An old person abnormal state monitoring and alarming method for nursing bed in nursing home

Abstract

This invention relates to the field of elderly safety monitoring technology, and more particularly to a method for monitoring and alarming abnormal states of elderly people using nursing home beds. The method includes: real-time acquisition of the elderly person's body pressure distribution data, heart rate and respiratory data, and bed posture data; identifying the elderly person's current behavioral state as either resting or moving based on the body pressure distribution data and bed posture data; calculating a heart rate deviation index and a respiratory abnormality index based on the heart rate and respiratory data, and determining whether the elderly person's vital signs are abnormal based on these indices; when the elderly person's vital signs are normal, determining whether the elderly person's behavioral state is abnormal based on the number of body movements per unit time and the maximum resting time during the day, and determining the alarm level based on the body movement impact coefficient and rhythm disorder coefficient. This invention improves the accuracy of monitoring abnormal states of the elderly and the targeted nature of alarms.

Description

Technical Field

[0001] This invention relates to the field of elderly safety monitoring technology, and in particular to a method for monitoring and alarming abnormal conditions of elderly people in nursing home beds. Background Technology

[0002] With the accelerating aging of the global population, the care pressure on elderly care institutions is increasing daily. Due to declining physiological functions, the elderly often experience slow movement, decreased balance, and cognitive impairment. At night or when unattended, they are highly susceptible to falls, sudden illnesses (such as cardiovascular accidents), and even prolonged absences from bed. Failure to detect and address these issues promptly can lead to serious consequences, even endangering their lives.

[0003] Currently, traditional nursing homes mainly rely on regular manual inspections or family members accompanying residents to monitor the elderly's condition. However, this method has many shortcomings: First, it is costly and inefficient, especially at night or during shift changes, where blind spots in monitoring are likely to occur; second, when elderly people experience sudden abnormalities (such as unconscious falls or respiratory arrest), they often cannot actively call for help, leading to missed opportunities for optimal rescue; and third, although some nursing beds are equipped with simple handheld call buttons or bedside alarms, these require active operation by the elderly, limiting their applicability.

[0004] Existing technologies include some health monitoring methods based on contact sensors (such as wristbands and chest straps). However, elderly people often have poor compliance with wearable devices, easily refusing to use them due to discomfort, forgetfulness, or resistance. Furthermore, frequent charging and loosening of the devices also affect the continuity and reliability of monitoring. In addition, some solutions can only detect the state of being out of bed, lacking the ability to recognize complex situations such as abnormal posture (e.g., partial fall from bed) and sudden changes in vital signs, making it difficult to meet the actual care needs of nursing homes.

[0005] Therefore, there is an urgent need for a non-contact, all-weather, high-precision method for abnormal status monitoring and graded alarm that can be integrated into the nursing bed system without changing the elderly’s living habits or requiring them to wear masks, so as to improve the level of smart care in elderly care institutions, reduce nursing risks, and protect the life safety and quality of life of the elderly. Summary of the Invention

[0006] To address this, the present invention provides a method for monitoring and alarming abnormal states of the elderly in nursing home beds. This method overcomes the problems in existing technologies that fail to consider the spatiotemporal correlation of multi-source sensor data and the dynamic evolution of the elderly’s behavior, resulting in an inability to effectively distinguish between normal activities and real abnormal events. Consequently, the alarm mechanism may frequently issue false alarms due to minor disturbances or delay alarms due to a lack of predictive capabilities.

[0007] To achieve the above objectives, the present invention provides a method for monitoring and alarming abnormal conditions of elderly people in nursing home beds, characterized in that it includes: Step S1: Real-time data collection of the elderly’s body pressure distribution, heart rate and respiratory data and bed posture data is carried out by deploying pressure sensor array, non-contact vital sign sensor and bed motion sensor on the nursing bed. Step S2: Based on the body pressure distribution data and bed posture data, identify whether the elderly person's current behavioral state is a resting state or a moving state. The moving state includes turning over, sitting up, and getting out of bed. Step S3: Calculate the heart rate deviation index and respiratory abnormality index based on the heart rate and respiratory data, and determine whether the elderly person's vital signs are abnormal based on the heart rate deviation index and respiratory abnormality index. In the case of Level I abnormality, determine whether to trigger the vital signs abnormality alarm based on the postural state, the duration of the abnormality, or the degree of abnormal body movement matching. In the case of Level II abnormality, the pressure distribution ratio and pressure change rate in the preset bed edge area are calculated based on the body pressure distribution data to determine whether the elderly person is about to get out of bed, and to trigger a bed exit warning when the elderly person is about to get out of bed. Step S4: When the elderly person's vital signs are not abnormal, determine whether the elderly person's behavior is abnormal based on the number of body movements per unit time and the maximum resting time during the day, and determine the alarm level based on the body movement impact coefficient and rhythm disorder coefficient. The alarm level includes a level 1 alarm, a level 2 alarm, and a level 3 alarm.

