An emotion regulation training method based on rtfMRI-NF technology

Abstract

The present invention relates to the field of interactive training technology, and specifically discloses an emotion regulation training method based on rtfMRI-NF technology, the method comprising performing structural image scanning on a user to obtain a standard model; performing a resting state scanning on the user based on a preset scanning instruction to obtain collected data, and obtaining and displaying a dynamic model; displaying a preset training process to the user, obtaining and displaying the activity information of the user's brain area, querying and feeding back the regulation strategy in a preset regulation strategy library according to the activity information of the brain area; stopping the feedback regulation strategy, obtaining and displaying the activity information of the user's brain area, and obtaining the user's autonomous regulation ability value; when the user's autonomous regulation ability value reaches a preset regulation threshold, performing a resting state scanning on the user after a preset time period, obtaining collected data, and generating an evaluation report. The present invention trains the user's emotion regulation ability through rtfMRI-NF technology, and can help the user self-regulate his or her emotional state.

Description

Technical Field

[0001] The present invention relates to the technical field of interactive training, and in particular to an emotion regulation training method based on rtfMRI-NF technology. Background Art

[0002] Real time functional Magnetic Resonance Imaging Neurofeedback (rtfMRI-NF) is an important cognitive behavioral therapy (CBT) that has emerged in recent years. This technology quickly records the subject's brain neural activity and provides targeted real-time feedback to the subject, who then trains and regulates himself according to the current neural activity.

[0003] Researchers have used this technology to treat depression, post-traumatic stress disorder, schizophrenia and other diseases with CBT, and have achieved good results. However, there are currently few reports on the use of this method to improve insomnia by regulating brain function in patients with ID and depression. Summary of the invention

[0004] The purpose of the present invention is to provide an emotion regulation training method based on rtfMRI-NF technology to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An emotion regulation training method based on rtfMRI-NF technology, the method comprising:

[0007] Scan the user's structure image to obtain a standard model;

[0008] Performing a static scan on the user based on a preset scanning instruction to obtain collected data, performing spatial standardization processing on the collected data according to the standard model, and obtaining and displaying a dynamic model;

[0009] Displaying a preset training process to the user, acquiring and displaying the activity information of the user's brain area, and querying and feeding back the adjustment strategy in a preset adjustment strategy library according to the activity information of the brain area;

[0010] Stop the feedback regulation strategy, obtain and display the activity information of the user's brain area, and obtain the user's autonomous regulation ability value;

[0011] When the user's self-regulation ability value reaches a preset regulation threshold, the user is scanned in a resting state after a preset time period to obtain collected data and generate an evaluation report.

[0012] As a further solution of the present invention: in the method, each resting-state scan lasts for 6 minutes and 30 seconds, and data from 260 time points are collected; each time a preset training process is displayed to the user, activity information of the user's brain area is acquired and displayed, and an adjustment strategy is queried and fed back in a preset adjustment strategy library based on the activity information of the brain area. Training is performed for 3 rounds, using a Block design, resting for 30 seconds, adjusting the target brain area for 30 seconds each, alternating for 3 times, and lasting for 6 minutes and 20 seconds; the step of adjusting the target brain area includes up-regulation and down-regulation.

[0013] As a further solution of the present invention: the steps of performing structural image scanning and resting state scanning on the user include:

[0014] Scan the user and generate a magnetic resonance scan image sequence in real time;

[0015] Preprocessing the magnetic resonance scan image sequence to obtain a preprocessed magnetic resonance scan image;

[0016] Corresponding target data is extracted from the preprocessed magnetic resonance scan image according to a preset algorithm.

[0017] As a further solution of the present invention: the preprocessing of the magnetic resonance scan image sequence to obtain the preprocessed magnetic resonance scan image comprises:

[0018] Performing format conversion on the magnetic resonance scanning image sequence;

[0019] The magnetic resonance scanning image sequence after format conversion is corrected, standardized and interference removed.

