Nursing institution safety risk management and control system based on digital twinborn technology

Abstract

The invention discloses an old-age care institution safety risk management and control system based on a digital twinning technology, and relates to the technical field of digital twinning application old-age care safety risks, and the system can perform fusion analysis on video images, meteorological data, old-age behavior characteristics and other multi-dimensional data in an old-age care institution, and accurately identify factors which may cause risks. Through analysis of video images, the system can identify dangerous characteristics such as ground water spots, glass doors, sockets and the like and associate the dangerous characteristics with behavior characteristics of old people. And the gestures and gaits of the old people are monitored, so that the risk of falling or slipping is judged, and a falling coefficient Sd is calculated in real time. For an accident, the system monitors changes in the environment, such as sudden object movement or falling sound and noisy sound between the elderly, and calculates an accident coefficient Yw. Different from a traditional universal alarm system, the scheme triggers an alarm mechanism in a targeted manner according to the specific environment condition of the old.

Description

Technical Field

[0001] The present invention relates to the field of digital twin application elderly care safety risk technology, and specifically to a elderly care institution safety risk management and control system based on digital twin technology. Background Art

[0002] With the increasing aging of the population, the demand for nursing homes is increasing, but it also raises safety issues for the elderly in nursing homes. After the age of 65, the motor system of the elderly declines, and muscle strength and joint flexibility gradually decrease, resulting in inconvenience in movement and weakened limb coordination. They are more likely to slip when encountering water stains. In addition, the elderly often have osteoporosis, which can easily lead to serious consequences such as bone fractures after a fall.

[0003] The physiological state and mobility of the elderly may be fragile, which may lead to accidents such as falls during daily activities, especially when the ground is slippery or visibility is low. Traditional safety monitoring systems may find it difficult to accurately distinguish between falls and normal activities of the elderly, and do not monitor the visibility of the current environment. As a result, many elderly people may bump into glass doors or fall due to impaired amblyopia when there is heat indoors, triggering safety accidents. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides a safety risk management and control system for nursing homes based on digital twin technology. By using digital twin technology, through real-time data collection and analysis, it is possible to more accurately identify the risk of falling of the elderly due to slippery ground and low visibility. This solution not only focuses on the fact that the elderly fall, but also associates factors such as water stains and visibility with the falling behavior, providing a more comprehensive risk warning. This multi-factor correlation warning helps to identify potential dangerous situations in advance. Unlike traditional universal alarm systems, this solution triggers the alarm mechanism in a targeted manner according to the specific environmental conditions of the elderly. For example, in areas with insufficient light or water stains, the system can adopt different alarm methods, such as sound alarms, notifying staff, etc., to ensure a quick response when risks occur.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a safety risk management and control system for nursing homes based on digital twin technology, including a regional division unit, a digital twin modeling unit, a park facility collection unit, a facility feature extraction unit, a behavior collection unit, a correlation unit, an analysis unit and an early warning unit;

[0008] The area division unit is used to divide the nursing home park into several functional areas, including a living area, a leisure area, an activity area and a dining area;

[0009] The digital twin modeling unit is used to establish a three-dimensional model of the nursing home through digital twin technology, three-dimensional composition, point cloud modeling and panoramic modeling technology; and map several parks in the digital twin modeling unit to mark the area of ​​each region;

[0010] The park facility acquisition unit is used to deploy several sensor groups and monitoring equipment to cover several areas, and is used to acquire video images and meteorological data of several areas of the park in real time to establish a data set A;

[0011] The feature extraction unit is used to extract features from the sub-dataset A, and identify the first area danger feature and the second area danger feature; the analysis unit performs fitting analysis on the first area danger feature and the corresponding second area danger feature, and calculates the water vapor visibility coefficient Njd, the protection factor Fh and the support factor Zc; the water vapor visibility coefficient Njd is calculated by the following formula:

[0012]