[0008] Furthermore, the body pressure distribution data includes real-time pressure values ​​collected by pressure sensor arrays distributed in various regions of the bed, the sum of pressure values ​​in each region, the coordinates of the pressure center, and the rate of change of pressure values ​​in each region over time. The heart rate and respiratory data include real-time heart rate values ​​and real-time respiratory rate values; The bed posture data includes the lifting angle of the upper body movable frame of the bed, as well as the vibration frequency and vibration amplitude of the bed frame.

[0009] Furthermore, in step S2, the process of identifying the elderly person's current behavioral state based on the body pressure distribution data and bed posture data is as follows: Calculate the coordinates of the pressure center of the body pressure distribution, and determine the elderly person's center of gravity distribution based on the real-time position and movement speed of the pressure center; Determine whether the bed is in a raised or lowered state based on the angle at which the upper body movable frame of the bed is raised; Based on the changing patterns of pressure values ​​in different regions of the body pressure distribution, combined with the movement trajectory of the pressure center and changes in bed posture, the current behavioral state of the elderly is classified into lying down, turning over, sitting up, or getting out of bed.

[0010] Furthermore, in step S3, the process of determining whether the elderly person's vital signs are abnormal based on the heart rate deviation index and the respiratory abnormality index is as follows: Calculate the heart rate deviation index and respiratory abnormality index based on the heart rate and respiratory data; If the heart rate deviation index is less than the first preset deviation index and the respiratory abnormality index is less than the first preset abnormality index, then the elderly person's vital signs are determined to be normal. If the heart rate deviation index is greater than or equal to the first preset deviation index and less than the second preset deviation index, or if the respiratory abnormality index is greater than or equal to the first preset abnormality index and less than the second preset abnormality index, then the elderly person's vital signs are judged to be level two abnormal. If the heart rate deviation index is greater than or equal to the second preset deviation index, or the respiratory abnormality index is greater than or equal to the second preset abnormality index, the elderly person's vital signs are judged to be level one abnormality. The severity of the first-level anomaly is greater than that of the second-level anomaly.

[0011] Furthermore, in the case of a Level 1 abnormality, if the posture is a resting state, the duration of the abnormality determines whether to trigger a vital signs abnormality alarm. If the heart rate deviation index is greater than the second preset deviation index and the duration of the heart rate deviation index exceeding the second preset deviation index is greater than the first preset duration, then it is determined that an abnormal vital signs alarm is triggered. If the respiratory abnormality index is greater than the second preset abnormality index and the duration of the respiratory abnormality index exceeding the second preset abnormality index is greater than the second preset duration, then it is determined that a vital signs abnormality alarm is triggered. If the posture state is a body movement state, then the abnormal vital signs alarm is triggered based on the condition that the abnormal body movement matching degree is less than the preset matching degree. The abnormal body movement matching degree is the ratio of the duration of body movement during the period of abnormal signs to the total duration of abnormal signs.

[0012] Furthermore, under the condition of a level 2 abnormality, based on the condition that the pressure distribution ratio is greater than the first preset ratio and the pressure change rate is greater than the preset rate, it is determined that the elderly person is about to get out of bed and an early warning for getting out of bed is triggered. The pressure distribution ratio is the ratio of the pressure value within the preset bed edge area to the sum of the pressure values ​​in all areas.

[0013] Furthermore, in step S4, based on the condition that the number of body movements per unit time is greater than a preset number or the maximum daytime resting time is greater than a third preset time, the elderly person's behavioral state is judged to be abnormal, and the alarm level is determined based on the body movement impact coefficient and the rhythm disorder coefficient.

[0014] Furthermore, the process for determining the alarm level is as follows: The body motion impact coefficient is calculated based on the vibration amplitude and duration of the bed frame, and the rhythm disorder coefficient is calculated based on the temporal changes of the number of body motions per unit time and the coordinates of the pressure center. The body dynamic impact coefficient is compared with the first preset impact threshold and the second preset impact threshold, and the rhythm disorder coefficient is compared with the first preset disorder threshold and the second preset disorder threshold. If the body dynamic impact coefficient is greater than or equal to the first preset impact threshold and less than the second preset impact threshold, and the rhythm disorder coefficient is greater than or equal to the first preset disorder threshold and less than the second preset disorder threshold, then the alarm level is determined to be level three. If the body motion impact coefficient is greater than or equal to the second preset impact threshold and the rhythm disorder coefficient is less than the second preset disorder threshold, or if the body motion impact coefficient is less than the second preset impact threshold and the rhythm disorder coefficient is greater than or equal to the second preset disorder threshold, then the alarm level is determined to be level two. If the body dynamic impact coefficient is greater than or equal to the second preset impact threshold, and the rhythm disorder coefficient is greater than or equal to the second preset disorder threshold, then the alarm level is determined to be Level 1.

