Double-target synchronous stimulation method and system based on magnetic stimulator

Abstract

The invention discloses a double-target synchronous stimulation method and system based on a magnetic stimulator, and belongs to the field of medical instruments. The method comprises the steps of determining a first comprehensive behavior feedback value of a user; determining a first basic stimulation frequency of the first target spot and a second basic stimulation frequency of the second target spot; calculating a first adjustment stimulation frequency of the first target and a second adjustment stimulation frequency of the second target according to the first comprehensive behavior feedback value, the first basic stimulation frequency and the second basic stimulation frequency; and controlling the magnetic stimulator to perform double-target synchronous stimulation according to the first adjustment stimulation frequency and the second adjustment stimulation frequency. The scheme can ensure that the frequency and the intensity of each treatment are suitable for the current health condition and the treatment target of the patient. By automatically calculating the stimulation frequency and intensity and adjusting parameters, interference of manual operation is reduced, it is ensured that each treatment has high consistency and standardization, the repeatability of treatment can be improved, and it is ensured that the treatment effect is more stable.

Description

Technical Field

[0001] The present application relates to the field of medical device technology, and in particular to a dual-target synchronous stimulation method and system based on a magnetic stimulator. Background Art

[0002] As a non-invasive physical therapy method, the magnetic stimulator uses the pulsed magnetic field generated by the magnetic field coil to directly act on the cerebral cortex, improve neural electrical activity by regulating neural excitability, and safely and effectively treat Parkinson's disease, stroke, depression and other diseases, providing patients with new treatment options and hope for recovery.

[0003] The existing magnetic stimulator treatment process includes equipment preparation and inspection, patient preparation, and determination of treatment parameters including stimulation frequency and intensity based on the patient's condition and treatment goals. The magnetic stimulator is then used to accurately locate the patient and implement treatment.

[0004] However, the existing magnetic stimulator treatment process lacks sufficient consideration of the patient's real-time status and treatment response, and the treatment parameters are often based on preset values, which may limit the personalization and maximization of the treatment effect, and fail to make full use of real-time feedback to optimize the treatment experience. Summary of the invention

[0005] The present application provides a dual-target synchronous stimulation method and system based on a magnetic stimulator, which solves the problem that the existing magnetic stimulator treatment process lacks sufficient consideration of the patient's real-time status and treatment response, and the treatment parameters are often based on preset values, which may limit the personalization and maximization of the treatment effect, and fails to make full use of real-time feedback to optimize the treatment experience.

[0006] According to the first aspect of the present application, a dual-target synchronous stimulation method based on a magnetic stimulator is provided, the method comprising:

[0007] Obtaining a first cognitive performance feedback value, a first emotional response score feedback value, and a first physiological data feedback value of the user, and generating a first comprehensive behavior feedback value according to the first cognitive performance feedback value, the first emotional response score feedback value, and the first physiological data feedback value;

[0008] Acquire the condition data and treatment target data of the user, determine a first basal stimulation frequency of a first target point according to the condition data and the treatment target data, and determine a second basal stimulation frequency of a second target point;

[0009] Calculating a first adjusted stimulation frequency of the first target according to the first comprehensive behavior feedback value, the first basic stimulation frequency, and a preset calculation formula for the first target stimulation intensity, and calculating a second adjusted stimulation frequency of the second target according to the first comprehensive behavior feedback value, the second basic stimulation frequency, and a preset calculation formula for the second target stimulation intensity;

[0010] The magnetic stimulator is controlled to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency.

[0011] According to a second aspect of the present application, a dual-target synchronous stimulation system based on a magnetic stimulator is provided, the system comprising:

[0012] A comprehensive evaluation module, used to obtain a first cognitive performance feedback value, a first emotional response score feedback value, and a first physiological data feedback value of the user, and generate a first comprehensive behavior feedback value according to the first cognitive performance feedback value, the first emotional response score feedback value, and the first physiological data feedback value;

[0013] A basic stimulation frequency determination module, used to obtain the condition data and treatment target data of the user, determine a first basic stimulation frequency of a first target point according to the condition data and the treatment target data, and determine a second basic stimulation frequency of a second target point;

[0014] an adjustment stimulation frequency determination module, configured to calculate a first adjustment stimulation frequency of a first target according to the first comprehensive behavior feedback value, a first basic stimulation frequency, and a preset calculation formula for the first target stimulation intensity, and to calculate a second adjustment stimulation frequency of a second target according to the first comprehensive behavior feedback value, a second basic stimulation frequency, and a preset calculation formula for the second target stimulation intensity;

[0015] A control module is used to control the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency.

[0016] In the embodiment of the present application, the user's first cognitive performance feedback value, first emotional response score feedback value and first physiological data feedback value are obtained, and a first comprehensive behavior feedback value is generated according to the first cognitive performance feedback value, the first emotional response score feedback value and the first physiological data feedback value; the user's disease data and treatment target data are obtained, and the first basic stimulation frequency of the first target is determined according to the disease data and the treatment target data, and the second basic stimulation frequency of the second target is determined; the first adjustment stimulation frequency of the first target is calculated according to the first comprehensive behavior feedback value, the first basic stimulation frequency and the preset first target stimulation intensity calculation formula, and the second adjustment stimulation frequency of the second target is calculated according to the first comprehensive behavior feedback value, the second basic stimulation frequency and the preset second target stimulation intensity calculation formula; the magnetic stimulator is controlled to perform dual-target synchronous stimulation according to the first adjustment stimulation frequency and the second adjustment stimulation frequency. Through the above-mentioned dual-target synchronous stimulation method based on the magnetic stimulator, by determining the basic stimulation frequency of each target according to the disease data and the treatment target, and then adjusting it in combination with the patient's feedback value, it can be ensured that the frequency and intensity of each treatment are most suitable for the patient's current health condition and treatment goal. By automatically calculating the stimulation frequency, intensity, and adjusting the parameters, the interference of human operation is reduced, ensuring that each treatment is highly consistent and standardized, which helps to improve the repeatability of the treatment and ensure a more stable treatment effect.

[0017] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0019] Figure 1 It is a flow chart of a dual-target synchronous stimulation method based on a magnetic stimulator provided in Example 1 of the present application;

[0020] Figure 2 It is a flow chart of a dual-target synchronous stimulation method based on a magnetic stimulator provided in Example 2 of the present application;

[0021] Figure 3 It is a structural schematic diagram of a dual-target synchronous stimulation system based on a magnetic stimulator provided in Example 4 of the present application;

[0022] Figure 4A block diagram of an exemplary electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0025] The following is a detailed description of the dual-target synchronous stimulation method based on a magnetic stimulator provided in the embodiment of the present application through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0026] Embodiment 1

[0027] Figure 1 : is a flow chart of a dual-target synchronous stimulation method based on a magnetic stimulator provided in Example 1 of the present application. Figure 1 As shown, the specific steps include:

[0028] S101, obtaining a user's first cognitive performance feedback value, a first emotional response score feedback value, and a first physiological data feedback value, and generating a first comprehensive behavior feedback value according to the first cognitive performance feedback value, the first emotional response score feedback value, and the first physiological data feedback value.

[0029] First of all, the usage scenario of this solution can be to obtain the user's cognitive, emotional and physiological feedback data, generate a comprehensive behavioral feedback value, and determine the basic stimulation frequency of the dual targets in combination with the disease condition and treatment target data, and then adjust the stimulation frequency based on the comprehensive behavioral feedback value and the preset formula, and finally realize the scenario of personalized synchronous stimulation of the dual targets by the magnetic stimulator.

[0030] Based on the above usage scenarios, it can be understood that the executor of the present application can be a dual-target synchronous stimulation system based on a magnetic stimulator that integrates the functions of determining document modality, determining document feature information, determining alternative topics, and determining target topics. No excessive limitations are made here.

[0031] In this solution, the first cognitive performance feedback value may be evaluation data of the user's cognitive ability, which may be obtained through various cognitive tests and is usually used to evaluate the patient's thinking, memory, attention, and other aspects.

[0032] The first emotional response score feedback value can be used to assess the user's emotional state at the beginning of the treatment. The emotional response can be quantified by standardized emotional assessment tools, which can help understand the user's emotional fluctuations or psychological state.

