Brain-controlled training methods, devices, and electronic equipment

Abstract

This invention provides a training method, device, and electronic device for brain regulation, relating to the field of brain activity level regulation technology. The method includes: acquiring signals from a target subject's brain region using a near-infrared light source to obtain neural activity information corresponding to that brain region; extracting specific indicators from the neural activity information to obtain multiple indicator parameters; transmitting the time series corresponding to the multiple indicator parameters to a preset neurofeedback training model, causing the neurofeedback training model to output feedback signals; and regulating the neural activity information corresponding to the brain region based on the feedback signals to regulate the target subject's brain activity level. This application allows the target subject to autonomously regulate its brain activity level based on feedback signals corresponding to signals acquired from a near-infrared light source. This method can fully mobilize and stimulate the target subject's subjective initiative to improve brain activity levels, cognitive and emotional states, and the improvement effect has a relatively long-lasting effect.

Description

Technical Field

[0001] This invention relates to the field of brain activity level regulation technology, and in particular to a brain regulation training method, device, and electronic device. Background Technology

[0002] With the continuous development of neuroscience and technology, neuromodulation therapy, which uses physical methods (such as magnetism, electricity, and light) to alter the function of the central and peripheral nervous systems in patients with depression, has gradually become a technical direction for improving depressive states. As relatively new auxiliary training methods, the two most commonly used neuromodulation techniques in current auxiliary training for depression are repetitive transcranial magnetic stimulation (rTMS) and transcranial direct current stimulation (tDCS).

[0003] However, both techniques still have potential side effects and limitations: First, side effects on peripheral nervous system function. Side effects of repetitive transcranial magnetic stimulation (rTMS) mainly include syncope, facial spasms, pain, and cognitive impairment. Similarly, transcranial electrical stimulation (TCS) may cause problems including skin tingling, photohana, nausea, dizziness, and itching. Second, both rTMS and TCS use externally applied magnetic / electrical stimulation to excite or inhibit corresponding brain regions, thereby promoting healthy brain activity patterns. However, regardless of the method, the trainee is only passively receiving intervention, and the long-term effectiveness of the training is generally low after the treatment course ends, meaning the improvement is not sustainable. Summary of the Invention

[0004] The purpose of this invention is to provide a training method, device, and electronic device for brain regulation, so as to improve the timeliness of brain activity level regulation and improvement, and with fewer side effects.

[0005] In a first aspect, the present invention provides a training method for brain regulation, the method comprising: acquiring signals from a brain region of a target object using a near-infrared light source to obtain neural activity information corresponding to the brain region; extracting specific indicators from the neural activity information to obtain multiple indicator parameters; transmitting the time series corresponding to the multiple indicator parameters to a preset neural feedback training model so that the neural feedback training model outputs a feedback signal; and regulating the neural activity information corresponding to the brain region according to the feedback signal to regulate the brain activity level of the target object.

[0006] In an optional implementation, the aforementioned neural activity information includes sub-activity information corresponding to multiple time points; the specific indicators include oxyhemoglobin concentration and deoxyhemoglobin concentration; the step of extracting specific indicators from the neural activity information to obtain multiple indicator parameters includes: extracting the parameter values ​​of oxyhemoglobin concentration and deoxyhemoglobin concentration of each sub-activity information corresponding to each time point from the sub-activity information corresponding to multiple time points of the neural activity information; and for each time point, determining the parameter value of oxyhemoglobin concentration of each sub-activity information corresponding to the current time point as the indicator parameter corresponding to the current time point.

[0007] In an optional implementation, the above-mentioned multiple indicator parameters include indicator parameters corresponding to each time point in multiple time points; the step of transmitting the time series corresponding to the multiple indicator parameters to a preset neural feedback training model so that the neural feedback model outputs a feedback signal includes: preprocessing the indicator parameters corresponding to each time point to obtain the time series corresponding to each time point; transmitting the time series corresponding to each time point to the neural feedback training model and outputting the feedback signal corresponding to each time point.

[0008] In an optional implementation, the step of preprocessing the indicator parameters corresponding to each time point to obtain the time series corresponding to each time point includes: performing the following operations for each time point: smoothing the indicator parameters corresponding to the current time point based on the moving average method; performing baseline correction on the smoothed indicator parameters according to the baseline signal indicated within a preset threshold time period; and determining the time series corresponding to the current time point based on the baseline-corrected indicator parameters.

[0009] In an optional implementation, after the step of regulating the neural activity information corresponding to the brain region based on the feedback signal to regulate the brain activity level of the target object, the method further includes: obtaining an indication signal corresponding to the feedback signal based on the regulation result; and determining the degree of control over the brain activity level of the target object based on the indication signal corresponding to the feedback signal.

[0010] In an optional implementation, the method further includes: conducting a comprehensive assessment of the target subject based on a preset training time period to obtain assessment results of brain activity after brain activity level regulation, as well as assessment results of emotion and cognition.

[0011] In an optional implementation, the steps of comprehensively evaluating the target object based on a preset training period to obtain the evaluation results of brain activity after brain activity level regulation, as well as the evaluation results of emotion and cognition, include: obtaining evaluation values ​​corresponding to multiple dimensions according to the preset training period; and determining the set of evaluation values ​​corresponding to each dimension as the evaluation results of brain activity after brain activity level regulation, as well as the evaluation results of emotion and cognition.

[0012] Secondly, the present invention provides a brain regulation training device, comprising: a signal acquisition module for acquiring signals from a target object's brain region using a near-infrared light source based on a preset training time period and preset condition signals, thereby obtaining neural activity information corresponding to the brain region; an index parameter determination module for extracting specific indicators from the neural activity information to obtain multiple index parameters; a feedback signal determination module for transmitting the time series corresponding to the multiple index parameters to a preset neural feedback training model, so that the neural feedback model outputs a feedback signal; and a regulation module for regulating the neural activity information corresponding to the brain region according to the feedback signal, thereby regulating the brain activity level of the target object.

[0013] Thirdly, the present invention provides an electronic device including a processor and a memory, the memory storing machine-executable instructions that can be executed by the processor, the processor executing the machine-executable instructions to implement the above-mentioned brain regulation training method.

[0014] Fourthly, the present invention provides a machine-readable storage medium storing machine-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the aforementioned brain-controlled training method.

[0015] The embodiments of the present invention bring the following beneficial effects:

[0016] This invention provides a training method, device, and electronic device for brain regulation. It collects neural activity information from brain regions using a near-infrared light source. Compared to magnetic resonance imaging (MRI), this method causes less stimulation to the target subject, thus minimizing side effects. The invention also provides feedback signals based on the collected neural activity information, enabling the target subject to regulate their brain activity level. Furthermore, it collects neural activity information from the target subject's brain regions in real time to determine their brain activity level. The target subject can not only autonomously regulate neural activity in brain regions in real time but also understand the results of their regulation. This approach can stimulate the target subject's initiative. Moreover, since the improvement in brain activity level is the result of the target subject's own active regulation, it provides a more long-term opportunity for improvement for those lacking motivation.

