A health management detection method and system for the elderly

Abstract

This application proposes a health management and detection method and system for the elderly, which obtains behavioral task data and physiological data of the elderly through scales or non-invasive devices, extracts data features and fuses them, combines ensemble learning models, deep learning models and statistical learning models to build a cognitive state assessment model set, adopts a differentiated learning strategy to train the cognitive state assessment model set, builds a dynamic assessment system based on cognitive ability scores, and determines the assessment frequency. It adopts a correlation priority strategy of data features to determine the assessment items, establishes nonlinear mapping rules, sets training benchmark parameters according to cognitive ability scores, and formulates personalized cognitive training plans based on the dynamic assessment system and the individual data characteristics of the elderly. This application has a high degree of personalization, simple operation, and continuous and comprehensive data. It can capture the dynamic changes in cognitive ability, understand the differences between elderly groups in real time, and provide a timely and effective feedback mechanism.

Description

Technical Field

[0001] The present application relates to the technical field of cognitive testing for the elderly, and in particular to a method and system for health management testing for the elderly. Background Art

[0002] The core of cognitive health management lies in timely and accurate assessment of the cognitive status of the elderly, and providing personalized intervention measures based on the assessment results to delay the process of cognitive decline and improve the quality of life of the elderly.

[0003] Traditional cognitive assessment methods for the elderly mainly include paper-and-pencil tests, neuropsychological assessments, etc. In recent years, with the rapid development of information technology, technologies based on electronic devices and sensors have gradually been applied to the field of cognitive health management. Existing cognitive monitoring and management applications for the elderly include neuroscale assessment, eye movement technology assessment, and professional equipment assessment; neuroscale assessment utilizes cognitive function data of the elderly, such as attention and memory, but the flow scale is long and highly subjective, and there are many interference factors in actual application; eye movement technology assessment uses the paradigm of forward saccades, reverse saccades, and random saccades combined with eye movement technology to collect the gaze path and area of ​​the elderly when observing specific visual stimuli, but this method cannot be mutually verified with other assessment methods at the same time; professional equipment assessment uses specialized medical equipment and data analysis platforms to achieve data transmission, collection, and management, but this method is expensive and cannot be used as a large-scale cognitive screening tool. In addition, the above methods have many limitations, including:

[0004] Lack of personalized assessment and training programs: Although some applications have adopted different assessment methods, most of them use unified standards to evaluate the cognitive abilities of the elderly, failing to fully consider individual differences. As a result, subsequent training programs lack specificity and cannot meet the specific needs of different elderly people.

[0005] The assessment process is cumbersome and inconvenient: Traditional cognitive assessments usually require on-site guidance and operation by professionals, and involve multiple complex testing steps. For the elderly, there may be problems such as difficulty in operation and low participation. It is also not convenient for long-term and frequent monitoring.

[0006] Incomplete data collection and analysis: Existing assessment methods can often only obtain limited cognitive data, such as simple questionnaire test results. They cannot comprehensively and dynamically monitor the cognitive performance of the elderly in their daily lives, and it is difficult to detect subtle changes in cognitive abilities in a timely manner.

[0007] Lack of real-time feedback and guidance mechanisms: When elderly people are being evaluated or trained, they often cannot understand their performance and progress in real time, and are unable to adjust their behavior and training methods in a timely manner based on feedback, which affects the effectiveness of health management.

[0008] This application aims to solve the above technical problems and provide a method and system for elderly health management detection that can achieve personalized assessment and training, is easy to operate, collects comprehensive data and provides real-time feedback. Summary of the Invention

[0009] This application proposes the following technical solutions to address one or more technical deficiencies in the above-mentioned prior art.