[0033] The first physiological data feedback value can reflect the physiological state of the user before treatment. The physiological data of the user is usually monitored by sensor devices, such as heart rate, blood pressure, skin galvanic response, electromyography, etc.

[0034] The first comprehensive behavior feedback value may be a comprehensive evaluation of the overall behavior state of the user, and usually combines the cognitive performance feedback value, the emotional response score feedback value, and the physiological data feedback value to obtain a comprehensive score.

[0035] Cognitive performance feedback values ​​usually reflect the user's performance in cognitive abilities (such as memory, attention, information processing, etc.). The way to obtain this data is usually through specific cognitive tests, which can include the Stroop test: used to measure reaction time, information processing speed, and cognitive flexibility. The user needs to identify the color of the color name, which corresponds to the color of the displayed text. Digital span test: used to assess the capacity of short-term memory and working memory. Test the user's memory by asking them to remember a series of numbers in reverse. Other cognitive tasks: such as digital symbol substitution tasks, attention concentration tasks, etc., are used to assess cognitive functions in different dimensions. These tests can be performed through professional cognitive assessment tools or on smart devices. The results obtained by the user during the test can be used as the first cognitive performance feedback value, which is usually expressed as a numerical value, indicating the test score or reaction time.

[0036] The emotional response score feedback value can be obtained by evaluating the user's emotional state (such as anxiety, depression, stress, etc.). This can be done through a standardized emotional assessment questionnaire or self-assessment scale. Specifically, it can include PHQ-9: used to assess the user's depressive symptoms. The higher the score, the more severe the depressive symptoms. GAD-7: used to assess the user's anxiety symptoms. Self-emotional assessment: You can use an emotional diary or a quick self-assessment scale to understand the user's emotional state for the day. The score can include emotional fluctuations (such as anxiety, depression, anger, etc.). These assessment tools derive a quantitative emotional response score through user self-scoring or clinical scoring, which can be used as the first emotional response score feedback value.

[0037] The physiological data feedback value can reflect the user's physiological state, and physiological parameters can be monitored in real time through various sensors. Specifically, heart rate: measured in real time through wearable devices (such as smart watches, heart rate belts, etc.), reflecting cardiovascular health and emotional responses. Galvanic skin response (GSR): reflects the user's physiological stress response and can be measured by galvanic skin response sensors. Blood pressure: measures the user's blood pressure status through a sphygmomanometer. Body temperature, blood oxygen: can be monitored through temperature sensors and pulse oximeters to provide feedback on physical health status. After collecting these physiological data, they are converted into numerical values ​​through physiological monitoring equipment as the first physiological data feedback value.

[0038] Then the first comprehensive behavior feedback value is formed by weighted average:

[0039] CBF1=w1×CBF cognitive +w2×CBF emotion +w3×CBF physio ;

[0040] Among them, CBF1 is the first comprehensive behavioral feedback value; w1 is the preset cognitive performance weight; CBF cognitive is the first cognitive performance feedback value; w2 is the preset emotional response weight; CBF emotion is the first emotional response score feedback value; w3 is the preset physiological data weight; CBF physio is the first physiological data feedback value.

[0041] S102, obtaining the user's condition data and treatment target data, determining a first basal stimulation frequency of a first target point according to the condition data and the treatment target data, and determining a second basal stimulation frequency of a second target point.

[0042] Condition data can be the patient's medical history, clinical manifestations, signs, symptoms of the current disease, and health status data related to treatment. These data may include: disease type (such as depression, chronic pain, anxiety, etc.), clinical assessment results (such as symptom score, course of disease, severity), patient's physical signs (such as physiological parameters, body temperature, blood pressure, etc.), and related examination results (such as imaging, laboratory test results, etc.).

[0043] Treatment goal data can describe the specific goals set during treatment, usually based on the patient's condition data and expected efficacy. These goal data can include: primary treatment goals (such as improving symptoms, reducing pain, improving cognitive function, etc.), secondary treatment goals (such as improving quality of life, improving sleep, etc.), and specific treatment indicators (such as target pain scores, cognitive ability scores, emotional stability, etc.).

[0044] The first target can refer to the first target area or part selected during the treatment process, which is usually directly related to the patient's condition. Depending on the different treatment methods (such as magnetic stimulation, neuromodulation, etc.), the target can be: a specific brain area (such as the left prefrontal lobe, hippocampus, etc.), a specific area in the nervous system, or a part of the body (such as pain points, muscle groups, etc.).

[0045] The first basic stimulation frequency may be an initial stimulation frequency determined according to the patient's condition, treatment goals, and characteristics of the first target point, and is usually the frequency used to start treatment in a treatment plan.

[0046] The second target can be the second target area selected during treatment, which is usually complementary to the first target or an area that needs to be regulated in multi-site treatment.

[0047] The second basic stimulation frequency can be an initial stimulation frequency setting for the second target point. It is a frequency that matches the treatment goal and the needs of the target point, and provides a preliminary setting frequency for subsequent treatment.

[0048] The condition data (e.g., diagnosis results, disease type, previous treatment records, etc.) can be obtained from the patient's historical medical records. These data can automatically read the treatment target data through the hospital's EMR system. Then the location of the two targets, the user's condition data, and the treatment target data are input into the machine learning model (the target location is selected by the doctor based on the condition and treatment goals), which can automatically calculate and adjust the target's basal stimulation frequency. The model will output the optimal basal stimulation frequency for each target based on the patient's individual differences, condition data, and treatment goals.

[0049] The model training steps are:

[0050] Define input and output: Input data: target location data, disease data, and treatment target data, where target location data: the location of the target can be a spatial coordinate (such as the coordinates of a specific area of ​​the brain) or a category information derived from a doctor's diagnosis (such as target type: cerebral cortex, thalamus, etc.). If it is a spatial coordinate, you can consider inputting the location into the model as a vector; if it is categorical information, you can perform category encoding. For spatial location, the input can be a vector [x, y, z], where [x, y, z] is the three-dimensional coordinate of the target. For target type, the input can be a categorical variable (such as "target A", "target B", etc.), and one-hot encoding can be used. The output data is the basic stimulation frequency of each target. Then read the historical disease data, historical treatment target data, their corresponding historical target locations, and the historical basic stimulation frequency of the historical target locations. Then convert the historical target location, historical disease data, and historical treatment target data into a format suitable for the model, especially perform one-hot encoding and other processing on categorical variables (such as target type), and form a data set based on the above data. Then select the model and algorithm. The model can choose the regression algorithm in supervised learning. The following are several possible choices: 1. Linear regression: If the relationship between the data is relatively simple, you can start with the most basic linear regression model. It is suitable for the linear relationship between the target location, disease data, treatment target data and stimulation frequency. 2. Random forest regression: Random forest is an integrated learning method that is suitable for dealing with nonlinear problems. It can handle more complex input data, automatically extract features from the data, and is suitable for situations where there is no clear linear relationship. 3. Gradient boosting regression: Gradient boosting is a regression method based on decision trees, which is suitable for dealing with complex feature interactions and nonlinear problems, especially when the data volume is large and the features are complex. 4. Neural network: If the input data is very complex and contains nonlinear relationships, a deep learning model (such as a multi-layer perceptron) may be a suitable choice. Neural networks can automatically extract features through multi-layer calculations and can handle complex patterns. 5. Support vector machine regression: Support vector machine regression is suitable for processing data with nonlinear relationships. It can map data to high-dimensional space through kernel functions and find the best regression line. 6. Reinforcement learning: If the model is to dynamically adjust the treatment plan in real time and optimize it based on the patient's real-time feedback, then reinforcement learning can be considered. Through the design of the reward function, reinforcement learning can gradually adjust and optimize the stimulation frequency so that the treatment plan maximizes the patient's treatment effect. The data set is then divided into a training set, a validation set, and a test set. The training set is used for model training, the validation set is used to adjust hyperparameters, and the test set is used to evaluate the performance of the model. Then select the loss function. Specifically, you can choose the mean square error (MSE). For regression problems, the mean square error is a commonly used loss function. The loss function can measure the difference between the predicted stimulation frequency and the actual treatment effect.Then use the training set data to train the model and optimize the model parameters (such as weights and biases) by minimizing the loss function (such as MSE). Use the validation set to evaluate the generalization ability of the model and adjust the hyperparameters (such as learning rate, regularization term, etc.). If there is overfitting, you can consider using cross-validation, regularization and other techniques. Use the test set to evaluate the final performance of the model to ensure that the model has good predictive ability on unknown data.