[0017] Furthermore, the aforementioned near-infrared light source corresponds to fNIRS technology, which can accurately receive and transmit signals from various brain regions. Additionally, this fNIRS technology involves training the target subject by wearing a near-infrared light cap; therefore, the acquisition results are less affected by the target subject's body movements, making it more convenient and comfortable to operate. Moreover, compared to existing magnetic resonance imaging (MRI) techniques for modulating brain activity levels, it is less costly and has wider applicability.

[0018] Furthermore, this application eliminates the need for the target subjects to take any medication or undergo any invasive stimulation. The entire training process only requires wearing a near-infrared photoelectric cap. Therefore, the side effects experienced by the target subjects are limited to physical scalp discomfort caused by wearing the near-infrared photoelectric cap for an extended period of time. In other words, the side effects of this application are relatively minor.

[0019] Other features and advantages of the invention will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0020] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating a brain modulation training method provided in an embodiment of the present invention;

[0023] Figure 2 A flowchart of another brain modulation training method provided in an embodiment of the present invention;

[0024] Figure 3 A flowchart of another brain modulation training method provided in an embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of a brain modulation training device provided in an embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention;

[0027] Figure 6 A schematic diagram of the feedback signal located on the display screen according to an embodiment of the present invention;

[0028] Figure 7 A schematic diagram of an image showing how a target object regulates its brain activity level according to a control condition signal on a display screen, as provided in an embodiment of the present invention.

[0029] Figure 8 A schematic diagram of an image showing the location of the indicator signal corresponding to the feedback signal provided in an embodiment of the present invention on the display screen;

[0030] Figure 9 The first evaluation pattern, the second evaluation pattern, and the third evaluation pattern provided in the embodiments of the present invention, as well as the comparison result image of the first evaluation pattern and the third evaluation pattern, are schematic diagrams. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0032] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0033] Globally, on the one hand, depression, as an increasingly prevalent mental disorder, is receiving increasing attention from clinical researchers due to its complexity and intractability; on the other hand, more people are suffering from depressive moods and anxiety due to changes in lifestyle and a faster pace of life, and the more universally applicable techniques for improving and training these negative emotional states are extremely limited.

[0034] With the continuous development of neuroscience and technology, neuromodulation therapy, which uses physical methods (such as magnetism, electricity, and light) to alter the function of the central and peripheral nervous systems in patients with depression, has gradually become a technical direction for improving depressive states. As relatively new auxiliary training methods, the two most commonly used neuromodulation techniques in current auxiliary training for depression are repetitive transcranial magnetic stimulation (rTMS) and transcranial direct current stimulation (tDCS).

[0035] However, both techniques still have potential side effects and limitations: First, side effects on peripheral nervous system function. Side effects of repetitive transcranial magnetic stimulation (rTMS) mainly include syncope, facial spasms, pain, and cognitive impairment. Similarly, transcranial electrical stimulation (TCS) may cause problems including skin tingling, photohana, nausea, dizziness, and itching. Second, both rTMS and TCS use externally applied magnetic / electrical stimulation to excite or inhibit corresponding brain regions, thereby promoting healthy brain activity patterns. However, regardless of the method, the trainee is only passively receiving intervention, and the long-term effectiveness of the training is generally low after the treatment course ends, meaning the improvement is not sustainable.

[0036] To address the aforementioned issues, embodiments of the present invention provide a brain regulation training method, apparatus, and electronic device, which can be applied in scenarios involving the regulation of brain activity levels in target subjects.

[0037] To facilitate understanding of this embodiment, a brain regulation training method disclosed in this invention will first be described in detail. This method has a long-lasting effect on improving the regulation of brain activity levels and has few side effects; for example... Figure 1 As shown, the method includes the following specific steps:

[0038] Step S102: Signal acquisition is performed on the brain region of the target object using a near-infrared light source to obtain neural activity information corresponding to the brain region.

[0039] Specifically, the aforementioned brain regions include the dorsolateral prefrontal cortex (dlPFC), dorsomedial prefrontal cortex (dmPFC), and orbitofrontal cortex (OFC). These brain regions play important roles in an individual's emotional and cognitive functions. Therefore, in this embodiment, intervention and regulation of these brain regions are mainly carried out to enhance and improve the emotional and cognitive functions of the trained individuals. In specific implementation, neural activity information in the aforementioned brain regions is collected using a near-infrared light source.

[0040] Furthermore, the aforementioned near-infrared light source corresponds to fNIRS technology. In its specific implementation, the target subject wears a near-infrared photosensitive cap during training. The emitter of the cap emits a near-infrared light source with a wavelength between 600-900 nm at the corresponding location in the brain region, and then the receiver of the cap receives this near-infrared light. The fNIRS technology described above has good spatiotemporal resolution in signal acquisition from brain regions, thus enabling accurate reception and feedback of signals from various brain regions.

[0041] Step S104: Extract specific indicators from neural activity information to obtain multiple indicator parameters.

[0042] After obtaining the neural activity information corresponding to the above-mentioned brain regions, it is necessary to extract specific indicators that can be used to regulate the level of brain activity. Furthermore, since it is also necessary to determine the level of brain activity regulation of the above-mentioned target subjects, it is also necessary to determine specific indicators corresponding to multiple time points, that is, to collect neural activity information of the brain regions of the above-mentioned target subjects in real time to determine the level of brain activity of the above-mentioned target subjects. At this time, multiple indicator parameters can be obtained.

[0043] Step S106: Transmit the time series corresponding to multiple indicator parameters to the preset neural feedback training model so that the neural feedback training model outputs feedback signals.

[0044] Once the specific indicators corresponding to the above multiple time points are obtained, the indicator parameters corresponding to each time point are the time series corresponding to each time point. Then, the time series is transmitted to the preset neural feedback training model so that the neural feedback model outputs feedback signals.

[0045] Step S108: Based on the feedback signal, regulate the neural activity information corresponding to the brain region to regulate the brain activity level of the target subject.

[0046] Upon receiving the aforementioned feedback signal, the target object can regulate the neural activity information corresponding to the brain region based on the feedback signal, thereby regulating the target object's brain activity level.

[0047] This invention provides a brain regulation training method. This method collects neural activity information in brain regions using a near-infrared light source. Compared to magnetic resonance imaging (MRI), this method is lower in cost and easier to implement. The method uses the collected neural activity information to generate feedback signals, enabling the target subject to regulate their brain activity level based on these signals. Furthermore, it collects neural activity information from the target subject's brain regions in real time to determine the target subject's brain activity level. The target subject can regulate their brain activity level based on the neural activity information at the current time point and receive feedback signals for the next time point. Therefore, the target subject can not only autonomously regulate the neural activity information of brain regions in real time, but also understand the results of their brain activity regulation, which helps to prolong the effectiveness of the improvement in brain activity level regulation. In addition, the method of allowing the target subject to autonomously regulate their brain activity level can fully mobilize and stimulate the target subject's subjective initiative, providing an opportunity for improvement for those lacking motivation.

