A dynamic adjustment method based on a mindfulness therapy program for depression

Abstract

This invention provides a dynamic adjustment method for a mindfulness-based treatment plan for depression, belonging to the field of healthcare information technology. The method includes: collecting multidimensional patient information, including lifestyle behavior risk data, psychological scale data, and cognitive function assessment data; comprehensively assessing the patient's depression level; determining the priority of treatment modules based on the patient's multidimensional information; generating an initial treatment plan; calculating the comprehensive weight value of daily tasks and dynamically adjusting the training content for the next day; and periodically assessing the patient's condition, recalculating the priority of each treatment module, and optimizing the treatment plan. This invention constructs a complete closed-loop feedback optimization system through multidimensional data fusion assessment and intelligent algorithm dynamic adjustment, achieving precision and personalization of depression treatment plans, effectively improving treatment outcomes and patient compliance, reducing the risk of relapse, and providing a more scientific and effective treatment option for patients with depression.

Description

Technical Field

[0001] This invention relates to the field of healthcare information technology, and specifically to a dynamic adjustment method based on a mindfulness-based treatment plan for depression. Background Technology

[0002] Depression is a common mental disorder affecting approximately 300 million people worldwide. It not only severely impacts patients' quality of life but also increases suicide risk, placing a heavy burden on society and families. Currently, treatment methods for depression mainly include medication, psychotherapy, and comprehensive treatment. Among these, non-pharmacological interventions such as Mindfulness-Based Cognitive Therapy (MBCT), Cognitive Behavioral Therapy (CBT), and Exercise Therapy (ET) are receiving increasing clinical attention due to their high safety and lack of drug dependence.

[0003] However, traditional treatments for depression have several limitations and technical problems: First, the assessment methods are limited. Traditional depression assessments mainly rely on patient self-rating scales (such as PHQ-9, HAMD, etc.), lacking the support of objective physiological data (such as heart rate variability, cortisol levels) and behavioral data (exercise volume, sleep, social activities), leading to significant subjective bias in the assessment results and making it difficult to fully reflect the patient's true condition.

[0004] Secondly, treatment plans are static. Existing treatment technologies (such as CBT applications) mostly use fixed intervention modules, failing to dynamically adjust the intensity and content of treatment based on the patient's real-time status, thus failing to achieve personalized treatment and limiting efficacy. For example, Chinese patent application publication number CN116936036A discloses "A method and system for generating training programs for mindfulness-based insomnia treatment tasks." Although it considers dynamically adjusting training items based on the patient's education level, sleep efficiency, and age, its treatment plan adjustment mechanism is still relatively simple, mainly based on a single indicator (sleep efficiency) and lacking comprehensive analysis of multidimensional data. Furthermore, it does not establish a priority allocation mechanism for treatment modules, making it unable to provide differentiated treatment strategies for patients with different symptom severity levels.

[0005] Third, multimodal data is fragmented. Current technologies lack sufficient data interaction between physiological monitoring devices (such as smartwatches) and treatment systems, failing to achieve real-time linkage between physiological indicators and psychological interventions. The lack of ability to fuse and analyze multi-source heterogeneous data makes it difficult to reveal the complex relationships between depressive symptoms and physical state and behavioral patterns, thus affecting the accuracy of treatment plans.

[0006] Fourth, patient adherence is low. The lack of adherence prediction models based on behavioral data makes it impossible to accurately identify patients' treatment participation and compliance with medical advice, leading to a high likelihood of patients dropping out of the intervention program midway. Furthermore, existing technologies often employ simple task difficulty adjustment strategies, failing to consider individual differences such as patient preferences and optimal training time windows, thus failing to specifically improve patient participation.

[0007] Fifth, there is a lack of intelligent feedback loops. Existing methods are mostly open-loop systems, unable to adjust treatment strategies in real time based on intervention effects, making it difficult to establish a continuous improvement mechanism. The formulation and adjustment of treatment plans mainly rely on the subjective judgment of professionals, lacking standardized, data-driven intelligent decision support systems.

