Generative artificial intelligence and cognitive behavior therapy combined active health management method for old people

Abstract

The invention discloses a generative artificial intelligence and cognitive behavior therapy combined active health management method for old people, and relates to the technical field of active health management for old people, and the method comprises the following steps: 1, collecting the physiological parameters of the old people in real time through a wearable device, collecting the environment parameters of the residence of the old people in real time through an environment sensor, through a psychological assessment tool, based on a preset psychological assessment scale and real-time interactive questions and answers, psychological state parameters of the elderly are collected in real time, and data fusion processing is performed to construct an elderly health data set, so that the influence of physiological, environmental and psychological factors on the health of the elderly can be comprehensively considered; therefore, the overall health condition of the old people can be reflected more accurately, when the physiological data of the old people are abnormal, the environmental factors and the psychological state of the old people at the moment can be analyzed at the same time, reasons causing the abnormal physiological data of the old people can be known more comprehensively, then corresponding intervention tasks can be generated, and the intervention effect is improved.

Description

Technical Field

[0001] This invention relates to the field of proactive health management technology for the elderly, specifically to a proactive health management method for the elderly that combines generative artificial intelligence with cognitive behavioral therapy. Background Technology

[0002] Proactive health management for the elderly is a management model that focuses on the elderly themselves and aims to achieve continuous improvement in their health status and prevention of disease risks through self-monitoring, active participation, and scientific intervention. Its core lies in "proactivity," enabling the elderly to no longer passively receive medical or nursing services, but to actively take control of their own health through technological tools, knowledge learning, and behavioral adjustments.

[0003] Existing proactive health management methods for the elderly mainly rely on physiological indicators or simple behavioral data, often neglecting the comprehensive impact of environmental factors and psychological state on the health of the elderly. Moreover, in the process of proactive health management for the elderly, the physiological monitoring equipment, psychological assessment tools and intervention systems used are often operating independently, and the data flow is not interconnected. Therefore, when physiological abnormalities occur, it is difficult to analyze the causes of physiological abnormalities in combination with the elderly’s current psychological state and environmental factors, and it is even more inconvenient to automatically generate targeted cognitive behavioral intervention tasks, resulting in delayed intervention and limited effectiveness.

[0004] Therefore, in view of this, the present invention proposes a proactive health management method for the elderly that combines generative artificial intelligence with cognitive behavioral therapy to make up for and improve the shortcomings of existing technologies. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a proactive health management method for the elderly that combines generative artificial intelligence with cognitive behavioral therapy, thereby resolving the corresponding technical issues raised in the background section.

[0006] To achieve the above objectives, the technical solution adopted in this invention is: a proactive health management method for the elderly that combines generative artificial intelligence with cognitive behavioral therapy, comprising the following steps:

[0007] Step 1: Collect physiological parameters of the elderly in real time through wearable devices, collect environmental parameters of the elderly’s residence in real time through environmental sensors, and collect psychological state parameters of the elderly in real time through psychological assessment tools based on preset psychological assessment scales and real-time interactive Q&A. Then, perform data fusion processing on the collected physiological parameters, environmental parameters and psychological state parameters to construct an elderly health dataset.

[0008] Step 2: Based on the constructed elderly health dataset, combine generative artificial intelligence algorithms to monitor and analyze physiological parameters in real time. According to the preset standard range threshold, physiological parameters that exceed the standard range threshold are marked as abnormal data. Abnormal moments are acquired synchronously, and the abnormal moments are correlated with the corresponding environmental parameters and psychological state parameters to calculate the coupling coefficient.

[0009] Step 3: Based on the calculated coupling coefficient, a cognitive behavioral intervention task is generated for the elderly person’s current situation by combining generative artificial intelligence algorithm with the principles of cognitive behavioral therapy. This task includes emotion regulation methods and behavior adjustment suggestions. The generated cognitive behavioral intervention task is then pushed to the elderly person in real time via mobile terminal device.

[0010] Preferably, in step one:

[0011] The environmental sensors include temperature sensors, humidity sensors, and air quality index sensors installed in the elderly's residences. The psychological assessment tool is a psychological assessment application installed on a mobile terminal device. The preset psychological assessment scales include an emotional state scale, a stress level scale, and a cognitive function index scale.