[0020] As a further solution of the present invention: the step of obtaining and displaying the activity information of the user's brain area includes:

[0021] Obtain activity information of the user's brain area;

[0022] Feedback and regulation of brain activity information in the form of thermometers and curves;

[0023] The height of the thermometer indicates the percentage of signal change of the current target brain region relative to the baseline signal, and the curve indicates the signal intensity curve of the target brain region.

[0024] As a further solution of the present invention: the step of querying and feeding back the regulation strategy in a preset regulation strategy library according to the activity information of the brain region comprises:

[0025] Inputting the activity information of the brain region into a trained emotion analysis model to obtain user emotion parameters;

[0026] Determining an adjustment strategy according to the user emotion parameter; wherein the adjustment strategy at least includes a visual adjustment strategy;

[0027] When the adjustment strategy is a visual adjustment strategy, a stimulation image is extracted and displayed from a preset stimulation image library according to the user's emotional parameters; wherein the stimulation image library includes parameter items and image items.

[0028] As a further solution of the present invention: the step of generating the stimulus image library comprises:

[0029] Collect fMRI data in advance and train the image semantic real-time classification model and visual attention real-time decoding model;

[0030] Extracting images to be inspected from a preset library of images to be inspected in sequence, and displaying the images to be inspected to a user as a visual stimulus;

[0031] Acquire the first fMRI data in real time, and use the image semantic classification model to determine the semantic category of the image to be tested;

[0032] The image to be inspected and the corresponding semantic category are displayed to a user, a second fMRI data is collected in real time, the second fMRI data is input into the visual attention real-time decoding model, and a recognition result of the image semantic classification model is verified;

[0033] When the recognition result of the image semantic classification model passes the verification, a stimulus image library is generated according to the semantic category and the corresponding image to be tested.

[0034] As a further solution of the present invention: the steps of pre-collecting fMRI data and training the image semantic real-time classification model and the visual attention real-time decoding model include:

[0035] Users pre-participate in a brain region registration and positioning experiment, an image semantic classification training experiment, and a visual attention classification training experiment, collect corresponding fMRI data, and train a real-time image semantic classification model based on support vector machine and a real-time visual attention decoding model.

[0036] As a further solution of the present invention: the step of sequentially extracting the images to be inspected from the preset image library to be inspected and displaying the images to be inspected to the user as visual stimulation includes:

[0037] The images to be tested are extracted from the preset image library and displayed to the user, and fMRI data is collected at the same time; wherein, the stimulation duration is 3 TRs;

[0038] The stimulus images are semantically classified based on the trained image semantic real-time classification model, and the entire data preprocessing and classification process is completed within 1 TR.

[0039] As a further solution of the present invention, the step of displaying the image to be inspected and the corresponding semantic category to the user, acquiring the second fMRI data in real time, inputting the second fMRI data into the visual attention real-time decoding model, and verifying the recognition result of the image semantic classification model includes:

[0040] The image to be inspected and the corresponding semantic category are displayed to the user, and the image to be inspected and the corresponding semantic category are placed on both sides of the visual stimulation screen respectively; wherein the user gives feedback on whether the semantic category is correct through visual attention, if the category is correctly determined, the user pays attention to the semantic category, if the category is wrong, the user pays attention to the image to be inspected, and the visual attention interaction process lasts for 2 TRs;

[0041] The user's visual attention information is calculated based on the visual attention real-time decoding model to verify the recognition result of the image semantic classification model; wherein, the data preprocessing and visual attention decoding process are completed within 1 TR; the result of visual decoding is displayed to the user through the visual stimulation screen in the next TR.

