Neural feedback method, device and equipment based on brain power supply positioning and medium

Abstract

The invention relates to the technical field of electroencephalogram signal monitoring and processing, in particular to a neural feedback method and device based on electroencephalogram positioning, equipment and a medium, and the method comprises the following steps: acquiring electroencephalogram data of a target user; determining a source estimation result of the source space based on the electroencephalogram data of the target user; an interested brain region of the target user is determined, interested electroencephalogram data is determined based on the source estimation result of the source space and the interested brain region of the target user, and the interested brain region is associated with a neural training target of the target user; and on the basis of the interested electroencephalogram data of the target user, determining a characteristic value of the interested brain region, and taking the interested brain region electroencephalogram data and the corresponding characteristic value as a neural feedback index concerned by the target user. The acquired electroencephalogram data of the user can be converted into the activation map of the brain source space, the electroencephalogram data of the specified brain function area is extracted according to the cognitive function concerned by the user, and a more accurate and functional dissimilatory neural feedback process is realized.

Description

Technical Field

[0001] The present application relates to the technical field of electroencephalogram (EEG) signal monitoring and processing, and particularly relates to a neural feedback method, device, equipment and medium based on brain source localization. Background Art

[0002] The data spatial resolution relied on by the EEG-based neural feedback technology is limited, resulting in low precision of neural feedback. Therefore, there is no way to obtain the indicators of specific brain functional areas to support the neural feedback of different cognitive functions and users.

[0003] To obtain high-spatial-resolution brain imaging data (such as fMRI and fNIRS) for neural feedback, only the time resolution can be sacrificed, which in turn leads to the inability to capture the brain activities occurring within a short time window, and problems such as increased cost and complex experimental environment. Summary of the Invention

[0004] An object of the present application is to provide a neural feedback method, device, equipment and medium based on brain source localization. Through the neural feedback method based on brain source localization provided by the present application, the collected EEG data of the user can be converted into an activation map in the brain source space, and the "EEG data" of the specified brain functional area (region of interest, ROI) can be extracted according to the cognitive function concerned by the user, so as to realize a more accurate and function-specific neural feedback process.

[0005] According to an embodiment of the first aspect of the present application, a neural feedback method based on brain source localization is provided. The method includes: Obtain the EEG data of the target user; Based on the EEG data of the target user, determine the source estimation result in the source space; Determine the ROI of the target user. Based on the source estimation result in the source space and the ROI of the target user, determine the ROI-EEG data corresponding to the ROI of the target user, where the ROI is associated with the neural training target of the target user; Based on the ROI-EEG data of the target user, determine the eigenvalue of the ROI, and use the ROI-EEG data and the corresponding eigenvalue as the neural feedback indicators concerned by the target user.

[0006] In some embodiments, the determining the ROI of the target user includes: Obtain a brain segmentation atlas library, where the brain segmentation atlas library includes brain segmentation atlases that divide the brain into different regions by one or more principles; Obtain a whole-brain activation map, which is used to characterize the association relationship between the activated brain regions and the neural training target; Based on the neural training objective of the target user, match the whole-brain activation map with the brain region segmentation maps in the brain region segmentation map library, obtain the brain region with the highest activation degree in the brain region segmentation map, and use the brain region with the highest activation degree as the brain region of interest of the target user.

[0007] In some embodiments, the whole-brain activation map is used to characterize the activation of the brain source points corresponding to the neural training objective, and different neural training objectives correspond to different activation situations of brain source points.

[0008] In some embodiments, the method further includes: Based on the neural training objective of the target user, determine the whole-brain activation map corresponding to the neural training objective based on meta-analysis; Match the whole-brain activation map with the brain region segmentation maps in the brain region segmentation map library, obtain the brain region with the highest activation degree in the brain region segmentation map, and use the brain region with the highest activation degree as the brain region of interest of the target user.

[0009] In some embodiments, the whole-brain activation map includes a region composed of one or more activated source points, match the region composed of the source points with the brain region segmentation map, and select the brain region with the largest matching degree in the brain region segmentation map as the brain region of interest of the target user.

[0010] In some embodiments, the method further includes: Obtain the head structural image corresponding to the target user; Based on the head structural image of the target user, construct the head model of the target user and the brain source space to be estimated; Based on the electrode layout of the electroencephalogram acquisition device, the head model of the target user, and the brain source space to be estimated, determine the forward model of source localization; wherein, the forward model of source localization is used to characterize the physical relationship between the brain source space to be estimated mapped to the electroencephalogram data through the head model.

[0011] In some embodiments, the determining the source estimation result of the source space based on the electroencephalogram data of the target user includes: Obtain the electroencephalogram data of the target user, solve the electroencephalogram data based on the inverse solution model and the forward model of source localization, and determine the source estimation result of the source space corresponding to the electroencephalogram data.

[0012] In some embodiments, the obtaining step of the head structural image of the target user includes: If the head structural image of the target user himself / herself is queried, use the queried head structural image as the head structural image of the target user; If the head structure image of the target user himself cannot be queried, obtain the user feature vector of the target user; Match the user feature vector of the target user with the standard feature vectors in the standard brain database of head structure images, and use the head structure image corresponding to the standard brain with the highest matching degree as the head structure image corresponding to the target user.

[0013] In some embodiments, the user feature vector and the standard feature vector include the demographic information and head circumference data of the user.

[0014] In some embodiments, obtaining the electroencephalogram data of the target user includes obtaining the electroencephalogram data of the user through a contact electroencephalogram acquisition device or monitoring the electroencephalogram data of the user through a non-contact electroencephalogram device.

[0015] In some embodiments, monitoring the electroencephalogram data of the user through a non-contact electroencephalogram device includes: Obtain the head image corresponding to the target user at the current moment; Determine the head pose of the target user at the current moment based on the head image corresponding to the current moment; Determine the pose of the electroencephalogram cap based on the head pose at the current moment and the head pose corresponding to the previous moment, where the electroencephalogram cap includes a plurality of brain electrodes, and the plurality of brain electrodes monitor the electroencephalogram data of the target user in the pose corresponding to the electroencephalogram cap.

[0016] This application also provides a computer device, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps of the neurofeedback method based on brain source localization provided in any one of the above embodiments.

