A visual intelligent calling system for home-based elderly care
By using intelligent physical examination bracelets and sensor groups in the home-based elderly care visual smart call system to monitor the physiological, sleep and environmental characteristics of the elderly, generating a comprehensive body posture characteristic coefficient, solving the problem that guardians cannot pay attention to the elderly's living conditions in real time, and achieving intelligence Voice calls and emergency rescue have improved the quality of life and safety of the elderly.
Patent Information
- Application Number
- CN202410709042.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-03
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-06-03
AI Technical Summary
In the prior art, it is difficult for guardians to pay close attention to the living conditions of the elderly in full and real-time, resulting in the elderly who may face health risks and cannot receive timely assistance when they fall accidentally in daily life, which poses potential health risks.
A home-based elderly care visual smart call system is designed, including feature detection module, feature extraction module, visual monitoring module, integrated processing module and smart call module. The physiology, sleep and environment of the elderly are monitored in real time through intelligent physical examination bracelets and sensor groups. Features, generate comprehensive body posture feature coefficients to realize intelligent voice calls and emergency rescue.
The system can monitor the physical condition of the elderly in real time, identify fall events in a timely manner, provide emergency voice calls and remote rescue, improve the assistance opportunities for the elderly in emergency situations, ensure more reliable safety guarantees, and provide comprehensive body posture characteristics assessment. Comprehensive health management services.
Smart Images

Figure CN118447650B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of home-based elderly care, and in particular to a visual intelligent calling system for home-based elderly care. Background Art
[0002] As the trend of social aging continues to intensify, home-based elderly care has attracted much attention as an urgent and important social need. This type of elderly care emphasizes providing comprehensive care and support in a familiar and friendly family environment for the elderly, aiming to ensure that the elderly can live a dignified, comfortable and quality life in their later years. In the field of home-based elderly care, visual intelligent calling technology plays an important role, making it easier for guardians to observe the quality of life and safety of the elderly in real time and get help in time, providing a safer and more convenient home-based elderly care experience for the elderly at home.
[0003] In the current traditional elderly care model, guardians often face the dilemma of not being able to pay full and real-time attention to the living conditions of the elderly. Subjective factors often make it difficult for guardians to provide round-the-clock guardianship services, making it impossible for the elderly's living conditions to receive timely and effective attention. This poses a potential risk, that is, the elderly may face various health risks in their daily lives, and these problems may be ignored or delayed in response in the absence of comprehensive monitoring. In particular, due to the inconvenience of the elderly's mobility, they are prone to accidental falls. However, since the guardians cannot monitor the entire process, the elderly may face the dilemma of not receiving timely assistance after being injured. This delay may have an irreversible impact on the health of the elderly and may even lead to serious consequences. Summary of the invention
[0004] 1. Technical issues to be resolved
[0005] In view of the deficiencies in the prior art, the present invention provides a visual intelligent calling system for home-based elderly care, which solves the problems mentioned in the background technology.
[0006] Technical Solution
[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: including a feature detection module, a feature extraction module, a visual monitoring module, an integrated processing module and a smart call module;
[0008] The feature detection module is used to wear a smart physical examination bracelet on the hands of the ward, and install a detection device to perform real-time detection of the ward's comprehensive body feature data and fall data, and then the feature extraction module classifies and summarizes the detected comprehensive body feature data and fall data to generate a first data set and a second data set;
[0009] The visual monitoring module is used to set the monitoring device to connect to the remote mobile client, and connect the smart physical examination bracelet and the detection device in series to generate a visual monitoring system;
[0010] The integrated processing module includes a first processing unit, a second processing unit and a third associated processing unit, wherein the first processing unit is used to extract a related data set based on the first data set, and after dimensionless processing, perform analysis and calculation to obtain a physiological characteristic coefficient Smxs, a sleep characteristic coefficient Smtz and an indoor environment characteristic coefficient Snhj; and the second processing unit extracts a fall characteristic data set based on the second data set, and after dimensionless processing, performs analysis and calculation to obtain a fall characteristic coefficient Sdtz; and the third associated processing unit associates the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj for analysis and calculation to obtain a comprehensive body characteristic coefficient Tzxs;
[0011] The smart call module is used to preset the first call threshold Z and the fall characteristic coefficient Sdtz for preliminary comparative evaluation, generate relevant evaluation results, and generate corresponding call strategies according to the evaluation results. It is also used to preset the second call threshold V and obtain the comprehensive body characteristic coefficient Tzxs for comparative evaluation, and generate corresponding voice prompt calls according to the evaluation results.
[0012] Preferably, the feature detection module includes a first detection unit and a second detection unit;
[0013] The first detection unit includes a first detection device and a second integrated sensor group for detecting comprehensive body feature data;
[0014] The first detection device includes a medical intelligent physical examination bracelet, which is used to be worn by elderly people living at home to perform real-time detection of the elderly's physiological characteristics and sleep characteristics;
[0015] The second integrated sensor group is used to be deployed indoors to perform real-time detection of indoor environmental characteristic data of the elderly, and includes a temperature sensor, a humidity sensor, a particle detection sensor, a photoresistor and a decibel meter;
[0016] The second detection unit includes a third integrated sensor group, which is arranged in the living room, bedroom, kitchen and bathroom of the house to perform real-time detection of the movement characteristics of the elderly. The third integrated sensor group includes a depth sensor, a bone tracker, a gyroscope and an accelerometer to perform real-time detection of the elderly's fall characteristic data.