[0008] With the development of technologies such as the Internet of Things and artificial intelligence, wearable devices and smartphones can now collect multidimensional health data of the human body in real time, providing a data foundation for intelligent and personalized treatment of depression. However, how to effectively integrate this multidimensional data, establish a dynamically adjusted treatment plan generation mechanism, and improve the personalization and effectiveness of depression treatment remains a pressing technical problem to be solved. Summary of the Invention

[0009] The purpose of this invention is to provide a dynamic adjustment method based on mindfulness-based treatment for depression. By integrating multi-source data such as physiological, psychological, cognitive, and behavioral data, a comprehensive assessment model is established, and intelligent algorithms are used to dynamically generate and adjust personalized treatment plans to improve the accuracy and effectiveness of depression treatment.

[0010] To achieve the above objectives, the present invention provides the following technical solution:

[0011] A dynamic adjustment method based on mindfulness-based therapy for depression includes the following steps:

[0012] S1: Collection of multidimensional patient information, including data on patients’ life behavior risk, psychological scale data, and cognitive function assessment data;

[0013] S2: Based on the patient's multidimensional information, comprehensively assess the patient's level of depression;

[0014] S3: Determine the priority of treatment modules based on the patient's multidimensional information and depression level;

[0015] S4: Generate an initial treatment plan for the patient based on the priority of the therapy modules;

[0016] S5: Calculate the comprehensive weight value of daily tasks and dynamically adjust the training content for the next day;

[0017] S6: Periodically assess the patient's condition, recalculate the priority of each therapy module, and optimize the treatment plan.

[0018] Furthermore: In step S2, the methods for comprehensively assessing the patient's depression level include:

[0019] Standardize risk indicators strongly associated with depression;

[0020] Multiple linear regression analysis was conducted to establish a model for determining the level of depression.

[0021] The patient's depression level is determined based on the calculation results of the depression level assessment model.

[0022] Furthermore, the risk indicators strongly associated with depression include: anxiety level, attentional bias, memory function, processing speed, executive function, insomnia severity, interpersonal problems scale score, daily steps, daily screen time, daily sedentary time, and physical illness.

[0023] Furthermore: In step S3, the method for determining the priority of therapy modules based on the patient's multidimensional information includes:

[0024] S31: Calculate the initial overall weight value of each therapy;

[0025] S32: Adjust the overall weight value of each therapy;

[0026] S33: Determine the priority of each therapy module based on the corrected comprehensive weight value;

[0027] The therapies include: mindfulness-based cognitive therapy, cognitive behavioral therapy, exercise therapy, cognitive behavioral therapy for insomnia, interpersonal psychotherapy, and cognitive training.

[0028] Further: In step S32, the formula for correcting the overall weight value of each therapy is:

[0029]

[0030] in, I j For therapy j The overall weight value, α As the basic weight of the composite index, β For the weight of the time decay factor, i User feature weights, U t Weighted values ​​for patient characteristics, t At the current time point, c and t 0 is a parameter that controls the decay rate.

[0031] Furthermore: the aforementioned U t The correction rules for patient characteristic weighting values ​​include:

[0032] Age-weighted adjustment: When the patient is over 60 years old, the interpersonal psychotherapy weighting index is increased by 0.1;

[0033] Occupational weighting adjustment: When the patient is employed in professions such as internet, the weighting index of exercise therapy is increased by 0.1;

[0034] Body Mass Index (BMI) Correction: When a patient's BMI is overweight or obese, the exercise therapy weighted index is increased by 0.1.

[0035] Physical Illness Weight Adjustment: Based on the type of disease the patient suffers from, the weight of the corresponding treatment is increased.

[0036] Further: In step S5, the method for calculating the comprehensive weight value of daily tasks includes:

[0037] Calculate the schedule item:

[0038]

[0039] in, P current Current task progress P target For the target progress;

[0040] Evaluation criteria for computational tasks:

[0041]

[0042] in,

[0043]

[0044] D Rate the difficulty level. L Rate it according to your liking. E Validity score;

[0045] Calculate the time coefficient:

[0046]

[0047] in W n 、W h These are the weights for the same time period on the current day and historically. C n 、C h These are the average completion rates for the same period on the current day and historically.

[0048] Overall weight value = progress item × evaluation item × time coefficient.