[0048] Furthermore, the aforementioned near-infrared light source corresponds to fNIRS technology, which has good spatiotemporal resolution in signal acquisition from brain regions, thus enabling accurate reception and feedback of signals from various brain regions. Additionally, this fNIRS technology involves training the target subject by wearing a near-infrared light cap. Since the cap only needs to be worn on the target subject's head, the signal acquisition results are less affected by the target subject's body movements, making it easier for the target subject to cooperate and complete the training. Moreover, the method of wearing the near-infrared light cap is more convenient and comfortable for the target subject compared to lying flat on an MRI scanner. Furthermore, the cost of modulating brain activity levels based on fNIRS is lower than that of using MRI technology in the prior art; therefore, the embodiments of this invention are scalable.

[0049] Furthermore, the brain activity level regulation performed through the embodiments of the present invention allows the target subjects to train without taking any drugs or receiving any invasive stimulation. They only need to wear a near-infrared light hat throughout the training process. For the target subjects, the only side effect they experience is physical scalp discomfort caused by wearing the near-infrared light hat for too long. Therefore, the side effects produced by the embodiments of the present invention are also relatively small.

[0050] In accordance with the above embodiments, the present invention also provides another brain regulation training method. This method is implemented based on the above brain regulation training method. The method focuses on describing the specific process of extracting specific indicators from neural activity information to obtain multiple indicator parameters (implemented through steps S204-S206 below), and the specific process of transmitting the time series corresponding to the multiple indicator parameters to a preset neural feedback training model so that the neural feedback model outputs feedback signals (implemented through steps S208-S210 below). Figure 2 As shown, the method includes the following specific steps:

[0051] Step S202: Signal acquisition is performed on the brain region of the target object using a near-infrared light source to obtain neural activity information corresponding to the brain region.

[0052] Specifically, the neural activity information corresponding to a brain region contains sub-activity information at multiple time points. In practice, to determine the results of the regulation of brain activity levels in the target subject in real time, it is also necessary to collect signals from the target subject's brain regions in real time. At this time, sub-activity information at multiple time points can be obtained. Furthermore, real-time signal collection can be carried out specifically on the target brain regions of the target subject.

[0053] Step S204: Extract the parameter values ​​of oxyhemoglobin concentration and deoxyhemoglobin concentration of each sub-activity information corresponding to each time point from the sub-activity information corresponding to multiple time points of neural activity information.

[0054] Specifically, the sub-activity information corresponding to each of the above time points includes the concentrations of oxyhemoglobin and deoxyhemoglobin in the corresponding brain regions. The concentrations of oxyhemoglobin and deoxyhemoglobin can reflect the neural activity of the brain. By utilizing the differences in the absorption rates of oxyhemoglobin and deoxyhemoglobin in the above brain regions to the above near-infrared light sources of different wavelengths of 600-900nm, the parameter values ​​of the above oxyhemoglobin concentration and the above deoxyhemoglobin concentration can be obtained.

[0055] In practical implementation, based on the difference in absorption rates of oxyhemoglobin and deoxyhemoglobin to near-infrared light of different wavelengths (600-900nm), the incident light intensity is known and the emitted light intensity is measurable. At this point, according to Beer-Lambert Law, the parameter values ​​of the above-mentioned oxyhemoglobin concentration and the above-mentioned deoxyhemoglobin concentration can be obtained.

[0056] Step S206: For each time point, determine the parameter value of the oxyhemoglobin concentration of the sub-activity information corresponding to each current time point as the index parameter corresponding to the current time point.

[0057] Once the parameter values ​​of the oxyhemoglobin concentration and the deoxyhemoglobin concentration at each time point are obtained, since the change in oxyhemoglobin concentration is more sensitive to the regulatory task, the parameter value of the oxyhemoglobin concentration is determined as the indicator parameter corresponding to the current time point. The indicator parameter corresponding to the current time point can indirectly reflect the brain activity level of the target object at the current time point.

[0058] Step S208: Preprocess the index parameters corresponding to each time point to obtain the time series corresponding to each time point.

[0059] In practice, the following steps 10-12 are performed for each time point:

[0060] Step 10: Based on the moving average method, smooth the indicator parameters corresponding to the current time point.

[0061] In practical implementation, the above-mentioned neurofeedback training model uses the visual feedback signal output from the above time series as the signal displayed on the screen. However, since the original signal collected by fNIRS contains a large number of high-frequency noise components (including device noise, environmental noise, and some physiological noise), which are overflow noise, the above-mentioned index parameters need to be smoothed so that the feedback signal output from the above time series is a smooth line signal.

[0062] Step 11: Based on the baseline signal indicated within the preset threshold time period, perform baseline correction on the smoothed index parameters.

[0063] Furthermore, since the index parameters corresponding to the aforementioned brain regions are determined based on the near-infrared light emitted by the near-infrared photocap, the operation of the instrument hardware inevitably leads to detector response, which in turn affects the acquisition of neural activity information. This results in a difference between the actual acquired neural activity information and the theoretical neural activity information. Therefore, baseline correction is needed to approximate the removal of noise. In specific implementation, the parameter value of oxyhemoglobin concentration during a 10-second pre-scan is used as the baseline value for baseline correction. The parameter value of oxyhemoglobin concentration during the aforementioned 10-second period represents the baseline signal indicated within the aforementioned preset threshold time period.

[0064] Step 12: Based on the index parameters corrected by the baseline, determine the time series corresponding to the current time point.

[0065] Step S210: Transmit the time series corresponding to each time point to the neural feedback training model and output the feedback signal corresponding to each time point.

[0066] In practice, once the time series corresponding to each time point is obtained, the aforementioned neurofeedback training model outputs the visual feedback signal corresponding to the current time point based on the time series corresponding to the current time point. At this time, the target object can know its own brain activity level at the current time point based on the visual feedback signal.

[0067] Step S212: Based on the feedback signal, regulate the neural activity information corresponding to the brain region to regulate the brain activity level of the target subject.

[0068] Once the target individual determines their current brain activity level based on the feedback signal corresponding to that time point, they can regulate this level according to preset instructions. Specifically, these preset instructions can be various psychological control strategies employed by the target individual, such as recalling events that increase brain activity. The specific content of these preset instructions is not limited here. Regulation through these preset instructions can enable the target individual to spontaneously increase brain activity and improve cognitive behavior and emotional state, thereby alleviating emotional and cognitive impairments characterized by depressive mood.

[0069] Furthermore, after the brain activity level at the current time point is regulated, neural activity information of the brain region of the target object at the next time point is collected in real time to obtain the signal of the brain region at each time point, and at this time the concentration change of the oxyhemoglobin can be obtained.