[0017] Preferably, the feature extraction module includes a first extraction unit and a second extraction unit;
[0018] The first extraction unit is used to aggregate the detected comprehensive body feature data to generate a first data set, and extract the first data set;
[0019] The first data set includes a physiological characteristic data set, a sleep characteristic data set and an indoor environment characteristic data set;
[0020] The physiological characteristic data set includes heart rate Sxl, respiratory rate Shx, blood pressure Sxy, body temperature Stw and blood oxygen saturation Sbh;
[0021] The sleep characteristic data set includes the sleeping time Mrs, the waking time Mxl, the deep sleep time Mss, the light sleep time Mqs and the number of waking times Mcs;
[0022] The indoor environment characteristic data set includes temperature Nwd, humidity Nsd, particle concentration Nkl, noise decibel Nfb and light intensity Ngz;
[0023] The second extraction unit is used to generate a second data set after summarizing the detected fall feature data, and extract the second data set, wherein the second data set includes the fall feature data set;
[0024] The fall feature data set includes vertical acceleration Dcz, body inclination angle Dqx, body target height Dmb, center of gravity offset Dpy and body curvature Dql.
[0025] Preferably, the visual monitoring module constructs a user visual interface through front-end programming technology, and configures the mobile terminal code through front-end programming technology to optimize the visual interface to adapt to mobile phones and fixed-end devices;
[0026] A ToF camera is set up to obtain the three-dimensional coordinate information and live picture of the room, and then the live picture is embedded into the user visualization interface by front-end programming technology. At the same time, a login mechanism for account and password verification is set for entering the live interface, and the body contour and movement of the elderly detected by the third integrated sensor group are embedded into the live picture through human body detection and tracking algorithms, and the body contour information of the elderly entering the live picture is observed and monitored in real time. At the same time, the API application interface provided by the smart physical examination bracelet manufacturer and the sensor manufacturer is connected in series with the user visualization interface through the Internet of Things, and the detected physiological characteristic data, sleep characteristic data and indoor environment characteristic data of the elderly are transmitted in real time, and presented to the user visualization interface in a digital form.
[0027] Preferably, the integrated processing module comprises a first processing unit, a second processing unit and a third associated processing unit;
[0028] The first processing unit includes a physiological feature processing unit, a sleep feature processing unit and an indoor environment feature processing unit;
[0029] The physiological characteristic processing unit is used to perform dimensionless processing on the physiological characteristic data set in the first data set, and then analyze and calculate to obtain the physiological characteristic coefficient Smxs;
[0030] The physiological characteristic coefficient Smxs is obtained by the following formula:
[0031]
[0032] Preferably, the sleep characteristic processing unit is used to analyze and calculate the sleep characteristic coefficient Smtz after dimensionless processing based on the sleep characteristic data set in the first data set;
[0033] The sleep characteristic coefficient Smtz is obtained by the following formula:
[0034]
[0035] The indoor environment characteristic processing unit is used to analyze and calculate the indoor environment characteristic coefficient Snhj after dimensionless processing based on the indoor environment characteristic data set in the first data set;
[0036] The indoor environment characteristic coefficient Snhj is obtained by the following formula:
[0037]
[0038] Preferably, the second processing unit is used to extract the fall feature data set according to the second data set, and analyze and calculate to obtain the fall feature coefficient Sdtz after dimensionless processing;
[0039] The fall characteristic coefficient Sdtz is obtained by the following formula:
[0040]
[0041] Preferably, the third correlation processing unit is used to perform dimensionless processing on the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj obtained by the first processing unit, and then perform correlation calculation processing to obtain the comprehensive body characteristic coefficient Tzxs;
[0042] The comprehensive body characteristic coefficient Tzxs is obtained by the following formula:
[0043]
[0044] Wherein, a1, a2 and a3 represent the preset proportional coefficients of the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj respectively, and a1+a2≠a3, 0<a1<0.67, 0<a2<0.98, 0<a3<0.71, and the specific values are adjusted and set by the user, and A is the first correction constant.
[0045] Preferably, the smart call module includes a first call unit and a second call unit;
[0046] The first calling unit is used to preset a first calling threshold Z and a fall characteristic coefficient Sdtz for preliminary evaluation, and generate a relevant calling scheme according to relevant evaluation results. The specific evaluation scheme is as follows;
[0047] When the fall characteristic coefficient Sdtz> the first call threshold Z, it means that the elderly person meets the fall characteristics in the live picture of the current user visualization interface. At this time, the system automatically sends an intelligent voice call to the elderly person to determine whether the elderly person is conscious after falling. At the same time, the voice call is repeated three times, with an interval of 10 seconds between each call. If the elderly person does not respond, the system automatically calls the rescue team, generates an early warning message through the user visualization interface, and converts it into an intelligent voice call to the remote mobile and fixed end guardians;
[0048] When the fall feature coefficient Sdtz≤the first call threshold Z, it means that the fall feature of the elderly is not identified in the live picture of the user visualization interface. At this time, the second call mechanism is implemented to detect the vital signs of the elderly in real time.