[0017] This application also provides a computer-readable storage medium, storing a computer program, and when the computer program is executed by a processor, it implements the steps of the neurofeedback method based on brain source localization provided in any one of the above embodiments.

[0018] A neurofeedback method based on brain source localization proposed in this application can obtain the situation of brain neuronal activities on the premise of retaining the time resolution advantage of electroencephalogram data, and use it for neurofeedback to achieve neurofeedback with high spatial accuracy, and can extract different brain functional areas as neurofeedback indicators according to different cognitive functions and users.

[0019] Additional aspects and advantages of this application will be given in part in the following description, will become apparent in part from the following description, or will be understood through the practice of this application. Description of the Drawings

[0020] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the accompanying drawings, wherein: Figure 1 is a schematic flowchart of a neurofeedback method based on brain source localization provided in an embodiment of the present application; Figure 2 is a schematic flowchart of constructing a forward model for source localization between a brain source space to be estimated and electroencephalogram data provided in an embodiment of the present application; Figure 3 is a schematic diagram of a three - layer head model provided in an embodiment of the present application; Figure 4 is a schematic diagram of an electrode layout structure provided in an embodiment of the present application; Figure 5 is a schematic diagram of a standard brain library provided in an embodiment of the present application; Figure 6 is a schematic flowchart of determining an interested brain region of the target user provided in an embodiment of the present application; Figure 7 is a schematic diagram of a brain segmentation atlas provided in an embodiment of the present application; Figure 8 is a schematic diagram of a whole - brain activation atlas obtained based on meta - analysis provided in an embodiment of the present application; Figure 9 is a schematic diagram of a brain source space provided by the present application; Figure 10 is a schematic diagram of a neurofeedback device based on brain source localization provided in an embodiment of the present application; Figure 11 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. Detailed embodiments

[0021] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0022] The technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that those skilled in the art can implement it. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention.

[0023] To make the above - mentioned objectives, features and advantages of the present application more obvious and understandable, the following will describe in detail the specific embodiments of the present application in conjunction with the accompanying drawings.

[0024] As shown Figure 1 in the figure, a method for region of interest neurofeedback based on brain source localization provided by the present application estimates the activities in the brain source space, improves the accuracy of neurofeedback, and adjusts and expands the dimension of neurofeedback indicators for specific cognitive functions and users.

[0025] It includes: S101, acquiring the electroencephalogram (EEG) data of the target user.

[0026] In some embodiments, the target user can be a person to be detected or a person to be trained, specifically including people of different genders, ages, and races. The detection requirement (training requirement) of the person to be detected (person to be trained) can be a health check or a targeted check or training for a specific cause or a specific training goal. By observing the feedback of these checks, the user can autonomously adjust their cognition and brain activity state, so as to achieve the purpose of cognitive improvement or pathological state intervention.

[0027] In some embodiments, the target user can acquire EEG data by wearing a contact EEG device. In some other embodiments, the target user can also acquire EEG data by a non-contact EEG device.

[0028] S102, determining the source estimation result of the source space based on the EEG data of the target user.

[0029] Among them, the brain source space refers to the space involved in the process of analyzing brain nerve activities, in which the EEG signals recorded on the scalp are inversely deduced to the regions or sources in the brain that may generate these signals through certain mathematical models and algorithms. A spatial model is constructed by using the EEG signals recorded by scalp electrodes (brain electrodes) to infer the position and intensity of neuron activities in the brain.

[0030] In some embodiments, based on the obtained EEG data of the target user, the source estimation result of a given source space can be obtained through an inverse solution model to estimate the nerve activities inside the target user's brain. Among them, the inverse solution model is shown in the following formula.

[0031]

[0032] Among them, eLORETAW is a standard source localization method with good localization accuracy. W represents an inverse model constructed based on the forward model G and the covariance matrix of the EEG data itself, and is used to estimate the activation value of each source point in the source space from the EEG data.

[0033] G represents the forward model composed of a three-layer head model constructed according to the MRI structural image, the channel information of EEG, and the constructed source space, which is used to describe how each source point in the source space jointly affects and forms the observed signals on each channel of EEG.

[0034] J represents the activation map of the source space estimated based on the collected EEG data and the constructed inverse model, where each source point in the source space has an estimated activation value.

[0035] XEEG represents the collected EEG data.

[0036] In the above embodiments, the source estimation result of the source space is calculated through the EEG data obtained by the EEG acquisition device, and then the brain activity state of the target user is known. By feeding back the brain activity state to the user terminal, the user can be guided to adjust the brain activity state to achieve the goal of brain nerve training.

[0037] In some embodiments, a mapping physical model between the EEG data and the source estimation result can be pre-constructed, and then the source estimation result can be calculated based on the obtained EEG data through the physical model.

[0038] Such as Figure 2 , which is a schematic flow chart of constructing the forward model of source localization provided in one of the embodiments.

[0039] In some embodiments, the steps of constructing the forward model of source localization between the brain source space to be estimated and the EEG data include: S201, obtaining the head structural image corresponding to the target user.

[0040] Among them, the head structural image can be the MRI structural image of the target user.

[0041] In some embodiments, the head MRI structural image can be the user's own MRI structural image. In other embodiments, the head MRI structural image can also be a head MRI structural image similar to the user, such as an MRI structural image matched from a standard brain library.

[0042] S202, based on the head structural image of the target user, constructing the head model of the target user and the brain source space to be estimated.

[0043] Obtain the MRI structural image corresponding to the target user, and construct the corresponding head model based on the MRI structural image.

[0044] See Figure 3, the head model may include a three - layer head model, a scalp model, an outer skull model, and an inner skull model. The head model is constructed based on a standard brain or the user's own structural image. The red part is the scalp model, the green part is the outer skull model, and the blue part is the inner skull model.

[0045] The specific formula is as follows:

[0046] Among them, B represents the head model, and S scalp represents the scalp model (left side), and S outer_skull represents the outer skull model (middle), and S inner_skull represents the inner skull model (right side).

[0047] It can be understood that the accuracy of the constructed head model can be customized.

[0048] Obtain the MRI structural image corresponding to the target user, and determine the corresponding brain source space to be estimated based on the MRI structural image.