[0015] Furthermore, the Level 1 alarm is an emergency alarm, used to alert the elderly person to severe agitation or a high risk of falling out of bed, requiring immediate attention; The level 2 alarm is a warning alarm, used to indicate that the elderly person's behavioral rhythm is significantly abnormal and needs to be checked. The third-level alarm is a notification alarm, used to indicate that the elderly person's behavior is slightly abnormal, and only observation is recorded.

[0016] Furthermore, step S4 also includes: If an elderly person is detected to be out of bed during a preset period at night, an out-of-bed timer will be started. If the duration of continuous out-of-bed activity exceeds the fourth preset duration, a nighttime out-of-bed timeout alarm will be triggered.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention utilizes a pressure sensor array, a non-contact vital sign sensor, and a bed motion sensor deployed on a nursing bed to collect real-time data on body pressure distribution, heart rate and respiration, and bed posture. Based on the spatiotemporal correlation of multi-source data, it identifies the elderly person's current behavioral state, distinguishing between a resting state and a state of movement. In existing technologies, alarm mechanisms often rely on single sensor information, failing to differentiate between normal activities and genuine abnormal events, leading to frequent false alarms caused by everyday movements such as turning over or sitting up. This invention integrates body pressure distribution and bed posture data, introducing posture as a weighting factor in the assessment of abnormal vital signs. When a level-one abnormality occurs while the person is in a state of movement, the alarm is triggered based on the degree of matching of the abnormal movement, avoiding false triggers caused by fluctuations in heart rate and respiration due to brief movements.

[0018] 2. This invention achieves tiered assessment of abnormal vital signs by setting two threshold levels for heart rate deviation index and respiratory abnormality index, and combining the duration of abnormality with postural status for comprehensive judgment. In existing technologies, alarms are triggered solely based on whether heart rate or respiratory values ​​exceed limits, failing to distinguish between transient fluctuations and sustained abnormalities, easily leading to missed or delayed alarms. This invention, in cases of Level 1 abnormality and a resting state, requires the duration of the heart rate deviation index or respiratory abnormality index exceeding the corresponding threshold to trigger an alarm only after a preset duration, eliminating false alarms caused by instantaneous sensor noise or brief discomfort in the elderly. Simultaneously, in cases of Level 1 abnormality and physical activity, the invention uses abnormal physical activity matching to determine whether the abnormal vital signs are related to physical activity, improving alarm accuracy.

[0019] 3. This invention determines whether an elderly person is about to get out of bed by calculating the pressure distribution ratio and pressure change rate within a preset bedside area and triggers an exit warning. In existing technologies, exit alarms are mostly triggered after the elderly person has completely left the bed, lacking predictive capability. This prevents caregivers from intervening in advance and increases the risk of falls due to instability when getting out of bed. In the case of a level-two abnormal situation, this invention issues a warning when the elderly person is about to get out of bed, based on the condition that the pressure distribution ratio is greater than a first preset ratio and the pressure change rate is greater than a preset rate, providing caregivers with a window of opportunity for early response.

[0020] 4. This invention, when the elderly person's vital signs are normal, determines whether their behavioral state is abnormal based on the number of body movements per unit time and the maximum daytime resting time, and determines the alarm level based on the body movement impact coefficient and rhythm disorder coefficient. In existing technologies, behavioral abnormality monitoring often uses a single threshold, which cannot quantify the intensity of body movements and the degree of rhythm disorder. This invention calculates the body movement impact coefficient by measuring the vibration frequency and amplitude of the bed frame, reflecting the intensity of the elderly person's body movements; it calculates the rhythm disorder coefficient by measuring the number of body movements per unit time and the temporal changes in the pressure center coordinates, reflecting the stability of the elderly person's behavioral rhythm; and it sets two threshold levels to classify the alarm levels into Level 1, Level 2, and Level 3 alarms, achieving a graded assessment of the severity of behavioral abnormalities.