[0049] Preferably, the second calling unit is a second calling mechanism triggered by the first calling unit, and compares and evaluates the comprehensive body characteristic coefficient Tzxs obtained by the third associated processing unit through the preset second calling threshold V, and generates relevant evaluation results. The specific evaluation scheme is as follows;
[0050] When the comprehensive body characteristic coefficient Tzxs> the second call threshold V, it means that the current indoor environment of the elderly is abnormal. At this time, the monitoring equipment will periodically call the elderly to open windows for ventilation and dehumidification according to the changes in the indoor environment, prompting the elderly to improve their living environment;
[0051] When the comprehensive body characteristic coefficient Tzxs≤the second call threshold V, it indicates that the current vital signs of the elderly are abnormal. At this time, the physiological characteristics and sleep characteristics of the elderly will be analyzed, and the guardian will be called to conduct a comprehensive physical examination of the elderly. At the same time, a regular intelligent voice call will be made to the elderly to arrange their work and rest time reasonably.
[0052] Beneficial Effects
[0053] The present invention provides a visual intelligent calling system for home-based elderly care, which has the following beneficial effects:
[0054] (1) The system can not only comprehensively monitor the basic physiological characteristics of the guardian through the smart physical examination bracelet and detection equipment, but also track the guardian's sleep status and changes in the indoor environment in real time through the sensor group, especially in the monitoring of fall events, and make smart calls to the elderly and the medical team according to different situations. The system builds a user visual interface and embeds human contour and motion recognition algorithms, so that the user visual interface can detect the body characteristics of the guardian in real time and accurately identify the guardian's fall data in real time. Once the system detects an abnormality, the smart call module will start quickly and initiate an emergency voice call to identify the extent of the elderly's injury after the fall if necessary, and make an emergency call to the guardian's remote mobile device and fixed device to ensure that the elderly can quickly get help in an emergency. Through the smart call module, the system not only initiates a call when an abnormality is detected, but also provides an emergency voice call method, which further increases the elderly's chances of getting help. This intelligent care service can provide rapid and accurate support at critical moments, providing more reliable safety protection for elderly people living at home.
[0055] (2) The system generates a comprehensive body characteristic coefficient Tzxs by comprehensively processing physiological characteristics, sleep characteristics and indoor environment characteristics data through an integrated processing module. This enables the system to not only monitor the elderly's physical condition in real time, but also conduct a comprehensive assessment to provide the elderly with more comprehensive health management services. Through the second call unit, the system can trigger an early warning based on the comprehensive body characteristic coefficient, prompting the elderly to improve their living environment or undergo a comprehensive physical examination, thereby improving the quality of life at home.
[0056] (3) The system evaluates the vital signs of the elderly through the second call unit of the intelligent call module to implement a personalized call strategy. The system not only calls the guardian in time when physiological abnormalities are found in the elderly, but also generates voice prompt calls based on comprehensive physical characteristics to remind the elderly to arrange their work and rest time reasonably. At the same time, the system prompts the elderly to improve their living environment through monitoring equipment. This personalized call and care service helps to meet the diverse needs of the elderly and improve their quality of life. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] Figure 1 This is a flow chart of a visual intelligent calling system for home-based elderly care according to the present invention.
[0058] In the figure: 1. Feature detection module; 2. Feature extraction module; 3. Visual monitoring module; 4. Integrated processing module; 5. Intelligent call module; 11. First detection unit; 12. Second detection unit; 21. First extraction unit; 22. Second extraction unit; 41. First processing unit; 411. Physiological feature processing unit; 412. Sleep feature processing unit; 413. Indoor environment feature processing unit; 42. Second processing unit; 43. Third associated processing unit; 51. First call unit; 52. Second call unit. DETAILED DESCRIPTION
[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0060] Example 1
[0061] See also Figure 1 The present invention provides a visual intelligent call system for home-based elderly care. To achieve the above purpose, the present invention is implemented through the following technical solutions: including a feature detection module 1, a feature extraction module 2, a visual monitoring module 3, an integrated processing module 4 and an intelligent call module 5;
[0062] The feature detection module 1 is used to wear a smart physical examination bracelet on the hands of the ward, and install a detection device to perform real-time detection of the comprehensive body feature data and fall data of the ward, and then the feature extraction module 2 classifies and summarizes the detected comprehensive body feature data and fall data to generate a first data set and a second data set;
[0063] The visual monitoring module 3 is used to set the monitoring device to connect to the remote mobile client, and connect the smart physical examination bracelet and the detection device in series to generate a visual monitoring system;
[0064] The integrated processing module 4 includes a first processing unit 41, a second processing unit 42 and a third associated processing unit 43. The first processing unit 41 is used to extract the relevant data set based on the first data set, and after dimensionless processing, analyze and calculate to obtain the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj; and the second processing unit 42 extracts the fall characteristic data set based on the second data set, and after dimensionless processing, analyzes and calculates to obtain the fall characteristic coefficient Sdtz; and the third associated processing unit 43 associates the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj and performs associated analysis and calculation to obtain the comprehensive body characteristic coefficient Tzxs;
[0065] The intelligent call module 5 is used to preset the first call threshold Z and the fall characteristic coefficient Sdtz for preliminary comparative evaluation, generate relevant evaluation results, and generate corresponding call strategies according to the evaluation results. It is also used to preset the second call threshold V and obtain the comprehensive body characteristic coefficient Tzxs for comparative evaluation, and generate corresponding voice prompt calls according to the evaluation results.
