A mental health intervention method, device, electronic device and storage medium

Abstract

This invention provides a method, device, electronic device, and storage medium for mental health intervention. The method includes: acquiring user assessment behavior characteristic data, including consistency scores for answers, reasonableness scores for completion time, and regularity scores for response patterns; determining a credibility index based on the assessment behavior characteristic data, determining a warning level based on the credibility index, and determining a preset first intervention strategy based on the warning level; after the preset first intervention strategy is applied to the user, acquiring user characteristic data and forming a user characteristic vector based on the user characteristic data; assigning a corresponding preset second intervention strategy to the user through a trained classification model and the user's clustering categories for psychological intervention, acquiring intervention effect labels, and stopping the push of the preset second intervention strategy to the user if the levels of several pre-effect labels are lower than the preset label levels. This method can improve the effectiveness of mental health intervention.

Description

Technical Field

[0001] This invention relates to the field of mental health technology, and in particular to a mental health intervention method, device, electronic device, and storage medium. Background Art

[0002] Traditional mental health assessments primarily rely on face-to-face diagnoses and paper-and-pencil questionnaires. These methods are not only time-consuming and costly, but also susceptible to subjective factors and make it difficult to monitor changes in a patient's mental state in real time. Existing mental health systems mainly build user profiles based on psychological test results, lacking in-depth mining and analysis of users' multidimensional behavioral data. They rely solely on current mental state for early warning judgments, resulting in poor intervention effectiveness. Summary of the Invention

[0003] The purpose of this invention is to provide a method, device, electronic device, and storage medium for mental health intervention, in order to solve the technical problem that the effect of mental health intervention in the prior art is poor.

[0004] The technical solution of the present invention is as follows: a method for psychological health intervention is provided, comprising:

[0005] Acquire user assessment behavior characteristic data, which includes consistency score for answering questions, reasonableness score for completion time, and regularity score for response pattern;

[0006] A credibility index is determined based on the assessed behavioral characteristic data; a warning level is determined based on the credibility index; and a preset first intervention strategy is determined based on the warning level.

[0007] After the preset first intervention strategy is applied to the user, user feature data is acquired, and a user characteristic vector is formed based on the user feature data.

[0008] The user's cluster category is determined based on the user's characteristic vector. A corresponding preset second intervention strategy is assigned to the user through the trained classification model and the user's cluster category for psychological intervention. An intervention effect label is obtained. If the level of the intervention effect label is lower than the preset label level, the preset second intervention strategy is stopped from being pushed to the user. The classification model is trained based on the user feature vector sample and the preset second intervention strategy.

[0009] Furthermore, a credibility index is determined based on the assessed behavioral characteristic data, and a warning level is determined based on the credibility index, including:

[0010] The consistency score of the answers, the reasonableness score of the completion time, and the regularity score of the response pattern are weighted and summed to obtain a credibility index. If the credibility index is not greater than a first credibility threshold, the warning level is determined to be Level 1; if the credibility index is greater than the first credibility threshold but not greater than a second credibility threshold, the warning level is determined to be Level 2; if the credibility index is greater than the second credibility threshold but not greater than a third credibility threshold, the warning level is determined to be Level 3; if the credibility index is greater than the third credibility threshold but not greater than a fourth credibility threshold, the warning level is determined to be Level 4; and if the credibility index is greater than the fourth credibility threshold, the warning level is determined to be Level 5.

[0011] Further, a preset first intervention strategy is determined based on the aforementioned warning level, including:

[0012] If the warning level is Level 1, the preset first intervention strategy is regular monitoring; if the warning level is Level 2, the preset first intervention strategy is using a self-help resource package; if the warning level is Level 3, the preset first intervention strategy is using a combination of AI consultation and self-help tools; if the warning level is Level 4, the preset first intervention strategy is utilizing professional psychological counselors and assistive tools; if the warning level is Level 5, the preset first intervention strategy is providing emergency medical referral and immediate psychological intervention.

[0013] Further, user feature data is acquired, and a user characteristic vector is formed based on the user feature data, including:

[0014] Acquire data on course learning and interactive behavior, self-service tool usage and interaction, multimodal interaction of AI consultation, and integrated professional consultation feedback. Use at least one of these dimensions as user feature data, and form a user characteristic vector based on the user feature data.

[0015] Furthermore, the training steps of the classification model include:

[0016] Cluster the user feature vector samples to determine the cluster category of the corresponding users, and use the same preset second intervention strategy to conduct psychological intervention on users in the same cluster category to obtain intervention effect labels. The intervention effect labels are optimized by adjusting the preset second intervention strategy.