[0021] 5. This invention, within a preset nighttime period, activates an out-of-bed timer if it detects an elderly person being out of bed. When the continuous out-of-bed time exceeds a fourth preset duration, a nighttime out-of-bed overtime alarm is triggered. Existing technologies lack a time dimension in nighttime out-of-bed monitoring, making it difficult to distinguish between normal toilet use and abnormal prolonged absences, leading to reduced response efficiency for caregivers. This invention, by determining the nighttime period and accumulating out-of-bed time, triggers an alarm after the elderly person exceeds the time limit, avoiding over-response for short-term out-of-bed situations while promptly detecting abnormal situations such as prolonged absences. Attached Figure Description

[0022] Figure 1 This is a flowchart of a method for monitoring and alarming abnormal conditions of elderly people in nursing home beds according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating how to determine whether an elderly person's vital signs are abnormal, as described in an embodiment of the present invention. Figure 3 This is a flowchart for determining the alarm level in an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0024] Those skilled in the art will understand that the method for determining the above-mentioned parameters for a single item in this invention can be as follows: selecting the value with the highest proportion based on the data distribution as the preset standard parameter; using weighted summation to use the obtained value as the preset standard parameter; substituting each historical data into a specific formula and using the value obtained by the formula as the preset standard parameter; or other selection methods, as long as the present invention can clearly define different specific situations in the single item determination process through the obtained values.

[0025] Please see Figure 1 As shown, the present invention provides a method for monitoring and alarming abnormal conditions of elderly people in nursing home beds, comprising: Step S1: Real-time data collection of the elderly’s body pressure distribution, heart rate and respiratory data and bed posture data is carried out by deploying pressure sensor array, non-contact vital sign sensor and bed motion sensor on the nursing bed. Step S2: Based on the body pressure distribution data and bed posture data, identify whether the elderly person's current behavioral state is a resting state or a moving state. The moving state includes turning over, sitting up, and getting out of bed. Step S3: Calculate the heart rate deviation index and respiratory abnormality index based on the heart rate and respiratory data, and determine whether the elderly person's vital signs are abnormal based on the heart rate deviation index and respiratory abnormality index. In the case of Level I abnormality, determine whether to trigger the vital signs abnormality alarm based on the postural state, the duration of the abnormality, or the degree of abnormal body movement matching. In the case of Level II abnormality, the pressure distribution ratio and pressure change rate in the preset bed edge area are calculated based on the body pressure distribution data to determine whether the elderly person is about to get out of bed, and to trigger a bed exit warning when the elderly person is about to get out of bed. Step S4: When the elderly person's vital signs are not abnormal, determine whether the elderly person's behavior is abnormal based on the number of body movements per unit time and the maximum resting time during the day, and determine the alarm level based on the body movement impact coefficient and rhythm disorder coefficient. The alarm level includes a level 1 alarm, a level 2 alarm, and a level 3 alarm.

[0026] Specifically, in step S1, the pressure sensor array on the nursing bed is arranged in a matrix pattern, distributed across the entire surface of the bed, with a spacing of 5cm to 10cm (preferably 10cm). For the back area, buttock area, and preset bed edge area, the spacing is increased to 2cm to 5cm (preferably 3cm). The back area and buttock area are pre-defined based on statistical results of a large number of human lying postures. The preset bed edge area is a longitudinal strip area (preferably 20%) that occupies 15% to 25% of the width of the bed from the left and right edges towards the center of the bed. Each pressure sensor unit uses a thin-film pressure sensor, which is laid under the mattress or integrated inside the mattress. The sensor array has a sampling frequency of 10Hz to 50Hz (preferably 20Hz in this invention).

[0027] Specifically, the non-contact vital signs sensor uses a microwave radar sensor or a fiber optic sensor, which is installed at the head of the nursing bed or above the bed frame, maintaining a non-contact distance of 10 to 50 centimeters from the elderly person's body. It extracts real-time heart rate and real-time respiratory rate values ​​by emitting low-power microwave signals and receiving micro-motion echo signals caused by human chest and abdominal breathing and heartbeat.

[0028] Specifically, the bed motion sensor is a triaxial accelerometer, which is installed on the upper body movable frame and the bed chassis of the nursing bed. The triaxial accelerometer installed on the upper body movable frame is used to detect the lifting angle of the upper body movable frame, and the triaxial accelerometer installed on the bed chassis is used to detect the vibration frequency and vibration amplitude of the bed frame.

[0029] Specifically, the body pressure distribution data includes real-time pressure values ​​collected by pressure sensor arrays distributed in various areas of the bed, the sum of pressure values ​​in each area, the coordinates of the pressure center, and the rate of change of pressure values ​​in each area over time. The heart rate and respiratory data include real-time heart rate values ​​and real-time respiratory rate values; The bed posture data includes the lifting angle of the upper body movable frame of the bed, as well as the vibration frequency and vibration amplitude of the bed frame.