[0049] Furthermore, methods for dynamically adjusting the training content for the following day based on the calculated comprehensive weight value of the daily tasks include:

[0050] Next day's task type adjustment: Sorted by the proportion of the overall weight value of the task, the tasks with a high proportion are pushed as mandatory tasks;

[0051] The number of tasks will be adjusted the following day:

[0052]

[0053] in, T Count The number of tasks for the next day; N Base This serves as a baseline for the number of tasks. W t This represents the overall weighting value for the task.

[0054] The difficulty of the next day's mission has been adjusted.

[0055]

[0056] in D new The difficulty level of the next day's task; D current Given the current task difficulty, P a For actual completion rate, P t To the target progress, f(D) The ideal difficulty function;

[0057] Next day training time slot reset: Based on past training completion status, dynamically adjust the weight of the optimal training time slot.

[0058] Furthermore: In step S6, the periodic assessment of the patient's condition is conducted every two weeks, and the formula for periodically recalculating the priority of each therapy is as follows:

[0059]

[0060] in, α =0.4, β =0.3, c =0.2, d =0.1, W t This is the previous overall weight value. F r User feedback coefficient T r The time decay factor, P r This represents the degree of achievement of the phase goals.

[0061] Furthermore: the user feedback coefficient Fr The calculation formula is:

[0062]

[0063] in, ΔMetric For the rate of improvement of indicators, w i The weight of this indicator, Compliance Bonus The reward is based on adherence and is calculated according to the patient's completion of treatment tasks.

[0064] Furthermore: the calculation rule for the compliance reward is as follows:

[0065] If the average task completion rate is greater than 90% in the first two weeks, the reward is 0.5.

[0066] The average task completion rate in the first two weeks was between 60% and 90%, with a reward of 0.3.

[0067] If the average task completion rate is less than 60% in the first two weeks, the reward will be 0.

[0068] When the suicide factor is triggered, i.e., a score of 2 or higher on item 9 of the PHQ-9, the system will forcibly recommend manual intervention.

[0069] Furthermore, the treatment modules include mindfulness-based cognitive therapy, cognitive behavioral therapy, exercise therapy, cognitive behavioral therapy for insomnia, interpersonal psychotherapy, and cognitive training. The training cycle for the treatment program is nine weeks, seven days a week, and the daily training content includes theoretical learning, mandatory tasks, and optional tasks.

[0070] Compared with the prior art, the present invention has the following advantages:

[0071] I. This invention utilizes a multi-dimensional data fusion assessment model that comprehensively considers factors such as the patient's physiological data, psychological state, cognitive function, and behavioral habits, enabling a more comprehensive and objective assessment of the patient's depressive state. Compared to traditional assessment methods that rely solely on a single scale, this method reduces subjective bias and provides more accurate assessment results of depression levels, laying the foundation for subsequent personalized treatment.

[0072] Second, this invention employs a weighted coefficient-based therapy prioritization mechanism and a complex task weighting calculation model, which can automatically adjust the content, difficulty, and timing of the treatment plan based on the patient's real-time feedback and status changes. This dynamic optimization mechanism overcomes the limitations of traditional static treatment plans and can better adapt to individual patient differences and status changes during the treatment process.

[0073] Third, by calculating the comprehensive weight value of daily tasks and intelligently adjusting the training content for the following day, this method can provide patients with training tasks of moderate difficulty and reasonable duration, and optimize them according to patient preferences and the optimal training time window, effectively improving patient compliance. Simultaneously, through periodic assessments and user feedback coefficient calculations, continuous improvement of treatment outcomes is achieved.

[0074] Fourth, this invention constructs a complete closed-loop feedback system through a dual optimization mechanism of short-cycle (daily adjustment) and long-cycle (bi-weekly reassessment). This reinforcement learning-like mechanism can continuously learn from patient feedback and optimize treatment strategies, achieving continuous improvement in treatment outcomes. Attached Figure Description

[0075] Figure 1 This is a flowchart illustrating a dynamic adjustment method for a mindfulness-based therapy for depression in one embodiment of the present invention. Detailed Implementation

[0076] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0077] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0078] This invention provides a dynamic adjustment method for a mindfulness-based treatment plan for depression. Through multi-dimensional data collection, comprehensive evaluation, priority determination, plan generation, dynamic adjustment, and phased optimization, it achieves precision and personalization in the treatment of depression. The technical solution of this invention will be described in detail below with reference to specific embodiments.

