Mortise prediction-intervention-feedback system and control method

Abstract

The invention discloses a centrality prediction-intervention-feedback system and a control method, and relates to the technical field of centrality training systems.The system comprises a wearable user interaction device, and a user management module, a centrality intervention training module, a dynamic prediction module, an intervention effect evaluation module and a feedback interaction module which are connected in sequence; determining an initial mind level, depression level, and anxiety level of the user; based on the depression level and the anxiety level of the user, determining a target training scheme of the user, and prompting the user to carry out positive training according to the target training scheme; adjusting the target training scheme based on the emotional state factor; according to the method, the real-time mind level of the user and the completion progress of the target training scheme by the user are determined according to the preset time interval, the mind training report is generated in combination with the initial mind level and visualized, the mind training mode is selected by evaluating the mind level of the user, and the formulating reasonability of the mind training scheme can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of mindfulness training systems, and in particular to a mindfulness prediction-intervention-feedback system and control method. Background Art

[0002] Mindfulness training is a very popular psychological therapy today, helping users improve their concentration, relieve stress, eliminate negative emotions, get better sleep, and gain a sense of happiness in life. Existing mindfulness training methods often only provide mindfulness course audio, or training audio instructions, for users to practice on their own, but cannot provide corresponding learning and training effect evaluation, cannot provide feedback on learning or training effects, cannot provide real-time guidance to users, and learners cannot accurately grasp their own learning level, and are prone to give up halfway, which greatly reduces the effectiveness of mindfulness practice and affects learning enthusiasm.

[0003] Therefore, in order to improve the effectiveness of mindfulness training, it is urgent to provide a mindfulness training method or system. Summary of the invention

[0004] The purpose of this application is to provide a mindfulness prediction-intervention-feedback system and control method, which can improve the rationality of mindfulness training program formulation by evaluating the user's mindfulness level and selecting a mindfulness training method.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a mindfulness prediction-intervention-feedback method, comprising: a wearable user interaction device and a processing device;

[0007] The wearable user interaction device is connected to the processing device;

[0008] The processing device comprises: a user management module, a mindfulness intervention training module, a dynamic prediction module, an intervention effect evaluation module and a feedback interaction module connected in sequence;

[0009] The user management module is used to complete the user's personal account login and user personal account verification, and determine the user's initial mindfulness level, depression level and anxiety level;

[0010] The mindfulness intervention training module is used to determine the user's target training program based on the user's depression level and anxiety level, and prompt the user to perform mindfulness training according to the target training program;

[0011] The dynamic prediction module is used to determine the user's emotional state factor based on the user feedback data, and adjust the target training program based on the emotional state factor;

[0012] The intervention effect evaluation module is used to determine the user's real-time mindfulness level according to a preset time interval, construct a mindfulness level change table in combination with the initial mindfulness level, and construct a completion progress change table according to the user's training completion progress;

[0013] The feedback interaction module is used to generate a mindfulness training report according to a preset template based on the mindfulness level change table and the completion progress change table, and visualize the mindfulness training report;

[0014] The wearable user interaction device is connected to the mindfulness intervention training module and the dynamic prediction module respectively; the wearable user interaction device can be worn on the user's head; the wearable user interaction device is used to play the animation scene and sound scene corresponding to the target single training when receiving the target single training start instruction in the target training plan; the sound scene includes a voice prompt containing background music; the wearable user interaction device is also used to obtain user feedback data.

[0015] Optionally, the wearable user interaction device includes AR glasses.

[0016] Optionally, the target training program is a special training program or a systematic training program.

[0017] In a second aspect, the present application provides a control method for a mindfulness prediction-intervention-feedback system. Optionally, the control method for the mindfulness prediction-intervention-feedback system is applied to the mindfulness prediction-intervention-feedback system. The control method for the mindfulness prediction-intervention-feedback system includes:

[0018] Determine the user’s initial mindfulness, depression, and anxiety levels when the user first logs in;

[0019] Determine a target training program for the user based on the user's depression level and anxiety level; the target training program is a special training program or a system training program;

[0020] When the user is not logging in for the first time, prompting the user to perform mindfulness training according to the target training plan; prompting the user to perform mindfulness training according to the target training plan includes: upon receiving a target single training start instruction in the target training plan, playing an animation scene and a sound scene corresponding to the target single training, and obtaining user feedback data;

[0021] Determining an emotional state factor of the user based on the user feedback data, and adjusting the target training program based on the emotional state factor;

[0022] Determine the user's real-time mindfulness level according to a preset time interval, and construct a mindfulness level change table based on the initial mindfulness level;

[0023] According to the user's training completion progress, build a completion progress change table;

[0024] Based on the mindfulness level change table and the completion progress change table, a mindfulness training report is generated according to the preset template, and the mindfulness training report is visualized.

[0025] Optionally, when the user first logs in, determining the user's initial mindfulness level, depression level, and anxiety level, including:

[0026] Get the mindfulness level test paper filled out by the user;

[0027] According to the standard score statistical method and the mindfulness level test paper filled in by the user, the mindfulness level score is determined as the user's initial mindfulness level;

[0028] Get the depression level test paper filled out by the user;

[0029] Determine the depression level score according to the standard score statistical method and the depression level test paper filled in by the user;

[0030] Determine the depression level corresponding to the interval in which the depression level score is located as the depression level of the user;

[0031] Get the anxiety level test paper filled out by the user;

[0032] Determine the anxiety level score according to the standard score statistical method and the anxiety level test paper filled in by the user;

[0033] The anxiety level corresponding to the interval in which the anxiety level score is located is determined as the user's anxiety level.

[0034] Optionally, the depression level includes mild depression, moderate depression and severe depression;

[0035] The anxiety levels include mild anxiety, moderate anxiety and severe anxiety.