[0017] Furthermore, psychological intervention is conducted on users within the same cluster category using the same preset second intervention strategy, and intervention effect labels are obtained, including:

[0018] The same preset second intervention strategy is used to conduct psychological intervention on users in the same cluster category. The intervention effect is tracked in real time and in the short term, and real time effect score and short term effect score are obtained respectively. A comprehensive effect score is determined based on the real time effect score and the short term effect score, and an intervention effect label is obtained based on the comprehensive effect score.

[0019] Furthermore, the immediate effect tracking includes monitoring changes in mood, platform engagement, behavioral responses, and subjective satisfaction, while the short-term effect tracking includes monitoring symptom improvement, functional recovery, treatment adherence, and side effects.

[0020] Another technical solution of the present invention is as follows: a mental health intervention device is provided, including a data acquisition module, an early warning level determination module, a characteristic vector generation module, and an intervention module;

[0021] The data acquisition module is used to acquire user assessment behavior characteristic data, which includes consistency score for answering questions, reasonableness score for completion time, and regularity score for response pattern.

[0022] The warning level determination module is used to determine a credibility index based on the assessment behavior characteristic data, determine a warning level based on the credibility index, and determine a preset first intervention strategy based on the warning level.

[0023] The feature vector generation module is used to acquire user feature data after the preset first intervention strategy is applied to the user, and to form a user feature vector based on the user feature data.

[0024] The intervention module is used to determine the user's cluster category based on the user's characteristic vector, and assign a corresponding preset second intervention strategy to the user through a trained classification model and the user's cluster category to conduct psychological intervention, obtain an intervention effect label, and stop pushing the preset second intervention strategy to the user if the level of the intervention effect label is lower than the preset label level; the classification model is trained based on user feature vector samples and the preset second intervention strategy.

[0025] Another technical solution of the present invention is as follows: an electronic device is provided, including a memory and a processor. The memory stores a computer program that can be executed by the processor. When the processor executes the computer program, it implements the mental health intervention method as described in any of the above technical solutions.

[0026] Another technical solution of the present invention is as follows: a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and the computer program, when executed by a processor, implements the mental health intervention method as described in any of the above technical solutions.

[0027] The beneficial effects of this invention are as follows: It acquires user assessment behavior characteristic data, including consistency scores, completion time rationality scores, and response pattern regularity scores; it determines a credibility index based on the assessment behavior characteristic data, determines a warning level based on the credibility index, and determines a preset first intervention strategy based on the warning level; after the preset first intervention strategy is applied to the user, it acquires user characteristic data and forms a user characteristic vector based on the user characteristic data; it determines the user's cluster category based on the user characteristic vector, and assigns a corresponding preset second intervention strategy to the user for psychological intervention using a trained classification model and the user's cluster category, acquiring an intervention effect label; if the level of the intervention effect label is lower than a preset label level, it stops pushing the preset second intervention strategy to the user; the classification model is trained based on user characteristic vector samples and the preset second intervention strategy; through the above technical solution, it is possible to achieve early warning and intervention for mental health, improve the rationality of mental health intervention, and thus improve the effectiveness of mental health intervention. Attached Figure Description

[0028] Figure 1 This is a flowchart illustrating the mental health intervention method provided in an embodiment of the present invention.

[0029] Figure 2 This is a schematic diagram of the structure of the mental health intervention device provided in an embodiment of the present invention.

[0030] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0032] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0033] Figure 1 This is a flowchart illustrating a mental health intervention method according to an embodiment of the present invention. It should be noted that if substantially the same result is achieved, the mental health intervention method of the present invention does not necessarily follow the same approach. Figure 1 The illustrated process sequence is limited. For example... Figure 1 As shown, this mental health intervention method mainly includes the following steps:

[0034] S101, Obtain user assessment behavior characteristic data, including consistency score for answering questions, reasonableness score for completion time, and regularity score for response pattern;

[0035] In one specific embodiment, standardized psychological scale assessments and scale combination assessments are performed on users, and the user's assessment behavior characteristic data is recorded in real time. The assessment behavior characteristic data may include the consistency score of answering questions, the reasonableness score of completion time, and the regularity score of response pattern.

[0036] As one implementation method, the consistency score for answers can be calculated as follows: For example, question A is "I often feel anxious" (positive scoring, 0-3 points), and question B is "I rarely worry about the future" (negative scoring, 0-3 points); 0 points is never / never, 1 point is rarely / slight, 2 points is often / moderate, and 3 points is always / severe; assuming the user answers, question A is 2 points (often feels anxious), question B is 1 point (rarely worries about the future), positive score = option score, negative score = (highest score + lowest score) - option score, negative score is the converted score of question B, the maximum possible difference = interval normalization, answer consistency score = 1 - (2-2) / 3 = 1, the answer consistency score is 1, indicating complete consistency.

