Early warning method and device for abnormal activity of home-based care personnel

Abstract

The invention discloses an early warning method and device for activity abnormity of home-based care personnel, and relates to the technical field, the method comprises data acquisition, data analysis, an early warning mechanism and subsequent processing.Through multi-dimensional combination of a motion sensor, an intelligent bracelet and a camera, activity data of old people are comprehensively acquired from different angles, the activity state of the old people is reflected in real time, and the early warning effect is good. According to the invention, family members and nursing personnel can timely know the situation and rapidly respond when abnormity occurs, the safety is improved, the design of the smart bracelet is very intimate, an elderly activity abnormity algorithm is established, the elderly activity modes are divided into very active, general active and inactive, the activity rules are analyzed for different groups, and the elderly activity abnormity algorithm is established. Activity data of the elderly are compared with a group mode to which the elderly belongs in real time, abnormity can be found in time, mild, moderate and severe abnormity indexes are set in an early warning mechanism, accurate response is performed according to the severity of abnormal conditions, and the survival probability of the elderly in home life is integrally improved through the combination of the method and the device.

Description

Technical Field

[0001] The present invention relates to the technical field, and in particular to a method and device for early warning of abnormal activities of elderly people living at home. Background Art

[0003] Home-based elderly care (service) refers to socialized services that are provided to elderly people living at home with the family as the core, the community as the support, and professional services as the basis, with the main content being to solve the difficulties in daily life. The services include life care, medical services, and spiritual care services. There are two main forms: professionally trained service personnel provide home-based care services for the elderly; and the establishment of elderly day service centers in the community to provide day care services for the elderly.

[0004] Due to factors such as limited funding, there are only a limited number of professionally trained service personnel and a large workload. Therefore, it is impossible to provide 24-hour care services for home-based elderly people. Only passive sensing methods such as regular or irregular home visits can be adopted. Traditional passive sensing methods are difficult to obtain continuous and efficient information and cannot fully adapt to the new needs of home-based elderly care.

[0005] Traditional passive sensing methods such as regular or irregular on-site inspections have the following problems:

[0006] 1. Passive perception, time-consuming, and not timely. The biggest disadvantage of traditional means is that they perceive information passively. They only visit the door when they receive relevant messages, which does not give full play to subjective initiative. It is not conducive to obtaining information in the first time when an emergency occurs, nor is it conducive to the personal information management and recording of home-based elderly care personnel.

[0007] 2. It consumes a lot of manpower and material resources, and is greatly affected by the working conditions and personal business capabilities of the service personnel, and is not sustainable and stable. Regular or irregular door-to-door visits require service personnel to visit without determining the target. When the service personnel have limited time and energy, the deployment of service personnel is unreasonable. Therefore, we propose a method and device for abnormal early warning of activities of home-based elderly care personnel to solve the above problems. Summary of the invention

[0008] The purpose of the present invention is to provide a method and device for early warning of abnormal activities of elderly people at home, so as to solve the problems raised in the above-mentioned background technology.

[0009] In order to achieve the above-mentioned invention object, the present invention adopts the following technical scheme:

[0010] The present invention provides a method for early warning of abnormal activities of elderly people living at home, which specifically comprises the following steps:

[0011] S101, data collection, installing motion sensors in the main activity areas where the elderly live, having the elderly wear wearable smart bracelets to record physical activity data, and installing cameras in the main activity areas of the elderly;

[0012] S102: Data analysis: Based on the collected activity data of the elderly, an algorithm for determining abnormal activity of the elderly is established:

[0013]

[0014] Calculate the activity distance of the elderly, classify them into very active, moderately active and inactive groups, perform anomaly detection, and compare activity data and activity patterns in real time;

[0015] S103, early warning mechanism, multi-level warning, mild abnormality to remind family members or caregivers, moderate abnormality to send alarms and notify relevant personnel, severe abnormality to contact emergency rescue agencies, notification can be made via mobile phone text messages, emails and applications;

[0016] S104, follow-up processing, after receiving the warning, family members and caregivers can verify it by phone, check the surveillance and visit in person. If the elderly person is abnormal, send him to the hospital and provide help according to the situation. In the follow-up, parameters and algorithms can be adjusted according to the actual situation and warning effect.

