Health intervention method and device, storage medium and electronic equipment

Abstract

The invention relates to a health intervention method and device, a storage medium and electronic equipment, and relates to the technical field of health management, and the method comprises the steps: obtaining an illness state questionnaire corresponding to the illness state of a patient; in the process that the patient answers the illness state questionnaire, answering behavior characteristics of the patient are detected; then adjusting questions in the illness state questionnaire according to the answering behavior characteristics, and obtaining an adjusted target questionnaire; according to the answering result of the target questionnaire and the answering behavior characteristics of the target questionnaire, determining an early warning result corresponding to the patient; and finally, an intervention scheme determined by the medical terminal is obtained, an intervention evaluation result of the patient on the intervention scheme is received, the intervention scheme determined by the medical terminal is obtained, the intervention evaluation result of the patient on the intervention scheme is received, and the medical terminal is used for obtaining an early warning result of the patient corresponding to the patient terminal and correcting the early warning result of the patient. Determining an intervention scheme of the patient, obtaining an intervention evaluation result of the patient on the intervention scheme, and adjusting the intervention scheme according to a follow-up result of the patient.

Description

Technical Field

[0001] This disclosure relates to the field of health management technology, specifically to a health intervention method, device, storage medium, and electronic device. Background Technology

[0002] With the accelerating pace of society and increasing life pressures, mental health problems are becoming increasingly common, and the incidence of mental illnesses such as depression and anxiety continues to rise. Effective health interventions can promptly improve the health status of individuals or groups and prevent the occurrence or development of diseases.

[0003] Currently, related technologies statically assess a patient's health status based on the total score threshold of a patient's medical questionnaire, lacking dynamic interaction between doctors and patients. Summary of the Invention

[0004] In view of this, the present disclosure provides a health intervention method, device, storage medium and electronic device, the main purpose of which is to solve the technical problem of current related technologies that statically assess the health status of patients through the total score threshold of the patient's condition questionnaire, lacking dynamic interaction between doctors and patients.

[0005] According to a first aspect of this disclosure, a health intervention method is provided, performed by a patient terminal, the method comprising: Obtain the patient's condition questionnaire corresponding to their condition; During the patient's response to the questionnaire, the characteristics of the patient's response behavior were detected; Adjust the questions in the medical questionnaire based on the characteristics of the answering behavior, and obtain the adjusted target questionnaire; Based on the answers to the target questionnaire and the behavioral characteristics of the answers, the corresponding early warning results for the patients are determined; The system obtains the intervention plan determined by the medical terminal, receives the intervention evaluation results of the patient on the intervention plan, the medical terminal is used to obtain the warning results of the patient corresponding to the patient terminal, corrects the warning results of the patient, determines the intervention plan for the patient, obtains the intervention evaluation results of the patient on the intervention plan, the intervention plan is adjusted according to the follow-up results of the patient, and the follow-up results are obtained periodically during the intervention process.

[0006] According to a second aspect of this disclosure, a health intervention method is provided, performed by a healthcare terminal, comprising: The system obtains the patient's warning results corresponding to the patient's terminal. The patient terminal is used to obtain the patient's condition questionnaire. During the patient's answering of the condition questionnaire, the system detects the patient's answering behavior characteristics, adjusts the questions in the condition questionnaire based on the answering behavior characteristics, obtains the adjusted target questionnaire, and determines the patient's corresponding warning result based on the answering results and answering behavior characteristics of the target questionnaire. Revise the patient's early warning results and determine the patient's intervention plan; The intervention program obtains the patient's evaluation results of the intervention plan, which is adjusted based on the patient's follow-up results, which are obtained periodically during the intervention process.

[0007] According to a third aspect of this disclosure, a health intervention device is provided for application on a patient terminal side, the device comprising: The acquisition module is used to acquire the patient's condition questionnaire. The detection module is used to detect the patient's behavioral characteristics during the process of answering the questionnaire about their condition. The acquisition module is used to adjust the questions in the disease questionnaire based on the characteristics of the answering behavior, and to obtain the adjusted target questionnaire. The determination module is used to determine the corresponding early warning result for the patient based on the answer results and answer behavior characteristics of the target questionnaire; The acquisition module is used to acquire the intervention plan determined by the medical terminal, receive the patient's intervention evaluation result of the intervention plan, the medical terminal is used to acquire the patient's warning result corresponding to the patient terminal, correct the patient's warning result, determine the patient's intervention plan, acquire the patient's intervention evaluation result of the intervention plan, the intervention plan is adjusted according to the patient's follow-up results, and the follow-up results are acquired periodically during the intervention process.

[0008] According to a fourth aspect of this disclosure, a health intervention device is provided for use on a healthcare terminal side, the device comprising: The acquisition module is used to acquire the warning results of the patient corresponding to the patient terminal. The patient terminal is used to acquire the disease questionnaire corresponding to the patient's condition. During the patient's answering of the disease questionnaire, the module detects the patient's answering behavior characteristics, adjusts the questions in the disease questionnaire according to the answering behavior characteristics, acquires the adjusted target questionnaire, and determines the warning result corresponding to the patient based on the answering results and answering behavior characteristics of the target questionnaire. The determination module is used to correct the patient's early warning results and determine the patient's intervention plan; The acquisition module is used to acquire the patient's intervention evaluation results for the intervention plan. The intervention plan is adjusted based on the patient's follow-up results, which are acquired periodically during the intervention process.

[0009] According to a fifth aspect of the present disclosure, an electronic device is provided, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the computer program to implement a health intervention method as described in the first or second aspect.