[0049] The specific formula is as follows:

[0050] Among them, S represents the brain source space to be estimated, and s1, s2... s m represent the source points in the brain source space.

[0051] For the brain source space, see Figure 9 . In Figure 9 , the dot - shaped data represents the source points. The source space at the cortical level is constructed based on a standard brain or the user's own MRI structural image, and the number of source points is 8196. It should be noted that the spatial resolution and depth of the constructed brain source space can be customized.

[0052] S203, determine the forward model of source localization based on the electrode layout of the electroencephalogram acquisition device, the head model of the target user, and the brain source space to be estimated.

[0053] Among them, the forward model of source localization is used to characterize the physical relationship that the brain source space to be estimated is mapped to the electroencephalogram data through the head model.

[0054] See Figure 4 , which is the electrode layout corresponding to the obtained electroencephalogram acquisition device. Among them, the dots represent the brain electrodes used to collect electroencephalogram data, and the electrode layout includes but is not limited to the number and position layout of the brain electrodes, etc.

[0055] Determine the forward model of source localization based on the electrode layout of the electroencephalogram acquisition device, the head model of the target user, and the brain source space to be estimated.

[0056] The electrode layout specifically refers to the following formula:

[0057] Among them, e1…e n represents the spatial position information of several electrodes of the EEG.

[0058] Through the above steps, the layout position of the electrodes in the EEG acquisition device is registered with the head model space, establishing how the source space to be estimated is mapped to the electrodes, and establishing an objective physical model between the layout position of the electrodes in the EEG acquisition device and the head model space. Based on this objective physical model, the corresponding source space data can be further estimated from the acquired EEG data.

[0059] In some embodiments, the step of obtaining the MRI structural image of the target user includes: First, query whether the target user has their own MRI structural image. If the target user's own MRI structural image is queried, use the queried MRI structural image as the target user's MRI structural image; if the target user's own MRI structural image is not queried, obtain the user feature vector of the target user; match the user feature vector of the target user with the standard feature vectors in the standard brain library, and use the MRI structural image corresponding to the standard brain with the highest matching degree as the MRI structural image corresponding to the target user.

[0060] Specifically, if the target user has their own MRI structural image data, directly use their own MRI structural image; if not, select the standard brain with the highest similarity in the standard brain library as the standard brain used by the target user. According to the obtained standard brain or the target user's own MRI structural image, construct the source space of the brain to be estimated.

[0061] In some embodiments, the user feature vector and the standard feature vector include the demographic information and head circumference data of the user.

[0062] Collect the demographic information and head circumference data of the user to obtain a feature vector specific to the user, and the feature vector includes parameters such as age, gender, race, head circumference, etc., as shown below:

[0063] Establish a standard brain library, including standard brains of different genders, different ages, and different races (MNI152, fsaverage, UNCinfant, NKI…)(see Figure 5 ), record the demographic information and head model data of the standard brain for each standard brain record, and obtain the feature vector of each standard brain, and the feature vector is as follows:

[0064] Among them, T refers to the standard brain bank, which includes the feature vectors of different users.

[0065] Compare the user feature vector with the feature vectors of each standard brain in the constructed standard brain bank, and select the standard brain with the highest similarity as the standard brain used by the user. If the user has his own MRI structural image data, there is no need to match in the standard brain bank, and his own MRI structural image is directly used. Among them, the formula for matching the standard brain with the highest similarity to the target user in the standard brain bank is as follows:

[0066] Among them, argmax represents solving the similarity, f user represents the feature vector of the target user, and f template represents the feature vector of the standard brain in the standard library.

[0067] It should be noted that the above standard brain bank includes standard brains of different genders, different ages, and different races. Demographic information and head model data for constructing the standard brain are recorded for each standard brain to obtain the feature vector of each standard brain. For target users without their own MRI structural images, collect the demographic information and head circumference data of the target users to obtain the feature vector specific to the user, and compare the feature vector with the feature vectors of each standard brain in the standard brain bank, and select the standard brain with the highest similarity as the standard brain used by the user.

[0068] In the above embodiment, by establishing a standard brain bank and a matching algorithm, the most suitable standard brain template is provided for users without MRI structural images, which has the advantages of reducing costs and improving the source localization accuracy as much as possible.

[0069] S103. Based on the source estimation result in the source space and the brain regions of interest of the target user, determine the EEG data of the brain regions of interest of the target user.

[0070] In some embodiments, the examination purposes of different target users are different, which can be health examinations or targeted examinations for specific etiologies, so as to achieve the purpose of cognitive improvement or pathological state intervention. For example, the purposes of neurotraining can include attention deficit hyperactivity disorder, depression, autism, sleep disorders, etc.

[0071] For different training purposes, the brain regions of interest concerned by the target user are different. Therefore, according to the training purpose concerned by the target user, extract the EEG data of the brain regions corresponding to the training purpose and feedback it to the user, which can help the user know the activity state of the corresponding brain regions, and then can further target the brain regions for intervention adjustment or training to achieve the purpose of neurofeedback.

[0072] As Figure 6 shown, in some embodiments, determining the brain regions of interest of the target user includes: S601. Obtain a brain region segmentation atlas library, which includes brain region segmentation atlases that divide the brain into different regions by one or more principles.

[0073] S602. Obtain a whole-brain activation atlas, which is used to characterize the association between the activated brain regions and the neural training target.

[0074] S603. Based on the neural training target of the target user, match the whole-brain activation atlas with the brain region segmentation atlases in the brain region segmentation atlas library, obtain the brain region with the highest activation degree in the brain region segmentation atlas, and use the brain region with the highest activation degree as the brain region of interest of the target user.

[0075] In some embodiments, the brain can be divided into different brain region segmentation atlases based on different segmentation principles. For example, the brain region segmentation atlas can be divided by brain structure, or the brain structure can be divided into different brain region segmentation atlases according to the division principle of brain functional regions.

[0076] See Figure 7 , which is a schematic diagram of a brain region segmentation atlas provided in one of the embodiments. In Figure 7 , the cortex is divided into several functional regions. As shown in the following formula:

[0077] Among them, the formula represents different brain region segmentation atlases L atlas in the brain region segmentation atlas library, and the different brain region segmentation atlases are represented as R1... R k .

