Medical monitoring type old-age care robot

Abstract

The invention relates to the technical field of old-age care robots, in particular to a medical monitoring type old-age care robot which comprises a physiological monitoring unit, an air particle regulation and health feedback unit, an emotion and health fusion unit and a nursing auxiliary unit. The physiological monitoring unit is used for collecting physiological data of the old people in real time; the air particle regulation and control unit is used for detecting pollutants and biological particles in the air, analyzing the air quality in real time and automatically regulating air purification equipment or an external ventilation device in the robot body according to the particle concentration in the air and physiological data of the old people; the emotion and health fusion unit analyzes the mental health of the elderly; the nursing auxiliary unit comprises a mechanical arm and a voice control system and assists the old in daily activities. According to the invention, psychological support and emotional care are provided for the elderly in time, the life quality of the elderly is improved, and psychological health problems are effectively prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of elderly care robots, and in particular to a medical monitoring elderly care robot. Background Art

[0002] How to provide better medical care and life security for the elderly has become an important issue of concern to the society, especially in the management of common chronic diseases, emotional support and daily life care for the elderly. The demand is growing. The advancement of modern technology has led to the gradual application of robots in the field of elderly care. Through sensors, data analysis and automatic control technology, real-time monitoring of the health status of the elderly, environmental regulation and personalized care support can be achieved, which provides broad application prospects for the intelligent development of elderly care services.

[0003] Currently, the elderly care robots on the market usually have only limited functions, such as simple health monitoring or assisted care, and are unable to achieve comprehensive management of the complex health needs of the elderly. Especially in terms of health monitoring, existing technologies make it difficult to simultaneously integrate physiological, environmental and emotional data for accurate health assessments; at the same time, there is a lack of effective monitoring of indoor air quality, and the air environment cannot be adjusted in time according to the health status of the elderly. In addition, emotional care is relatively limited in the application of elderly care robots, the accuracy of emotional assessment is insufficient, and intervention measures are not flexible enough. It is impossible to provide personalized intervention plans in time according to the emotional fluctuations of the elderly. These shortcomings make elderly care robots have certain limitations in improving the quality of life and care effects of the elderly.

[0004] The present invention aims to address the deficiencies in the prior art and proposes a medical monitoring elderly care robot that can automatically adjust the strength and frequency of nursing actions to ensure that the elderly receive accurate and comfortable care in their daily lives, thereby improving their quality of life and reducing the burden of nursing care. Summary of the invention

[0005] The invention provides a medical monitoring type elderly care robot.

[0006] A medical monitoring elderly care robot, comprising a physiological monitoring unit, an air particle control and health feedback unit, an emotion and health fusion unit and a nursing assistance unit, wherein;

[0007] The physiological monitoring unit collects physiological data of the elderly in real time, including heart rate, blood pressure, blood oxygen, body temperature and respiratory rate;

[0008] The air particle control unit detects pollutants and biological particles in the air, analyzes the air quality in real time, and automatically adjusts the air purification equipment in the robot body or the external ventilation device according to the particle concentration in the air and the physiological data of the elderly, specifically including:

[0009] Air quality detection: Real-time detection of pollutants and biological particles in the air, including bacteria, viruses, allergens, PM2.5 and volatile organic compounds (VOCs), and generation of air particle concentration data;

[0010] Health impact assessment: Based on the generated air particle concentration data and combined with the physiological data of the elderly, the health risk assessment model is used to conduct correlation analysis to assess the potential impact of air pollutants on the health of the elderly;

[0011] Air purification and environmental control: Automatically adjust the air purification equipment inside the robot or wirelessly control external ventilation equipment based on the results of the health impact assessment;

[0012] The emotion and health fusion unit analyzes the mental health of the elderly through the integration of facial expression recognition, voice analysis and physiological data, and automatically generates an emotion intervention plan based on the analysis results, including playing soothing music, adjusting lighting or reminding caregivers to pay attention;

[0013] The nursing assistance unit includes a robotic arm and a voice control system to assist the elderly in daily activities, including eating, dressing, and sports rehabilitation training, and automatically adjusts the strength and frequency of the assistance movements based on feedback data from the physiological monitoring unit and the emotion and health fusion unit.

[0014] Optionally, the physiological monitoring unit includes:

[0015] Heart rate monitoring: A heart rate sensor based on photoplethysmography (PPG) is worn on the wrist or fingertips of the elderly to collect heart rate data in real time;

[0016] Blood pressure monitoring: Using a non-invasive inflatable cuff and pressure sensor, tied to the upper arm or wrist of the elderly, the oscillation method is used to monitor blood pressure changes in real time;

[0017] Blood oxygen monitoring: Optical blood oxygen sensors mounted on finger clips or earlobe clips use infrared and visible light transmission technology to measure the blood oxygen saturation of the elderly in real time;

[0018] Temperature monitoring: Use non-contact infrared temperature sensors or patch temperature sensors, placed on the forehead, ear canal or skin surface of the elderly to obtain temperature data in real time;

[0019] Respiratory rate monitoring: Real-time monitoring of the elderly’s respiratory rate and breathing pattern through chest strap respiratory sensors, piezoelectric sensors or radar-type non-contact sensors.