[0012] The physiological parameters include heart rate, blood pressure, and blood oxygen saturation; the environmental parameters include temperature, humidity, and air quality index; and the psychological state parameters include emotional state score, stress level score, and cognitive function index score.

[0013] As a preferred approach, based on the elderly’s answers and interactive question-and-answer results on the Emotional State Scale, Stress Level Scale, and Cognitive Function Index Scale, the total scores of the elderly on each scale are added together to obtain the Emotional State Score, Stress Level Score, and Cognitive Function Index Score.

[0014] As a preferred approach, the specific process for constructing a health dataset for the elderly is as follows:

[0015] S101. Obtain physiological parameters, environmental parameters, and psychological state parameters, and use the time series of the heart rate parameter with the highest sampling frequency among the physiological parameters as a benchmark to perform time alignment of the environmental parameters and psychological state parameters using interpolation.

[0016] S102. After time alignment, physiological parameters, environmental parameters, and psychological state parameters are integrated in the form of database tables. The integrated data is then standardized to unify parameters of different dimensions to the same scale range, so as to construct a health dataset for the elderly.

[0017] As a preferred method, the specific process for marking physiological parameters that exceed the standard range threshold as abnormal data is as follows:

[0018] S201. Obtain historical health datasets from historical databases, and based on these datasets, use a generative adversarial network (GAN) algorithm model to monitor and analyze physiological parameters in real time. Divide the historical health datasets into training and testing sets in a 7:3 ratio. Use the training set to train the GAN algorithm model, and use cross-validation to prevent overfitting. This allows the GAN algorithm model to learn the distribution characteristics and patterns of normal physiological parameters. Use the testing set to test and evaluate the trained GAN algorithm model, and further optimize the GAN algorithm model based on the evaluation results.

[0019] S202. Obtain the health dataset of the elderly and input the physiological parameters into the trained generative adversarial network algorithm model. The generative adversarial network algorithm model judges the input physiological parameters for anomalies based on the learned normal physiological parameter distribution characteristics. If the difference between the physiological parameters and the normal distribution exceeds the preset threshold, the input physiological parameters are initially judged as abnormal values.

[0020] S203. Based on the judgment result of outliers, compare it with the preset standard range threshold. If the input physiological parameter exceeds the standard range threshold, and the generative adversarial network algorithm model determines that the input physiological parameter is initially judged as an outlier, then the judged outlier is simultaneously marked as abnormal data.

[0021] As a preferred method, the specific process for calculating the coupling coefficient is as follows:

[0022] S301. Based on labeled abnormal data, obtain the abnormal time corresponding to the abnormal data, simultaneously obtain the environmental parameters and psychological state parameters corresponding to the abnormal time and organize them into data pairs. Use the Pearson correlation coefficient method to calculate the correlation between the psychological state parameters and the abnormal data to obtain the Pearson correlation coefficient r, the formula of which is:

[0023]

[0024] The sequence of psychological state parameters is X = (x1, x2, ..., x...). n );

[0025] The abnormal data sequence is Y = (y1, y2, ..., y n );

[0026] It is the mean of the sequence of psychological state parameters;

[0027] It is the mean of the outlier data sequence;

[0028] The value of r ranges from [-1, 1]. The closer the absolute value of r is to 1, the stronger the linear correlation between the two variables. The closer r is to 0, the weaker the linear correlation between the two variables.

[0029] S302. Based on environmental parameters, the Pearson correlation coefficient r is adjusted to calculate the coupling coefficient C between environmental parameters, psychological state parameters, and abnormal data. The formula is as follows:

[0030] C = r × f(e);

[0031] Where f(e) is the adjustment function;

[0032] e represents the environmental parameter;

[0033] The value of C ranges from [-1, 1]. The larger the absolute value of C, the stronger the coupling relationship.