[0036] Optionally, based on the depression level and anxiety level of the user, a target training program for the user is determined, including:

[0037] Determine whether the user is in severe depression or severe anxiety, and obtain a first determination result;

[0038] If the first judgment result is yes, a prompt "You are in severe emotional distress, please seek medical attention in time" will be issued;

[0039] If the first judgment result is no, then judging whether the user is in mild depression and mild anxiety at the same time, and obtaining a second judgment result;

[0040] If the second judgment result is yes, a prompt of "being in mild emotional distress" is issued, and the special training program is determined as the target training program;

[0041] If the second judgment result is no, a prompt of "being in moderate emotional distress" is issued, and the system training program is determined as the target training program.

[0042] Optionally, before determining the user's initial mindfulness level, depression level, and anxiety level, the method further includes:

[0043] Acquiring feedback data of multiple testers, and measuring the emotional state factor of the tester corresponding to each feedback data; the feedback data includes: brain oxygenated hemoglobin, deoxygenated hemoglobin, event-related potential, heart rate and respiratory rate;

[0044] The emotional state factor of the tester corresponding to each feedback data;

[0045] Taking the feedback data as input and the emotional state factor of the tester corresponding to each feedback data as output, the quantum hidden Markov algorithm model is trained to obtain the emotional state factor prediction model;

[0046] The emotional state factor prediction model is deployed in the dynamic prediction module of the mindfulness prediction-intervention-feedback system.

[0047] Optionally, determining the user's emotional state factor based on the user feedback data, and adjusting the target training program based on the emotional state factor, includes:

[0048] Inputting user feedback data into the emotional state factor prediction model to obtain the user's emotional state factor;

[0049] Determine the training program corresponding to the interval in which the user's emotional state factor is located as the adjusted target training program.

[0050] Optionally, the user's real-time mindfulness level is determined at a preset time interval, and a mindfulness level change table is constructed in combination with the initial mindfulness level, including:

[0051] Determine the user's real-time mindfulness level at a preset time interval; the method for determining the real-time mindfulness level is: obtain the mindfulness level test paper filled in by the user in real time; compare the mindfulness level test paper filled in by the user in real time with the mindfulness level test paper with a standard answer, and obtain the mindfulness level score as the user's real-time mindfulness level;

[0052] A mindfulness level variation table is constructed with the test time as the horizontal axis and the mindfulness level as the vertical axis; the mindfulness level includes an initial mindfulness level and real-time mindfulness levels corresponding to multiple test times.

[0053] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0054] The present application provides a mindfulness prediction-intervention-feedback system and control method, including: a wearable user interaction device and a processing device. The wearable user interaction device is connected to the processing device. The processing device includes: a user management module, a mindfulness intervention training module, a dynamic prediction module, an intervention effect evaluation module and a feedback interaction module connected in sequence. The user management module is used to complete the user's personal account login and user personal account verification, and determine the user's initial mindfulness level, depression level and anxiety level. The mindfulness intervention training module is used to determine the user's target training plan based on the user's depression level and anxiety level, and prompt the user to perform mindfulness training according to the target training plan. The target training plan is a special training plan or a system training plan. The dynamic prediction module is used to determine the user's emotional state factor based on the user feedback data, and adjust the target training plan based on the emotional state factor. The intervention effect evaluation module is used to determine the user's real-time mindfulness level according to a preset time interval, construct a mindfulness level change table in combination with the initial mindfulness level, and construct a completion progress change table according to the user's training completion progress. The feedback interaction module is used to generate a mindfulness training report according to a preset template based on the mindfulness level change table and the completion progress change table, and to visualize the mindfulness training report; by providing convenient and efficient mindfulness training services, it helps users relieve psychological pressure, establish a positive attitude, and provide psychological support and services to more users. Compared with the existing mindfulness training software, this application can provide targeted guidance for subsequent exercises based on practice data and evaluation effect data feedback, thereby improving the training effect; the multi-scenario training model provided by this application is supported by a scientific theoretical framework to provide users with targeted personalized training plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 This is a structural diagram of a mindfulness prediction-intervention-feedback system in one embodiment of the present application;

[0057] Figure 2 This is a flow chart of a control method of a mindfulness prediction-intervention-feedback system in one embodiment of the present application. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only 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.

[0059] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0060] At present, emotion prediction is mainly based on the current emotion level and the mindfulness assessment scale score to predict the emotion level at a certain point in the future. In fact, factors that affect the training effect also include the mindfulness attitude level, physiological state, task execution, training continuity, etc. during the mindfulness intervention process. Therefore, the present application provides, in an exemplary embodiment, a mindfulness prediction-intervention-feedback system that completes the recommendation of mindfulness therapy tasks based on multi-dimensional predictive evaluation. Compared with the prior art, it more dynamically and accurately evaluates the user's training process characteristics, recommends more appropriate and better matching tasks, and achieves maximum training effect and better compliance. Figure 1 As shown, the embodiment provides a mindfulness prediction-intervention-feedback system, comprising: a wearable user interaction device and a processing device. The wearable user interaction device is connected to the processing device.

[0061] The processing device includes: a user management module, a mindfulness intervention training module, a dynamic prediction module, an intervention effect evaluation module and a feedback interaction module which are connected in sequence.

[0062] The user management module is used to complete user personal account login and user personal account verification, and determine the user's initial mindfulness level, depression level and anxiety level.

[0063] The mindfulness intervention training module is used to determine the user's target training program based on the user's depression level and anxiety level, and prompt the user to perform mindfulness training according to the target training program. The target training program is a special training program or a systematic training program.

[0064] The dynamic prediction module is used to determine the user's emotional state factor based on user feedback data and adjust the target training plan based on the emotional state factor. The role of depression and anxiety levels is the same as that of other physiological indicators. The system determines the emotional state factor level and the corresponding training plan based on the depression, anxiety and physiological indicator levels.