[0010] Based on the first aspect of this application, a health management detection method for the elderly is proposed, comprising:

[0011] S1: Collecting behavioral task data and physiological data of the elderly through a scale or non-invasive device, and transmitting the behavioral task data and the physiological data to the cloud;

[0012] S2: extracting and fusing data features from the behavioral task data and physiological data, wherein the data features include task completion status, reaction time, and visual behavior patterns;

[0013] S3: weighting the ensemble learning model, deep learning model, and statistical learning model according to certain weights to construct a cognitive state assessment model set, training the cognitive state assessment model set using a differentiated learning strategy, analyzing the importance of the data features using a decision tree model, quantifying the correlation strength between the elderly's cognitive level and the data features using a regression model, and using the trained cognitive state assessment model set to score the behavioral task data and physiological data to obtain a cognitive ability score;

[0014] S4: constructing a dynamic assessment system based on the cognitive ability score, determining the assessment frequency by the cognitive ability score, determining the assessment items by adopting the correlation priority strategy of the data features, establishing a nonlinear mapping rule, activating a simplified assessment process when the cognitive ability score is below a preset threshold, and adding a high-level executive function test item when the cognitive ability score is above the preset threshold, thereby forming a step-by-step assessment plan;

[0015] S5: Set training benchmark parameters according to the cognitive ability score, track the behavioral task data and physiological data of the elderly in real time, formulate personalized cognitive training plans based on the dynamic evaluation system and the individual data characteristics of the elderly, compare the training performance of the elderly and provide feedback through personalized guidance suggestions.

[0016] Furthermore, the behavioral task data includes graphic recognition data, memory task data, scale data, interface operation trajectory data, task completion time data and attention test data;

[0017] The physiological data includes blood oxygen saturation data, electroencephalogram signal data, heart rate data and eye movement data.

[0018] Collecting physiological data through non-invasive devices and behavioral task data through a simple and easy-to-use visual interface design can not only ensure the continuity and comprehensiveness of the data, but also ensure the ease of operation for the elderly.

[0019] Furthermore, step S3 also includes using a support vector machine (SVM) to process the EEG signal data and the blood oxygen saturation data, processing the nonlinear separability problem through kernel function transformation, and analyzing the correlation between the eye movement data and the scale data.

[0020] Furthermore, step S3 also includes using a naive Bayes classifier to make conditional independence assumptions on the task completion time data and the interface operation trajectory data and perform rapid reasoning.

[0021] Furthermore, step S3 also includes calculating Gain values ​​for the eye movement data and the scale data, sorting the importance of data features and screening key indicators.

[0022] Furthermore, step S3 also includes using a time series algorithm to capture the long-range dependency of the heart rate data through a memory gating mechanism to reduce the mean absolute error.

[0023] Using a differentiated learning strategy to train a set of cognitive state assessment models can ensure the accuracy and robustness of the model output results.

[0024] Furthermore, step S5 also includes adjusting the personalized cognitive training program through reinforcement learning and state-action-reward mechanism.

[0025] Developing personalized cognitive training programs for the elderly and adjusting them in a timely manner can help them understand their training progress in a timely manner, improve their training enthusiasm, and improve the accuracy and reliability of cognitive assessments.

[0026] Based on the second aspect of this application, a health management and detection system for the elderly is also proposed, including:

[0027] Acquisition module: collects behavioral task data and physiological data of the elderly through a scale or non-invasive device, and transmits the behavioral task data and the physiological data to the cloud;

[0028] Fusion module: extracting data features from the behavioral task data and physiological data and fusing them, wherein the data features include task completion status, reaction time, and visual behavior patterns;

[0029] Analysis module: The integrated learning model, deep learning model, and statistical learning model are weighted according to certain weights to construct a cognitive state assessment model set, the differentiated learning strategy is used to train the cognitive state assessment model set, the importance of the data features is analyzed through a decision tree model, the correlation strength between the cognitive level of the elderly and the data features is quantified through a regression model, and the behavioral task data and physiological data are scored using the trained cognitive state assessment model set to obtain a cognitive ability score;

[0030] Evaluation module: constructing a dynamic evaluation system based on the cognitive ability score, determining the evaluation frequency by the cognitive ability score, determining the evaluation items by adopting the correlation priority strategy of the data features, establishing nonlinear mapping rules, activating a simplified evaluation process when the cognitive ability score is below a preset threshold, and adding high-level executive function test items when the cognitive ability score is above the preset threshold, thereby forming a step-by-step evaluation plan;

[0031] Feedback module: Set training benchmark parameters according to the cognitive ability score, track the behavioral task data and physiological data of the elderly in real time, formulate personalized cognitive training plans based on the dynamic evaluation system and the individual data characteristics of the elderly, compare the training performance of the elderly and provide feedback through personalized guidance suggestions.

