Method and system for positive-feeling intervention based on personality difference and positive-feeling level

Abstract

The invention discloses a correctness intervention method and system based on personality difference and correctness level. The method comprises the following steps: acquiring brain wave monitoring data, neuroplasm level evaluation data and mind admission level evaluation data of a user; and inputting the neuroplasm level evaluation data and the mind admission level evaluation data of the user into a preset classification model to respectively output the probabilities of the user belonging to a high attention level and a high admission level, thereby respectively calculating the number of training days of the user in the four training modules in combination with brain wave monitoring data. And further forming a personalized metronome intervention scheme for the user. And permutation and combination are performed on the four training modules according to the number of days, and one training module is randomly selected as a daily training theme, so that daily training contents are pushed to the user for performing positive-thought intervention. According to the method, five factors, namely personality and mind are combined with electroencephalogram monitoring, so that the mind target is matched with mind training, and the mind evaluation accuracy and the mind training effect are improved.

Description

Technical Field

[0001] The invention relates to a mindfulness intervention method based on personality differences and mindfulness levels, and also relates to a corresponding mindfulness intervention system, belonging to the technical field of cognitive training. Background Art

[0002] Mindfulness, as a well-known form of meditation, has seen rapid development in research and practice in recent years. Mindfulness meditation is becoming increasingly popular around the world, which is closely related to the increasingly fast pace of life and the increasing pressure on people. Especially among the elite groups who are under much more pressure than ordinary people, mindfulness meditation has become synonymous with "healthy lifestyle". Practitioners focus on the "flow of breathing" to focus more on the present, improve concentration and relieve stress. Mindfulness meditation helps busy people find a way to "coexist" with stress, and has now become a healthy lifestyle recognized by major companies and mainstream elites.

[0003] At present, as a simple mindfulness audio output, the choice of audio in the form of "sound companionship" mainly depends on the trainee's independent choice and trial. The increase in spontaneity undoubtedly increases the trial and error rate at the expense of mindfulness safety. At the same time, the mixed content and difficulty of mindfulness products reduce the trainee's error tolerance, and current products do not conduct timely evaluation of the training effect of mindfulness trainees, which greatly reduces the effect and efficiency of mindfulness training, and safety is not well guaranteed.

[0004] With the increasing penetration of mindfulness, mindfulness training is being widely tried by a large number of people. An activity that is tried by a large number of people needs an "instruction manual" that not only indicates the appropriate groups of people for mindfulness training, how people with different needs and characteristics can choose the training that suits them, but also explains the adverse reactions of mindfulness, and provides timely intervention for people who have adverse reactions. Provide protective factors for people who want to try it, and ensure that they can conduct mindfulness training in a healthy, effective and safe manner. Summary of the invention

[0005] The primary technical problem to be solved by the present invention is to provide a mindfulness intervention method based on personality differences and mindfulness levels.

[0006] Another technical problem to be solved by the present invention is to provide a mindfulness intervention system based on personality differences and mindfulness levels.

[0007] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:

[0008] According to a first aspect of an embodiment of the present invention, a mindfulness intervention method based on personality differences and mindfulness levels is provided, comprising the following steps:

[0009] Based on the physiological data of the user, the percentile rank of the user's EEG frequency in the norm is obtained; and based on the preset personality scale and the mindfulness five-factor scale, the neuroticism level evaluation data and the mindfulness acceptance level evaluation data of the user are obtained in turn;

[0010] Inputting the neuroticism level assessment data and the mindfulness acceptance level assessment data of the user into a preset classification model to output the probability that the user belongs to a high attention level and the probability that the user belongs to a high acceptance level respectively;

[0011] Based on the probability that the user has a high attention level and a high acceptance level, combined with the percentage rank of the user's EEG frequency in the norm, the number of training days for the user in four training modules is calculated respectively to form a personalized mindfulness intervention program for the user; wherein the four training modules are: a high attention level training module, a low attention level training module, a high acceptance level training module and a low acceptance level training module, and each training module corresponds to a task library;

[0012] Based on the user's personalized mindfulness intervention program, the four training modules are randomly arranged and combined according to the number of days to form a training module set;

[0013] A training module is randomly selected from the training module set as the training theme of the day, and a preset number of training tasks are selected from the corresponding task library based on the training theme of the day as the training content of the day, so as to push the training content of the day to the user for mindfulness training;

[0014] When the user completes the training content for the day, a training module is randomly selected from the remaining training module set as the training topic for the next day, and this cycle is repeated until the user completes the personalized mindfulness intervention program.

[0015] Preferably, the neuroticism level assessment data and the mindfulness acceptance level assessment data of the user are input into a preset classification model to respectively output the probability that the user belongs to a high attention level and a high acceptance level, including:

[0016] Obtain user portraits and task portraits in the historical training library; wherein the user portraits include physiological monitoring data, neuroticism subscale data, and mindfulness five-factor scale data of historical users; the task portraits include task duration and benefit levels of historical users performing high attention level training, low attention level training, high acceptance level training, and low acceptance level training;

[0017] Based on the user portrait and task portrait, four different decision tree models are established using multinomial logistic regression:

[0018]

[0019] Based on four different decision tree models, the information x of the current user is input to output the probability that the user corresponds to high neuroticism and low mindfulness acceptance level, high neuroticism and high mindfulness acceptance level, low neuroticism and low mindfulness acceptance level, and low neuroticism and high mindfulness acceptance level;

[0020]

[0021] Among them, F kM (x) represents the k-th decision tree, k∈(1,4); m represents the m-th user; M represents the set of all users; c 1m I represents a decision tree calculation formula under the black box model; x represents user data; R 1m represents the set of all user data under the first decision tree; I represents the Ith time; exp represents the exponential function with the natural parameter e as the base.

[0022] Preferably, the training days of the user in the four training modules are calculated in the following manner:

[0023] Based on the four decision tree models, the user's high neuroticism probability p1 and high acceptance level probability p2 are calculated and output; wherein the high neuroticism probability p1 is equal to the sum of the probability of high neuroticism and low mindfulness acceptance level and the probability of high neuroticism and high mindfulness acceptance level, and the high acceptance level probability p2 is equal to the sum of the probability of low neuroticism and low mindfulness acceptance level and the probability of low neuroticism and high mindfulness acceptance level;

[0024] The number of training days for the user in the four training modules is calculated by the following formula:

[0025] Number of days of low attention level training = p 1* X, number of days of high attention level training = (1-p1)*Y, number of days of high acceptance level training = p 2* Z, number of days of training at low acceptance level = p2*Q;

[0026] Among them, X, Y, Z, and Q are the best mapping segmentation standard feature values ​​generated by the four decision tree models. The value obtained by weighting the percentile rank of the user's EEG frequency in the norm represents the optimal training time for the user if he or she fully possesses a certain personality trait and mindfulness acceptance type.