[0020] Optionally, the air quality detection includes:

[0021] Particle detection: Detect particles in the air, including PM2.5 and PM10, through particle sensors, using laser scattering or optical detection technology to monitor particle concentration in real time;

[0022] Volatile organic compound detection: Detect volatile organic compounds (VOCs) in the air through electrochemical or semiconductor gas sensors and generate gas concentration data in real time;

[0023] Biological particle detection: Based on the optical particle counting method, it detects biological particles in the air, including bacteria, viruses and allergens, and analyzes their quantity and types in real time;

[0024] Multimodal data fusion: Comprehensively analyze the collected pollutants and biological particles to generate particle concentration data in the air, expressed as:

[0025] C air =w PM ·P PM +w VOC ·V VOC +w bio ·B bio ;

[0026] Among them, C air is the fused air particle concentration data, P PM is PM2.5 or PM10 particle data, V VOC is the volatile organic compound data, B bio is the biological particle data (such as bacteria, viruses, etc.), w PM 、w VOC 、w bio are the corresponding weights respectively.

[0027] Optionally, the health risk assessment model adopts a Gaussian mixture model (GMM), and the Gaussian mixture model (GMM) includes:

[0028] Data standardization: standardize air particle concentration data and physiological data;

[0029] The basic structure of the Gaussian mixture model: The Gaussian mixture model is used to model the standardized air particle concentration data and physiological data, which can be expressed as:

[0030]

[0031] Where X is the multidimensional input data, including standardized air particle concentration data and physiological data, is the kth Gaussian distribution with mean μ k , the covariance matrix is ​​∑ k , π kis the weight of the kth mixture component, θ contains all model parameters, and K is the total number of Gaussian components (different potential health states, including healthy, mild risk, moderate risk, and severe risk);

[0032] Introducing personalized weights for health status: Introducing personalized weights for health status to dynamically adjust the weights of different health risk states based on the different sensitivities of the elderly to air pollution (e.g., patients with chronic diseases are more susceptible to air pollution);

[0033] Dynamically update parameters: Capture the impact of air pollutants on the health of the elderly, introduce the time dimension, dynamically update the parameters of the model, and smooth the impact of historical air quality on health by using time-weighted average;

[0034] Health risk probability output: Based on the dynamically updated Gaussian mixture model, the probability of each health state is output, indicating the potential risk of air pollution to the health of the elderly.

[0035] Optionally, the air purification and environment control include:

[0036] Air purification control: By receiving the results of the health impact assessment, the air purification equipment in the robot body is automatically adjusted, including adjusting the wind speed, filter working mode and purification intensity;

[0037] External ventilation control: Connect with external intelligent ventilation equipment through wireless communication, remotely control the opening, closing and ventilation intensity adjustment of external intelligent ventilation equipment based on the results of health impact assessment, and realize dynamic optimization of indoor air circulation and quality.

[0038] Optionally, the emotion and health integration unit includes:

[0039] Facial expression recognition: The facial expressions of the elderly are captured by cameras, and convolutional neural networks (CNN) are used to analyze facial features in real time to identify the emotional states of the elderly, including happiness, sadness, anger, and anxiety;

[0040] Voice emotion analysis: The microphone collects the voice signals of the elderly and evaluates the emotional information in the voice, including intonation, speaking speed, and volume, to determine the emotional state of the elderly.

[0041] Data fusion and emotional intervention: The emotional state of facial expression recognition and voice emotion analysis are integrated with physiological data to comprehensively analyze the mental health status of the elderly. Based on the analysis results, emotional intervention plans are automatically generated, including playing soothing music, adjusting ambient lighting, or reminding caregivers to pay attention.

[0042] Optionally, the facial expression recognition includes:

[0043] Camera collection: Use the camera to capture the facial images of the elderly in real time;

[0044] Facial feature extraction: Real-time analysis of facial features based on convolutional neural networks (CNN) to extract facial key points, including feature vectors of eyes, mouth corners, and eyebrows.

[0045] Emotion classification: The extracted facial feature vectors are input into the convolutional neural network for classification to identify the emotional states of the elderly, including happiness, sadness, anger, and anxiety.

[0046] Optionally, the speech emotion analysis includes:

[0047] Voice collection: The voice signals of the elderly are collected in real time through microphones;

[0048] Speech feature extraction: Use speech signal processing algorithms to extract emotional features in speech, including intonation (fundamental frequency F0), speaking speed, and volume, which are used to determine the emotional information in speech;

[0049] Emotion classification: The extracted emotional features are input into the support vector machine (SVM) model to output the emotional state of the elderly, including the emotional categories of happiness, sadness, anger, and anxiety.

[0050] Optionally, the data fusion and emotion intervention include:

[0051] Multimodal data fusion: The emotional state of facial expression recognition, the emotional state of voice emotion analysis and physiological data are integrated and processed, and the current mental health index H of the elderly is comprehensively generated using the weighted average method;

[0052] Mental health status determination: Based on the fused mental health index H, the mental health status of the elderly is determined using the predefined threshold interval and divided into different emotional risk levels, including low risk, medium risk and high risk;

[0053] Emotional intervention: Automatically generate emotional intervention plans based on the judgment results, including playing soothing music, adjusting ambient lighting, or reminding caregivers to pay attention.

[0054] Optionally, the nursing assistance unit includes:

[0055] Robotic arm assistance: Through data interaction with the physiological monitoring unit and the emotion and health fusion unit, it receives real-time feedback on the elderly's physiological data and mental health, and assists the elderly in daily activities, including eating assistance, dressing assistance, and sports rehabilitation training;

[0056] Voice control system: Controls the robotic arm to perform auxiliary tasks through voice commands, and adjusts the movement intensity and operation frequency of the robotic arm in real time based on feedback data from the physiological monitoring unit and the emotion and health fusion unit.

