Method and system for adjusting difficulty of neural feedback task, and terminal

Abstract

Disclosed in the present invention are a method and system for adjusting the difficulty of a neural feedback task, and a terminal. The method comprises: setting a neural feedback task, and collecting and recording, by means of an electroencephalogram (EEG) device, an EEG when a target user executes the neural feedback task; preprocessing the EEG to obtain continuous EEG data, and calculating global field power on the basis of the EEG data; clustering the global field power to obtain a plurality of microstate templates, and performing correlation analysis on the plurality of microstate templates to obtain a specific microstate; and calculating an average duration, an occurrence frequency and a coverage rate of the specific microstate, and adjusting the training difficulty of the neural feedback task on the basis of the average duration, the occurrence frequency and the coverage rate, so as to achieve neural feedback adjustment of the target user. The present invention provides a more flexible and accurate neural feedback adjustment method. A brain region microstate is used to monitor the acceptance degree of a testee so as to adjust the difficulty of a paradigm, and more effective working memory training is provided for the testee in the form of multi-angle test.

Description

A difficulty adjustment method, system and terminal of a neurofeedback task TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a difficulty adjustment method, system, terminal and computer readable storage medium of a neurofeedback task. BACKGROUND

[0002] The principle of neurofeedback is operant conditioning, aiming to train and regulate the brain through brain feedback, has the ability to repair and retrain brain activity, and can be used to control the brain state of patients and healthy people to enhance human cognitive function.

[0003] At present, neurofeedback mainly focuses on feedback training of working memory using theta waves in brain waves. The specific method includes using visual or auditory stimulation to guide subjects to adjust their brain waves to achieve the target set by the experimenter. By monitoring brain wave activity, real-time feedback helps subjects gradually adjust to improve their working memory performance. This method promotes memory capacity by enhancing specific brain wave frequencies.

[0004] However, the above-mentioned scheme has certain limitations, mainly reflected in: poor flexibility: many existing systems mainly rely on a single brain wave frequency band such as alpha wave and beta wave to evaluate the psychological state of the user, and the difficulty of regulating these brain waves is regulated by a unified regulating means, which lacks targeted measures and is difficult to adapt to the large differences in individual acceptance of difficulty. Insufficient monitoring capability: when processing brain feedback signals, existing schemes often only use a single indicator to give feedback, lacking monitoring of the actual acceptance of the subject, resulting in an overall regulation that is not known. Poor task participation: although existing neurofeedback schemes try to actively guide subjects to regulate towards the target direction by reducing the difficulty of the experiment, this means lacks appeal to the subject and is difficult to mobilize the enthusiasm of the subject.

[0005] Therefore, the prior art still needs to be improved and developed.

[0006] SUMMARY

[0007] The main purpose of the present application is to provide a difficulty adjustment method, system, terminal and computer readable storage medium of a neurofeedback task, which aims to solve the problem that the existing technology does not consider the change of brain region microstate and the difference of individual acceptance when designing neurofeedback with hierarchical difficulty, resulting in poor working memory training effect of the subject.

[0008] To achieve the above-mentioned purpose, the present application provides a difficulty adjustment method of a neurofeedback task, which comprises the following steps:

[0009] setting a neurofeedback task, obtaining electroencephalogram (EEG) data of a target user performing the neurofeedback task collected and recorded by an EEG device;

[0010] preprocessing the EEG data to obtain continuous EEG data, and calculating global field power (GFP) from the EEG data;

[0011] clustering the GFP to obtain a plurality of microstate templates, and performing correlation analysis on the plurality of microstate templates to obtain a specific microstate;

[0012] calculating average duration, occurrence frequency and coverage of the specific microstate, and adjusting training difficulty of the neurofeedback task according to the average duration, the occurrence frequency and the coverage to realize neurofeedback adjustment on the target user.

[0013] Optionally, the difficulty adjustment method of the neurofeedback task, wherein the neurofeedback task is a rocket moving program, and the EEG data is brain activation in a target region of interest of the target user performing the rocket moving program.

[0014] wherein the moving speed of the rocket in the rocket moving program is proportional to the adjustment amplitude of theta waves of the target user.

[0015] Optionally, the difficulty adjustment method of the neurofeedback task, wherein the preprocessing the EEG data to obtain continuous EEG data specifically comprises:

[0016] performing signal decomposition on the EEG data by continuous wavelet transform technology to obtain intermediate data;

[0017] performing source signal separation on the intermediate data by independent component analysis technology to obtain continuous EEG data.