[0037] As one implementation method, the reasonableness of completion time for a scale refers to whether the total time spent by a participant in completing a self-assessment scale matches the number of items, the complexity of the item stems, and the average reading comprehension speed of the respondents. Reasonable time reflects the seriousness of the responses and the reliability of the data, and is an important part of quality control. Each self-assessment scale contains a different number of items; the more items, the longer the completion time should be. Some scales have short item stems, such as "I feel nervous," while others are longer, such as "In the past two weeks, have I often felt depressed due to trivial matters?" The longer the item stem, the more time is required for reading and comprehension. It is generally assumed that respondents answer attentively, with an average reading and reaction time of approximately 5-10 seconds per item. This value may be adjusted based on the participant's age, educational background, and the complexity of the items. The calculation of the reasonableness score for completion time (response anomaly judgment) can be as follows: Reasonableness score for completion time = Overall reasonableness calculation weight × Reasonableness score for time + Calculation weight for uniformity of time distribution × Time distribution score + Extreme time penalty weight × Extreme time penalty score. As an example, the overall time reasonableness calculation weight is 0.5, the overall minimum and maximum times are set, and the reasonable range is [minimum time, maximum time]. The time distribution uniformity calculation weight is 0.3, the time distribution score = 1 / (1 + answer variance / historical variance), the extreme time penalty weight is 0.2, the standard time = 9 × 20 = 180 seconds, the actual time = 138 seconds, within the reasonable range [90, 540], the time reasonableness score = 1.0, the time variance = var([12,8,15,20,10,18,14,25,16]) = 25.8, the reference variance = 30 (based on historical data), the time distribution score = 1 / (1 + 25.8 / 30) = 0.54, there is no extreme time (if there is no extreme time), the extreme time penalty score = 1.0, the completion time reasonableness score = 0.5 × 1.0 + 0.3 × 0.54 +0.2×1.0 = 0.862.

[0038] As one implementation method, response pattern regularity is used to determine whether there is a logical answer trajectory in the user's answering process, reflecting whether the user's answering behavior is regular and stable, and whether there are obvious abnormal response behaviors (such as random selection, repeated selection of the same option, etc.). The response pattern regularity score can be determined by calculating entropy. The higher the entropy, the greater the diversity; the higher the entropy value, the greater the uncertainty, the more uniform the distribution, and the better the diversity. Conversely, the lower the entropy value, the greater the certainty, the more concentrated the distribution, and the worse the diversity. As an example, with a total of 9 questions and the option distribution as follows: 1 (0 times), 2 (2 times), 3 (5 times), 4 (2 times), 5 (0 times), the probability of each option is... = 0 / 9 = 0, = 2 / 9 ≈ 0.22, = 5 / 9 ≈ 0.56, = 2 / 9 ≈ 0.22, = 0 / 9 = 0, Answer entropy (actual entropy): H = -[0×0 + 0.22×(-1.50)+ 0.56×(-0.65) + 0.22×(-1.50) + 0×0] = -[0 + (-0.33) + (-0.364) + (-0.33)+ 0]= -(-1.024) = 1.024 ≈ 1.027. When all options have equal probabilities of being selected, the entropy reaches its maximum value. For 5 options, the probability of each option = 1 / 5 = 0.2, the maximum entropy = -5 × (0.2 × log(0.2)) = -5 × (0.2 × (-1.609)) = -5 × (-0.322) = 1.609. Response pattern regularity score (diversity score) = actual entropy / maximum entropy = 1.027 / 1.609 = 0.64. Diversity score rating: 0.8-1.0 corresponds to excellent diversity, indicating serious answers; 0.6-0.8 corresponds to good diversity, indicating some bias but reasonable; 0.4-0.6 corresponds to average diversity, indicating obvious bias; 0.2-0.4 corresponds to poor diversity, indicating possible response bias; 0.0-0.2 corresponds to very poor diversity, indicating possible random answers or extreme response tendencies.