[0010] According to a sixth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a health intervention method as described in the first or second aspect. By utilizing the above technical solutions, the health intervention method, device, and electronic device provided in this disclosure, compared with the prior art, firstly obtain a patient's condition questionnaire corresponding to their condition through a patient terminal; during the patient's answering of the questionnaire, detect the patient's answering behavior characteristics; then adjust the questions in the questionnaire based on the answering behavior characteristics to obtain the adjusted target questionnaire; furthermore, determine the corresponding early warning result for the patient based on the answering results and answering behavior characteristics of the target questionnaire; finally, obtain the intervention plan determined by the medical terminal and receive the patient's intervention evaluation results for the intervention plan. The medical terminal is used to evaluate the early warning results. The intervention plan is revised to determine the patient's intervention plan and the patient's intervention evaluation results are obtained. The intervention plan is adjusted according to the patient's follow-up results, which are obtained periodically during the intervention process. This allows for dynamic adjustment of the target questionnaire during the patient's answering process. Based on the answering results and behavioral characteristics of the adjusted target questionnaire, the patient's early warning result is determined, realizing dynamic evaluation of the patient. It also allows the medical terminal to obtain the intervention plan after the early warning result is revised, realizing dynamic interaction between doctors and patients. The medical terminal can also continuously monitor the intervention effect and optimize the intervention plan based on the follow-up results, thereby optimizing the doctor-patient interaction experience and effect. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0012] To more clearly illustrate the technical solutions in the embodiments or related technologies of this disclosure, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0013] Figure 1 This is a schematic flowchart of a health intervention method provided in an embodiment of the present disclosure; Figure 2 A flowchart illustrating an example provided in an embodiment of this application is shown; Figure 3 A flowchart illustrating an example provided in an embodiment of this application is shown; Figure 4 This is a schematic flowchart of another health intervention method provided in an embodiment of this disclosure; Figure 5A flowchart illustrating an example provided in an embodiment of this application is shown; Figure 6 This is a schematic diagram of the structure of a health intervention device provided in an embodiment of the present disclosure. Figure 7 This is a schematic diagram of the structure of a health intervention device provided in an embodiment of this disclosure. Detailed Implementation

[0014] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description. It should be noted that, unless otherwise specified, the embodiments of this disclosure and the features described therein can be combined with each other.

[0015] The following description, with reference to the accompanying drawings, outlines a health intervention method, apparatus, storage medium, and electronic device according to embodiments of the present disclosure.

[0016] In some embodiments, relying solely on a total questionnaire score threshold (such as the total score of the Symptom Checklist-90, SCL-90) to assess a patient's condition fails to identify dynamic risks, exhibits deficiencies in the early warning mechanism, and has a high false positive rate. In some special cases, such as when the total score meets the threshold but there is no substantial risk (e.g., the patient randomly selects options leading to an inflated total score), this may be due to the limited input parameters, only reading the total questionnaire score and ignoring behavioral data. Secondly, current systems primarily assess patients and return data for manual intervention by doctors. Data feedback and interaction are not timely enough, resulting in a one-way doctor-patient interaction problem.

[0017] To address the technical problem of current methods that statically assess patient health status using a total score threshold from a patient's medical questionnaire, lacking dynamic interaction between doctors and patients, this embodiment provides a health intervention method, such as... Figure 1 As shown, the method, executed by the patient's terminal, includes the following steps: like Figure 1 As shown, embodiments of this disclosure provide a health intervention method, including: Step 101: Obtain the patient's condition questionnaire.

[0018] In some embodiments, patients can independently select a corresponding medical questionnaire based on their perceived condition or the system's preliminary screening results through a patient terminal (such as an application, WeChat mini-program, etc.). After completing the questionnaire, the system assesses the patient's current health status based on their answers and generates and pushes a matching personalized intervention plan accordingly. The patient terminal (patient end, user end) can be used for classification assessment. For different medical questionnaires (such as follow-up questionnaires in multiple follow-up processes), different medical questionnaires are managed by doctors specializing in that area. Patients conduct assessments, and the AI ​​assessment results automatically generate standardized data packages (including risk labels and behavioral feature vectors), allowing them to see the diagnostic and treatment plans provided by the doctor.

[0019] Step 102: During the patient's response to the questionnaire, detect the patient's behavioral characteristics in answering the questions.

[0020] Specifically, during the patient's questionnaire process, event listeners can be embedded in the questionnaire page code. When the user interacts with the page (such as clicking, swiping, inputting, or switching pages), these listeners will automatically record the event's timestamp, type, target element, and other information, enabling multi-dimensional data collection. This includes collecting scale and factor total scores for grading, as well as assessing the patient's behavioral characteristics. The collected patient questionnaire data can also be uploaded to a cloud server in real time or at scheduled intervals. The cloud or the patient's terminal can then process the patient's questionnaire data and extract multi-dimensional behavioral characteristics for problem alerts, obtaining the corresponding behavioral characteristics of the patient.

[0021] For example, answering behavior characteristics may include, but are not limited to, single question answering time, total answering time, frequency of option modification, page dwell time, answering speed change pattern, scrolling / sliding behavior, input text characteristics, device usage characteristics, etc. Each characteristic can be used to reflect different potential psychological meanings (e.g., a student's answering time suddenly increases from 30 seconds to 5 minutes, indicating worsening anxiety). This allows for attention to dynamic behavior during the answering process, improving the real-time detection of the patient's psychological state, facilitating real-time early warning, reducing deficiencies in the early warning mechanism, and thus lowering the false detection rate.

[0022] Step 103: Adjust the questions in the medical questionnaire based on the characteristics of the answering behavior, and obtain the adjusted target questionnaire.

[0023] In some embodiments, AI models (such as machine learning models, deep learning models, etc.) can be used to adjust subsequent follow-up questionnaires based on the user's current answers, perform adaptive assessment, provide an adaptive assessment path, and dynamically adjust subsequent follow-up questions based on the user's current answers, such as adding suicide risk assessment questions after a complete questionnaire detects depressive tendencies. For example, the target questionnaire can be a disease questionnaire that is adjusted in real time based on the patient's answering behavior characteristics, or it can be a questionnaire dynamically adjusted during the current answering process, or an adjusted follow-up questionnaire for subsequent answering processes, etc.

[0024] Specifically, the AI ​​can adaptively adjust questions based on preset adjustment rules. It can extract corresponding questions or questionnaires from a pre-set electronic question bank based on the question adjustment instructions corresponding to the answer behavior characteristics, and perform adjustments such as question modification, replacement, addition, and jump. The selected questions are dynamically assembled into a new questionnaire to generate an adjusted target questionnaire that is suitable for the patient's current health status and reduces the false detection rate.

