracing strategy, to obtain spatial position information of the effective brain source signals.

[0145] The establishment module 640 is configured to calculate electroencephalogram conduction distances of the effective brain source signals to each lead point according to the spatial position information of the lead points, the spatial position information of the effective brain source signals, and a preset electrical conductivity matrix of brain tissues, and establish an electroencephalogram conduction distance matrix corresponding to each effective brain source signal based on the electroencephalogram conduction distances of the effective brain source signals to the lead points.

[0146] The screening module 650 is configured to screen the lead points based on the electroencephalogram conduction distance matrices of the target individual, to obtain a plurality of target lead points for the target individual.

[0147] Optionally, the acquisition module 610 is specifically configured to:

[0148] Acquire high-dimensional electroencephalogram signals of the target individual collected by the multi-lead device.

[0149] Perform dimension reduction processing on the high-dimensional electroencephalogram signals, to obtain low-dimensional electroencephalogram signals.

[0150] Perform filtering processing on the low-dimensional electroencephalogram signals by using preset filtering parameters, to obtain the electroencephalogram signals of the target individual.

[0151] Optionally, the decomposition module 620 is specifically configured to:

[0152] Perform noise removal processing on the electroencephalogram signals, to obtain noise-removed electroencephalogram signals.

[0153] Decompose the electroencephalogram signals into independent electroencephalogram signals in the same number as the lead points, based on an independent component analysis strategy.

[0154] Optionally, the tracing module 630 is specifically configured to:

[0155] Select effective brain source signals containing electroencephalogram neural data from the independent electroencephalogram signals.

[0156] Acquire a skull cavity conductor model of the target individual; the skull cavity conductor model includes geometric position information of a three-dimensional structure of electroencephalogram neural data in a skull cavity and electrode position information of the lead points.

[0157] For each effective brain source signal, the electrode position information of the effective brain source signal is calculated according to the electrode position information of the electroencephalogram nerve and the effective brain source signal, and the spatial position information of the effective brain source signal is determined based on the geometric position information of the three-dimensional structure of the intracranial electroencephalogram nerve and the electrode position information of the effective brain source signal.

[0158] Optionally, the establishing module 640 is specifically configured to:

[0159] For each effective brain source signal, the spatial distance of the effective brain source signal to each lead point is determined according to the spatial position information of the effective brain source signal and the spatial position information of each lead point.

[0160] For each lead point, the electroencephalogram conduction distance of the effective brain source signal to the lead point is calculated according to the spatial position information of the effective brain source signal, the spatial position information of the lead point, the spatial distance of the effective brain source signal to the lead point, and the preset electrical conductivity matrix of the brain tissue.

[0161] Based on the electroencephalogram conduction distance of the effective brain source signal to each lead point, the electroencephalogram conduction distance matrix of the effective brain source signal is established.

[0162] Optionally, the screening module 650 is specifically configured to:

[0163] For each effective brain source signal, the lead point closest to the electroencephalogram conduction distance of the effective brain source signal is selected as the target lead point from the lead points in the electroencephalogram conduction distance matrix corresponding to the effective brain source signal.

[0164] Optionally, the apparatus further comprises:

[0165] The re-screening module is configured to, in a case where the number of target lead points does not satisfy the preset lead point number, select a lead point satisfying the preset lead screening information as a target lead point from the lead points other than the target lead points.

[0166] Optionally, the apparatus further comprises:

[0167] The first electroencephalogram signal acquisition module is configured to acquire the electroencephalogram signals corresponding to the target lead points, and take the electroencephalogram signals corresponding to all target lead points as the target electroencephalogram signals of the target individual; or

[0168] The second electroencephalogram signal acquisition module is configured to, for each effective brain source signal, perform inverse transformation processing on the effective brain source signal through the electroencephalogram conduction distance matrix corresponding to the effective brain source signal, to obtain the electroencephalogram signals corresponding to the target lead points.

[0169] The modules in the above lead selection device based on traceability and individual differences can be implemented by software, hardware, or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so that the processor can call and execute the operations of the modules.

[0170] In an embodiment, a computer device is provided, which can be a terminal, and an internal structure diagram of the computer device can be as shown in FIG. 1. Figure 7 The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved by WIFI, mobile cellular network, NFC (near field communication), or other technologies. The computer program is executed by the processor to implement a lead selection method based on traceability and individual differences. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball, or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0171] Those skilled in the art can understand that Figure 7 The structure shown in FIG. 1 is only a block diagram of part of the structure related to the scheme of the present application, and does not limit the computer device to which the scheme of the present application is applied. Specifically, the computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0172] In an embodiment, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0173] In an embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0174] In an embodiment, a computer program product is provided, which includes a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0175] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0176] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments. Any reference to memory, database or other medium used in the embodiments provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0177] The technical features of the above embodiments can be combined in any way. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictory, it should be considered as the scope of the present application.