[0030] Specifically, in step S2, the process of identifying the elderly person's current behavioral state based on the body pressure distribution data and bed posture data is as follows: Calculate the coordinates of the pressure center of the body pressure distribution, and determine the elderly person's center of gravity distribution based on the real-time position and movement speed of the pressure center; Determine whether the bed is in a raised or lowered state based on the angle at which the upper body movable frame of the bed is raised; Based on the changing patterns of pressure values ​​in different regions of the body pressure distribution, combined with the movement trajectory of the pressure center and changes in bed posture, the current behavioral state of the elderly is classified into the resting state, the turning-over state, the sitting-up state, or the bed-out state. The criteria for determining the resting state are: the displacement amplitude of the pressure center coordinate within a preset time period is less than the first preset displacement threshold, the change in the pressure distribution range is less than the preset range change threshold, and the change in the lifting angle of the upper body movement frame of the bed is less than the first preset angle threshold. The criteria for determining the turning state are: the center of pressure moves from one side of the bed width to the other side within a preset time period, and the moving speed is greater than the preset turning speed threshold. The conditions for determining the sitting-up state are: the rate of decrease of the pressure value in the back area is greater than the first preset rate threshold, the rate of increase of the pressure value in the buttock area is greater than the second preset rate threshold, and the lifting angle of the upper body movement frame of the bed is greater than the preset sitting-up angle threshold. The criteria for determining the bed leave status are: the sum of the pressure values ​​in all areas is less than the preset bed leave pressure threshold, and the duration is greater than the preset bed leave confirmation time. In this embodiment of the invention, the preferred values ​​for each threshold are as follows: In the determination of the resting state, the preset duration for calculating the displacement of the pressure center is 5s, the first preset displacement threshold is 3cm, the preset range change threshold corresponding to the change in pressure distribution range is 10%, and the first preset angle threshold is 5°; In the determination of the turning state, the preset duration for judging the lateral movement of the pressure center is 3s, and the preset turning speed threshold is 5cm / s; In the determination of the sitting-up state, the first preset rate threshold is 50Pa / s, the second preset rate threshold is 80Pa / s, and the preset sitting-up angle threshold is 30°; In the determination of the leaving-bed state, the preset leaving-bed pressure threshold is 50N, and the preset leaving-bed confirmation duration is 5s.

[0031] Please see Figure 2 As shown, it is a flowchart for determining whether an elderly person's vital signs are abnormal according to an embodiment of the present invention; Specifically, in step S3, the process of determining whether the elderly person's vital signs are abnormal based on the heart rate deviation index and respiratory abnormality index is as follows: Based on the heart rate and respiratory data, a heart rate deviation index and a respiratory abnormality index are calculated, where the heart rate deviation index = |current heart rate Individual baseline heart rate | / Individual baseline heart rate is determined based on the elderly person's historical heart rate data in the past 3 days while in a resting state. For elderly people using it for the first time, the group reference heart rate range (e.g., 60–70 beats / minute) of the same age and in the same resting state is used as the baseline, and it is dynamically updated after collecting sufficient individual data; Abnormal Respiratory Index = Current Respiratory Rate The preset median respiratory rate is calculated as: preset median respiratory rate + total duration of apnea / preset apnea threshold. In this embodiment of the invention, the preset median respiratory rate is 20 breaths / minute, and the preset apnea threshold is 20 seconds. If the heart rate deviation index is less than the first preset deviation index and the respiratory abnormality index is less than the first preset abnormality index, then the elderly person's vital signs are determined to be normal. If the heart rate deviation index is greater than or equal to the first preset deviation index and less than the second preset deviation index, or if the respiratory abnormality index is greater than or equal to the first preset abnormality index and less than the second preset abnormality index, then the elderly person's vital signs are judged to be level two abnormal. If the heart rate deviation index is greater than or equal to the second preset deviation index, or the respiratory abnormality index is greater than or equal to the second preset abnormality index, the elderly person's vital signs are judged to be level one abnormality. The severity of the first-level anomaly is greater than that of the second-level anomaly; In this embodiment of the invention, the first preset deviation index is 0.2, the second preset deviation index is 0.4, the first preset abnormality index is 0.5, and the second preset abnormality index is 1.0.