[0018] Optionally, the difficulty adjustment method of the neurofeedback task, wherein the calculating GFP from the EEG data specifically comprises:

[0019] calculating GFP(t) from electrode information corresponding to the EEG data:

[0020] wherein t represents time, N represents the number of electrodes, i represents the serial number of the electrode, v i (t) represents the potential of the i-th electrode at time t, represents the average value of the potentials of all electrodes at time t.

[0021] Optionally, the difficulty adjustment method of the neurofeedback task, wherein the global field power is clustered to obtain a plurality of microstate templates, and the plurality of microstate templates are analyzed for correlation to obtain a specific microstate, specifically comprising:

[0022] The electrode positions corresponding to the global field power are clustered using a K-means clustering method:

[0023] wherein J represents clustering, K represents the number of clusters, k represents the ordinal number of the cluster, x i represents the electrode position vector of the i th electrode, μ k represents the centroid of the k th cluster.

[0024] According to the clustering result, a plurality of microstate templates are obtained, and the plurality of microstate templates are analyzed for correlation to obtain a specific microstate A with the largest correlation with the user's working memory.

[0025] Optionally, the difficulty adjustment method of the neurofeedback task, wherein the average duration, occurrence frequency and coverage of the specific microstate are calculated, specifically comprising:

[0026] The average duration Duration A of the specific microstate A is calculated.

[0027] wherein N A represents the number of occurrences of the specific microstate A, j represents the ordinal number of the number of occurrences of the specific microstate, d j represents the duration of the j th occurrence of the specific microstate.

[0028] The occurrence frequency Frequency A of the specific microstate A is calculated.

[0029] wherein T represents the total time.

[0030] The coverage Coverage A of the specific microstate A is calculated.

[0031] wherein T A represents the total duration or the number of total duration segments of the occurrence of the specific microstate A, and T total represents the total duration of all microstates.

[0032] Optionally, the difficulty adjustment method of the neurofeedback task, wherein the training difficulty of the neurofeedback task is adjusted according to the average duration, the occurrence frequency and the coverage, specifically comprising:

[0033] obtaining a self-regulation ability of the target user according to the average duration, the occurrence frequency and the coverage rate;

[0034] if the self-regulation ability is enhanced, reducing the flight acceleration of the rocket in the rocket movement program, and if the self-regulation ability is weakened, increasing the flight acceleration of the rocket in the rocket movement program.

[0035] In addition, to achieve the above object, the present application also provides a difficulty adjustment system of a neurofeedback task, wherein the difficulty adjustment system of the neurofeedback task comprises:

[0036] an electroencephalogram data acquisition module, configured to set a neurofeedback task, and acquire electroencephalogram data of a target user performing the neurofeedback task recorded by an electroencephalogram device;

[0037] a data preprocessing model module, configured to preprocess the electroencephalogram data to obtain continuous electroencephalogram (EEG) data, and calculate global field power according to the EEG data;

[0038] a specific microstate acquisition module, configured to cluster the global field power to obtain a plurality of microstate templates, and perform correlation analysis on the plurality of microstate templates to obtain a specific microstate;

[0039] a training difficulty adjustment module, configured to calculate an average duration, an occurrence frequency and a coverage rate of the specific microstate, and adjust a training difficulty of the neurofeedback task according to the average duration, the occurrence frequency and the coverage rate, so as to realize neurofeedback adjustment on the target user.

[0040] In addition, to achieve the above object, the present application also provides a terminal, wherein the terminal comprises a memory, a processor and a difficulty adjustment program of a neurofeedback task stored in the memory and executable on the processor, and the difficulty adjustment program of the neurofeedback task realizes the steps of the difficulty adjustment method of the neurofeedback task when executed by the processor.

[0041] In addition, to achieve the above object, the present application also provides a computer readable storage medium, wherein the computer readable storage medium stores a difficulty adjustment program of a neurofeedback task, and the difficulty adjustment program of the neurofeedback task realizes the steps of the difficulty adjustment method of the neurofeedback task when executed by a processor.