[0013] Wherein, wd represents the indoor temperature value, sd represents the indoor air humidity value, wc represents the difference between the outdoor temperature and the indoor temperature, Gz represents the light intensity value, dxc represents the density value of the surrounding obstructions, and MJ represents the indoor area value of the current area; α represents the visibility value of the elderly in a normal environment; T1, T2 and T3 represent the weight coefficient values ​​of the indoor temperature value wd, the indoor air humidity value sd and the difference between the outdoor temperature and the indoor temperature wc, and T1+T2+T3=1.0; the meaning of the formula is that the water vapor visibility coefficient Njd can be calculated in areas with large outdoor temperature differences, fog or bathrooms. For people with reduced vision, it refers to the prediction of visibility based on the weather conditions at the time, which reduces the risk of elderly people slipping, falling and hitting glass doors due to poor visibility;

[0014] The behavior collection unit is used to extract the behavior characteristics of the elderly through the data set A, including the characteristics of falls and slips, accidental events, sports habits and facility preferences; and the analysis unit analyzes and calculates the behavior characteristics of the elderly to obtain the fall coefficient Sd, the accident coefficient Yw and the facility demand coefficient Sx;

[0015] The correlation unit is used to correlate the water vapor visibility coefficient Njd with the fall coefficient Sd to obtain the fall factor U1; to correlate the protection factor Fh with the accident coefficient Yw to calculate the protection factor U2; to correlate the support coefficient Zc with the facility demand coefficient Sx to calculate the demand factor T3;

[0016] The fall factor U1, protection factor U2 and demand factor T3 are compared with the preset thresholds to obtain an evaluation result, and the early warning unit sets corresponding control instructions according to the evaluation result.

[0017] Preferably, it also includes a configuration unit, which is used to configure a health positioning bracelet on each elderly person and display each positioning bracelet in real time in the digital twin modeling unit; when the behavior collection unit collects the characteristics of falls and slips and the characteristics of accidents, a first early warning instruction is generated, and the early warning unit receives the first early warning instruction and performs corresponding early warning control.

[0018] Preferably, the data set A includes a sub-data set B1 and a sub-data set B2; the sub-data set B1 includes video image data of several regions, and the data set B2 includes meteorological data of several regions;

[0019] The first area danger features are obtained by the feature extraction unit performing feature recognition on the video image in the sub-dataset B1, and the first area danger features include ground water stain features, glass door features, socket features, armrest support features and rest seat features; the second danger features are obtained by the feature extraction unit performing recognition and extraction on the sub-dataset B2; the second danger features include meteorological data features related to the area with glass doors.

[0020] Preferably, the digital twin modeling unit is used to model various facilities within the nursing home, including rooms, equipment, furniture, glass doors, campus facilities, and the status, operation and maintenance status of simulated equipment.

[0021] Preferably, the video images of several areas are identified, and the socket protection features are extracted, and the socket positions in the video images are monitored by a target monitoring algorithm;

[0022] For each detected socket, further analyze the image to determine the status of the socket's safety cover; use image processing technology, including image segmentation and feature extraction, to identify the status of the safety cover, including whether the socket protective cover is intact and whether the protective cover is open. For each socket, analyze the wettability and set the determination method to whether it is higher than 1 meter from the ground. If the socket is less than 1 meter, it is determined to be wettable and the protective cover needs to be closed for safety protection;

[0023] The protection factor Fh of the current area is calculated based on the safety status, position and wettability characteristics. The protection factor Fh is calculated using the following formula:

[0024]

[0025] Wherein, SYpL represents the usage frequency value of the sockets in the current area, FGL represents the coverage rate of the safety covers covering the sockets in the current area, YssL represents the coverage rate of the sockets higher than 1 meter in the current area, W1 and W2 represent the weight values of FGL and YssL, and 0.65 < W1 < 0.85, 0.25 < W2 < 0.55, and W1 + W2 ≥ 1.15.