[0032] Based on the third aspect of the present application, a computer program product is further proposed, which includes one or more computer programs, and when the computer programs are executed by a computer processor, the method described in any one of the above is implemented.

[0033] The technical effect of this application is that: this application combines and mutually verifies multiple assessment methods, increases the reliability of cognitive assessment results without increasing the complexity of the assessment, solves the problem of separation between behavioral task data and physiological data in traditional elderly cognitive ability assessment, and the problem of a single traditional elderly cognitive ability assessment method, avoids a one-size-fits-all assessment method and training method, improves the reliability of cognitive ability assessment, designs different personalized assessment and training programs for the individual differences of the elderly, accurately adapts to the assessment difficulty, and effectively improves the effect of health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Other features, objects and advantages of the present application will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings.

[0035] Figure 1 This is a general flow chart of a health management and detection method for the elderly provided according to an embodiment of the present application;

[0036] Figure 2This is a general framework diagram of an elderly health management and detection system provided according to an embodiment of the present application;

[0037] Figure 3 This is a specific operation diagram of an elderly health management and detection system provided according to an embodiment of the present application;

[0038] Figure 4 It is a structural diagram of a computer system suitable for implementing the electronic device of the embodiment of the present application. DETAILED DESCRIPTION

[0039] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the relevant invention are shown in the accompanying drawings.

[0040] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0041] Reference below Figure 1 , Figure 1 A method for monitoring health management of the elderly is shown, comprising:

[0042] S1: Collecting behavioral task data and physiological data of the elderly through a scale or non-invasive device, and transmitting the behavioral task data and the physiological data to the cloud;

[0043] S2: extracting and fusing data features from the behavioral task data and physiological data, wherein the data features include task completion status, reaction time, and visual behavior patterns;

[0044] S3: weighting the ensemble learning model, deep learning model, and statistical learning model according to certain weights to construct a cognitive state assessment model set, training the cognitive state assessment model set using a differentiated learning strategy, analyzing the importance of the data features using a decision tree model, quantifying the correlation strength between the elderly's cognitive level and the data features using a regression model, and using the trained cognitive state assessment model set to score the behavioral task data and physiological data to obtain a cognitive ability score;

[0045] S4: constructing a dynamic assessment system based on the cognitive ability score, determining the assessment frequency by the cognitive ability score, determining the assessment items by adopting the correlation priority strategy of the data features, establishing a nonlinear mapping rule, activating a simplified assessment process when the cognitive ability score is below a preset threshold, and adding a high-level executive function test item when the cognitive ability score is above the preset threshold, thereby forming a step-by-step assessment plan;

[0046] S5: Set training benchmark parameters according to the cognitive ability score, track the behavioral task data and physiological data of the elderly in real time, formulate personalized cognitive training plans based on the dynamic evaluation system and the individual data characteristics of the elderly, compare the training performance of the elderly and provide feedback through personalized guidance suggestions.

[0047] It should be noted that the behavioral task data includes graphic recognition data, memory task data, scale data, interface operation trajectory data, task completion time data and attention test data;

[0048] The physiological data includes blood oxygen saturation data, electroencephalogram signal data, heart rate data and eye movement data.

[0049] It should be noted that step S3 also includes processing the EEG signal data and blood oxygen saturation data using a support vector machine (SVM), processing nonlinear separability problems through kernel function transformation, and analyzing the correlation between eye movement data and scale data.

[0050] It should be noted that step S3 also includes using a naive Bayes classifier to make conditional independence assumptions on the task completion time data and the interface operation trajectory data and perform rapid reasoning.

[0051] It should be noted that step S3 also includes calculating Gain values ​​for the eye movement data and scale data, sorting the importance of data features, and screening key indicators.

[0052] It should be noted that step S3 also includes using a time series algorithm to capture the long-range dependency of the heart rate data through a memory gating mechanism to reduce the mean absolute error.