[0051] S103, calculating the first adjusted stimulation frequency of the first target according to the first comprehensive behavioral feedback value, the first basic stimulation frequency and the preset first target stimulation intensity calculation formula, and calculating the second adjusted stimulation frequency of the second target according to the first comprehensive behavioral feedback value, the second basic stimulation frequency and the preset second target stimulation intensity calculation formula.

[0052] The preset first target point stimulation intensity calculation formula and the preset second target point stimulation intensity calculation formula ky are formulas for adjusting the intensity of magnetic stimulation of each target point according to the patient's feedback data.

[0053] The first adjusted stimulation frequency and the second adjusted stimulation frequency can be new stimulation frequencies of each target point compared with the original basic frequency after feedback calculation, which will reflect the patient's treatment feedback and the response of the target point.

[0054] The first comprehensive behavior feedback value and the first basic stimulation frequency can be substituted into the preset first target stimulation intensity calculation formula to calculate the first adjustment stimulation frequency of the first target. The first comprehensive behavior feedback value and the second basic stimulation frequency can be substituted into the preset second target stimulation intensity calculation formula to calculate the first adjustment stimulation frequency of the first target.

[0055] On the basis of the above technical solution, optionally, the preset calculation formula for the first target point stimulation intensity is:

[0056] I1(t)=α·(B(t)) δ ·F1(t)+β·(1-B(t)) δ F2(t);

[0057] Wherein, I1(t) is the first adjustment stimulation frequency; α is the preset first target stimulation weight; (B(t)) is the first comprehensive behavior feedback value; δ is the preset behavior feedback adjustment factor; F1(t) is the first basic stimulation frequency of the first target;

[0058] The preset calculation formula for the second target stimulation intensity is:

[0059] I2(t)=β·(1-B(t)) δ F2(t);

[0060] Wherein, I2(t) is the second adjusted stimulation frequency; β is the preset second target stimulation weight; and F2(t) is the second basic stimulation frequency of the second target.

[0061] In this protocol, δ is used to control how the stimulation intensity is adjusted during treatment as different conditions (such as cognition, emotion, or physiological feedback) change. This parameter determines how the basic stimulation intensity is initially adjusted based on the patient's individual characteristics or treatment goals. It is generally set by the clinician based on the patient's condition, historical treatment feedback, and treatment plan. For example, for different diseases or target areas, the amplitude of the change in stimulation intensity may be different, so different δ values ​​need to be set.

[0062] α represents the relative importance or priority of the first target in the treatment process. It determines the relative impact of the first target stimulation intensity and other targets or treatment goals. A larger α means that the first target contributes more to the treatment effect, so a higher stimulation intensity or higher attention is required.

[0063] β represents the relative importance or priority of the second target in the treatment. By using β, the stimulation intensity of the second target can be controlled to balance the effects of the two targets.

[0064] Clinicians will set the initial weights based on historical treatment data of a large number of patients or the results of clinical studies. Based on the patient's condition and treatment goals and the patient's specific needs, these data can help doctors understand which targets have a greater impact on the treatment effect of a specific patient group, thereby adjusting α and β.

[0065] S104, controlling the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency;

[0066] A magnetic stimulator is a medical device that generates a high-intensity magnetic field through electromagnetic principles. It is usually used to treat neurological diseases such as depression, anxiety, chronic pain, cognitive impairment, etc. The magnetic stimulator acts on the brain or other target areas in a non-invasive way, using the intensity and frequency of the magnetic field to regulate neural activity. Common forms of magnetic stimulation include transcranial magnetic stimulation and repetitive transcranial magnetic stimulation.

[0067] The probe of the magnetic stimulator can be positioned at the exact position of the first target and the second target, and the stimulation parameters of the magnetic stimulator can be set according to the first adjustment stimulation frequency and the second adjustment stimulation frequency, and then the magnetic stimulator is started to perform dual-target synchronous stimulation. At this time, the magnetic stimulator will act on the two targets at the same time to apply electromagnetic stimulation.

[0068] In the embodiment of the present application, the user's first cognitive performance feedback value, first emotional response score feedback value and first physiological data feedback value are obtained, and a first comprehensive behavior feedback value is generated according to the first cognitive performance feedback value, the first emotional response score feedback value and the first physiological data feedback value; the user's disease data and treatment target data are obtained, and the first basic stimulation frequency of the first target is determined according to the disease data and the treatment target data, and the second basic stimulation frequency of the second target is determined; the first adjustment stimulation frequency of the first target is calculated according to the first comprehensive behavior feedback value, the first basic stimulation frequency and the preset first target stimulation intensity calculation formula, and the second adjustment stimulation frequency of the second target is calculated according to the first comprehensive behavior feedback value, the second basic stimulation frequency and the preset second target stimulation intensity calculation formula; the magnetic stimulator is controlled to perform dual-target synchronous stimulation according to the first adjustment stimulation frequency and the second adjustment stimulation frequency. Through the above-mentioned dual-target synchronous stimulation method based on the magnetic stimulator, by determining the basic stimulation frequency of each target according to the disease data and the treatment target, and then adjusting it in combination with the patient's feedback value, it can be ensured that the frequency and intensity of each treatment are most suitable for the patient's current health condition and treatment goal. By automatically calculating the stimulation frequency, intensity, and adjusting the parameters, the interference of human operation is reduced, ensuring that each treatment is highly consistent and standardized, which helps to improve the repeatability of the treatment and ensure a more stable treatment effect.

[0069] Embodiment 2

[0070] Figure 2 is a flow chart of a dual-target synchronous stimulation method based on a magnetic stimulator provided in Example 2 of the present application, such as Figure 2 As shown, the specific method includes the following steps:

[0071] S201, obtaining the user's Stroop test data, digit span test data and WCST test data, and determining a first cognitive performance feedback value according to the Stroop test data, digit span test data and WCST test data.

[0072] The Stroop test is a classic cognitive psychology test used to assess attention control and information processing speed. The test tests the subject's conflict resolution ability by asking the subject to match a color word with a stimulus that is inconsistent with the color itself. Stroop test data can be performance data in this test, which usually includes the following: Reaction time: The time required for the subject to answer correctly. Accuracy: The percentage of subjects who completed the test correctly. Number of errors: The number of questions that the subject answered incorrectly during the test. Then determine the Stroop test data using the following formula:

[0073] Stroop test data = a1×ReactionTime+a2×Accuracy+a3×ErrorCount

[0074] Among them, a1 is the preset reaction time weight; ReactionTime is the reaction time; a2 is the preset accuracy weight; Accuracy is the accuracy; a3 is the preset error count weight; Error Count is the error count.

[0075] The Digit Span Test is used to assess working memory and attention. In the test, the subject needs to hear a series of numbers and then repeat the numbers after hearing them. The difficulty of the test will gradually increase, and the tester will be required to recall the order and re-state the numbers in the correct order. Digit span test data usually includes: Direct Digit Span: The length of the digit sequence that the subject can correctly recall. Reverse Digit Span: The length of the digit sequence that the subject can correctly recall in reverse order. The digit span test data can be determined by the following formula:

[0076] Digital span test data = b1×Direct Span+b2×Reverse Span

[0077] Among them, b1 is the preset direct digital span weight; Direct Span is the direct digital span weight; b2 is the preset reverse digital span weight; Reverse Span is the reverse digital span.