[0025] Step 104: Based on the answers to the target questionnaire and the behavioral characteristics of the target questionnaire, determine the corresponding early warning result for the patient.

[0026] In some embodiments, AI can be used to automatically generate early warning results for patients based on the answers and behavioral characteristics of the target questionnaire. The early warning results can be used to classify the mental health problems of each patient. Based on different classifications, the AI ​​model can extract the core of the problem, generate early warnings and preliminary intervention plans, and conduct online interventions. In this way, mental health interventions can be carried out in real time, improving diagnostic efficiency.

[0027] Step 105: Obtain the intervention plan determined by the medical terminal and receive the patient's intervention evaluation results.

[0028] The intervention plan is adjusted based on the patient's follow-up results, which are obtained periodically during the intervention process and can be used to monitor the patient's health status. For example, follow-up results for each patient can be obtained according to a preset follow-up cycle. Follow-up results may include, but are not limited to, subjective information (obtainable through questionnaires), objective physiological indicators, behavioral data, medical event records, and physician assessment information. Regular follow-up of patients allows for the periodic tracking of their health status after treatment, in order to monitor the condition and adjust the intervention plan.

[0029] Specifically, the healthcare terminal (doctor's end) can be used to obtain the patient's warning results corresponding to the patient's terminal, correct the warning results, determine the patient's intervention plan based on the patient's follow-up results, and finally obtain the patient's intervention evaluation results. For example, patients can use a mini-program running on their patient terminal to independently select the corresponding questionnaire based on their perceived condition or the system's preliminary screening results (e.g., the Patient Health Questionnaire-9 (PHQ-9) scale for depression, and the Generalized Anxiety Disorder-7 (GAD-7) scale for anxiety disorder). After the patient completes the questionnaire, the system assesses their current health status based on their answers and generates and pushes a matching personalized intervention plan (e.g., pushing relaxation audio to low-risk users, and initiating crisis intervention scripts and generating a doctor's work order for medium- and high-risk users). Doctors can view patient evaluation results, implementation feedback, follow-up results, and other information through the healthcare terminal, and dynamically correct and adjust the intervention plan, thereby achieving closed-loop management of doctor-patient collaboration.

[0030] In some embodiments, the medical terminal can be used to display the warning results of each patient. Doctors can further revise the warning results based on the details of the patient's questionnaire. Patients can rate and provide feedback on the intervention plan revised by the doctor or automatically generated by the patient terminal, and provide feedback on the intervention assessment results to the corresponding doctor. The doctor can then adjust the intervention plan based on the patient feedback and follow-up results, realizing real-time dynamic interaction between doctors and patients, and effectively helping doctors to grasp the development of the patient's condition.

[0031] Compared with related technologies, the patient terminal in this embodiment can obtain a questionnaire corresponding to the patient's condition; during the patient's answering of the questionnaire, the terminal detects the patient's answering behavior characteristics; then, based on the answering behavior characteristics, the terminal adjusts the questions in the questionnaire to obtain the adjusted target questionnaire; furthermore, based on the answering results and answering behavior characteristics of the target questionnaire, the terminal determines the corresponding warning result for the patient; finally, the terminal obtains the intervention plan determined by the medical staff and receives the patient's intervention evaluation results. The medical staff terminal is used to correct the warning result, determine the patient's intervention plan, and obtain the patient's intervention evaluation results. The intervention plan is adjusted according to the patient's follow-up results, which are obtained periodically during the intervention process. This allows for dynamic adjustment of the target questionnaire during the patient's answering process, and determination of the patient's warning result based on the adjusted target questionnaire's answering results and answering behavior characteristics, achieving dynamic evaluation of the patient. It also allows for obtaining the intervention plan after the medical staff terminal corrects the warning result, enabling dynamic interaction between doctors and patients. The medical staff terminal can also continuously monitor the intervention effect and optimize the intervention plan based on the follow-up results, thus optimizing the doctor-patient interaction experience and effect.

[0032] Based on the technical implementation shown in the above embodiments, in order to further illustrate the specific implementation process of the method in this embodiment, step 104 may optionally include: determining the warning result based on the scale score corresponding to the target questionnaire; and / or, establishing a patient profile corresponding to the patient based on the answering behavior characteristics of the target questionnaire, and determining the warning result based on the patient profile.

[0033] Optionally, the patient terminal can determine the warning result based on the scale score corresponding to the target questionnaire and / or the answering behavior characteristics of the target questionnaire, thereby providing multiple warning methods.

[0034] In some embodiments, AI is used to automatically assess a patient's health status based on dynamically adjusted target questionnaire scale scores and provide early warning results. For example, the early warning results may include answer details, early warning level, and early warning information. Correspondingly, a patient profile can be established based on the answer behavior characteristics of the target questionnaire, and early warning results can be generated based on the profile characteristics. For example, early warning results can also be generated by combining profile characteristics and scale scores. Specifically, a multi-factor fusion model can be used to fuse multiple features such as answer behavior characteristics, profile characteristics, and scale scores to provide early warnings about the patient's health status and generate early warning results, thereby avoiding the shortcomings of assessment based solely on a single scale score threshold and improving the accuracy of patient status assessment.

[0035] Among these, the characteristics of answering behavior may include, but are not limited to, answering time and the number of times the question is corrected.

[0036] Optionally, step 104 may further include: generating a warning message based on the comparison between the answer time and the preset answer time threshold; and / or, generating a warning message based on the comparison between the number of times the question is corrected and the preset number of times the question is corrected.

[0037] For example, the preset answer time threshold can be a time range preset based on the patient's average answer time, such as average answer time ± 2 minutes; the preset number of question corrections can be a number range preset based on the patient's average number of question corrections, such as average number of question corrections ± 2 times.