[0042] In the present application, a neurofeedback task is set, and the brain waves of the target user performing the neurofeedback task are collected and recorded by an electroencephalogram device; the brain waves are preprocessed to obtain continuous EEG data, and the global field power is calculated according to the EEG data; the global field power is clustered to obtain a plurality of microstate templates, the correlation of the plurality of microstate templates is analyzed to obtain a specific microstate; the average duration, occurrence frequency and coverage rate of the specific microstate are calculated, and the training difficulty of the neurofeedback task is adjusted according to the average duration, occurrence frequency and coverage rate, so as to realize the neurofeedback adjustment of the target user. The present application provides a more flexible and accurate neurofeedback adjustment method, which adjusts the difficulty of the paradigm by monitoring the acceptance of the subject by using the brain microstate, and provides more effective working memory training for the subject in the form of multi-angle detection. BRIEF DESCRIPTION OF DRAWINGS

[0043] Fig. 1 is a flowchart of a preferred embodiment of the difficulty adjustment method of the neurofeedback task of the present application;

[0044] Fig. 2 is a visual stimulation diagram of the neurofeedback task in the difficulty adjustment method of the neurofeedback task of the present application;

[0045] Fig. 3 is a neurofeedback system regulation flowchart in the difficulty adjustment method of the neurofeedback task of the present application;

[0046] Fig. 4 is a schematic diagram of the effect of neurofeedback in the difficulty adjustment method of the neurofeedback task of the present application;

[0047] Fig. 5 is a structure diagram of a preferred embodiment of the difficulty adjustment system of the neurofeedback task of the present application;

[0048] Fig. 6 is a schematic diagram of the running environment of a preferred embodiment of the terminal of the present application. DETAILED DESCRIPTION

[0049] The present application provides a difficulty adjustment method of a neurofeedback task and related equipment. In order to make the purpose, technical scheme and effect of the present application more clear and explicit, the present application will be further described in detail below with reference to the drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0050] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as generally understood by those skilled in the art to which the present application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood as having meanings consistent with those in the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as such.

[0051] In addition, if the description of "first", "second" and the like is involved in the embodiments of the present application, the description of "first", "second" and the like is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can be explicitly or implicitly included at least one of the features. In addition, the technical solutions of various embodiments can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, nor in the protection scope required by the present application.

[0052] The difficulty adjustment method of the neural feedback task in the preferred embodiment of the present application is shown in FIG. 1, and the difficulty adjustment method of the neural feedback task comprises the following steps:

[0053] Step S10, setting a neural feedback task, and acquiring and recording the brain waves of a target user when performing the neural feedback task by using an electroencephalogram device.

[0054] In the embodiment, the neural feedback task is a rocket moving program (as shown in FIG. 2), and the brain waves are the brain activation in a target region of interest when the target user performs the rocket moving program.

[0055] Specifically, neural feedback is a spontaneous self-brain regulation, and the subject adjusts by controlling the imagination strategy or brain activity. The neural feedback paradigm of the present application is a rocket moving program and can receive real-time feedback. The feedback content is about the brain activation in the target region of interest when the target user performs the rocket moving program. The moving speed of the rocket in the rocket moving program is proportional to the theta wave regulation amplitude of the target user.

[0056] It should be noted that the visual game stimulation used by the neural feedback system of the present application is not limited here, and other stimulation forms such as hearing, touch, etc. can be used to replace the visual game stimulation according to different situations and scenes.

[0057] Further, in order to enhance the motivation, a score (0-10) will appear on the screen, reflecting the percentage of the distance across the space in each NF (neural feedback), for example, 60% is 6 points. The brain waves of the subject (target user) are recorded during the NF.

[0058] Step S20, pre-processing the brain waves to obtain continuous EEG data, and calculating the global field power according to the EEG data.

[0059] The brain waves are preprocessed to obtain continuous EEG data, specifically including:

[0060] The brain waves are signal-decomposed by a continuous wavelet transform technique to obtain intermediate data, and the intermediate data are source-signal-separated by an independent component analysis technique to obtain continuous EEG data.

[0061] It can be understood that the continuous wavelet transform is used to decompose wavelet signals, and the wavelet is a small time and local oscillation. The Fourier transform decomposes the signal into infinite long sines and cosines, thereby losing all time position information, while the basic function of the continuous wavelet transform is the scaling and shifting version of the time-localized parent wavelet. The independent component analysis is a signal processing technique aiming to separate source signals from linearly mixed signals of multiple source signals. The independent component analysis has wide application fields, including but not limited to speech recognition, image processing, biological signal processing, etc. Its advantages lie in that it can extract useful information from high-dimensional data, reduce noise influence, and be used for dimension reduction to map high-dimensional data to low-dimensional space while retaining important information.

