CN114169366B

CN114169366B - Neural feedback training system and method

Info

Publication number: CN114169366B
Application number: CN202111399690.9A
Authority: CN
Inventors: 李小俚; 陈贺; 张昊
Original assignee: Beijing Normal University
Current assignee: Beijing Normal University
Priority date: 2021-11-19
Filing date: 2021-11-19
Publication date: 2023-10-20
Anticipated expiration: 2041-11-19
Also published as: CN114169366A

Abstract

The present disclosure provides a nerve feedback training system and method, the system comprising: and the electroencephalogram signal acquisition device is used for acquiring a first task electroencephalogram signal of the training object. The processing device is used for acquiring a nerve feedback training scheme of the training object, wherein the nerve feedback training scheme comprises a filtering frequency band, an electroencephalogram characteristic index and excitation conditions of the training object for setting brain rhythms; the electroencephalogram characteristic extraction model is used for configuring a training object according to the filtering frequency band and the electroencephalogram characteristic index; the method comprises the steps of inputting a first task brain electrical signal into an electroencephalogram feature extraction model to obtain an index value of an electroencephalogram feature index; and the device is used for acquiring the excitation information and displaying the excitation information to the training object under the condition that the index value meets the excitation condition.

Description

Neural feedback training system and method

Technical Field

The embodiment of the application relates to the technical field of nerve regulation, in particular to a nerve feedback training system and a nerve feedback training method.

Background

The biofeedback training is one type of biofeedback training. The brain activity state, such as brain wave, blood oxygen amount of brain and the like, is monitored in real time, and appropriate sound, image, touch feedback and the like are given to a trainee through the assistance of a computer system, so that a training object changes the brain activity state through subjectively sensing and consciously changing own biological signals, the self-regulation capacity of the brain is enhanced, and the brain function is improved.

The current nerve feedback training system is based on a set of fixed nerve feedback training scheme to train different training objects, and can not train a trainer in a targeted manner, so that the training effect of the nerve feedback training is poor.

Disclosure of Invention

The embodiment of the application aims to provide a nerve feedback training system and a nerve feedback training method, which can solve the problem of poor training effect of nerve feedback training.

In order to solve the technical problems, the application is realized as follows:

in a first aspect, an embodiment of the present application provides a nerve feedback training system, including:

an electroencephalogram signal acquisition device and a processing device; the electroencephalogram signal acquisition device is connected with the processing device;

the electroencephalogram signal acquisition device is used for acquiring a first task electroencephalogram signal of a training object and sending the first task electroencephalogram signal to the processing device; the first task electroencephalogram signal is an electroencephalogram signal when the training object performs a training task;

the processing device is used for acquiring a nerve feedback training scheme of the training object, wherein the nerve feedback training scheme comprises a filtering frequency band of the training object for setting brain rhythms, an electroencephalogram characteristic index for performing nerve feedback training and excitation conditions, and the electroencephalogram characteristic index is used for reflecting brain function states set by the training object; the electroencephalogram feature extraction model is used for configuring the electroencephalogram feature extraction model of the training object according to the filtering frequency band and the electroencephalogram feature index, wherein the electroencephalogram feature extraction model reflects the mapping relation between the electroencephalogram signal of the training object and the index value of the electroencephalogram feature index; the method comprises the steps of inputting the first task electroencephalogram signal into the electroencephalogram feature extraction model to obtain an index value of the electroencephalogram feature index; and the device is used for acquiring excitation information and displaying the excitation information to the training object under the condition that the index value meets the excitation condition.

Optionally, the processing device includes:

the device comprises a scheme design module, a feedback presentation module, an electroencephalogram feature extraction module and a display module;

the scheme design module is used for acquiring the nerve feedback training scheme and sending the nerve feedback training scheme to the feedback presentation module;

the first signal input end of the feedback presentation module is connected with the scheme design module to receive the nerve feedback training scheme, excitation conditions are configured according to the nerve feedback training scheme, and a configuration file of the brain electricity feature extraction model is generated according to the filtering frequency band and the brain electricity feature index; the first signal output end of the feedback presentation module is connected with the electroencephalogram feature extraction module so as to send the configuration file to the electroencephalogram feature extraction module; the second signal input end of the feedback presentation module is connected with the electroencephalogram feature extraction module to receive the index value output by the electroencephalogram feature extraction module, and the second signal output end of the feedback presentation module is connected with the display module; the feedback presentation module is used for judging whether the received index value meets the excitation condition, acquiring the excitation information under the condition that the index value meets the excitation condition, and sending the excitation information to the display module;

The display module is used for displaying the excitation information to the training object;

the electroencephalogram feature extraction module configures the electroencephalogram feature extraction model according to the configuration file under the condition that the configuration file is received; the second signal input end of the electroencephalogram feature extraction module is connected with the electroencephalogram signal acquisition device to receive the first task electroencephalogram signal, and the electroencephalogram feature extraction module is used for inputting the received first task electroencephalogram signal into the electroencephalogram feature extraction model to obtain the index value and sending the index value to the feedback presentation module.