[0034] As a preferred approach, the specific process for generating cognitive-behavioral intervention tasks tailored to the current situation of older adults is as follows:

[0035] S401. Based on the calculated Pearson correlation coefficient and coupling coefficient, locate the root cause of the current health problems of the elderly. According to the principles of cognitive behavioral therapy, design cognitive intervention content, push guiding words to the elderly through mobile terminal devices, provide the elderly with emotion regulation methods, and at the same time design behavioral intervention measures, and provide behavioral adjustment suggestions to the elderly in combination with environmental parameters and the elderly's physical condition.

[0036] S402. Use mobile terminal devices to push the generated cognitive behavioral intervention tasks to the elderly in real time, and establish a feedback mechanism to collect feedback information from the elderly during the execution of the intervention tasks. Based on the feedback information, use generative artificial intelligence algorithms to adjust and optimize the intervention tasks.

[0037] Compared with existing technologies, the beneficial effects of this invention are as follows: It collects physiological parameters of the elderly in real time through wearable devices, environmental parameters of the elderly's residences in real time through environmental sensors, and psychological state parameters of the elderly in real time through psychological assessment tools based on preset psychological assessment scales and real-time interactive question-and-answer sessions. Data fusion processing is then performed to construct an elderly health dataset. Generative artificial intelligence algorithms are used to monitor and analyze physiological parameters in real time. Based on preset standard threshold ranges, physiological parameters exceeding the standard threshold ranges are marked as abnormal data. Abnormal moments are simultaneously acquired, and correlation analysis is performed between abnormal moments and corresponding environmental and psychological state parameters to calculate the coupling coefficient. Through generative artificial intelligence algorithms combined with cognitive behavioral therapy principles, cognitive behavioral intervention tasks tailored to the elderly's current situation are generated, including emotion regulation methods and behavioral adjustment suggestions. These generated cognitive behavioral intervention tasks are pushed to the elderly in real time via mobile terminal devices. This approach comprehensively considers the impact of physiological, environmental, and psychological factors on the health of the elderly, thus more accurately reflecting their overall health status. When abnormal physiological data is observed, the environmental factors and the elderly's psychological state are analyzed simultaneously to gain a more comprehensive understanding of the causes of the abnormal physiological data, thereby generating corresponding intervention tasks and improving the intervention effect. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the overall structure of a preferred embodiment of the present invention. Detailed Implementation

[0039] 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 some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] Embodiments of the present invention:

[0041] Please refer to Figure 1 As shown, the proactive health management method for the elderly that combines generative artificial intelligence with cognitive behavioral therapy includes the following steps:

[0042] Step 1: Collect physiological parameters of the elderly in real time through wearable devices, collect environmental parameters of the elderly’s residence in real time through environmental sensors, and collect psychological state parameters of the elderly in real time through psychological assessment tools based on preset psychological assessment scales and real-time interactive Q&A. Then, perform data fusion processing on the collected physiological parameters, environmental parameters and psychological state parameters to construct an elderly health dataset.

[0043] Step 2: Based on the constructed elderly health dataset, combine generative artificial intelligence algorithms to monitor and analyze physiological parameters in real time. According to the preset standard range threshold, physiological parameters that exceed the standard range threshold are marked as abnormal data. Abnormal moments are acquired synchronously, and the abnormal moments are correlated with the corresponding environmental parameters and psychological state parameters to calculate the coupling coefficient.

[0044] Step 3: Based on the calculated coupling coefficient, a cognitive behavioral intervention task is generated for the elderly person’s current situation by combining generative artificial intelligence algorithm with the principles of cognitive behavioral therapy. This task includes emotion regulation methods and behavior adjustment suggestions. The generated cognitive behavioral intervention task is then pushed to the elderly person in real time via mobile terminal device.

[0045] In step one:

[0046] The environmental sensors include temperature sensors, humidity sensors, and air quality index sensors installed in the elderly’s residences. The psychological assessment tool is a psychological assessment application installed on a mobile terminal device. The preset psychological assessment scales include an emotional state scale, a stress level scale, and a cognitive function index scale.

[0047] Physiological parameters include heart rate, blood pressure, and blood oxygen saturation; environmental parameters include temperature, humidity, and air quality index; and psychological parameters include emotional state score, stress level score, and cognitive function index score.