[0039] S102, determine a credibility index based on the assessment behavior characteristic data, determine a warning level based on the credibility index, and determine a preset first intervention strategy based on the warning level;

[0040] In some embodiments, a credibility index is determined based on the assessment behavior characteristic data, and a warning level is determined based on the credibility index, including:

[0041] The consistency score of the answers, the reasonableness score of the completion time, and the regularity score of the response pattern are weighted and summed to obtain a credibility index. If the credibility index is not greater than a first credibility threshold, the warning level is determined to be Level 1; if the credibility index is greater than the first credibility threshold but not greater than a second credibility threshold, the warning level is determined to be Level 2; if the credibility index is greater than the second credibility threshold but not greater than a third credibility threshold, the warning level is determined to be Level 3; if the credibility index is greater than the third credibility threshold but not greater than a fourth credibility threshold, the warning level is determined to be Level 4; and if the credibility index is greater than the fourth credibility threshold, the warning level is determined to be Level 5.

[0042] In one specific embodiment, the credibility index = × Consistency score in answering questions + ×Completion Time Reasonableness Score+ × Response pattern regularity score, for example = 0.4, = 0.3, = 0.3 (weighting coefficient). Different warning levels can be displayed in different colors on the user interface, with dynamic grading thresholds. Level 1 (dark green) indicates a good mental state, requiring no special intervention; Level 2 (light green) indicates mild psychological stress, and self-help resources can be recommended; Level 3 (yellow) indicates moderate psychological risk, and AI-assisted intervention can be provided; Level 4 (orange) indicates high psychological risk, and professional human counseling can be provided; Level 5 (red) indicates a severe psychological crisis, requiring emergency medical referral.

[0043] In some embodiments, a preset first intervention strategy is determined based on the warning level, including:

[0044] If the warning level is Level 1, the preset first intervention strategy is regular monitoring; if the warning level is Level 2, the preset first intervention strategy is using a self-help resource package; if the warning level is Level 3, the preset first intervention strategy is using a combination of AI consultation and self-help tools; if the warning level is Level 4, the preset first intervention strategy is utilizing professional psychological counselors and assistive tools; if the warning level is Level 5, the preset first intervention strategy is providing emergency medical referral and immediate psychological intervention.

[0045] In one specific embodiment, a preset first intervention strategy is determined based on the warning level. If the warning level is Level 1, the preset first intervention strategy is regular monitoring, which can be once every two weeks, using a lightweight assessment method. If the warning level is Level 2, the preset first intervention strategy is to use a self-help resource package, which may include a psychological course library, meditation exercises, reading materials, and emotion management tools. If the warning level is Level 3, the preset first intervention strategy is to use a combination of artificial intelligence consultation and self-help tools, which may include in-depth conversations with chatbots and personalized exercises. If the warning level is Level 4, the preset first intervention strategy is to utilize professional psychological counselors and auxiliary tools, which may include AI-assisted analysis. If the warning level is Level 5, the preset first intervention strategy is to conduct emergency medical referrals and immediate psychological intervention, which may include hospital green channels and 24-hour monitoring.

[0046] S103, after the preset first intervention strategy is applied to the user, user feature data is obtained, and a user characteristic vector is formed based on the user feature data;

[0047] In some embodiments, acquiring user feature data and forming a user characteristic vector based on the user feature data includes:

[0048] Acquire data on course learning and interactive behavior, self-service tool usage and interaction, multimodal interaction of AI consultation, and integrated professional consultation feedback. Use at least one of these dimensions as user feature data, and form a user characteristic vector based on the user feature data.

[0049] In one specific embodiment, the course learning and interaction behavior dimension may include learning engagement, interaction activity, knowledge absorption effect, and content preference; the self-help tool usage and interaction dimension may include tool usage duration, category, content, and behavioral data; the AI ​​(artificial intelligence) consultation multimodal interaction dimension may include text sentiment evolution, topic distribution, help content recognition, voice sentiment, sentiment consistency, and multimodal features; and the professional consultation feedback integration dimension may include professional profile and consultant confidence, where professional profile = [diagnostic label, treatment recommendation, prognostic assessment, risk level, intervention focus], and consultant confidence = [assessment certainty, treatment response expectation, relapse risk assessment]. The user characteristic data under all the above dimensions can be quantified using values ​​of [0,1].

[0050] S104, determine the user's cluster category based on the user characteristic vector, assign a corresponding preset second intervention strategy to the user through the trained classification model and the user's cluster category for psychological intervention, obtain the intervention effect label, and stop pushing the preset second intervention strategy to the user if the level of the intervention effect label is lower than the preset label level; the classification model is trained based on the user feature vector sample and the preset second intervention strategy.

[0051] In some embodiments, the training steps of the classification model include:

[0052] Cluster the user feature vector samples to determine the cluster category of the corresponding users, and use the same preset second intervention strategy to conduct psychological intervention on users in the same cluster category to obtain intervention effect labels. The intervention effect labels are optimized by adjusting the preset second intervention strategy.