[0017] Preferably, the data collection includes determining the location, evaluating the daily activity trajectory of the elderly, installing motion sensors in the bedroom, living room, bathroom and kitchen areas, and selecting sensors according to needs and environment.

[0018] Preferably, the data collection also includes selecting a smart bracelet and installing a camera, installing the camera in the main activity areas of the elderly such as the living room, bedroom, and kitchen, paying attention to privacy, and selecting fixed-focus, zoom, and pan-tilt cameras according to needs.

[0019] Preferably, the data analysis requires cleaning and organizing the collected activity data of the elderly to remove outliers and noise, establish an abnormal activity determination algorithm for the elderly to divide the elderly into very active, generally active and inactive groups, analyze their daily activity patterns for different groups respectively, determine their respective activity patterns, including activity time and activity range, monitor the activity data of the elderly in real time, and compare them with the activity patterns of the group to which they belong. If there is a large difference, it is judged to be abnormal.

[0020] Preferably, the early warning mechanism needs to analyze the activity data and behavior patterns of the elderly and set specific indicators for mild, moderate and severe abnormalities. A decrease in activity frequency of less than 20% is a mild abnormality, 20% to 50% is a moderate abnormality, and more than 50% is a severe abnormality.

[0021] Preferably, the early warning mechanism monitors the activity data of the elderly, compares the current state with the normal activity pattern in real time, finds deviations, and conducts abnormality level assessment. When the system determines that there is a slight abnormality, a reminder message is sent to the elderly's family or caregiver via mobile phone text message or email.

[0022] Preferably, when a moderate abnormality warning is triggered in the early warning mechanism, the system sounds an alarm and simultaneously sends a notification to relevant personnel via mobile phone text messages, emails, and mobile phone applications. The notification should clearly state the specific circumstances and possible causes of the abnormality. If a severe abnormality is detected, the system immediately contacts the emergency rescue agency and sends an emergency notification to family members, caregivers, and relevant emergency contacts. The notification must include the location information and current condition of the elderly person.

[0023] Preferably, in the subsequent processing, after receiving the early warning, the family members and caregivers initiate a verification procedure and try to contact the elderly by phone to understand their current status and whether there are any abnormal conditions. If the elderly cannot be contacted by phone, the family members and caregivers check the cameras installed in the elderly's activity area to observe the elderly's activities and determine whether there are any abnormal signs. If the situation is still unclear or urgent, the family members and caregivers go to the elderly's residence in person to check and ensure the elderly's safety.

[0024] Preferably, if there are abnormal conditions for the elderly during the subsequent processing, action is taken according to the specific situation. If the elderly are unwell, contact a medical institution to arrange for medical treatment. If the elderly fall and cannot get up, or if there is equipment failure, etc., provide corresponding help and support to solve the elderly’s problems. Combined with the actual situation, evaluate the accuracy and timeliness of the early warning, and adjust the parameters and algorithms of the early warning system based on the analysis results.

[0025] A device for activities of elderly people living at home, the smart bracelet comprising an outer shell, a holder for a closed ring being installed at the opening of the outer shell, a velvet sheet for contacting a human body being adhered to the inner ring wall of the outer shell, a plurality of monitors being installed on the side of the holder close to a human arm, the outer shell being made of silicone material, a plurality of rubber strips for driving the outer shell to close being installed in the inner cavity of the outer shell, and a telescopic spring for improving the strength of the overall structure being sleeved on the surface of the rubber strip.