[0042] Compared with the prior art, the beneficial effects of the present invention are: for the first time, rtfMRI-NF technology is used to regulate amygdala activity to regulate depression in ID patients and improve insomnia in ID patients; by using the currently advanced rtfMRI-NF technology, by analyzing the changes in resting state and brain networks in ID patients with depression before and after rtfMRI-NF training, and the relationship between these and clinical behavioral changes, the feasibility and neural mechanism of regulating depression in ID patients through rtfMRI-NF and thus improving insomnia are explored, and the comorbidity mechanism of ID and depression is clarified; by adding transfer training and conducting multiple training sessions on subjects for multiple days, the role and sustained effect of rtfMRI-NF in improving depression in ID patients are explored. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0044] Figure 1 This is a flowchart of the emotion regulation training method based on rtfMRI-NF technology.

[0045] Figure 2 This is the first sub-process flowchart of the emotion regulation training method based on rtfMRI-NF technology.

[0046] Figure 3 This is the second sub-process flowchart of the emotion regulation training method based on rtfMRI-NF technology.

[0047] Figure 4 This is the third sub-process flowchart of the emotion regulation training method based on rtfMRI-NF technology. DETAILED DESCRIPTION

[0048] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0049] Real time functional Magnetic Resonance Imaging Neurofeedback (rtfMRI-NF) is an important cognitive behavioral therapy (CBT) that has emerged in recent years. This technology quickly records the subject's brain neural activity and provides targeted real-time feedback to the subject, who is then trained and self-regulated based on the current neural activity. Researchers have used this technology to perform CBT treatments on depression, post-traumatic stress disorder, schizophrenia and other diseases, and have achieved good results.

[0050] At present, technicians in this field conduct neurofeedback training by training patients with depression to upregulate the activity of the amygdala. The results show that patients can upregulate the activity of this brain region and improve their emotional state. In the early stage, our research group used rtfMRI-NF to conduct emotion regulation training on normal subjects and found that the functional connection between the subjects' amygdala and the anterior cingulate gyrus and other self-regulatory emotion-related brain regions was strengthened, which enhanced the positive emotional state. We used rtfMRI-NF to regulate the activity of the anterior cingulate gyrus of patients with herpes zoster to improve their perception of pain.

[0051] The above studies show that rtfMRI-NF training of depressed patients can regulate the activity of abnormal brain regions and their networks, thereby improving their behavioral performance. However, there are currently few reports on the use of this method to improve insomnia by regulating brain function in patients with ID and depression.

[0052] Figure 1 The flowchart of the emotion regulation training method based on rtfMRI-NF technology is shown. In an embodiment of the present invention, an emotion regulation training method based on rtfMRI-NF technology includes steps S100 to S500:

[0053] Step S100: Scan the user's structure image to obtain a standard model;

[0054] The user is scanned structurally to obtain a standard model. The scanning process in this step does not place too many requirements on the user. Regardless of whether the user is in an agitated or calm state, the scanned "contour" is roughly the same, which is the above-mentioned standard model.

[0055] Step S200: performing a static scan on the user based on a preset scanning instruction to obtain collected data, performing spatial standardization processing on the collected data according to the standard model, and obtaining and displaying a dynamic model;

[0056] Step S200 is the resting state scanning process, and the user is told to relax and close his eyes as much as possible without any mental activity. Each resting state scan lasts for 6 minutes and 30 seconds, and collects data at 260 time points. In fact, the standard of resting state is very vague, as long as it is different from that of users in a restless state. As for the specific reason, for people with ID symptoms, relaxation itself is not an easy thing.

[0057] Step S300: showing the preset training process to the user, acquiring and displaying the activity information of the user's brain area, and querying and feeding back the adjustment strategy in the preset adjustment strategy library according to the activity information of the brain area;

[0058] Step S300 is a specific execution step. First, let the user become familiar with the training process. This process can be completed using some flowcharts. Then, the activity information of the user's brain area is obtained in real time. With the help of the preset adjustment strategy library, the feedback adjustment strategy can be queried. According to the feedback adjustment strategy, the user can intentionally adjust the activity of the brain area, thereby stabilizing emotions and improving sleep.