Optionally, the processing device further includes a filtering frequency band acquisition module;

the electroencephalogram signal acquisition device is also used for acquiring a first closed-eye electroencephalogram signal of the training object; the first eye-closing electroencephalogram signal is an electroencephalogram signal obtained in a set time period when the training object keeps an eye-closing state;

the signal input end of the filtering frequency band acquisition module is connected with the electroencephalogram signal acquisition device so as to receive the first closed-eye electroencephalogram signal; the signal output end of the filtering frequency band acquisition module is connected with the scheme design module; the filtering frequency band acquisition module is used for obtaining the individualized alpha peak frequency of the training object according to the first closed-eye electroencephalogram signal; obtaining the filtering frequency band according to the personalized alpha peak frequency, and sending the filtering frequency band to the scheme design module;

The scheme design module is further used for generating the nerve feedback training scheme according to the filtering frequency band, the preset electroencephalogram characteristic index and the excitation condition.

Optionally, the processing device further comprises a training evaluation module;

the signal input end of the training evaluation module is connected with the electroencephalogram feature extraction module to acquire a plurality of index values obtained in the nerve feedback training process and generate a training evaluation report according to the index values; and the signal output end of the training evaluation module is connected with the display module so as to send the training evaluation report to the display module for display.

Optionally, the nerve feedback training scheme further includes a first acquisition channel identifier, where the first acquisition channel identifier is used to mark a planned acquisition channel of the first task electroencephalogram signal; the first task electroencephalogram signal comprises a second acquisition channel identifier, and the second acquisition channel identifier is used for marking an actual acquisition channel of the first task electroencephalogram signal;

the feedback presentation module is further configured to send the first acquisition channel identifier to the electroencephalogram feature extraction module;

The electroencephalogram feature extraction module is further used for detecting whether the first acquisition channel identifier is consistent with the second acquisition channel identifier after receiving the first task electroencephalogram signals; under the condition that the first acquisition channel identification is consistent with the second acquisition channel identification, inputting the electroencephalogram signals of the first task to the electroencephalogram feature extraction model; acquiring prompt information under the condition that the first acquisition channel identifier is inconsistent with the second acquisition channel identifier; and the electroencephalogram feature extraction module is connected with the display module to send the prompt information to the display module for display.

In a second aspect, an embodiment of the present application provides a neural feedback training method, including:

acquiring a nerve feedback training scheme of a training object; the nerve feedback training scheme comprises a filtering frequency band of the training object for setting brain rhythm, and brain electricity characteristic indexes and excitation conditions for performing nerve feedback training; the brain electrical characteristic index is used for reflecting the brain function state set by the training object;

configuring an electroencephalogram characteristic extraction model of the training object according to the filtering frequency band and the electroencephalogram characteristic index; the electroencephalogram characteristic extraction model reflects a mapping relation between the electroencephalogram signal of the training object and the index value of the electroencephalogram characteristic index;

Acquiring a first task brain electrical signal of a training object; the first task electroencephalogram signal is an electroencephalogram signal when the training object performs a training task;

inputting the first task electroencephalogram signal into the electroencephalogram feature extraction model to obtain an index value of the electroencephalogram feature index;

acquiring excitation information under the condition that the index value meets the excitation condition;

and displaying the excitation information to the training object.

Optionally, before the acquiring the biofeedback training scheme, the method further includes:

acquiring a first closed-eye electroencephalogram signal of the training object; the first eye-closing electroencephalogram signal is an electroencephalogram signal obtained in a set time period when the training object keeps an eye-closing state;

obtaining the individuation alpha peak frequency of the training object according to the first closed-eye electroencephalogram signal;

obtaining the filtering frequency band according to the individuation alpha peak frequency;

and acquiring the nerve feedback training scheme according to the filtering frequency band, the preset electroencephalogram characteristic index and the excitation condition.

Optionally, the first closed-eye electroencephalogram signal at least comprises an electroencephalogram signal of an O1 channel and an electroencephalogram signal of an O2 channel; the step of obtaining the individualized alpha peak frequency of the training object according to the first closed-eye electroencephalogram signal comprises the following steps:

Preprocessing the first closed-eye electroencephalogram signal to obtain a second closed-eye electroencephalogram signal;

acquiring an electroencephalogram signal of the O1 channel in the second closed-eye electroencephalogram signal, and taking the alpha peak frequency of the electroencephalogram signal of the O1 channel as a first alpha peak frequency;

acquiring an electroencephalogram signal of the O2 channel in the second closed-eye electroencephalogram signal, and taking the alpha peak frequency of the electroencephalogram signal of the O2 channel as a second alpha peak frequency;

and obtaining the individualized alpha peak frequency of the training object according to the first alpha peak frequency and the second alpha peak frequency.

Optionally, the method further comprises:

acquiring at least two index values;

and generating a training evaluation report according to at least two index values.

the method further comprises the steps of:

Detecting whether the first acquisition channel identifier is consistent with the second acquisition channel identifier;

under the condition that the first acquisition channel identification is consistent with the second acquisition channel identification, inputting the electroencephalogram signals of the first task to the electroencephalogram feature extraction model;

acquiring prompt information under the condition that the first acquisition channel identifier is inconsistent with the second acquisition channel identifier;

and sending the prompt information to a display module for display.

According to the nerve feedback training system provided by the embodiment of the application, the electroencephalogram feature extraction model and the excitation condition can be configured according to the acquired nerve feedback training scheme of the training object, namely, in the nerve feedback training process, the training object is trained based on the electroencephalogram feature extraction model and the excitation condition aiming at the training object, so that the pertinence of training is improved, and the training effect of the nerve feedback training is further improved.

Other features of the present specification and its advantages will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description, serve to explain the principles of the specification.

FIG. 1 is a schematic block diagram of a neurofeedback training system in accordance with one embodiment;

FIG. 2 is a schematic block diagram of a processing device according to one embodiment;

FIG. 3 is a schematic block diagram of a processing device according to another embodiment;

FIG. 4 is a schematic block diagram of a processing device according to yet another embodiment;

fig. 5 is a flow diagram of a neural feedback training method, according to one embodiment.