[0062] In this embodiment, the continuous wavelet transform is used to construct a time-frequency representation of the signal. The brain waves are signal-decomposed by a continuous wavelet transform technique to obtain intermediate data that can provide good time and frequency positioning. Further, the intermediate data are source-signal-separated by an independent component analysis technique to effectively extract key information and obtain continuous EEG (Electroencephalogram) data.

[0063] Further, the global field power is calculated according to the EEG data corresponding to the electrode information. The global field power (GFP) is an index for describing the intensity of brain electrical signals, especially in EEG analysis. The GFP measures the global electric field intensity by calculating the standard deviation of electrical activity on all electrodes, reflecting the overall intensity and synchronicity of brain activity.

[0064] The calculation method of the global field power generally involves averaging the square of the potential difference on all electrodes and then taking the square root. This can be achieved by calculating the standard deviation of electrical activity on all electrodes. The global field power GFP(t) is calculated according to the EEG data corresponding to the electrode information, which is represented as:

[0065] where t represents time, N represents the number of electrodes, i represents the ordinal number of the electrode, v i (t) represents the potential of the i-th electrode at time t, represents the average value of the potential of all electrodes at time t.

[0066] Step S30, clustering the global field power to obtain a plurality of microstate templates, and performing correlation analysis on the plurality of microstate templates to obtain a specific microstate.

[0067] Specifically, the calculated values of the GFP of each electrode are different during the electroencephalogram experiment, and the electrode position corresponding to the GFP point represents the spatial distribution thereof, so the electrode positions corresponding to the global field power are clustered using a K-means clustering method (an unsupervised learning algorithm used to divide a data set into several categories, wherein the data points in each category are as similar as possible, and the data points in different categories are as different as possible. This method is based on distance measurement, and the cluster centers are updated iteratively so that the distance between each data point and the cluster center of the category to which it belongs is minimized):

[0068] wherein J represents clustering, K represents the number of clusters, k represents the ordinal number of the cluster, x i represents the electrode position vector of the i th electrode, μ k represents the centroid of the k th cluster.

[0069] Further, a plurality of microstate templates are obtained according to the clustering results, and correlation analysis is performed on the plurality of microstate templates to obtain a specific microstate A having the greatest correlation with the working memory of the user.

[0070] It can be understood that a microstate refers to a stable distribution mode of electroencephalogram, and several microstates can be separated from the same task in an electroencephalogram task. In the present application, the indicators of the microstates are used to detect the participation degree of the subjects, and the average duration, occurrence frequency and coverage rate are used for judgment. Correlation analysis refers to analyzing two or more variable elements having correlation, so as to measure the close degree of the correlation between two variable factors. The elements need to have a certain connection or probability to perform correlation analysis.

[0071] Step S40, calculating the average duration, occurrence frequency and coverage rate of the specific microstate, and adjusting the training difficulty of the neurofeedback task according to the average duration, the occurrence frequency and the coverage rate, so as to realize neurofeedback adjustment on the target user.

[0072] The calculation of the average duration, occurrence frequency and coverage rate of the specific microstate specifically includes:

[0073] The average duration Duration A of the specific microstate A is calculated. wherein N A represents the occurrence frequency of the specific microstate A, j represents the ordinal number of the occurrence frequency of the specific microstate, and d jindicates the duration of the jth occurrence of the specific microstate.

[0074] calculating the frequency of occurrence of the specific microstate A Frequency A : where T indicates the total time.

[0075] calculating the coverage of the specific microstate A Coverage A : where T A indicates the total duration or the total number of duration segments of the occurrence of the specific microstate A, T total indicates the total duration of all microstates.

[0076] Further, the adjusting the training difficulty of the neurofeedback task according to the average duration, the frequency of occurrence and the coverage specifically comprises:

[0077] obtaining the self-regulation ability of the target user according to the average duration, the frequency of occurrence and the coverage;

[0078] if the self-regulation ability is enhanced, the flight acceleration of the rocket in the rocket moving program is reduced, and if the self-regulation ability is weakened, the flight acceleration of the rocket in the rocket moving program is increased.