[0065] The intervention effect evaluation module is used to determine the user's real-time mindfulness level according to preset time intervals, construct a mindfulness level change table based on the initial mindfulness level, and construct a completion progress change table based on the user's training completion progress.

[0066] The feedback interaction module is used to generate a mindfulness training report according to a preset template based on the mindfulness level change table and the completion progress change table, and to visualize the mindfulness training report.

[0067] The wearable user interaction device is connected to the mindfulness intervention training module and the dynamic prediction module respectively. The wearable user interaction device can be worn on the user's head. The wearable user interaction device is used to play the animation scene and sound scene corresponding to the target single training when receiving the target single training start instruction in the target training plan. The sound scene includes a voice prompt with background music. The wearable user interaction device is also used to obtain user feedback data. The wearable user interaction device includes AR glasses.

[0068] 1. User management module

[0069] The user management module is responsible for logging in and verifying the user's personal account. When a user logs in for the first time, they need to complete the basic information, including name, age, gender, etc., and conduct an emotional level assessment. The assessment tools include the Mindfulness Assessment Scale (FFMQ, corresponding to the mindfulness level), the Depression Screening Scale (PHQ-9, corresponding to the depression level) and the Anxiety Screening Scale (GAD-7, corresponding to the anxiety level). All questions must be completed, scored and calculated. The system collects user emotional level assessment data through these scales and stores it in the user database. Through the user's answers, the background calculation forms the basic information of the user's mindfulness (used to evaluate the effect of the exercise) and emotional level (used to push training plans), and pushes training plans and work suggestions.

[0070] The PHQ-9 rating scale is a scale used to assess the severity of depression. Its scores range from 0 to 27, corresponding to different levels of depression. Example: No motivation or interest in doing things. 0 points for no motivation at all, 1 point for several days, 2 points for more than a week, and 3 points for almost every day. Depression levels are divided according to the following rules:

[0071] Mild (no depression, mild depression): 0-4 points indicate no depression. 5-9 points indicate mild depression.

[0072] Moderate (moderate depression, moderate to severe depression): 10-14 points indicate moderate depression. 15-19 points indicate moderate to severe depression.

[0073] Severe (it is recommended to seek medical treatment and follow the doctor's advice for treatment): 20-27 points indicate severe depression.

[0074] GAD-7 Scoring Criteria: Applicable to the screening and assessment of generalized anxiety disorder. Example: Feeling nervous, anxious, or anxious. 0 points for not feeling nervous, anxious, or anxious at all, 1 point for several days, 2 points for more than a week, and 3 points for almost every day. Anxiety levels are divided according to the following rules:

[0075] Mild (normal anxiety, mild anxiety): 0-4 points: normal anxiety, 5-9 points: mild anxiety.

[0076] Medium (moderate anxiety, moderate to severe anxiety): 10-13 points: moderate anxiety, 14-18 points: moderate to severe anxiety.

[0077] Severe (seek medical advice and follow doctor's advice): 19-21 points: severe anxiety

[0078] Emotional level prediction: The system evaluates the user's depression and anxiety levels. For users with PHQ-9 and GAD-7 scores below 9 (i.e., depression and anxiety levels below mild), the system will recommend special training; for users with PHQ-9 scores between 10 and 19 and GAD-7 scores between 10 and 14 (i.e., depression and anxiety levels above moderate), the system will recommend daily training and set up corresponding training plans (only training methods are recommended, and the frequency is controlled by the user) and reminders (Table 1). This recommendation result is displayed to the user through the personalized recommendation module of the user interface.

[0079] Table 1 Target training program selection rules

[0080]

[0081] As an alternative implementation, the user management module is used for user information management: including basic information collection, scale assessment to measure depression and anxiety indicators, mindfulness 12-factor (A_L) questionnaire survey, physiological indicators, and according to the quantum hidden Markov model, using current anxiety scores, depression scores, mindfulness 12-factor scores, and physiological indicator scores and other data to predict the emotional state at a certain point in the future. The prediction algorithm is expressed by the following quantum hidden Markov algorithm:

[0082]

[0083] in, represents the predicted probability of emotional state at a certain point in the future; ρ(M q ) represents a given environment subspace M q The conditional density matrix of the quantum system (i.e., in the current emotional state). The density matrix describes the state of the system under the current emotional state, that is, the predicted probability of the emotional state at a certain point in the future. L is a physiological measurement indicator, such as heart rate, cerebral blood flow, etc. i represents the summation index, which is used to sum all possible Kraus operators or other related operators, and t represents the time variable, which is used to describe the evolution of the quantum system over time. τ represents the integral variable, which is used to represent the lower limit of the integral in the time integral, and is usually used together with time t to describe the influence of the past state of the system on the current state. Represents the environment subspace M q Perform a partial trace operation. This operation is used to eliminate the ambient degrees of freedom from the density matrix of the entire system and obtain the conditional density matrix of the system. E(M q,l ) indicates that the space representing the environment is divided into different subspaces, M q,l Denotes the lth subspace. L'(t) represents the Liouvillian superoperator related to the system-environment coupling, which describes the impact of the environment on the system, that is, predicting indicator data, such as anxiety scores, depression scores, heart rate data, cerebral blood flow data, etc.; under the weak coupling approximation, L' can be regarded as a perturbation. G(t,τ) represents the Green's function related to the system Hamiltonian HS, which is used to describe the evolution of the system from time τ to time t. L'(τ) represents the Liouvillian superoperator representing the system-environment coupling at time τ. represents the conjugate transpose of the Green's function, which is used to describe the inverse process of system evolution. T (t) represents the total density matrix representing the entire system (including the quantum system and the environment) at time t.