[0053] It should be noted that step S5 also includes adjusting the personalized cognitive training program through reinforcement learning and state-action-reward mechanism.

[0054] It should be noted that the test task operation is completed by touching the screen and behavioral task data is obtained, and physiological data is collected through non-invasive equipment. The non-invasive equipment includes a camera, a scale, and a sensor. This application combines physiological data and behavioral task data to improve the accuracy and reliability of cognitive assessment and ensure the continuity and comprehensiveness of data collection.

[0055] It should be noted that the behavioral task data and the physiological data are transmitted to the cloud via cloud transmission technology, and the data are encrypted and integrity checked to ensure the integrity and confidentiality of the data.

[0056] In a specific embodiment, an infrared eye tracking system is used to obtain eye movement data by projecting infrared light into the user's eyes and detecting changes in the light reflected from the eyes, which has higher accuracy and stability.

[0057] Use EEG sensors to measure the brain's electrical activity and analyze the relationship between specific bands in EEG signals (such as alpha waves, beta waves, etc.) and cognitive states.

[0058] In a specific embodiment, in real-time monitoring and remote health management scenarios, high-speed wireless communication technologies such as Wi-Fi, Bluetooth, or 5G are used to transmit data to the cloud. 5G has higher bandwidth and lower latency, and can transmit large amounts of cognitive data more quickly and stably.

[0059] It should be noted that the integrated learning model includes random forest and XGBoost, the deep learning model includes LSTM and graph convolutional network, and the statistical learning model includes support vector machine and Gaussian process model.

[0060] In a specific embodiment, preferably, a random forest model, a bidirectional LSTM model, and a support vector regression model are used and weighted according to a ratio of 6:3:1 to form a basic model group, and then a stratified five-fold cross-validation is performed to ensure that the age and gender distribution of each fold of data remains consistent, ensuring that the correlation coefficient of the cognitive ability assessment results output by each model reaches above 0.85.

[0061] In a specific embodiment, the cognitive ability score value ranges from 0 to 100 points. For the moderate cognitive decline group with a cognitive ability score of 40 to 60 points, an assessment frequency of twice a week is adopted. If the standard deviation of the cognitive ability score value exceeds 8 points for three consecutive times, the dynamic encryption mechanism is triggered and the assessment frequency is changed to 3 times a week to ensure that the cognitive fluctuations of the elderly are captured in a timely manner.

[0062] In a specific embodiment, the random forest model is used to calculate the correlation weights between the characteristics of the elderly's physiological data and behavioral task data and their cognitive ability scores, and to match each user with the three most correlated assessment contents. For example, for an elderly person with a cognitive ability score of 65 and a brain wave correlation of 0.32, the system focuses on deploying attention persistence tests.

[0063] In a specific embodiment, the cognitive ability assessment of the elderly includes assessment items, assessment frequency and assessment difficulty; when the elderly's cognitive ability score is lower than 30 points, a simplified assessment process is activated, such as shortening the assessment time by 30% or canceling the assessment time limit; when the elderly's cognitive ability score is higher than 60 points, a high-level executive function test item is added.

[0064] It should be noted that the personalized training program includes training content, training duration, and training difficulty. In the embodiment, the 20% cognitive load redundancy design principle is adopted, that is, the training difficulty is 120% of the current cognitive ability score value. The benchmark parameters are set according to the cognitive ability score range. For example, the training duration for elderly people with a cognitive ability score of 50-70 is set to 35 minutes. Closed-loop optimization is achieved by real-time tracking of training completion and physiological data.

[0065] When the completion rate of three consecutive training tasks is less than 60% and the heart rate variability (HRV) decreases by less than 15%, the three-level downgrade mechanism is triggered, the training difficulty is reduced by 10%, the training time is shortened by 20%, and 25% of the training items are replaced; conversely, if the cognitive ability score of the elderly improves by more than 5 points, the stepped intensive training will be initiated, the weekly training difficulty will be increased by 8% and new cross-modal training tasks will be added.