[0079] In the embodiment, the self-regulation ability of the target user according to the average duration, the frequency of occurrence and the coverage can be set with different weights according to actual conditions, and then added to obtain the self-regulation ability of the target user, and the training difficulty of the neurofeedback is determined according to the self-regulation ability. If the subject's self-regulation is very efficient, that is, the number of microstate occurrences increases, the feedback difficulty increases, and the rocket flight acceleration slows down (for example, 63% is 6 minutes). Only when the subject's theta wave regulation amplitude is larger, the flight speed of the rocket can be accelerated. If the subject's self-regulation effect is not good, that is, the number of microstate occurrences decreases, the feedback difficulty decreases, and the rocket flight speed will be faster, that is, the theta wave regulation amplitude is not so large (for example, 57% is 6 minutes). In this way, stepless neurofeedback regulation is achieved.

[0080] It should be noted that, in order to ensure that the adjustment is working memory, the adjustment amplitude of the theta wave is obtained, and therefore the theta wave is found to be closely related to the memory capacity of a person in cognitive neuroscience, and documents prove that the working memory capacity of the subject can be improved by adjusting the state of the theta wave. Meanwhile, the theta wave brain electrical component related to memory regulated by the present application is used for working memory training, and if other brain cognitive abilities are to be regulated, other brain electrical frequency bands (such as alpha wave, beta wave) can be replaced, and the acceptance monitoring of the corresponding function microstate is received.

[0081] As shown in FIG. 2, it can be understood that several colors of meteors will randomly appear in the process of rocket flight. The subject is required to remember the number of times each color of meteor appears, and answers in the form of filling out a questionnaire after each neurofeedback training is completed.

[0082] Further, as shown in FIG. 3, the entire neurofeedback training process is 8 days. On the first day, the subject is required to complete the working memory task; on the second day to the sixth day, the subject is required to complete the visual neurofeedback training task of the day, and the subject is informed to try to make the rocket move faster (the speed of the rocket is controlled by the subject, which is determined by the subject by imagining the theta wave amplitude) and farther, but does not guide the subject to specific psychological strategies. Each training lasts for 5 minutes, and there is a 2-minute rest time after each training, and the training is ended after the preset training time, and the subject's brain electrical microstate is analyzed at the same time to adjust the difficulty of the neurofeedback paradigm. On the seventh day, the subject is required to complete the same working memory task again. After the target user completes the entire neurofeedback training process, the working memory capacity of the target user will be enhanced (as shown in FIG. 4).

[0083] Further, the present application has collected the experimental conditions of 5 subjects, and through statistical significance test, it can be found that the subject's theta wave phase synchronization index related to working memory is obviously improved after completing the pre-test-neurofeedback-post-test, and therefore it is determined that the experiment is feasible for subsequent neurofeedback regulation of haptic memory brain electrical signals.

[0084] The present application monitors the number of times of the working memory brain electrical microstate and the coverage frequency as the basis for changing the difficulty of the neurofeedback system, and adjusts the difficulty of the neurofeedback steplessly with variable difficulty adjustment parameters; breaks the limitation of the existing neurofeedback difficulty template, and introduces a personalized difficulty adjustment system that changes the difficulty according to the acceptance of the subject. This not only greatly increases the participation of the subject and the motivation of the subject, but also enables the neurofeedback system to more comprehensively monitor the functional state of the subject to make the intervention more accurate and effective.

[0085] The beneficial effects of the present application are:

[0086] (1) Improve the difficulty of the experiment setting flexibility: by analyzing the correlation between the regulation difficulty and the acceptance of the subjects, the present application aims to provide a variable difficulty coefficient, so that the regulation difficulty is not limited to a fixed framework, but is adjusted in real time according to the acceptance of the subjects.

[0087] (2) Enhance the monitoring ability: the present application is committed to real-time monitoring and analysis of the brain electrical signals, using the real-time change of the beta wave change to give the subjects feedback signals, using the brain area microstate to monitor the acceptance of the subjects to adjust the difficulty of the paradigm, and providing more effective working memory training and rehabilitation treatment for the subjects in the form of multi-angle detection.

[0088] (3) Improve the participation of the subjects in the task: the present application uses a more interesting and higher participation computer game as the experimental paradigm of the neural feedback of the subjects, increases the participation and motivation of the subjects.