[0078] WCST can be a cognitive psychology task used to assess cognitive flexibility, abstract reasoning ability, and problem-solving ability. In the test, subjects need to classify cards according to different rules and adjust their classification strategies based on feedback. WCST test data usually includes: Number of categories: the number of correct classifications completed. Number of errors: the number of incorrect classifications. The number of times the functional classification was completed for the first time. The WCST test data can be calculated using the following formula:

[0079] WCST test data = c1×Number+c2×Error+c3×First Correct

[0080] Among them, c1 is the preset category number weight; Number is the category number; c2 is the preset error number weight; Error is the number of errors; c3 is the preset function classification weight; First Correct is the number of times the function classification is completed for the first time.

[0081] The first cognitive performance feedback value can be an indicator calculated based on the results of multiple cognitive tests (such as Stroop, digit span test, WCST), which is used to evaluate the cognitive performance of the subject at a specific time point. It reflects the performance of the subject on these cognitive tasks and is usually calculated based on the following factors: Stroop test data (reaction time, accuracy, etc.), digit span test data (correct digit sequence length, etc.), WCST test data (number of errors, classification completion, etc.).

[0082] You can collect data from various tests (Stroop test data, digit span test data, and WCST test data). Since the scales and units of each test are different, the data of each test needs to be standardized to ensure that they can be compared under the same standard. Common standardization methods include: Z-score standardization: subtract the mean from each test data and divide it by the standard deviation. Percentage conversion: convert the test results into percentages to reflect relative performance. Then weight the standardized data according to certain weights to obtain the first cognitive performance feedback value. The first cognitive performance feedback value can be determined by the following formula:

[0083] First cognitive performance feedback value

[0084] =d1×Stroop test data+d2×Digit span test data+d3

[0085] ×WCST test data

[0086] Among them, d1 is the preset Stroop test data weight; d2 is the preset digit span test data weight; d3 is the preset WCST test data weight.

[0087] S202, obtaining a user's emotion self-assessment scale, and determining a first emotion response rating feedback value of the user according to the user's emotion self-assessment scale.

[0088] Emotional self-rating scales are tools used to assess an individual's current emotional state, usually consisting of a series of questions designed to understand an individual's emotional experience at a specific point in time. They are usually completed in a self-report format. Emotional self-rating scales can help quantify an individual's emotional state for assessment in psychology, medicine, or other fields.

[0089] The first emotional response score feedback value can be a value evaluated based on the results of the user's emotional self-assessment scale. It is a quantitative expression of the user's emotional state, usually used to reflect the intensity, duration and type of emotion. This value can be calculated by weighted average or through a certain model based on multiple items in the emotional scale (such as pleasure, activation, anxiety, depression, etc.).

[0090] Users fill out a self-assessment scale of emotions, such as the Self-Assessment Affective Scale (SAM) or DASS-21. These scales can be presented in the form of a questionnaire and require users to choose the appropriate answer based on their actual feelings. According to the design of the self-assessment scale of emotions, each dimension (such as pleasure, activation, depression, anxiety, etc.) will have a different scoring standard (such as a Likert scale, usually a scale of 1 to 5 or 1 to 7). These data need to be converted into standardized numerical values ​​(for example, Z-score standardization or normalization to a range of 0-100). For example, in the DASS-21 scale, the score of anxiety is a scale of 1-4 (such as: 1 = none, 4 = very severe). These scores may need to be converted into numerical form or normalized. Based on the standardized scale scores, the following methods can be used to calculate the first emotional response score feedback value: If the scale contains multiple dimensions (such as pleasure, activation, anxiety, depression, etc.), each dimension can be assigned a weight and a weighted average can be calculated. The results of all scales are standardized to a unified range (e.g., 0 to 100), and then a feedback value is synthesized based on the positive and negative values ​​of the emotion (e.g., pleasure is a positive emotion, anxiety is a negative emotion). The final output is the first emotional response score feedback value, which reflects the user's emotional state. In health management, psychological intervention or treatment, this feedback value will help formulate subsequent treatment or intervention strategies.

[0091] S203: Acquire the overall physiological data of the user, and determine a first physiological data feedback value of the user according to the overall physiological data of the user.

[0092] Overall physiological data can be a set of various data related to the individual's physiological state, usually used to reflect the individual's health status, physical state, or other physiological indicators. Specifically, overall physiological data can include the following categories: Heart rate: usually indicates the number of heartbeats per minute, reflecting heart health and physical activity level. Blood pressure: reflects the pressure generated when the heart pumps blood, usually including systolic pressure and diastolic pressure. Respiratory rate: the number of breaths per minute, usually related to the individual's lung function and metabolic state. Body temperature: reflects the thermal balance state in the individual's body, usually used to monitor whether there is infection or other health problems. Blood oxygen saturation: usually measured by a pulse oximeter, reflects the concentration of oxygen in the blood, indicating lung and heart function. Weight, height, BMI: by calculating the ratio of weight to height, it reflects the degree of obesity of the individual. These data can be collected in real time through various devices (such as sphygmomanometers, electrocardiographs, thermometers, pulse oximeters, smart bracelets, etc.).

[0093] The first physiological data feedback value may be a comprehensive feedback value obtained based on the overall physiological data of the user. This value is used to reflect the physiological state of the user, and it can be calculated based on multiple physiological parameters. This feedback value is usually used to assess the health status of the individual or whether there are potential physiological problems.

[0094] Different measurement tools or devices can be used to collect the user's physiological data. For example, heart rate data can be obtained through a smart bracelet, blood oxygen level can be obtained using a pulse oximeter, body temperature can be obtained using a thermometer, blood pressure can be obtained using a sphygmomanometer, etc. Ensure that the time and conditions of data collection are relatively consistent to ensure the accuracy and comparability of the data. Data can be collected through regular monitoring (such as every hour or every day) or during specific health examinations. Standardize or normalize the collected physiological data so that different indicators can be compared on the same scale. For example, the normal range of blood pressure is usually 90 / 60mmHg to 120 / 80mmHg, while the normal range of heart rate is 60-100bpm. Through standardization, these indicators can be converted to the same scale, such as a range of 0 to 100. For each physiological indicator, each physiological data is converted into a standardized score between 0 and 100, and then different weights are assigned to each physiological data item (such as heart rate, blood oxygen, body temperature, etc.), and then their weighted average is calculated. After the calculation is completed, a numerical value (for example, in the range of 0 to 100) is obtained, which can be used as the first physiological data feedback value.

[0095] S204: Generate a first comprehensive behavior feedback value according to the first cognitive performance feedback value, an emotional response score feedback value, and the first physiological data feedback value.

[0096] The first comprehensive behavior feedback value can be formed in the form of weighted average:

[0097] CBF1=w1×CBF cognitive +w2×CBF emotion +w3×CBF physio ;

[0098] Among them, CBF1 is the first comprehensive behavioral feedback value; w1 is the preset cognitive performance weight; CBF cognitive is the first cognitive performance feedback value; w2 is the preset emotional response weight; CBF emotion is the first emotional response score feedback value; w3 is the preset physiological data weight; CBF physio is the first physiological data feedback value.

[0099] S205, obtaining the user's condition data and treatment target data, determining a first basal stimulation frequency of a first target point according to the condition data and the treatment target data, and determining a second basal stimulation frequency of a second target point.

[0100] S206, calculating the first adjusted stimulation frequency of the first target according to the first comprehensive behavioral feedback value, the first basic stimulation frequency and the preset first target stimulation intensity calculation formula, and calculating the second adjusted stimulation frequency of the second target according to the first comprehensive behavioral feedback value, the second basic stimulation frequency and the preset second target stimulation intensity calculation formula.

[0101] S207: Control the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency.

[0102] In this embodiment, cognitive data such as the Stroop test, the digit span test, and the WCST test, and physiological and emotional data such as the emotional self-rating scale and overall physiological data are integrated to generate a first comprehensive behavioral feedback value, which can provide users with comprehensive and personalized health feedback and greatly improve the accuracy, effectiveness, and experience of health management and treatment.