[0027] Preferably, before pushing the training content of the day to the user for mindfulness training, the method further includes:

[0028] Acquire the training environment selected by the user, so as to push the training content of the day to the user for mindfulness training in the training environment;

[0029] The training environment includes at least: a personal training scene and a virtual training room group training scene.

[0030] Preferably, the mindfulness intervention method further comprises:

[0031] Introducing an external neurofeedback monitoring device to initially collect the basic brain wave frequency characteristics of the user in a relaxed state and a focused state;

[0032] During the process of the user completing the training content of the day, continuously monitoring the brain wave frequency characteristics of the user;

[0033] When the user completes the training content of the day, the built-in analysis software of the external neurofeedback monitoring device is used to perform data analysis on the brain wave frequency characteristics of the user, thereby generating a brain wave frequency analysis report of the user's training of the day;

[0034] After the user completes the personalized mindfulness intervention program, a brain wave frequency analysis list of the user is generated based on the brain wave frequency analysis report of the user's daily training.

[0035] Preferably, during the process of the user completing the training content of the day, a softmax regression logarithmic loss function algorithm is used to dynamically adjust the next training task until the training content of the day is completed.

[0036] Preferably, during the process of the user performing mindfulness training, the user's daily mindfulness training data and objective training effects are collected;

[0037] When the user completes T / 2 days of mindfulness training, the mindfulness training data and objective training effect of the user in the first half of the period are formed; wherein T represents the total number of training days of the personalized mindfulness intervention program;

[0038] Inputting the mindfulness training data and objective training effects of the user in the first half of the cycle into four decision tree models for model iteration, so as to re-obtain the probability of the user corresponding to high neuroticism and low mindfulness acceptance level, high neuroticism and high mindfulness acceptance level, low neuroticism and low mindfulness acceptance level, and low neuroticism and high mindfulness acceptance level, and readjust the training days of the user in the four training modules;

[0039] Based on the readjusted number of training days of the user in the four training modules, daily training content is pushed to the user until the second half of the cycle of mindfulness training is completed.

[0040] According to a second aspect of an embodiment of the present invention, a mindfulness intervention system based on personality differences and mindfulness levels is provided, comprising:

[0041] Login unit, used for user registration and system login;

[0042] An evaluation unit, connected to the login unit, and having a built-in physiological data monitoring module, a personality assessment scale, and a mindfulness five-factor assessment scale, for respectively evaluating the user's EEG frequency, neuroticism level, and mindfulness acceptance level;

[0043] a classification unit connected to the evaluation unit and preset with a classification model to receive the neuroticism level evaluation data and the mindfulness acceptance level evaluation data of the user, and output the probability that the user belongs to a high attention level and a high acceptance level through the classification model;

[0044] a calculation unit connected to the classification unit and preset with a calculation model, so as to calculate the number of training days of the user in four training modules based on the probability that the user belongs to a high attention level and a high acceptance level, and in combination with the EEG frequency evaluation data of the user, so as to form a personalized mindfulness intervention program for the user; wherein the four training modules are: a high attention level training module, a low attention level training module, a high acceptance level training module and a low acceptance level training module, and each training module corresponds to a task library;

[0045] An intervention unit is connected to the computing unit and has the four training modules, so as to randomly arrange and combine the four training modules according to the number of days to form a training module set; and randomly extract a training module from the training module set as the training theme of the day, and extract a preset number of training tasks from the corresponding task library based on the training theme of the day as the training content of the day, so as to push the training content of the day to the user for mindfulness training; and when the user completes the training content of the day, randomly extract a training module from the remaining training module set again as the training theme of the next day, and repeat this cycle until the user completes the personalized mindfulness intervention plan.

[0046] Preferably, the mindfulness intervention system further comprises:

[0047] An environment selection unit, connected to the intervention unit, for allowing the user to select a training environment before pushing the training content of the day to the user for mindfulness training; wherein the training environment at least includes: a personal training scene and a virtual training room group training scene;

[0048] An external neurofeedback monitoring device is connected to the intervention unit to continuously monitor the brain wave frequency characteristics of the user while the user completes the personalized mindfulness intervention program.

[0049] According to a third aspect of an embodiment of the present invention, there is provided a mindfulness intervention system based on personality differences and mindfulness levels, comprising a processor and a memory, wherein the processor reads a computer program in the memory to execute the above-mentioned mindfulness intervention method.

[0050] Compared with the prior art, the present invention has the following technical effects:

[0051] (1) The user is evaluated by combining personality, five factors of mindfulness and EEG monitoring. Different and more targeted training modules are arranged according to the different personality traits and different levels of mindfulness acceptance of users. Compared with other mindfulness training or meditation apps, the app has added preliminary evaluation and assessment. It can examine whether users can benefit from mindfulness from the perspective of personality and the adaptability of mindfulness, the difficulty and safety of benefiting from mindfulness, and the most effective way to benefit from mindfulness. In this way, the matching of mindfulness goals and mindfulness training is achieved, and the effect of mindfulness meditation is evaluated and the frequency of mindfulness meditation is pushed based on the EEG frequency band, which improves the accuracy of mindfulness evaluation and the effect of mindfulness training.

[0052] (2) Form a personalized intervention plan for mindfulness meditation based on individual personality and mindfulness level traits. Users can be classified according to their different personality traits and mindfulness levels, so that different training modes and targeted plans can be pushed to them at different stages, increasing the scientific nature of self-help meditation push.

[0053] (3) It provides the freedom to choose the meditation environment, and enables the freedom to choose between group meditation and individual meditation environments for personal self-help meditation. Users can choose a mode based on their experience and feelings in the two modes of group training and individual training, or simply based on their preferences. This is more conducive to users having a sense of control over mindfulness training, and thus increasing their control over the training process and their own growth. A mode that suits them and a sense of control over their lives make users feel happy and increase their confidence and motivation in treating diseases.

[0054] (4) Provide a training adjustment mechanism with real-time feedback to improve the efficiency of meditation and reduce the safety issues of meditation. Improve the evaluation mechanism of traditional meditation evaluation methods, from indirect feedback of indicators to more intuitive neural feedback, improve the accuracy of evaluation results and refine the measurement of meditation effects. Further provide an effective monitoring mechanism for the occurrence of adverse reactions to meditation, and use factual feedback to ensure the safety of meditators. And further improve the efficiency of meditation on the basis of ensuring safety.

[0055] (5) The present invention realizes the neurofeedback tracking and evaluation of mindfulness training. It combines the user's specific brain wave frequency band characteristics to provide the user with a more suitable mindfulness intervention frequency band plan. Compared with the traditional self-service push mode of indiscriminate mindfulness audio frequency and mindfulness training content, it is more systematic and scientific, and can improve the safety and overall treatment efficiency of mindfulness training. At the same time, it can improve the user's conviction in the scientific nature of mindfulness, thereby improving their compliance and reducing their dropout rate.