[0089] It can be seen that the present application sets a neural feedback task, acquires the brain waves of a target user performing the neural feedback task recorded by an electroencephalogram device, pre-processes the brain waves to obtain continuous EEG data, calculates global field power according to the EEG data, clusters the global field power to obtain a plurality of microstate templates, analyzes the correlation of the plurality of microstate templates to obtain a specific microstate, calculates the average duration, occurrence frequency and coverage rate of the specific microstate, and adjusts the training difficulty of the neural feedback task according to the average duration, occurrence frequency and coverage rate, so as to realize the neural feedback regulation of the target user. A more flexible and accurate neural feedback regulation method is provided, the brain area microstate is used to monitor the acceptance of the subjects to adjust the difficulty of the paradigm, and the subjects are provided with more effective working memory training in the form of multi-angle detection.

[0090] Further, as shown in FIG. 5, based on the difficulty adjustment method of the neural feedback task, the present application also correspondingly provides a difficulty adjustment system of a neural feedback task, wherein the difficulty adjustment system of the neural feedback task comprises:

[0091] An electroencephalogram data acquisition module 41 is configured to set a neural feedback task, acquire the brain waves of a target user performing the neural feedback task recorded by an electroencephalogram device;

[0092] A data pre-processing model module 42 is configured to pre-process the brain waves to obtain continuous EEG data, and calculate global field power according to the EEG data;

[0093] A specific microstate acquisition module 43 is configured to cluster the global field power to obtain a plurality of microstate templates, analyze the correlation of the plurality of microstate templates to obtain a specific microstate;

[0094] The training difficulty adjustment module 44 is configured to calculate the average duration, the frequency of occurrence and the coverage of the specific microstate, and adjust the training difficulty of the neurofeedback task according to the average duration, the frequency of occurrence and the coverage, so as to achieve the adjustment of the neurofeedback to the target user.

[0095] Further, as shown in FIG. 6, based on the above-mentioned neurofeedback task difficulty adjustment method and system, the present application also correspondingly provides a terminal, which comprises a processor 10, a memory 20 and a display 30. FIG. 6 only shows part of the components of the terminal, but it should be understood that all the components shown are not required to be implemented, and more or less components can be alternatively implemented.

[0096] The memory 20 can be an internal storage unit of the terminal in some embodiments, such as a hard disk or a memory of the terminal. The memory 20 can also be an external storage device of the terminal in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 20 can include both the internal storage unit and the external storage device of the terminal. The memory 20 is configured to store application software and various data installed on the terminal, such as program codes of the terminal, etc. The memory 20 can also be configured to temporarily store data that has been output or will be output. In an embodiment, the memory 20 stores the neurofeedback task difficulty adjustment program 40, which can be executed by the processor 10, so as to implement the neurofeedback task difficulty adjustment method of the present application.

[0097] The processor 10 can be a central processing unit (CPU), a microprocessor or other data processing chip in some embodiments, which is configured to run program codes or process data stored in the memory 20, such as to execute the neurofeedback task difficulty adjustment method, etc.

[0098] The display 30 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. in some embodiments. The display 30 is configured to display information of the terminal and to display a visualized user interface. The components 10-30 of the terminal communicate with each other through a system bus.

[0099] In an embodiment, the following steps are implemented when the processor 10 executes the difficulty adjustment program 40 of the neurofeedback task in the memory 20:

[0100] Setting a neurofeedback task, obtaining the brain waves of a target user performing the neurofeedback task recorded by a brain electrical device;

[0101] Pretreating the brain waves to obtain continuous EEG data, and calculating global field power from the EEG data;

[0102] Clustering the global field power to obtain a plurality of microstate templates, and performing correlation analysis on the plurality of microstate templates to obtain a specific microstate;

[0103] Calculating the average duration, occurrence frequency and coverage rate of the specific microstate, and adjusting the training difficulty of the neurofeedback task according to the average duration, the occurrence frequency and the coverage rate to achieve neurofeedback adjustment on the target user.

[0104] Among them, the neurofeedback task is a rocket moving program, and the brain waves are the brain activation of the target user performing the rocket moving program in the target region of interest;

[0105] Among them, the moving speed of the rocket in the rocket moving program in space is proportional to the adjustment amplitude of the theta wave of the target user.

[0106] Among them, the pretreatment of the brain waves to obtain continuous EEG data specifically includes:

[0107] Signal decomposition of the brain waves is performed through continuous wavelet transform technology to obtain intermediate data;

[0108] Source signal separation of the intermediate data is performed through independent component analysis technology to obtain continuous EEG data.