[0103] On the basis of the above technical solution, optionally, after controlling the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency, the method further includes:

[0104] updating the overall physiological state data of the user in real time, and obtaining the overall pain data of the user in real time, inputting the preset behavior feedback adjustment factor, the overall physiological state data and the overall pain data into a preset adjustment model, and determining whether the preset behavior feedback adjustment factor needs to be updated;

[0105] If the preset behavior feedback adjustment factor needs to be updated, the preset behavior feedback adjustment factor is updated through a preset adjustment model;

[0106] Acquire the brain activity monitoring data of each target point of the user, the physiological state data of each target point, and the pain data of each target point in real time, input the preset first target stimulation weight, the preset second target stimulation weight, the brain activity monitoring data of each target point, the physiological state data of each target point, and the pain data of each target point into the preset adjustment model, and determine whether the preset first target stimulation weight and the preset second target stimulation weight need to be updated;

[0107] If the preset first target stimulation weight and the preset second target stimulation weight need to be updated, the preset first target stimulation weight and the preset second target stimulation weight are updated by using a preset adjustment model;

[0108] Accordingly, after updating the preset first target stimulation weight and the preset second target stimulation weight by using the preset adjustment model, the method further includes:

[0109] The preset first target stimulation intensity calculation formula is updated according to the updated preset behavior feedback adjustment factor and the preset first target stimulation weight, and the preset second target stimulation intensity calculation formula is updated according to the updated preset behavior feedback adjustment factor and the preset second target stimulation weight.

[0110] In this solution, overall pain data can refer to the user's pain perception level over a certain period of time, which is usually quantified by a standardized pain scale or scoring system. Common pain assessment tools include: Visual analog scale: allows users to select a value from 0 to 10 to express the intensity of pain, 0 represents no pain, and 10 represents the most severe pain. Numerical scoring method: users select a number from 1 to 10 to indicate the intensity of pain. Pain mask: used to assess the nature and intensity of pain and its impact on mood and function. These data can be collected from user self-reports, clinical observations, or sensors (such as pressure sensors, galvanic skin response, etc.) to monitor changes in pain in real time.

[0111] The preset adjustment model can be a computational model or algorithm, usually implemented through machine learning or a rule engine, which is used to dynamically adjust parameters such as behavioral feedback factors and stimulation weights based on real-time acquired physiological, brain area activity, pain and other data. The purpose of the adjustment model is to ensure that intervention measures (such as magnetic stimulation, etc.) can be adjusted to the real-time state of the individual to achieve the best effect. The model can update the preset parameters in real time based on the user's physiological and psychological state. For example: Behavioral feedback adjustment factor: adjust the stimulation frequency or intensity based on real-time cognitive performance, emotional feedback and physiological data. Stimulation weight: In the case of dual-target stimulation, adjust the relative weight of each target based on real-time feedback to ensure the accuracy of the stimulation.

[0112] Brain activity monitoring data can be real-time data reflecting the activity of different brain regions collected through electroencephalogram, functional magnetic resonance imaging, near-infrared spectroscopy or other brain function monitoring equipment. These data are helpful in analyzing the response patterns of the brain, especially when performing neural regulation (such as magnetic stimulation). Electroencephalogram: It measures the electrical activity of the brain through electrodes and is often used to analyze the activity status of different brain regions, such as alpha waves, beta waves, etc.

[0113] Functional magnetic resonance imaging: indirectly reflects brain activity by detecting changes in cerebral blood flow. Near-infrared spectroscopy: evaluates brain activity by detecting changes in the concentration of oxygenated hemoglobin in the brain.

[0114] The physiological state data of each target point can be the physiological response of a specific target area during treatment or stimulation. These data do not involve the physiological state of the whole body, but focus on the specific area stimulated during treatment. Specifically, they may include: local blood flow (such as blood circulation in the skin or muscle area), local skin temperature: especially during heat therapy, cold therapy or other local stimulation, temperature changes in the stimulated area may affect the treatment effect. Local skin electrical response: Unlike the whole body GSR, the local skin electrical response reflects the activity of the skin sweat glands in the stimulated area.

[0115] The pain data of each target may refer to the feedback on the pain level for each target during or after stimulation. These data are usually collected through self-reporting or sensing devices. Each target may correspond to a different part or goal. For example, stimulation of a head target and a back target may result in different pain responses. Pain data may include: Pain intensity: Record the user's subjective perception of pain through scales such as VAS and NRS. Pain location: Record the specific area where the pain occurs to help identify which target stimulation causes the pain. Pain duration: Measures the duration of pain, reflecting the degree of discomfort of the stimulation to the user.

[0116] The overall physiological state data can come from wearable devices or real-time monitoring systems. Common devices include heart rate monitors, blood pressure monitors, thermometers, skin galvanic response sensors, breathing sensors, etc. The physiological data collected in real time needs to be connected to the data processing platform through sensors. The platform needs to clean, filter, synchronize and standardize the collected data to ensure the accuracy and stability of the data. By setting the data transmission and processing frequency, the real-time update of the physiological state data can be achieved. The device and data processing system need to have low-latency response capabilities. The overall pain data is usually obtained through the user's subjective feedback (such as pain rating scales or questionnaires) and possible auxiliary sensors (such as pain rating sensors, body surface temperature sensors, etc.). The user's pain state can be inferred through regular surveys or users actively feedback their pain feelings during treatment, combined with physiological sensor data. The pain state is quantified in real time based on the pain score (for example, a scoring system from 0 to 10) and physiological data (such as muscle tension, skin galvanic response, etc.). The above data is then input into the preset adjustment model, and the model needs to determine whether to update the behavioral feedback adjustment factor based on these inputs. This process can be achieved through a feedback control system. For example, when the overall physiological data and pain data deviate from the expected threshold, the model may require adjustment of the behavioral feedback factor. The output of the model determines whether the behavioral feedback adjustment factor needs to be updated. The model can determine whether an update is needed based on certain rules, algorithms, or thresholds. If an update is needed, it can be done through the calculation formula of the adjustment factor. For example, weighted average, optimization algorithm or other control strategy can be used to update the factor so that future feedback and treatment adjustments are more accurate.

[0117] Then, real-time data monitoring is performed on each target. Common methods include using electroencephalogram (EEG), functional magnetic resonance imaging (fMRI), local electromyography (EMG), skin galvanic response sensors, temperature sensors, etc. According to the characteristics of each target, its brain area activity, local physiological state (such as blood flow, muscle reaction, temperature) and pain perception are analyzed. The data of each target will be monitored and fed back separately. The data of each target (including brain area activity, local physiological state and pain data) and the preset stimulation weights of the first target and the second target are input into the model. The model will calculate and adjust the weight of target stimulation based on these data. If the model determines that the physiological state or pain response of the target exceeds a certain threshold, the stimulation weight may be updated. The model outputs a new stimulation weight to control the stimulation intensity of the target. Finally, by updating the calculation results of the model and combining the user's real-time data, the weights of each factor in the formula are adjusted to achieve the best treatment effect.

[0118] The training steps for the preset adjustment model are:

[0119] First, historical data is collected: the user's overall physiological state data: such as heart rate, blood pressure, body temperature, respiratory rate, etc. The user's overall pain data: including pain score, pain area, pain changes, etc. Brain area activity monitoring data of each target: such as electroencephalogram (EEG) data, brain functional imaging data, etc. Physiological state data of each target: for example, physiological response data for a specific target, such as local blood flow changes, temperature changes, etc. Pain data of each target: pain perception data related to each target. Preset behavioral feedback adjustment factors: historical feedback factors used for model training, including previously adjusted factor values. Preset target stimulation weights: stimulation weights in historical data, used to learn the relationship between stimulation intensity and feedback adjustment. Ensure that all collected historical data are in the same format, remove noise and perform normalization. Extract important features from historical data to form a training set. Then train a multi-input model, the input features of which include historical overall physiological state data, pain data, brain area activity data, etc. The output of the model is behavioral feedback adjustment factors and target stimulation weights, that is, the model will predict the factors and stimulation weights that need to be adjusted under specific physiological and pain states. By using the behavioral feedback adjustment factors in historical data as target variables, the model learns how to optimize these factors based on physiological, pain, and brain activity data. Then, the loss is calculated based on the difference between the behavioral adjustment factors of historical feedback and the adjustment factors output by the model to optimize the model's predictive ability. Using optimization algorithms such as gradient descent, the model weights are iteratively updated to make the prediction results close to the expected feedback factors. The trained model can accept real-time updated user data (such as real-time physiological status, pain data, etc.) and adjust the behavioral feedback factors and target stimulation weights in real time based on these data.