Detailed Description

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

The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the application, its application, or uses.

Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.

In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.

< System example >

FIG. 1 is a schematic block diagram of a neurofeedback training system according to one embodiment.

As shown in fig. 1, the nerve feedback training system includes an electroencephalogram signal acquisition device 1000 and a processing device 2000. The electroencephalogram signal acquisition apparatus 1000 and the processing apparatus 2000 may be connected via a wired network or a wireless network, and are not particularly limited herein.

In this embodiment, the electroencephalogram signal acquisition apparatus 1000 is configured to perform step S103 to acquire a first task electroencephalogram signal of a training object. For executing step S104, the first task brain electrical signal is sent to the processing device 2000.

In the process of performing the nerve feedback training, a training object is required to execute a set training task. The training task may be set in advance according to the brain function state of the training. For example, in the case where the brain function state of training is the attention state, a visual search task may be selected as the training task.

In this embodiment, during the training task set by the training object, the electroencephalogram signal of the training object is acquired as the first task electroencephalogram signal by the electroencephalogram signal acquisition apparatus 1000.

In one embodiment, the electroencephalogram signal acquisition apparatus 1000 includes a multichannel electroencephalogram acquisition cap. The multichannel brain electrical acquisition cap comprises a plurality of acquisition electrodes so as to acquire brain electrical signals of different brain areas through a plurality of acquisitions.

In this embodiment, the first task brain electrical signal comprises brain electrical signals of a plurality of channels. The electroencephalogram signals of each channel correspond to the electroencephalogram signals of different electroencephalogram regions.

In this embodiment, the electroencephalogram signal acquisition device 1000 may send the acquired electroencephalogram signal of the first task to the processing device 2000 in real time, or may send the electroencephalogram signal of the first task to the processing device 2000 according to a preset frequency, which is not limited herein.

In this embodiment, the processing apparatus 2000 is configured to execute step S101 to obtain a neurofeedback training scheme for a training object. The nerve feedback training scheme comprises a filtering frequency band for setting brain rhythm of a training object, an electroencephalogram characteristic index for performing nerve feedback training and excitation conditions.

Different brain rhythm features reflect different brain functional states. For example, the relative energy of alpha rhythms in an electroencephalogram signal reflects the attentiveness state of an individual, and the higher the relative energy of alpha rhythms, the better the attentiveness state of the corresponding individual.

When training the set brain function state, it is necessary to extract a set brain rhythm corresponding to the set brain function state from the electroencephalogram signal, and an index reflecting the characteristics of the set brain rhythm is used as an electroencephalogram characteristic index for performing nerve feedback training. Because the brain characteristic index can reflect the set brain function state of the training object, the change of the set brain function state of the training object can be obtained by tracking the index value change of the brain characteristic index in the nerve feedback training process. For example, when the brain function state is the attention state and the attention state of the training subject is subjected to the nerve feedback training, an alpha rhythm related to the attention state is extracted from the electroencephalogram signal, and the relative energy of the alpha rhythm reflecting the characteristics of the alpha rhythm is used as an electroencephalogram characteristic index for performing the nerve feedback training.

Different brain rhythms have different frequency ranges, so that the set brain rhythms can be extracted from the brain electrical signals through a filter with a filtering frequency band consistent with the frequency range of the set brain rhythms. For example, the frequency range of the alpha rhythm is 7-14HZ, and the alpha rhythm can be extracted from the electroencephalogram signal through a filter with the filtering frequency range of 7-14 HZ.

In the nerve feedback training process, in order to guide the training object to actively perform the adjustment of setting brain rhythm, excitation conditions are set. And when the index value of the brain electrical characteristic index meets the excitation condition, namely, the set brain function state meets the set requirement, feeding back excitation information to the training object. Thus, the training subjects actively adjust the set brain rhythm to obtain the excitation information, thereby realizing the adjustment of the set brain function state.

The incentive information may be a bonus point that may be accumulated. After training is completed, the training object can exchange the corresponding rewards with the rewards points, and the higher the rewards points, the higher the exchangeable rewards values. In this way, the training subjects will actively adjust and set the brain rhythm in order to obtain higher value rewards, thereby improving the training efficiency of the nerve feedback. The motivational information may be textual information representing a appreciation, such as "very bar-! ". The incentive information may also be image information representing a incentive, for example, a "large task window", and may also be other information representing a incentive, which is not particularly limited herein.

In one embodiment, the excitation conditions include a positive excitation condition and a negative excitation condition, and the corresponding excitation information includes positive excitation information and negative excitation information. Wherein the positive incentive information is information representing rewards, and the negative incentive information is information representing penalties.

In this embodiment, when the index value of the electroencephalogram characteristic index satisfies the positive excitation condition, that is, when the set brain function state satisfies the set requirement, the positive excitation information is displayed to the training subject. When the index value of the electroencephalogram characteristic index satisfies the negative excitation condition, that is, when the set brain function state does not satisfy the set requirement, negative excitation information is displayed to the training object. Thus, in order to acquire positive excitation information and avoid negative excitation information, the training object actively adjusts the set brain rhythm, thereby realizing the adjustment of the set brain function state.

Different brain function states correspond to different training directions, for example, some brain function states need to be improved, some brain function states need to be reduced, and some brain function states need to be maintained within a set range.