[0038] For example, a mini-program can be used to calculate the patient's average answer time. If the answer time is not within the time range of ±2 minutes of the average answer time, an early warning message can be generated during the patient's answering process. The number of times the patient repeatedly corrects the questions can be counted and the average value can be calculated. If the number of times the target questionnaire corrects the questions is not within the time range corresponding to ±2 times of the average number of corrections, an early warning message can be generated. The early warning message may include, but is not limited to, the early warning level. Optionally, the method in this embodiment may further include: determining the symptom combination group or risk trajectory group corresponding to the patient; pushing the corresponding group intervention plan for the patient's symptom combination group or risk trajectory group, and dynamically adjusting the group intervention plan according to the patient's follow-up results; assigning the target doctor to the target patient according to the warning result of the target patient in the symptom combination group or risk trajectory group, and assigning the target patient to the target doctor's private chat queue.

[0039] In some embodiments, AI-powered data captures patients into groups based on symptom combinations / risk trajectories, automatically generating group intervention templates (e.g., group A receives relaxation training, group B receives medication adherence reminders). Patients requiring medication or psychotherapy are then pushed to the target doctor's account, allowing the doctor to communicate with multiple patients, enabling one-to-many doctor-patient interaction, increasing doctor-patient interaction rates, achieving targeted intervention, and improving intervention efficiency. Correspondingly, the group intervention plan can be dynamically adjusted based on follow-up results of different patient groups to improve the intervention effect for the entire group.

[0040] Specifically, AI can be used for grouping, such as grouping by symptom combination (e.g., "high suicide risk + poor medication adherence"), or by risk trajectory (e.g., "anxiety score weekly increase > 20%" group), and automated intervention can be implemented. For example, if insomnia is the dominant symptom, a sleep restriction therapy tutorial can be pushed to the user; if medication adherence is poor, daily medication reminders and a side effect feedback portal can be provided.

[0041] For example, patients can be tagged based on warning information. Patients with high warning levels (such as those with high-risk events like suicidal tendencies) can be marked as "red-label patients" or "ineffective group interventions," and automatically assigned to a doctor's private chat queue. This effectively reduces the time doctors spend screening a large number of low-risk patients, allowing them to quickly focus on high-risk cases. Furthermore, for users with different risk levels, corresponding target doctors can be matched for management.

[0042] Optionally, the method in this embodiment may further include: classifying the patient's warning results into warning levels and determining the target warning level corresponding to the user; and determining intervention measures corresponding to different target warning levels based on the warning characteristics of the warning results.

[0043] In some embodiments, the warning level may include, but is not limited to, low-risk, medium-risk, and high-risk levels, and the target warning level may be an assessment level determined based on the patient's condition. For different warning levels, AI can be used to capture warning features and match them in real time with simple intervention methods for processing.

[0044] For example, the system can categorize warnings into categories such as "mild anxiety," "depressive tendencies," and "warnings regarding time constraints and repeated revisions," and these can be filtered and sorted by score. The program automatically pushes intervention measures based on the questionnaire results. If the warning level is low risk, relaxation audio / mindfulness exercises can be pushed; if the warning level is medium to high risk, suicide crisis intervention scripts will be activated, and doctor's work orders and treatment suggestions will be automatically pushed.

[0045] Optionally, patient-side functions may also include: matching scales by symptom category (depression → PHQ-9, anxiety → GAD-7); conducting regular follow-up assessments to generate longitudinal mental health profiles; generating structured data packages after receiving assessment data, which may include, but are not limited to, risk tags and behavioral feature vectors. Patients can assess their mental state at any time when they perceive changes in their condition, and if the condition becomes severe, the data will be promptly sent to the doctor's end.

[0046] In some embodiments, such as Figure 2 The diagram illustrates a three-dimensional architecture topology of a system providing an intelligent mental health assessment and intervention system. This system includes patient terminals, medical staff terminals, and a cloud server. It dynamically assesses patients' mental health status through AI algorithms, enabling one-to-many interaction between doctors and patients, tiered early warning systems, two-way structured interactive data analysis, and dynamic evaluation of the treatment process. For example, a regional medical center can receive resource scheduling instructions and coordinate resources. Attending physicians can develop structured and personalized treatment plans based on patient conditions and report high-risk patients. The AI ​​cloud server can generate early warning lists and intervention plans based on scale data and behavioral characteristics. Doctors receive the intervention plans pushed by the AI ​​and make necessary corrections. They can also adjust the intervention plan based on follow-up results. Patients can execute the treatment plan and provide feedback through their terminals. Doctors receive patient feedback and can further adjust the intervention plan, thereby achieving real-time dynamic interaction between doctors and patients.

[0047] Specifically, such as Figure 3The diagram shows the patient-side flowchart. Patients can log in to the system via a mini-program, select an assessment scale, and answer questions dynamically in real time. The system dynamically collects and analyzes the user's answering behavior characteristics, combines the results with AI-based tiered alerts, updates the user's health record in real time, allows viewing of historical records, and generates risk labels (such as mild, moderate, and severe risk). The alert results are then passed to the intervention matching engine, which adapts the path based on the user's answering time, modification frequency, and other behavioral characteristics, adjusting the questions in real time and sending the adjusted results back to the intervention matching engine for automatic matching of appropriate intervention plans. The user receives system notifications. The recommended intervention plan is implemented, and the treatment plan is carried out. During the treatment process, the system can regularly provide feedback on the treatment effect and compliance. Based on the feedback information, the system can continuously optimize the intervention plan, forming a closed loop of continuous improvement. Specifically, the system can obtain the patient's health status according to the current intervention plan through follow-up surveys. The follow-up results of each survey can be sent to the doctor's end, and the system can receive the intervention plan adjusted by the doctor based on the follow-up results. Through continuous follow-up monitoring and optimization of the adjusted intervention plan, the continuity and initiative of doctor-patient collaboration can be enhanced, the doctor-patient interaction experience and effect can be optimized, the frequency of information exchange and response time between doctors and patients can be significantly improved, and the intervention effect can be improved.