[0084] 2. Mindfulness intervention training module

[0085] According to the prediction results of emotional state, the user's emotional state can be divided into three types: severe, moderate, and mild. Based on the repeated measurement of emotional data and the emotion prediction results of S2, the quantum hidden Markov algorithm is used to determine the mindfulness factor score. The push plan is determined based on the scores of each mindfulness factor and the emotional state prediction results. When the predicted emotional state is severe, medical information is pushed directly. When the predicted emotional state is mild or moderate, the training content corresponding to the lower mindfulness factor score is packaged into a training plan. When the predicted emotional state is mild and the mindfulness factor scores are all higher than XXX points, the user can choose at least one factor corresponding to the training plan for autonomous training.

[0086] After the daily practice, evaluate the user's emotional state level, mindfulness factor level, number of training tasks completed, and practice duration after the practice. Starting from the second day of the week, set the user's training plan of the previous day as the initial training plan for the day. Adjust the difficulty ratio of the training items in the mindfulness training task library of the day according to the user's emotional state and mindfulness factor level. Adjust the number of training items and the practice duration of each item in the mindfulness training task of the day according to the actual number of tasks completed and the practice duration of the previous day by the user. Remind the users who have not practiced to practice, provide psychological education, and explain the practice tasks and effects of the week. After completing the training of the week, before the training of the next week, comprehensively consider the training effects of the users every day of the week, calculate the change rate of the emotional state, mindfulness factor level and the comprehensive emotional state and mindfulness factor level of the week, and determine whether to adjust the difficulty ratio of the training items in the training task library of the next week according to the change rate of the emotional state, mindfulness factor level and the comprehensive emotional state and mindfulness factor level of the week.

[0087] Task recommendation within the topic: After the daily practice, evaluate the user's emotional state level, mindfulness factor level, number of training tasks completed, and practice time after the day's practice. Starting from the second day, set the user's training plan of the previous day as the initial training plan for the day. Adjust the difficulty ratio of the training items in the mindfulness training task library of the day according to the user's emotional state and mindfulness factor level. Adjust the number of training items and the practice time of each item in the mindfulness training task of the day according to the actual number of tasks completed and the practice time of the user on the previous day. Provide practice reminders to users who have not practiced, provide psychological education, and explain the practice tasks and effects of the week. After completing the training of this topic, before the next topic training, comprehensively consider the daily training effect of the user in this topic, calculate the daily emotional state, mindfulness factor level change rate of this topic, and the comprehensive emotional state and mindfulness factor level change rate of the week, and determine whether to adjust the difficulty ratio of the training items in the next topic training task library according to the daily emotional state, mindfulness factor level change rate of this topic, and the comprehensive emotional state and mindfulness factor level change rate of the week.

[0088] As an alternative implementation, the mindfulness training module includes two intervention programs: system training and special training. The training plan is automatically pushed according to the user's emotional distress level. Each program is equipped with a detailed introduction and voice guidance to help users plan, understand and complete the training.

[0089] 2.1 System Training

[0090] The systematic training program is an emotional distress intervention program integrated by the developers based on the existing mindfulness cognitive therapy, mainly for people with moderate emotional distress. The systematic training program includes a 48-day systematic training plan (including 8 themes such as mindfulness awareness, perception, attention, flexibility, acceptance, thinking, behavior, and mindful living, each theme contains 6 days of training content).

[0091] Training process and feedback: Daily training content includes detailed introduction, operation steps, knowledge point explanation, audio training and practice voice guidance. Users can conduct self-training according to the system push. After the practice is completed, users are reminded to click the complete practice button (the system background marks the progress of the practice, such as "the current training is 50% completed"). After daily training, the system will push home practice tasks to users.

[0092] Training execution and progress management: After the user completes the training for the day, the system automatically records the user's training time and completion progress (e.g., completing the training audio is recorded as 50%, submitting the home practice task is recorded as 100%), and pushes the training content for the next day as planned. And so on.

[0093] 2.2 Specialized training

[0094] Special training includes four special themes: awakening, pause, cultivation, and enjoyment. Each theme contains multiple similar training items. The system guides users to practice mindfulness through training audio. Special training execution: The system automatically enters the special training mode based on the user's emotional distress level (the aforementioned emotional assessment belongs to the range of mild depression and mild anxiety). Awakening special training is pushed as planned, and subsequent training is pushed based on dynamic prediction results.

[0095] 3. Dynamic prediction module

[0096] The system collects, stores and analyzes the user's learning data, emotional level assessment data, feedback data, etc. Through data analysis, the system can understand the user's current status, learning habits, training effects, emotional changes, etc., so as to dynamically predict the user's future emotions and mental health status, and provide users with more personalized and accurate training recommendations and guidance. At the same time, the system can also apply the data analysis results to subsequent training content optimization, function improvement, etc., to continuously improve the system's user experience and training effects. Based on the model prediction results, the system pushes training topics, each of which corresponds to one or more emotional management characteristic factors, forming a complete emotional management training intervention plan.

[0097] The evaluation is conducted for the idiosyncratic and stable psychological and behavioral characteristics of the customer population, and the stateful daily psychological and behavioral fluctuations. The evaluation is mainly based on physiological measurements, collecting fNIRS near-infrared brain imaging, EEG brain electroencephalography detection, blood oxygen saturation detection, and PPG optical heart rate detection, real-time collection of brain electroencephalography, heart rate, and blood oxygen triple physiological data. The main measurement indicators include (but are not limited to) brain oxygenated hemoglobin, deoxyhemoglobin, event-related potentials, heart rate, respiratory rate, etc. The physiological measurement device model is shown in Table 2.

[0098] Table 2 Physiological measurement device models

[0099]

[0100]

[0101] Whenever necessary, users can use the system prediction module to predict their emotional and mental health status at a certain time in the future based on existing evaluation data (the system defaults to predicting the situation in the next seven days, and customers can modify the prediction range according to their own needs, with the shortest prediction being 1 day in the future and the longest prediction being 15 days in the future).