[0053] In one specific embodiment, K-means clustering is used to initially group users and pre-assign strategies. Then, labels are generated by tracking intervention effects. Finally, a classification model capable of predicting the matching effect between users and corresponding strategies is trained, achieving intervention decision optimization from experience-driven to data-driven. Specifically, the user feature vector samples can be clustered to obtain the corresponding user cluster categories. The user feature vector samples can be X = [learning engagement, interaction activity, knowledge absorption effect, content preference, tool usage time, tool category preference, text sentiment mean, topic distribution, voice sentiment consistency, professional diagnostic label, consultant confidence, ...]. The minimization objective function of K-means clustering is... , For the i-th user feature vector sample, For the j-th category, Let be the weights corresponding to the i-th feature and the j-th category. Using the same preset second intervention strategy, psychological intervention is performed on users within the same cluster category to obtain intervention effect labels. An initial preset second intervention strategy can be set, and the intervention effect labels can be optimized by adjusting the preset second intervention strategy.

[0054] In one specific embodiment, after clustering users using the K-means clustering algorithm, each clustering result can be further semanticized to form several clustering labels (clustering categories) with psychological intervention guidance significance. These clustering labels include: High Engagement - Low Distress (CL-A): These users have high learning engagement, relatively stable emotional states, low psychological assessment risk levels, and active platform interaction. Self-help growth resource packages and advanced psychology courses are recommended as intervention methods. High Distress - Proactive Help-Seeking (CL-B): These users exhibit medium to high psychological risk levels and can proactively use AI consultation. Their dialogue texts have high emotional density. A combination of AI consultation and self-help tools is recommended, and this should be incorporated into a continuous intervention process. Low Activity - High Defensiveness (CL-C): These users use tools less frequently, have fewer interactive behaviors, and limited emotional expression, often exhibiting defensive or avoidant attitudes. Intervention strategies should focus on building a sense of security and trust, supplemented by lightweight interactive tasks. Emotionally Sensitive - Low Learning Engagement (CL-D): These users experience significant emotional fluctuations but have low learning engagement on the platform, short tool usage time, and a preference for negative emotional topics. Emotional stabilization training and short-term effectiveness exercises are suitable. High Anxiety - Logically Consistent (CL-E): These users have relatively high psychological assessment scores. High-risk users (CL-F): These users frequently use self-help tools, but their behavior lacks clear purpose and often involves repetitive operations. Intervention should focus on optimizing the tool combination structure and enhancing their self-awareness through goal-oriented guidance. Multimodal conflicting users (CL-G): These users show low risk in scale assessments, but their AI dialogue or voice data reveals a high degree of repression or conflict, indicating potential psychological distress. Intervention should be supported using multimodal emotion recognition results combined with professional human assessment. Professionally labeled, stress-triggered users (CL-H): These users have recently experienced significant stress, have clear professional diagnostic labels within the system, and AI text analysis shows a high emotional activation state. They need rapid access to human consultation or crisis intervention channels. Silent users (CL-I): These users rarely interact and lack effective behavioral or emotional data. They should be activated through gentle content delivery and passive guidance mechanisms. In practical applications, for the current user, the cluster category of the current user can be determined based on the user characteristic vector, and then a corresponding preset second intervention strategy can be assigned to the current user for psychological intervention to obtain the intervention effect label.

[0055] In one specific embodiment, for training the classification model, user group patterns, i.e., cluster labels, can be determined first through clustering. Then, a prediction model is trained based on historical intervention effects. Based on user behavioral characteristics and psychological states (instantaneous effect tracking and short-term effect tracking), intervention effect labels (excellent / good / moderate / poor / harmful) are determined. If the intervention effect label is "excellent," the current intervention plan is recommended and its intensity increased; if the intervention effect label is "harmful," it is stopped immediately, and alternative plans are switched. Others can continue to be observed and adjusted. Training data includes user feature vectors, cluster labels, a preset second intervention strategy, and effect labels. During classification model prediction and iteration, user feature vectors, cluster labels (users), and the preset second intervention strategy can be used as inputs, and the effect (effect label) as the output. The model can be retrained periodically using new label data. The cluster boundaries (increasing or decreasing cluster labels) and classification decision boundaries (increasing or decreasing effect labels) can be adjusted. Incremental learning (new effect feedback data) can be used to update the classification model.