[0026] Preferably, the video images of several areas are recognized, and the number of supports in the current area is extracted; through the target monitoring algorithm, the positions of the supports in the video images are monitored;

[0027] For each detected seat, the image is further analyzed to monitor the positions of the supports. The supports include seats, railings and handrails; the handrails, seats or railings are used to provide additional support, and the distances between the supports are identified. The elderly are weak and need supports after walking a few steps. Identifying the specific distances between the supports can reduce the risk of the elderly falling due to exhaustion without supports; the single support load-bearing value zcz of the supports is collected, and the area of the current area is calculated to calculate the support quantity coverage rate zfg and the average adjacent distance value JL of the supports, and the support coefficient Zc is obtained through fitting calculation

[0028] The support coefficient Zc is calculated by the following formula:

[0029]

[0030] Wherein, SLZ represents the total number of supports in the current area, W3 and W4 respectively represent the total load-bearing support value in the current area and the weight value of the average adjacent distance value JL of the supports, and 0.55 < W3 < 0.75, 0.45 < W5 < 0.55, and W1 + W2 ≥ 1.10; the single support load-bearing value zcz of the supports is obtained by calculating the load weight in the middle of the support design.

[0031] Preferably, the behavior acquisition unit includes a fall and slip feature monitoring unit and an accident feature monitoring unit;

[0032] The fall and slip feature monitoring unit is used to monitor the postures and gaits of the elderly, and judge the features of falling or slipping by analyzing sudden posture changes and staggers. The number of times of the fall features of the elderly in the current area on a single day is identified. The formula for calculating the fall coefficient Sd is:

[0033]

[0034] Wherein, rs represents the historical number of fallen people in the current area, N fall represents the number of fall feature times, and sjT represents the observed time period, including single day, weekly and monthly; to quantify the number of fall feature times N within a period of timefall Value;

[0035] The accident feature monitoring unit is used to monitor the environmental changes around the elderly, including sudden object movement, falling sound, and arguing sound, and detect accidents caused by the elderly arguing; set the number of times of the accident features of the elderly in the current area on a single day, and the formula for calculating the accident coefficient Yw is:

[0036]

[0037] In the formula, LS represents the historical accident probability value of the current area, N accident represents the number value of the accident features of the elderly in the current area, and sjT represents the observation time period, including a single day, weekly, and monthly; to quantify the number value of the accident features of the elderly in the current area within a period of time N accident Value of the number of times.

[0038] Preferably, the behavior acquisition unit further includes a facility demand acquisition unit, which is used to collect the preference data of the elderly for different facilities, obtained through survey documents, and calculate the implementation hobby grading and data;

[0039] And it is used to monitor the usage frequency of the facilities in the elderly's leisure area, including the daily occupancy time of the facilities, obtained by using sensors or timers, and calculate the facility demand coefficient Sx based on the overall facility usage coverage;

[0040]

[0041] In the formula, FF represents the usage coverage value of the facilities in the current area, FU represents the facility usage frequency value, and DHRS represents the number value of the elderly waiting to use the facilities; W5, W6, and W7 respectively represent the weight values of the usage coverage value FF of the facilities in the current area, the facility usage frequency value FU, and the number value DHRS of the elderly waiting to use the facilities, and 0.35 < W5 < 0.56, 0.35 < W6 < 0.76, 0.85 < W7 < 0.96, and W5 + W6 = W7 ≥ 1.65.

[0042] Preferably, the correlation formulas of the fall factor U1, protection factor U2, and demand factor T3 are obtained as follows:

[0043] U1 = Njd * Sd

[0044] U2 = Fh * Yw

[0045] U3 = Zc + Sx

[0046] Compare the fall factor U1, protection factor U2, and demand factor T3 with their respective preset thresholds, and the preset thresholds include the fall threshold Td , protection threshold T f and the demand threshold T s ;

[0047] When the fall factor U1> fall threshold T d When the risk of falling is

[0048] When the protection factor U2> protection threshold T f When the risk is , it is considered as a protection risk;

[0049] When the demand factor T3> the demand threshold T s When , it is determined to be demand risk.