[0070] In practice, after receiving the feedback signal corresponding to the current time point, the target object continues to regulate its brain activity level to obtain the brain activity level at the next time point, i.e., it can obtain the feedback signal corresponding to the next time point. Specifically, the feedback signal corresponding to each of the above time points is displayed on the display screen so that the target object can understand its own brain activity level at the current time point.

[0071] In practice, the feedback signal corresponding to each time point appears from the left side of the display screen. After obtaining the feedback signal for the next time point, the feedback signal for the original time point shifts to the right. During the real-time acquisition of signals from the brain region of the target object, the feedback signal corresponding to each time point forms a curve. The target object can use this curve to understand the changes in neural activity information in the brain region.

[0072] Furthermore, the higher the rise of the feedback signal in the curve, the higher the index of the neural activity information of the target object, i.e., the more obvious the regulatory effect. Specifically, in this embodiment of the invention, a feedback signal is generated by collecting the activity level of the target brain region. Then, the target object is trained to self-regulate its brain activity level based on the feedback signal at the current time point. The regulation and improvement effects on brain activity level, emotion, and cognitive functions after self-regulation have a longer duration.

[0073] Furthermore, the aforementioned display screen also includes a regulatory condition signal, which indicates whether the target object needs to regulate its own brain activity level. Specifically, the regulatory condition signal includes a regulatory condition signal and a resting condition signal. In a specific implementation, the aforementioned display screen displays a cloudless sunny day image signal and a cloudy rainy day image signal, wherein the cloudless sunny day image signal is the regulatory condition signal, and the cloudy rainy day image signal is the resting condition signal.

[0074] In specific implementation, the positions of the aforementioned adjustment condition signal and the rest condition signal on the aforementioned display screen are both vertically displayed images, interleaved on the display screen. This arrangement is the default position in this embodiment. Specifically, the positions of the aforementioned adjustment condition signal and the rest condition signal on the aforementioned display screen can also be set according to user needs, and are not limited here. When the feedback signal advances to the aforementioned adjustment condition signal, the target object can regulate its brain activity level according to preset instructions. When the feedback signal advances to the aforementioned rest condition signal, the target object does not need to regulate its brain activity level.

[0075] Specifically, the aforementioned feedback signal is located on the image displayed on the screen via the following... Figure 6 express.

[0076] In the above figure, the odd-numbered columns from left to right are the rest condition signals among the aforementioned control condition signals, and the even-numbered columns from left to right are the adjustment condition signals among the aforementioned control condition signals.

[0077] Another brain regulation training method provided in this invention determines corresponding index parameters by utilizing the difference in absorption rates of oxyhemoglobin and deoxyhemoglobin to near-infrared light of different wavelengths (600-900nm). Feedback signals are then obtained based on these index parameters, enabling the target subject to regulate their brain activity level according to the feedback signals. The method for determining the index parameters is simple and quick. Furthermore, the feedback signal in this invention is a curve signal displayed on a screen. After receiving the feedback signal corresponding to the current time point, the target subject can autonomously regulate their brain activity level to obtain the feedback signal for the next time point. Based on the curve signal, the target subject can clearly understand the result of their brain activity regulation, thereby fully mobilizing and stimulating their initiative. Secondly, the display screen also includes regulation condition signals, including adjustment condition signals and rest condition signals, enabling the target subject to actively consider whether they need to regulate their brain activity level at the current time point, further mobilizing and stimulating their initiative.

[0078] In view of the above embodiments, the present invention also provides another brain regulation training method, which is implemented based on the above brain regulation training method, such as... Figure 3 As shown, the method includes the following specific steps:

[0079] Step S302: Signal acquisition is performed on the brain region of the target object using a near-infrared light source to obtain neural activity information corresponding to the brain region.

[0080] Specifically, the process of step S302 is the same as that of step S202, and will not be repeated here.

[0081] Step S304: Extract specific indicators from neural activity information to obtain multiple indicator parameters.

[0082] Specifically, the above-mentioned multiple indicator parameters are indicator parameters corresponding to multiple time points. The specific process of step S304 is the same as that of steps S204-S206, and will not be repeated here.

[0083] Step S306: Transmit the time series corresponding to multiple indicator parameters to the preset neurofeedback training model so that the neurofeedback training model outputs feedback signals.

[0084] Specifically, the process of determining the time series corresponding to the above-mentioned multiple indicator parameters is the same as the specific process of step S210 above, and will not be repeated here.

[0085] Furthermore, the feedback signal output by the aforementioned neurofeedback training model can be a feedback signal that is not determined based on the numerical values ​​of the aforementioned time series, that is, the aforementioned feedback signal does not change, and the feedback signal corresponding to each time point displayed on the aforementioned display screen is a visual feedback signal that does not change, such as a straight line. The aforementioned target object cannot understand the level of brain activity corresponding to the current time point through the aforementioned display screen. At this time, the aforementioned target object only adjusts the level of brain activity based on the regulatory condition signals in the aforementioned display screen.

[0086] Step S308: Based on the feedback signal, regulate the neural activity information corresponding to the brain region to regulate the brain activity level of the target subject.

[0087] In specific implementation, when the feedback signal on the display screen advances to the adjustment condition signal, the target object adjusts its brain activity level according to the preset instruction; when the feedback signal advances to the rest condition signal, the target object does not need to adjust its brain activity level.

[0088] Specifically, when the target object adjusts its brain activity level according to the regulatory condition signals on the display screen, the images on the display screen are processed through the following... Figure 7 express.

[0089] Specifically, the aforementioned images are used to indicate that the target object cannot understand the level of brain activity at the current point in time based on the images on the aforementioned display screen.

[0090] Step S310: Based on the control results, obtain the indication signal corresponding to the feedback signal.

[0091] Specifically, after the target object adjusts its brain activity level according to the regulatory condition signal, it can also obtain the actual feedback signal corresponding to the feedback signal at the current time point. This actual feedback signal is the indicator signal corresponding to the feedback signal. The actual feedback signal represents the target object's true brain activity level at the current time point. At this time, the second object can obtain the indicator signal corresponding to the feedback signal. In this embodiment, the second object is the display screen of the backend server, that is, the display screen of the backend server displays the actual feedback signal corresponding to the target object at the current time point. The form of the actual feedback signal is consistent with the form of the feedback signal in step S212, and will not be described again here.

[0092] Step S312: Determine the target subject's level of control over brain activity based on the indication signal corresponding to the feedback signal.

[0093] Upon receiving the indication signal corresponding to the aforementioned feedback signal, the result of the brain activity level regulation of the target object can be determined based on the indication signal. In this embodiment, since the target object cannot obtain its current brain activity level, it can only regulate its brain activity level according to the regulation condition signal on the display screen. Therefore, based on the brain activity level regulation result determined according to the indication signal, the degree of mastery of the target object's brain activity level regulation can be determined.