[0056] (6) The training modules and content are adjusted in a timely manner according to the changes in the user's personality traits and the improvement of the user's mindfulness acceptance level. At the same time, the user's EEG frequency monitoring will timely and effectively push the sound frequency suitable for the user and monitor the user's mindfulness training status. Doctors can also adjust the user's treatment plan based on the data fed back by the software and monitoring equipment to achieve the best treatment effect for the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 An overall flow chart of a mindfulness intervention method based on personality differences and mindfulness levels provided in the first embodiment of the present invention;

[0058] Figure 2 A detailed flow chart of a mindfulness intervention method based on personality differences and mindfulness levels provided in the first embodiment of the present invention;

[0059] Figure 3 A structural diagram of a mindfulness intervention system based on personality differences and mindfulness levels provided in a second embodiment of the present invention;

[0060] Figure 4 This is a structural diagram of a mindfulness intervention system based on personality differences and mindfulness levels provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0061] The technical content of the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0062] The technical concept of the embodiment of the present invention is: by comprehensively evaluating and analyzing the physiological monitoring data of the user, the Big Five Personality Inventory Revised Edition-Neuroticism subscale evaluation data, and the Mindfulness Five Factor Scale evaluation data, the users are divided into four types according to the comprehensive evaluation results, namely: high neuroticism and low mindfulness acceptance level people, high neuroticism and high mindfulness acceptance level people, low neuroticism and high mindfulness acceptance level people, and low neuroticism and low mindfulness acceptance level people. Accordingly, four targeted intervention plans are formed for the four types of users, as follows:

[0063] ① High neuroticism and low mindfulness and acceptance level: a program that focuses on low attention and low acceptance level training, supplemented by high attention and high acceptance level training.

[0064] ② High neuroticism and high mindfulness acceptance level: a program that focuses on low attention level and high acceptance level training, supplemented by high attention level and low acceptance level training.

[0065] ③ Low neuroticism and high mindfulness and acceptance level: a program that focuses on high attention level and low acceptance level training, supplemented by low attention level and high acceptance level training.

[0066] ④ Low neuroticism and low mindfulness and acceptance level: a program that focuses on high attention and high acceptance level training, supplemented by low attention and low acceptance level training.

[0067] First embodiment

[0068] like Figure 1 and Figure 2 As shown, the first embodiment of the present invention provides a mindfulness intervention method based on personality differences and mindfulness levels, which specifically includes steps S1 to S7:

[0069] S1: Obtain the user's brain wave monitoring data and scale evaluation data.

[0070] In this embodiment, based on the user's physiological data, the user's EEG frequency percentile in the norm is obtained. In addition, based on the preset personality scale and the mindfulness five-factor scale, the user's neuroticism level evaluation data and mindfulness acceptance level evaluation data are obtained in turn.

[0071] Specifically, it includes steps S11 to S13:

[0072] S11: Obtain the percentile rank of the user's EEG frequency in the norm.

[0073] Neuroscience and psychology studies have shown that the five EEG frequency bands of delta (1-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), beta (13-30 Hz) and gamma (36-44 Hz) are closely related to various physiological and psychological activities of human beings. Therefore, in this embodiment, the EEG monitoring device is used to monitor the user's EEG to obtain the user's EEG frequency data.

[0074] In addition, based on historical data, the EEG frequency domain norms of historical users can be obtained. By comparing the user's EEG frequency data with the EEG frequency domain norms, the percentile rank of the user in the norm can be obtained, which is a real number between 0 and 1.

[0075] S12: Obtain the user's neuroticism level assessment data.

[0076] In this embodiment, the neuroticism subscale of the Big Five Personality Inventory (revised version) is used to assess the neurotic personality of the user, thereby obtaining the user's scores in the neuroticism subscale (ie, neuroticism level assessment data).

[0077] Users with a neurotic personality score of 38.8 or above are classified as high neuroticism, and the higher the score, the higher the neurotic personality level. Therefore, based on the total score of the user in the neuroticism subscale, it can be determined whether the user has a high attention level or a low attention level.

[0078] S13: Obtain the user's mindfulness acceptance level assessment data.

[0079] In this embodiment, the five-factor mindfulness scale is used to evaluate the user's mindfulness acceptance level, thereby obtaining the user's scores in the five-factor mindfulness scale (i.e., mindfulness acceptance level evaluation data).

[0080] The two levels of non-judge items and non-reaction items in the five-factor scale of mindfulness are used as the criteria for determining the acceptance level. Users with a score greater than 45 are classified as having a high mindfulness acceptance level, and the higher the score, the higher the acceptance level. Therefore, based on the user's total score in the five-factor scale of mindfulness, it can be determined whether the user has a high or low acceptance level.

[0081] S2: Input the user's neuroticism level assessment data and mindfulness acceptance level assessment data into a preset classification model to output the probability that the user belongs to a high attention level and a high acceptance level, respectively.

[0082] Specifically, it includes steps S21 to S23:

[0083] S21: Obtain user portraits and task portraits in the historical training library.

[0084] The user profile includes the physiological monitoring data, neuroticism subscale data, and mindfulness five-factor scale data of historical users. The task profile includes the task duration and benefit degree of historical users in high attention level training, low attention level training, high acceptance level training, and low acceptance level training.

[0085] S22: Based on user portraits and task portraits, four different decision tree models were established using multinomial logistic regression.

[0086] It can be understood that in this embodiment, since users are divided into four types: high neuroticism and low mindfulness acceptance level, high neuroticism and high mindfulness acceptance level, low neuroticism and low mindfulness acceptance level, and low neuroticism and high mindfulness acceptance level. Correspondingly, they correspond to: low attention level and low acceptance level training, low attention level and high acceptance level training, high attention level and low acceptance level training, and high attention level and high acceptance level training. Therefore, multinomial logistic regression (SoftmaxRegression) is used for classification, thereby establishing the following four decision tree models:

[0087]

[0088] S23: Based on four different decision tree models, input the current user's information x to output the probability that the user corresponds to high neuroticism and low mindfulness acceptance level, high neuroticism and high mindfulness acceptance level, low neuroticism and low mindfulness acceptance level, and low neuroticism and high mindfulness acceptance level;

[0089]

[0090] Among them, F kM (x) represents the k-th decision tree, k∈(1,4); m represents the m-th user; M represents the set of all users; c 1m I represents a decision tree calculation formula under the black box model; x represents user data; R 1m represents the set of all user data under the first decision tree; I represents the Ith time; exp represents the exponential function with the natural parameter e as the base.

[0091] It can be understood that in this embodiment, four different decision tree models together constitute the preset classification model. In addition, the probability of high neuroticism is equal to the sum of the probability of high neuroticism and low mindfulness acceptance level and the probability of high neuroticism and high mindfulness acceptance level; the probability of high acceptance level is equal to the sum of the probability of low neuroticism and low mindfulness acceptance level and the probability of low neuroticism and high mindfulness acceptance level.