[0079] In one embodiment of the present invention, the dynamic adjustment method based on mindfulness-based therapy for depression includes six main steps: collection of multidimensional patient information, comprehensive assessment of depression level, determination of priority of treatment modules, generation of initial treatment plan, dynamic adjustment of daily tasks, and phased optimization. Specifically, it includes the following steps:

[0080] S1: Collect multidimensional information about the patient.

[0081] Specifically, the collected information includes three categories of data: lifestyle risk data, psychological scale data, and cognitive function assessment data. Lifestyle risk data includes the patient's name, gender, date of birth, average daily steps, average daily sedentary time, nighttime sleep duration, cumulative daily screen time, physical illness information, dietary habits, training content format preferences (audio-visual), and training time preferences (morning, noon, evening). Psychological scale data includes scores on the Hypodepressive Cognitive Inventory-9 (PHQ-9), the Hypodepressive Anxiety Inventory (HAMA), the Insomnia Inventory (ISI), the Interpersonal Problems Scale-Solution (IIP-SC), the Five Factor Mindfulness Scale (FFMQ), the Regurgitation Scale (RSS), and the Adaptive Disorder Scale (ADNM). Cognitive function assessment data is obtained through four cognitive tasks: dot detection task, spatial recognition task, symbol-digit conversion, and the stroop task, which assess the patient's attentional bias, memory, processing speed, and executive function, respectively.

[0082] S2: Based on the collected multidimensional information, comprehensively assess the patient's level of depression.

[0083] Specifically, the assessment process consists of two steps: first, the risk indicators strongly associated with depression are standardized to make them comparable; then, multiple linear regression analysis is performed to establish a depression level assessment model.

[0084] Standardized indicators include: anxiety level, attentional bias, memory function, processing speed, executive function, insomnia severity, interpersonal problems scale score, daily steps, daily screen time, daily sedentary time, and physical illness. Taking sedentary time as an example, daily sedentary time ≤ 2 hours is the optimal situation (normalized value 1); daily sedentary time ≥ 6 hours is the worst situation (normalized value 0). For sedentary time between 2 and 6 hours, the normalized value is calculated using the following formula:

[0085]

[0086] in, T jz This represents the normalized sedentary time. t This represents the actual time spent sitting.

[0087] Screen time and steps are also normalized using a similar method.

[0088] Multiple linear regression analysis was conducted by collecting a large amount of patient data on various risk indicators and PHQ-9 depression scale scores, using each risk indicator as an independent variable and the depression score as a dependent variable, and establishing a regression model using the multiple linear regression method.

[0089] Sphq = a + β 1×Anxiety+ β 2× Attention bias + β 3× Memory function +...+ β 12 × Physical illness.

[0090] Based on the predicted PHQ-9 score, the level of depression is divided into three levels: low risk (predicted PHQ-9 ≤ 9 points); medium risk (predicted PHQ-9 10-14 points); and high risk (predicted PHQ-9 ≥ 15 points).

[0091] S3: Determine the priority of treatment modules based on the patient's multidimensional information.

[0092] Specifically, the therapy modules in this embodiment include: mindfulness-based cognitive therapy, cognitive behavioral therapy, exercise therapy, cognitive behavioral therapy for insomnia, interpersonal psychotherapy, and cognitive training. The method for determining priorities includes three sub-steps: calculating the initial comprehensive weight value for each therapy, correcting the comprehensive weight value for each therapy, and determining the priority based on the corrected comprehensive weight value.

[0093] The initial overall weight value for each therapy is calculated by weighted summation of the key indicators for each therapy module. For example, the key indicators and weights for mindfulness-based cognitive therapy are: mindfulness level (0.3), history of relapse (0.25), anxiety (0.2), attentional bias (0.15), and physical illness (0.1), with the following overall weight value:

[0094]

[0095] in w j As weight, x j' These are the standardized indicator values. Other therapies, such as cognitive behavioral therapy and interpersonal psychotherapy, also use similar methods to calculate their initial comprehensive weight values.