[0094] Specifically, the indication signal corresponding to the feedback signal obtained by the second object is obtained through the following... Figure 8 express.

[0095] Step S314: Based on the preset training time period, a comprehensive assessment of the target subject is conducted to obtain the assessment results of brain activity after the brain activity level is regulated, as well as the assessment results of emotion and cognition.

[0096] Specifically, the assessment results corresponding to the above-mentioned regulation of brain activity levels are determined through the following steps 20-21:

[0097] Step 20: Determine the evaluation values ​​corresponding to multiple dimensions based on the preset training time period.

[0098] Specifically, the aforementioned multiple dimensions include the first dimension, the second dimension, the third dimension, the fourth dimension, and the fifth dimension. The aforementioned preset training time periods include the first preset training time period and the second preset training time period.

[0099] In practice, the evaluation value corresponding to the first dimension can be determined based on the regulation results obtained in step S212 or the degree of mastery of brain activity level regulation obtained in step S312. Specifically, steps S202-S212 or S302-S312 can be performed 5 rounds per day. The first round of training is a warm-up, and rounds 2-5 are formal training. Each round lasts 3-4 minutes. Steps S202-S212 are performed on the first 3 days of the week (Monday to Wednesday) to regulate and train the brain activity level of the target subject. Steps S302-S312 are performed on Fridays of the week to regulate and train the brain activity level of the target subject and determine the degree of mastery of brain activity level regulation. A training cycle lasts two weeks.

[0100] The aforementioned first preset training time period can be the time period corresponding to the 2nd to 5th rounds of training on Monday of the first week in the aforementioned training cycle; it can also be the time period corresponding to the 2nd to 5th rounds of training on Wednesday of the first week in the aforementioned training cycle and the time period corresponding to the 1st to 5th rounds of training on Friday of the first week in the aforementioned training cycle; or it can be the time period corresponding to the 2nd to 5th rounds of training on Wednesday of the second week in the aforementioned training cycle and the time period corresponding to the 1st to 5th rounds of training on Friday of the second week in the aforementioned training cycle.

[0101] Specifically, the evaluation value corresponding to the first dimension can be determined based on the control results obtained according to steps S202-S212 and the degree of control mastery of brain activity level obtained according to steps S302-S312 for the first preset training time period, or it can be determined solely based on the control results. Further, the first dimension is a brain activation dimension. Specifically, the evaluation value corresponding to the first dimension determined based on the 2nd-5th rounds of training on Monday of the first week in the training cycle is used to determine the baseline value of brain activity level corresponding to the training; the evaluation value corresponding to the first dimension determined based on the time period corresponding to the 2nd-5th rounds of training on Wednesday of the first week in the training cycle and the 1st-5th rounds of training on Friday of the first week in the training cycle is used to determine the corresponding brain activity level during the training process; the evaluation value corresponding to the first dimension determined based on the time period corresponding to the 2nd-5th rounds of training on Wednesday of the second week in the training cycle and the 1st-5th rounds of training on Friday of the second week in the training cycle is used to determine the corresponding brain activity level after the training.

[0102] In practical implementation, the evaluation value corresponding to the first dimension mentioned above can be determined through the following steps 30-33:

[0103] Step 30: Use the NIRS_SPM toolkit and internal scripts in Matlab (The MathWorks, Inc.) to perform offline preprocessing and offline analysis on the signals acquired via the near-infrared light source. Matlab is a scientific computing language and programming environment used for algorithm development, data visualization, data analysis, and numerical computation.

[0104] Specifically, in the aforementioned offline preprocessing, the NIRS analysis package (NAP) was used to detect and correct head motion artifacts in the oxyhemoglobin signal acquired via a near-infrared light source. Second-order denoising was employed to eliminate baseline drift, and low-pass filtering (using a Gaussian smoothing kernel with a full width at half maximum (FWHM) of 4 seconds) was used to eliminate high-frequency noise.

[0105] During offline analysis, a generalized linear model (GLM) was used. The resting condition signal and the regulatory condition signal from the aforementioned regulatory condition signals were respectively incorporated into the GLM to calculate the hemodynamic response signal associated with each regulatory condition signal. Hemodynamics, a branch of biomechanics, primarily aims to apply the theories and methods of fluid mechanics to study the causes, conditions, states, and various influencing factors of blood flow along blood vessels, in order to elucidate the laws governing blood flow, its physiological significance, and its relationship with disease.

[0106] Step 31: Based on the generalized linear model corresponding to the above offline analysis, extract the β value corresponding to each of the above control condition signals.

[0107] The generalized linear model (GLM) described above can be summarized as a model framework serving a set of response variables from an exponential distribution family, with model parameters obtained through maximum likelihood estimation. Beta regression is a type of generalized linear model used to model continuous variables (such as proportions, percentages, etc.) from standard unit intervals, and can be considered when the response variable follows a beta distribution.

[0108] Step 32: Divide the β value by the residual corresponding to the generalized linear model to obtain the evaluation value for each round of training.

[0109] In mathematical statistics, the residual refers to the difference between the actual observed value and the estimated value (fitted value). The residual contains important information about the basic assumptions of the model. If the regression model is correct, the residual can be considered as the observed value of the error. The information provided by the residual is typically used to examine the reasonableness of the model assumptions and the reliability of the data.

[0110] Step 33: Based on the first preset training time period and the evaluation values ​​corresponding to each round of training, obtain the evaluation values ​​corresponding to the first dimension.

[0111] Specifically, when the first preset training time period is the time period corresponding to the 2nd to 5th rounds of training on Monday of the first week, the evaluation value corresponding to the first dimension is the average value of the evaluation value corresponding to each round of training in the 2nd to 5th rounds.

[0112] When the first preset training time period is the time period corresponding to the 2nd to 5th rounds of training on Wednesday of the first week and the time period corresponding to the 1st to 5th rounds of training on Friday of the first week in the above training cycle, the evaluation value corresponding to the first dimension is: (average of the evaluation values ​​corresponding to each round of training on Wednesday of the first week + average of the evaluation values ​​corresponding to each round of training on Friday of the first week) / 2, where " / " is the division symbol.

[0113] When the first preset training time period is the time period corresponding to the 2nd to 5th rounds of training on Wednesday of the second week and the 1st to 5th rounds of training on Friday of the second week in the above training cycle, the evaluation value corresponding to the first dimension is: (average of the evaluation values ​​corresponding to each round of training on Wednesday of the second week + average of the evaluation values ​​corresponding to each round of training on Friday of the second week) / 2.

[0114] The aforementioned second preset training time period can be used to conduct a second test and obtain a second test result. This second preset training time period can be, when the training cycle is used as a unit, before step S202 on every Monday, where the second test result is determined before proceeding to step S202; alternatively, the second preset training time period can be the first or second Friday of the training cycle, after step S312. In this time period, steps S302-S312 are executed first, and then the second test result is determined.