In one embodiment, to meet the training direction requirements of different brain function states, the excitation conditions are classified into three types, an ascending excitation condition, a descending excitation condition, and a maintenance excitation condition.

In this embodiment, in the ascending excitation condition, the positive excitation condition is that the index value of the electroencephalogram characteristic index is greater than the set upper limit threshold, and the negative excitation condition is that the index value of the electroencephalogram characteristic index is less than the set lower limit threshold. In the descending excitation condition, the negative excitation condition is that the index value of the electroencephalogram characteristic index is larger than a set upper limit threshold value, and the positive excitation condition is that the index value of the electroencephalogram characteristic index is smaller than a set lower limit threshold value. In the hold excitation condition, the positive excitation condition is that the index value of the electroencephalogram characteristic index is larger than or equal to a set lower limit threshold value and smaller than or equal to a set upper limit threshold value, and the negative excitation condition is that the index value of the electroencephalogram characteristic index is larger than or smaller than the set upper limit threshold value. Wherein the set upper threshold is greater than the set lower threshold.

In this embodiment, the processing device 2000 is further configured to execute step S102, and configure an electroencephalogram feature extraction model of the training object according to the filtering frequency band and the electroencephalogram feature index. The electroencephalogram characteristic extraction model reflects the mapping relation between the electroencephalogram signals of the training object and index values of electroencephalogram characteristic indexes. And step S105 is performed, wherein the first task brain electrical signal is input into the brain electrical characteristic extraction model to obtain an index value of the brain electrical characteristic index. For executing step S106, in the case where the index value satisfies the excitation condition, excitation information is acquired, and the excitation information is displayed to the training object.

In this embodiment, the processing device 2000 may be a mobile phone, a tablet computer, a notebook computer, or a desktop computer, which is not limited herein.

In one embodiment, the processing device 2000, as shown in FIG. 2, includes: a plan design module 2100, a feedback presentation module 2200, an electroencephalogram feature extraction module 2300, and a display module 2400.

In this embodiment, the solution design module 2100 is configured to perform step S201, acquire a biofeedback training solution, perform step S202, and send the biofeedback training solution to the feedback presentation module 2200.

In this embodiment, a first signal input of the feedback presentation module 2200 is coupled to the protocol design module 2100 to receive a neuro feedback training protocol. The feedback presentation module 2200 is configured to execute step S203, when receiving the biofeedback training scheme, to configure excitation conditions according to the biofeedback training scheme; and the step S204 is used for executing the step S, and generating a configuration file of the electroencephalogram feature extraction model according to the filtering frequency band and the electroencephalogram feature index.

In one embodiment, the electroencephalogram feature extraction module is configured with a filtering model and a plurality of index value calculation models. The plurality of index value calculation models may include a brain rhythm relative energy calculation model, a coherence calculation model, a complexity calculation model, and the like, and are not particularly limited herein.

In this embodiment, the electroencephalogram feature extraction module is provided with a perfect data interface, and a new index value calculation model can be added according to specific requirements so as to adapt to the requirements of various nerve feedback training.

In this embodiment, the feedback presentation module 2200 generates a subscription instruction of the corresponding index value calculation model according to the electroencephalogram feature index in the neurofeedback training scheme. For example, when the electroencephalogram feature index obtained by the feedback presentation module 2200 is the alpha-rhythm relative energy, a subscription instruction of an index value calculation model corresponding to the alpha-rhythm relative energy is generated, and when the index value calculation model is subscribed by the subscription instruction, a corresponding index value calculation operation is executed.

In this embodiment, the feedback presentation module 2200 uses the subscription instruction and the filtering frequency band as a configuration file of the electroencephalogram feature extraction model.

In this embodiment, the first signal output end of the feedback presentation module 2200 is connected with the electroencephalogram feature extraction module 2300 to send the configuration file to the electroencephalogram feature extraction module 2300, so as to implement personalized configuration of the electroencephalogram feature extraction model, so that the configured electroencephalogram feature extraction model can perform opposite electroencephalogram feature extraction on the training object.

In this embodiment, the second signal input end of the feedback presentation module 2200 is connected to the electroencephalogram feature extraction module 2300 to receive the index value output by the electroencephalogram feature extraction module 2300, and the second signal output end of the feedback presentation module 2200 is connected to the display module 2400. The feedback presentation module 2200 is configured to determine whether the received index value meets an excitation condition, obtain excitation information when the index value meets the excitation condition, and send the excitation information to the display module.

In this embodiment, the display module 2400 is configured to perform step S211 to display motivational information to a training object. The display module may be a liquid crystal display screen or a touch display screen, and is not particularly limited herein.

In this embodiment, the electroencephalogram feature extraction module 2300 performs step S205 when receiving the configuration file, and configures an electroencephalogram feature extraction model according to the configuration file.

In an embodiment in which the configuration file includes a subscription instruction and a filtering frequency band, the electroencephalogram feature extraction module 2300 sets the filtering frequency band of the filter model according to the filtering frequency band in the configuration file, subscribes to a corresponding index value calculation model according to the subscription instruction, and thus obtains an electroencephalogram feature extraction model for the training object.

In the embodiment, the electroencephalogram feature extraction model can be flexibly configured according to the configuration file, so that the electroencephalogram feature extraction model in the nerve feedback training can accurately extract the index value of the electroencephalogram feature index of the training object, the nerve feedback training based on the index value is more targeted, and the effectiveness of the nerve feedback training is improved.