[0057] Beneficial effects of the present invention:

[0058] The present invention collects the heart rate, blood pressure, blood oxygen, body temperature and respiratory rate of the elderly in real time through a physiological monitoring unit to ensure a comprehensive grasp of the elderly's physical condition. At the same time, the air particle control unit can accurately monitor pollutants and biological particles in the air, and automatically adjust the air purification equipment or external ventilation device according to the health impact assessment model to ensure that the indoor air quality meets the health standard, avoid the occurrence of respiratory diseases, and provide a safe and healthy living environment for the elderly.

[0059] The present invention, through the emotion and health fusion unit, integrates facial expressions, voice emotion analysis and physiological data to comprehensively evaluate the mental health status of the elderly. Based on the threshold interval set by historical data, the system can dynamically determine the emotional risk level of the elderly and automatically generate emotional intervention plans, such as playing soothing music, adjusting lighting or reminding nursing staff to intervene, so as to provide psychological support and emotional care for the elderly in a timely manner, improve their quality of life, and effectively prevent mental health problems.

[0060] The present invention assists the elderly in completing daily activities, including eating, dressing, and exercise rehabilitation training, through a robotic arm and a voice control system. It combines physiological monitoring and emotional feedback to intelligently adjust the movement strength and frequency of the robotic arm to achieve personalized nursing support. This intelligent and automated nursing solution not only improves the comfort and safety of the elderly, but also reduces the workload of nursing staff, providing more convenient and efficient life care management for the elderly. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 A schematic diagram of a robot functional unit according to an embodiment of the present invention;

[0063] Figure 2 Schematic diagram of an air particle control unit according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0065] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0066] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0067] like Figure 1-Figure 2 As shown, a medical monitoring elderly care robot includes a physiological monitoring unit, an air particle control and health feedback unit, an emotion and health fusion unit and a nursing assistance unit, wherein;

[0068] The physiological monitoring unit collects the elderly's physiological data in real time, including heart rate, blood pressure, blood oxygen, body temperature and respiratory rate;

[0069] The air particle control unit detects pollutants and biological particles in the air, analyzes the air quality in real time, and automatically adjusts the air purification equipment in the robot body or the external ventilation device according to the particle concentration in the air and the physiological data of the elderly to ensure healthy indoor air and avoid damage to the respiratory system or infection of the elderly. Specifically, it includes:

[0070] Air quality detection: Real-time detection of pollutants and biological particles in the air, including bacteria, viruses, allergens, PM2.5 and volatile organic compounds (VOCs), and generation of air particle concentration data;

[0071] Health impact assessment: Based on the generated air particle concentration data and combined with the physiological data of the elderly, the health risk assessment model is used to conduct correlation analysis to assess the potential impact of air pollutants on the health of the elderly;

[0072] Air purification and environmental control: Based on the results of the health impact assessment, the robot can automatically adjust the air purification equipment inside the robot or wirelessly control the external ventilation equipment to ensure that the air quality meets safety standards and optimize the living environment for the elderly.

[0073] The emotion and health fusion unit analyzes the mental health of the elderly through the integration of facial expression recognition, voice analysis and physiological data, and automatically generates emotional intervention plans based on the analysis results, including playing soothing music, adjusting lighting or reminding caregivers to pay attention;

[0074] The nursing assistance unit includes a robotic arm and a voice control system to assist the elderly in daily activities, including eating, dressing, and exercise rehabilitation training. It also automatically adjusts the strength and frequency of the assistance movements based on feedback data from the physiological monitoring unit and the emotional and health fusion unit to ensure personalized assistance support.

[0075] Through the above content, comprehensive monitoring of the health of the elderly, automated management of environmental control and personalized care are realized. It can not only dynamically adjust the air quality and daily care plans according to the real-time health status of the elderly, but also provide psychological support through intelligent emotional analysis, ensuring that the elderly live in a safe, healthy and comfortable environment.

[0076] The physiological monitoring unit includes:

[0077] Heart rate monitoring: A heart rate sensor based on photoplethysmography (PPG) is worn on the wrist or fingertips of the elderly to collect heart rate data in real time;

[0078] Blood pressure monitoring: Using a non-invasive inflatable cuff and pressure sensor, tied to the upper arm or wrist of the elderly, the oscillation method is used to monitor blood pressure changes in real time;

[0079] Blood oxygen monitoring: Optical blood oxygen sensors mounted on finger clips or earlobe clips use infrared and visible light transmission technology to measure the blood oxygen saturation of the elderly in real time;

[0080] Temperature monitoring: Use non-contact infrared temperature sensors or patch temperature sensors, placed on the forehead, ear canal or skin surface of the elderly to obtain temperature data in real time;

[0081] Respiratory rate monitoring: Real-time monitoring of the elderly’s respiratory rate and breathing pattern through chest strap respiratory sensors, piezoelectric sensors or radar-type non-contact sensors;

[0082] Through the above content, we can ensure continuous tracking of the health status of the elderly and abnormal warnings, improve the accuracy and comfort of monitoring, effectively avoid the inconvenience caused by traditional monitoring methods, provide more personalized health management and timely intervention, and ensure the safety of the elderly.