[0102] Based on the mindfulness emotion mechanism and clinical work experience, the mindfulness training program independently developed collects large-scale user data and uses the generalized structural equation model to fit the user emotion management characteristic factors. The analysis process can be expressed by the following algorithm:

[0103] χ=Λξ+δ (2)

[0104] Among them, χ represents the predicted probability of the emotional state in formula (1), ξ represents the emotional management characteristic factor, Λ represents the relationship strength between the observed indicator and the emotional management characteristic factor, and δ represents the measurement error. Through this algorithm, the emotional management characteristic factor of college students can be fitted and the relationship between the observed indicator and the emotional management characteristic factor can be clarified. Taking the fitting of two emotional management characteristic factors with six observed indicators as an example, formula (2) can be expressed as:

[0105]

[0106] Among them, χ1, χ2, χ3, χ4, χ5, χ6 represent the predicted probability of emotional state, λ11, λ21, λ31, λ42, λ52, λ62 represent the relationship strength between the prediction index and the emotional management characteristic factor, ξ1, ξ2 represent the emotional management characteristic factor, δ1, δ2, δ3, δ4, δ5, δ6 represent the measurement error.

[0107] Similarly, the above algorithm can be used to fit the relationship between the emotion management feature factor and the training theme factor, and then formulate the training theme. The analysis process can be expressed by the following algorithm:

[0108] A=ΓH+δ (4)

[0109] Among them, Α represents the emotion management characteristic factor, H represents the training theme factor, Γ represents the relationship strength between the special training factor and the emotion management characteristic factor, and δ represents the measurement error. Through this algorithm, the training theme factor can be fitted and the relationship between the emotion management characteristic factor and the training theme factor can be clarified. Taking the fitting of six emotion management characteristic factors to two training theme factors as an example, formula (4) can be expressed as:

[0110]

[0111] Among them, α1, α2, α3, α4, α5, α6 represent emotion management characteristic factors, γ11, γ21, γ31, γ42, γ52, γ62 represent the relationship strength between emotion management characteristic factors and training theme factors, H1, H2 represent training theme factors, δ1, δ2, δ3, δ4, δ5, δ6 represent measurement errors.

[0112] Formula (1) is used to predict the user's emotional or mental health state at a certain point in the future, and the algorithm of formula (2) is used to match the emotional and psychological state with the emotional management characteristic factors. The algorithm of formula (4) is further used to match the emotional management characteristic factors with the special training theme factors, thereby realizing the connection between the emotional and psychological state prediction and the training plan, and improving the efficiency of accurate push of the training plan.

[0113] 4. Intervention effect evaluation module

[0114] The intervention effect evaluation module is another core technology of this application and a major innovation that distinguishes it from other similar mindfulness learning software.

[0115] The effect evaluation of intervention training is achieved through evaluation data analysis. The intervention effect evaluation module records the data generated by users before, during and after training, including training data (training times, training frequency, process data; process completion progress percentage; completion evaluation; used to generate reports) and evaluation data.

[0116] The training data includes training duration, training frequency, training effect and other data; the evaluation data includes the client’s own demographic data (such as age, gender, occupation, etc.) and psychological and behavioral evaluation data, such as anxiety scores, depression scores, brain oxygenated hemoglobin, deoxygenated hemoglobin, event-related potentials, heart rate, etc.

[0117] Collect and record customer training data and evaluation data. The data is stored in commercial cloud servers (such as Alibaba Cloud, Baidu Cloud, or Tencent Cloud, etc.). The evaluation system backend provides data downloads for system operation staff. The data file format is tab-delimited text format or comma-delimited text format.

[0118] The intervention effect evaluation is divided into two parts: individual effect evaluation (individual data analysis) and group effect evaluation (group data analysis).

[0119] In the individual data analysis section, after an individual customer submits the assessment result, the system first determines whether this is the first time the customer has submitted the assessment result, and assigns a timestamp to the assessment result. If the customer has taken multiple assessments on a certain assessment, each assessment result will be assigned a timestamp. Customers can choose to view the changes in the score of a certain question of a certain assessment over time, or they can choose to view the changes in the entire assessment result over time. The data of the entire assessment result and its change trend are expressed as the average score of the original score of the assessment question.

[0120] In the group data analysis section, organizations or corporate customers can directly download the original data for self-analysis according to their own needs, or they can ask the evaluation system to directly provide the evaluation results. The evaluation system decides whether to provide cross-layer correlation and multi-layer modeling results based on the organizational hierarchical structure and repeated measurement status. Specifically, if there are repeated measurements of members participating in the evaluation within the organization, or if the organization is divided into different subgroups according to certain characteristics, the system provides cross-layer correlation to explain to what extent the intra-individual change trend of the measured phenomenon has individual differences, or to what extent the measured relationship has sub-group differences. If the organizational customer wants to obtain further detailed information, the system provides an interface for the customer to customize the analysis model, assisting the customer to select the predictor variables and outcome variables of interest at different organizational levels, and customize the model analysis by themselves. For high-level predictor variables (such as organizational characteristics), the system automatically performs total centering, and for low-level predictor variables (such as individual characteristics), the system automatically performs group centering. After the customer submits the customized analysis, the system performs analysis and outputs visualization results and analysis reports such as three-line tables, line charts, and bar charts.

[0121] After the awakening theme exercise is completed, a questionnaire assessment of mindfulness perception and description is conducted (standard questionnaires are available). If the evaluation results do not meet the statistical standard compared to the pre-training test, the perception-specific supplementary exercises are recommended until the standard is met. If the standard is met, the next pause-specific theme training is continued. If the evaluation results do not meet the statistical standard compared to the pre-training test, the pause-specific supplementary exercises are recommended. This is repeated to complete the four theme trainings in sequence. Finally, an overall assessment of the trait mindfulness level and the emotional level is conducted, and an overall practice report is provided to the user, as well as a comparison of the before and after data.