[0032] Specifically, in a Level 1 abnormal situation, if the posture is a resting state, the duration of the abnormality determines whether to trigger a vital signs abnormality alarm. If the heart rate deviation index is greater than the second preset deviation index and the duration of the heart rate deviation index exceeding the second preset deviation index is greater than the first preset duration, then it is determined that an abnormal vital signs alarm is triggered. If the respiratory abnormality index is greater than the second preset abnormality index and the duration of the respiratory abnormality index exceeding the second preset abnormality index is greater than the second preset duration, then it is determined that a vital signs abnormality alarm is triggered. If the posture state is a body movement state, then the abnormal vital signs alarm is triggered based on the condition that the abnormal body movement matching degree is less than the preset matching degree. The abnormal body movement matching degree is the ratio of the duration of body movement during the period of abnormal signs to the total duration of abnormal signs. It can be understood that the abnormal body movement matching degree is used to quantify the degree of overlap between abnormal signs and body movement events in time, so as to determine whether the abnormal signs are physiological reactions caused by body movement activities or pathological abnormalities caused by non-body movement factors. Abnormal body movement matching degree = duration of body movement during the period of abnormal signs / total duration of abnormal signs. In this embodiment of the invention, the first preset duration is 30 seconds, the second preset duration is 20 seconds, and the preset matching degree is 0.5.

[0033] Specifically, under the condition of a level 2 abnormal situation, based on the condition that the pressure distribution ratio is greater than the first preset ratio and the pressure change rate is greater than the preset rate, it is determined that the elderly person is about to get out of bed and an early warning for getting out of bed is triggered. The pressure distribution ratio is the ratio of the pressure value in the preset bed edge area to the sum of the pressure values ​​in all areas. Pressure distribution ratio = pressure value in the preset bed edge area / sum of the pressure values ​​in all areas. The pressure change rate is used to reflect how quickly the elderly person's center of gravity moves towards the edge of the bed. The higher the rate, the faster the elderly person is moving towards the edge of the bed, and the greater the risk of falling out of bed or rolling over. Pressure change rate = change in total pressure value in the preset bed edge area / change in time. In this embodiment of the invention, the first preset percentage is 30%, and the preset rate is 5 kg / s.

[0034] Specifically, in step S4, based on the condition that the number of body movements per unit time is greater than the preset number or the maximum daytime resting time is greater than the third preset time, the elderly person's behavior is judged to be abnormal, and the alarm level is determined based on the body movement impact coefficient and the rhythm disorder coefficient. The unit for calculating the number of physical movements per unit time is the hour, that is, the total number of physical movement events within 1 hour is taken as the number of physical movements per unit time. When the amplitude of body acceleration rises from a state continuously below 0.05g to a state greater than or equal to 0.1g, and this state lasts for at least 0.5 seconds, it is marked as the start of body movement; when the amplitude of body acceleration falls to a state below 0.05g, and this state lasts for at least 0.5 seconds, it is marked as the end of body movement; a duration of not less than 1 second from start to end is counted as one valid body movement event; a resting interval of less than 2 seconds between two adjacent body movement events is combined into the same body movement event; The amplitude of body acceleration is collected and calculated in real time by the triaxial accelerometer of the bed. The amplitude of body acceleration is equal to the sum of the squares of the acceleration values ​​of the triaxial accelerometer in the X-axis, Y-axis and Z-axis directions, and then the square root is taken.

[0035] In this embodiment of the invention, the daytime period is set to 6:00-22:00, the preset number of times is 20, and the third preset duration is 4 hours.

[0036] Specifically, the process for determining the alarm level is as follows: The body motion impact coefficient is calculated based on the vibration amplitude and duration of the bed frame, and the rhythm disorder coefficient is calculated based on the temporal changes of the number of body motions per unit time and the coordinates of the pressure center. Body dynamic impact coefficient = (peak acceleration of bed vibration ÷ gravitational acceleration) × The peak acceleration of bed vibration is collected by bed motion sensor, the gravitational acceleration is a constant of 9.8 m / s², and the duration of body movement is determined by the start and end time of the body movement event, with 1 second as the unit time constant. Rhythm disturbance coefficient = Standard deviation of the interval between adjacent peak body motion times / Average of the interval between adjacent peak body motion times; The body dynamic impact coefficient is compared with the first preset impact threshold and the second preset impact threshold, and the rhythm disorder coefficient is compared with the first preset disorder threshold and the second preset disorder threshold. If the body dynamic impact coefficient is greater than or equal to the first preset impact threshold and less than the second preset impact threshold, and the rhythm disorder coefficient is greater than or equal to the first preset disorder threshold and less than the second preset disorder threshold, then the alarm level is determined to be level three. If the body motion impact coefficient is greater than or equal to the second preset impact threshold and the rhythm disorder coefficient is less than the second preset disorder threshold, or if the body motion impact coefficient is less than the second preset impact threshold and the rhythm disorder coefficient is greater than or equal to the second preset disorder threshold, then the alarm level is determined to be level two. If the body dynamic impact coefficient is greater than or equal to the second preset impact threshold, and the rhythm disorder coefficient is greater than or equal to the second preset disorder threshold, then the alarm level is determined to be Level 1. In this embodiment of the invention, the first preset impact threshold is 0.5, the second preset impact threshold is 1.5, the first preset disorder threshold is 0.15, and the second preset disorder threshold is 0.6.