[0050] Preferably, the early warning unit includes an alarm triggering unit, an enhanced monitoring unit and an auxiliary providing unit;

[0051] The trigger alarm unit is used to generate corresponding alarm notifications according to the fall risk, protection risk and demand risk, and remind the staff of the risk situation in the corresponding area;

[0052] The enhanced monitoring unit is used to increase the monitoring frequency of the corresponding areas of the current fall risk, protection risk and demand risk, so as to facilitate the timely discovery of problems;

[0053] The auxiliary unit is used to provide the elderly with caring handrails, railings and facilities, providing better support and protection.

[0054] (III) Beneficial effects

[0055] The present invention provides a safety risk management system for nursing homes based on digital twin technology. It has the following beneficial effects:

[0056] (1) The safety risk management system for nursing homes based on digital twin technology takes into account multiple factors, including fall risk, protection risk, and demand risk. Through the comprehensive evaluation of fall factors, protection factors, and demand factors, the system can accurately determine the degree of risk and issue an alarm in time when the risk exceeds the preset threshold, thereby improving the safety of the elderly.

[0057] (2) The digital twin technology-based nursing home safety risk management system monitors risk factors in real time based on the behavioral characteristics of the elderly, environmental factors, and facility requirements. Through digital twin modeling technology and image analysis, it identifies and quantifies dangerous features such as water stains on the ground, glass doors, sockets, handrails, and seats, providing personalized risk assessment and protection plans for each area.

[0058] (3) The system correlates different risk factors, such as correlating the water vapor visibility coefficient Njd with the fall coefficient Sd, the protection coefficient Fh with the accident coefficient Yw, the support coefficient Zc with the facility demand coefficient Sx, etc. Through this comprehensive analysis, the system can more comprehensively assess the risk situation and accurately identify problems and hidden dangers.

[0059] (4) The system uses digital twin technology and sensor monitoring equipment to collect real-time data within the nursing home, including video images, meteorological data, and behavioral characteristics of the elderly. When the risk of falls, protection, and needs exceeds the preset threshold, the system can quickly generate an alarm notification to remind staff and take appropriate measures to ensure the safety and comfort of the elderly. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a flowchart diagram of the safety risk management system for nursing homes based on digital twin technology of the present invention; DETAILED DESCRIPTION

[0061] 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.

[0062] As the population ages, the demand for nursing homes is growing, but this also raises safety issues for the elderly in nursing homes. The physiological state and mobility of the elderly may be fragile, leading to accidents such as falls during daily activities, especially when the ground is slippery or visibility is low. To solve this problem, digital twin technology provides an innovative solution for the safety risk management system of nursing homes.

[0063] Example 1

[0064] The present invention provides a security risk management and control system for nursing homes based on digital twin technology, and the security risk management and control system for nursing homes based on digital twin technology includes a region division unit, a digital twin modeling unit, a park facility collection unit, a facility feature extraction unit, a behavior collection unit, a correlation unit, an analysis unit, and an early warning unit;

[0065] The area division unit is used to divide the nursing home park into several functional areas, including a living area, a leisure area, an activity area and a dining area;

[0066] The digital twin modeling unit is used to establish a three-dimensional model of the nursing home through digital twin technology, three-dimensional composition, point cloud modeling and panoramic modeling technology; and map several parks in the digital twin modeling unit to mark the area of ​​each region;

[0067] The park facility acquisition unit is used to deploy several sensor groups and monitoring equipment to cover several areas, and is used to acquire video images and meteorological data of several areas of the park in real time to establish a data set A;