[0092] S3: Develop a personalized mindfulness intervention plan for the user.

[0093] In this embodiment, after calculating the user's high neuroticism probability and high acceptance level probability based on the above step S2, the number of training days for the user in the four training modules is calculated in combination with the user's EEG frequency percentile in the norm, thereby forming a personalized mindfulness intervention plan for the user. The four training modules are: high attention level training module, low attention level training module, high acceptance level training module and low acceptance level training module, and each training module corresponds to a task library.

[0094] Specifically, it includes steps S31 to S32:

[0095] S31: Based on the four decision tree models, calculate and output the user's high neuroticism probability p1 and high acceptance level probability p2.

[0096] S32: The number of training days for the user in the four training modules is calculated by the following formula:

[0097] Number of days of low attention level training = p 1* X,

[0098] High attention level training days = (1-p1)*Y,

[0099] High acceptance level training days = p 2* Z,

[0100] Number of days of training at low acceptance level = p2*Q.

[0101] Among them, X, Y, Z, and Q are the best mapping segmentation standard feature values ​​generated by the four decision tree models. The value is weighted by the percentile rank of the user's EEG frequency in the norm, representing the optimal training time for the user if he or she fully possesses a certain personality trait and mindfulness acceptance type.

[0102] It is understandable that, for each user, the personalized mindfulness intervention program includes training content of four training modules, the difference being that the number of training days for each training module is different.

[0103] Below, the four training modules are described in detail:

[0104] A low attention level training module

[0105] Module A: Low-Attention-Level Thematic Mindfulness Training

[0106] Combined with the EEG frequency band characteristics, using audio training that matches the user's frequency band, it helps users to conduct two basic trainings, mindfulness breathing and body scanning exercises, to achieve low-intensity training at the level of attention monitoring and acceptance. This module mainly includes two aspects of exercises: mindfulness breathing training and body scanning exercises (low attention level). The detailed description is as follows:

[0107] a. Mindfulness breathing training

[0108] The audio training method aims to reduce distractions in the brain and relieve anxiety by focusing on breathing. The practice audio usually contains a gentle guiding voice, guiding the user to deeply observe the feeling of each inhalation and exhalation, and to maintain attention by counting and matching the rhythm of background music. This not only helps to reduce daily stress and enhance mindfulness, but also improves the ability to self-regulate emotional and physical reactions, thereby improving the overall quality of life and mental health.

[0109] b. Body scan exercise (low attention level)

[0110] The audio training method does not require the user to reach a certain state or high attention, but to be with each part of the body and be aware of the feeling of each part. Therefore, there is no need to expect any special effects, just to be aware and observe truthfully. It belongs to the practice of paying attention to and accepting the body level, which is low attention and low acceptance compared to the acceptance of emotions and thoughts.

[0111] It includes the following five units:

[0112] Output unit: presents the system content library visually and auditorily, and stores it in a personalized way;

[0113] Interaction unit: interact with users by touching and clicking the screen;

[0114] Observation unit: collects user’s EEG data;

[0115] Evaluation unit: Analyze the EEG data of users during meditation and generate user portrait reports;

[0116] Storage medium: stores the user's training plan, preset training content and daily updated training log, and stores the user's meditation development curve.

[0117] Module B: Mindful Environment Selection

[0118] Users can choose individual practice mode or join a virtual online practice group for training.

[0119] It includes the following three units:

[0120] Output unit: presents the system content library visually and auditorily, and stores it in a personalized way;

[0121] Interaction unit: interact with users by touching and clicking the screen;

[0122] Storage medium: stores the user's preset training mode.

[0123] 2. High Attention Level Training Module

[0124] Combined with the brainwave frequency characteristics, using audio training that matches the user's frequency band, it helps users to conduct training based on the three-step breathing space and mindfulness gratitude exercises to achieve low-intensity training at the level of attention monitoring and acceptance. This module mainly includes two aspects of exercises: three-step breathing space exercises and body scanning (high attention level) exercises. The detailed description is as follows:

[0125] Module C: High-level attention-focused thematic mindfulness training

[0126] a. Three-step breathing space exercise

[0127] Use audio to conduct the three-step breathing space training. The three-step breathing space is a very classic and relatively simple mindfulness meditation practice. This practice was developed by Professor Mark Williams of the Oxford Mindfulness Center and is the most important practice in mindfulness cognitive therapy. Through this practice, you can bring your attention back to your inner experience, reconnect with your body and mind, and then connect with the larger world with an expanded awareness.

[0128] b. Body scan exercise (high attention level)

[0129] Body scan practice using audio. The high-level body scan practice is a deep mindfulness practice that aims to increase connection and awareness with each part of the body through highly focused attention. This practice requires the user to be sensitive to the sensations in each part of the body, starting from the toes and gradually moving up to the head, carefully sensing the touch, temperature or inner movement of each area. This method encourages the practitioner to deeply understand and accept the body's feelings without any judgment or change.

[0130] This practice not only improves body awareness, but also helps improve emotional regulation and reduce stress. Through continuous practice, practitioners can achieve psychological and physiological balance and improve the quality of life. This type of deep awareness practice is suitable for individuals who already have a certain foundation and hope to improve concentration and self-awareness by enhancing body perception.

[0131] It includes the following five units:

[0132] Output unit: presents the system content library visually and auditorily, and stores it in a personalized way;

[0133] Interaction unit: interact with users by touching and clicking the screen;

[0134] Observation unit: collects user’s EEG data;

[0135] Evaluation unit: Analyze the EEG data of users during meditation and generate user portrait reports;

[0136] Storage medium: stores the user's training plan, preset training content and daily updated training log, and stores the user's meditation development curve.

[0137] Module D: Mindful Environment Selection

[0138] Users can choose individual practice mode or join a virtual online practice group for training.

[0139] It includes the following three units:

[0140] Output unit: presents the system content library visually and auditorily, and stores it in a personalized way;

[0141] Interaction unit: interact with users by touching and clicking the screen;

[0142] Storage medium: stores the user's preset training mode.

[0143] Three low-reception level training modules

[0144] Module E: Mindfulness training for low-receptive topics

[0145] Combined with the brain wave frequency characteristics, using audio training that matches the user's frequency band, it helps users to conduct training mainly based on mindfulness exercises and body gratitude exercises, so as to achieve low-intensity training at the level of attention monitoring and acceptance. This module mainly includes two aspects of exercises: mindfulness exercises and body gratitude exercises. The specific operation process is as follows:

[0146] a. Conceptual thinking exercises (low acceptance orientation)

[0147] Using audio training, the Mindfulness of Thoughts (Low Acceptance Orientation) is designed to help users learn how to keep a certain distance from their thoughts. This practice does not focus on analyzing specific negative emotions or thoughts, but rather observes one's own thinking patterns more broadly to cultivate a detached observer's perspective. During the practice, the audio-guided content includes a gentle guiding voice that teaches participants how to identify and observe their own thoughts instead of identifying or reacting to them. This method emphasizes acceptance and non-judgmental attitudes, encouraging participants to let thoughts flow freely without trying to control or change them.