[0066] In this embodiment, through the feature detection module 1, the system can monitor the comprehensive body characteristics and fall data of the guardian in real time, so that when an emergency occurs to the elderly, an alarm can be issued in time, which improves the efficiency of responding to emergencies and optimizes the problem of untimely monitoring caused by subjective factors of the guardian. The integrated processing module 4 generates a comprehensive body characteristic coefficient Tzxs by analyzing and calculating the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj. This provides a basis for comprehensive health assessment, helping guardians to better understand the health status of the wards, thereby achieving more comprehensive health management. The smart call module 5 realizes a personalized call strategy by presetting the first call threshold Z and the fall characteristic coefficient Sdtz. The system can adjust the timing of the voice prompt call according to the actual situation of the ward, thereby improving the intelligence level of the system, avoiding unnecessary false alarms, and ensuring the accuracy of the call. The visual monitoring module 3 presents the monitored data in a digital form on the user interface by connecting to the remote mobile client, which improves the guardian's visualization of the elderly's living conditions, enhances the user experience, and makes guardianship more convenient and intuitive. The system uses the first call unit 51 of the smart call module 5 to automatically call the rescue team in the event of an emergency such as a fall, which helps to shorten the rescue response time and minimize the risk of irreversible damage to the elderly due to gaps in monitoring and untimely rescue after an accidental fall.
[0067] Example 2
[0068] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the feature detection module 1 includes a first detection unit 11 and a second detection unit 12;
[0069] The first detection unit 11 includes a first detection device and a second integrated sensor group for detecting comprehensive body feature data;
[0070] The first detection equipment includes a medical smart physical examination bracelet, which is worn by elderly people living at home to detect their physiological characteristics and sleep characteristics in real time;
[0071] The second integrated sensor group is used to be deployed indoors to perform real-time detection of indoor environmental characteristic data of the elderly, including a temperature sensor, a humidity sensor, a particle detection sensor, a photoresistor and a decibel meter;
[0072] The second detection unit 12 includes a third integrated sensor group, which is arranged in the living room, bedroom, kitchen and bathroom of the house to perform real-time detection of the movement characteristics of the elderly. The third integrated sensor group includes a depth sensor, a bone tracker, a gyroscope and an accelerometer to perform real-time detection of the elderly's fall characteristic data.
[0073] In this embodiment, the feature detection module 1 realizes comprehensive monitoring of multiple aspects of the guardian through the first detection unit 11 and the second detection unit 12, combined with a medical intelligent physical examination bracelet and a variety of integrated sensors. The medical intelligent physical examination bracelet in the first detection unit 11 can monitor the physiological characteristics and sleep characteristics of the elderly in real time, and provide real-time data, which not only provides a basis for health assessment, but also can timely alarm when an accident or emergency occurs to the elderly. The second integrated sensor group in the first detection unit 11 is used to detect the indoor environment characteristics of the elderly in real time, and provide scientific living environment management suggestions. The third integrated sensor group in the second detection unit 12 performs real-time detection of the movement characteristics and fall characteristics of the elderly, and realizes timely identification of the movement status of the elderly, especially for emergency situations such as falls, and realizes rapid response and rescue. Through multiple sensors and equipment, the system can collect the elderly's information in all directions, build a panoramic health file for the elderly, and provide more comprehensive data support for medical treatment, nursing and prevention.
[0074] Example 3
[0075] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the feature extraction module 2 includes a first extraction unit 21 and a second extraction unit 22;
[0076] The first extraction unit 21 is used to aggregate the detected comprehensive body feature data to generate a first data set, and extract the first data set;
[0077] The first data set includes a physiological characteristic data set, a sleep characteristic data set and an indoor environment characteristic data set;
[0078] The physiological characteristic data set includes heart rate Sxl, respiratory rate Shx, blood pressure Sxy, body temperature Stw and blood oxygen saturation Sbh;
[0079] The sleep feature dataset includes the sleeping time Mrs, waking time Mxl, deep sleep time Mss, light sleep time Mqs and waking times Mcs;
[0080] The indoor environment characteristic dataset includes temperature Nwd, humidity Nsd, particle concentration Nkl, noise decibel Nfb and light intensity Ngz;
[0081] The second extraction unit 22 is used to generate a second data set after summarizing the detected fall feature data, and extract the second data set, where the second data set includes the fall feature data set;
[0082] The fall feature dataset includes vertical acceleration Dcz, body tilt angle Dqx, body target height Dmb, center of gravity offset Dpy and body curvature Dql.
[0083] In this embodiment, the feature extraction module 2 comprehensively extracts the comprehensive body feature data and fall feature data through the first extraction unit 21 and the second extraction unit 22, and generates the first data set and the second data set by parallel classification and aggregation. The first extraction unit 21 is responsible for aggregating and extracting the physiological characteristics, sleep characteristics and indoor environment characteristics to form the first data set, which provides a basis for comprehensively evaluating the health status of the guardian. The second extraction unit 22 is responsible for aggregating and extracting the fall feature data to form detailed fall feature information of the second data set, which provides accurate data support for the system to accurately judge and quickly respond to the fall of the elderly. The first data set and the second data set are classified according to different dimensions such as physiological characteristics, sleep characteristics, indoor environment characteristics and fall characteristics, making the data more orderly and easy to manage, and also providing a clear data basis for subsequent analysis and application. The formation of the first data set and the second data set provides a sufficient data basis for the calculation of the comprehensive body feature coefficient of the integrated processing module, which helps the system to make a more comprehensive and accurate assessment of the overall status of the guardian.