[0026] Compared with the prior art, one or more of the above technical solutions have the following beneficial effects:

[0027] The present invention uses a multi-dimensional combination of motion sensors, smart bracelets and cameras to comprehensively collect elderly activity data from different angles, reflect the elderly activity status in real time, and allow family members and caregivers to understand the situation in a timely manner and respond quickly in abnormal situations, thereby improving safety. The design of the smart bracelet is also very considerate, and the elderly activity patterns are divided into three types: very active, generally active and inactive. The activity patterns are analyzed for different groups to provide a basis for personalized elderly care services. An abnormal activity judgment algorithm for the elderly is established, and the elderly activity data is compared with the group pattern in real time to detect abnormalities in a timely manner. The early warning mechanism sets mild, moderate and severe abnormal indicators, and responds accurately according to the severity of the abnormal situation to improve the survival rate of the elderly. The method and device bring higher safety and better quality of life to the existing elderly home-based elderly care life. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0029] Figure 1 It is a schematic diagram of the overall method framework of the present invention;

[0030] Figure 2 It is a structural schematic diagram of a data acquisition module of the present invention;

[0031] Figure 3 It is a schematic diagram of the structure of the data analysis module of the present invention;

[0032] Figure 4 It is a schematic diagram of the structure of the smart bracelet of the present invention;

[0033] Figure 5 It is a schematic diagram of the internal structure of the smart bracelet of the present invention.

[0034] In the figure: 1, outer shell; 101, velvet sheet; 2, card holder; 201, monitor; 3, rubber strip; 301, telescopic spring. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0036] See also Figure 1-Figure 5The present invention provides a method and device for early warning of abnormal activities of elderly people living at home, including data collection, data analysis, early warning mechanism and subsequent processing. The activity data of the elderly are comprehensively collected from different angles, and the activity patterns of the elderly are divided into three types: very active, generally active and inactive. The activity patterns are analyzed for different groups, providing a basis for personalized elderly care services, and abnormalities can be discovered in time.

[0037] Among them, data collection needs to determine the location first, evaluate the daily activity trajectory of the elderly, install motion sensors, infrared, motion and pressure sensors in the bedroom, living room, bathroom and kitchen areas, select sensors according to needs and environment, ensure firm installation, and debug after installation to ensure normal operation. At the same time, choose smart bracelets, help the elderly put on the bracelets, install cameras, and install cameras in the main areas of elderly activities such as living rooms, bedrooms, and kitchens. Pay attention to privacy. You can choose cameras in inconspicuous positions or adjustable angles. Choose fixed focal length, zoom or pan-tilt cameras according to needs to ensure firm installation. Debug after installation to ensure normal image quality and monitoring range. Multi-dimensional data collection motion sensors, smart bracelets and camera combinations collect elderly activity data from different angles, comprehensively reflect the activity status, and provide accurate basis for abnormal warnings. Sensors and bracelets record activity data in real time, and cameras observe in real time, so that family members and caregivers can understand the activity status of the elderly in a timely manner, and deal with abnormalities in a timely manner. When the elderly's activities are abnormal, timely warnings are issued to remind attention to the elderly's situation and improve safety.

[0038] In data analysis, it is necessary to clean and organize the collected activity data of the elderly, remove outliers and noise, and calculate the activity distance of the elderly in a certain period of time, the number of activity steps per day, the time spent in a specific area per day, and the duration of specific activities per day through the number of steps recorded by wearable devices combined with step length estimation and other methods;

[0039] Standardize the data to make different types of data comparable, and convert data such as activity steps and dwell time into values ​​with a mean of 0 and a standard deviation of 1.

[0040] Determine the number of clusters K, observe the activity patterns of the elderly, determine the number of possible classifications, and classify the activity patterns of the elderly into three types: very active, generally active, and inactive. Select K = 3;

[0041] Randomly select K data points from the elderly data set as the initial centroids. If there are 100 elderly people's activity data and K=3 clustering is to be performed, then randomly select 3 from these 100 data points as the initial centroids. For each elderly person's data point, calculate its distance to each centroid;

[0042]

[0043] Here, x is the data point of an elderly person, which contains multiple features such as the number of steps and residence time, y is the centroid, and n is the number of features.

[0044] Assign the data points of the elderly to the cluster with the nearest centroid. If the data point of an elderly person is closest to centroid 1, then assign the elderly person to the cluster represented by centroid 1.