[0048] Based on the elderly’s answers and interactive question-and-answer results on the Emotional State Scale, Stress Level Scale, and Cognitive Function Index Scale, the total scores of the elderly on each scale were added together to obtain the Emotional State Score, Stress Level Score, and Cognitive Function Index Score.

[0049] The specific process of constructing a health dataset for the elderly is as follows:

[0050] S101. Obtain physiological parameters, environmental parameters, and psychological state parameters, and use the time series of the heart rate parameter with the highest sampling frequency among the physiological parameters as a benchmark to perform time alignment of the environmental parameters and psychological state parameters using interpolation.

[0051] S102. After time alignment, physiological parameters, environmental parameters, and psychological state parameters are integrated in the form of database tables. The integrated data is then standardized to unify parameters of different dimensions to the same scale range, so as to construct a health dataset for the elderly.

[0052] The specific process for marking physiological parameters that exceed the standard threshold range as abnormal data is as follows:

[0053] S201. Obtain historical health datasets from historical databases, and based on these datasets, use a generative adversarial network (GAN) algorithm model to monitor and analyze physiological parameters in real time. Divide the historical health datasets into training and testing sets in a 7:3 ratio. Use the training set to train the GAN algorithm model, and use cross-validation to prevent overfitting. This allows the GAN algorithm model to learn the distribution characteristics and patterns of normal physiological parameters. Use the testing set to test and evaluate the trained GAN algorithm model, and further optimize the GAN algorithm model based on the evaluation results.

[0054] S202. Obtain the health dataset of the elderly and input the physiological parameters into the trained generative adversarial network algorithm model. The generative adversarial network algorithm model judges the input physiological parameters for anomalies based on the learned normal physiological parameter distribution characteristics. If the difference between the physiological parameters and the normal distribution exceeds the preset threshold, the input physiological parameters are initially judged as abnormal values.

[0055] S203. Based on the judgment result of outliers, compare it with the preset standard range threshold. If the input physiological parameter exceeds the standard range threshold, and the generative adversarial network algorithm model determines that the input physiological parameter is initially judged as an outlier, then the judged outlier is simultaneously marked as abnormal data.

[0056] The specific process for calculating the coupling coefficient is as follows:

[0057] S301. Based on labeled abnormal data, obtain the abnormal time corresponding to the abnormal data, simultaneously obtain the environmental parameters and psychological state parameters corresponding to the abnormal time and organize them into data pairs. Use the Pearson correlation coefficient method to calculate the correlation between the psychological state parameters and the abnormal data to obtain the Pearson correlation coefficient r, the formula of which is:

[0058]

[0059] The sequence of psychological state parameters is X = (x1, x2, ..., x...). n );

[0060] The abnormal data sequence is Y = (y1, y2, ..., y n );

[0061] It is the mean of the sequence of psychological state parameters;

[0062] It is the mean of the outlier data sequence;

[0063] The value of r ranges from [-1, 1]. The closer the absolute value of r is to 1, the stronger the linear correlation between the two variables. The closer r is to 0, the weaker the linear correlation between the two variables.

[0064] S302. Based on environmental parameters, the Pearson correlation coefficient r is adjusted to calculate the coupling coefficient C between environmental parameters, psychological state parameters, and abnormal data. The formula is as follows:

[0065] C = r × f(e);

[0066] Where f(e) is the adjustment function;

[0067] e represents the environmental parameter;

[0068] The value of C ranges from [-1, 1]. The larger the absolute value of C, the stronger the coupling relationship.

[0069] The specific process for generating cognitive-behavioral intervention tasks tailored to the current situation of older adults is as follows:

[0070] S401. Based on the calculated Pearson correlation coefficient and coupling coefficient, locate the root cause of the current health problems of the elderly. According to the principles of cognitive behavioral therapy, design cognitive intervention content, push guiding words to the elderly through mobile terminal devices, provide the elderly with emotion regulation methods, and at the same time design behavioral intervention measures, and provide behavioral adjustment suggestions to the elderly in combination with environmental parameters and the elderly's physical condition.