[0083] Air quality testing includes:

[0084] Particle detection: Detect particles in the air, including PM2.5 and PM10, through particle sensors, using laser scattering or optical detection technology to monitor particle concentration in real time;

[0085] Volatile organic compound detection: Detect volatile organic compounds (VOCs) in the air through electrochemical or semiconductor gas sensors and generate gas concentration data in real time;

[0086] Biological particle detection: Based on the optical particle counting method, it detects biological particles in the air, including bacteria, viruses and allergens, and analyzes their quantity and types in real time;

[0087] Multimodal data fusion: Comprehensively analyze the collected pollutants and biological particles to generate particle concentration data in the air, expressed as:

[0088] C air =w PM ·P PM +w VOC ·V VOC +w bio ·B bio ;

[0089] Among them, C air is the fused air particle concentration data, P PM is PM2.5 or PM10 particle data, V VOC is the volatile organic compound data, B bio is the biological particle data (such as bacteria, viruses, etc.), w PM 、w VOC 、w bio are the corresponding weights, w PM +w VOC +w bio =1;

[0090] Weight w PM 、w VOC 、w bio The setting basis and value are as follows:

[0091] Weight w PM Higher, because PM2.5 and other particulate matter have a greater impact on the respiratory system, the value is 0.5;

[0092] Weight w VOC Lower, because it detects volatile organic compounds, but long-term exposure may affect the immune and nervous systems, so the value is 0.2;

[0093] Weight wbio Higher, especially when detecting biological particles such as viruses and bacteria that have an important impact on respiratory health, the value is 0.3;

[0094] Through the above content, we can comprehensively evaluate the potential threats of air quality to the respiratory system, immune system and long-term health of the elderly, thereby achieving accurate environmental monitoring and personalized health protection, effectively improving the reliability and adaptability of air detection, and ensuring that the elderly can live in a safe air environment.

[0095] The health risk assessment model uses the Gaussian mixture model (GMM), which includes:

[0096] Data standardization: The air particle concentration data and physiological data are standardized to ensure that the input data of different dimensions have the same scale, expressed as:

[0097]

[0098] Where X is the original value of air particle concentration data or physiological data, μ X is the mean of the data, σ X is the standard deviation of the data, and X′ is the standardized data;

[0099] The basic structure of the Gaussian mixture model: The Gaussian mixture model is used to model the standardized air particle concentration data and physiological data, which can be expressed as:

[0100]

[0101] Where X is the multidimensional input data, including standardized air particle concentration data and physiological data, is the kth Gaussian distribution with mean μ k , the covariance matrix is ​​∑ k , π k is the weight of the kth mixture component and satisfies θ contains all model parameters, K is the total number of Gaussian components (different potential health states, including healthy, mild risk, moderate risk, and severe risk);

[0102] Introducing personalized weights for health status: Introducing personalized weights for health status, dynamically adjusting the weights of different health risk states according to the different sensitivities of the elderly to air pollution (e.g., patients with chronic diseases are more susceptible to air pollution), and improving the accuracy of the assessment, expressed as:

[0103] π k ′=π k f(H);

[0104] Among them, πk ′ is the adjusted weight of the kth mixed component, and f(H) is a function used to adjust the weight based on the physiological condition H of the elderly (such as chronic disease history, respiratory diseases, etc.);

[0105] The function f(H) is calculated using the weighted average of different health factors and is expressed as:

[0106] f(H)=1+w1·I respiratory +w2·I chronic +w3·I immune ;

[0107] Among them, w1, w2, and w3 are weight coefficients of different health factors, indicating the influence of these health factors on risk sensitivity, which can be determined through data training. respiratory is a binary indicator variable indicating whether the elderly have respiratory diseases (such as asthma, chronic obstructive pulmonary disease, etc.). If so, I respiratory =1, otherwise 0,I chronic It is a binary indicator variable, indicating whether the elderly have a history of chronic diseases (such as diabetes, hypertension, etc.). chronic =1, otherwise 0, I immune It is a binary indicator that indicates the immune system status of the elderly (such as whether they are immunocompromised). If the immune system is immunocompromised, immune =1, otherwise 0;

[0108] Dynamically update parameters: Capture the impact of air pollutants on the health of the elderly, introduce the time dimension, dynamically update the parameters of the model, and smooth the impact of historical air quality on health by using time-weighted average, expressed as:

[0109]

[0110] in, is the updated mean at time t+1, is the updated covariance matrix, α is the time weighting coefficient, which controls the balance of influence between historical data and current data, and X t is the input data (air particle concentration and physiological data) at time t, is the mean of the kth Gaussian distribution at time t, is the covariance matrix of the kth Gaussian distribution at time t, It is the deviation product between the input data and the mean, which is used to update the covariance matrix;

[0111] Health risk probability output: Based on the dynamically updated Gaussian mixture model, the probability of each health state is output to indicate the potential risk of air pollution to the health of the elderly, expressed as:

[0112]

[0113] Among them, P(H k |X) indicates that given the air particle concentration data and physiological data X, the elderly are in the kth health state H k The probability of (healthy, mild risk, moderate risk, severe risk), π k ′ is the weight of the kth Gaussian component after personalized adjustment, is the probability density function of the kth Gaussian distribution, The denominator is the weighted sum of all health states, which is used to standardize the probability distribution to ensure that the sum of the probabilities of each health state is 1;

[0114] Through the above content, the potential risks of air pollution to the health of the elderly can be assessed more accurately. By introducing personalized weights for health status, the model dynamically adjusts the weights according to the different physiological conditions of the elderly (such as respiratory diseases or low immunity), thereby providing personalized health risk assessments. At the same time, the model can capture the long-term cumulative effects of air pollution through dynamic parameter updates in the time dimension, thereby improving the sensitivity to health risks and prediction accuracy, enhancing the level of personalization of health management, and providing more timely and effective health warnings for the elderly.