[0068] The feature extraction unit is used to extract features from the sub-dataset A, and identify the first area danger feature and the second area danger feature; the analysis unit performs fitting analysis on the first area danger feature and the corresponding second area danger feature, and calculates the water vapor visibility coefficient Njd, the protection factor Fh and the support factor Zc; the water vapor visibility coefficient Njd is calculated by the following formula:

[0069]

[0070] Wherein, wd represents the indoor temperature value, sd represents the indoor air humidity value, wc represents the difference between the outdoor temperature and the indoor temperature, Gz represents the light intensity value, dxc represents the density value of the surrounding obstructions, and MJ represents the indoor area value of the current area; α represents the visibility value of the elderly in a normal environment; T1, T2 and T3 represent the weight coefficient values ​​of the indoor temperature value wd, the indoor air humidity value sd and the difference between the outdoor temperature and the indoor temperature wc, and T1+T2+T3=1.0; the meaning of the formula is that the water vapor visibility coefficient Njd can be calculated in areas with large outdoor temperature differences, fog or bathrooms. For people with reduced vision, it refers to the prediction of visibility based on the weather conditions at the time, which reduces the risk of elderly people slipping, falling and hitting glass doors due to poor visibility;

[0071] The behavior collection unit is used to extract the behavior characteristics of the elderly through the data set A, including the characteristics of falls and slips, accidental events, sports habits and facility preferences; and the analysis unit analyzes and calculates the behavior characteristics of the elderly to obtain the fall coefficient Sd, the accident coefficient Yw and the facility demand coefficient Sx;

[0072] The correlation unit is used to correlate the water vapor visibility coefficient Njd with the fall coefficient Sd to obtain the fall factor U1; to correlate the protection factor Fh with the accident coefficient Yw to calculate the protection factor U2; to correlate the support coefficient Zc with the facility demand coefficient Sx to calculate the demand factor T3;

[0073] The fall factor U1, protection factor U2 and demand factor T3 are compared with the preset thresholds to obtain an evaluation result, and the early warning unit sets corresponding control instructions according to the evaluation result.

[0074] In this embodiment, the implementation steps of this scheme include regional division, digital twin modeling, sensor data collection, feature extraction, elderly behavior analysis, and protection assessment. Through the application of digital twin technology, video images and meteorological data of the region can be collected in real time to establish an accurate data set. At the same time, through feature extraction and behavior analysis, key elderly behavior characteristics such as falls, slips, accidents, exercise habits and facility requirements can be obtained. These characteristics are associated and fitted in the analysis unit to obtain key parameters such as water vapor visibility coefficient Njd, protection factor Fh and support factor Zc. And combined with the calculation to obtain the fall factor U1, protection factor U2 and demand factor T3 exceeding the preset threshold, the early warning unit will set the corresponding control instructions according to the evaluation results. This may include triggering alarms, notifying staff, strengthening monitoring, providing auxiliary facilities and other measures to reduce risks and ensure the safety of the elderly. The present invention has obvious advantages in solving the problem of elderly people falling due to water stains and low visibility. This innovative solution not only improves the quality of life of the elderly, but also enhances the safety and risk management capabilities of nursing homes.

[0075] Example 2

[0076] This embodiment is explained in Example 1, please refer to Figure 1 Specifically, it also includes a configuration unit, which is used to configure a health positioning bracelet on each elderly person, and display each positioning bracelet in real time in the digital twin modeling unit; when the behavior collection unit collects the characteristics of falls and slips and the characteristics of accidents, it generates a first warning instruction, and the warning unit receives the first warning instruction and performs corresponding warning control.

[0077] In this embodiment, the configuration unit is responsible for configuring a health positioning bracelet for each elderly person, which can track the location and movement of the elderly in real time. Through these bracelets, the system can obtain the real-time location information of the elderly and visualize it in the digital twin modeling unit. This helps the system to more accurately identify the location of the elderly, so as to better assess risks and take corresponding preventive measures. The configuration unit is closely integrated with the behavior collection unit. When the behavior collection unit detects the characteristics of a fall, slip, or accident of the elderly, the configuration unit generates a first warning instruction. This warning instruction can include the real-time location of the elderly and the details of the triggering event, providing more information for the warning unit to more accurately assess risks.