[0045] For each cluster, calculate the mean of all elderly data points in the cluster as the new centroid;

[0046] If there are 30 data points of elderly people in a cluster, calculate the average value of each feature of these elderly people, get the new centroid, and repeat the steps of allocating data points and updating the centroid until the centroid no longer changes or the maximum number of iterations is reached;

[0047] The final K clusters can represent different activity patterns of the elderly;

[0048] Cluster 1 may represent a very active group of elderly people, who take many steps and spend a relatively balanced amount of time in various areas.

[0049] Cluster 2 may represent a generally active group of elderly people with moderate levels of activity.

[0050] Cluster 3 may represent an inactive group of elderly people, who have few steps and spend most of their time in a specific area.

[0051] Analyze the daily activity patterns of different groups and determine their respective activity patterns, including activity time, activity range, etc.

[0052] Real-time monitoring of the elderly's activity data is carried out and compared with the activity patterns of the group to which they belong. If there is a large difference, it is judged as abnormal. The elderly can be classified through machine learning algorithms, which can more accurately reflect the activity status of the elderly and provide a basis for personalized elderly care services. Real-time comparison of activity data and patterns can promptly detect abnormal activities of the elderly and improve their safety. Targeted elderly care plans can be formulated for groups with different activity levels. For example, very active elderly people can be provided with more social activities, while inactive elderly people can receive strengthened health monitoring and rehabilitation services, which will help family members and caregivers manage the lives of the elderly more efficiently and allocate resources reasonably.

[0053] In the early warning mechanism, the activity data and behavior patterns of the elderly are analyzed, and specific indicators for mild, moderate and severe abnormalities are set. A decrease in activity frequency of less than 20% is a mild abnormality, 20% to 50% is a moderate abnormality, and more than 50% is a severe abnormality. Or the absence of activity in a specific area for a period of time can be used as a basis for judging different degrees of abnormality. The activity data of the elderly are continuously monitored, and the current state is compared with the normal activity pattern in real time. Once a deviation is found, an abnormal level assessment is immediately performed. In this way, the elderly can be classified according to their activity data to better understand the characteristics of their activities and provide a basis for subsequent abnormal detection and personalized services. When the system determines that there is a mild abnormality, a reminder message is sent to the elderly's family or caregiver via mobile phone text messages or emails. The information content should include a brief description of the abnormal situation and the key points of recommended observation. When a moderate abnormality warning is triggered, the system sounds an alarm and sends a notification to relevant personnel via mobile phone text messages, emails and mobile phone applications. The specific situation and possible causes of the abnormality should be clearly stated in the notification so that relevant personnel can take further action. Once a severe abnormality is detected, the system immediately contacts the emergency rescue agency and sends an emergency notification to the family, caregivers and relevant emergency contacts. The notification must include the elderly person’s location information and current condition so that rescue personnel can respond quickly.

[0054] Different levels of early warning mechanisms can respond accurately according to the severity of abnormal situations, ensuring that the most appropriate actions can be taken in various situations to avoid overreaction or underreaction. Relevant personnel can be notified through various methods such as mobile phone text messages, emails and applications, which improves the timeliness and reliability of notifications. Family members and caregivers can choose the way to receive notifications according to their own habits and actual conditions to ensure that they will not miss important information. For severe abnormal situations, directly contacting emergency rescue agencies can greatly shorten the rescue time and increase the survival rate of the elderly. At the same time, notifying family members and caregivers can also allow them to take some preliminary rescue measures before the arrival of rescuers. Notifying family members and caregivers of mild abnormalities enables them to pay closer attention to and care for the elderly, adjust the elderly's lifestyle in time or provide necessary help. Notifications of moderate and severe abnormalities can mobilize more resources to provide comprehensive support for the elderly.