[0109] Among them, the calculation of the global field power from the EEG data specifically includes:

[0110] The global field power GFP(t) is calculated according to the EEG data corresponding electrode information:

[0111] Among them, t represents time, N represents the number of electrodes, i represents the serial number of the electrode, v i (t) represents the potential of the i-th electrode at time t, represents the average value of the potentials of all electrodes at time t.

[0112] The global field power is clustered to obtain a plurality of micro-state templates, and the plurality of micro-state templates are analyzed for correlation to obtain a specific micro-state, specifically comprising:

[0113] The electrode positions corresponding to the global field power are clustered using a K-means clustering method:

[0114] Wherein J represents clustering, K represents the number of clusters, k represents the ordinal number of the cluster, x i represents the electrode position vector of the i-th electrode, μ k represents the centroid of the k-th cluster.

[0115] According to the clustering result, a plurality of micro-state templates are obtained, and the plurality of micro-state templates are analyzed for correlation to obtain a specific micro-state A related to the working memory of the user.

[0116] The average duration, occurrence frequency and coverage of the specific micro-state are calculated, specifically comprising:

[0117] The average duration Duration A of the specific micro-state A is calculated.

[0118] Wherein N A represents the number of occurrences of the specific micro-state A, j represents the ordinal number of the occurrence of the specific micro-state, d j represents the duration of the j-th occurrence of the specific micro-state.

[0119] The occurrence frequency Frequency A of the specific micro-state A is calculated.

[0120] Wherein T represents the total time.

[0121] The coverage Coverage A of the specific micro-state A is calculated.

[0122] Wherein T A represents the total duration or the number of total duration segments of the occurrence of the specific micro-state A, and T total represents the total duration of all micro-states.

[0123] The training difficulty of the neural feedback task is adjusted according to the average duration, the occurrence frequency and the coverage, specifically comprising:

[0124] The self-regulation ability of the target user is obtained according to the average duration, the occurrence frequency and the coverage.

[0125] If the self-regulation ability is enhanced, the flight acceleration of the rocket in the rocket movement program is reduced, and if the self-regulation ability is weakened, the flight acceleration of the rocket in the rocket movement program is increased.

[0126] To sum up, the present application provides a difficulty adjustment method and system of a neurofeedback task, and a terminal, the method comprising: setting a neurofeedback task, collecting and recording the brain waves of a target user performing the neurofeedback task through an electroencephalogram device; preprocessing the brain waves to obtain continuous EEG data, and calculating the global field power according to the EEG data; clustering the global field power to obtain a plurality of microstate templates, and performing correlation analysis on the plurality of microstate templates to obtain a specific microstate; calculating the average duration, occurrence frequency and coverage rate of the specific microstate, and adjusting the training difficulty of the neurofeedback task according to the average duration, occurrence frequency and coverage rate, so as to realize the neurofeedback adjustment of the target user. The present application provides a more flexible and accurate neurofeedback adjustment method, which adjusts the difficulty of the paradigm by monitoring the acceptance of the subject through the brain microstate, and provides more effective working memory training for the subject in the form of multi-angle detection.

[0127] It should be noted that in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, method, article or terminal including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or terminal. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or terminal including the element.

[0128] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the computer program can include the processes of the above-mentioned embodiments of the method. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0129] It should be understood that the application is not limited to the above examples, and those skilled in the art can make improvements or changes according to the above description, and all these improvements and changes shall fall within the protection scope of the appended claims of the present application.

Claims

1. A method for adjusting difficulty of a neurofeedback task, the method comprising: determining a difficulty level of a neurofeedback task; and adjusting the difficulty level of the neurofeedback task based on a user's performance on the neurofeedback task. The difficulty adjustment method of the neurofeedback task comprises: setting a neurofeedback task, obtaining electroencephalogram (EEG) of a target user performing the neurofeedback task recorded by an EEG device; preprocessing the EEG to obtain continuous EEG data, and calculating global field power (GFP) from the EEG data; clustering the GFP to obtain a plurality of microstate templates, and performing correlation analysis on the plurality of microstate templates to obtain a specific microstate; calculating average duration, occurrence frequency and coverage rate of the specific microstate, and adjusting training difficulty of the neurofeedback task according to the average duration, the occurrence frequency and the coverage rate to achieve neurofeedback adjustment of the target user.