[0059] Step S400: stop the feedback regulation strategy, obtain and display the activity information of the user's brain area, and obtain the user's autonomous regulation ability value;

[0060] After step S300, the user adjusts the activity of the target brain area according to the experience and strategy of previous training, and observes whether the subject can complete the adjustment of the target brain area without feedback information. The experimental paradigm is the same as neurofeedback training. Before and after each training, the user's emotional state is measured by an emotion-related scale to generate an autonomous adjustment ability value. Everyone's attention ability is different, so different people's adjustment ability after training is also different.

[0061] Step S500: When the user's autonomous regulation ability value reaches a preset regulation threshold, a resting state scan is performed on the user after a preset time period to obtain collected data and generate an evaluation report.

[0062] When the user's self-regulation ability reaches a certain level, the user is asked to rest for about five minutes in a calm state, and then the resting state data is collected. The purpose of this process is to verify the training effect.

[0063] Furthermore, in the method, each resting-state scan lasts for 6 minutes and 30 seconds, and data from 260 time points are collected; each time a preset training process is displayed to the user, activity information of the user's brain area is obtained and displayed, and an adjustment strategy is queried and fed back in a preset adjustment strategy library based on the activity information of the brain area. Training is performed for 3 rounds, using a block design, resting for 30 seconds, adjusting the target brain area for 30 seconds each, alternating for 3 times, and lasting for 6 minutes and 20 seconds; the step of adjusting the target brain area includes up-regulation and down-regulation.

[0064] As a preferred embodiment of the technical solution of the present invention, the steps of performing structural image scanning and resting state scanning on the user include:

[0065] Scan the user and generate a magnetic resonance scan image sequence in real time;

[0066] Preprocessing the magnetic resonance scan image sequence to obtain a preprocessed magnetic resonance scan image;

[0067] Corresponding target data is extracted from the preprocessed magnetic resonance scan image according to a preset algorithm.

[0068] Specifically, the preprocessing of the magnetic resonance scan image sequence to obtain the preprocessed magnetic resonance scan image includes:

[0069] Performing format conversion on the magnetic resonance scanning image sequence;

[0070] The magnetic resonance scanning image sequence after format conversion is corrected, standardized and interference removed.

[0071] In one example of the present invention, after scanning the user and generating a magnetic resonance scan image sequence in real time, the magnetic resonance scan image sequence can be preprocessed, specifically, including format conversion of the magnetic resonance scan image sequence and correction, standardization and interference removal of the format-converted magnetic resonance scan image sequence, thereby obtaining a preprocessed magnetic resonance scan image, and then extracting corresponding target data from the preprocessed magnetic resonance scan image according to a preset algorithm, thereby obtaining real-time processed scan image data. In this embodiment, the processed scan image data can also be displayed to the user in real time, so that the user can also understand the relevant magnetic resonance data in a timely manner.

[0072] Figure 2 The first sub-flow chart of the emotion regulation training method based on rtfMRI-NF technology is shown, and the step of obtaining and displaying the activity information of the user's brain area includes:

[0073] Step S301: obtaining activity information of the user's brain area;

[0074] Step S302: Feedback and adjust the activity information of the brain area by means of a thermometer and a curve;

[0075] The height of the thermometer indicates the percentage of signal change of the current target brain region relative to the baseline signal, and the curve indicates the signal intensity curve of the target brain region.

[0076] During training, the activity information of the regulating brain area is fed back in the form of a thermometer and a curve. The patients are told that the information they obtain represents the activity of the emotion-related brain area, and they need to use a certain strategy to up-regulate or down-regulate the activity of the brain area. If the strategy used in the previous simulation is not effective, the subjects can try to use a different emotion induction strategy. The height of the thermometer indicates the percentage change of the signal of the current target brain area relative to the baseline signal, and the curve indicates the signal intensity curve of the target brain area.