[0115] Specifically, determining the second test result before step S202 on Mondays aims to establish a baseline value for the second test result before the start of training. Determining the second test result on the first Friday of the training cycle aims to determine the second test result during training and to confirm the brain regulation status after a week of training. Determining the second test result on the second Friday of the training cycle aims to determine the second test result at the end of all training. In practice, the times corresponding to the second preset time period are the default times in this embodiment. Furthermore, the specific second preset time period can be set according to user needs.

[0116] Specifically, the second test can be assessed using the following self-report questionnaires and clinical evaluations: the Hamilton Depression Scale (HAMD) and the Hamilton Anxiety Scale (HAMA), as well as the Clinical Assessment Interview of Negative Symptoms (CAINS) to evaluate the target subjects' depressive symptoms, anxiety symptoms, and anhedonia symptoms. Alternatively, the Beck Depression Inventory (BDI) and the State-trait Anxiety Inventory (STAI) can be used to examine the target subjects' subjective depressive mood and anxiety traits. The Emotional Regulation Questionnaire (ERQ) and the Emotional Expressivity Scale (EES) can also be used to measure the target subjects' emotion regulation and expression abilities. The verbal and spatial working memory abilities of the aforementioned target individuals can also be measured through the Spatial Working Memory task (SWM) and the Letter-Number Sequencing task (LNS).

[0117] In practical implementation, the evaluation value corresponding to the second dimension can be determined through the Spatial Working Memory Task (SWM) and the Character Digit Span Test (LNS). Specifically, the second dimension can be a cognitive function dimension, and the evaluation value corresponding to the second dimension can be determined by the following formula: X = (SWM + (LNS_1 / 32*100 + LNS_2 / 9*100) / 2) / 2, where X is the evaluation value corresponding to the second dimension, SWM is the accuracy rate of the Spatial Working Memory Task, LNS is the test result of the Character Digit Span Test, LNS_1 is the number of correct items in the Character Digit Span Test, and LNS_2 is the longest item number passed in the Character Digit Span Test.

[0118] Specifically, the assessment value corresponding to the third dimension can be obtained based on the test results of the Hamilton Depression Rating Scale (HAMD), the Hamilton Anxiety Rating Scale (HAMA), the Beck Depression Rating Scale (BDI), and the State-Trait Anxiety Inventory (STAI). In this case, the aforementioned third dimension is the depression and anxiety dimension.

[0119] Furthermore, the aforementioned State-Trait Anxiety Inventory (STAI) can also be administered after completing five rounds of training steps S202-S212 each day to determine the emotional state of the target subjects on the day of training.

[0120] In practical implementation, the evaluation value corresponding to the third dimension mentioned above can be determined by the following formula: Y = 100 - (BDI / 63*100 + HAMD / 53*100 + HAMA / 56*100 + STAI_State / 80*100) / 4. Where Y is the third dimension mentioned above.

[0121] Furthermore, the assessment value corresponding to the fourth dimension can be obtained based on the test results of the Negative Symptoms and Anhedonia Assessment (CAINS). In this case, the fourth dimension is the anhedonia dimension. In specific implementation, the assessment value corresponding to the fourth dimension can be determined by the following formula: Z = 100 - (CAINS_MAP / 36*100 + CAINS_EXP / 16*100) / 2, where Z is the fourth dimension, and CAINS_MAP and CAINS_EXP are the two dimensions of this clinical assessment.

[0122] Furthermore, the assessment value for the fifth dimension can be obtained based on the test results of the Emotion Regulation Questionnaire (ERQ) and the Emotion Expression Scale (EES). In this case, the fifth dimension is the emotional function dimension. In practice, the assessment value for the fifth dimension can be determined using the following formula:

[0123] P = (EES_Exp / 36*100 + EES_Sup / 66*100 + ERQ_CR / 42*100 + ERQ_ES / 28*100) / 4, where P is the evaluation value corresponding to the fifth dimension mentioned above, EES_Exp and EES_Sup are the two dimensions of the EES scale, and ERQ_CR and ERQ_ES are the two dimensions of the ERQ scale.

[0124] Specifically, the assessment value for each dimension is determined based on the assessment value for each vector within that dimension. In practice, the assessment value for each vector in that dimension is first divided by its total score and then multiplied by 100 to convert it into a general percentage. For example, in the formula BDI / 63*100 for the depression and anxiety dimension (i.e., the third dimension), 63 points represents the total score of the BDI scale (i.e., the vector in the third dimension mentioned above). Then, the average of the percentage scores for each vector in that dimension is used to determine the assessment value for that dimension.

[0125] Furthermore, the assessment values ​​corresponding to the third dimension (i.e., the depression and anxiety dimension) or the fourth dimension (i.e., the anhedonia dimension) are determined by subtracting the average of the percentages of each vector in the current dimension from 100.

[0126] Furthermore, the evaluation values ​​corresponding to the second and third dimensions, as well as the evaluation values ​​corresponding to the fourth and fifth dimensions, all have 0 as the origin and 100 as the maximum value. The maximum and minimum values ​​of the evaluation values ​​corresponding to the first dimension can be obtained by appropriately expanding the maximum and minimum t values ​​among all existing samples in the specific implementation. Currently, they range from -5 to 20.

[0127] Step 21: Determine the set of assessment values ​​corresponding to each dimension as the assessment results of brain activity after brain activity level regulation, as well as the assessment results of emotion and cognition.

[0128] In specific implementation, the evaluation value corresponding to the first dimension can be the evaluation value determined based on the 2nd to 5th rounds of training on Monday of the first week in the training cycle; or it can be the evaluation value determined based on the time period corresponding to the 2nd to 5th rounds of training on Wednesday of the first week in the training cycle and the 1st to 5th rounds of training on Friday of the first week in the training cycle; or it can be the evaluation value determined based on the time period corresponding to the 2nd to 5th rounds of training on Wednesday of the second week in the training cycle and the 1st to 5th rounds of training on Friday of the second week in the training cycle. The evaluation values ​​corresponding to the second, third, fourth, and fifth dimensions can be the evaluation values ​​determined before step S202 of each Monday in the training cycle; or they can be the evaluation values ​​determined after step S312 of the first or second Friday of the training cycle.

[0129] Then, the set of the first evaluation values ​​corresponding to the first, second, third, fourth and fifth dimensions is determined, that is, the baseline values ​​of the evaluation values ​​of the first, second, third, fourth and fifth dimensions. In this embodiment, the set of the first evaluation values ​​can be a chart-style visualization report. The evaluation values ​​corresponding to these five dimensions can form a first evaluation graph, which includes a first area value.