[0066] In a specific embodiment, the state-action-reward mechanism obtains a state value based on the cognitive ability score and the heart rate variability (HRV) trend, adjusts the action difficulty of the training task based on the state value, and gives appropriate rewards based on the improvement rate of task completion. The state-action-reward mechanism realizes self-evolution with personalized adjustment, which improves the cognitive training efficiency of the elderly by 41%.

[0067] It should be noted that when the elderly are training, the accuracy and reaction time are displayed in real time through a visual interface and compared with the previous training results. A reward and incentive mechanism is set up to provide targeted suggestions and guidance based on the elderly's training results and cognitive status, and provide specific training methods and techniques when the elderly perform poorly in a certain training item.

[0068] It should be noted that this application evaluates the gaze point coordinates and scanning frequency in the eye movement data and the option dwell time and correction times in the scale data, performs time alignment through the dynamic time warping algorithm, and constructs an attention weight matrix to achieve feature fusion. Combined with the collective verification of multiple methods, it solves the problem of the separation of behavioral and physiological data in traditional assessments, as well as the shortcomings of the single traditional cognitive ability assessment method, and improves the reliability of cognitive assessments.

[0069] It should be noted that the support vector machine model is used for small sample physiological data and sparse physiological data collected intermittently by wearable devices. The support vector machine model shows high robustness in data correlation analysis;

[0070] For training difficulty adjustment scenarios that require real-time feedback, a naive Bayes classifier is used;

[0071] Using ensemble learning algorithms (such as XGBoost and LightGBM) to process noisy data can stabilize the model AUC value at 0.82-0.91;

[0072] For continuously monitored physiological indicators and cognitive decline trend prediction task scenarios, using time series algorithms (such as LSTM and TCN) can reduce the mean absolute error by 23%-37%;

[0073] For dynamic training scheme optimization scenarios, using reinforcement learning algorithms (such as PPO and DQN) can achieve self-evolution of personalized strategies and improve training efficiency by 41%.

[0074] Reference below Figure 2 , Figure 2 A health management and detection system for the elderly is shown, which includes an acquisition module a, a fusion module b, an analysis module c, an evaluation module d and a feedback model e.

[0075] In a specific embodiment, the acquisition module a is configured to: collect behavioral task data and physiological data of the elderly through a scale or non-invasive device, and transmit the behavioral task data and the physiological data to the cloud.

[0076] In a specific embodiment, the fusion module b is configured to: extract data features from the behavioral task data and physiological data and fuse them, wherein the data features include task completion status, reaction time, and visual behavior patterns.

[0077] In a specific embodiment, the analysis module c is configured to: weight the integrated learning model, deep learning model and statistical learning model according to certain weights and construct a cognitive state assessment model set, adopt a differentiated learning strategy to train the cognitive state assessment model set, analyze the importance of the data features through a decision tree model, quantify the correlation strength between the cognitive level of the elderly and the data features through a regression model, and use the trained cognitive state assessment model set to score the behavioral task data and physiological data to obtain a cognitive ability score.

[0078] In a specific embodiment, the evaluation module d is configured to: construct a dynamic evaluation system based on the cognitive ability score, determine the evaluation frequency through the cognitive ability score, determine the evaluation items using the correlation priority strategy of the data features, establish nonlinear mapping rules, enable a simplified evaluation process when the cognitive ability score is lower than a preset threshold, and add high-level executive function test items when the cognitive ability score is higher than the preset threshold to form a step-by-step evaluation plan.

[0079] In a specific embodiment, the feedback module e is configured to: set training benchmark parameters according to the cognitive ability score, track the behavioral task data and physiological data of the elderly in real time, formulate personalized cognitive training plans based on the dynamic evaluation system and the individual data characteristics of the elderly, compare the training performance of the elderly and provide feedback through personalized guidance suggestions.

[0080] It should be noted that the data collected in this application is comprehensive and continuous, integrating behavioral task data and physiological data. Through deep learning and other algorithms, the dynamic changes of the data are analyzed and the changing trends of cognitive abilities are identified, cognitive fluctuations are captured in a timely manner, and personalized assessments are conducted on the elderly based on the results of data analysis. The assessment results are accurate and effective. Personalized training plans are formulated based on the assessment results to achieve precise adaptation of training programs and training difficulty, which is conducive to early detection of cognitive decline in the elderly and computational intervention, and effective health management.