[0077] Figure 3 The second sub-flow chart of the emotion regulation training method based on rtfMRI-NF technology is shown, and the step of querying and feeding back the regulation strategy in the preset regulation strategy library according to the activity information of the brain area includes:

[0078] Step S303: inputting the activity information of the brain region into the trained emotion analysis model to obtain the user emotion parameters;

[0079] Step S304: determining an adjustment strategy according to the user emotion parameter; wherein the adjustment strategy at least includes a visual adjustment strategy;

[0080] Step S305: when the adjustment strategy is a visual adjustment strategy, extracting and displaying a stimulation image from a preset stimulation image library according to the user's emotional parameters; wherein the stimulation image library includes parameter items and image items.

[0081] The user's emotional parameters are generally in a scoring system, for example, 100 points means very happy and 0 points means very depressed, and the standards are pre-set; there can be many feedback adjustment strategies, such as stimulation from the aspects of vision, taste, touch, hearing and smell, and these sensory stimulations can affect people's mood; among them, vision and hearing are the easiest to implement under the background of existing computer technology, and visual feedback is easier to monitor than auditory feedback. Therefore, in the above content, a basic limitation is made on the adjustment strategy, that is, the adjustment strategy at least includes a visual adjustment strategy.

[0082] The adjustment strategy is determined by the preparatory work. The adjustment strategy is related to the user emotion parameter. Each user emotion parameter has a corresponding adjustment strategy for adjusting the user emotion parameter to a preset range.

[0083] Figure 4The third sub-process flowchart of the emotion regulation training method based on rtfMRI-NF technology is shown, and the step of generating the stimulus image library includes steps S3051 to S3055:

[0084] Step S3051: pre-collect fMRI data, and train an image semantic real-time classification model and a visual attention real-time decoding model;

[0085] First, the process of generating the stimulus image library requires the use of an image semantic real-time classification model and a visual attention real-time decoding model. Step S3051 is the step of training these two models, and its input is fMRI data. It should be noted that the fMRI data in step S3051 is the fMRI data of a "sample user", and there are many "sample users".

[0086] Step S3052: extracting images to be inspected from a preset library of images to be inspected in sequence, and displaying the images to be inspected to the user as visual stimulation;

[0087] Step S3053: collecting the first fMRI data in real time, and using the image semantic classification model to determine the semantic category of the image to be tested;

[0088] Step S3052 to step S3053 is the execution process, extracting the image to be tested from the preset library of images to be tested, and then displaying it to the user. Based on the user's reaction, the meaning of the image to be tested to the user is determined. It is worth mentioning that the image to be tested is random and can be downloaded from the Internet. The same image may have different meanings to different people. For example, some people feel at ease when seeing images of rainy days, while some people feel annoyed when seeing images of rainy days. Therefore, different images to be tested need to be "assigned".

[0089] Step S3054: displaying the image to be inspected and the corresponding semantic category to the user, acquiring second fMRI data in real time, inputting the second fMRI data into the visual attention real-time decoding model, and verifying the recognition result of the image semantic classification model;

[0090] Step S3055: When the recognition result of the image semantic classification model passes the verification, a stimulus image library is generated according to the semantic category and the corresponding image to be tested.

[0091] Step S3054 to step S3055 is a verification module, which is used to verify whether the above-mentioned "assignment" result is correct.

[0092] Furthermore, the steps of pre-collecting fMRI data and training an image semantic real-time classification model and a visual attention real-time decoding model include:

[0093] Users pre-participate in a brain region registration and positioning experiment, an image semantic classification training experiment, and a visual attention classification training experiment, collect corresponding fMRI data, and train a real-time image semantic classification model based on support vector machine and a real-time visual attention decoding model.

[0094] Specifically, the step of extracting the images to be inspected from a preset library of images to be inspected in sequence and displaying the images to be inspected to the user as visual stimulation includes:

[0095] The images to be tested are extracted from the preset image library and displayed to the user, and fMRI data is collected at the same time; wherein, the stimulation duration is 3 TRs;

[0096] The stimulus images are semantically classified based on the trained image semantic real-time classification model, and the entire data preprocessing and classification process is completed within 1 TR.