[0130] It is also possible to determine the set of second or third evaluation values ​​corresponding to the first, second, third, fourth, and fifth dimensions, that is, the evaluation values ​​of the first, second, third, fourth, and fifth dimensions during the training process. In this embodiment, the representation of the set of second or third evaluation values ​​is consistent with the representation of the set of first evaluation values, and will not be elaborated here. At this time, a second evaluation graph or a third evaluation graph can be obtained. The second evaluation graph contains a second area value, and the third evaluation graph contains a third area value.

[0131] Specifically, the aforementioned first evaluation graph, second evaluation graph, and third evaluation graph, as well as the comparison results between the first and third evaluation graphs, are determined through the following... Figure 9 express.

[0132] in, Figure 9 The first graphic in the image is the aforementioned first evaluation graphic. The graphic to the right of the first evaluation graphic is the aforementioned second evaluation graphic. The graphic below the first evaluation graphic is the aforementioned third evaluation graphic. The graphic below the second evaluation graphic is the comparison result between the first and third evaluation graphics. Specifically, after the aforementioned target object completes the comprehensive evaluation, the result is... Figure 9 The assessment results of brain activity after regulation of the corresponding brain activity level, as well as the assessment results of emotion and cognition.

[0133] Furthermore, Figure 9 The farther the point corresponding to each dimension is from the origin, the better the state of that dimension. The greater the difference in area between two evaluation graphs, the better the improvement effect.

[0134] The assessment of the aforementioned depression and anxiety dimensions primarily includes the degree to which the target individuals experience low mood and anxiety in their daily lives. The further the score of this dimension is from the center point, the lower the degree of depression and anxiety, and the fewer instances of low mood and anxiety in the target individuals' daily lives. The assessment of the aforementioned anhedonia dimension primarily includes the frequency and intensity of the target individuals' pleasurable experiences in their daily lives, as well as their expectation of pleasurable experiences. The further the score of this dimension is from the center point, the lower the degree of anhedonia, the more times the target individuals experience pleasurable experiences in their daily lives, and the stronger their expectation of pleasurable experiences. The assessment of the aforementioned cognitive function dimension primarily includes the target individuals' memory and attention. The further the score of this dimension is from the center point, the better the target individuals' memory and attention. The assessment of the aforementioned emotional function dimension primarily includes the target individuals' expression and regulation of emotions in daily life. The further the score of this dimension is from the center point, the more positive emotional expression and regulation the target individuals possess. The assessment of the aforementioned brain function dimension primarily includes the activation of the corresponding brain regions of the target individuals. The farther the score in this dimension is from the center point, the higher the activity level of the target object in that area.

[0135] Another brain regulation training method provided in this invention determines the target subject's level of mastery of brain activity regulation by having the target subject autonomously regulate the neural activity information corresponding to the brain region based solely on the regulation condition signal, rather than directly understanding the feedback signal corresponding to the current time point. This enables the target subject to autonomously and effectively learn some positive brain regulation strategies and transfer them to their future life. Therefore, the effect of brain activity level regulation through this invention is not limited to the time of brain activity level regulation. The target subject can also have a long-lasting and positive impact on themselves by using the strategies learned in this brain activity level regulation training in their daily life.

[0136] The embodiments of the present invention also determine the assessment values ​​of multiple dimensions of the target object, providing a basis for the training effect of regulating the brain activity level of the target object and further treatment.

[0137] Based on the above system embodiments, this invention also provides a brain-modulation training device; such as Figure 4 As shown, the device includes:

[0138] The signal acquisition module 401 is used to acquire signals from the brain region of the target object through a near-infrared light source based on a preset training time period and preset condition signals, so as to obtain neural activity information corresponding to the brain region.

[0139] The indicator parameter determination module 402 is used to extract specific indicators from neural activity information to obtain multiple indicator parameters.

[0140] The feedback signal determination module 403 is used to transmit the time series corresponding to multiple index parameters to the preset neural feedback training model so that the neural feedback model outputs feedback signals.

[0141] The regulation module 404 is used to regulate the neural activity information corresponding to the brain region based on the feedback signal, so as to regulate the brain activity level of the target object.

[0142] Furthermore, the aforementioned indicator parameter determination module 402 is also used to extract the parameter values ​​of oxyhemoglobin concentration and deoxyhemoglobin concentration of sub-activity information corresponding to each time point from the sub-activity information corresponding to multiple time points of neural activity information; and for each time point, to determine the parameter value of oxyhemoglobin concentration of sub-activity information corresponding to each current time point as the indicator parameter corresponding to the current time point.

[0143] The aforementioned feedback signal determination module 403 is further configured to preprocess the indicator parameters corresponding to each time point to obtain the time series corresponding to each time point; transmit the time series corresponding to each time point to the neural feedback training model, and output the feedback signal corresponding to each time point. The aforementioned feedback signal determination module 403 is further configured to perform the following operations for each time point: smooth the indicator parameters corresponding to the current time point based on the moving average method; perform baseline correction on the smoothed indicator parameters according to the baseline signal indicated within a preset threshold time period; and determine the time series corresponding to the current time point based on the baseline-corrected indicator parameters.

[0144] Furthermore, the above method also includes a regulation mastery determination module 404, which is used to obtain an indication signal corresponding to the feedback signal based on the regulation result; and to determine the level of regulation mastery of the target object's brain activity level based on the indication signal corresponding to the feedback signal.

[0145] Furthermore, the above method also includes an evaluation result determination module 405, used to comprehensively evaluate the target subject based on a preset training time period, and obtain evaluation results of brain activity after brain activity level regulation, as well as evaluation results of emotion and cognition. Furthermore, the evaluation result determination module 405 is also used to obtain evaluation values ​​corresponding to multiple dimensions according to the preset training time period; and to determine the set of evaluation values ​​corresponding to each dimension as the evaluation results of brain activity after brain activity level regulation, as well as the evaluation results of emotion and cognition.

[0146] This invention provides a brain modulation training device that collects neural activity information in brain regions using a near-infrared light source. This near-infrared light source corresponds to fNIRS technology, which can accurately receive and relay signals from various brain regions. Furthermore, this fNIRS technology involves training the target subject while wearing a near-infrared light cap; therefore, the acquisition results are less affected by the target subject's body movements, making it more convenient and comfortable to operate. Secondly, compared to existing magnetic resonance imaging (MRI) technology for modulating brain activity levels, this method is less costly and has wider applicability.

[0147] This invention also uses collected neural activity information to generate feedback signals, enabling the target subject to regulate its brain activity level based on these signals. Furthermore, this invention collects neural activity information from brain regions of the target subject in real time to determine its brain activity level. The target subject can not only autonomously regulate neural activity information in brain regions in real time, but also understand the results of its regulation, which helps extend the effectiveness of the improvement effect of brain activity level regulation. In addition, the method of allowing the target subject to autonomously regulate its brain activity level can fully mobilize and stimulate the subject's subjective initiative, providing opportunities for improvement for subjects lacking motivation.