[0055] After the family and caregivers receive the warning, they will immediately start the verification procedure. First, try to contact the elderly by phone to understand their current status and whether there are any abnormalities. If the phone cannot reach the elderly, check the cameras installed in the elderly's activity area to observe the elderly's activities and determine whether there are any abnormal signs. If the situation is still unclear or more urgent, the family and caregivers will go to the elderly's residence in person to check to ensure the safety of the elderly. If it is found that the elderly do have abnormal conditions, take action according to the specific situation. If the elderly are unwell, immediately contact the medical institution to arrange for medical treatment. If the elderly encounter other difficulties, such as falling and being unable to get up, equipment failure, etc., provide corresponding help and support to solve the elderly's problems. After handling the abnormal situation, analyze and summarize the warning event. Combined with the actual situation, evaluate the accuracy and timeliness of the warning, and adjust the parameters and algorithms of the warning system according to the analysis results. For example, adjust the threshold of abnormal judgment, optimize the model parameters of the machine learning algorithm, etc. to improve the accuracy and reliability of the early warning, continuously monitor the activities of the elderly, verify the effect of the adjustment, and continuously optimize the early warning system to ensure that prompt action can be taken after receiving the early warning, verify the abnormal situation, avoid delaying the rescue of the elderly, take corresponding measures according to the specific abnormal situation of the elderly, provide personalized help and support, meet the actual needs of the elderly, and improve the performance of the early warning system by continuously adjusting parameters and algorithms to make it more accurate and reliable, provide better protection for the safety of the elderly, form a closed-loop follow-up processing mechanism, and constantly draw lessons from actual conditions, continuously improve the early warning system, and adapt to the changing activity patterns and needs of the elderly.

[0056] The smart bracelet includes an outer shell, a holder for a closed ring is installed at the opening of the outer shell, a velvet sheet for contacting the human body is adhered to the inner ring wall of the outer shell, and a variety of monitors are installed on the side of the holder close to the human arm. The outer shell is made of silicone material, and a plurality of rubber strips for driving the outer shell to close are installed in the inner cavity of the outer shell. The surface of the rubber strip is sleeved with a telescopic spring for improving the overall structural strength. The outer shell is made of silicone material, which is soft in texture and will not cause discomfort when in contact with human skin. It is especially suitable for people with sensitive skin such as the elderly. Even if worn for a long time, it will not cause compression or friction damage to the skin, and the velvet sheet adhered to the inner ring wall further increases the comfort of wearing. The velvet sheet is soft and skin-friendly, which can reduce the friction between the bracelet and the skin. It also has a certain sweat absorption effect to keep the skin dry.

[0057] The rubber strip and telescopic spring in the inner cavity of the outer shell cooperate with each other to provide the driving force for the outer shell to close, so that the bracelet can fit tightly on the wrist and is not easy to loosen or fall off. The telescopic spring is sleeved on the surface of the rubber strip to improve the overall structural strength. This allows the bracelet to better maintain its shape and structural integrity when it is pulled or squeezed by external forces, extending its service life.

[0058] The outer shell is a hollow lightweight structure, which reduces the weight of the bracelet, making it easier for the elderly to wear it without putting too much burden on their wrists. This lightweight design also makes it convenient for the elderly to carry out various activities in their daily lives without affecting the flexibility of their hands. A variety of monitors are installed on the side of the card holder close to the human arm, which can monitor the elderly's physical condition in real time, such as heart rate, blood pressure, blood oxygen, etc. These monitoring data are crucial for the health management of the elderly. They can detect potential health problems in a timely manner, provide a reference for doctors' diagnosis and treatment, and provide an effective health monitoring tool for home-based elderly care, which helps to improve the quality of life and safety of the elderly.

[0059] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for early warning of abnormal activities of elderly people living at home, characterized in that: The specific steps include: S101, data collection, installing motion sensors in the main activity areas where the elderly live, having the elderly wear wearable smart bracelets to record physical activity data, and installing cameras in the main activity areas of the elderly; S102: Data analysis: Based on the collected activity data of the elderly, an algorithm for determining abnormal activity of the elderly is established: Calculate the activity distance of the elderly, classify them into very active, moderately active and inactive groups, perform anomaly detection, and compare activity data and activity patterns in real time; S103, early warning mechanism, multi-level warning, mild abnormality to remind family members or caregivers, moderate abnormality to send alarms and notify relevant personnel, severe abnormality to contact emergency rescue agencies, notification can be made via mobile phone text messages, emails and applications; S104, follow-up processing, after receiving the warning, family members and caregivers can verify it by phone, check the surveillance and visit in person. If the elderly person is abnormal, send him to the hospital and provide help according to the situation. In the follow-up, parameters and algorithms can be adjusted according to the actual situation and warning effect.