[0122] Whether the pre- and post-test results reach a statistically significant level can be determined according to the following algorithm:

[0123] T=x / (SD / √n) (6)

[0124] Among them, T represents the test value of the paired sample t test between the pre- and post-test, x represents the mean of the pre- and post-test differences, SD represents the standard deviation of the pre- and post-test differences, and n is the paired sample size.

[0125] 5. Feedback interaction module

[0126] Based on the data analysis results, the feedback interaction function module of this system can provide users with personalized course learning or training suggestions to help users formulate training plans more scientifically, which is also one of the advantageous functions of this system.

[0127] 5.1 Evaluation Feedback

[0128] For the training process, the system provides feedback on the training process characteristics based on the training data, including the actual training situation of this link, possible problems in the training process, and improvement suggestions. For the evaluation results, the system feedbacks the current evaluation situation, recommends the links that need to be added to the training, and improvement suggestions.

[0129] If after the user completes the staged training, the mindfulness trait assessment results show that the expected training effect has not been achieved, that is, there is no significant difference in the relevant assessment results before and after the training, the system will give corresponding practice suggestions to encourage the user to continue practicing; if the relevant assessment results before and after the training have significantly improved, the system will jump to other relatively insufficient training modules to continue practicing, so as to improve the overall level of the user's mindfulness traits.

[0130] For individual customers, the system provides viewing and downloading of past personal training and assessment history data based on personal accounts, including historical training process feature change curves, assessment result trend charts, descriptive statistical results, and original data. For organizational customers, the system provides downloading of original data based on administrator permissions, which can be delivered to organizational customers after personal sensitive information is desensitized.

[0131] The data analysis results are presented in the form of visualization options and analysis reports such as three-line tables, line charts, and bar charts. The analysis report can be opened directly in the default browser of the mobile phone or sent to a specified email address. If the customer has bound a personal email address to the system or logged in to the system with a personal email address, the system will send the evaluation results to that email address by default. The evaluation result document is sent as an email attachment, and the document format can be selected in pdf or docx format. The default email address can be changed in the system settings.

[0132] Organizational or individual customers can subscribe to the training and assessment system via email to receive relevant training information or learn about new features of system upgrades.

[0133] 5.2 Practice Feedback

[0134] Based on the interactive dialogues between offline group counseling practice leaders and participants, an interactive feedback corpus is established.

[0135] Based on the interactive feedback corpus, the system extracts the experiences and questions submitted by users to classify and extract key information. The key information includes three categories. The first category is the user's description of the practice experience; the second category is the description of the difficulties and discomfort encountered by the user during the practice; and the third category is the description of the problems encountered by the user during the practice.

[0136] Classified feedback is provided based on the extracted information. For the first type of description, the system pushes affirmative and encouraging expressions and strengthens the mindfulness attitude reinforcement; for the second type of description, the system pushes supportive and encouraging expressions and strengthens the non-judgment, non-reaction and friendly attitude; for the third type of description, the system pushes answers to related questions.

[0137] The front end of this application is developed using the WeChat applet framework, using WXML and WXSS for page layout and style design, and using JavaScript to implement page interaction and logic processing. At the same time, the API interface provided by the WeChat applet is used to implement functions such as user information acquisition, data storage and transmission.

[0138] The backend is developed using Node.js and Express frameworks, and MongoDB is used as a database to store user information and training data. The backend service is mainly responsible for processing front-end requests, implementing functions such as user authentication, data query and update, etc. At the same time, data analysis tools are used to process and analyze training data to provide users with personalized training suggestions.

[0139] This application strictly protects user information. During the user registration and login process, encryption technology is used to transmit and store sensitive information. At the same time, the mini program will regularly back up and encrypt user data to ensure data security and reliability.

[0140] During the development process, strict unit testing, integration testing, and performance testing will be carried out to ensure the stability and availability of the Mini Program. After the testing is completed, it will be deployed and released online to provide services to users.

[0141] Actual scenario example:

[0142] Assume that Mr. Zhang is an office worker. Recently, due to the high pressure at work, he often feels anxious and nervous, which affects his quality of life and work efficiency. He decides to use the mindfulness self-help system developed by Guangdong University of Foreign Studies for self-help training.

[0143] 1. User management module:

[0144] Mr. Zhang first registered and logged in through the system login interface, filling in his basic personal information, such as name, age and occupation.

[0145] Then, he completed the emotional level assessment in the system, including anxiety level test, depression level test, etc.

[0146] 2. Emotional level assessment, prediction, and recommendation module:

[0147] Based on Mr. Zhang’s assessment results, the system determined that his emotional level was mildly anxious.

[0148] Therefore, the system recommended that Mr. Zhang enter the special training module and receive customized training on anxiety.

[0149] 3. Training module:

[0150] Based on the system recommendation, Mr. Zhang entered the special training module.

[0151] This module provides a series of mindfulness training content for anxiety.

[0152] Mr. Zhang conducts special training every day according to the system's guidance and submits feedback after each training.

[0153] 4. Dynamic evaluation module:

[0154] During Mr. Zhang's special training, the system regularly assesses his emotional and physiological levels.

[0155] These assessment results are compared with previous data and predict the possible emotional state in the next 7 days. The system then pushes specialized training content on the next topic based on the prediction results to adapt to Mr. Zhang's training progress; or continues with more training content on the same topic based on any problems he may still have.

[0156] 5. System training module.

[0157] If Mr. Zhang's emotional level has reached moderate, or he requires mindfulness training with an updated system, he can choose to enter the system training module. The system training module includes training on eight topics, including mindfulness awareness, perception, and attention, which can help Mr. Zhang improve his mindfulness level comprehensively.