The second signal input end of the electroencephalogram feature extraction module 2300 is connected with the electroencephalogram signal acquisition device 1000 to receive the electroencephalogram signal of the first task, and the electroencephalogram feature extraction module 2300 is used for executing step S207 to input the electroencephalogram signal of the first task received into the electroencephalogram feature extraction model to obtain an index value. For performing step S208, the index value is sent to the feedback presentation module 2200.

It has been found that the frequency distribution ranges of the set brain rhythms are different between different individuals and different age groups of the same individual, and therefore, the set brain rhythms extracted based on the fixed filter frequency band do not accurately reflect the set brain rhythm characteristics of the training subjects.

In one embodiment, the processing device 2000 as shown in fig. 3, further includes a filter band obtaining module 2500, where the filter band obtaining module 2500 is configured to accurately obtain a filter band of the training object for setting a brain rhythm.

In the distribution of brain rhythms, the alpha rhythm is between a high-frequency rhythm and a low-frequency rhythm, so that most of brain rhythms are divided by adopting the peak frequency of the alpha rhythm to anchor and set the filtering frequency band of the brain rhythm. For example, if the peak frequency of the alpha rhythm is iAPF, the filtering frequency band of the alpha rhythm is 0.8iAPF-1.2 iAPF, the filtering frequency band of the delta rhythm is 1-4Hz, the filtering frequency band of the theta rhythm is 4-0.8*iAPF,low beta, the filtering frequency band of the high beta rhythm is 1.2 x iAPF-2 x iAPF, the filtering frequency band of the gamma rhythm is 2 x iAPF-3 x iAPF, and the filtering frequency band of the gamma rhythm is 3 x iAPF-70Hz.

And because the alpha rhythm is obvious in the eye-closed state, the brain electrical signal of the training object in the eye-closed state can be obtained, and the individualized alpha rhythm peak frequency of the training object is calculated according to the eye-closed brain electrical signal, so that the accuracy of calculating the individualized alpha rhythm peak frequency can be improved, and the accuracy of calculating the filtering frequency band is further improved.

In this embodiment, the first closed-eye brain electrical signal of the training object is acquired by the brain electrical signal acquisition device 1000. The first eye-closing electroencephalogram signal is an electroencephalogram signal obtained in a set time period when a training object keeps an eye-closing state. The set duration may be set in advance according to an application scenario, and for example, the set duration may be 120s.

In this embodiment, the signal input end of the filtering frequency band obtaining module 2500 is connected to the electroencephalogram signal acquisition apparatus 1000 to receive the first closed-eye electroencephalogram signal. The signal output end of the filtering frequency band acquisition module 2500 is connected with the scheme design module 2100. The filtering frequency band obtaining module 2500 is configured to obtain an individualized alpha peak frequency of the training object according to the first closed-eye electroencephalogram signal. And obtaining a filtering frequency band according to the individuation alpha peak frequency. The filtered frequency band is sent to the project design module 2100.

In this embodiment, the solution design module 2100 is further configured to generate the biofeedback training solution according to a filtering frequency band, a preset electroencephalogram characteristic index, and an excitation condition. Wherein, the brain function state according to training sets up the brain electricity characteristic index that is used for training, sets up the excitation condition according to the index value of brain electricity characteristic index before training the training object, so, can be through the individuation nerve feedback training scheme of scheme design module 2100 generation to the training object.

In one embodiment, the processing device 2000 is shown in FIG. 4, and further includes a training evaluation module 2600. The signal input end of the training evaluation module 2600 is connected with the electroencephalogram feature extraction module 2300 to obtain at least two index values of the nerve feedback training process, and generate a training evaluation report according to the at least two index values.

In one embodiment, the training evaluation module 2600 acquires the index value in real time during the biofeedback training process, and generates a training evaluation report according to the rate of change of the index value during the biofeedback training process after the biofeedback training result. For example, in a heightened neurofeedback training, the alpha rhythm relative energy is raised by 10% relative to that before training, and the attention of the training subject is advanced by 10% relative to that before training.

In this embodiment, the signal output of the training evaluation module 2600 is connected to the display module 2400 to send the training evaluation report to the display module 2400 for display.

In the training process, as the training object sets the adjustment of brain function state, the index value of the brain electrical characteristic index also changes. At this time, according to the change condition of the index value in the evaluation result, the excitation condition in the nerve feedback training scheme can be dynamically adjusted, so that the training difficulty is maintained at a proper level, and the effectiveness of the nerve feedback training is improved.

In order to meet the training requirements of different brain function states, multiple electrode channels and reference modes can be arranged in the nerve feedback training scheme. Wherein the binaural electrode (M1/M2) and the Cz channels are fixed, and the other 6 channels can be selected from 16 channels (F3, F4, fz, F7, F8, T3, T4, C3, C4, T5, T6, P3, P4, pz, O1 and O2) in the 10-20 system, wherein 0-6 channels are selected. There are 6 alternatives for the reference mode: cz reference, binaural connection reference, ipsilateral reference, contralateral reference, left ear reference and right ear reference. The combination of the electrode and the reference mode can be selected according to specific training requirements in the design of the nerve feedback scheme.

In one embodiment, the neurofeedback training regimen may further comprise a first acquisition channel identification, the first acquisition channel identification being used to mark a planned acquisition channel of the first task brain electrical signal.