[0081] It should be noted that if Figure 3 As shown, in the elderly health management and detection system, the elderly complete system tasks through touch screen interaction, and the system collects behavioral task data. At the same time, the non-invasive equipment equipped with the system captures the user's physiological data, encrypts the collected data, and transmits it to the cloud and performs integrity verification;

[0082] The system pre-processes the collected data, including data cleaning, normalization, and removal of outliers and noise. It then extracts and fuses the data features of the collected data, inputs them into the cognitive status assessment model set for integrated analysis, and combines artificial intelligence algorithms to dynamically identify and assess the cognitive status of the elderly.

[0083] The training frequency is adjusted according to the cognitive ability scores of the elderly, and the training difficulty is controlled in a step-by-step manner to generate a training plan. The difficulty is adjusted in real time, and then three levels of demotion and training reinforcement are carried out according to heart rate variability (HRV) and task completion.

[0084] The training results are fed back to the elderly in real time. The system rewards the elderly based on their training performance and provides personalized guidance and suggestions, identifies incorrect training patterns, and pushes training techniques to the elderly based on these incorrect training patterns.

[0085] Reference below Figure 4 , which shows a structural diagram of a computer system suitable for implementing an electronic device of an embodiment of the present application. Figure 4 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0086] like Figure 4 As shown, the computer system includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 402 or programs loaded from a storage unit 408 into a random access memory (RAM) 403. Various programs and data required for system operation are also stored in RAM 403. CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to bus 404.

[0087] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including devices such as a liquid crystal display (LCD) and speakers; a storage section 408 including devices such as a hard disk; and a communication section 409 including a network interface card such as a LAN card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 410 as needed, so that computer programs read from the media can be installed in the storage section 408 as needed.

[0088] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for executing the method illustrated in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication portion 409 and / or installed from removable media 411. When executed by central processing unit (CPU) 401, the computer program performs the functions defined in the methods of this application. It should be noted that the computer-readable storage medium of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such a propagated data signal may take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0089] Computer program code for performing the operations of the present application can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0090] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0091] The modules described in the embodiments of the present application may be implemented by software or hardware.

[0092] As another aspect, the present application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or it may exist independently and not be assembled into the electronic device. The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the electronic device, the electronic device: collects behavioral task data and physiological data of the elderly through a scale or non-invasive device, and transmits the behavioral task data and the physiological data to the cloud; extracts data features from the behavioral task data and physiological data and fuses them, the data features including task completion status, reaction time and visual behavior pattern; weights the integrated learning model, deep learning model and statistical learning model according to certain weights and constructs a cognitive state assessment model set, adopts a differentiated learning strategy to train the cognitive state assessment model set, analyzes the importance of the data features through a decision tree model, and quantifies the correlation strength between the elderly’s cognitive level and the data features through a regression model. The behavioral task data and physiological data are scored using a set of trained cognitive state assessment models to obtain a cognitive ability score; a dynamic assessment system is constructed based on the cognitive ability score, the assessment frequency is determined by the cognitive ability score, the assessment items are determined using a correlation priority strategy of the data features, and a nonlinear mapping rule is established. When the cognitive ability score is lower than a preset threshold, a simplified assessment process is enabled, and when the cognitive ability score is higher than a preset threshold, a high-order executive function test item is added to form a step-by-step assessment plan; training benchmark parameters are set according to the cognitive ability score, the behavioral task data and physiological data of the elderly are tracked in real time, and a personalized cognitive training plan is formulated based on the dynamic assessment system and the individual data characteristics of the elderly, and the training performance of the elderly is compared and feedback is provided through personalized guidance suggestions.