[0115] Air purification and environmental control include:

[0116] Air purification control: By receiving the results of the health impact assessment, the air purification equipment in the robot body is automatically adjusted, including adjusting the wind speed, filter working mode and purification intensity to ensure that the air quality meets the set health standards;

[0117] External ventilation control: Connect with external intelligent ventilation equipment through wireless communication, remotely control the opening and closing of external intelligent ventilation equipment and adjust the ventilation intensity based on the results of health impact assessment, and realize dynamic optimization of indoor air circulation and quality;

[0118] Through the above content, personalized air management solutions can be provided to ensure that the elderly are always in a safe and healthy air environment under different health conditions. This automated and personalized control method not only improves the accuracy of environmental management, but also reduces the need for manual intervention, greatly improving the intelligence and convenience of elderly care.

[0119] The Emotional and Health Integration Unit includes:

[0120] Facial expression recognition: The facial expressions of the elderly are captured by cameras, and convolutional neural networks (CNN) are used to analyze facial features in real time to identify the emotional states of the elderly, including happiness, sadness, anger, and anxiety;

[0121] Voice emotion analysis: The microphone collects the voice signals of the elderly and evaluates the emotional information in the voice, including intonation, speaking speed, and volume, to determine the emotional state of the elderly.

[0122] Data fusion and emotional intervention: The emotional state of facial expression recognition and voice emotion analysis is integrated with physiological data to comprehensively analyze the mental health of the elderly. Based on the analysis results, an emotional intervention plan is automatically generated, including playing soothing music, adjusting ambient lighting, or reminding caregivers to pay attention.

[0123] Through the above content, the emotional fluctuations of the elderly can be perceived in real time, and the accuracy of the assessment can be improved. At the same time, the automatic generation of personalized emotional intervention plans can effectively improve the emotions of the elderly and improve their quality of life. Through intelligent and personalized emotional monitoring and intervention, not only the efficiency of elderly care is improved, but also mental health problems can be prevented in time, providing more comprehensive care.

[0124] Facial expression recognition includes:

[0125] Camera collection: Use the camera to capture the facial images of the elderly in real time;

[0126] Facial feature extraction: Based on the convolutional neural network (CNN), real-time analysis of facial features is performed to extract facial key points, including feature vectors of eyes, mouth corners, and eyebrows, expressed as:

[0127]

[0128] Among them, f l (x, y) is the output feature map value of the lth convolutional layer at position (x, y), I l-1 (x+i, y+j is the input image pixel value at position (x+i, y+j) of the l-1th layer, K l (i, j) is the weight matrix of the convolution kernel, size is m×n, b l is the bias term of the convolution layer, m is the size of the convolution kernel in the vertical direction, and n is the size of the convolution kernel in the horizontal direction;

[0129] a l (x,y)=max(0,f l (x,y));

[0130] Among them, a l (x,y) is the activation value of the lth convolutional layer at position (x,y);

[0131]

[0132] Among them, P l(x,y) is the feature value output by the pooling layer, a l (x·p+i,y·p+j) is the activation value in the pooling window, the activation value in the range of p×p, the convolutional layer output value provided by ReLU, p is the size of the pooling window, which is 2×2;

[0133] Emotion classification: The extracted facial feature vectors are input into the convolutional neural network for classification to identify the emotional states of the elderly, including happiness, sadness, anger, and anxiety, expressed as:

[0134]

[0135] Among them, z k is the activation value of the k-th emotional state, W ki is the connection weight, which represents the weight between the i-th feature and the k-th class, v i is the flattened feature vector, which comes from the output of the previous convolution and pooling process, b k is the bias term;

[0136]

[0137] Where P(y=k|x) is the probability that the input x is classified as the kth emotion, z k is the activation value of the fully connected layer for the kth emotional state, where K is the total number of emotional categories;

[0138] y * = argmax k {P(y=k|x)};

[0139] Among them, y * For the final determined emotional state category, the emotional category with the highest probability is selected as the recognition result;

[0140] Through the above content, the convolution layer can be used to effectively extract key facial features, such as eyes, corners of the mouth, and eyebrows. The fully connected layer and Softmax function can be used to accurately identify the emotional state of the elderly, including happiness, sadness, anger, and anxiety. It has efficient, real-time, and non-invasive emotion recognition capabilities, and can provide high-precision emotion monitoring without interfering with the elderly, which helps to adjust care plans in a timely manner and improve the quality of life of the elderly.