[0084] Example 4
[0085] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the visual monitoring module 3 builds a user visual ,interface through the front-end programming technology, and configures the mobile terminal code through the front-end ,programming technology, and optimizes the visual interface to adapt to mobile ,terminal and fixed terminal devices;
[0086] A ToF camera is set up to obtain the three-dimensional coordinate information and live picture of the room, and then the live picture is embedded into the user visualization interface by front-end programming technology. At the same time, a login mechanism for account and password verification is set for entering the live interface, and the body contour and movement of the elderly detected by the third integrated sensor group are embedded into the live picture through human body detection and tracking algorithms, and the body contour information of the elderly entering the live picture is observed and monitored in real time. At the same time, the API application interface provided by the smart physical examination bracelet manufacturer and the sensor manufacturer is connected in series with the user visualization interface through the Internet of Things, and the detected physiological characteristic data, sleep characteristic data and indoor environment characteristic data of the elderly are transmitted in real time, and presented to the user visualization interface in a digital form.
[0087] In this embodiment, the visual monitoring module 3 constructs a user-friendly visual interface through front-end programming technology, so that the guardian can easily access and understand the health status of the elderly. Both the mobile phone and the fixed-end device can log in to the user visual interface through the account and password verification to realize remote monitoring of the elderly. The three-dimensional coordinate information of the room is obtained through the ToF camera. The visual monitoring module 3 embeds the live picture into the user interface to realize the real-time display of the indoor environment, which helps the guardian to understand the environment of the elderly more intuitively and find abnormal situations in time. The visual monitoring module adopts the login mechanism of account and password verification, which improves the security of the system and ensures that only authorized guardians can access the monitoring data and live pictures of the elderly. Through the human body detection and tracking algorithm, the body contour and movement of the elderly detected by the third integrated sensor group are embedded in the live picture in real time. This real-time monitoring helps the guardian to quickly perceive the activity status of the elderly, especially to provide timely feedback in emergency situations such as falls. Through the Internet of Things technology, the physiological characteristic data, sleep characteristic data and indoor environment characteristic data of the elderly are transmitted in real time and presented in digital form in the user visual interface, which not only facilitates the real-time monitoring of the guardian, but also provides convenience for subsequent data analysis and comprehensive evaluation.
[0088] Example 5
[0089] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the integrated processing module 4 includes a first processing unit 41, a second processing unit 42 and a third associated processing unit 43;
[0090] The first processing unit 41 includes a physiological characteristic processing unit 411, a sleep characteristic processing unit 412 and an indoor environment characteristic processing unit 413;
[0091] The physiological characteristic processing unit 411 is used to perform dimensionless processing on the electrical data set in the first data set, and then analyze and calculate to obtain the physiological characteristic coefficient Smxs;
[0092] The physiological characteristic coefficient Smxs is obtained by the following formula;
[0093]
[0094] The sleep characteristic processing unit 412 is used to perform dimensionless processing on the lightning arrester equipment data set in the first data set, and then analyze and calculate to obtain the sleep characteristic coefficient Smtz;
[0095] The sleep characteristic coefficient Smtz is obtained by the following formula;
[0096]
[0097] The indoor environment characteristic processing unit 413 is used to analyze and calculate the indoor environment characteristic coefficient Snhj after dimensionless processing based on the mechanical abnormality data set in the first data set;
[0098] The indoor environment characteristic coefficient Snhj is obtained by the following formula;
[0099]
[0100] In this embodiment, the physiological characteristic coefficient Smxs is obtained by performing dimensionless processing and analytical calculation on the physiological characteristic data in the first data set, which helps to identify the physiological state of the elderly and provide basic data for subsequent health assessments. The sleep characteristic coefficient Smtz is obtained by processing the sleep characteristic data in the first data set, which helps to monitor the sleep quality and sleep habits of the elderly and promptly discover sleep problems or abnormal conditions. The indoor environment characteristic coefficient Snhj is obtained by processing the indoor environment characteristic data in the first data set, which enables guardians to understand whether the environment in which the elderly are located is comfortable and safe, and to take necessary measures to improve the environment in a timely manner. The operation and analysis of the above processing units help to comprehensively evaluate the health status and living environment of the elderly, provide comprehensive information to guardians, help better manage and care for the health and life of the elderly, and lay the foundation for subsequent intelligent calls.