[0097] In addition, it is characterized in that the step of displaying the image to be inspected and the corresponding semantic category to the user, acquiring the second fMRI data in real time, inputting the second fMRI data into the visual attention real-time decoding model, and verifying the recognition result of the image semantic classification model includes:

[0098] The image to be inspected and the corresponding semantic category are displayed to the user, and the image to be inspected and the corresponding semantic category are placed on both sides of the visual stimulation screen respectively; wherein the user gives feedback on whether the semantic category is correct through visual attention, if the category is correctly determined, the user pays attention to the semantic category, if the category is wrong, the user pays attention to the image to be inspected, and the visual attention interaction process lasts for 2 TRs;

[0099] The user's visual attention information is calculated based on the visual attention real-time decoding model to verify the recognition result of the image semantic classification model; wherein, the data preprocessing and visual attention decoding process are completed within 1 TR; the result of visual decoding is displayed to the user through the visual stimulation screen in the next TR.

[0100] The functions that can be achieved by the emotion regulation training method based on rtfMRI-NF technology are all completed by a computer device, and the computer device includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories. The program code is loaded and executed by the one or more processors to achieve the functions of the emotion regulation training method based on rtfMRI-NF technology.

[0101] The processor takes out instructions from the memory one by one, analyzes the instructions, and then completes the corresponding operations according to the instruction requirements, generating a series of control commands, so that the various parts of the computer can automatically, continuously and coordinately move to become an organic whole, realize the input of programs, the input of data, and the calculation and output of results. The arithmetic operations or logical operations generated in this process are all completed by the operator; the memory includes a read-only memory (ROM), which is used to store computer programs, and a protection device is provided outside the memory.

[0102] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0103] Those skilled in the art will understand that the description of the above service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, etc.

[0104] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire user terminal.

[0105] The memory can be used to store computer programs and / or modules. The processor can realize various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as an information collection template display function, a product information release function, etc.); the data storage area can store data created according to the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to release, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0106] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the modules / units in the above-mentioned embodiment system, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program can realize the functions of the above-mentioned various system embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0107] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0108] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An emotion regulation training method based on rtfMRI-NF technology, characterized in that: The method comprises: Scan the user's structure image to obtain a standard model; Performing a static scan on the user based on a preset scanning instruction to obtain collected data, performing spatial standardization processing on the collected data according to the standard model, and obtaining and displaying a dynamic model; Displaying a preset training process to the user, acquiring and displaying the activity information of the user's brain area, and querying and feeding back the adjustment strategy in a preset adjustment strategy library according to the activity information of the brain area; Stop the feedback regulation strategy, obtain and display the activity information of the user's brain area, and obtain the user's autonomous regulation ability value; When the user's self-regulation ability value reaches a preset regulation threshold, a resting state scan is performed on the user after a preset time period to obtain collected data and generate an evaluation report; The step of querying and feeding back the regulation strategy in a preset regulation strategy library according to the activity information of the brain region comprises: Inputting the activity information of the brain region into a trained emotion analysis model to obtain user emotion parameters; Determining an adjustment strategy according to the user emotion parameter; wherein the adjustment strategy at least includes a visual adjustment strategy; When the adjustment strategy is a visual adjustment strategy, a stimulation image is extracted and displayed from a preset stimulation image library according to the user's emotional parameters; wherein the stimulation image library includes parameter items and image items; The step of generating the stimulus image library comprises: Collect fMRI data in advance and train the image semantic real-time classification model and visual attention real-time decoding model; Extracting images to be inspected from a preset library of images to be inspected in sequence, and displaying the images to be inspected to a user as a visual stimulus; Acquire the first fMRI data in real time, and use the image semantic real-time classification model to determine the semantic category of the image to be tested; The image to be inspected and the corresponding semantic category are displayed to a user, a second fMRI data is collected in real time, the second fMRI data is input into the visual attention real-time decoding model, and a recognition result of the image semantic classification model is verified; When the recognition result of the image semantic classification model passes the verification, generating a stimulus image library according to the semantic category and the corresponding image to be tested; The step of displaying the image to be inspected and the corresponding semantic category to the user, acquiring the second fMRI data in real time, inputting the second fMRI data into the visual attention real-time decoding model, and verifying the recognition result of the image semantic classification model includes: The image to be inspected and the corresponding semantic category are displayed to the user, and the image to be inspected and the corresponding semantic category are placed on both sides of the visual stimulation screen respectively; wherein the user gives feedback on whether the semantic category is correct through visual attention, if the category is correctly determined, the user pays attention to the semantic category, if the category is wrong, the user pays attention to the image to be inspected, and the visual attention interaction process lasts for 2 TRs; The user's visual attention information is calculated based on the visual attention real-time decoding model to verify the recognition result of the image semantic classification model; wherein, the data preprocessing and visual attention decoding process are completed within 1 TR; the result of visual decoding is displayed to the user through the visual stimulation screen in the next TR.