[0078] Example 3

[0079] This embodiment is explained in Example 1, please refer to Figure 1Specifically, the data set A includes a sub-data set B1 and a sub-data set B2; the sub-data set B1 includes video image data of several regions, and the data set B2 includes meteorological data of several regions;

[0080] The first area danger features are obtained by the feature extraction unit performing feature recognition on the video image in the sub-dataset B1, and the first area danger features include ground water stain features, glass door features, socket features, armrest support features and rest seat features; the second danger features are obtained by the feature extraction unit performing recognition and extraction on the sub-dataset B2; the second danger features include meteorological data features related to the area with glass doors.

[0081] In this embodiment, the analysis unit correlates the first area hazard feature with the second hazard feature. This means that the system considers the relationship between the meteorological data features associated with the glass door and the hazard features of other areas. This comprehensive analysis helps to more accurately assess potential risks; assess the risks that the elderly may face in different areas, especially the risk of falling related to factors such as water stains and visibility. This method can better understand the relationship between the environment and the behavior of the elderly, so as to more effectively take preventive and control measures to ensure a safe environment in the elderly care institution.

[0082] Example 4

[0083] This embodiment is explained in Example 1, please refer to Figure 1 Specifically, the digital twin modeling unit is used to model various facilities within the nursing home, including rooms, equipment, furniture, glass doors, campus facilities, and the status, operation and maintenance status of simulated equipment.

[0084] In this embodiment, the system can simulate the status, operation and maintenance of different facilities in a digital environment, thereby achieving a true reflection of the actual environment in the elderly care institution. This environmental simulation capability enables the system to more accurately identify potential risk sources, including risks related to facilities and equipment. For example, the system can simulate the status of a glass door to check whether there are unsafe conditions that may cause the elderly to slip or hit.

[0085] Example 5

[0086] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically, the video images of several regions are identified and the ,protection features of the sockets are extracted, and the socket positions in the ,video images are monitored by the target monitoring algorithm;

[0087] For each detected socket, the image is further analyzed to determine the status of the socket's safety cover; image processing techniques, including image segmentation and feature extraction, are used to identify the status of the safety cover, including whether the socket protective cover is intact and whether the protective cover is in an open state. For each socket, the wettability is analyzed, and the determination method is set as whether it is more than 1 meter above the ground. If the socket is less than 1 meter, it is determined that there is a risk of wetness, and safety protection for closing the protective cover is required.

[0088] Based on the safety cover status, location, and wettability characteristics, the protection coefficient Fh of the current area is calculated. The protection coefficient Fh is calculated through the following formula:

[0089]

[0090] In the formula, SYpL represents the usage frequency value of the sockets in the current area, FGL represents the coverage rate of the sockets covered by the safety cover in the current area, YssL represents the coverage rate of the sockets more than 1 meter above the ground in the current area, W1 and W2 represent the weight values of FGL and YssL, and 0.65 < W1 < 0.85, 0.25 < W2 < 0.55, and W1 + W2 ≥ 1.15.

[0091] In this embodiment, this protection coefficient Fh comprehensively considers the usage situation, safety cover status, and wettability of the sockets and is used to evaluate the protection level of the area. The system can determine whether corresponding safety protection measures need to be taken according to different protection coefficient Fh values to ensure the safety of the elderly.