2. The method of claim 1, wherein, The neurofeedback task is a rocket movement program, and the EEG is brain activation of the target user in a target region of interest when performing the rocket movement program; wherein the movement speed of the rocket in the rocket movement program is proportional to the adjustment amplitude of theta waves of the target user.

3. The method of claim 1, wherein the difficulty of the neurofeedback task is adjusted based on the determined level of engagement. The preprocessing of the EEG to obtain continuous EEG data specifically comprises: performing signal decomposition on the EEG by continuous wavelet transform to obtain intermediate data; performing source signal separation on the intermediate data by independent component analysis to obtain continuous EEG data.

4. The method of claim 1, wherein the difficulty of the neurofeedback task is adjusted based on the determined level of attention. The calculation of GFP from the EEG data specifically comprises: A global field power GFP(t) is computed from the EEG data corresponding electrode information: where t denotes time, N denotes the number of electrodes, i denotes the ordinal number of the electrode, v i (t) denotes the i the potential of the electrode at time t, representing the average value of potentials of all electrodes at time t.

5. The method of claim 4, wherein, The clustering of the GFP to obtain a plurality of microstate templates, and the correlation analysis on the plurality of microstate templates to obtain a specific microstate specifically comprise: using a K-means clustering method to cluster the electrode positions corresponding to the global field power: where J denotes the clustering, K denotes the number of clusters, k denotes the ordinal number of the cluster, x i denotes the electrode position vector of the i-th electrode, μ k denotes the centroid of the k-th cluster; obtaining a plurality of microstate templates according to the clustering results, and performing correlation analysis on the plurality of microstate templates to obtain a specific microstate A with the largest correlation with working memory of the user.

6. The method of claim 5, wherein the difficulty of the neurofeedback task is adjusted based on the determined level of engagement. The calculation of average duration, occurrence frequency and coverage rate of the specific microstate specifically comprises: calculating the average duration Duration of the specific microstate A A : where N A denotes the number of occurrences of a particular microstate A, j denotes the ordinal number of the occurrence of the particular microstate, d i denotes the duration of the jth occurrence of the particular microstate; calculating the frequency of occurrence Frequency of the particular microstate A A : wherein T represents total time. calculating a coverage of the particular microstate A A : where T A represents the total time length or the total number of time length segments of the occurrence of the specific microstate A, T total represents the total time length of all microstates.

7. The method of claim 2, wherein the difficulty of the neurofeedback task is adjusted based on the determined level of engagement. The adjustment of training difficulty of the neurofeedback task according to the average duration, the occurrence frequency and the coverage rate specifically comprises: obtaining self-regulation ability of the target user according to the average duration, the occurrence frequency and the coverage rate; if the self-regulation ability is enhanced, reducing flight acceleration of the rocket in the rocket movement program, and if the self-regulation ability is weakened, increasing flight acceleration of the rocket in the rocket movement program. The difficulty adjustment system of the neurofeedback task comprises:

8. A difficulty adjustment system for a neurofeedback task, characterized by an EEG data acquisition module for setting a neurofeedback task, and obtaining EEG of a target user performing the neurofeedback task recorded by an EEG device; a data preprocessing model module for preprocessing the EEG to obtain continuous EEG data, and calculating GFP from the EEG data; a specific microstate acquisition module for clustering the GFP to obtain a plurality of microstate templates, and performing correlation analysis on the plurality of microstate templates to obtain a specific microstate; and a difficulty adjustment module for calculating average duration, occurrence frequency and coverage rate of the specific microstate, and adjusting training difficulty of the neurofeedback task according to the average duration, the occurrence frequency and the coverage rate. The training difficulty adjustment module is configured to calculate an average duration, a frequency of occurrence and a coverage rate of the specific microstate, and adjust a training difficulty of the neurofeedback task according to the average duration, the frequency of occurrence and the coverage rate, so as to achieve neurofeedback adjustment on the target user.

9. A terminal, characterized by comprising: The terminal comprises a memory, a processor and a neurofeedback task difficulty adjustment program stored on the memory and executable on the processor, and the neurofeedback task difficulty adjustment program, when executed by the processor, implements the steps of the neurofeedback task difficulty adjustment method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a neurofeedback task difficulty adjustment program, and the neurofeedback task difficulty adjustment program, when executed by a processor, implements the steps of the neurofeedback task difficulty adjustment method according to any one of claims 1-7.

Images