[0101] Example 6
[0102] This embodiment is explained in Example 1, please refer to Figure 1 Specifically: the second processing unit 42 is used to extract the fall feature data set according to the second data set, and analyze and calculate the fall feature coefficient Sdtz after dimensionless processing;
[0103] The fall characteristic coefficient Sdtz is obtained by the following formula;
[0104]
[0105] In this embodiment, the unit extracts and processes the second data set, i.e., the fall feature data set, and then calculates, which helps to identify the fall of the elderly, so that emergency measures can be taken in time. The extracted fall feature data is dimensionless processed so that the processing result does not depend on the specific data range, which helps to improve the robustness and applicability of the system. Through analysis and calculation, the fall feature coefficient Sdtz is obtained. The fall feature coefficient Sdtz reflects whether the elderly have fallen. As an important reference indicator for evaluating the safety status of the elderly, through this processing unit, the system can more accurately identify the fall of the elderly, issue an alarm in time, and help the guardian to take quick action to ensure the safety of the elderly. This helps to prevent accidents and reduce the potential risks caused by the elderly falling.
[0106] Example 7
[0107] This embodiment is explained in Example 5. Please refer to Figure 1 Specifically, the third correlation processing unit 43 is used to perform dimensionless processing on the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj obtained by the first processing unit 41, and then perform correlation calculation processing to obtain the comprehensive body characteristic coefficient Tzxs;
[0108] The comprehensive body characteristic coefficient Tzxs is obtained by the following formula;
[0109]
[0110] Wherein, a1, a2 and a3 represent the preset proportional coefficients of the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj respectively, and a1+a2≠a3, 0<a1<0.67, 0<a2<0.98, 0<a3<0.71, and the specific values are adjusted and set by the user, and A is the first correction constant.
[0111] In this embodiment, the unit performs dimensionless processing on the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj, and then performs associated calculation processing, so as to more comprehensively consider the comprehensive factors of the elderly's physiological state, sleep conditions and living environment. Through associated analysis and calculation, the comprehensive body characteristic coefficient Tzxs is obtained, which comprehensively reflects the overall state of the elderly, including information on multiple aspects such as physiology, sleep and environment. The user can customize the degree of emphasis on different characteristics by adjusting the preset proportional coefficients a1, a2 and a3 according to actual needs, and provide user-set parameters to make the system more flexible and able to be personalized according to the actual situation of different elderly people. Through this processing unit, the system can comprehensively consider the various information of the elderly and provide users with a more comprehensive and accurate comprehensive body characteristic assessment, which helps guardians better understand the overall condition of the elderly under guardianship, discover potential health problems in a timely manner, and thus take effective care and intervention measures.
[0112] Example 8
[0113] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the intelligent call module 5 includes a first call unit 51 and a second call unit 52;
[0114] The first calling unit 51 is used to preset a first calling threshold Z and a fall characteristic coefficient Sdtz for preliminary evaluation, and generate a relevant calling scheme according to relevant evaluation results. The specific evaluation scheme is as follows;
[0115] When the fall characteristic coefficient Sdtz> the first call threshold Z, it means that the elderly person meets the fall characteristics in the live picture of the current user visualization interface. At this time, the system automatically sends an intelligent voice call to the elderly person to determine whether the elderly person is conscious after falling. At the same time, the voice call is repeated three times, with an interval of 10 seconds between each call. If the elderly person does not respond, the system automatically calls the rescue team, generates an early warning message through the user visualization interface, and converts it into an intelligent voice call to the remote mobile and fixed end guardians;
[0116] When the fall feature coefficient Sdtz≤the first call threshold Z, it means that the fall feature of the elderly is not identified in the live picture of the user visualization interface. At this time, the second call mechanism is implemented to detect the vital signs of the elderly in real time.
[0117] The second calling unit 52 is triggered by the second calling mechanism of the first calling unit 51, and compares and evaluates the obtained comprehensive body characteristic coefficient Tzxs obtained by the third associated processing unit 43 through the preset second calling threshold V, and generates relevant evaluation results. The specific evaluation scheme is as follows;
[0118] When the comprehensive body characteristic coefficient Tzxs> the second call threshold V, it means that the current indoor environment of the elderly is abnormal. At this time, the monitoring equipment will periodically call the elderly to open windows for ventilation and dehumidification according to the changes in the indoor environment, prompting the elderly to improve their living environment;
[0119] When the comprehensive body characteristic coefficient Tzxs≤the second call threshold V, it indicates that the current vital signs of the elderly are abnormal. At this time, the physiological characteristics and sleep characteristics of the elderly will be analyzed, and the guardian will be called to conduct a comprehensive physical examination of the elderly. At the same time, a regular intelligent voice call will be made to the elderly to arrange their work and rest time reasonably.
[0120] In this embodiment, the first calling unit 51 compares and evaluates the fall characteristic coefficient Sdtz with the preset first calling threshold Z. Once the fall characteristic of the elderly is detected, the system will automatically send an intelligent voice call to the elderly. This helps to timely discover the elderly's fall, make an emergency call and judge the elderly's consciousness. If the elderly do not respond, the system will make a voice loop call, with an interval of 10 seconds between each call. If the elderly still do not respond, the system will automatically call the rescue team. This multi-level calling mechanism improves the timely response to emergency situations, generates early warning information through the user visual interface, and converts it into an intelligent voice call to the guardians of the remote mobile terminal and the fixed terminal to ensure that the guardians can understand the elderly's situation in time. The second calling mechanism compares and evaluates the preset second calling threshold V with the comprehensive body characteristic coefficient Tzxs to determine whether there is an abnormality in the elderly's living environment. The system will regularly call the elderly to open the window for ventilation and dehumidification to remind the elderly to improve their living environment, which helps to prevent health problems related to the environment. At the same time, the system will analyze the physiological characteristics and sleep characteristics of the elderly, call the guardian to conduct a comprehensive physical examination of the elderly, and remind the elderly to arrange their work and rest time reasonably, which helps to fully understand the health status and living habits of the elderly and implement targeted care and intervention.