[0048] In this way, this embodiment provides an AI closed-loop engine of "dynamic assessment - real-time early warning - precise intervention", establishing a comprehensive psychological health assessment stratification system. It can create a complete psychological health record for patients, allowing them to fully understand their own situation and recognize their illness, and classify psychological health problems. Based on different classifications, the AI ​​model captures the core of the problem, generates early warnings and preliminary intervention plans, and conducts online intervention. During the intervention process, the intervention effect is fed back to the doctor in real time, and the intervention plan is adjusted. This enables real-time dynamic interaction between doctors and patients, helps doctors grasp the development of the patient's condition, facilitates online communication between doctors and patients to promptly detect changes in the patient's condition, address patient problems, and improve patient compliance.

[0049] Compared with related technologies, the patient terminal in this embodiment can determine the warning result based on the scale score and / or the answering behavior characteristics of the target questionnaire, avoiding the defects of assessment based solely on a single scale score threshold, and improving the accuracy of patient status assessment. It can also group patients by symptom combination or risk trajectory, and push corresponding group intervention plans to patients to achieve targeted intervention and improve intervention efficiency. Based on the warning result of the target patient, the terminal assigns the target patient to the target doctor and places the target patient in the target doctor's private chat queue, improving the doctor-patient interaction rate and effectively reducing the time doctors spend screening a large number of low-risk patients, allowing doctors to quickly focus on high-risk cases. Furthermore, for users with different risks, the terminal can match the target doctor with the corresponding direction for management, reducing the misdiagnosis rate. In addition, doctors can view patient assessment results and implementation feedback through the medical terminal, and dynamically modify the intervention plan, solving the problems of insufficient data feedback and interaction and one-way doctor-patient interaction, and realizing closed-loop management of doctor-patient collaboration.

[0050] The above embodiments describe a health intervention process on the patient's terminal side. Furthermore, to fully illustrate the implementation of this embodiment, another health intervention method is provided, executed by a medical terminal. For example... Figure 4 As shown, the method includes: Step 201: Obtain the warning results for the patient corresponding to the patient terminal.

[0051] The patient terminal is used to obtain a questionnaire corresponding to the patient's condition. During the patient's answering of the questionnaire, the terminal detects the patient's answering behavior characteristics, adjusts the questions in the questionnaire based on the answering behavior characteristics, obtains the adjusted target questionnaire, and determines the corresponding warning result for the patient based on the answering results and answering behavior characteristics of the target questionnaire.

[0052] In some embodiments, doctors can view patient information through medical terminals (such as applications, WeChat mini programs, etc.), obtain the warning results of the patients corresponding to the patient terminals, see all the patients under their management, monitor the mental health status of patients at any time, revise treatment plans, and conduct simple online follow-up consultations, realizing a data-driven collaborative governance system for both doctors and patients and enabling classified management.

[0053] Step 202: Revise the patient's early warning results and determine the patient's intervention plan.

[0054] In some embodiments, doctors can correct the warning results given by the patient's terminal through a medical terminal to avoid misdiagnosis caused by abnormalities such as equipment malfunction. Specifically, the diagnostic and treatment plans determined by the doctor are uploaded to the system in a structured format and pushed in real time for treatment. For example, when correcting the AI, the doctor can override the warning conclusion, such as determining that a long time of answering questions is due to equipment malfunction rather than anxiety, or that the patient randomly selected options resulting in an inflated total score, which poses no substantial risk.

[0055] Step 203: Obtain the patient's intervention evaluation results for the intervention plan.

[0056] The intervention plan is adjusted based on the patient's follow-up results, which are obtained regularly during the intervention process. The medical staff terminal can continuously monitor and optimize the intervention plan based on the follow-up results, thereby enhancing the continuity and initiative of doctor-patient collaboration, optimizing the doctor-patient interaction experience and effect, significantly improving the frequency of information exchange and response time between doctors and patients, and thus improving the intervention effect.

[0057] In some embodiments, the medical terminal can obtain the intervention evaluation results from the patient terminal, realize patient feedback-driven iteration, have patients rate the intervention plan (e.g., 1-5 stars), analyze the feedback text, optimize the AI ​​template library based on the analysis results, solve the problems of insufficient data feedback and interaction and one-way doctor-patient interaction, and realize closed-loop management of doctor-patient collaboration.

[0058] Compared with related technologies, this embodiment can obtain the patient's warning results corresponding to the patient terminal through the medical terminal. The medical terminal can correct the warning results given by the patient terminal and continuously monitor the intervention effect of the intervention plan based on the follow-up results, adjust the intervention plan, realize dynamic interaction between doctors and patients, optimize the doctor-patient interaction experience and effect, and the patient terminal can dynamically adjust the target questionnaire during the patient's answering process. Based on the answering results and answering behavior characteristics of the adjusted target questionnaire, the patient's warning result is determined, realizing dynamic assessment of the patient's health status.

[0059] Further optionally, step 201 may specifically include: classifying patients according to their risk level or disease type using a patient grouping dashboard; and displaying the warning results corresponding to different categories of patient groups.

[0060] For example, the doctor-side functionality may include a patient grouping dashboard that displays an overview of all patients and categorizes them by color (possibly based on disease severity, risk level, etc.), and can be presented in categories by risk level / disease type.

[0061] Specifically, such as Figure 5The diagram illustrates the workflow of a healthcare terminal. The system comprises multiple stages, including early warning monitoring, data analysis, treatment plan development, execution tracking, and feedback analysis, ultimately achieving continuous optimization of treatment plans and personalized treatment. For example, doctors can log into the system and view patient information through a patient dashboard. The dashboard can be categorized by color and features early warning monitoring via pop-up alerts, such as prompting doctors to prioritize patients marked in red. After selecting a patient, the doctor retrieves the corresponding data package (such as structured data like the patient's medical records, examination results, and historical treatment records) for structured analysis. Based on the analysis results and standardized templates, a personalized treatment plan is developed. The plan editor refines the plan content (such as medication and therapy options), and the finalized treatment plan is officially published. Relevant healthcare personnel and patients are notified, and the system begins tracking the implementation of the treatment plan. The system receives patient ratings and text feedback to assess treatment effectiveness and satisfaction. Based on patient feedback and treatment effect data, the treatment model and algorithm are continuously revised and optimized. Doctors can also adjust and modify the treatment plan based on follow-up results, early warning results, and other actual patient conditions to improve treatment effectiveness and efficiency. The optimized model can be used for subsequent patient treatment plan development, forming a closed loop of continuous improvement.