[0071] S402. Use mobile terminal devices to push the generated cognitive behavioral intervention tasks to the elderly in real time, and establish a feedback mechanism to collect feedback information from the elderly during the execution of the intervention tasks. Based on the feedback information, use generative artificial intelligence algorithms to adjust and optimize the intervention tasks.

[0072] By collecting physiological parameters of the elderly in real time through wearable devices, environmental parameters of their residences in real time through environmental sensors, and psychological state parameters of the elderly in real time through psychological assessment tools based on preset psychological assessment scales and real-time interactive question and answer, the data is fused and processed to construct an elderly health dataset. Generative artificial intelligence algorithms are then used to monitor and analyze physiological parameters in real time. Physiological parameters exceeding preset standard thresholds are marked as abnormal data, and the moments of abnormality are simultaneously acquired. These abnormal moments are then correlated with corresponding environmental and psychological state parameters to calculate the coupling coefficient. Using generative artificial intelligence algorithms combined with cognitive behavioral therapy principles, cognitive behavioral intervention tasks tailored to the elderly's current situation are generated, including emotion regulation methods and behavioral adjustment suggestions. These generated cognitive behavioral intervention tasks are pushed to the elderly in real time via mobile devices. This approach comprehensively considers the impact of physiological, environmental, and psychological factors on the health of the elderly, thus more accurately reflecting their overall health status. When abnormal physiological data is detected, the system simultaneously analyzes the environmental factors and the elderly's psychological state to gain a more comprehensive understanding of the causes of the abnormal physiological data, thereby generating corresponding intervention tasks and improving intervention effectiveness.

[0073] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value.

[0074] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

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

[0076] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A proactive health management method for the elderly that combines generative artificial intelligence with cognitive behavioral therapy, characterized in that: Includes the following steps: Step 1: Collect physiological parameters of the elderly in real time through wearable devices, collect environmental parameters of the elderly’s residence in real time through environmental sensors, and collect psychological state parameters of the elderly in real time through psychological assessment tools based on preset psychological assessment scales and real-time interactive Q&A. Then, perform data fusion processing on the collected physiological parameters, environmental parameters and psychological state parameters to construct an elderly health dataset. Step 2: Based on the constructed elderly health dataset, combine generative artificial intelligence algorithms to monitor and analyze physiological parameters in real time. According to the preset standard range threshold, physiological parameters that exceed the standard range threshold are marked as abnormal data. Abnormal moments are acquired synchronously, and the abnormal moments are correlated with the corresponding environmental parameters and psychological state parameters to calculate the coupling coefficient. Step 3: Based on the calculated coupling coefficient, a cognitive behavioral intervention task is generated for the elderly person’s current situation by combining generative artificial intelligence algorithm with the principles of cognitive behavioral therapy. This task includes emotion regulation methods and behavior adjustment suggestions. The generated cognitive behavioral intervention task is then pushed to the elderly person in real time via mobile terminal device.

2. The method for proactive health management of the elderly combining generative artificial intelligence and cognitive behavioral therapy according to claim 1, characterized in that, In step one: The environmental sensors include temperature sensors, humidity sensors, and air quality index sensors installed in the elderly's residences. The psychological assessment tool is a psychological assessment application installed on a mobile terminal device. The preset psychological assessment scales include an emotional state scale, a stress level scale, and a cognitive function index scale. The physiological parameters include heart rate, blood pressure, and blood oxygen saturation; the environmental parameters include temperature, humidity, and air quality index; and the psychological state parameters include emotional state score, stress level score, and cognitive function index score.

3. The method for proactive health management of the elderly combining generative artificial intelligence and cognitive behavioral therapy according to claim 2, characterized in that, Based on the elderly’s answers and interactive question-and-answer results on the Emotional State Scale, Stress Level Scale, and Cognitive Function Index Scale, the total scores of the elderly on each scale were added together to obtain the Emotional State Score, Stress Level Score, and Cognitive Function Index Score.