[0056] In one specific embodiment, the pre-set second intervention strategy may include scale tools, psychological self-help tools, psychological science popularization courses, AI-assisted healing frequency, and therapeutic techniques. For primary school users, the scale tools are: pre-test and post-test of the Childhood Depression Questionnaire (CDI); psychological self-help tools are: Little Rabbit's Rainy Day, Echo of the Sea, Emotion Planet Adventure, Fight the Mind Monster, Emotion Adventure, I Am a Treasure Child, and See Your Strengths; psychological science popularization courses are: Qiqi's Mood Weather Station and Positive Suggestion Transformation; AI-assisted healing frequency is: 1 time / week for mild cases, 2-3 times / week for moderate cases, and 4-5 times / week for severe cases; and therapeutic techniques are: gamified CBT cognitive restructuring and emotion recognition and expression. For junior high school users, the following tools are available: Scale tools: Patient Health Questionnaire-9 (PHQ-9) pre-test and post-test; Self-help psychological tools: Echo of the Sea, Emotional Planet Adventure, Fight the Mind Monster, Emotional Adventure, I Am a Treasure Child, See Your Strengths; Popular psychology courses: Make Emotions Sweeter and Less Salty, Where is Your Emotional 'Control Panel'?, Why Does Your Body Also Act Up When You're in a Bad Mood?; AI Healing Chat Frequency: Mild: 1 time / week, Moderate: 2-3 times / week, Severe: 4-5 times / week; Therapeutic Techniques: CBT Cognitive Restructuring, Behavioral Activation, Mindfulness Meditation. For high school and adult users, the following tools are available: Scales: Patient Health Questionnaire-9 (PHQ-9) pre-test and post-test; Self-help tools: Echo of the Sea, Emotional Planet Adventure, Fight the Mind Monster, Emotional Adventure, I Am a Treasure Child, See Your Strengths; Psychological science courses: What to do if you are always at odds with yourself, Adolescent Emotional Adventure; AI-assisted healing frequency: Mild: 1 time / week, Moderate: 2-3 times / week, Severe: 4-5 times / week; Therapeutic techniques: Deep CBT, ACT Acceptance Commitment, DBT Emotion Regulation.

[0057] In some embodiments, psychological intervention is performed on users within the same cluster category using the same preset second intervention strategy to obtain intervention effect labels, including:

[0058] The same preset second intervention strategy is used to conduct psychological intervention on users in the same cluster category. The intervention effect is tracked in real time and in the short term, and real time effect score and short term effect score are obtained respectively. A comprehensive effect score is determined based on the real time effect score and the short term effect score, and an intervention effect label is obtained based on the comprehensive effect score.

[0059] In one specific embodiment, the comprehensive effect score = α × immediate effect score + β × short-term effect score. The intervention effect label can be divided into 5 levels according to the comprehensive effect score: excellent (comprehensive effect score ≥ 1.5) indicates that the intervention effect is significant and the user benefits greatly; good (comprehensive effect score [1.0, 1.5)) indicates that the intervention effect is obvious and the user benefits significantly; moderate (comprehensive effect score [0.5, 1.0)) indicates that the intervention effect is average and the user benefits partially; poor (comprehensive effect score [0-0.5)) indicates that the intervention effect is weak and the user benefits slightly; and harmful (comprehensive effect score < 0) indicates that the intervention produces negative effects. If the level of the intervention effect label is lower than the preset label level (e.g., the third level), then the preset second intervention strategy will stop being pushed to the user.

[0060] In some embodiments, the immediate effect tracking includes monitoring mood changes, platform engagement, behavioral responses, and subjective satisfaction, while the short-term effect tracking includes monitoring symptom improvement, functional recovery, treatment adherence, and side effects.

[0061] In one specific embodiment, immediate effect tracking includes monitoring changes in mood, platform engagement, behavioral responses, and subjective satisfaction, which can be quantified using values ​​of [0,1]. Immediate effect tracking can be for 0-24 hours. Short-term effect tracking includes monitoring symptom improvement, functional recovery, treatment adherence, and side effects, which can also be quantified using values ​​of [0,1]. Short-term effect tracking can be for 1-4 weeks.