[0062] Optionally, step 202 may specifically include: correcting the patient's warning results and determining the patient's intervention plan, including: obtaining the target intervention plan determined by the doctor based on the warning results of the target patient, the target intervention plan including the treatment plan uploaded through the structured treatment plan template; and updating the warning model and intervention template library based on the tracking results of the target patient's execution of the treatment plan.

[0063] Among them, the early warning model (such as AI model, multi-factor fusion model) can be used to output early warning results for target patients, and can be configured on patient terminals, medical staff terminals, cloud servers, etc.; the intervention template library can be used to provide multiple intervention templates (such as AI template library), which can be configured on patient terminals, medical staff terminals, cloud servers, etc. For example, the multi-factor fusion model can integrate the answering behavior characteristics and scale scores of patients during the answering process to conduct early warning of patients' health status and generate early warning results.

[0064] For example, doctors select an intervention plan based on the patient's assessment results, upload a structured treatment plan template, and input a standardized template into the treatment plan (relaxation training / cognitive behavioral therapy steps / medication adjustment / follow-up visits, etc.). The intervention plan can be dynamically revised based on subsequent follow-up results, AI warning data, and other information. Patients can provide feedback on the intervention plan (e.g., "This relaxation training is ineffective"). Accordingly, the intervention plan can be further adjusted based on the patient's feedback.

[0065] Optionally, an alternative architecture for collaborative doctor-patient management can be provided. An independent questionnaire app can be used for assessment, with doctors collecting data in the background, performing manual calculations, and then implementing interventions. Existing communication methods such as WeChat and telephone can be used during intervention. Regarding the choice of intervention strategies, doctors can choose existing plans or specify targeted interventions based on the patient's responses, without AI-assisted intervention. Alternatively, doctors can manually select plans from a fixed intervention library (e.g., pre-stored 10 relaxation training templates).

[0066] In specific application scenarios, a psychological assessment and early warning management system for doctor-patient interaction (an AI-based digital comprehensive intervention system for depression) can be provided. This system may include, but is not limited to, patient-side, family-side, doctor-side, and community-side interfaces. The patient-side may include multi-dimensional assessment modules, multi-dimensional intervention modules, and management modules for multi-dimensional assessment of patients and the development of personalized intervention plans, allowing patients to undergo multi-dimensional personalized intervention training and recording their personal status. The family-side may include science education modules, interactive modules, and Q&A modules for providing science education to family members, assisting with intervention training for patients, and viewing patient information. The doctor-side may include a patient list module, an online multi-dimensional assessment module, and an online help module for online assessment and Q&A. The community-side can connect to the patient-side and doctor-side for manual intervention for high-risk patients. Through intelligent and personalized methods, this system helps patients alleviate depressive symptoms from multiple dimensions throughout the entire process of assessment, treatment, and prognosis.

[0067] In this way, a multi-terminal mental health management system is formed based on medical staff terminals and patient terminals. AI algorithms dynamically assess patients' mental health status, enabling one-to-many interactions between doctors and patients. This system provides tiered early warning, two-way structured interactive data analysis, and dynamic evaluation of the treatment process, improving the accuracy of risk identification and reducing false positives. A multi-factor fusion model combining behavioral characteristics (answering time / modification frequency) and scale scores avoids the limitations of a single total score threshold. It also enhances the sensitivity of dynamic risk capture; if a patient exhibits high-risk events such as suicidal tendencies, a red-mark warning can be triggered, with real-time risk mitigation measures pushed. Furthermore, it optimizes the allocation and efficiency of medical resources, significantly increasing doctor management effectiveness. AI automatically completes 80% of standardized assessments (such as risk grading and intervention template matching), increasing the number of patients a doctor can manage while reducing their workload. Finally, it establishes a categorized diagnosis and treatment mechanism: automatically assigning doctors based on symptom groups. Group interventions are more efficient, with targeted template distribution reducing intervention time by 90%. Patient compliance and efficacy are significantly enhanced, and treatment dropout rates decrease. The two-way interaction mechanism (real-time patient feedback + dynamic doctor adjustment of treatment plans) addresses the "disconnection" pain point of traditional one-way interventions, deepening patients' understanding of the disease. The construction of structured longitudinal health records (including visualized reports of behavioral characteristics) improves patients' understanding of their condition. It facilitates proactive prevention and control of major public safety risks, enabling early warning of suicide / violent incidents. Through high-risk behavior trajectory modeling, crisis intervention can be achieved 72 hours in advance, saving public health resources. The precise grading mechanism ensures that offline emergency interventions focus only on patients with high risk, avoiding excessive use of emergency resources. It possesses system autonomy and continuous evolution capabilities. Feedback data from both doctors and patients (doctor-corrected records + patient ratings) automatically feeds back into the model for training, shortening the intervention plan update cycle from 3 months to 1 week. The medical knowledge base expands dynamically, and structured plans uploaded by doctors (such as new cognitive therapy templates) are anonymized and entered into the AI ​​template library, driving exponential growth in the system's diagnostic and treatment capabilities.