[0178] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A lead screening method based on traceability and individual differences, characterized in that, The method comprises: obtaining brain electrical signals of a target individual collected by each lead point of a multi-lead device; decomposing the brain electrical signals into a plurality of independent brain electrical signals according to the number of lead points of the multi-lead device; determining effective brain source signals in each of the independent brain electrical signals; selecting, in each of the independent brain electrical signals, effective brain source signals containing brain electrical neural data; obtaining a skull cavity conductor model of the target individual; the skull cavity conductor model comprises geometric position information of a three-dimensional structure of brain electrical nerves in the skull cavity and electrode position information of each lead point; for each effective brain source signal, calculating spatial positioning information of the effective brain source signal according to the electrode position information of the brain electrical signals and the effective brain source signal, and determining spatial position information of the effective brain source signal based on the geometric position information of the three-dimensional structure of brain electrical nerves in the skull cavity and the electrode position information of the effective brain source signal; calculating brain electrical conduction distances of each effective brain source signal to each lead point according to the spatial position information of each lead point, the spatial position information of each effective brain source signal and a preset electrical conductivity matrix of each tissue of the brain, and establishing a brain electrical conduction distance matrix corresponding to each effective brain source signal based on the brain electrical conduction distances of each effective brain source signal to each lead point; screening each lead point based on each brain electrical conduction distance matrix of the target individual to obtain a plurality of target lead points for the target individual.

2. The method of claim 1, wherein, The method comprises: obtaining brain electrical signals of a target individual collected by each lead point of a multi-lead device; decomposing the brain electrical signals into a plurality of independent brain electrical signals according to the number of lead points of the multi-lead device; determining effective brain source signals in each of the independent brain electrical signals; 3. The method of claim 1, wherein, selecting, in each of the independent brain electrical signals, effective brain source signals containing brain electrical neural data; obtaining a skull cavity conductor model of the target individual; the skull cavity conductor model comprises geometric position information of a three-dimensional structure of brain electrical nerves in the skull cavity and electrode position information of each lead point; for each effective brain source signal, calculating spatial positioning information of the effective brain source signal according to the electrode position information of the brain electrical signals and the effective brain source signal, and determining spatial position information of the effective brain source signal based on the geometric position information of the three-dimensional structure of brain electrical nerves in the skull cavity and the electrode position information of the effective brain source signal; 4. The method of claim 1, wherein, calculating brain electrical conduction distances of each effective brain source signal to each lead point according to the spatial position information of each lead point, the spatial position information of each effective brain source signal and a preset electrical conductivity matrix of each tissue of the brain, and establishing a brain electrical conduction distance matrix corresponding to each effective brain source signal based on the brain electrical conduction distances of each effective brain source signal to each lead point; screening each lead point based on each brain electrical conduction distance matrix of the target individual to obtain a plurality of target lead points for the target individual. The method comprises: obtaining brain electrical signals of a target individual collected by each lead point of a multi-lead device; decomposing the brain electrical signals into a plurality of independent brain electrical signals according to the number of lead points of the multi-lead device; determining effective brain source signals in each of the independent brain electrical signals; selecting, in each of the independent brain electrical signals, effective brain source signals containing brain electrical neural data; obtaining a skull cavity conductor model of the target individual; the skull cavity conductor model comprises geometric position information of a three-dimensional structure of brain electrical nerves in the skull cavity and electrode position information of each lead point; for each effective brain source signal, calculating spatial positioning information of the effective brain source signal according to the electrode position information of the brain electrical signals and the effective brain source signal, and determining spatial position information of the effective brain source signal based on the geometric position information of the three-dimensional structure of brain electrical nerves in the skull cavity and the electrode position information of the effective brain source signal; calculating brain electrical conduction distances of each effective brain source signal to each lead point according to the spatial position information of each lead point, the spatial position information of each effective brain source signal and a preset electrical conductivity matrix of each tissue of the brain, and establishing a brain electrical conduction distance matrix corresponding to each effective brain source signal based on the brain electrical conduction distances of each effective brain source signal to each lead point; screening each lead point based on each brain electrical conduction distance matrix of the target individual to obtain a plurality of target lead points for the target individual. The method comprises: obtaining brain electrical signals of a target individual collected by each lead point of a multi-lead device; decomposing the brain electrical signals into a plurality of independent brain electrical signals according to the number of lead points of the multi-lead device; determining effective brain source signals in each of the independent brain electrical signals; selecting, in each of the independent brain electrical signals, effective brain source signals containing brain electrical neural data; obtaining a skull cavity conductor model of the target individual; the skull cavity conductor model comprises geometric position information of a three-dimensional structure of brain electrical nerves in the skull cavity and electrode position information of each lead point; for each effective brain source signal, calculating spatial positioning information of the effective brain source signal according to the electrode position information of the brain electrical signals and the effective brain source signal, and determining spatial position information of the effective brain source signal based on the geometric position information of the three-dimensional structure of brain electrical nerves in the skull cavity and the electrode position information of the effective brain source signal; calculating brain electrical conduction distances of each effective brain source signal to each lead point according to the spatial position information of each lead point, the spatial position information of each effective brain source signal and a preset electrical conductivity matrix of each tissue of the brain, and establishing a brain electrical conduction distance matrix corresponding to each effective brain source signal based on the brain electrical conduction distances of each effective brain source signal to each lead point; screening each lead point based on each brain electrical conduction distance matrix of the target individual to obtain a plurality of target lead points for the target individual. Based on the electroencephalogram conduction distance of the effective brain source signal to each lead point, an electroencephalogram conduction distance matrix of the effective brain source signal is established.