[0037] Specifically, the Level 1 alarm is an emergency alarm, used to alert the elderly person to severe agitation or a high risk of falling out of bed, requiring immediate attention; The level 2 alarm is a warning alarm, used to indicate that the elderly person's behavioral rhythm is significantly abnormal and needs to be checked. The third-level alarm is a notification alarm, used to indicate that the elderly person's behavior is slightly abnormal, and only observation is recorded.

[0038] Specifically, step S4 also includes: If an elderly person is detected to be out of bed during a preset period at night, an out-of-bed timer will be started. If the duration of continuous out-of-bed time exceeds the fourth preset duration, a nighttime out-of-bed timeout alarm will be triggered. In this embodiment of the invention, the nighttime preset period is set to 22:00-6:00, and the fourth preset duration is 30 minutes.

[0039] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples; within the framework of the invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in the details for the sake of brevity.

[0040] This invention is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for monitoring and alarming of abnormal condition of an elderly person in a nursing home care bed, characterized by, include: Step S1: Real-time data collection of the elderly’s body pressure distribution, heart rate and respiratory data and bed posture data is carried out by deploying pressure sensor array, non-contact vital sign sensor and bed motion sensor on the nursing bed. Step S2: Based on the body pressure distribution data and bed posture data, identify whether the elderly person's current behavioral state is a resting state or a moving state. The moving state includes turning over, sitting up, and getting out of bed. Step S3: Calculate the heart rate deviation index and respiratory abnormality index based on the heart rate and respiratory data, and determine whether the elderly person's vital signs are abnormal based on the heart rate deviation index and respiratory abnormality index. In the case of Level I abnormality, determine whether to trigger the vital signs abnormality alarm based on the postural state, the duration of the abnormality, or the degree of abnormal body movement matching. In the case of Level II abnormality, the pressure distribution ratio and pressure change rate in the preset bed edge area are calculated based on the body pressure distribution data to determine whether the elderly person is about to get out of bed, and to trigger a bed exit warning when the elderly person is about to get out of bed. Step S4: When the elderly person's vital signs are not abnormal, determine whether the elderly person's behavior is abnormal based on the number of body movements per unit time and the maximum resting time during the day, and determine the alarm level based on the body movement impact coefficient and rhythm disorder coefficient. The alarm level includes a level 1 alarm, a level 2 alarm, and a level 3 alarm.

2. The geriatric abnormal state monitoring and alarming method for nursing bed in old-age home according to claim 1, characterized in that, The body pressure distribution data includes real-time pressure values ​​collected by pressure sensor arrays distributed in various areas of the bed, the sum of pressure values ​​in each area, the coordinates of the pressure center, and the rate of change of pressure values ​​in each area over time. The heart rate and respiratory data include real-time heart rate values ​​and real-time respiratory rate values; The bed posture data includes the lifting angle of the upper body movable frame of the bed, as well as the vibration frequency and vibration amplitude of the bed frame.

3. The method for monitoring and alarming abnormal conditions of elderly people in nursing home beds according to claim 2, characterized in that, In step S2, the process of identifying the elderly person's current behavioral state based on the body pressure distribution data and bed posture data is as follows: Calculate the coordinates of the pressure center of the body pressure distribution, and determine the elderly person's center of gravity distribution based on the real-time position and movement speed of the pressure center; Determine whether the bed is in a raised or lowered state based on the angle at which the upper body movable frame of the bed is raised; Based on the changing patterns of pressure values ​​in different regions of the body pressure distribution, combined with the movement trajectory of the pressure center and changes in bed posture, the current behavioral state of the elderly is classified into lying down, turning over, sitting up, or getting out of bed.