[0148] Through this practice, participants can increase awareness of their own thinking habits and reduce automatic thought responses, ultimately helping to reduce psychological stress and increase mental resilience. This practice is particularly beneficial for those who wish to reduce overthinking and increase mental clarity.

[0149] b. Physical gratitude exercises

[0150] The audio-based mindfulness gratitude exercise mainly emphasizes gratitude for the body. Infusing love into oneself and improving the level of acceptance of the body, the exercise encourages users to be grateful for the hard work and effort of their body throughout the day, to look at themselves with kindness, and to accept their body. In this process, users gradually develop a positive acceptance of the body, which in turn helps to have a positive impact on real life.

[0151] It includes the following five units:

[0152] Output unit: presents the system content library visually and auditorily, and stores it in a personalized way;

[0153] Interaction unit: interact with users by touching and clicking the screen;

[0154] Observation unit: collects user brain data;

[0155] Evaluation unit: Analyze the EEG data of users during meditation and generate user portrait reports;

[0156] Storage medium: stores the user's training plan, preset training content and daily updated training log, and stores the user's meditation development curve.

[0157] Module F: Mindfulness Science Video

[0158] Mindfulness science videos can increase users' acceptance of mindfulness meditation. Popular science education explains the concepts, practical methods and scientific basis of mindfulness meditation, enabling people to better understand and use this practice.

[0159] The popular science video series on mindfulness meditation is based on the basic theory of mindfulness and the MBCT theory of mindfulness-based cognitive therapy. It aims to systematically introduce and teach the core concepts and practical skills of mindfulness meditation through an 8-week text and animation course. The course content mainly includes basic education on mindfulness (understanding the definition and background of mindfulness), mindfulness breathing practice (learning how to cultivate mindfulness by paying attention to breathing), body scanning (gradually becoming aware of each part of the body to enhance body awareness), emotional awareness training (learning how to observe and accept your emotions mindfully), cognitive reshaping to change negative cognition of stress and challenges), and daily application (applying mindfulness techniques to daily life to improve the quality of life), as well as summary and review. The first 6 weeks focus on learning new knowledge, and the last 2 weeks are dedicated to strengthening and consolidating knowledge.

[0160] There are fixed weekly and daily goals every week, combined with corresponding weekly and daily themes. Each popular science content takes about 3 minutes to learn, quickly providing key knowledge points to help users understand and remember easily. Through this structured and step-by-step learning method, users can effectively learn mindfulness meditation and integrate it into their lives to achieve a more peaceful and conscious lifestyle.

[0161] It includes the following three units:

[0162] Output unit: presents the system content library visually and auditorily, and stores it in a personalized way;

[0163] Interaction unit: interact with users by touching and clicking the screen;

[0164] Storage medium: stores the user's preset daily popular science content and daily updated popular science content.

[0165] Module G: Mindful Environment Selection

[0166] Users can choose individual practice mode or join a virtual online practice group for training.

[0167] It includes the following three units:

[0168] Output unit: presents the system content library visually and auditorily, and stores it in a personalized way;

[0169] Interaction unit: interact with users by touching and clicking the screen;

[0170] Storage medium: stores the user's preset training mode.

[0171] Four high acceptance level modules

[0172] Combined with the characteristics of brain wave frequency, using audio training that matches the user's frequency band, it helps users to conduct training mainly focusing on emotion observation training and mindfulness and loving-kindness training, so as to achieve a higher level of training in attention monitoring and acceptance and cultivate the ability to awaken positive emotions.

[0173] Module H: High-level Thematic Mindfulness Training

[0174] This module H mainly includes two exercises: emotion observation training and mindfulness and loving-kindness training. The specific operation process is as follows:

[0175] a. Emotion Observation Exercise

[0176] Using audio training, participants learn how to observe and accept their emotions, rather than over-identify with or judge them. The core of this practice is to cultivate the view of emotions as objective phenomena rather than part of personal identity. Through audio guidance, users are taught how to identify, name and calmly observe their emotional fluctuations without trying to control or change them.

[0177] The practice emphasizes an accepting and non-judgmental attitude toward all experienced emotions, which requires a high level of self-acceptance and emotional awareness. In this way, users can gradually learn how to remain calm and clear in the face of emotional stress, thereby improving their ability to cope with challenges in life. In the long term, this practice helps promote emotion regulation skills, enhance personal resilience and overall well-being. This practice is suitable for people who want to improve their emotion management skills, especially in dealing with stress, anxiety and depression.

[0178] b. Mindfulness and loving-kindness training

[0179] Using audio training, mindfulness and loving-kindness training is a very effective exercise to enhance positive emotions and happiness. Let the practitioner imagine or recall a good friend sitting in front of him, and then give kindness to the other person in his heart, generating feelings of love and joy. The object of imagination can be oneself or others, which will also bring different effects. It can awaken a variety of positive emotions, including love, joy, tranquility and other positive emotions. Blessing oneself or cultivating kindness towards oneself can improve one's attitude towards oneself, increase self-acceptance and reduce self-criticism. At the same time, self-care can help people truly accept themselves, and help people enhance self-control and make progress.

[0180] It includes the following five units:

[0181] Output unit: presents the system content library visually and auditorily, and stores it in a personalized way;

[0182] Interaction unit: interact with users by touching and clicking the screen;

[0183] Observation unit: collects user’s EEG data;

[0184] Evaluation unit: Analyze the EEG data of users during meditation and generate user portrait reports;

[0185] Storage medium: stores the user's training plan, preset training content and daily updated training log, and stores the user's meditation development curve.

[0186] Module I: Mindful Environmental Selection

[0187] Users can choose individual practice mode or join a virtual online practice group for training.

[0188] It includes the following three units:

[0189] Output unit: presents the system content library visually and auditorily, and stores it in a personalized way;

[0190] Interaction unit: interact with users by touching and clicking the screen;

[0191] Storage medium: stores the user's preset training mode.

[0192] S4: Push personalized mindfulness intervention plans to users for mindfulness intervention.

[0193] After the personalized mindfulness intervention plan for the user is obtained based on step S3, different daily training contents need to be pushed to the user according to specific push steps until the user completes the personalized mindfulness intervention plan.

[0194] Specifically, it includes steps S41 to S45:

[0195] S41: Form a training module set.

[0196] Specifically, based on the user's personalized mindfulness intervention plan, the four training modules are randomly arranged and combined according to the number of days to form a training module set. It can be understood that in this embodiment, the training module of each day can be regarded as an element in a module set, and the same training module trained at different times represents different elements in the module set.