[0141] Speech sentiment analysis includes:

[0142] Voice collection: The microphone collects the elderly's voice signals in real time to ensure the clarity and integrity of the voice data;

[0143] Speech feature extraction: The speech signal processing algorithm is used to extract the emotional features in the speech, including intonation (fundamental frequency F0), speaking speed and volume, which are used to judge the emotional information in the speech, expressed as:

[0144]

[0145] Where F0(t) is the fundamental frequency (intonation) at time t, T0(t) is the period at time t;

[0146]

[0147] Among them, S is the speaking speed, which means the number of speech words per unit time, and N words is the number of words in the speech segment, T speech is the duration of speech;

[0148]

[0149] Where E is the energy (volume) of the speech signal, x[n] is the sampled speech signal value, and N is the number of sampling points of the speech signal;

[0150] Emotion classification: The extracted emotional features are input into the support vector machine (SVM) model to output the emotional state of the elderly, including the emotional categories of happiness, sadness, anger, and anxiety, expressed as:

[0151]

[0152] Among them, f(x) is the classification function, x i is a training sample, x is the input speech feature vector, α i and i is the Lagrange multiplier and label, K(x i ,x) is the kernel function used to calculate the similarity between features, b is the bias term of the classifier, and M is the number of training samples;

[0153] Through the above content, emotional changes can be monitored in real time without visual contact with the elderly. By analyzing multi-dimensional voice features, more delicate and accurate emotional assessments can be provided, providing an intelligent and real-time solution for emotional care and mental health monitoring of the elderly, which helps to detect emotional fluctuations in a timely manner and make corresponding interventions.

[0154] Data fusion and emotional intervention include:

[0155] Multimodal data fusion: The emotional state of facial expression recognition, the emotional state of voice emotion analysis, and physiological data are fused and processed, and the weighted average method is used to comprehensively generate the current mental health index H of the elderly, which is expressed as:

[0156] H=w4·E facial +w5·E vocal +w6·P physio ;

[0157] Among them, H is the mental health index, which is used to characterize the mental health status of the elderly, and E facial Emotional state for facial expression recognition, E vocal is the emotional state of speech sentiment analysis, P physio is the comprehensive evaluation result of physiological data, w4, w5, and w6 are weighting coefficients;

[0158] Comprehensive evaluation results of physiological data P physio It is expressed as:

[0159]

[0160] Among them, P physio is the comprehensive evaluation result of physiological data, S i is the standardized score of the ith physiological index (such as heart rate, blood pressure, blood oxygen, etc.), w i,physio is the weight of the ith physiological index, indicating the impact of the physiological index on health assessment, and p is the total number of physiological indexes;

[0161] The weight w of the i-th physiological index i,physio The setting basis depends on the influence of various physiological indicators on the mental health and emotional fluctuations of the elderly. Usually, heart rate, blood pressure, respiratory rate and indicators closely related to emotions and stress will be given higher weights, while body temperature and blood oxygen index weights may be lower. The weight of heart rate is 0.4, the weight of blood pressure is 0.3, the weight of respiratory rate is 0.1, the weight of body temperature is 0.05, and the weight of blood oxygen index is 0.15.

[0162] The setting basis and values ​​of weighted coefficients w4, w5, and w6 specifically include:

[0163] The weighting coefficient w4 is set based on the importance of facial expressions in reflecting the emotional state of the elderly. If the elderly have obvious facial expressions, facial expression recognition may have a higher weight, and the value is 0.4;

[0164] The weighting coefficient w5 is set based on the fact that it can capture the changes in the tone, speed and volume of the elderly and reflect more delicate emotions. For some elderly people, their voice may reflect emotional fluctuations better than facial expressions. The value is 0.3;

[0165] The weighting coefficient w6 is set based on its direct impact on mental health, especially heart rate and blood pressure, which can reflect mood swings. The weight setting depends on the importance of physiological health status. When the elderly have chronic diseases or cardiovascular problems, the weight of physiological data will increase, and the value is 0.3;

[0166] Mental health status determination: Based on the fused mental health index H, the mental health status of the elderly is determined using the predefined threshold interval and divided into different emotional risk levels, including low risk, medium risk and high risk;

[0167] Emotional intervention: Automatically generate emotional intervention plans based on the judgment results, including playing soothing music, adjusting ambient lighting, or reminding caregivers to pay attention;

[0168] The predefined threshold intervals are based on historical data and include:

[0169] Data collection: Collect historical health data of the elderly, including facial expression recognition, voice emotion analysis and physiological data, and generate a corresponding mental health index H for each data point;

[0170] Data statistical analysis: Statistic the collected health indexes, calculate the distribution of the mental health index H, and divide the risk level by percentile;

[0171] Percentile threshold setting: Based on the percentile of historical data, health indexes below the 25th percentile are considered low risk, those between the 25th and 75th percentiles are considered medium risk, and those above the 75th percentile are considered high risk, expressed as:

[0172]

[0173] Among them, H is the mental health index, which is generated by multimodal data fusion, T1 is the 25th percentile in the historical data, corresponding to the upper limit of low risk, and T2 is the 75th percentile in the historical data, corresponding to the lower limit of high risk;

[0174] Through the above content, the mental health status of the elderly can be accurately assessed and personalized intervention plans can be automatically generated. The accuracy of the assessment can be improved by using multimodal data fusion, avoiding the deviation that may be caused by a single data source. At the same time, the risk threshold setting based on historical data can dynamically adapt to the emotional fluctuations of individual elderly people. It can not only realize real-time emotional monitoring, but also provide personalized emotional intervention plans according to different risk levels, thereby improving the mental health and quality of life of the elderly.