[0078] The whole-brain activation atlas is used to characterize the activation of the brain source points corresponding to the neural training target. Different neural training targets correspond to different brain source point activation situations.

[0079] The whole-brain activation atlas represents the activation state map in the whole brain. The association between the activated source points and the neural training target can be queried in the whole-brain activation atlas. For example, when the applied neural training target is to improve attention, then the corresponding activated source point can be queried as source point one in this whole-brain activation atlas. When the neural training target is to overcome sleep disorders, then the corresponding activated source point can be queried as source point two in this whole-brain activation atlas.

[0080] Through the whole-brain activation atlas, the source point data activated in the brain under different neural training targets can be known.

[0081] See Figure 8 , which is a schematic diagram of the whole-brain activation map obtained based on meta-analysis provided in one of the embodiments.

[0082] In Figure 8 , corresponding neurotraining objectives, as well as display parameters, positions, etc. of the brain region activation map can be selected.

[0083] After determining the whole-brain activation map corresponding to the neurotraining objective, it further includes matching the whole-brain activation map with the brain region segmentation map in the brain region segmentation map library, and then obtaining the brain region with the highest activation degree in the brain region segmentation map, and taking the brain region with the highest activation degree as the region of interest of the target user. That is to say, finally, the brain region segmentation map most associated with the training purpose of the target user is obtained. Subsequently, this brain region segmentation map can be used as the region of interest of the target user's current neurotraining. By only focusing on the neurofeedback parameters of this brain region, the neurofeedback training objective of this time can be achieved. And in this process, the brain source point data associated with the neurotraining objective is converted into specific brain regions. The data volume of the source point data will be very large. By converting the source point data into brain regions, data dimensionality reduction is achieved, and the user's attention is focused on a specific region through the brain region, rather than scattered source points. In this way, the neurofeedback intervention effect of the user can also be improved.

[0084] In some embodiments, the whole-brain activation map includes regions composed of one or more activated source points. The regions composed of the source points are matched with the brain region segmentation map, and the brain region with the largest matching degree in the brain region segmentation map is selected as the region of interest of the target user. Specifically, see Figure 8 .

[0085] It should be noted that the activated source points in the whole-brain activation map may be scattered in multiple regions, and the sizes and shapes of the multiple regions are different. By matching one or more activated source points in the whole-brain activation map with the brain region segmentation maps in the brain region segmentation map library, the brain region with the highest activation degree (the brain region corresponding to the brain region segmentation map) can be matched in the brain region segmentation map library based on the principle of maximum matching as the region of interest of the user. Among the selected regions of interest, it is the region with the greatest relevance to the current neurotraining objective and the region with the highest activation degree during the training process.

[0086] In some embodiments, the method further includes: determining the whole-brain activation map corresponding to the neurotraining objective of the target user based on meta-analysis; matching the whole-brain activation map with the brain region segmentation maps in the brain region segmentation map library, obtaining the brain region with the highest activation degree in the brain region segmentation map, and taking the brain region with the highest activation degree as the region of interest of the target user.

[0087] That is to say, the brain regions of interest of the user are determined from the brain segmentation atlas library. The specific determination method is to perform a maximum value matching between the activated source points in the whole-brain activation atlas and the brain segmentation atlas library. The specific formula is as follows:

[0088] Where a j represents the average activation intensity of the j-th brain region; R j represents the j-th brain region, which is composed of several source points in the source space; S i represents the i-th source point in a certain brain region; A F represents the meta-analysis activation atlas obtained from Neurosynth; j* represents the index of the brain region with the strongest activation found among all brain regions.

[0089] In the above-mentioned embodiment, by establishing a brain segmentation atlas library and combining the results of functional magnetic resonance meta-analysis to assist in localization, the most suitable brain functional regions are selected for the specified cognitive function and the user, which has the advantage of providing the best choice for the selection of brain functional regions.

[0090] Performing real-time source localization during the electroencephalogram (EEG) data acquisition process to provide the user with neurofeedback indicators of specific brain functional regions (brain regions of interest) has the advantages of improving the neurofeedback accuracy and being adaptable to different cognitive functions and individuals.

[0091] S104. Based on the EEG data of the brain regions of interest of the target user, determine the characteristic values of the brain regions of interest as the neurofeedback indicators concerned by the user.

[0092] Performing real-time source localization during the EEG data acquisition process to provide the user with the EEG data of specific brain functional regions (brain regions of interest), calculating the characteristic values of the brain regions of interest, and using the characteristic values as the neurofeedback indicators concerned by the user. The user only needs to focus on the neurofeedback indicators of this local brain region of interest to achieve the adjustment and training of the nerves.

[0093] Among them, the characteristic values can be peak values, mean values, etc., which are not limited here.

[0094] In the above-mentioned embodiment, the collected EEG data of the user is converted into the source estimation results in the source space. Considering that the data in the source estimation results in the source space exists in the form of source points, the data volume is large and the brain regions cannot be clearly located. Since nerve movement is associated and linked with specific brain regions, in this application, the brain regions of interest corresponding to the current nerve training target are determined through meta-analysis, and then the source estimation results of the user in the source space are converted into the EEG data of specific brain regions. The user only needs to focus on the data changes in this brain region to achieve the training of neurofeedback.

[0095] In some embodiments, neurofeedback is provided to the user by presenting specific brain activity waveforms for neural adjustment training. These waveforms are rather abstract and not intuitive, making it difficult for the user to directly obtain the state of their own brain activity and also making neural training challenging. In the above embodiments, the waveform is visually represented as a certain feature of the brain region of interest, i.e., the feature of the brain region of interest in this embodiment, and the feature value of interest is calculated as the neurofeedback index that the user needs to focus on. In this way, the user can intuitively know the state of their own brain activity based on the feature value of the region of interest, and then conduct targeted neural training to improve the effect of neural training.