2. The emotion regulation training method based on rtfMRI-NF technology according to claim 1, characterized in that: In the method, each resting-state scan lasts for 6 minutes and 30 seconds, and data from 260 time points are collected; each time a preset training process is displayed to the user, activity information of the user's brain area is obtained and displayed, and when the adjustment strategy is queried and fed back in a preset adjustment strategy library based on the activity information of the brain area, three rounds of training are performed, using a block design, resting for 30 seconds, adjusting the target brain area for 30 seconds each, alternating for 3 times, and lasting for 6 minutes and 20 seconds; the step of adjusting the target brain area includes up-regulation and down-regulation.

3. The emotion regulation training method based on rtfMRI-NF technology according to claim 1, characterized in that: The steps of performing structural imaging and resting state scanning on a user include: Scan the user and generate a magnetic resonance scan image sequence in real time; Preprocessing the magnetic resonance scan image sequence to obtain a preprocessed magnetic resonance scan image; Corresponding target data is extracted from the preprocessed magnetic resonance scan image according to a preset algorithm.

4. The emotion regulation training method based on rtfMRI-NF technology according to claim 3, characterized in that: The preprocessing of the magnetic resonance scan image sequence to obtain a preprocessed magnetic resonance scan image comprises: Performing format conversion on the magnetic resonance scanning image sequence; The magnetic resonance scanning image sequence after format conversion is corrected, standardized and interference removed.

5. The emotion regulation training method based on rtfMRI-NF technology according to claim 1, characterized in that: The step of obtaining and displaying the activity information of the user's brain area comprises: Obtain activity information of the user's brain area; Feedback and regulation of brain activity information in the form of thermometers and curves; The height of the thermometer indicates the percentage of signal change of the current target brain region relative to the baseline signal, and the curve indicates the signal intensity curve of the target brain region.

6. The emotion regulation training method based on rtfMRI-NF technology according to claim 5, characterized in that: The steps of pre-collecting fMRI data and training an image semantic real-time classification model and a visual attention real-time decoding model include: Users pre-participate in a brain region registration and positioning experiment, an image semantic classification training experiment, and a visual attention classification training experiment, collect corresponding fMRI data, and train a real-time image semantic classification model based on support vector machine and a real-time visual attention decoding model.

7. The emotion regulation training method based on rtfMRI-NF technology according to claim 6, characterized in that: The step of sequentially extracting the images to be inspected from a preset library of images to be inspected and displaying the images to be inspected to the user as visual stimulation includes: The images to be tested are extracted from the preset image library and displayed to the user, and fMRI data is collected at the same time; wherein, the stimulation duration is 3 TRs; The stimulus images are semantically classified based on the trained image semantic real-time classification model, and the entire data preprocessing and classification process is completed within 1 TR.

Images