[0197] For example: the user trains in the high attention level training module for 5 days, the low attention level training module for 3 days, the high acceptance level training module for 7 days, and the low acceptance level training module for 2 days, then the training module set includes 5+3+7+2=17 elements in total. The training module set can be obtained by randomly arranging and combining these 17 elements.

[0198] S42: Extract the user's training content for the day.

[0199] Specifically, a training module is randomly selected from the training module set as the training theme of the day. Then, based on the training theme of the day, a preset number of training tasks are selected from the corresponding task library as the training content of the day.

[0200] S43: Obtain the training environment selected by the user, so as to push the training content of the day to the user for mindfulness training in the training environment.

[0201] Among them, the training environment at least includes: personal training scenes and virtual training room group training scenes. As a result, users are provided with the freedom to choose the meditation environment, realizing the freedom to choose between group meditation and individual meditation environments. Users can choose the training environment based on their own experience and feelings in the two modes of group training and individual training, or simply from the perspective of preference, which is more conducive to the user's sense of control over mindfulness training, thereby increasing the control over the training process and the progress of their own growth. The mode that suits them and the sense of control over their lives make users feel happy and enhance their confidence and motivation for mindfulness meditation.

[0202] In addition, when the user completes the training content of the day, the logarithmic loss function algorithm of softmax regression is used to dynamically adjust the next training task until the training content of the day is completed.

[0203] In this embodiment, the dynamic adjustment process of the training task is: the logarithmic loss function algorithm of softmax regression is used to measure the accuracy of the model prediction by calculating the logarithmic probability difference between the true category and the predicted category. Specifically, for a given training data set, the softmax regression model outputs a probability distribution for each sample, indicating the possibility that the sample belongs to each category. Then, by calculating the logarithmic probability difference between the true category and the predicted category, the loss function value is obtained, and then the loss function is minimized by an optimization algorithm (such as gradient descent) to update the parameters of the model and improve the prediction accuracy of the model.

[0204] Among them, the specific calculation process of the loss function is as follows:

[0205] For each sample, the softmax regression model outputs a vector, each element of which represents the predicted probability that the sample belongs to a certain category.

[0206] The true category is represented by an element in the vector, which should have a value of 1 (for a binary classification problem) or more than 1 (for a multi-classification problem).

[0207] The loss function is obtained by summing the logarithmic product of the true category and the predicted probability of each sample. If the true category is j, the corresponding term in the loss function is -logP(y=j|x), where P(y=j|x) is the probability that the model predicts that sample x belongs to category j. It can effectively measure the difference between the model's predicted distribution and the true distribution.

[0208] By minimizing the loss function, that is, maximizing the probability of predicting the correct category, the softmax regression model can learn the optimal parameters, thereby improving the accuracy of predicting future data, and thus effectively measuring the difference between the model's predicted distribution and the true distribution.

[0209] S44: Repeat the above steps S42 to S43 until the user completes the personalized mindfulness intervention plan.

[0210] It is understandable that when the user completes the training content of the day, the number of training days for the corresponding training module is reduced by one, which is equivalent to reducing the number of elements in the training module set by one. Therefore, when training the next day, it is necessary to randomly select a training module from the remaining training module set as the training topic for the next day, and repeat this cycle until the user completes the personalized mindfulness intervention plan.

[0211] In addition, during the user's mindfulness intervention, an external neurofeedback monitoring device is introduced to initially collect the user's basic brain wave frequency characteristics in a relaxed state and a focused state. And, while the user is completing the day's training content, the user's brain wave frequency characteristics are continuously monitored. Therefore, after the user completes the day's training content, the user's brain wave frequency characteristics are analyzed using the built-in analysis software of the external neurofeedback monitoring device to generate a brain wave frequency analysis report for the user's training that day. After the user completes the personalized mindfulness intervention plan, a brain wave frequency analysis list for the user is generated based on the user's daily training brain wave frequency analysis report.

[0212] It can be understood that the training adjustment mechanism based on the real-time feedback provided by the external neural feedback monitoring device in this embodiment improves the efficiency of mindfulness meditation and reduces the occurrence of safety issues during mindfulness meditation. The evaluation mechanism of the traditional meditation evaluation method is improved, from indirect feedback of indicators to more intuitive neural feedback, to improve the accuracy of the evaluation results and the refined measurement of the effect of mindfulness meditation. Furthermore, an effective monitoring mechanism is provided for the occurrence of adverse reactions to meditation, using factual feedback to ensure the safety of meditators, and further improving the efficiency of meditation on the basis of ensuring safety.

[0213] In the above embodiment, preferably, in step S44, the following steps are further included:

[0214] S441: When the user is doing mindfulness training, the user's daily mindfulness training data and objective training effects are collected. Thus, when the user completes T / 2 days of mindfulness training, the user's mindfulness training data and objective training effects for the first half of the cycle are formed; wherein T represents the total number of training days of the personalized mindfulness intervention program.

[0215] S442: Input the user's mindfulness training data and objective training effects in the first half of the cycle into four decision tree models for model iteration to re-obtain the user's corresponding probabilities of high neuroticism and low mindfulness acceptance level, high neuroticism and high mindfulness acceptance level, low neuroticism and low mindfulness acceptance level, and low neuroticism and high mindfulness acceptance level, and readjust the user's training days in the four training modules.

[0216] S443: Pushing daily training content to the user based on the readjusted number of training days of the user in the four training modules until the second half of the mindfulness training is completed.

[0217] Second embodiment

[0218] like Figure 3As shown, based on the above-mentioned first embodiment, the second embodiment of the present invention provides a mindfulness intervention system based on personality differences and mindfulness levels, including a login unit 1, an evaluation unit 2, a classification unit 3, a calculation unit 4, an intervention unit 5, an environment selection unit 6 and an external neurofeedback monitoring device 7.

[0219] Specifically, the login unit 1 is used for user registration and system login.

[0220] The evaluation unit 2 is connected to the login unit 1, and has a built-in physiological data monitoring module, a personality assessment scale and a mindfulness five-factor assessment scale, which are used to evaluate the user's EEG frequency, neuroticism level and mindfulness acceptance level, respectively, so as to obtain the user's EEG frequency percentile rank in the norm, neuroticism level assessment data and mindfulness acceptance level assessment data.

[0221] The classification unit 3 is connected to the evaluation unit 2 and is preset with a classification model to receive the user's neuroticism level evaluation data and mindfulness acceptance level evaluation data, and output the probability that the user belongs to a high attention level and a high acceptance level through the classification model.

[0222] The calculation unit 4 is connected to the classification unit 3 and is preset with a calculation model to calculate the number of training days of the user in the four training modules based on the probability of the user belonging to a high attention level and a high acceptance level, and combined with the user's EEG frequency evaluation data, so as to form a personalized mindfulness intervention plan for the user.