[0120] In this solution, by updating physiological status, pain data, and brain activity monitoring data in real time, the system can dynamically adjust behavioral feedback factors and stimulation weights to achieve personalized and precise treatment. Continuous optimization is performed based on user changes to ensure the continuity and stability of treatment. At the same time, the intelligent adjustment process reduces manual intervention and improves the efficiency and convenience of treatment.

[0121] On the basis of the above technical solution, optionally, after updating the preset calculation formula for the first target stimulation intensity according to the updated preset first target stimulation weight, and updating the preset calculation formula for the second target stimulation intensity according to the updated preset second target stimulation weight, the method further includes:

[0122] Calculating a first adjusted stimulation frequency of the first target according to the first comprehensive behavior feedback value, the first basic stimulation frequency, and the updated preset calculation formula for the first target stimulation intensity, and calculating a second adjusted stimulation frequency of the second target according to the first comprehensive behavior feedback value, the second basic stimulation frequency, and the updated preset calculation formula for the second target stimulation intensity;

[0123] Controlling the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency;

[0124] Accordingly, after controlling the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency, the method further includes:

[0125] If it is identified that there is an updated preset behavior feedback adjustment factor and / or an updated preset first target stimulation weight and a preset second target stimulation weight, the preset first target stimulation intensity calculation formula is updated according to the updated preset behavior feedback adjustment factor and / or the updated preset first target stimulation weight, and the preset second target stimulation intensity calculation formula is updated according to the updated preset behavior feedback adjustment factor and / or the updated preset second target stimulation weight;

[0126] updating the first adjusted stimulation frequency of the first target according to the first comprehensive behavior feedback value, the first basic stimulation frequency, and the updated preset calculation formula for the first target stimulation intensity, and updating the second adjusted stimulation frequency of the second target according to the first comprehensive behavior feedback value, the second basic stimulation frequency, and the updated preset calculation formula for the second target stimulation intensity;

[0127] The magnetic stimulator is controlled to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency until the treatment process is completed.

[0128] In this solution, the first adjusted stimulation frequency of the first target can be calculated by combining these factors according to the first comprehensive behavior feedback value, the first basic stimulation frequency and the updated preset first target stimulation intensity calculation formula. Specifically, the stimulation frequency of the first target needs to be dynamically adjusted according to the user's comprehensive behavior feedback state. This process involves information obtained from the user's current physiological, emotional and cognitive data to accurately set the stimulation frequency to achieve the most optimized treatment effect. The calculation formula will combine the first basic stimulation frequency (which is the initial preset value) and the stimulation intensity calculation formula of the first target. This calculation formula will be dynamically adjusted according to the user's feedback value to determine the adjusted first target stimulation frequency. Similarly, the second adjusted stimulation frequency of the second target can also be calculated according to similar logic. By inputting the first comprehensive behavior feedback value, the second basic stimulation frequency and the updated preset second target stimulation intensity calculation formula, the adjustment frequency of the second target can be obtained. Here, the stimulation frequency of the second target also needs to comprehensively consider the user's current physiological, emotional and other states to ensure the accuracy and personalization of the treatment. After calculating the first adjusted stimulation frequency of the first target and the second adjusted stimulation frequency of the second target, these two frequencies will be used to control the magnetic stimulator to achieve synchronous stimulation of the two targets. This synchronous stimulation can ensure that the treatment process applies appropriate stimulation to the two targets at the same time, thereby achieving more effective treatment. During the treatment process, if an updated preset behavioral feedback adjustment factor, or an updated preset change in the first target stimulation weight and the second target stimulation weight is identified, the system will readjust the stimulation intensity calculation formula according to these updated values. In other words, when the preset behavioral feedback adjustment factor or the target stimulation weight changes, the updated formula will be used to recalculate the stimulation intensity of the first target and the second target. The updated factors and weights adjust the stimulation intensity calculation formula so that the stimulation frequency and intensity of each target are more in line with the treatment needs and the user's real-time status until the treatment process is completed.

[0129] In this solution, by continuously monitoring the user's physiological state, pain level, and behavioral feedback, the treatment strategy can be adjusted in a timely manner to ensure that the stimulation frequency and intensity always match the user's current state, thereby improving the effectiveness and comfort of the treatment.

[0130] Based on the above technical solution, optionally, the overall pain data of the user is obtained in real time, including:

[0131] The user's physiological stress index data, pain score data and facial expression images are acquired in real time, and the physiological stress index data, pain score data and facial expression images are input into a preset pain analysis model to obtain overall pain data.

[0132] In this solution, physiological stress index data can reflect the body's stress state by monitoring physiological responses, including but not limited to heart rate, blood pressure, respiratory rate, galvanic skin response (EDA), blood oxygen saturation (SpO2), body temperature, etc. These indicators reflect the body's response to pain, pressure or other stressors. Physiological monitoring equipment such as heart rate monitors, sphygmomanometers, respiratory monitors, galvanic skin response sensors, etc. can be used. Real-time data is collected and transmitted to the system for analysis.

[0133] Pain score data can be the patient's subjective report of pain perception, usually using a numerical rating scale (such as visual analog scale VAS, digital pain score NRS) or a descriptive scale to record the patient's assessment of the intensity of pain. It can be obtained through a patient self-assessment questionnaire (for example, NRS score 0-10, 0 represents no pain, 10 represents the most severe pain). It can also be obtained through interaction with the patient or through the automatic scoring system of the medical device.

[0134] The facial expression image can be an image of the user's face captured by a camera. Through image processing and facial recognition technology (such as expression recognition algorithm), the user's facial muscle activity is analyzed to evaluate his or her emotions and pain response. Common expressions include frowning, tight lips, etc., which are often associated with pain or discomfort. Real-time shooting can be performed using a high-definition camera or facial recognition equipment. Facial expression recognition technology (for example, OpenFace, Face++, etc.) is applied to analyze the user's facial expression.

[0135] The preset pain analysis model can be a multi-dimensional analysis model, which usually combines machine learning, data analysis and other technologies to integrate the user's physiological data, pain score data and facial expression data to obtain a comprehensive pain status assessment. The purpose of this model is to predict the user's pain perception based on multiple input data sources and provide data support for subsequent treatment or intervention.

[0136] Physiological stress index data, pain score data, and facial expression images can be obtained from sensors or devices in real time. Physiological stress index data is obtained by connecting to physiological monitoring equipment (such as heart rate belts, skin electrical sensors). Pain score data is obtained through the patient's self-assessment questionnaire (digital scale) or real-time input. Facial expression data is captured by a camera and analyzed in real time using an expression recognition algorithm. The collected data is then cleaned, normalized, and feature extracted to ensure that the data input to the model is standardized and avoids noise interference. The physiological data, pain score, and facial expression images are fused into a comprehensive data set for subsequent analysis. The integrated data is input into a preset pain analysis model. The model will derive "overall pain data" based on the input data, which may be a comprehensive pain score or pain level that reflects the user's current pain experience.