[0175] The Nursing Assistance Unit includes:

[0176] Robotic arm assistance: Through data interaction with the physiological monitoring unit and the emotion and health fusion unit, it receives real-time feedback on the elderly's physiological data and mental health, and assists the elderly in daily activities, including eating assistance, dressing assistance, and sports rehabilitation training;

[0177] Feeding assistance uses a robotic arm to deliver food based on the elderly’s hand movements and feeding needs, adjusting the delivery speed and force to avoid too fast or too slow operations;

[0178] Dressing assistance: According to the hand flexibility and body posture of the elderly, the robotic arm adjusts the strength of the dressing assistance to ensure a smooth and comfortable dressing process;

[0179] Sports rehabilitation training monitors the limb status of the elderly, and the robotic arm automatically controls the operating force and frequency of the sports rehabilitation equipment to ensure the safety and effectiveness of sports training;

[0180] Voice control system: The elderly control the robotic arm to perform auxiliary tasks through voice commands, and adjust the action intensity and operation frequency of the robotic arm in real time based on the feedback data from the physiological monitoring unit and the emotion and health fusion unit, which is expressed as:

[0181] F adjust =w7·P physio +w8·E emotion ;

[0182] Among them, F adjust is the adjustment strength and frequency of the robot arm’s movements, P physio is the feedback value of the physiological monitoring unit (such as heart rate, blood pressure, etc.), E emotion is the feedback value of the emotion and health integration unit, w7 and w8 are weighting coefficients;

[0183] The setting basis and value range of weighting coefficients w7 and w8 specifically include:

[0184] The weighting coefficient w7 is set based on the fact that physiological feedback (such as heart rate, blood pressure, etc.) directly reflects the physical condition of the elderly. Especially when doing exercise rehabilitation or other physical activities, changes in heart rate and blood pressure are very important for the adjustment of auxiliary movements. If the physiological monitoring data shows that the elderly are in a high cardiovascular load state, the system will give priority to adjusting the strength and frequency of the robotic arm to reduce the physical pressure of the elderly. Therefore, the weight of physiological feedback is relatively large, and the value is 0.7;

[0185] The weighting coefficient w8 is set based on the fact that emotional feedback reflects the psychological state of the elderly. If the elderly show emotional stress, anxiety or discomfort, the system needs to adjust the auxiliary strength and movement frequency of the robotic arm according to the emotional state. The weight of emotional feedback will depend on the degree of influence of the elderly's emotional fluctuations on task execution, and the value is 0.3;

[0186] Through the above content, the strength and frequency of auxiliary actions can be intelligently adjusted to provide personalized nursing support for the elderly. It can perceive the physical condition and emotional changes of the elderly in real time, and automatically adjust the execution method of auxiliary tasks, such as eating, dressing and sports rehabilitation training, to ensure that each operation is safe and comfortable. The nursing assistance unit realizes dynamic adjustment according to individual needs, improves the comfort and quality of life of the elderly in daily life, and reduces the workload of caregivers.

[0187] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0188] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A medical monitoring elderly care robot, characterized in that: It includes a physiological monitoring unit, an air particle control unit, an emotion and health integration unit, and a nursing assistance unit, among which; The physiological monitoring unit collects physiological data of the elderly in real time, including heart rate, blood pressure, blood oxygen, body temperature and respiratory rate; The air particle control unit detects pollutants and biological particles in the air, analyzes the air quality in real time, and automatically adjusts the air purification equipment in the robot body or the external ventilation device according to the particle concentration in the air and the physiological data of the elderly, specifically including: Air quality detection: Real-time detection of pollutants and biological particles in the air, including bacteria, viruses, allergens, PM2.5 and volatile organic compounds, and generation of air particle concentration data; Health impact assessment: Based on the generated air particle concentration data and combined with the physiological data of the elderly, the health risk assessment model is used to conduct correlation analysis to assess the potential impact of air pollutants on the health of the elderly; Air purification and environmental control: Automatically adjust the air purification equipment inside the robot or wirelessly control external ventilation equipment based on the results of the health impact assessment; The emotion and health fusion unit analyzes the mental health of the elderly through the integration of facial expression recognition, voice analysis and physiological data, and automatically generates an emotion intervention plan based on the analysis results, including playing soothing music, adjusting lighting or reminding caregivers to pay attention; The nursing assistance unit includes a robotic arm and a voice control system to assist the elderly in daily activities, including eating, dressing, and sports rehabilitation training, and automatically adjusts the strength and frequency of the assistance movements based on feedback data from the physiological monitoring unit and the emotion and health fusion unit.

2. A medical monitoring elderly care robot according to claim 1, characterized in that: The physiological monitoring unit comprises: Heart rate monitoring: A heart rate sensor using photoplethysmography is worn on the wrist or fingertips of the elderly to collect heart rate data in real time; Blood pressure monitoring: Using a non-invasive inflatable cuff and pressure sensor, tied to the upper arm or wrist of the elderly, the oscillation method is used to monitor blood pressure changes in real time; Blood oxygen monitoring: Optical blood oxygen sensors mounted on finger clips or earlobe clips use infrared and visible light transmission technology to measure the blood oxygen saturation of the elderly in real time; Temperature monitoring: Use non-contact infrared temperature sensors or patch temperature sensors, placed on the forehead, ear canal or skin surface of the elderly to obtain temperature data in real time; Respiratory rate monitoring: Real-time monitoring of the elderly’s respiratory rate and breathing pattern through chest strap respiratory sensors, piezoelectric sensors or radar-type non-contact sensors.