[0096] Electroencephalogram (EEG), as a non-invasive brain function detection technology, has been widely used in the fields of neuroscience, medical diagnosis, and brain-computer interfaces due to its high temporal resolution, low cost, and convenient operation. Neurofeedback, as a special form of biofeedback training, generally calculates various brain activity indicators based on real-time collected EEG signals as control feedback signals. By observing these feedbacks, users can autonomously adjust their cognition and brain activity state to achieve the purpose of cognitive improvement or pathological state intervention. Currently, there are many applications of EEG-based neurofeedback methods, such as interventions for attention deficit hyperactivity disorder, depression, autism, sleep disorders, etc., but there are the following limitations: (1) The feedback localization accuracy is limited. Most neurofeedback systems perform frequency / power feedback based on electrode channels (such as C3, C4, etc.), with poor spatial resolution; (2) The feedback is not specific enough. Neurofeedback usually cannot clearly correspond to specific brain functional areas, making it difficult to further refine the training objectives; (3) The feedback dimension is single, ignoring the spatio-temporal dynamic changes of the neural network of brain activity.

[0097] To address the problem of insufficient spatial resolution of traditional EEG-based neurofeedback methods, in some embodiments, the EEG source localization method can be used to estimate the activity in the brain source space and improve the spatial resolution.

[0098] Brain source localization technology performs mathematical modeling and inversion on multi-channel electroencephalogram (EEG) data by combining the brain structural information obtained from magnetic resonance imaging (MRI), and estimates the neural source activities in the cerebral cortex and even subcortical regions. The core idea of brain source localization technology is that since the EEG signals measured on the limited electrodes on the scalp are affected by the volume conduction effect, the measured EEG signals are only a mixed representation of neural source activities. By constructing a forward model and an inverse solution model, the EEG signals are restored to the neural source activities in a given source space. After source localization, the spatial resolution of the EEG data is improved, and the activity state of specific brain functional areas (such as the lateral occipital cortex, medial occipital cortex, or ventral occipital cortex, etc.) over time can be restored. Neural feedback based on brain source localization can greatly improve the accuracy of neural feedback, adjust it for specific cognitive functions and users, and expand the dimensions of neural feedback metrics.

[0099] In some embodiments, the neural feedback method based on brain source localization includes the following steps: Obtain the head structural image corresponding to the user. When the target user has their own MRI structural image, the user's own MRI structural image is used. If not, the standard brain with the highest similarity in the standard brain library is selected as the standard brain used by the target user.

[0100] Construct a head model. A head model is constructed according to the above-mentioned MRI structural image. Specifically, a three-layer head model can be constructed: a scalp model, an outer skull model, and an inner skull model.

[0101] Construct the brain source space to be estimated. The brain source space to be estimated is constructed according to the above-mentioned MRI structural image.

[0102] Construct a forward model for source localization. Obtain the electrode layout data of the EEG acquisition device, and based on the electrode layout data, the constructed head model, and the constructed brain source space to be estimated, establish a physical relationship model of how the brain source space to be estimated is mapped to the electrode layout data through the head model, that is, construct a forward model for source localization.

[0103] Neurofeedback for collecting EEG data for source localization. The user wears an EEG device or uses a non-contact EEG device to collect the user's EEG data. When the sampling points reach the length of the source localization time window, the EEG data within this time window is obtained. For example, if the designed source localization time window is 0.5 s, source localization is performed every time 0.5 s of EEG data is collected. After obtaining the EEG data within the corresponding time window, the forward model of source localization constructed in advance is used to calculate the brain source space to be estimated corresponding to the EEG data. The brain regions of interest corresponding to the user's current training target are obtained, and the EEG data of interest corresponding to these brain regions of interest is obtained from the brain source space to be estimated, and the eigenvalue corresponding to the EEG data of interest is calculated as an index for neurofeedback. Among them, the steps for determining the brain regions of interest of the target user include determining the whole-brain activation map based on the neurotraining target, matching the obtained whole-brain activation map with the brain region segmentation map in the brain region segmentation map library, and selecting the brain region segmentation map with the highest activation degree as the brain region of interest of the target user.

[0104] In the above embodiments, through the source localization method, the EEG data corresponding to the brain regions of interest associated with the neurotraining target of the target user can be obtained, rather than focusing on the source space data of the entire brain. On the one hand, data dimensionality reduction is achieved, reducing from a relatively large number of source space data points to data of some specific brain regions. And the user only needs to focus on the data of the brain regions of interest, which also has more training pertinence and improves the training efficiency of the user. And during the neurofeedback process, the index value of the EEG data of the brain regions of interest is calculated, and the user only needs to focus on this index value during the neurofeedback training process, and the user can complete the neurotraining independently without having much experience.

[0105] In the above embodiments, considering that the data spatial resolution relied on by the EEG-based neurofeedback technology is limited, resulting in low neurofeedback accuracy, it is impossible to obtain the indicators of specific brain functional areas to support neurofeedback for different cognitive functions and users. To obtain high-spatial-resolution brain imaging data (such as fMRI and fNIRS) for neurofeedback, only the time resolution can be sacrificed, which in turn leads to the inability to capture brain activities occurring within a short time window, and there are also problems such as increased cost and complex experimental environment.

[0106] Therefore, this application proposes a neurofeedback method based on brain source localization, which can obtain the situation of brain nerve source activities on the premise of retaining the time resolution advantage of EEG data and use it for neurofeedback, realizing neurofeedback with relatively high spatial accuracy, and being able to extract different brain functional areas as neurofeedback indicators according to different cognitive functions and users.

[0107] The present application also provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements the steps of the neurofeedback method based on brain power localization provided in any of the above embodiments.

[0108] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the neurofeedback method based on brain power localization provided in any of the above embodiments.

[0109] A computer program product has a program or instruction stored thereon, and when the program or instruction is executed by a processor, it implements the steps of the neurofeedback method based on brain power localization provided in any of the above embodiments.

[0110] In some embodiments, the method further includes monitoring the electroencephalogram (EEG) data of the user through a non-contact EEG device. For example, the target user can be an infant, a vegetative person who cannot control their body, etc. The non-contact EEG acquisition device is not directly worn on the head of the target user, which can make the data acquisition more flexible. And when the head pose of the target user changes, the pose of the corresponding EEG acquisition device can also be adjusted adaptively.

[0111] In this way, for infants who need neurotraining, real-time acquisition of EEG data can also be achieved through non-contact EEG acquisition devices. Furthermore, the EEG data of the brain regions of interest and the corresponding characteristic values can be extracted from the acquired EEG data as the indicators of neurofeedback.