[0062] The mental health intervention method provided in this invention acquires user assessment behavior characteristic data, including consistency scores for answers, reasonableness scores for completion time, and regularity scores for response patterns. Based on the assessment behavior characteristic data, a credibility index is determined, a warning level is determined based on the credibility index, and a preset first intervention strategy is determined based on the warning level. After the preset first intervention strategy is applied to the user, user characteristic data is acquired, and a user characteristic vector is formed based on the user characteristic data. The user's cluster category is determined based on the user characteristic vector. Using a trained classification model and the user's cluster category, a corresponding preset second intervention strategy is assigned to the user for psychological intervention. An intervention effect label is obtained. If the level of the intervention effect label is lower than a preset label level, the preset second intervention strategy is stopped from being pushed to the user. The classification model is trained based on user characteristic vector samples and the preset second intervention strategy. This method can achieve early warning and intervention for mental health, improve the rationality of mental health intervention, and thus improve the effectiveness of mental health intervention.

[0063] The mental health intervention method provided in this invention can realize closed-loop management of the entire process from initial assessment and evaluation to continuous intervention. By deeply mining users' comprehensive behavioral data, it can dynamically optimize intervention strategies and integrate multi-dimensional information such as users' assessment data, behavioral data, and feedback data to achieve closed-loop optimization of dynamic risk warning, intelligent intervention recommendation, and effect tracking and feedback. This enables truly personalized and adaptive continuous and precise intervention, thereby improving the effectiveness of mental health intervention.

[0064] Based on the above-described mental health intervention methods, this invention provides a mental health intervention device, the structural schematic of which is shown below. Figure 2 As shown, the mental health intervention device 20 includes a data acquisition module 21, an early warning level determination module 22, a characteristic vector generation module 23, and an intervention module 24;

[0065] The data acquisition module 21 is used to acquire the user's assessment behavior characteristic data, which includes the consistency score of answering questions, the reasonableness score of completion time, and the regularity score of response pattern.

[0066] The warning level determination module 22 is used to determine a credibility index based on the assessment behavior characteristic data, determine a warning level based on the credibility index, and determine a preset first intervention strategy based on the warning level.

[0067] The feature vector generation module 23 is used to acquire user feature data after the preset first intervention strategy is applied to the user, and to form a user feature vector based on the user feature data.

[0068] The intervention module 24 is used to determine the user's cluster category based on the user's characteristic vector, and to assign a corresponding preset second intervention strategy to the user through a trained classification model and the user's cluster category for psychological intervention, and to obtain an intervention effect label. If the level of the intervention effect label is lower than the preset label level, the preset second intervention strategy will not be pushed to the user. The classification model is trained based on the user feature vector sample and the preset second intervention strategy.

[0069] For other details regarding the implementation of the above technical solutions by each module in the above-mentioned mental health intervention device, please refer to the description of the mental health intervention method provided in the above-mentioned embodiments of the invention, which will not be repeated here.

[0070] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Figure 3 As shown, the electronic device 30 includes a processor 31 and a memory 32 communicatively connected to the processor 31.

[0071] The memory 32 stores program instructions for implementing the mental health intervention method of any of the above embodiments.

[0072] The processor 31 is used to execute program instructions stored in the memory 32 for mental health intervention.

[0073] The processor 31 can also be referred to as a CPU (Central Processing Unit). The processor 31 may be an integrated circuit chip with signal processing capabilities. The processor 31 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0074] This invention provides a computer-readable storage medium that stores program instructions capable of implementing all the methods described above. The storage medium can be non-volatile or volatile. These program instructions can be stored in the storage medium as a software product and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0075] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0076] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. The above are merely embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

[0077] The above description is merely an embodiment of the present invention. It should be noted that those skilled in the art can make improvements without departing from the inventive concept of the present invention, but these improvements all fall within the protection scope of the present invention.

Claims

1. A mental health intervention method, characterized in that, include: Acquire user assessment behavior characteristic data, which includes consistency score for answering questions, reasonableness score for completion time, and regularity score for response pattern; The consistency score of the answers, the reasonableness score of the completion time, and the regularity score of the response pattern are weighted and summed to obtain a credibility index. If the credibility index is not greater than the first credibility threshold, the warning level is determined to be the first level. If the credibility index is greater than the first credibility threshold and not greater than the second credibility threshold, the warning level is determined to be Level 2; if the credibility index is greater than the second credibility threshold and not greater than the third credibility threshold, the warning level is determined to be Level 3. If the credibility index is greater than the third credibility threshold and not greater than the fourth credibility threshold, the warning level is determined to be level four; If the credibility index is greater than the fourth credibility threshold, the warning level is determined to be the fifth level. A preset first intervention strategy is determined based on the warning level. The determination of the preset first intervention strategy based on the warning level includes: if the warning level is Level 1, the preset first intervention strategy is regular monitoring; if the warning level is Level 2, the preset first intervention strategy is using a self-service resource package; if the warning level is Level 3, the preset first intervention strategy is using a combination of artificial intelligence consultation and self-service tools; if the warning level is Level 4, the preset first intervention strategy is utilizing professional psychological counselors and auxiliary tools; if the warning level is Level 5, the preset first intervention strategy is to conduct emergency medical referral and immediate psychological intervention. After the preset first intervention strategy is applied to the user, user feature data is acquired, and a user characteristic vector is formed based on the user feature data. The user's cluster category is determined based on the user's characteristic vector. A corresponding preset second intervention strategy is assigned to the user through the trained classification model and the user's cluster category for psychological intervention. An intervention effect label is obtained. If the level of the intervention effect label is lower than the preset label level, the preset second intervention strategy is stopped from being pushed to the user. The classification model is trained based on the user feature vector sample and the preset second intervention strategy.