[0093] Finally, it should be noted that the above description is merely a preferred embodiment of this application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention herein is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the aforementioned inventive concept. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for detecting health management of the elderly, characterized in that: include: S1: Collecting behavioral task data and physiological data of the elderly through a scale or non-invasive device, and transmitting the behavioral task data and the physiological data to the cloud; S2: extracting and fusing data features from the behavioral task data and physiological data, wherein the data features include task completion status, reaction time, and visual behavior patterns; S3: weighting the ensemble learning model, deep learning model, and statistical learning model according to certain weights to construct a cognitive state assessment model set, training the cognitive state assessment model set using a differentiated learning strategy, analyzing the importance of the data features using a decision tree model, quantifying the correlation strength between the elderly's cognitive level and the data features using a regression model, and using the trained cognitive state assessment model set to score the behavioral task data and physiological data to obtain a cognitive ability score; S4: constructing a dynamic assessment system based on the cognitive ability score, determining the assessment frequency by the cognitive ability score, determining the assessment items by adopting the correlation priority strategy of the data features, establishing a nonlinear mapping rule, activating a simplified assessment process when the cognitive ability score is below a preset threshold, and adding a high-level executive function test item when the cognitive ability score is above the preset threshold, thereby forming a step-by-step assessment plan; S5: Set training benchmark parameters according to the cognitive ability score, track the behavioral task data and physiological data of the elderly in real time, formulate personalized cognitive training plans based on the dynamic evaluation system and the individual data characteristics of the elderly, compare the training performance of the elderly and provide feedback through personalized guidance suggestions.

2. The method according to claim 1, characterized in that The behavioral task data includes graphic recognition data, memory task data, scale data, interface operation trajectory data, task completion time data and attention test data; The physiological data includes blood oxygen saturation data, electroencephalogram signal data, heart rate data and eye movement data.

3. The method according to claim 2, characterized in that Step S3 also includes processing the EEG signal data and blood oxygen saturation data using a support vector machine (SVM), processing nonlinear separability problems through kernel function transformation, and analyzing the correlation between the eye movement data and the scale data.

4. The method according to claim 1, wherein Step S3 also includes using a naive Bayes classifier to make conditional independence assumptions on the task completion time data and the interface operation trajectory data and perform rapid reasoning.

5. The method according to claim 1, wherein Step S3 also includes calculating Gain values ​​for the eye movement data and scale data, sorting the importance of data features, and screening key indicators.

6. The method according to claim 1, wherein Step S3 also includes using a time series algorithm to capture the long-range dependency of the heart rate data through a memory gating mechanism to reduce the mean absolute error.

7. The method according to claim 1, characterized in that Step S5 also includes adjusting the personalized cognitive training program through reinforcement learning and state-action-reward mechanism.

8. A health management and detection system for the elderly, characterized by: include: Acquisition module: collects behavioral task data and physiological data of the elderly through a scale or non-invasive device, and transmits the behavioral task data and the physiological data to the cloud; Fusion module: extracting data features from the behavioral task data and physiological data and fusing them, wherein the data features include task completion status, reaction time, and visual behavior patterns; Analysis module: The integrated learning model, deep learning model, and statistical learning model are weighted according to certain weights to construct a cognitive state assessment model set, the differentiated learning strategy is used to train the cognitive state assessment model set, the importance of the data features is analyzed through a decision tree model, the correlation strength between the cognitive level of the elderly and the data features is quantified through a regression model, and the behavioral task data and physiological data are scored using the trained cognitive state assessment model set to obtain a cognitive ability score; Evaluation module: constructing a dynamic evaluation system based on the cognitive ability score, determining the evaluation frequency by the cognitive ability score, determining the evaluation items by adopting the correlation priority strategy of the data features, establishing nonlinear mapping rules, activating a simplified evaluation process when the cognitive ability score is below a preset threshold, and adding high-level executive function test items when the cognitive ability score is above the preset threshold, thereby forming a step-by-step evaluation plan; Feedback module: Set training benchmark parameters according to the cognitive ability score, track the behavioral task data and physiological data of the elderly in real time, formulate personalized cognitive training plans based on the dynamic evaluation system and the individual data characteristics of the elderly, compare the training performance of the elderly and provide feedback through personalized guidance suggestions.

9. A computer program product having one or more computer programs thereon, characterized in that: When the computer program is executed by a computer processor, the method according to any one of claims 1 to 7 is implemented.

Images