4. The method for proactive health management of the elderly combining generative artificial intelligence and cognitive behavioral therapy according to claim 3, characterized in that, The specific process of constructing a health dataset for the elderly is as follows: S101. Obtain physiological parameters, environmental parameters, and psychological state parameters, and use the time series of the heart rate parameter with the highest sampling frequency among the physiological parameters as a benchmark to perform time alignment of the environmental parameters and psychological state parameters using interpolation. S102. After time alignment, physiological parameters, environmental parameters, and psychological state parameters are integrated in the form of database tables. The integrated data is then standardized to unify parameters of different dimensions to the same scale range, so as to construct a health dataset for the elderly.

5. The method for proactive health management of the elderly combining generative artificial intelligence and cognitive behavioral therapy according to claim 4, characterized in that, The specific process for marking physiological parameters that exceed the standard threshold range as abnormal data is as follows: S201. Obtain historical health datasets from historical databases, and based on these datasets, use a generative adversarial network (GAN) algorithm model to monitor and analyze physiological parameters in real time. Divide the historical health datasets into training and testing sets in a 7:3 ratio. Use the training set to train the GAN algorithm model, and use cross-validation to prevent overfitting. This allows the GAN algorithm model to learn the distribution characteristics and patterns of normal physiological parameters. Use the testing set to test and evaluate the trained GAN algorithm model, and further optimize the GAN algorithm model based on the evaluation results. S202. Obtain the health dataset of the elderly and input the physiological parameters into the trained generative adversarial network algorithm model. The generative adversarial network algorithm model judges the input physiological parameters for anomalies based on the learned normal physiological parameter distribution characteristics. If the difference between the physiological parameters and the normal distribution exceeds the preset threshold, the input physiological parameters are initially judged as abnormal values. S203. Based on the judgment result of outliers, compare it with the preset standard range threshold. If the input physiological parameter exceeds the standard range threshold, and the generative adversarial network algorithm model determines that the input physiological parameter is initially judged as an outlier, then the judged outlier is simultaneously marked as abnormal data.

6. The method for proactive health management of the elderly combining generative artificial intelligence and cognitive behavioral therapy according to claim 5, characterized in that, The specific process for calculating the coupling coefficient is as follows: S301. Based on labeled abnormal data, obtain the abnormal time corresponding to the abnormal data, simultaneously obtain the environmental parameters and psychological state parameters corresponding to the abnormal time and organize them into data pairs. Use the Pearson correlation coefficient method to calculate the correlation between the psychological state parameters and the abnormal data to obtain the Pearson correlation coefficient r, the formula of which is: The sequence of psychological state parameters is X = (x1, x2, ..., x...). n ); The abnormal data sequence is Y = (y1, y2, ..., y n ); It is the mean of the sequence of psychological state parameters; It is the mean of the outlier data sequence; The value of r ranges from [-1, 1]. The closer the absolute value of r is to 1, the stronger the linear correlation between the two variables. The closer r is to 0, the weaker the linear correlation between the two variables. S302. Based on environmental parameters, the Pearson correlation coefficient r is adjusted to calculate the coupling coefficient C between environmental parameters, psychological state parameters, and abnormal data. The formula is as follows: C = r × f(e); Where f(e) is the adjustment function; e represents the environmental parameter; The value of C ranges from [-1, 1]. The larger the absolute value of C, the stronger the coupling relationship.

7. The method for proactive health management of the elderly combining generative artificial intelligence and cognitive behavioral therapy according to claim 6, characterized in that, The specific process for generating cognitive-behavioral intervention tasks tailored to the current situation of older adults is as follows: S401. Based on the calculated Pearson correlation coefficient and coupling coefficient, locate the root cause of the current health problems of the elderly. According to the principles of cognitive behavioral therapy, design cognitive intervention content, push guiding words to the elderly through mobile terminal devices, provide the elderly with emotion regulation methods, and at the same time design behavioral intervention measures, and provide behavioral adjustment suggestions to the elderly in combination with environmental parameters and the elderly's physical condition. S402. Use mobile terminal devices to push the generated cognitive behavioral intervention tasks to the elderly in real time, and establish a feedback mechanism to collect feedback information from the elderly during the execution of the intervention tasks. Based on the feedback information, use generative artificial intelligence algorithms to adjust and optimize the intervention tasks.

Images