[0137] The training steps of the preset pain analysis model are:

[0138] A large amount of historical data can be collected, which should include: physiological stress index data: such as heart rate, blood pressure, skin galvanic response, respiratory rate, etc. Pain score data: for example, the patient's self-rating of pain (such as visual analog scale, digital rating scale, etc.). Facial expression image data: facial expression images obtained through the camera, these images are converted into numerical features through the expression recognition algorithm. Then remove missing values, outliers, duplicate data, etc. to ensure data quality. Label information such as pain score and pain level to ensure that the data can be aligned with the goal of model training. Different types of data may have different dimensions and distributions, and need to be normalized or standardized to ensure that the scale of all input data is consistent and suitable for model training. According to the needs of the model, extract effective features from the raw data. The feature extraction step is crucial to the performance of the model, usually including: physiological data features: such as average heart rate, heart rate variability, skin galvanic response, etc. Pain score features: directly use the patient's pain score data. Facial expression image features: extract numerical features of facial expressions, such as facial muscle activity intensity, facial expression changes, etc. through facial expression recognition algorithms (such as OpenFace, deep convolutional neural networks, etc.). Then create labels: Generate corresponding label data through the collected pain score data. Labels can be: pain severity (pain score) comprehensive score or value of overall pain perception (overall pain data). Then select the model architecture, multi-input model: The model needs to process different types of data at the same time, so a multi-input model (such as parallel input layer in neural network) would be an ideal choice. The main inputs include: physiological stress index data (such as heart rate, skin galvanic response, etc.) pain score data (provided by the user), facial expression image data (image features extracted by CNN). Model type: Deep neural network (DNN): suitable for processing high-dimensional data, especially when complex features need to be extracted from physiological data and images. Convolutional neural network (CNN): used to process facial expression image data and extract features from images. Regression model: suitable for predicting continuous pain scores (such as pain intensity or pain perception value). Then all input data (physiological stress index data, pain score data and facial expression image data) are passed into the neural network for forward propagation to calculate the model's predicted value. Use an appropriate loss function, such as mean square error (MSE), to measure the difference between the pain score predicted by the model and the true label. The gradient of the loss function is calculated through the back-propagation algorithm, and the parameters of the model (i.e., the weights of the neural network) are updated to minimize the prediction error. Common optimization algorithms (such as Adam, SGD, etc.) are used to update the model weights to improve the prediction accuracy. Then the training set and validation set are divided, and the validation set is used to evaluate the generalization ability of the model. Common evaluation indicators include: Prediction error: such as mean square error (MSE) or mean absolute error (MAE), which is used to measure the accuracy of pain score prediction.Training stability: Check whether the loss value of the model decreases steadily and whether there are signs of overfitting or underfitting. Further evaluate the stability and robustness of the model through cross-validation (such as K-fold cross-validation). Then adjust the hyperparameters of the model (such as learning rate, number of layers, number of neurons in each layer, etc.) to improve the performance of the model. Hyperparameter tuning can be performed using methods such as grid search, random search, or Bayesian optimization. An important value output by the model is the predicted overall pain perception data, that is, the predicted pain perception intensity based on physiological stress indicators, pain scores, and facial expression images.

[0139] In this solution, by acquiring physiological stress data, pain scores, and facial expression images in real time and combining them with pain analysis models, patients can be provided with more accurate and personalized pain management solutions, thereby improving the efficiency and effectiveness of treatment.

[0140] On the basis of the above technical solution, optionally, after controlling the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency until the treatment process is completed, the method further includes:

[0141] If the preset evaluation time interval is reached, obtaining the user's second cognitive performance feedback value, second emotional response score feedback value, and second physiological data feedback value, and generating a second comprehensive behavior feedback value according to the second cognitive performance feedback value, second emotional response score feedback value, and second physiological data feedback value;

[0142] A treatment effect score is calculated according to the first comprehensive behavior feedback value, the second comprehensive behavior feedback value and a preset scoring formula, and the treatment effect score is sent to a control center.

[0143] In this solution, the preset evaluation time interval refers to a specific time interval set during the treatment process. Whenever this time point is reached, the system will conduct an evaluation and generate a new comprehensive behavioral feedback value based on the feedback data to calculate the treatment effect score.

[0144] The second cognitive performance feedback value may refer to the user's cognitive performance score during the evaluation time interval. It may be measured through a series of standardized cognitive tests, questionnaires, task performance (such as memory, attention, reaction time, etc.). This data reflects the changes or improvements in cognitive ability during treatment.

[0145] The second emotional response score feedback value may refer to the emotional response score of the user within the evaluation time interval. It is usually measured by a standardized emotional scale (such as anxiety, depression, happiness, etc.) or physiological emotional response monitoring (such as facial expressions, heart rate changes, etc.). It reflects the changes in the user's emotional state.

[0146] The second physiological data feedback value may refer to the user's physiological data feedback (such as heart rate, skin galvanic response, body temperature, blood pressure, etc.) within the evaluation time interval, which can reflect the changes in the user's physiological stress or health status during the treatment process.

[0147] The second comprehensive behavior feedback value can be a comprehensive value calculated by combining the second cognitive performance feedback value, the second emotional response score feedback value and the second physiological data feedback value through a weighted formula. This is an indicator that comprehensively reflects the user's overall performance (cognition, emotion, physiology) and behavioral state within the evaluation time interval.

[0148] The preset scoring formula may be a predefined calculation method for calculating a treatment effect score according to different feedback values ​​(such as a first comprehensive behavior feedback value and a second comprehensive behavior feedback value).

[0149] The treatment effect score can be a quantitative indicator used to evaluate the user's performance and treatment effect during the treatment process. It is a result calculated based on multiple feedback data, reflecting whether the treatment is effective and whether the user's various indicators (cognition, emotion, physiology) have improved.

[0150] The control center can be a management and monitoring system that receives the treatment effect score and makes corresponding adjustments or decisions based on the score. The control center can be a software platform or automated system that is responsible for real-time tracking of treatment progress, evaluation of treatment effects, adjustment of treatment plans, and providing feedback to relevant personnel.

[0151] Every time a preset evaluation time interval is reached, the user's second cognitive performance feedback value, second emotional response score feedback value and second physiological data feedback value are collected again, and the second comprehensive behavior feedback value is calculated by weighted calculation. Then, the first comprehensive behavior feedback value and the second comprehensive behavior feedback value are substituted into the preset scoring formula to calculate the treatment effect score, and it is sent to the control center via wireless communication technology.

[0152] In this solution, the user's cognitive, emotional and physiological states are regularly evaluated, and real-time feedback is provided, and the treatment effect score is calculated in combination with the comprehensive behavioral feedback value. This mechanism can provide the control center with accurate treatment effect data, thereby achieving the goal of dynamically adjusting the treatment strategy and ensuring continuous optimization and personalized management of the treatment.

[0153] Based on the above technical solution, an optional, preset scoring formula is:

[0154]

[0155] Among them, Score is the treatment effect score; D i (t) is the second comprehensive behavior feedback value; D i(0) is the first comprehensive behavior feedback value; k is the preset behavior adjustment constant; t is the preset evaluation time interval.

[0156] Embodiment 3

[0157] Figure 3 is a schematic diagram of the structure of a dual-target synchronous stimulation system based on a magnetic stimulator provided in Example 3 of the present application, such as Figure 3 As shown, specifically including the following:

[0158] A comprehensive evaluation module 301 is used to obtain a first cognitive performance feedback value, a first emotional response score feedback value, and a first physiological data feedback value of the user, and generate a first comprehensive behavior feedback value according to the first cognitive performance feedback value, the first emotional response score feedback value, and the first physiological data feedback value;

[0159] A basic stimulation frequency determination module 302 is used to obtain the condition data and treatment target data of the user, determine a first basic stimulation frequency of a first target point according to the condition data and the treatment target data, and determine a second basic stimulation frequency of a second target point;

[0160] The stimulation frequency adjustment determination module 303 is used to calculate the first adjustment stimulation frequency of the first target according to the first comprehensive behavior feedback value, the first basic stimulation frequency and the preset first target stimulation intensity calculation formula, and to calculate the second adjustment stimulation frequency of the second target according to the first comprehensive behavior feedback value, the second basic stimulation frequency and the preset second target stimulation intensity calculation formula;

[0161] The control module 304 is used to control the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency.

[0162] Embodiment 4

[0163] Figure 4 A schematic block diagram of an electronic device 400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0164] The electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in the ROM 402 or a computer program loaded from the storage unit 408 into the RAM 404. In the RAM 404, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 404 are connected to each other via a bus 404. An I / O interface 405 is also connected to the bus 404.

[0165] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0166] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as the dual-target synchronous stimulation method based on a magnetic stimulator. For example, in some embodiments, the dual-target synchronous stimulation method based on a magnetic stimulator may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 404 and executed by the computing unit 401, one or more steps of the dual-target synchronous stimulation method based on a magnetic stimulator described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute the dual-target synchronous stimulation method based on a magnetic stimulator in any other appropriate manner (for example, by means of firmware).