2. The mental health intervention method according to claim 1, characterized in that, Acquiring user feature data and forming a user characteristic vector based on the user feature data includes: Acquire data on course learning and interactive behavior, self-service tool usage and interaction, multimodal interaction of AI consultation, and integrated professional consultation feedback. Use at least one of these dimensions as user feature data, and form a user characteristic vector based on the user feature data.

3. The mental health intervention method according to claim 1, characterized in that, The training steps for the classification model include: Cluster the user feature vector samples to determine the cluster category of the corresponding users, and use the same preset second intervention strategy to conduct psychological intervention on users in the same cluster category to obtain intervention effect labels. The intervention effect labels are optimized by adjusting the preset second intervention strategy.

4. The mental health intervention method according to claim 3, characterized in that, Using the same preset second intervention strategy to conduct psychological intervention on users within the same cluster category, and obtaining intervention effect labels, including: The same preset second intervention strategy is used to conduct psychological intervention on users in the same cluster category. The intervention effect is tracked in real time and in the short term, and real time effect score and short term effect score are obtained respectively. A comprehensive effect score is determined based on the real time effect score and the short term effect score, and an intervention effect label is obtained based on the comprehensive effect score.

5. The mental health intervention method according to claim 4, characterized in that, The immediate effect tracking includes monitoring changes in mood, platform engagement, behavioral responses, and subjective satisfaction, while the short-term effect tracking includes monitoring symptom improvement, functional recovery, treatment adherence, and side effects.

6. A mental health intervention device, characterized in that, It includes a data acquisition module, an early warning level determination module, a characteristic vector generation module, and an intervention module; The data acquisition module is used to acquire user assessment behavior characteristic data, which includes consistency score for answering questions, reasonableness score for completion time, and regularity score for response pattern. The warning level determination module is used to perform a weighted summation of the consistency score of the answers, the reasonableness score of the completion time, and the regularity score of the response pattern to obtain a credibility index. If the credibility index is not greater than the first credibility threshold, the warning level is determined to be the first level. If the credibility index is greater than the first credibility threshold and not greater than the second credibility threshold, the warning level is determined to be Level 2; if the credibility index is greater than the second credibility threshold and not greater than the third credibility threshold, the warning level is determined to be Level 3. If the credibility index is greater than the third credibility threshold and not greater than the fourth credibility threshold, the warning level is determined to be level four; If the credibility index is greater than the fourth credibility threshold, the warning level is determined to be the fifth level. A preset first intervention strategy is determined based on the warning level. The determination of the preset first intervention strategy based on the warning level includes: if the warning level is Level 1, the preset first intervention strategy is regular monitoring; if the warning level is Level 2, the preset first intervention strategy is using a self-service resource package; if the warning level is Level 3, the preset first intervention strategy is using a combination of artificial intelligence consultation and self-service tools; if the warning level is Level 4, the preset first intervention strategy is utilizing professional psychological counselors and auxiliary tools; if the warning level is Level 5, the preset first intervention strategy is to conduct emergency medical referral and immediate psychological intervention. The feature vector generation module is used to acquire user feature data after the preset first intervention strategy is applied to the user, and to form a user feature vector based on the user feature data. The intervention module is used to determine the user's cluster category based on the user's characteristic vector, and assign a corresponding preset second intervention strategy to the user through a trained classification model and the user's cluster category to conduct psychological intervention, obtain an intervention effect label, and stop pushing the preset second intervention strategy to the user if the level of the intervention effect label is lower than the preset label level; the classification model is trained based on user feature vector samples and the preset second intervention strategy.

7. An electronic device, comprising a memory and a processor, wherein the memory stores a computer program executable by the processor, characterized in that, When the processor executes the computer program, it implements the mental health intervention method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the mental health intervention method as described in any one of claims 1 to 5.

Images