5. The method of claim 1, wherein, The method further comprises: For each effective brain source signal, the effective brain source signal is inversely transformed through the electroencephalogram conduction distance matrix corresponding to the effective brain source signal, to obtain the electroencephalogram signal corresponding to each target lead point.

6. The method of claim 5, wherein, The method further comprises: In a case where the number of target lead points does not satisfy the preset number of lead points, a lead point satisfying preset lead screening information is selected as a target lead point from the lead points other than the target lead points.

7. The method of claim 1, wherein, The method further comprises: The electroencephalogram signals corresponding to the target lead points are obtained, and the electroencephalogram signals corresponding to all target lead points are taken as target electroencephalogram signals of the target individual; or For each effective brain source signal, the effective brain source signal is inversely transformed through the electroencephalogram conduction distance matrix corresponding to the effective brain source signal, to obtain the electroencephalogram signal corresponding to each target lead point.

8. A lead selection device based on traceability and individual differences, characterized by, The device comprises: An acquisition module is configured to acquire electroencephalogram signals of a target individual collected by lead points of a multi-lead device; A decomposition module is configured to decompose the electroencephalogram signals into a plurality of independent electroencephalogram signals according to the number of lead points of the multi-lead device; A tracing module is configured to determine effective brain source signals in the independent electroencephalogram signals; select effective brain source signals containing electroencephalogram neural data from the independent electroencephalogram signals; acquire a cranial cavity conductor model of the target individual; the cranial cavity conductor model comprises geometric position information of a three-dimensional structure of electroencephalogram neural in the cranial cavity and electrode position information of the lead points; for each effective brain source signal, calculate spatial positioning information of the effective brain source signal according to the electrode position information of the electroencephalogram signals and the effective brain source signal, and determine spatial position information of the effective brain source signal based on the geometric position information of the three-dimensional structure of electroencephalogram neural in the cranial cavity and the electrode position information of the effective brain source signal; An establishment module is configured to calculate electroencephalogram conduction distances of each effective brain source signal to each lead point according to the spatial position information of each lead point, the spatial position information of each effective brain source signal, and a preset electrical conductivity matrix of each tissue of the brain, and establish an electroencephalogram conduction distance matrix corresponding to each effective brain source signal based on the electroencephalogram conduction distances of each effective brain source signal to each lead point; A screening module is configured to screen each lead point based on each electroencephalogram conduction distance matrix of the target individual, to obtain a plurality of target lead points for the target individual.

9. The apparatus of claim 8, wherein, The acquisition module is specifically configured to: Acquire high-dimensional electroencephalogram signals of a target individual collected by a multi-lead device; Perform dimension reduction processing on the high-dimensional electroencephalogram signals to obtain low-dimensional electroencephalogram signals; Perform filtering processing on the low-dimensional electroencephalogram signals through preset filtering parameters to obtain electroencephalogram signals of the target individual. 10.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-9. The processor, when executing the computer program, implements the steps of the method according to any one of claims 1 to 7.

Images