[0167] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0168] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0169] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0170] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0171] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0172] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0173] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0174] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

[0175] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

[0176] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

Claims

1. A dual-target synchronous stimulation method based on a magnetic stimulator, characterized in that: The method comprises: Obtaining a first cognitive performance feedback value, a first emotional response score feedback value, and a first physiological data feedback value of the user, and generating a first comprehensive behavior feedback value according to the first cognitive performance feedback value, the first emotional response score feedback value, and the first physiological data feedback value; Acquire the condition data and treatment target data of the user, determine a first basal stimulation frequency of a first target point according to the condition data and the treatment target data, and determine a second basal stimulation frequency of a second target point; Calculating a first adjusted stimulation frequency of the first target according to the first comprehensive behavior feedback value, the first basic stimulation frequency, and a preset calculation formula for the first target stimulation intensity, and calculating a second adjusted stimulation frequency of the second target according to the first comprehensive behavior feedback value, the second basic stimulation frequency, and a preset calculation formula for the second target stimulation intensity; The magnetic stimulator is controlled to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency.

2. The method for synchronously stimulating two targets based on a magnetic stimulator according to claim 1, characterized in that: The preset calculation formula for the first target stimulation intensity is: I1(t)=α·(B(t)) δ ·F1(t)+β·(1-B(t)) δ ·F2(t); Wherein, I1(t) is the first adjustment stimulation frequency; α is the preset first target stimulation weight; (B(t)) is the first comprehensive behavior feedback value; δ is the preset behavior feedback adjustment factor; F1(t) is the first basic stimulation frequency of the first target; The preset calculation formula for the second target stimulation intensity is: I2(t)=β·(1-B(t)) δ ·F2(t); Wherein, I2(t) is the second adjusted stimulation frequency; β is the preset second target stimulation weight; and F2(t) is the second basic stimulation frequency of the second target.

3. The method for synchronously stimulating two targets based on a magnetic stimulator according to claim 1, characterized in that: Acquiring a first cognitive performance feedback value, a first emotional response score feedback value, and a first physiological data feedback value of a user, and generating a first comprehensive behavior feedback value according to the first cognitive performance feedback value, the first emotional response score feedback value, and the first physiological data feedback value, including: Acquire the user's Stroop test data, digit span test data, and WCST test data, and determine a first cognitive performance feedback value according to the Stroop test data, digit span test data, and WCST test data; Obtaining the user's emotional self-assessment scale, and determining the user's first emotional response rating feedback value according to the user's emotional self-assessment scale; Acquire the overall physiological data of the user, and determine a first physiological data feedback value of the user according to the overall physiological data of the user; A first comprehensive behavior feedback value is generated according to the first cognitive performance feedback value, an emotional response score feedback value, and the first physiological data feedback value.

4. The method for synchronously stimulating two targets based on a magnetic stimulator according to claim 3, characterized in that: After controlling the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency, the method further includes: updating the overall physiological state data of the user in real time, and obtaining the overall pain data of the user in real time, inputting the preset behavior feedback adjustment factor, the overall physiological state data and the overall pain data into a preset adjustment model, and determining whether the preset behavior feedback adjustment factor needs to be updated; If the preset behavior feedback adjustment factor needs to be updated, the preset behavior feedback adjustment factor is updated through a preset adjustment model; Acquire the brain activity monitoring data of each target point of the user, the physiological state data of each target point, and the pain data of each target point in real time, input the preset first target stimulation weight, the preset second target stimulation weight, the brain activity monitoring data of each target point, the physiological state data of each target point, and the pain data of each target point into the preset adjustment model, and determine whether the preset first target stimulation weight and the preset second target stimulation weight need to be updated; If the preset first target stimulation weight and the preset second target stimulation weight need to be updated, the preset first target stimulation weight and the preset second target stimulation weight are updated by using a preset adjustment model; Accordingly, after updating the preset first target stimulation weight and the preset second target stimulation weight by using the preset adjustment model, the method further includes: The preset first target stimulation intensity calculation formula is updated according to the updated preset behavior feedback adjustment factor and the preset first target stimulation weight, and the preset second target stimulation intensity calculation formula is updated according to the updated preset behavior feedback adjustment factor and the preset second target stimulation weight.

5. The method for synchronously stimulating two targets based on a magnetic stimulator according to claim 4, characterized in that: After updating the preset first target stimulation intensity calculation formula according to the updated preset first target stimulation weight, and updating the preset second target stimulation intensity calculation formula according to the updated preset second target stimulation weight, the method further includes: Calculating a first adjusted stimulation frequency of the first target according to the first comprehensive behavior feedback value, the first basic stimulation frequency, and the updated preset calculation formula for the first target stimulation intensity, and calculating a second adjusted stimulation frequency of the second target according to the first comprehensive behavior feedback value, the second basic stimulation frequency, and the updated preset calculation formula for the second target stimulation intensity; Controlling the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency; Correspondingly, after controlling the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency, the method further includes: If it is identified that there is an updated preset behavior feedback adjustment factor and / or an updated preset first target stimulation weight and a preset second target stimulation weight, the preset first target stimulation intensity calculation formula is updated according to the updated preset behavior feedback adjustment factor and / or the updated preset first target stimulation weight, and the preset second target stimulation intensity calculation formula is updated according to the updated preset behavior feedback adjustment factor and / or the updated preset second target stimulation weight; updating the first adjusted stimulation frequency of the first target according to the first comprehensive behavior feedback value, the first basic stimulation frequency, and the updated preset calculation formula for the first target stimulation intensity, and updating the second adjusted stimulation frequency of the second target according to the first comprehensive behavior feedback value, the second basic stimulation frequency, and the updated preset calculation formula for the second target stimulation intensity; The magnetic stimulator is controlled to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency until the treatment process is completed.

6. The method for synchronously stimulating two targets based on a magnetic stimulator according to claim 4, characterized in that: Get the user's overall pain data in real time, including: The user's physiological stress index data, pain score data and facial expression images are acquired in real time, and the physiological stress index data, pain score data and facial expression images are input into a preset pain analysis model to obtain overall pain data.

7. The method for synchronously stimulating two targets based on a magnetic stimulator according to claim 5, characterized in that: After controlling the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency until the treatment process is completed, the method further includes: If the preset evaluation time interval is reached, obtaining the user's second cognitive performance feedback value, second emotional response score feedback value, and second physiological data feedback value, and generating a second comprehensive behavior feedback value according to the second cognitive performance feedback value, second emotional response score feedback value, and second physiological data feedback value; A treatment effect score is calculated according to the first comprehensive behavior feedback value, the second comprehensive behavior feedback value and a preset scoring formula, and the treatment effect score is sent to a control center.

8. The method for synchronously stimulating two targets based on a magnetic stimulator according to claim 7, characterized in that: The default scoring formula is: Among them, Score is the treatment effect score; D i (t) is the second comprehensive behavior feedback value; D i (0) is the first comprehensive behavior feedback value; k is the preset behavior adjustment constant; t is the preset evaluation time interval.

9. A dual-target synchronous stimulation system based on a magnetic stimulator, used to perform the method according to any one of claims 1 to 8, characterized in that: The system comprises: A comprehensive evaluation module, used to obtain a first cognitive performance feedback value, a first emotional response score feedback value, and a first physiological data feedback value of the user, and generate a first comprehensive behavior feedback value according to the first cognitive performance feedback value, the first emotional response score feedback value, and the first physiological data feedback value; A basic stimulation frequency determination module, used to obtain the condition data and treatment target data of the user, determine a first basic stimulation frequency of a first target point according to the condition data and the treatment target data, and determine a second basic stimulation frequency of a second target point; an adjustment stimulation frequency determination module, configured to calculate a first adjustment stimulation frequency of a first target according to the first comprehensive behavior feedback value, a first basic stimulation frequency, and a preset calculation formula for the first target stimulation intensity, and to calculate a second adjustment stimulation frequency of a second target according to the first comprehensive behavior feedback value, a second basic stimulation frequency, and a preset calculation formula for the second target stimulation intensity; A control module is used to control the magnetic stimulator to perform dual-target synchronous stimulation according to the first adjusted stimulation frequency and the second adjusted stimulation frequency.

10. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8.

Images