[0158] 6. Feedback and evaluation:

[0159] After a period of special training, Mr. Zhang's anxiety was significantly relieved.

[0160] Based on Mr. Zhang’s training data and evaluation results, the system generated a detailed training report, showing his learning progress and achievements.

[0161] In another exemplary embodiment of the present application, Figure 2 , a control method of a mindfulness prediction-intervention-feedback system is provided, the control method of the mindfulness prediction-intervention-feedback system is applied to the mindfulness prediction-intervention-feedback system, the control method of the mindfulness prediction-intervention-feedback system comprises:

[0162] Step 201: When a user logs in for the first time, determine the user's initial mindfulness level, depression level, and anxiety level.

[0163] Step 202: Determine the user's target training program based on the user's depression level and anxiety level. The target training program is a special training program or a system training program.

[0164] Step 203: When the user is not logging in for the first time, prompt the user to perform mindfulness training according to the target training plan. Prompting the user to perform mindfulness training according to the target training plan includes: upon receiving a target single training start instruction in the target training plan, playing an animation scene and a sound scene corresponding to the target single training, and obtaining user feedback data.

[0165] Step 204: Determine the user's emotional state factor based on the user feedback data, and adjust the target training program based on the emotional state factor.

[0166] Step 205: Determine the user's real-time mindfulness level at a preset time interval, and construct a mindfulness level change table in combination with the initial mindfulness level.

[0167] Step 206: Construct a completion progress change table according to the user's training completion progress.

[0168] Step 207: Based on the mindfulness level change table and the completion progress change table, a mindfulness training report is generated according to a preset template, and the mindfulness training report is visualized.

[0169] Step 201 includes:

[0170] Step 201 - 1 : Obtain the mindfulness level test paper filled in by the user.

[0171] Step 201 - 2 : Determine the mindfulness level score as the user's initial mindfulness level according to the standard score statistical method and the mindfulness level test paper filled in by the user.

[0172] Step 201 - 3: Obtain the depression level test paper filled in by the user.

[0173] Step 201 - 4 : Determine the depression level score according to the standard score statistical method and the depression level test paper filled in by the user.

[0174] Step 201-5: Determine the depression level corresponding to the interval in which the depression level score is located as the depression level of the user. The depression level includes mild depression, moderate depression and severe depression.

[0175] Step 201-6: Obtain the anxiety level test paper filled out by the user.

[0176] Step 201-7: Determine the anxiety level score according to the standard score statistical method and the anxiety level test paper filled in by the user.

[0177] Step 201-8: Determine the anxiety level corresponding to the interval in which the anxiety level score is located as the user's anxiety level. The anxiety level includes mild anxiety, moderate anxiety and severe anxiety.

[0178] Step 202 includes:

[0179] Step 202-1: Determine whether the user is in severe depression or severe anxiety, and obtain a first determination result. If the first determination result is yes, execute step 202-2; if the first determination result is no, execute step 202-3.

[0180] Step 202-2: Issue a reminder that "You are in severe emotional distress, please seek medical attention immediately."

[0181] Step 202-3: Determine whether the user is in mild depression and mild anxiety at the same time, and obtain a second determination result. If the first determination result is yes, execute step 202-4; if the first determination result is no, execute step 202-5.

[0182] Step 202-4: Issue a "mild emotional distress" prompt and determine the special training program as the target training program.

[0183] Step 202-5: Issue a "moderate emotional distress" prompt and determine the system training program as the target training program.

[0184] Before step 201, the method further includes:

[0185] Step 208: Acquire feedback data of multiple testers, and measure the emotional state factor of the tester corresponding to each feedback data. The feedback data includes: anxiety score, depression score, brain oxygenated hemoglobin, deoxygenated hemoglobin, event-related potential, heart rate and respiratory rate.

[0186] Step 209: Obtain the emotional state factor of the tester corresponding to each feedback data.

[0187] Step 2010: Taking the feedback data as input and the emotional state factor of the tester corresponding to each feedback data as output, the quantum hidden Markov algorithm model is trained to obtain an emotional state factor prediction model.

[0188] Step 2011: Deploy the emotional state factor prediction model in the dynamic prediction module of the mindfulness prediction-intervention-feedback system.

[0189] Step 204 includes:

[0190] Step 204 - 1 : Input the user feedback data into the emotional state factor prediction model to obtain the user's emotional state factor.

[0191] Step 204 - 2 : Determine the training program corresponding to the interval in which the user's emotional state factor is located as the adjusted target training program.

[0192] Step 205 includes:

[0193] Step 205-1: Determine the user's real-time mindfulness level at a preset time interval. The real-time mindfulness level is determined by obtaining a mindfulness level test paper filled in by the user in real time. Compare the mindfulness level test paper filled in by the user in real time with the standard answer mindfulness level test paper, and obtain a mindfulness level score as the user's real-time mindfulness level.

[0194] Step 205-2: Construct a mindfulness level change table with the test time as the horizontal axis and the mindfulness level as the vertical axis. The mindfulness level includes the initial mindfulness level and the real-time mindfulness levels corresponding to multiple test times.