[0148] The brain regulation training device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the method embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0149] This invention also provides an electronic device, such as... Figure 5 As shown, the electronic device includes a processor 101 and a memory 100, the memory 100 storing machine-executable instructions that can be executed by the processor 101, the processor 101 executing the machine-executable instructions to implement the above-described brain modulation training method.

[0150] The memory 100 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 103 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network. The bus 102 may be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0151] Processor 101 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 101 or by instructions in software form. Processor 101 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 100, and processor 101 reads information from memory 100 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0152] This invention also provides a machine-readable storage medium storing machine-executable instructions. When these machine-executable instructions are called and executed by a processor, they cause the processor to implement a brain-controlled training method. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0153] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A brain regulation training method, characterized in that, The method includes: Signals are collected from the brain regions of the target object using a near-infrared light source to obtain neural activity information corresponding to the brain regions; the brain regions include the dorsolateral prefrontal cortex, the dorsomedial prefrontal cortex, and the orbitofrontal cortex. Specific indicators are extracted from the neural activity information to obtain multiple indicator parameters; The time series corresponding to the multiple indicator parameters are transmitted to a preset neural feedback training model so that the neural feedback training model outputs a feedback signal. Based on the feedback signal, the regulation result of the target object's brain activity level is determined; After the step of determining the regulation result of the target object's brain activity level based on the feedback signal, the method further includes: Based on the control results, the indication signal corresponding to the feedback signal is obtained; The degree of control over the brain activity level of the target object is determined based on the indication signal corresponding to the feedback signal. The method further includes: Based on a preset training period, the target object is comprehensively evaluated to obtain the evaluation results of brain activity after brain activity level regulation, as well as the evaluation results of emotion and cognition. The step of comprehensively evaluating the target subject based on a preset training period to obtain evaluation results of brain activity after brain activity level regulation, as well as evaluation results of emotion and cognition, includes: Based on the preset training time period, evaluation values ​​corresponding to multiple dimensions are obtained; The set of evaluation values ​​corresponding to each dimension is determined as the evaluation result of brain activity after the brain activity level is regulated, as well as the evaluation results of emotion and cognition. The multiple dimensions include a first dimension, a second dimension, a third dimension, a fourth dimension, and a fifth dimension. The first dimension represents the brain activation dimension, the second dimension represents the cognitive function dimension, the third dimension represents the depression and anxiety dimension, the fourth dimension represents the anhedonia dimension, and the fifth dimension represents the emotional function dimension. The first dimension is determined based on the activation status of the corresponding brain regions of the target object; the second dimension is determined based on the assessment of the target object's memory and attention; the third dimension is determined based on the assessment of the degree of depression and anxiety felt by the target object in life; the fourth dimension is determined based on the assessment of the frequency and intensity of the target object's happy experiences in life, as well as the target object's expectation of happy experiences; and the fifth dimension is determined based on the assessment of the target object's emotional expression and regulation in daily life.

2. The method according to claim 1, characterized in that, The neural activity information includes sub-activity information corresponding to multiple time points; the specific indicators include oxyhemoglobin concentration and deoxyhemoglobin concentration; the step of extracting specific indicators from the neural activity information to obtain multiple indicator parameters includes: From the sub-activity information corresponding to multiple time points of the neural activity information, extract the parameter values ​​of the oxyhemoglobin concentration and the parameter values ​​of the deoxyhemoglobin concentration of each sub-activity information corresponding to the time point; For each time point, the parameter value of the oxyhemoglobin concentration of the sub-activity information corresponding to each current time point is determined as the index parameter corresponding to the current time point.

3. The method according to claim 1, characterized in that, The multiple indicator parameters include the indicator parameters corresponding to each time point in multiple time points; The step of transmitting the time series corresponding to the multiple indicator parameters to a preset neural feedback training model, so that the neural feedback model outputs a feedback signal, includes: Preprocess the index parameters corresponding to each time point to obtain the time series corresponding to each time point; The time series corresponding to each time point is transmitted to the neural feedback training model, and the feedback signal corresponding to each time point is output.

4. The method according to claim 3, characterized in that, The step of preprocessing the index parameters corresponding to each time point to obtain the time series corresponding to each time point includes: Perform the following operations for each of the aforementioned time points: Based on the moving average method, the indicator parameters corresponding to the current time point are smoothed. Based on the baseline signal indicated within a preset threshold time period, the smoothed index parameters are baseline corrected. Based on the index parameters corrected by the baseline, the time series corresponding to the current time point is determined.

5. A brain-controlled training device, characterized in that, The device includes: The signal acquisition module is used to acquire signals from the brain regions of the target object using a near-infrared light source based on a preset training time period and preset condition signals, and to obtain neural activity information corresponding to the brain regions; the brain regions include the dorsolateral prefrontal cortex, the dorsomedial prefrontal cortex, and the orbitofrontal cortex. The indicator parameter determination module is used to extract specific indicators from the neural activity information to obtain multiple indicator parameters; The feedback signal determination module is used to transmit the time series corresponding to the multiple index parameters to a preset neural feedback training model so that the neural feedback model outputs a feedback signal. The regulation module is used to determine the regulation result of the brain activity level of the target object based on the feedback signal; The device further includes a control mastery level determination module, used to obtain an indication signal corresponding to the feedback signal based on the control result; and to determine the control mastery level of the target object's brain activity level based on the indication signal corresponding to the feedback signal. The device also includes an evaluation result determination module, which is used to comprehensively evaluate the target object based on a preset training time period to obtain the evaluation results of brain activity after brain activity level regulation, as well as the evaluation results of emotion and cognition. The evaluation result determination module is further configured to obtain evaluation values ​​corresponding to multiple dimensions based on the preset training time period; and to determine the set of evaluation values ​​corresponding to each dimension as the evaluation result of brain activity after the brain activity level regulation, as well as the evaluation results of emotion and cognition; wherein, the multiple dimensions include a first dimension, a second dimension, a third dimension, a fourth dimension, and a fifth dimension, the first dimension representing the brain activation dimension, the second dimension representing the cognitive function dimension, the third dimension representing the depression and anxiety dimension, the fourth dimension representing the anhedonia dimension, and the fifth dimension representing the emotional function dimension; the first dimension is determined based on the activation status of the corresponding brain region of the target object; the second dimension is determined based on the evaluation of the target object's memory and attention; the third dimension is determined based on the evaluation of the degree of depression and anxiety felt by the target object in life; the fourth dimension is determined based on the evaluation of the frequency and intensity of the target object's happy experiences in life, and the target object's expectation of happy experiences; and the fifth dimension is determined based on the evaluation of the target object's emotional expression and regulation in daily life.

6. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing machine-executable instructions that can be executed by the processor, the processor executing the machine-executable instructions to implement the brain modulation training method according to any one of claims 1 to 4.

7. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores machine-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the brain modulation training method according to any one of claims 1 to 4.

Images