[0121] Specific example:
[0122] Physiological characteristic coefficient Smxs:
[0123]
[0124] Heart rate Sxl: 9.27, respiratory rate Shx: 5.62, blood pressure Sxy: 3.48, body temperature Stw: 8.15, blood oxygen saturation Sbh: 6.89;
[0125] Sleep characteristic coefficient Smtz:
[0126]
[0127] Time to fall asleep Mrs: 4.27, time to wake up Mxl: 1.93, deep sleep time Mss: 3.56, light sleep time Mqs: 9.41, number of wake-ups Mcs: 6.78;
[0128] Indoor environment characteristic coefficient Snhj:
[0129]
[0130] Temperature Nwd: 3.92, humidity Nsd: 8.73, particle concentration Nkl: 7.33, noise decibel Nfb: 5.48, light intensity Ngz: 2.38;
[0131] Comprehensive body characteristic coefficient Tzxs:
[0132]
[0133] Proportional coefficient: a1=0.16, a2=0.17, a3=0.12, first correction constant A: 0.05;
[0134] Fall characteristic coefficient Sdtz:
[0135]
[0136] Vertical acceleration Dcz: 4.91, body tilt angle Dqx: 9.12, body target height Dmb: 6.24, center of gravity offset Dpy: 8.01, body curvature Dql: 7.96;
[0137] Among them, the calculation results are rounded to two decimal places;
[0138] At this time, the first call threshold Z is set to 1. At this time, the fall feature coefficient Sdtz> the first call threshold Z, which means that in the live picture of the current user visualization interface, the elderly person is identified as meeting the fall features. At this time, the system automatically sends an intelligent voice call to the elderly person to determine the elderly person's consciousness after the fall. At the same time, the voice call is looped 3 times, with an interval of 10 seconds between each call. If the elderly person does not respond, the system automatically calls the rescue team, and generates early warning information through the user visualization interface, and converts it into an intelligent voice call to the remote mobile and fixed guardians.
[0139] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A visual intelligent calling system for home-based elderly care, characterized by: It comprises a feature detection module (1), a feature extraction module (2), a visual monitoring module (3), an integrated processing module (4) and an intelligent call module (5); The feature detection module (1) is used to wear a smart physical examination bracelet on the hand of the ward, and install a detection device to perform real-time detection of the ward's comprehensive body feature data and fall data, and then the feature extraction module (2) classifies and summarizes the detected comprehensive body feature data and fall data to generate a first data set and a second data set; The feature detection module (1) comprises a first detection unit (11) and a second detection unit (12); The first detection unit (11) comprises a first detection device and a second integrated sensor group, which are used to detect comprehensive body feature data; The first detection device includes a medical intelligent physical examination bracelet, which is used to be worn by elderly people living at home to perform real-time detection of the elderly's physiological characteristics and sleep characteristics; The second integrated sensor group includes a temperature sensor, a humidity sensor, a particle detection sensor, a photoresistor and a decibel meter; The second detection unit (12) comprises a third integrated sensor group, the third integrated sensor group comprises a depth sensor, a bone tracker, a gyroscope and an accelerometer, and collects body contour data and movement data of the elderly in real time; The feature extraction module (2) comprises a first extraction unit (21) and a second extraction unit (22); The first extraction unit (21) is used to aggregate the detected comprehensive body feature data to generate a first data set, and extract the first data set; The first data set includes a physiological characteristic data set, a sleep characteristic data set and an indoor environment characteristic data set; The physiological characteristic data set includes heart rate Sxl, respiratory rate Shx, blood pressure Sxy, body temperature Stw and blood oxygen saturation Sbh; The sleep characteristic data set includes the sleeping time Mrs, the waking time Mxl, the deep sleep time Mss, the light sleep time Mqs and the waking times Mcs; The indoor environment characteristic data set includes temperature Nwd, humidity Nsd, particle concentration Nkl, noise decibel Nfb and light intensity Ngz; The second extraction unit (22) is used to aggregate the detected fall feature data to generate a second data set, and extract the second data set, wherein the second data set includes a fall feature data set; The fall feature data set includes vertical acceleration Dcz, body tilt angle Dqx, body target height Dmb, center of gravity offset Dpy and body curvature Dql; The visual monitoring module (3) is used to set the monitoring device to connect to the remote mobile client, and to connect the smart physical examination bracelet and the detection device in series to generate a visual monitoring system; The visual monitoring module (3) constructs a user visual interface through front-end programming technology, and configures the mobile terminal code through front-end programming technology to optimize the visual interface to adapt to mobile phones and fixed-end devices; A ToF camera is set to obtain indoor three-dimensional coordinate information and indoor live images, and then the live images are embedded into the user visualization interface by front-end programming technology. At the same time, a login mechanism for account and password verification is set for entering the live interface. Through human body detection and tracking algorithms, the contour data and motion data of the elderly detected by the third integrated sensor group are embedded into the live image, and the body contour information of the elderly entering the live image is observed and monitored in real time. At the same time, the API application interface provided by the smart physical examination bracelet manufacturer and the sensor manufacturer is connected in series with the user visualization interface through the Internet of Things, and the physiological characteristic data, sleep characteristic data and indoor environment characteristic data of the elderly detected are transmitted in real time, and presented to the user visualization interface in a digital form; The integrated processing module (4) comprises a first processing unit (41), a second processing unit (42) and a third associated processing unit (43), wherein the first processing