[0195] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0196] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A mindfulness prediction-intervention-feedback system, characterized in that: include: a wearable user interaction device and a processing device; The wearable user interaction device is connected to the processing device; The processing device comprises: a user management module, a mindfulness intervention training module, a dynamic prediction module, an intervention effect evaluation module and a feedback interaction module connected in sequence; The user management module is used to complete the user's personal account login and user personal account verification, and determine the user's initial mindfulness level, depression level and anxiety level; The mindfulness intervention training module is used to determine the user's target training program based on the user's depression level and anxiety level, and prompt the user to perform mindfulness training according to the target training program; The dynamic prediction module is used to determine the user's emotional state factor based on the user feedback data, and adjust the target training program based on the emotional state factor; The intervention effect evaluation module is used to determine the user's real-time mindfulness level according to a preset time interval, construct a mindfulness level change table in combination with the initial mindfulness level, and construct a completion progress change table according to the user's training completion progress; The feedback interaction module is used to generate a mindfulness training report according to a preset template based on the mindfulness level change table and the completion progress change table, and visualize the mindfulness training report; The wearable user interaction device is connected to the mindfulness intervention training module and the dynamic prediction module respectively; the wearable user interaction device can be worn on the user's head; the wearable user interaction device is used to play the animation scene and sound scene corresponding to the target single training when receiving the target single training start instruction in the target training plan; the sound scene includes a voice prompt containing background music; the wearable user interaction device is also used to obtain user feedback data.

2. The mindfulness prediction-intervention-feedback system according to claim 1, characterized in that: The wearable user interaction device includes AR glasses.

3. The mindfulness prediction-intervention-feedback system according to claim 1, characterized in that: The target training program is a special training program or a systematic training program.

4. A control method for a mindfulness prediction-intervention-feedback system, characterized in that: The control method of the mindfulness prediction-intervention-feedback system is applied to the mindfulness prediction-intervention-feedback system according to any one of claims 1 to 3, and the control method of the mindfulness prediction-intervention-feedback system comprises: Determine the user’s initial mindfulness, depression, and anxiety levels when the user first logs in; Determine a target training program for the user based on the user's depression level and anxiety level; the target training program is a special training program or a system training program; When the user is not logging in for the first time, prompting the user to perform mindfulness training according to the target training plan; prompting the user to perform mindfulness training according to the target training plan includes: upon receiving a target single training start instruction in the target training plan, playing an animation scene and a sound scene corresponding to the target single training, and obtaining user feedback data; Determining an emotional state factor of the user based on the user feedback data, and adjusting the target training program based on the emotional state factor; Determine the user's real-time mindfulness level according to a preset time interval, and construct a mindfulness level change table based on the initial mindfulness level; According to the user's training completion progress, build a completion progress change table; Based on the mindfulness level change table and the completion progress change table, a mindfulness training report is generated according to the preset template, and the mindfulness training report is visualized.

5. The control method of the mindfulness prediction-intervention-feedback system according to claim 4, characterized in that: When a user first logs in, determine the user’s initial mindfulness, depression, and anxiety levels, including: Get the mindfulness level test paper filled out by the user; According to the standard score statistical method and the mindfulness level test paper filled in by the user, the mindfulness level score is determined as the user's initial mindfulness level; Get the depression level test paper filled out by the user; Determine the depression level score according to the standard score statistical method and the depression level test paper filled in by the user; Determine the depression level corresponding to the interval in which the depression level score is located as the depression level of the user; Get the anxiety level test paper filled out by the user; Determine the anxiety level score according to the standard score statistical method and the anxiety level test paper filled in by the user; The anxiety level corresponding to the interval in which the anxiety level score is located is determined as the user's anxiety level.

6. The control method of the mindfulness prediction-intervention-feedback system according to claim 5, characterized in that: The depression levels include mild depression, moderate depression, and severe depression; The anxiety levels include mild anxiety, moderate anxiety and severe anxiety.

7. The control method of the mindfulness prediction-intervention-feedback system according to claim 5, characterized in that: Based on the user's depression and anxiety levels, determine the user's target training program, including: Determine whether the user is in severe depression or severe anxiety, and obtain a first determination result; If the first judgment result is yes, a prompt "You are in severe emotional distress, please seek medical attention in time" is issued; If the first judgment result is no, then judging whether the user is in mild depression and mild anxiety at the same time, and obtaining a second judgment result; If the second judgment result is yes, a "mild emotional distress" prompt is issued, and the special training program is determined as the target training program; If the second judgment result is no, a "moderate emotional distress" prompt is issued, and the system training program is determined as the target training program.

8. The control method of the mindfulness prediction-intervention-feedback system according to claim 6, characterized in that: Prior to determining the user's initial mindfulness, depression, and anxiety levels, it also included: Acquiring feedback data from multiple testers, and measuring the emotional state factor of the tester corresponding to each feedback data; the feedback data includes: anxiety score, depression score, brain oxygenated hemoglobin, deoxygenated hemoglobin, event-related potential, heart rate and respiratory rate; The emotional state factor of the tester corresponding to each feedback data; Taking the feedback data as input and the emotional state factor of the tester corresponding to each feedback data as output, the quantum hidden Markov algorithm model is trained to obtain the emotional state factor prediction model; The emotional state factor prediction model is deployed in the dynamic prediction module of the mindfulness prediction-intervention-feedback system.

9. The control method of the mindfulness prediction-intervention-feedback system according to claim 8, characterized in that: Determining the user's emotional state factor based on the user feedback data, and adjusting the target training program based on the emotional state factor, including: Inputting user feedback data into the emotional state factor prediction model to obtain the user's emotional state factor; Determine the training program corresponding to the interval in which the user's emotional state factor is located as the adjusted target training program.

10. The control method of the mindfulness prediction-intervention-feedback system according to claim 4, characterized in that: The user's real-time mindfulness level is determined according to a preset time interval, and a mindfulness level change table is constructed in combination with the initial mindfulness level, including: Determine the user's real-time mindfulness level at a preset time interval; the method for determining the real-time mindfulness level is: obtain the mindfulness level test paper filled in by the user in real time; compare the mindfulness level test paper filled in by the user in real time with the mindfulness level test paper with a standard answer, and obtain the mindfulness level score as the user's real-time mindfulness level; A mindfulness level variation table is constructed with the test time as the horizontal axis and the mindfulness level as the vertical axis; the mindfulness level includes an initial mindfulness level and real-time mindfulness levels corresponding to multiple test times.

Images