[0068] Compared with related technologies, the medical terminal in this embodiment can correct the warning results given by the patient terminal, continuously monitor the intervention effect of the intervention plan based on follow-up results, adjust the intervention plan, realize dynamic interaction between doctors and patients, optimize the doctor-patient interaction experience and effect, and display the warning results corresponding to different categories of patients, effectively reducing the time doctors spend screening a large number of low-risk patients, allowing doctors to quickly focus on high-risk cases, and matching corresponding target doctors for different risk users for management, thereby improving intervention efficiency. Based on the above Figure 1 The specific implementation of the method shown in this embodiment provides a health intervention device, such as... Figure 6 As shown, the device is applied to the patient terminal side and includes: an acquisition module 31, a detection module 32, and a determination module 33. Module 31 is used to obtain the patient's condition questionnaire. The detection module 32 is used to detect the patient's answering behavior characteristics during the patient's answering of the medical questionnaire; Module 31 is used to adjust the questions in the disease questionnaire based on the characteristics of the answering behavior, and to obtain the adjusted target questionnaire. Module 33 is used to determine the corresponding early warning result for the patient based on the answer results and answer behavior characteristics of the target questionnaire; The acquisition module 31 is used to acquire the intervention plan determined by the medical terminal, receive the patient's intervention evaluation results on the intervention plan, and the medical terminal is used to acquire the patient's warning results corresponding to the patient terminal, correct the patient's warning results, determine the patient's intervention plan, acquire the patient's intervention evaluation results on the intervention plan, and adjust the intervention plan according to the patient's follow-up results. The follow-up results are acquired periodically during the intervention process.

[0069] In some examples of this embodiment, the determining module 33 is specifically configured to determine the warning result based on the scale score corresponding to the target questionnaire; and / or, to establish a patient profile corresponding to the patient based on the answering behavior characteristics of the target questionnaire, and to determine the warning result based on the patient profile; the answering behavior characteristics include the answering time and the number of times the questions were corrected; determining the warning result corresponding to the patient based on the answering results of the target questionnaire and the answering behavior characteristics of the target questionnaire also includes: generating warning information based on the comparison result of the answering time with the preset answering time threshold; and / or, generating warning information based on the comparison result of the number of times the questions were corrected with the preset number of times the questions were corrected.

[0070] In some examples of this embodiment, the determining module 33 is further configured to determine the symptom combination group or risk trajectory group corresponding to the patient; push the group intervention plan corresponding to the patient for the symptom combination group or risk trajectory group, and dynamically adjust the group intervention plan according to the patient's follow-up results; assign the target doctor corresponding to the target patient according to the warning result of the target patient in the symptom combination group or risk trajectory group, and assign the target patient to the target doctor's private chat queue.

[0071] In some examples of this embodiment, the determining module 33 is further configured to classify the patient's warning results into warning levels, determine the target warning level corresponding to the user, and determine the intervention measures corresponding to different target warning levels based on the warning characteristics of the warning results.

[0072] It should be noted that other corresponding descriptions of the functional units involved in the health intervention device applicable to the patient terminal side provided in this embodiment can be found in the following references. Figure 1 The corresponding descriptions of the Chinese methods will not be repeated here.

[0073] Furthermore, as Figure 4The specific implementation of the method shown in this embodiment provides a health intervention device that can be applied to the medical terminal side, such as... Figure 7 As shown, the device includes: an acquisition module 41 and a determination module 42; The acquisition module 41 is used to acquire the warning result of the patient corresponding to the patient terminal. The patient terminal is used to acquire the disease questionnaire corresponding to the patient's condition. During the patient's answering of the disease questionnaire, the patient's answering behavior characteristics are detected. The questions in the disease questionnaire are adjusted according to the answering behavior characteristics. The adjusted target questionnaire is acquired. Based on the answering results of the target questionnaire and the answering behavior characteristics of the target questionnaire, the warning result corresponding to the patient is determined. Module 42 is used to correct the patient's early warning results and determine the patient's intervention plan; The acquisition module 41 is used to acquire the patient's intervention evaluation results for the intervention plan. The intervention plan is adjusted according to the patient's follow-up results, which are acquired periodically during the intervention process.

[0074] In some examples of this embodiment, the acquisition module 41 is further configured to classify patients according to their risk level or disease type through a patient grouping dashboard; display the warning results corresponding to different categories of patient groups; correct the warning results of patients and determine the intervention plan for patients, including: acquiring the target intervention plan determined by the doctor based on the warning results of the target patient, the target intervention plan including the treatment plan uploaded through the structured treatment plan template; updating the warning model and the intervention template library based on the tracking execution results of the target patient's treatment plan, the warning model being used to output the warning results of the target patient, and the intervention template library being used to provide multiple intervention templates.

[0075] It should be noted that other corresponding descriptions of the functional units involved in the health intervention device applicable to the medical terminal side provided in this embodiment can be found in the following references. Figure 4 The corresponding descriptions of the Chinese methods will not be repeated here.

[0076] Based on the above, Figure 1 , Figure 4 Accordingly, this embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. Figure 1 , Figure 4 The method shown.

[0077] Based on this understanding, the technical solution disclosed herein can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive) and includes several instructions to cause a computer device (such as a personal computer, server, or network device) to execute the methods of various implementation scenarios of this disclosure.

[0078] Based on the above, Figure 1 , Figure 4 The method shown, and Figure 6 , Figure 7 To achieve the above objectives, this disclosure also provides an electronic device, comprising a storage medium and a processor; the storage medium for storing a computer program; and the processor for executing the computer program to implement the above-described virtual device embodiments. Figure 1 , Figure 4 The method shown.

[0079] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0080] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0081] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of health intervention programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software within the health intervention physical device.

[0082] Through the above description of the embodiments, those skilled in the art can clearly understand that this disclosure can be implemented by means of software plus necessary general-purpose hardware platforms, or it can be implemented by hardware. Through the solution of this disclosure, the patient terminal can determine the warning result based on the scale score corresponding to the target questionnaire and / or the answering behavior characteristics of the target questionnaire, avoiding the defects of assessment based solely on a single scale score threshold, improving the accuracy of patient status assessment. It can also group patients by symptom combination or risk trajectory, push corresponding group intervention plans to patients, achieve targeted intervention, improve intervention efficiency, assign target doctors to target patients based on the warning results of the target patients, and assign target patients to the target doctor's private chat queue, improving the doctor-patient interaction rate, effectively reducing the time doctors spend screening a large number of low-risk patients, allowing doctors to quickly focus on high-risk cases, and matching target doctors with corresponding directions for management of users with different risks, reducing the misdiagnosis rate. Furthermore, doctors can view patient assessment results and implementation feedback through the medical terminal, and dynamically modify the intervention plan, solving the problems of insufficient data feedback and interaction, and one-way doctor-patient interaction, achieving closed-loop management of doctor-patient collaboration.