In this embodiment, the planned acquisition channel of the first task brain electrical signal may be set according to a specifically trained brain function state. Each planned acquisition channel has a corresponding acquisition channel identifier. For example, in the neurofeedback training for improving the attention, the planned acquisition channels of the first task electroencephalogram signals may be an A1 channel, an A2 channel, a Cz channel, an F3 channel, an F4 channel, a P3 channel, a P4 channel, an O1 channel and an O2 channel, where A1, A2, cz, F3, F4, P3, P4, O1 and O2 are the first acquisition channel identifiers corresponding to each planned acquisition channel. A1, A2, cz, F3, F4, P3, P4, O1 and O2 are brain region positions corresponding to the acquisition channels, and the brain region positions are calibrated positions in the international 10/20 system.

In this embodiment, the electroencephalogram signal acquisition device 1000 includes a second acquisition channel identifier in acquiring the first task electroencephalogram signal, where the second acquisition channel identifier is used to mark an actual acquisition channel of the first task electroencephalogram signal.

Before performing the nerve feedback training, the actual acquisition channel of the electroencephalogram signal acquisition device 1000 needs to be set according to the planned acquisition channel, but in the setting process of the actual acquisition channel, the situation that the set actual acquisition channel is inconsistent with the planned acquisition channel is unavoidable. Thus, in one embodiment of the application, the processing device 2000 may also be used to perform consistency checks of the acquisition channels.

In this embodiment, the feedback presentation module 2200 is further configured to send the first acquisition channel identifier in the neurofeedback training scenario to the electroencephalogram feature extraction module 2300. The electroencephalogram feature extraction module 2300 detects whether the first acquisition channel identifier is consistent with the second acquisition channel identifier after receiving the electroencephalogram signal of the first task; under the condition that the first acquisition channel identification is consistent with the second acquisition channel identification, the first task brain electrical signal is input to the brain electrical characteristic extraction model. Under the condition that the first acquisition channel identification is inconsistent with the second acquisition channel identification, acquiring prompt information, and sending the prompt information to a display module 2400 connected with the electroencephalogram feature extraction module 2300 for display. Therefore, a worker can change a reference mode, the position of the acquisition electrode and the like according to the prompt information, and the accuracy of the setting of the acquisition channel is ensured.

In one embodiment, the processing device 2000 further includes a data acquisition module.

In this embodiment, the signal input end of the data acquisition module is connected to the signal output end of the electroencephalogram signal acquisition apparatus 1000 to receive an electroencephalogram signal. The signal output end of the data acquisition module is connected with the electroencephalogram feature extraction module 2300 to send the received electroencephalogram signals to the electroencephalogram feature extraction module.

The data acquisition module can draw the data waveform of the brain electrical signal in real time and adjust the display in the process of acquiring the brain electrical data.

The data acquisition module comprises various buttons corresponding to different waveform display modes, can adjust the channel number, amplitude range, display width and the like of waveform display of the electroencephalogram signals according to the requirement of acquired data, and can also select whether to display a reference line or not. The waveform of the brain electrical signal is updated in a rolling coverage mode, and the current position and the moment triggered by the event are marked by red lines.

The data acquisition module supports impedance detection, impedance data of electrodes of the electroencephalogram acquisition device can be displayed on a schematic diagram of scalp positions where the electrodes are located in different colors in the impedance detection process, and in the preparation process of actual data acquisition, experimenters can intuitively see the real-time impedance condition, so that the contact condition of the electrodes and skin can be timely adjusted.

The data acquisition module supports joint synchronous acquisition of video data in addition to receiving the electroencephalogram data transmitted by the electroencephalogram acquisition device 1000. The programming interface provided by an image processing library Accord (https:// gate. Com/Accord-net/frame /) is adopted to support video recording with various resolutions and code rates, and recording and image storage functions in the recording process. In terms of communication between the electroencephalogram acquisition device 1000 and the data set acquisition module, two connection modes of wired and wireless are supported, wherein the wired mode is connected through USB, and the wireless mode is connected through WI-FI. The data acquisition module can support synchronous acquisition of a plurality of electroencephalogram acquisition devices 1000.

In the aspect of brain electricity data storage, the data acquisition module can support data storage of European data format (.edf) file format, EDF plus file format and BDF plus file format, and is not particularly limited herein.

The data acquisition module can cooperate with other systems besides acquisition, display and storage of brain electricity and video data, and meets various data acquisition requirements. Stimulation, such as in ERP research, typically presents synchronization with the electroencephalogram data. The data acquisition module supports two collaboration modes, namely synchronization of external events to electroencephalogram records and forwarding of electroencephalogram data to an external system, and in the first collaboration mode, a certain port is monitored in a program, and the external events are transmitted through the port and synchronized to the electroencephalogram records. In the second cooperation, the acquired brain electricity data is forwarded to the appointed network address and port in real time through the network port, so that the data real-time transmission sharing is realized.

In addition to the acquisition of brain electricity, event recording during the nerve feedback training process is also completed by the data acquisition module. By means of the peripheral cooperation function of the acquisition system, various events are sent to the acquisition module and recorded synchronously with the electroencephalogram data, such as the start and the end of feedback, the selection of a feedback scheme, the variation of tested behaviors and the like, so that subsequent data analysis is facilitated.

In one embodiment, the training evaluation module 2600 may also be connected to the data acquisition module to receive the electroencephalogram data stored by the data acquisition module to generate a training evaluation report from the electroencephalogram data.

< method example >

As shown in fig. 5, the nerve feedback training method of the present embodiment may include steps S505 to S510.

S505, acquiring a nerve feedback training scheme of the training object. The nerve feedback training scheme comprises a filtering frequency band for setting brain rhythm of a training object, an electroencephalogram characteristic index for performing nerve feedback training and excitation conditions; the brain electrical characteristic index is used for reflecting the brain function state set by the training object.