[0112] A non-contact EEG signal acquisition method is adopted. During the EEG signal acquisition process, the EEG electrodes are not directly attached to the scalp, and the EEG signals of the monitored brain regions are accurately monitored by adjusting the poses of the EEG electrodes.

[0113] In some embodiments, the step of monitoring the EEG data of the user through a non-contact EEG device includes: Step 1, obtaining the head image corresponding to the target user at the current moment.

[0114] In some embodiments, the target user may include an infant or other users who need EEG monitoring.

[0115] In some embodiments, the head image at the current moment may be obtained by real-time acquisition through a depth sensor or other image acquisition devices.

[0116] In some embodiments, the image acquisition device can be fixed on a bracket. The position of the bracket is immovable, and the pose of the image acquisition device can be adjusted.

[0117] Step 2, determining the head pose corresponding to the target user at the current moment based on the head image corresponding to the current moment.

[0118] Among them, the pose includes position and orientation.

[0119] In some embodiments, after obtaining the head image of the target user corresponding to the current moment through an image acquisition device, it further includes performing pose analysis on the head image to determine the head position and head orientation of the target user at the current moment.

[0120] Step three, based on the head pose at the current moment and the head pose corresponding to the previous moment, determine the pose of the EEG cap, where the EEG cap includes a plurality of brain electrodes, and the plurality of brain electrodes monitor the EEG data of the target user under the pose corresponding to the EEG cap.

[0121] Among them, the EEG cap is similar to a helmet, and the brain electrodes can be arranged inside the helmet, and each brain electrode can move horizontally and vertically.

[0122] In some embodiments, the previous moment is earlier than the current moment, and the head pose corresponding to the previous moment is the historical head position and orientation calculated based on the head image acquired at the previous moment.

[0123] In some embodiments, the pose of the EEG cap can be determined based on the head pose at the current moment and the previous N historical head poses. The EEG cap includes a plurality of brain electrodes, and the plurality of brain electrodes are used to monitor the EEG data of the target user. N is an integer greater than or equal to 1.

[0124] In some embodiments, the target user may include infants and young children. When collecting the brain data of infants and young children, the heads of infants and young children are easily uncontrollable and prone to movement, so that the relative position between the brain electrodes and the scalp of infants and young children may shift, resulting in unstable signal acquisition positions. Therefore, during the EEG monitoring process, it is necessary to continuously obtain the head images of infants and young children, determine the head position and head orientation of infants and young children at the current moment based on the acquired head image corresponding to the current moment, compare the head pose at the current moment with the historical poses at the previous or multiple previous moments, so as to evaluate the amplitude of the change in the head pose of infants and young children, and then determine whether it is necessary to adjust the position and orientation of the brain electrodes to ensure the accuracy of the EEG data monitoring of infants and young children.

[0125] In the above embodiments, when the target user is a newborn or an infant, in order to avoid irritation and damage to the skin of newborns and infants, a non-contact EEG monitoring method can be used. The non-contact EEG monitoring method makes the EEG cap not directly contact the head of the infant. However, when the head of the infant moves, it is easy to cause the brain electrodes to deviate from the EEG monitoring area, resulting in inaccurate EEG data monitoring.

[0126] The EEG monitoring method provided by this application can calculate the similarity between the current head pose and the previous N historical head poses, so as to determine whether it is necessary to adjust the EEG cap and how to adjust the pose of the EEG cap, ensuring that the EEG electrodes can continuously and accurately monitor the monitored brain area, thereby continuously and stably monitoring the EEG signals of the target user.

[0127] In some embodiments, determining the pose of the EEG cap based on the head pose at the current moment and the head pose corresponding to the previous moment includes: Step 1, determine the distance between the head pose at the current moment and the head pose at the previous moment.

[0128] Step 2, in response to the distance being greater than a preset threshold, adjust the current pose of the EEG cap based on the head pose at the current moment, and the EEG electrodes in the EEG cap continue to monitor the EEG data of the target user in the adjusted pose.

[0129] Step 3, in response to the distance not being greater than the preset threshold, the EEG electrodes in the EEG cap continue to monitor the EEG data of the target user in the current pose.

[0130] In some embodiments, the pose of the EEG cap can be determined based on the head pose at the current moment and the previous N historical head poses, including: determining the distance between the head pose at the current moment and the previous N head poses. Based on the distance being greater than the preset threshold, it indicates that the head pose of the target user has changed significantly, and it is necessary to synchronously adjust the pose of the EEG cap. Therefore, the pose of the EEG cap can be adjusted based on the head pose at the current moment, and the head EEG data monitoring of the target user continues based on the adjusted pose of the EEG cap, so that the pose of the EEG cap is always consistent with the head pose of the target user.

[0131] In the above embodiments, electroencephalogram (EEG) monitoring is performed on a specific area of the target user's head through the EEG electrodes in the EEG cap. A deviation threshold of the EEG electrodes is preset, and the distance between the head pose at the current moment and the previous N head poses at the previous moment is calculated in real time. If the distance is greater than the preset threshold, the pose of the EEG cap is adjusted according to the previous pose, so that the EEG electrodes in the EEG cap can continuously and accurately monitor the specific area of the target user's head. If the distance is less than or equal to the preset threshold, it indicates that the pose of the target user is the same or basically the same between the current moment and the previous moment. At the current moment, there is no need to adjust the pose of the EEG cap or the EEG electrodes. Therefore, EEG monitoring can be continued based on the pose of the EEG cap at the previous moment at the current moment. At the next moment, the head pose of the target user can be obtained through the sensor again, and the distance between the head pose at the current moment and the previous N head poses is determined again, and the size of the distance at this time and the preset threshold is judged, and the determination result decides whether to adjust the EEG cap pose.

[0132] It can be understood that the EEG electrodes are arranged in the EEG cap, and adjusting the pose of the EEG cap also realizes the adjustment of the pose of the EEG electrodes.

[0133] In some embodiments, adjusting the current pose of the EEG cap based on the head pose at the current moment includes: using the head pose of the target user at the current moment as the control target of the robotic arm, and the robotic arm controls and adjusts the current position and current direction of the EEG cap, so that the EEG cap moves to a pose that matches the head position and head direction of the target user at the current moment, and the EEG electrodes in the EEG cap collect the EEG data of the target user at the adjusted pose.