[0096] The formula for adjusting the overall weight of each therapy is as follows:

[0097]

[0098] in, I j For therapy j The overall weight value, α This is the basic weight of the composite index (default 0.6). β The weight of the time decay factor is 0.3 initially, which decreases exponentially as treatment progresses. i User feature weights (default 0.1). U tWeighted values ​​for patient characteristics, t At the current time point, c and t 0 is a parameter that controls the decay rate (e.g.) c =0.1, t 0 = 14 days.

[0099] Patient feature weighting U t The correction rules include: age weighting correction (when the patient is over 60 years old, the interpersonal psychotherapy weighting index is increased by 0.1); occupation weighting correction (when the patient is in an internet-related occupation, the exercise therapy weighting index is increased by 0.1); body mass index correction (when the patient's BMI is overweight or obese, the exercise therapy weighting index is increased by 0.1); and physical disease weighting correction (the weight of the corresponding therapy is adjusted according to the patient's specific disease type, such as the exercise therapy index for patients with metabolic diseases is increased by 0.05, and the MBCT index for patients with chronic pain is increased by 0.05, etc.).

[0100] The therapies are ranked in descending order based on the corrected comprehensive weight values. The top 3 therapies are recommended as mandatory training tasks, and the remaining therapies are pushed as optional training tasks. In addition, the system has set two special rules: a mandatory rule (when the patient's comprehensive depression assessment level is moderate or above, MBCT is mandatory as the first priority) and a safety rule (when the suicide factor is triggered, i.e., the score of item 9 in PHQ-9 is 2 or above, the system will mandatoryly recommend manual intervention).

[0101] S4: Generate the initial treatment plan for the patient based on the priority of the therapy module.

[0102] Specifically, the system pre-sets a nine-week training plan, seven days a week, with at least 45 minutes per day. Based on the aforementioned treatment priorities, corresponding training content is matched to the patient. The initial treatment plan includes theoretical learning, mandatory tasks, and optional tasks, each with detailed instructions on training content, time, and format.

[0103] S5: Calculate the comprehensive weight value of daily tasks and dynamically adjust the training content for the next day.

[0104] Specifically, the method for calculating the overall weight value of daily tasks includes calculating the progress item, the evaluation item, and the time coefficient.

[0105] The formula for calculating the progress item is:

[0106]

[0107] in, P current Current task progress P target For the target progress.

[0108] The formula for calculating the evaluation items is:

[0109]

[0110] in,

[0111]

[0112] D Difficulty rating (1-5). L Rate your liking level (1-5). E Validity score (1-5).

[0113] The formula for calculating the time coefficient is:

[0114]

[0115] in W n 、W h These are the weights for the same time period on the current day and historically. C n 、C h These are the average completion rates for the current day and for the same historical period, respectively.

[0116] Ultimately, the overall weight value = schedule item × evaluation item × time coefficient.

[0117] Based on the calculated daily task weight value, the system dynamically adjusts the training content for the next day in four aspects: task type adjustment, task quantity adjustment, task difficulty adjustment, and training time period reset.

[0118] Task type adjustment is achieved by sorting tasks in descending order based on their respective proportions. Tasks with higher proportions are designated as mandatory. The formula for calculating the proportion of each task is as follows:

[0119] .

[0120] The formula for adjusting the number of tasks is as follows:

[0121]

[0122] in, T Count The number of tasks for the next day; N Base This serves as a baseline for the number of tasks. W tThis is the overall weight value for the tasks. The specific rules are as follows: when Wt≥0.8, add 1-2 tasks of the same type; when 0.5≤Wt<0.8, maintain the current number of tasks of the same type; when Wt<0.5, reduce 1 task of the same type.

[0123] The formula for adjusting task difficulty is as follows:

[0124]

[0125] in D new The difficulty level of the next day's task; D current Given the current task difficulty, P a For actual completion rate, P t The target progress (expected to be 100%). f(D) The ideal difficulty function is used. Training time slot reset is achieved by analyzing the patient's training completion rate, effectiveness score, and liking score for each time period over the past week, calculating the optimal training time slot, and adjusting the weight allocation accordingly.