[0223] The intervention unit 5 is connected to the calculation unit 4 and has four training modules, which are used to randomly arrange and combine the four training modules according to the number of days to form a training module set, and randomly extract a training module from the training module set as the training theme of the day, and extract a preset number of training tasks from the corresponding task library based on the training theme of the day as the training content of the day, so as to push the training content of the day to the user for mindfulness training. And, when the user completes the training content of the day, a training module is randomly extracted from the remaining training module set as the training theme of the next day, and this cycle is repeated until the user completes the personalized mindfulness intervention plan.

[0224] The environment selection unit 6 is connected to the intervention unit 5 so as to allow the user to select a training environment before the training content of the day is pushed to the user for mindfulness training.

[0225] The external neurofeedback monitoring device 7 is connected to the intervention unit 5 to continuously monitor the user's brain wave frequency characteristics while the user completes the personalized mindfulness intervention program.

[0226] Third embodiment

[0227] like Figure 4As shown, the third embodiment of the present invention further provides a mindfulness intervention system based on personality differences and mindfulness levels. The mindfulness intervention system includes one or more processors 21 and a memory 22. The memory 22 is coupled to the processor 21 and is used to store one or more programs. When the one or more programs are executed by the one or more processors 21, the one or more processors 21 implement the mindfulness intervention method based on personality differences and mindfulness levels in the above embodiment.

[0228] The processor 21 is used to control the overall operation of the mindfulness intervention system to complete all or part of the steps of the mindfulness intervention method based on personality differences and mindfulness levels. The processor 21 can be a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a digital signal processing (DSP) chip, etc. The memory 22 is used to store various types of data to support the operation of the mindfulness intervention system, and these data may include, for example, instructions for any application or method used to operate on the mindfulness intervention system, and application-related data. The memory 22 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, etc.

[0229] In an exemplary embodiment, the mindfulness intervention system can be implemented by a computer chip or entity, or by a product with a certain function, for executing the above-mentioned mindfulness intervention method based on personality differences and mindfulness levels, and achieving the same technical effect as the above-mentioned method. A typical embodiment is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0230] In another exemplary embodiment, the present invention further provides a computer-readable storage medium including program instructions, which, when executed by a processor, implements the steps of the mindfulness intervention method based on personality differences and mindfulness levels in any of the above embodiments. For example, the computer-readable storage medium may be the above-mentioned memory including program instructions, and the above-mentioned program instructions may be executed by a processor of a mindfulness intervention system to complete the above-mentioned mindfulness intervention method based on personality differences and mindfulness levels, and achieve the same technical effect as the above-mentioned method.

[0231] In summary, the mindfulness intervention method and system based on personality differences and mindfulness levels provided by the embodiments of the present invention have the following beneficial effects:

[0232] (1) The user is evaluated by combining personality, five factors of mindfulness and EEG monitoring. Different and more targeted training modules are arranged according to the different personality traits and different levels of mindfulness acceptance of users. Compared with other mindfulness training or meditation apps, the app has added preliminary evaluation and assessment. It can examine whether users can benefit from mindfulness from the perspective of personality and the adaptability of mindfulness, the difficulty and safety of benefiting from mindfulness, and the most effective way to benefit from mindfulness. In this way, the matching of mindfulness goals and mindfulness training is achieved, and the effect of mindfulness meditation is evaluated and the frequency of mindfulness meditation is pushed based on the EEG frequency band, which improves the accuracy of the evaluation of mindfulness effects and mindfulness training.

[0233] (2) Form a personalized intervention plan for mindfulness meditation based on individual personality and mindfulness level traits. Users can be classified according to their different personality traits and mindfulness levels, so that different training modes and targeted plans can be pushed to them at different stages, increasing the scientific nature of self-help meditation push.

[0234] (3) It provides the freedom to choose the meditation environment, and enables the freedom to choose between group meditation and individual meditation environments for personal self-help meditation. Users can choose a mode based on their experience and feelings in the two modes of group training and individual training, or simply based on their preferences. This is more conducive to users having a sense of control over mindfulness training, and thus increasing their control over the training process and their own growth. A mode that suits them and a sense of control over their lives make users feel happy and increase their confidence and motivation in treating diseases.

[0235] (4) Provide a training adjustment mechanism with real-time feedback to improve the efficiency of meditation and reduce the safety issues of meditation. Improve the evaluation mechanism of traditional meditation evaluation methods, from indirect feedback of indicators to more intuitive neural feedback, improve the accuracy of evaluation results and refine the measurement of meditation effects. Further provide an effective monitoring mechanism for the occurrence of adverse reactions to meditation, and use factual feedback to ensure the safety of meditators. And further improve the efficiency of meditation on the basis of ensuring safety.

[0236] (5) The present invention realizes the neurofeedback tracking and evaluation of mindfulness training. It combines the user's specific brain wave frequency band characteristics to provide the user with a more suitable mindfulness intervention frequency band plan. Compared with the traditional self-service push mode of indiscriminate mindfulness audio frequency and mindfulness training content, it is more systematic and scientific, and can improve the safety and overall treatment efficiency of mindfulness training. At the same time, it can improve the user's conviction in the scientific nature of mindfulness, thereby improving their compliance and reducing their dropout rate.

[0237] (6) The training modules and content are adjusted in a timely manner according to the changes in the user's personality traits and the improvement of the user's mindfulness acceptance level. At the same time, the user's EEG frequency monitoring will timely and effectively push the sound frequency suitable for the user and monitor the user's mindfulness training status. Doctors can also adjust the user's treatment plan based on the data fed back by the software and monitoring equipment to achieve the best treatment effect for the user.

[0238] It should be noted that the above embodiments are only examples, and the technical solutions of the various embodiments can be combined, all within the protection scope of the present invention.

[0239] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0240] The above is a detailed description of the mindfulness intervention method and system based on personality differences and mindfulness levels provided by the present invention. For those skilled in the art, any obvious changes made to it without departing from the essence of the present invention will constitute an infringement of the patent right of the present invention and will bear the corresponding legal liability.

Claims

1. A mindfulness intervention method based on personality differences and mindfulness levels, characterized by The steps include: Based on the physiological data of the user, the percentile rank of the user's EEG frequency in the norm is obtained; and based on the preset personality scale and the mindfulness five-factor scale, the neuroticism level evaluation data and the mindfulness acceptance level evaluation data of the user are obtained in turn; Inputting the neuroticism level assessment data and the mindfulness acceptance level assessment data of the user into a preset classification model to output the probability that the user belongs to a high attention level and the probability that the user belongs to a high acceptance level respectively; Based on the probability that the user has a high attention level and a high acceptance level, combined with the percentage rank of the user's EEG frequency in the norm, the number of training days for the user in four training modules is calculated respectively to form a personalized mindfulness intervention program for the user; wherein the four training modules are: a high attention level training module, a low attention level training module, a high acceptance level training module and a low acceptance level training module, and each training module corresponds to a task library; Based on the user's personalized mindfulness intervention program, the four training modules are randomly arranged and combined according to the number of days to form a training module set; A training module is randomly selected from the training module set as the training theme of the day, and a preset number of training tasks are selected from the corresponding task library based on the training theme of the day as the training content of the day, so as to push the training content of the day to the user for mindfulness training; When the user completes the training content for the day, a training module is randomly selected from the remaining training module set as the training topic for the next day, and this cycle is repeated until the user completes the personalized mindfulness intervention program.