[0134] Specifically, the EEG cap can be arranged at the end of the robotic arm, and the pose of the EEG cap is controlled by the robotic arm. When it is detected that the head pose of the target user changes greatly at the current moment, the pose of the EEG cap is synchronously adjusted by the robotic arm, so that the pose of the EEG cap can match the head pose of the target user at the current moment, and the head EEG data of the target user can be continuously and accurately detected.

[0135] In some embodiments, the determining step of the head pose of the target user includes: determining the coordinate set of the head edge points of the target user based on the head image; determining the head pose of the target user based on the coordinate set of the head edge points.

[0136] In some embodiments, the acquired head image can be segmented based on an image segmentation algorithm to remove irrelevant information and obtain a target image. Then, edge detection is performed on the target image through an edge detection algorithm to obtain the coordinate set of the edge points of the head image, and the head pose of the target user is determined based on the coordinate set of the head edge points.

[0137] It can be understood that the edge detection algorithm and the image segmentation algorithm can be existing mature algorithms, which are not limited herein.

[0138] In some embodiments, the method further includes: determining the head size of the target user based on the head image of the target user; determining the scaling coefficient of the EEG cap and the layout scaling coefficient of the brain electrodes in the EEG cap based on the head size of the target user; adjusting the size of the EEG cap based on the scaling coefficient, and adjusting the coordinate position layout of the brain electrodes in the EEG cap based on the layout scaling coefficient.

[0139] It can be understood that the head sizes of different target users are different, so the size requirements for the EEG caps of different target users are also different. It is very important to set an EEG cap that matches the head size of the corresponding target user, which is the basic condition for obtaining accurate monitoring data.

[0140] In some embodiments, it further includes determining the head size of the target user based on the head image of the target user, and then adjusting the size of the EEG cap adaptively based on the head size of the target user, so that the size of the EEG cap matches the head size of the target user.

[0141] The brain electrodes are arranged in the EEG cap, and the positions of the brain electrodes in the EEG cap can change. When the size of the EEG cap changes, the positions of the brain electrodes in the EEG cap will also change adaptively.

[0142] In some embodiments, the relative positional relationship of the brain electrodes in the EEG cap is fixed. The initial layout coordinates of the brain electrodes in the EEG cap can be obtained first, and the distance between the brain electrodes can be scaled based on the scaling coefficient of the EEG cap to obtain the target coordinates of the brain electrodes.

[0143] In this way, the head size of the target user is determined based on the head image of the target user, and then the size of the EEG cap and the positions of the brain electrodes in the EEG cap are adjusted adaptively, so that the finally adjusted EEG cap and brain electrodes match the target user, in order to monitor more accurate brain data.

[0144] In some embodiments, the head size of the target user includes the head transverse size and the head longitudinal size; The step of determining the head size of the target user includes: determining the ear key points, nose key points, and head key points of the target user based on the head image, where the ear key points include the left ear key point and the right ear key point; determining the head transverse size of the target user based on the ear key points and the head key points; determining the head longitudinal size of the target user based on the nose key points and the head key points.

[0145] In some embodiments, the head size can be determined based on head key points. For example, after obtaining a head image based on a sensor, a trained key point detection model is used to output the coordinates of the head key point, nose key point, left ear key point, and right ear key point.

[0146] By using the coordinates of the left ear key point and the right ear key point and the coordinates of the head edge point set, a head top curve fitting is performed, and the curve length is calculated as the head transverse size.

[0147] By calculating the distance between the nose key point and the midpoint of the head top curve along the head surface, and multiplying by 2, the head longitudinal size can be obtained.

[0148] Determine the head size of the target user based on the head transverse size and head longitudinal size of the target user, so as to determine the size of the EEG cap and the coordinate arrangement of the EEG electrodes according to the head size.

[0149] In some embodiments, the method further includes obtaining a head image of the target user based on a depth sensor; The step of determining the shooting pose of the depth sensor includes: obtaining a working plane image corresponding to the working plane and the plane normal vector corresponding to the working plane based on the depth sensor, where the working plane includes the plane corresponding to the working platform for monitoring the EEG data of the target user; determining the shooting position and shooting direction of the depth sensor based on the on-site observation distance, the working distance of the depth sensor, and the plane normal vector.

[0150] In some embodiments, a head image of the target user can be captured by a depth sensor, and then the head pose and head size of the target user can be calculated from the head image.

[0151] In some embodiments, the pose setting of the sensor is very important. If the pose setting of the sensor is unreasonable, accurate head pose and head size data cannot be obtained from the captured head image, which may lead to unreasonable EEG electrode monitoring poses and inaccurate brain data.

[0152] In some embodiments, it further includes setting the shooting pose of the sensor. First, a working plane image corresponding to the working plane is collected by the sensor, and the shooting pose of the sensor is determined based on the working plane image.

[0153] In some embodiments, after obtaining the working plane image corresponding to the working plane, the method further includes: extracting a plurality of internal coordinate point sets from the working plane image based on a preset marking template; converting the coordinate systems of the plurality of internal coordinate point sets into a world coordinate system, and determining the plane normal vector corresponding to the working plane based on the internal coordinate point sets in the world coordinate system.

[0154] Specifically, the target user to be examined lies flat on the working platform. The RGBD sensor takes a photo of the working platform to obtain a working plane image. Using a 2D edge detection / image segmentation algorithm and combining with a marker template of known shape and size, the internal point coordinates of n markers on the working plane and the corresponding depth information are obtained. In some embodiments, the coordinates of these points can be recorded as C_POINTS (camera_set_1, camera_set_2, …, camera_set_n). Then, the external parameters are used to convert the 3D coordinates in the camera coordinate system to the world coordinate system of the bracket base W_POINTS (world_set_1, world_set_2, …, world_set_n).

[0155] Using the coordinate information of all points in W_POINTS, plane fitting is performed to obtain the plane normal vector N = [nx, ny, nz]. According to the working distance and field of view of the sensor, the optimal observation distance d is set. The center position P_c = [x_c, y_c, d_c] of the working plane is calculated based on the marker point set. Then the sensor shooting position can be P1 = P_c + N * d, and the direction is perpendicular to the working plane where the working platform is located. Furthermore, based on the determined position and direction, the target pose of the sensor is determined, and the manipulator is used to adjust the sensor to this target pose to obtain the head data of the target user.