[0126] S6: Periodically assess the patient's condition, recalculate the priority of each therapy module, and optimize the treatment plan.

[0127] Specifically, the phased assessments will be conducted every two weeks, starting from week 3. The formula for recalculating the priority of each therapy during each phase is as follows:

[0128]

[0129] in, α =0.4, β =0.3, c =0.2, d =0.1, W t This is the previous overall weight value. F r User feedback coefficient T r The time decay factor, P r This represents the degree of achievement of the phase goals.

[0130] The formula for calculating the user feedback coefficient Fr is:

[0131]

[0132] in, ΔMetric For the rate of improvement of indicators, w i The weight of this indicator, Compliance BonusThis is a compliance reward, calculated based on the patient's completion of treatment tasks. The calculation rules for compliance rewards are as follows: if the average task completion rate in the first two weeks is greater than 90%, the reward is 0.5; if the average task completion rate in the first two weeks is between 60% and 90%, the reward is 0.3; if the average task completion rate in the first two weeks is less than 60%, the reward is 0.

[0133] Time decay factor T r Controlled using the Sigmoid function:

[0134] .

[0135] Phase Goal Achievement P r The trigger conditions are: the stage goal is achieved, the PHQ-9 score decreases by ≥20%, and the HAMA score decreases by ≥15%; if the goal is achieved, Pr=1, otherwise it is 0.

[0136] Based on the recalculated treatment priorities according to the phased assessment results, the system adjusts the content and difficulty of subsequent treatment plans to continuously optimize treatment outcomes. This dual adjustment mechanism (daily task adjustment and bi-weekly phased optimization) constitutes a complete closed-loop feedback system, capable of continuously learning from patient feedback and optimizing treatment strategies.

[0137] In practical applications, this method can also be customized to meet the specific needs of patients. For example, for patients with serious physical illnesses, the weight of corresponding therapies can be increased; for patients at risk of suicide, safety intervention mechanisms can be forcibly activated; and for patients with severely impaired cognitive function, the cognitive difficulty requirements of the training tasks can be reduced.

[0138] Through the above description of specific implementation methods, it can be seen that the dynamic adjustment method based on mindfulness-based treatment for depression provided by the present invention achieves precision and personalization in the treatment of depression through multi-dimensional data fusion and intelligent algorithm dynamic adjustment, which can effectively improve the treatment effect, reduce the risk of relapse, and provide more scientific and effective treatment options for patients with depression.

[0139] The above embodiments are only for illustrating the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement it accordingly. They should not be construed as limiting the scope of protection of the present invention. All equivalent changes or modifications made in accordance with the spirit and essence of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A dynamic adjustment method based on a mindfulness treatment program for depression, characterized in that, Includes the following steps: S1: Collection of multidimensional patient information, including data on patients’ life behavior risk, psychological scale data, and cognitive function assessment data; S2: Based on the patient's multidimensional information, comprehensively assess the patient's level of depression; S3: Determine the priority of treatment modules based on the patient's multidimensional information and depression level; S4: Generate an initial treatment plan for the patient based on the priority of the therapy modules; S5: Calculate the comprehensive weight value of daily tasks and dynamically adjust the training content for the next day; S6: Periodically assess the patient's condition, recalculate the priority of each therapy module, and optimize the treatment plan; In step S3, the method for determining the priority of treatment modules based on the patient's multidimensional information includes: S31: Calculate the initial comprehensive weight value of each therapy; S32: Adjust the overall weight value of each therapy, using the following formula: wherein, I j is a therapy j is a combined weight value, α is a combined index base weight, β is a time decay factor weight, θ is a user feature weight, U t is a patient feature weight, t is a current time point, γ and t 0 is a parameter to control the decay speed; S33: Determine the priority of each therapy module based on the corrected comprehensive weight value; In step S5, the method for calculating the comprehensive weight value of daily tasks includes: Calculate the schedule item: wherein, P current is the current task progress; P target Target progress; Evaluation items for computational tasks: in, D a difficulty score, L a likeability score, E an effectiveness score; Calculate the time coefficient: wherein W n 、W h are respectively the weight of the same time period of the day, history, C n 、C h are respectively the average completion degree of the same time period of the day, history; Overall weight value = Schedule item × Evaluation item × Time coefficient; In step S5, the method for dynamically adjusting the training content for the next day based on the calculated daily task comprehensive weight value includes: Next day's task type adjustment: Sorted by the proportion of the overall weight value of the task, the tasks with a high proportion are pushed as mandatory tasks; The number of tasks will be adjusted the following day: wherein, T Count is the number of tasks for the next day; N Base is the number of tasks reference value, W t is the task comprehensive weight value; The difficulty of the next day's mission has been adjusted. in D new The difficulty level for the next day's mission; D current Given the current task difficulty, P a For actual completion rate, P t To the target schedule, f (D) The ideal difficulty function; Next day training time slot reset: Based on past training completion status, dynamically adjust the weight of the optimal training time slot.