3. A medical monitoring elderly care robot according to claim 1, characterized in that: The air quality detection includes: Particle detection: Detect particles in the air, including PM2.5 and PM10, through particle sensors, using laser scattering or optical detection technology to monitor particle concentration in real time; Volatile organic compound detection: Detect volatile organic compounds in the air through electrochemical or semiconductor gas sensors and generate gas concentration data in real time; Biological particle detection: Based on the optical particle counting method, it detects biological particles in the air, including bacteria, viruses and allergens, and analyzes their quantity and types in real time; Multimodal data fusion: Comprehensively analyze the collected pollutants and biological particles to generate particle concentration data in the air, expressed as: C air =w PM ·P PM +w VOC ·V VOC +w bio ·B bio ; Among them, C air is the fused air particle concentration data, P PM is PM2.5 or PM10 particle data, V VOC is the volatile organic compound data, B bio is the biological particle data, w PM 、w VOC 、w bio are the corresponding weights respectively.

4. A medical monitoring elderly care robot according to claim 3, characterized in that: The health risk assessment model adopts a Gaussian mixture model, which includes: Data standardization: standardize air particle concentration data and physiological data; The basic structure of the Gaussian mixture model: The Gaussian mixture model is used to model the standardized air particle concentration data and physiological data, which can be expressed as: Where X is the multidimensional input data, including standardized air particle concentration data and physiological data, is the kth Gaussian distribution with mean μ k , the covariance matrix is ​​∑ k , π k is the weight of the kth mixture component, θ contains all model parameters, and K is the total number of Gaussian components; Introducing personalized weights for health status: Introducing personalized weights for health status to dynamically adjust the weights of different health risk states based on the different sensitivities of the elderly to air pollution; Dynamically update parameters: Capture the impact of air pollutants on the health of the elderly, introduce the time dimension, dynamically update the parameters of the model, and smooth the impact of historical air quality on health by using time-weighted average; Health risk probability output: Based on the dynamically updated Gaussian mixture model, the probability of each health state is output to indicate the potential risk of air pollution to the health of the elderly.

5. The medical monitoring elderly care robot according to claim 4, characterized in that: The air purification and environmental control include: Air purification control: By receiving the results of the health impact assessment, the air purification equipment in the robot body is automatically adjusted, including adjusting the wind speed, filter working mode and purification intensity; External ventilation control: Connect with external intelligent ventilation equipment through wireless communication, remotely control the opening, closing and ventilation intensity adjustment of external intelligent ventilation equipment based on the results of health impact assessment, and realize dynamic optimization of indoor air circulation and quality.

6. The medical monitoring elderly care robot according to claim 1, characterized in that: The emotion and health integration unit includes: Facial expression recognition: The facial expressions of the elderly are captured by cameras, and convolutional neural networks are used to analyze facial features in real time to identify the emotional states of the elderly, including happiness, sadness, anger, and anxiety; Voice emotion analysis: The microphone collects the elderly’s voice signals, evaluates the emotional information in the voice, including intonation, speaking speed, and volume, and determines the emotional state of the elderly; Data fusion and emotional intervention: The emotional state of facial expression recognition and voice emotion analysis are integrated with physiological data to comprehensively analyze the mental health status of the elderly. Based on the analysis results, emotional intervention plans are automatically generated, including playing soothing music, adjusting ambient lighting, or reminding caregivers to pay attention.

7. The medical monitoring elderly care robot according to claim 6, characterized in that: The facial expression recognition comprises: Camera collection: Use the camera to capture the facial images of the elderly in real time; Facial feature extraction: Real-time analysis of facial features based on convolutional neural networks to extract facial key points, including feature vectors of eyes, mouth corners, and eyebrows. Emotion classification: The extracted facial feature vectors are input into the convolutional neural network for classification to identify the emotional states of the elderly, including happiness, sadness, anger, and anxiety.

8. The medical monitoring elderly care robot according to claim 7, characterized in that: The speech emotion analysis includes: Voice collection: The voice signals of the elderly are collected in real time through microphones; Speech feature extraction: Use speech signal processing algorithms to extract emotional features in speech, including intonation, speaking speed, and volume, which are used to determine the emotional information in speech; Emotion classification: The extracted emotional features are input into the support vector machine model to output the emotional state of the elderly, including the emotional categories of happiness, sadness, anger, and anxiety.

9. The medical monitoring elderly care robot according to claim 8, characterized in that: The data fusion and emotion intervention include: Multimodal data fusion: The emotional state of facial expression recognition, the emotional state of voice emotion analysis and physiological data are integrated and processed, and the current mental health index H of the elderly is comprehensively generated using the weighted average method; Mental health status determination: Based on the fused mental health index H, the mental health status of the elderly is determined using the predefined threshold interval and divided into different emotional risk levels, including low risk, medium risk and high risk; Emotional intervention: Automatically generate emotional intervention plans based on the judgment results, including playing soothing music, adjusting ambient lighting, or reminding caregivers to pay attention.

10. The medical monitoring elderly care robot according to claim 1, characterized in that: The nursing assistance unit comprises: Robotic arm assistance: Through data interaction with the physiological monitoring unit and the emotion and health fusion unit, it receives real-time feedback on the elderly's physiological data and mental health, and assists the elderly in daily activities, including eating assistance, dressing assistance, and sports rehabilitation training; Voice control system: Controls the robotic arm to perform auxiliary tasks through voice commands, and adjusts the movement intensity and operation frequency of the robotic arm in real time based on feedback data from the physiological monitoring unit and the emotion and health fusion unit.

Images