4. The method for monitoring and alarming abnormal conditions of elderly people in nursing home beds according to claim 3, characterized in that, In step S3, the process of determining whether the elderly person's vital signs are abnormal based on the heart rate deviation index and respiratory abnormality index is as follows: Calculate the heart rate deviation index and respiratory abnormality index based on the heart rate and respiratory data; If the heart rate deviation index is less than the first preset deviation index and the respiratory abnormality index is less than the first preset abnormality index, then the elderly person's vital signs are determined to be normal. If the heart rate deviation index is greater than or equal to the first preset deviation index and less than the second preset deviation index, or if the respiratory abnormality index is greater than or equal to the first preset abnormality index and less than the second preset abnormality index, then the elderly person's vital signs are judged to be level two abnormal. If the heart rate deviation index is greater than or equal to the second preset deviation index, or the respiratory abnormality index is greater than or equal to the second preset abnormality index, the elderly person's vital signs are judged to be level one abnormality. The severity of the first-level anomaly is greater than that of the second-level anomaly.

5. The method for monitoring and alarming abnormal conditions of elderly people in nursing home beds according to claim 4, characterized in that, In a Level 1 abnormal situation, if the posture is a resting state, the duration of the abnormality determines whether to trigger a vital signs abnormality alarm. If the heart rate deviation index is greater than the second preset deviation index and the duration of the heart rate deviation index exceeding the second preset deviation index is greater than the first preset duration, then it is determined that an abnormal vital signs alarm is triggered. If the respiratory abnormality index is greater than the second preset abnormality index and the duration of the respiratory abnormality index exceeding the second preset abnormality index is greater than the second preset duration, then it is determined that a vital signs abnormality alarm is triggered. If the posture state is a body movement state, then the abnormal vital signs alarm is triggered based on the condition that the abnormal body movement matching degree is less than the preset matching degree. The abnormal body movement matching degree is the ratio of the duration of body movement during the period of abnormal signs to the total duration of abnormal signs.

6. The method for monitoring and alarming abnormal conditions of elderly people in nursing home beds according to claim 5, characterized in that, In the case of a level 2 abnormality, based on the condition that the pressure distribution ratio is greater than the first preset ratio and the pressure change rate is greater than the preset rate, it is determined that the elderly person is about to get out of bed and an exit warning is triggered. The pressure distribution ratio is the ratio of the pressure value within the preset bed edge area to the sum of the pressure values ​​in all areas.

7. The method for monitoring and alarming abnormal conditions of elderly people in nursing home beds according to claim 6, characterized in that, In step S4, based on the condition that the number of body movements per unit time is greater than the preset number or the maximum daytime resting time is greater than the third preset time, the elderly person's behavior is judged to be abnormal, and the alarm level is determined based on the body movement impact coefficient and the rhythm disorder coefficient.

8. The method for monitoring and alarming abnormal conditions of elderly people in nursing home beds according to claim 7, characterized in that, The process for determining the alarm level is as follows: The body motion impact coefficient is calculated based on the vibration amplitude and duration of the bed frame, and the rhythm disorder coefficient is calculated based on the temporal changes of the number of body motions per unit time and the coordinates of the pressure center. The body dynamic impact coefficient is compared with the first preset impact threshold and the second preset impact threshold, and the rhythm disorder coefficient is compared with the first preset disorder threshold and the second preset disorder threshold. If the body dynamic impact coefficient is greater than or equal to the first preset impact threshold and less than the second preset impact threshold, and the rhythm disorder coefficient is greater than or equal to the first preset disorder threshold and less than the second preset disorder threshold, then the alarm level is determined to be level three. If the body motion impact coefficient is greater than or equal to the second preset impact threshold and the rhythm disorder coefficient is less than the second preset disorder threshold, or if the body motion impact coefficient is less than the second preset impact threshold and the rhythm disorder coefficient is greater than or equal to the second preset disorder threshold, then the alarm level is determined to be level two. If the body dynamic impact coefficient is greater than or equal to the second preset impact threshold, and the rhythm disorder coefficient is greater than or equal to the second preset disorder threshold, then the alarm level is determined to be Level 1.

9. The method for monitoring and alarming abnormal conditions of elderly people in nursing home beds according to claim 8, characterized in that, The first-level alarm is an emergency alarm, used to alert the elderly person to severe agitation or a high risk of falling out of bed, requiring immediate attention. The level 2 alarm is a warning alarm, used to indicate that the elderly person's behavioral rhythm is significantly abnormal and needs to be checked. The third-level alarm is a notification alarm, used to indicate that the elderly person's behavior is slightly abnormal, and only observation is recorded.

10. The method for monitoring and alarming abnormal conditions of elderly people in nursing home beds according to claim 1, characterized in that, Step S4 also includes: If an elderly person is detected to be out of bed during a preset period at night, an out-of-bed timer will be started. If the duration of continuous out-of-bed activity exceeds the fourth preset duration, a nighttime out-of-bed timeout alarm will be triggered.

Images