[0156] The present application also provides a non-contact electroencephalogram monitoring system, which includes: a bracket module, a manipulator module, an image acquisition module, a working platform module, an electroencephalogram cap module, and a control module; the image acquisition module is installed on the bracket module and is used to acquire the head image of the target user and / or the working platform image corresponding to the working platform module; the electroencephalogram cap module is installed at the end of the manipulator, the manipulator is used to adjust the pose of the electroencephalogram cap, and the electroencephalogram electrodes in the electroencephalogram cap are used to monitor the electroencephalogram data of the target user; the working platform module is used to carry the target user; the control module is used to control the manipulator to adjust the pose of the electroencephalogram cap based on the head pose of the target user, and the electroencephalogram electrodes in the electroencephalogram cap are used to monitor the electroencephalogram data of the target user.

[0157] As Figure 10 shown, it is a schematic diagram of the modules of the neurofeedback device based on brain source localization provided in the embodiments of the present application.

[0158] A neurofeedback device 1000 based on brain source localization, the device includes: An acquisition module 1001, configured to acquire the electroencephalogram data of the target user; A source estimation determination module 1002, configured to determine a source estimation result of a source space based on the EEG data of the target user; An interested brain region determination module 1003, configured to determine an interested brain region of the target user, and determine interested EEG data corresponding to the interested brain region of the target user based on the source estimation result of the source space and the interested brain region of the target user, where the interested brain region is associated with the neural training objective of the target user; A neurofeedback module 1004, configured to determine a feature value of the interested brain region based on the interested EEG data of the target user, and use the interested brain region EEG data and the corresponding feature value as a neurofeedback index concerned by the target user.

[0159] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0160] In one embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0161] The present application further provides a computer program product, including a computer program or instruction, and when the computer program or instruction is executed by a processor, the steps of the method provided in any one of the above embodiments are implemented.

[0162] Those skilled in the art can understand that Figure 11 the structure shown in

[0163] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0164] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0165] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A neurofeedback method based on brain power source localization, characterized in that The method includes: Obtaining the electroencephalogram (EEG) data of the target user; Based on the EEG data of the target user, determining the source estimation result in the source space; Determining the brain regions of interest of the target user, and based on the source estimation result in the source space and the brain regions of interest of the target user, determining the EEG data of interest corresponding to the brain regions of interest of the target user, wherein the brain regions of interest are associated with the neurotraining objectives of the target user; Based on the EEG data of interest of the target user, determining the eigenvalue of the brain regions of interest, and taking the EEG data of the brain regions of interest and the corresponding eigenvalue as the neurofeedback indicators concerned by the target user.

2. The method according to claim 1, wherein The determination of the brain regions of interest of the target user includes: Obtaining a brain segmentation atlas library, where the brain segmentation atlas library includes brain segmentation atlases that divide the brain into different regions by one or more principles; Obtaining a whole-brain activation atlas, which is used to characterize the association relationship between the activated brain regions and the neurotraining objectives; Based on the neurotraining objectives of the target user, matching the whole-brain activation atlas with the brain segmentation atlases in the brain segmentation atlas library, obtaining the brain region with the highest activation degree in the brain segmentation atlas, and taking the brain region with the highest activation degree as the brain regions of interest of the target user.

3. The method according to claim 2, wherein The whole-brain activation atlas is used to characterize the activation situation of the brain source points corresponding to the neurotraining objectives, and different neurotraining objectives correspond to different activation situations of the brain source points.

4. The method according to claim 3, characterized in that The method further includes: Based on the neurotraining objectives of the target user, determining the whole-brain activation atlas corresponding to the neurotraining objectives based on meta-analysis; Matching the whole-brain activation atlas with the brain segmentation atlases in the brain segmentation atlas library, obtaining the brain region with the highest activation degree in the brain segmentation atlas, and taking the brain region with the highest activation degree as the brain regions of interest of the target user.

5. The method according to claim 4, characterized in that The whole-brain activation atlas includes a region composed of one or more activated source points, matching the region composed of the source points with the brain segmentation atlas, and selecting the brain region with the largest matching degree in the brain segmentation atlas as the brain regions of interest of the target user.

6. The method according to claim 1, wherein The method further includes: Obtaining the head structural image corresponding to the target user; Based on the head structural image of the target user, constructing the head model of the target user and the brain source space to be estimated; Based on the electrode layout of the EEG acquisition device, the head model of the target user, and the brain source space to be estimated, determining the forward model of source localization; wherein, the forward model of source localization is used to characterize the physical relationship between the brain source space to be estimated mapped to the EEG data through the head model.

7. The method according to claim 6, characterized in that, The determination of the source estimation result in the source space based on the EEG data of the target user includes: Obtaining the EEG data of the target user, solving the EEG data based on the inverse solution model and the forward model of source localization, and determining the source estimation result in the source space corresponding to the EEG data.

8. The method according to claim 6, characterized in that The obtaining step of the head structural image of the target user includes: If the head structure image of the target user itself is queried, the queried head structure image is used as the head structure image of the target user; If the head structure image of the target user itself cannot be queried, the user feature vector of the target user is obtained; The user feature vector of the target user is matched with the standard feature vectors in the standard brain library of head structure images, and the head structure image corresponding to the standard brain with the highest matching degree is used as the head structure image corresponding to the target user.

9. The method according to claim 1, wherein The acquisition of the electroencephalogram data of the target user includes acquiring the electroencephalogram data of the user through a contact electroencephalogram acquisition device or monitoring the electroencephalogram data of the user through a non-contact electroencephalogram device.

10. The method according to claim 9, wherein Monitoring the electroencephalogram data of the user through a non-contact electroencephalogram device includes: Obtaining the head image corresponding to the target user at the current moment; Determining the head pose corresponding to the target user at the current moment based on the head image corresponding to the current moment; Determining the pose of the electroencephalogram cap based on the head pose corresponding to the current moment and the head pose corresponding to the previous moment, wherein a plurality of brain electrodes are included in the electroencephalogram cap, and the plurality of brain electrodes monitor the electroencephalogram data of the target user in the pose corresponding to the electroencephalogram cap.

Images