2. The method for dynamically adjusting a mindfulness-based therapy program for depression according to claim 1, characterized in that, In step S2, the methods for comprehensively assessing the patient's level of depression include: Standardize risk indicators strongly associated with depression; Multiple linear regression analysis was conducted to establish a model for determining the level of depression. The patient's depression level is determined based on the calculation results of the depression level assessment model.

3. The method for dynamically adjusting a mindfulness-based therapy program for depression according to claim 2, characterized in that, The risk indicators strongly associated with depression include: anxiety level, attentional bias, memory function, processing speed, executive function, insomnia severity, interpersonal problems scale score, daily steps, daily screen time, daily sedentary time, and physical illness.

4. The method for dynamically adjusting a mindfulness-based therapy program for depression according to claim 1, characterized in that, In step S3, the various therapies include: mindfulness-based cognitive therapy, cognitive behavioral therapy, exercise therapy, cognitive behavioral therapy for insomnia, interpersonal psychotherapy, and cognitive training.

5. The method for dynamically adjusting a mindfulness-based therapy program for depression according to claim 1, characterized in that, The U t The correction rules for patient characteristic weighting values ​​include: Age-weighted adjustment: When the patient is over 60 years old, the interpersonal psychotherapy weighting index is increased by 0.1; Occupational weighting adjustment: When the patient is employed in professions such as internet, the weighting index of exercise therapy is increased by 0.1; Body Mass Index (BMI) Correction: When a patient's BMI is overweight or obese, the exercise therapy weighted index is increased by 0.

1. Physical Illness Weight Adjustment: Based on the type of disease the patient suffers from, the weight of the corresponding treatment is increased.

6. The method for dynamically adjusting a mindfulness-based therapy program for depression according to claim 1, characterized in that, In step S6, the patient's condition is assessed periodically every two weeks, and the formula for recalculating the priority of each therapy is as follows: in, α =0.4, β =0.3, γ =0.2, δ =0.1, W t This is the previous overall weight value. F r User feedback coefficient T r The time decay factor, P r This represents the degree of achievement of the phase goals.

7. The method for dynamically adjusting a mindfulness-based therapy program for depression according to claim 1, characterized in that, User feedback coefficient Fr The calculation formula is: in, ΔMetric For the rate of improvement of indicators, w i The weight of this indicator, Compliance Bonus The reward is based on adherence and is calculated according to the patient's completion of treatment tasks.

8. A method for dynamically adjusting a mindfulness-based therapy program for depression according to claim 7, characterized in that, The calculation rules for the compliance reward are as follows: If the average task completion rate is greater than 90% in the first two weeks, the reward is 0.

5. The average task completion rate in the first two weeks was between 60% and 90%, with a reward of 0.

3. If the average task completion rate is less than 60% in the first two weeks, the reward will be 0. When the suicide factor is triggered, i.e., a score of 2 or higher on item 9 of the PHQ-9, the system will forcibly recommend manual intervention.

9. A method for dynamically adjusting a mindfulness-based therapy program for depression according to any one of claims 1-8, characterized in that, The treatment modules include mindfulness-based cognitive therapy, cognitive behavioral therapy, exercise therapy, cognitive behavioral therapy for insomnia, interpersonal psychotherapy, and cognitive training. The training cycle for the treatment program is nine weeks, seven days a week, and the daily training content includes theoretical learning, mandatory tasks, and optional tasks.

Images