2. The mindfulness intervention method according to claim 1, characterized in that Inputting the neuroticism level assessment data and the mindfulness acceptance level assessment data of the user into a preset classification model to output the probability that the user belongs to a high attention level and a high acceptance level, respectively, including: Obtain user portraits and task portraits in the historical training library; wherein the user portraits include physiological monitoring data, neuroticism subscale data, and mindfulness five-factor scale data of historical users; the task portraits include task duration and benefit levels of historical users performing high attention level training, low attention level training, high acceptance level training, and low acceptance level training; Based on the user portrait and task portrait, four different decision tree models are established using multinomial logistic regression: Based on four different decision tree models, the information x of the current user is input to output the probability that the user corresponds to high neuroticism and low mindfulness acceptance level, high neuroticism and high mindfulness acceptance level, low neuroticism and low mindfulness acceptance level, and low neuroticism and high mindfulness acceptance level; Among them, F kM (x) represents the k-th decision tree, k∈(1,4); m represents the m-th user; M represents the set of all users; c 1m I represents a decision tree calculation formula under the black box model; x represents user data; R 1m represents the set of all user data under the first decision tree; I represents the Ith time; exp represents the exponential function with the natural parameter e as the base.

3. The mindfulness intervention method according to claim 2, characterized in that The training days of the user in the four training modules are calculated as follows: Based on the four decision tree models, the user's high neuroticism probability p1 and high acceptance level probability p2 are calculated and output; wherein the high neuroticism probability p1 is equal to the sum of the probability of high neuroticism and low mindfulness acceptance level and the probability of high neuroticism and high mindfulness acceptance level, and the high acceptance level probability p2 is equal to the sum of the probability of low neuroticism and low mindfulness acceptance level and the probability of low neuroticism and high mindfulness acceptance level; The number of training days for the user in the four training modules is calculated by the following formula: Number of days of low attention level training = p 1* X, number of days of high attention level training = (1-p1)*Y, number of days of high acceptance level training = p 2* Z, number of days of low acceptance level training = p2*Q; Among them, X, Y, Z, and Q are the best mapping segmentation standard feature values ​​generated by the four decision tree models. The value obtained by weighting the percentile rank of the user's EEG frequency in the norm represents the optimal training time for the user if he or she fully possesses a certain personality trait and mindfulness acceptance type.

4. The mindfulness intervention method according to claim 1, characterized in that Before pushing the training content of the day to the user for mindfulness training, the method further includes: Acquire the training environment selected by the user, so as to push the training content of the day to the user for mindfulness training in the training environment; The training environment includes at least: a personal training scene and a virtual training room group training scene.

5. The mindfulness intervention method according to claim 1, characterized in that Also includes: Introducing an external neurofeedback monitoring device to initially collect the basic brain wave frequency characteristics of the user in a relaxed state and a focused state; During the process of the user completing the training content of the day, continuously monitoring the brain wave frequency characteristics of the user; When the user completes the training content of the day, the built-in analysis software of the external neurofeedback monitoring device is used to perform data analysis on the brain wave frequency characteristics of the user, thereby generating a brain wave frequency analysis report of the user's training of the day; After the user completes the personalized mindfulness intervention program, a brain wave frequency analysis list of the user is generated based on the brain wave frequency analysis report of the user's daily training.

6. The mindfulness intervention method according to claim 1, characterized in that: When the user completes the training content of the day, the logarithmic loss function algorithm of softmax regression is used to dynamically adjust the next training task until the training content of the day is completed.

7. The mindfulness intervention method according to claim 2, characterized in that: During the process of the user performing mindfulness training, collecting the user's daily mindfulness training data and objective training effects; When the user completes T / 2 days of mindfulness training, the mindfulness training data and objective training effect of the user in the first half of the period are formed; wherein T represents the total number of training days of the personalized mindfulness intervention program; Inputting the mindfulness training data and objective training effects of the user in the first half of the cycle into four decision tree models for model iteration, so as to re-obtain the probability of the user corresponding to high neuroticism and low mindfulness acceptance level, high neuroticism and high mindfulness acceptance level, low neuroticism and low mindfulness acceptance level, and low neuroticism and high mindfulness acceptance level, and readjust the training days of the user in the four training modules; Based on the readjusted number of training days of the user in the four training modules, daily training content is pushed to the user until the second half of the cycle of mindfulness training is completed.

8. A mindfulness intervention system based on personality differences and mindfulness levels, characterized by include: Login unit, used for user registration and system login; An evaluation unit, connected to the login unit, and having a built-in physiological data monitoring module, a personality assessment scale, and a mindfulness five-factor assessment scale, for respectively evaluating the user's EEG frequency, neuroticism level, and mindfulness acceptance level; a classification unit connected to the evaluation unit and preset with a classification model to receive the neuroticism level evaluation data and the mindfulness acceptance level evaluation data of the user, and output the probability that the user belongs to a high attention level and a high acceptance level through the classification model; a calculation unit connected to the classification unit and preset with a calculation model, so as to calculate the number of training days of the user in four training modules based on the probability that the user belongs to a high attention level and a high acceptance level, and in combination with the EEG frequency evaluation data of the user, so as to form a personalized mindfulness intervention program for the user; wherein the four training modules are: a high attention level training module, a low attention level training module, a high acceptance level training module and a low acceptance level training module, and each training module corresponds to a task library; An intervention unit is connected to the computing unit and has the four training modules, so as to randomly arrange and combine the four training modules according to the number of days to form a training module set; and randomly extract a training module from the training module set as the training theme of the day, and extract a preset number of training tasks from the corresponding task library based on the training theme of the day as the training content of the day, so as to push the training content of the day to the user for mindfulness training; and when the user completes the training content of the day, randomly extract a training module from the remaining training module set again as the training theme of the next day, and repeat this cycle until the user completes the personalized mindfulness intervention plan.

9. The mindfulness intervention system according to claim 8, characterized in that Also includes: An environment selection unit, connected to the intervention unit, for allowing the user to select a training environment before pushing the training content of the day to the user for mindfulness training; wherein the training environment at least includes: a personal training scene and a virtual training room group training scene; An external neurofeedback monitoring device is connected to the intervention unit to continuously monitor the brain wave frequency characteristics of the user while the user completes the personalized mindfulness intervention program.

10. A mindfulness intervention system based on personality differences and mindfulness levels, characterized by The invention comprises a processor and a memory, wherein the processor reads a computer program in the memory to execute the mindfulness intervention method according to any one of claims 1 to 7.

Images