unit (41) is used to extract the associated data set based on the first data set, perform dimensionless processing, and then perform analysis and calculation to obtain the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj; The second processing unit (42) extracts the fall characteristic data set based on the second data set, performs dimensionless processing, and then performs analysis and calculation to obtain the fall characteristic coefficient Sdtz; the third correlation processing unit (43) then performs correlation analysis and calculation on the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz, and the indoor environment characteristic coefficient Snhj to obtain the comprehensive body posture characteristic coefficient Tzxs; The first processing unit (41) includes a physiological characteristic processing unit (411), a sleep characteristic processing unit (412) and an indoor environment characteristic processing unit (413); The physiological characteristic processing unit (411) is used to perform dimensionless processing on the physiological characteristic data set in the first data set, and then analyze and calculate to obtain the physiological characteristic coefficient Smxs; The physiological characteristic coefficient Smxs is obtained by the following formula: The third correlation processing unit (43) is used to perform dimensionless processing on the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj obtained by the first processing unit (41), and then perform correlation calculation processing to obtain a comprehensive body characteristic coefficient Tzxs; The comprehensive body characteristic coefficient Tzxs is obtained by the following formula: Wherein, a1, a2 and a3 represent the preset proportional coefficients of the physiological characteristic coefficient Smxs, the sleep characteristic coefficient Smtz and the indoor environment characteristic coefficient Snhj respectively, and their specific values are adjusted and set by the user, and A is the first correction constant; The intelligent call module (5) is used to preset a first call threshold value Z and a fall characteristic coefficient Sdtz for preliminary comparative evaluation, generate relevant evaluation results, and generate a corresponding call strategy based on the evaluation results. It is also used to preset a second call threshold value V and obtain a comprehensive body characteristic coefficient Tzxs for comparative evaluation, and generate a corresponding voice prompt call based on the evaluation results.
2. According to claim 1, a visual intelligent calling system for home-based elderly care is characterized by: The sleep characteristic processing unit (412) is used to perform dimensionless processing on the sleep characteristic data set in the first data set, and then analyze and calculate to obtain the sleep characteristic coefficient Smtz; The sleep characteristic coefficient Smtz is obtained by the following formula: The indoor environment characteristic processing unit (413) is used to perform dimensionless processing on the indoor environment characteristic data set in the first data set, and then analyze and calculate to obtain the indoor environment characteristic coefficient Snhj; The indoor environment characteristic coefficient Snhj is obtained by the following formula:
3. According to claim 1, a visual intelligent calling system for home-based elderly care is characterized by: The second processing unit (42) is used to extract a fall feature data set based on the second data set, and analyze and calculate to obtain a fall feature coefficient Sdtz after dimensionless processing; The fall characteristic coefficient Sdtz is obtained by the following formula:
4. According to claim 1, a visual intelligent calling system for home-based elderly care is characterized by: The intelligent call module (5) comprises a first call unit (51) and a second call unit (52); The first calling unit (51) is used to preset a first calling threshold Z and a fall characteristic coefficient Sdtz for preliminary evaluation, and generate a relevant calling plan according to the relevant evaluation results. The specific evaluation plan is as follows; When the fall characteristic coefficient Sdtz> the first call threshold Z, it means that the elderly person meets the fall characteristics in the live picture of the current user visualization interface. At this time, the system automatically sends an intelligent voice call to the elderly person to determine whether the elderly person is conscious after falling. At the same time, the voice call is repeated three times, with an interval of 10 seconds between each call. If the elderly person does not respond, the system automatically calls the rescue team, generates an early warning message through the user visualization interface, and converts it into an intelligent voice call to the remote mobile and fixed end guardians; When the fall feature coefficient Sdtz≤the first call threshold Z, it means that the fall feature of the elderly is not identified in the live picture of the user visualization interface. At this time, the second call mechanism is implemented to detect the vital signs of the elderly in real time.
5. According to claim 4, a visual intelligent calling system for home-based elderly care is characterized by: The second calling unit (52) is triggered by the second calling mechanism of the first calling unit (51), compares and evaluates the comprehensive body characteristic coefficient Tzxs obtained by the third associated processing unit (43) through the preset second calling threshold V, and generates relevant evaluation results. The specific evaluation scheme is as follows; When the comprehensive body characteristic coefficient Tzxs> the second call threshold V, it means that the current indoor environment of the elderly is abnormal. At this time, the monitoring equipment will periodically call the elderly to open windows for ventilation and dehumidification according to the changes in the indoor environment, prompting the elderly to improve their living environment; When the comprehensive body characteristic coefficient Tzxs≤the second call threshold V, it indicates that the current vital signs of the elderly are abnormal. At this time, the physiological characteristics and sleep characteristics of the elderly will be analyzed, and the guardian will be called to conduct a comprehensive physical examination of the elderly. At the same time, a regular intelligent voice call will be made to the elderly to arrange their work and rest time reasonably.