S506, configuring an electroencephalogram feature extraction model of the training object according to the filtering frequency band and the electroencephalogram feature index. The electroencephalogram characteristic extraction model reflects the mapping relation between the electroencephalogram signals of the training object and index values of electroencephalogram characteristic indexes.

S507, acquiring a first task brain electrical signal of the training object. The first task electroencephalogram signal is an electroencephalogram signal when the training object performs a training task.

S508, inputting the electroencephalogram signals of the first task into the electroencephalogram feature extraction model to obtain index values of the electroencephalogram feature indexes.

S509, when the index value satisfies the excitation condition, excitation information is acquired.

S510, displaying excitation information to the training object.

In one embodiment, steps S501-S504 are also included prior to acquiring the biofeedback training regimen.

S501, acquiring a first closed-eye brain electrical signal of a training object. The first eye-closing electroencephalogram signal is an electroencephalogram signal obtained in a set time period when a training object keeps an eye-closing state.

S502, obtaining the individuation alpha peak frequency of the training object according to the first closed-eye electroencephalogram signal.

In one embodiment, the first closed-eye electroencephalogram signal includes at least an electroencephalogram signal of an O1 channel and an electroencephalogram signal of an O2 channel. Step S502 specifically includes S502-1 to 502-5.

S502-1, preprocessing the first closed-eye electroencephalogram signal to obtain a second closed-eye electroencephalogram signal.

In this embodiment, the step of preprocessing the first closed-eye electroencephalogram signal includes S502-1-1 to S502-1-3.

S502-1-1, segmenting the electroencephalogram signals of the channels according to a preset segmentation rule to obtain a plurality of electroencephalogram signal segments corresponding to the channels.

The preset segmentation rule may be as follows: the electroencephalogram signals are divided into electroencephalogram signal fragments with the length of 4s in a 2s overlapping mode. Taking the segmentation of the electroencephalogram signal corresponding to the Cz channel as an example, the first segmentation rule is described as follows: extracting a 0s-4s closed-eye computer signal from the closed-eye electroencephalogram signal corresponding to the Cz channel as an electroencephalogram signal fragment in a first time period; and extracting the closed-eye electroencephalogram signals of the 2s-6s as electroencephalogram signal fragments in the second time period, extracting the closed-eye electroencephalogram signals of the 4s-8s as electroencephalogram signal fragments in the third time period, and the like to obtain a plurality of electroencephalogram signal fragments corresponding to the Cz channel. And segmenting the electroencephalogram signals of other channels according to an electroencephalogram signal segmentation method corresponding to the Cz channel to obtain a plurality of electroencephalogram signal segments corresponding to each channel.

The preset segmentation rules may also be set according to specific requirements, and are not specifically limited herein.

S502-1-2, screening a set number of electroencephalogram fragments with the lowest myoelectricity ratio from a plurality of electroencephalogram fragments corresponding to each channel, and splicing to obtain effective electroencephalograms corresponding to each channel.

The step of obtaining the effective electroencephalogram signal corresponding to the Cz channel comprises the following steps: and carrying out normalization processing on a plurality of electroencephalogram signal fragments corresponding to the Cz channel, and calculating the power spectrum of each electroencephalogram signal fragment after normalization processing. Based on the power spectrum of each electroencephalogram signal segment, the ratio of 40-100Hz energy to 1-100Hz energy is calculated and used as the myoelectricity ratio of each electroencephalogram signal segment. And sequencing according to the myoelectricity proportion of each electroencephalogram signal segment. And screening out the electroencephalogram signal fragments with the lowest myoelectricity occupation ratio and the set number, and splicing to obtain the effective electroencephalogram signal corresponding to the Cz channel.

In this embodiment, the set number may be preset according to specific requirements, for example, the set number may be 40, that is, the 40 electroencephalogram segments with the lowest myoelectricity occupation ratio are screened and spliced, so as to obtain the effective electroencephalogram corresponding to the Cz channel.

And obtaining effective brain electrical signals corresponding to each channel by referring to the Cz channel processing method.

S502-1-3, obtaining a second closed-eye test brain electrical signal based on the effective brain electrical signals corresponding to the channels. Specifically, the effective brain electrical signals corresponding to the channels are combined to obtain a second closed-eye test brain electrical signal.

Alpha rhythms are most pronounced in the occipital region (i.e., O1 and O2 locations). Therefore, the individualized alpha peak frequency can be accurately calculated according to the electroencephalogram signals acquired at the O1 and O2 positions.

S502-2, acquiring an electroencephalogram signal of an O1 channel in the second closed-eye electroencephalogram signal, and taking the alpha peak frequency of the electroencephalogram signal of the O1 channel as a first alpha peak frequency.

S502-3, acquiring an electroencephalogram signal of an O2 channel in the second closed-eye electroencephalogram signal, and taking the alpha peak frequency of the electroencephalogram signal of the O2 channel as a second alpha peak frequency.

S502-4, obtaining the individuation alpha peak frequency of the training object according to the first alpha peak frequency and the second alpha peak frequency.

In this embodiment, the average value of the first alpha peak frequency and the second alpha peak frequency may be used as the individualized alpha peak frequency of the training object, or the weighted average value of the first alpha peak frequency and the second alpha peak frequency may be used as the individualized alpha peak frequency of the training object, which is not particularly limited herein.

S503, obtaining a filtering frequency band according to the individuation alpha peak frequency.