2. The method for early warning of abnormal activities of elderly people living at home according to claim 1, characterized in that: The data collection includes determining the location, evaluating the daily activity trajectory of the elderly, installing motion sensors in the bedroom, living room, bathroom and kitchen areas, and selecting sensors according to needs and environment.

3. The method for early warning of abnormal activities of elderly people living at home according to claim 1, characterized in that: The data collection also includes selecting smart bracelets and installing cameras, installing cameras in the main areas where the elderly move around, such as living rooms, bedrooms, and kitchens, paying attention to privacy, and selecting fixed-focus, zoom, and pan-tilt cameras according to needs.

4. The method for early warning of abnormal activities of elderly people living at home according to claim 1, characterized in that: In the data analysis, it is necessary to clean and organize the collected activity data of the elderly, remove outliers and noise, establish an abnormal activity judgment algorithm for the elderly, divide the elderly into very active, generally active and inactive groups, analyze their daily activity patterns for different groups, determine their respective activity patterns, including activity time and activity range, monitor the activity data of the elderly in real time, and compare it with the activity pattern of the group to which they belong. If there is a large difference, it is judged to be abnormal.

5. The method for early warning of abnormal activities of elderly people living at home according to claim 1, characterized in that: The early warning mechanism needs to analyze the activity data and behavior patterns of the elderly and set specific indicators for mild, moderate and severe abnormalities. A decrease in activity frequency of less than 20% is a mild abnormality, 20% to 50% is a moderate abnormality, and more than 50% is a severe abnormality.

6. The method for early warning of abnormal activities of elderly people living at home according to claim 1, characterized in that: The early warning mechanism monitors the activity data of the elderly, compares the current status with the normal activity pattern in real time, finds deviations, and conducts abnormality level assessment. When the system determines that it is a mild abnormality, a reminder message is sent to the elderly's family or caregiver via mobile phone text message or email.

7. The method for early warning of abnormal activities of elderly people living at home according to claim 1, characterized in that: When a moderate abnormality warning is triggered in the early warning mechanism, the system will sound an alarm and simultaneously send notifications to relevant personnel via mobile phone text messages, emails, and mobile phone applications. The notifications should clearly state the specific circumstances and possible causes of the abnormality. If a severe abnormality is detected, the system will immediately contact the emergency rescue agency and send an emergency notification to family members, caregivers, and relevant emergency contacts. The notifications must include the location information and current condition of the elderly person.

8. The method for early warning of abnormal activities of elderly people living at home according to claim 1, characterized in that: In the subsequent processing, after receiving the early warning, the family members and caregivers will start the verification procedure and try to contact the elderly by phone to understand their current status and whether there are any abnormalities. If the elderly cannot be contacted by phone, the cameras installed in the elderly’s activity area will be checked to observe the elderly’s activities and determine whether there are any abnormal signs. If the situation is still unclear or more urgent, the family members and caregivers will go to the elderly’s residence in person to check and ensure the elderly’s safety.

9. The method for early warning of abnormal activities of elderly people living at home according to claim 1, characterized in that: If there are abnormal conditions for the elderly during the follow-up processing, action will be taken based on the specific situation. If the elderly are unwell, contact a medical institution to arrange for medical treatment. If the elderly fall and cannot get up, or if there is equipment failure, provide corresponding help and support to solve the elderly’s problems. Based on the actual situation, evaluate the accuracy and timeliness of the early warning, and adjust the parameters and algorithms of the early warning system based on the analysis results.

10. The device used in the method for early warning of abnormal activities of home-based elderly care personnel according to claim 1, characterized in that: The smart bracelet includes an outer shell, a holder for a closed ring is installed at the opening of the outer shell, a velvet sheet for contacting the human body is adhered to the inner ring wall of the outer shell, a variety of monitors are installed on the side of the holder close to the human arm, the outer shell is made of silicone material, and a plurality of rubber strips for driving the outer shell to close are installed in the inner cavity of the outer shell, and a telescopic spring for improving the overall structural strength is sleeved on the surface of the rubber strip.

Images