[0083] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the term "comprising" or any other variations thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0084] The above are merely specific embodiments of this disclosure, enabling those skilled in the art to understand or implement this disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A health intervention method, characterized in that, include: Obtain the patient's condition questionnaire corresponding to their condition; During the patient's response to the questionnaire, the characteristics of the patient's response behavior were detected; Adjust the questions in the disease questionnaire based on the aforementioned answering behavior characteristics to obtain the adjusted target questionnaire; Based on the answers to the target questionnaire and the behavioral characteristics of the answers, the corresponding early warning result for the patient is determined; The system obtains the intervention plan determined by the medical terminal, receives the intervention evaluation results of the patient on the intervention plan, the medical terminal is used to obtain the warning results of the patient corresponding to the patient terminal, corrects the warning results of the patient, determines the intervention plan for the patient, obtains the intervention evaluation results of the patient on the intervention plan, the intervention plan is adjusted according to the follow-up results of the patient, and the follow-up results are obtained periodically during the intervention process.

2. The method according to claim 1, characterized in that, The determination of the warning result corresponding to the patient based on the answer results and answer behavior characteristics of the target questionnaire includes: The warning result is determined based on the scale score corresponding to the target questionnaire; and / or, Based on the answering behavior characteristics of the target questionnaire, a patient profile corresponding to the patient is established, and the early warning result is determined based on the patient profile; The characteristics of the answering behavior include answering time and the number of times the question was corrected; The step of determining the warning result corresponding to the patient based on the answer results and answer behavior characteristics of the target questionnaire also includes: Based on the comparison between the answer time and the preset answer time threshold, an early warning message is generated; and / or, Based on the comparison between the number of corrected questions and the preset number of corrected questions, an early warning message is generated.

3. The method according to claim 1, characterized in that, The method further includes: Determine the corresponding symptom combination group or risk trajectory group for the patient; Based on the patient's symptom combination group or risk trajectory group, a corresponding group intervention plan is pushed to the patient, and the group intervention plan is dynamically adjusted according to the patient's follow-up results; Based on the warning results of the target patient in the symptom combination group or risk trajectory group, the target patient is assigned a target doctor and the target patient is assigned to the target doctor's private chat queue.

4. The method according to claim 1, characterized in that, The method further includes: The patient's warning results are classified into warning levels to determine the target warning level corresponding to the user; Based on the warning characteristics of the warning results, intervention measures corresponding to different target warning levels are determined.

5. A health intervention method, characterized in that, include: The system obtains the warning result of the patient corresponding to the patient terminal. The patient terminal is used to obtain the disease questionnaire corresponding to the patient's condition. During the patient's answering of the disease questionnaire, the system detects the patient's answering behavior characteristics, adjusts the questions in the disease questionnaire according to the answering behavior characteristics, obtains the adjusted target questionnaire, and determines the warning result corresponding to the patient based on the answering results of the target questionnaire and the answering behavior characteristics of the target questionnaire. The patient's early warning results are revised to determine the patient's intervention plan; The intervention evaluation results of the patient on the intervention plan are obtained, and the intervention plan is adjusted according to the patient's follow-up results, which are obtained periodically during the intervention process.

6. The method according to claim 5, characterized in that, The acquisition of the patient's early warning result corresponding to the patient's terminal includes: Patients are categorized according to their risk level or disease type using a patient grouping dashboard. Displays the warning results corresponding to different categories of patient groups; The process of correcting the patient's early warning results and determining the patient's intervention plan includes: Obtain the target intervention plan determined by the doctor based on the early warning results of the target patient, the target intervention plan including the treatment plan uploaded through the structured treatment plan template; Based on the tracking results of the treatment plan performed by the target patient, the early warning model and the intervention template library are updated. The early warning model is used to output early warning results for the target patient, and the intervention template library is used to provide multiple intervention templates.

7. A health intervention device, characterized in that, include: The acquisition module is used to acquire the patient's condition questionnaire. The detection module is used to detect the patient's behavioral characteristics in answering the questionnaire about their condition. The acquisition module is used to adjust the questions in the medical questionnaire based on the answering behavior characteristics and acquire the adjusted target questionnaire. The determination module is used to determine the warning result corresponding to the patient based on the answer results and answer behavior characteristics of the target questionnaire; The acquisition module is used to acquire the intervention plan determined by the medical terminal, receive the patient's intervention evaluation result of the intervention plan, the medical terminal is used to acquire the patient's warning result corresponding to the patient terminal, correct the patient's warning result, determine the patient's intervention plan, acquire the patient's intervention evaluation result of the intervention plan, the intervention plan is adjusted according to the patient's follow-up results, and the follow-up results are acquired periodically during the intervention process.

8. A health intervention device, characterized in that, include: The acquisition module is used to acquire the warning result of the patient corresponding to the patient terminal. The patient terminal is used to acquire the disease questionnaire corresponding to the patient's condition. During the patient's answering of the disease questionnaire, the module detects the patient's answering behavior characteristics, adjusts the questions in the disease questionnaire according to the answering behavior characteristics, acquires the adjusted target questionnaire, and determines the warning result corresponding to the patient based on the answering results of the target questionnaire and the answering behavior characteristics of the target questionnaire. The determination module is used to correct the patient's early warning results and determine the patient's intervention plan; The acquisition module is used to acquire the patient's intervention evaluation results for the intervention plan. The intervention plan is adjusted according to the patient's follow-up results, which are acquired periodically during the intervention process.

9. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the health intervention method as described in any one of claims 1 to 4, or the health intervention method as described in any one of claims 5 to 6.

10. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform a health intervention method as claimed in any one of claims 1 to 4, or a health intervention method as claimed in any one of claims 5 to 6.

Images