For example, if the calculated individualized alpha peak frequency is iAPF, the filtered frequency of the alpha rhythm may be 0.8iAPF-1.2 iAPF, the filtered frequency of the delta rhythm may be 1-4Hz, the filtered frequency of the theta rhythm may be 1.2 x iAPF-2 x iAPF, the filtered frequency of the high beta rhythm may be 2 x iAPF-3 x iAPF, and the filtered frequency of the gamma rhythm may be 3 x iAPF-70Hz.

S504, acquiring a nerve feedback training scheme according to the filtering frequency band, a preset electroencephalogram characteristic index and excitation conditions.

In one embodiment, the biofeedback training method further includes: acquiring at least two index values of a nerve feedback training process; and generating a training evaluation report according to at least two index values.

In one embodiment, the neurofeedback training protocol further includes a first acquisition channel identification, the first acquisition channel identification being used to mark a planned acquisition channel of the first task brain electrical signal. The first task electroencephalogram signal comprises a second acquisition channel identifier, and the second acquisition channel identifier is used for marking an actual acquisition channel of the first task electroencephalogram signal.

In this embodiment, the nerve feedback training method further includes: and detecting whether the first acquisition channel identifier is consistent with the second acquisition channel identifier. And under the condition that the first acquisition channel identification is consistent with the second acquisition channel identification, inputting the electroencephalogram signals of the first task into the electroencephalogram feature extraction model. Under the condition that the first acquisition channel identification is inconsistent with the second acquisition channel identification, acquiring prompt information, and sending the prompt information to a display module for display.

One or more embodiments of the present description may be a system, method, and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement aspects of the present description.

The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.

Computer program instructions for carrying out operations of embodiments of the present description may be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present description are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information for computer-readable program instructions, which may execute the computer-readable program instructions.

Various aspects of the present description are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present description. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

The embodiments of the present specification have been described above, and the above description is illustrative, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvement in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the application is defined by the appended claims.

Claims

1. A biofeedback training system, comprising:

the processing device is used for acquiring a nerve feedback training scheme of the training object, wherein the nerve feedback training scheme comprises a filtering frequency band of the training object for setting brain rhythms, an electroencephalogram characteristic index for performing nerve feedback training and excitation conditions, and the electroencephalogram characteristic index is used for reflecting brain function states set by the training object; the electroencephalogram feature extraction model is used for generating a configuration file of an electroencephalogram feature extraction model according to the filtering frequency band and the electroencephalogram feature index, and configuring the electroencephalogram feature extraction model of the training object according to the configuration file, wherein the electroencephalogram feature extraction model reflects the mapping relation between the electroencephalogram signal of the training object and the index value of the electroencephalogram feature index; the method comprises the steps of inputting the first task electroencephalogram signal into the electroencephalogram feature extraction model to obtain an index value of the electroencephalogram feature index, wherein the index value of the electroencephalogram feature index is obtained through calculation of an index value calculation model in the electroencephalogram feature extraction model, and the index value calculation model is determined through the electroencephalogram feature index in the nerve feedback training scheme; and the device is used for acquiring excitation information and displaying the excitation information to the training object under the condition that the index value meets the excitation condition so as to guide the training object to carry out adjustment for setting brain function states.

2. The system of claim 1, wherein the processing means comprises:

3. The system of claim 2, wherein the processing means further comprises a filtered band acquisition module;

4. The system of claim 2, wherein the processing device further comprises a training evaluation module;

5. The system of claim 2, wherein the neurofeedback training regimen further comprises a first acquisition channel identification, the first acquisition channel identification being used to mark a planned acquisition channel of the first task brain electrical signal; the first task electroencephalogram signal comprises a second acquisition channel identifier, and the second acquisition channel identifier is used for marking an actual acquisition channel of the first task electroencephalogram signal;

6. A method of biofeedback training, comprising:

generating a configuration file of an electroencephalogram feature extraction model according to the filtering frequency band and the electroencephalogram feature index, and configuring the electroencephalogram feature extraction model of the training object according to the configuration file; wherein the electroencephalogram characteristic extraction model reflects a mapping relation between the electroencephalogram signal of the training object and the index value of the electroencephalogram characteristic index;

inputting the first task electroencephalogram signal into the electroencephalogram feature extraction model to obtain an index value of the electroencephalogram feature index, wherein the index value of the electroencephalogram feature index is obtained through calculation of an index value calculation model in the electroencephalogram feature extraction model, and the index value calculation model is determined through the electroencephalogram feature index in the nerve feedback training scheme;

and displaying the excitation information to the training object so as to guide the training object to adjust the set brain function state.

7. The method of claim 6, further comprising, prior to acquiring the biofeedback training regimen:

8. The method of claim 7, wherein the first closed-eye electroencephalogram signal comprises at least an O1 channel electroencephalogram signal and an O2 channel electroencephalogram signal; the step of obtaining the individualized alpha peak frequency of the training object according to the first closed-eye electroencephalogram signal comprises the following steps:

9. The method of claim 6, wherein the method further comprises:

Acquiring at least two index values;

10. The method of claim 6, wherein the neurofeedback training regimen further comprises a first acquisition channel identification, the first acquisition channel identification being used to mark a planned acquisition channel of the first task brain electrical signal; the first task electroencephalogram signal comprises a second acquisition channel identifier, and the second acquisition channel identifier is used for marking an actual acquisition channel of the first task electroencephalogram signal;

the method further comprises the steps of:

and sending the prompt information to a display module for display.