[0092] Embodiment 6

[0093] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically, the video images of several areas are recognized, and the number of supports in the current area is extracted; through the target monitoring algorithm, the positions of the supports in the video images are monitored;

[0094] For each detected seat, the image is further analyzed to monitor the position of the support. The supports include seats, railings, and handrails; the handrails, seats, or railings are used to provide additional support, and the distance between the supports is identified. The elderly are weak and need supports after walking a few steps. Identifying the specific distance between the supports reduces the risk of the elderly falling due to exhaustion without a support. The single support load-bearing value zcz of the support is collected, and the support number coverage rate zfg of the current area is calculated, that is, the ratio of the number of supports to the total area of the area, and the average adjacent distance value JL of the supports is calculated. The support coefficient Zc is obtained through fitting calculation.

[0095] The support coefficient Zc is calculated through the following formula:

[0096]

[0097] In the formula, SLZ represents the total number of supports in the current area, W3 and W4 respectively represent the total load-bearing support value of the current area and the weight value JL of the average adjacent distance value of the supports, and 0.55 < W3 < 0.75, 0.45 < W5 < 0.55, and W1 + W2 ≥ 1.10; the single support load-bearing value zcz of the support is calculated by the load weight in the city designed by the support.

[0098] In this embodiment, the support coefficient Zc synthesizes the information of the number of supports, the load-bearing capacity, and the distance between the supports to evaluate the support situation of the elderly in the current area. The system can judge whether the support situation of the area is sufficient according to different support coefficient Zc values, so as to take corresponding measures to ensure the safety of the elderly's actions.

[0099] Embodiment 7

[0100] This embodiment is an explanatory description carried out in Embodiment 1, please refer to Figure 1 , specifically, the behavior acquisition unit includes a fall and slip feature monitoring unit and an accident feature monitoring unit;

[0101] The fall and slip feature monitoring unit is used to monitor the posture and gait of the elderly, judge the characteristics of falling or slipping by analyzing sudden posture changes and stumbles, identify the number of times of the elderly's fall characteristics in the current area on a single day, and the formula for calculating the fall coefficient Sd is:

[0102]

[0103] In the formula, rs represents the value of the historical number of falls in the current area, N fall represents the number of times of fall characteristics, and sjT represents the observation time period, including a single day, a week, and a month; to quantify the number of times of fall characteristics N within a period of time fall value;

[0104] The accident feature monitoring unit is used to monitor the environmental changes around the elderly, including sudden object movement, falling sound, and arguing sound, and detect accidents caused by the elderly arguing; set the number of times of the elderly's accident characteristics in the current area on a single day, and the formula for calculating the accident coefficient Yw is:

[0105]

[0106] In the formula, LS represents the historical accident probability value of the current area, N accident represents the value of the number of times of the elderly's accident characteristics in the current area, and sjT represents the observation time period, including a single day, a week, and a month; to quantify the number of times of the elderly's accident characteristics N in the current area within a period of timeaccident The value of the number of times.

[0107] In this embodiment, through the fall coefficient Sd and the accident coefficient Yw, the system can evaluate the risks of falls and accidents of the elderly in the current area. This helps the system to issue alerts in a timely manner and take corresponding measures to ensure the safety of the elderly.

[0108] Embodiment 8

[0109] This embodiment is an explanatory description carried out in Embodiment 1. Please refer to Figure 1 , specifically, the behavior acquisition unit further includes a facility demand acquisition unit, which is used to collect the preference data of the elderly for different facilities, obtained through survey documents, and calculate and obtain the implementation hobby grading and data;

[0110] And it is used to monitor the usage frequency of the facilities in the elderly's leisure area, including the daily occupancy time of the facilities, obtained by using sensors or timers, and calculate the facility demand coefficient Sx through the overall facility usage coverage;

[0111]

[0112] In the formula, FF represents the usage coverage value of the facilities in the current area, FU represents the facility usage frequency value, and DHRS represents the number of people waiting for the use of the facilities by the elderly; W5, W6, and W7 respectively represent the weight values of the usage coverage value FF of the facilities in the current area, the facility usage frequency value FU, and the number of people DHRS waiting for the use of the facilities by the elderly, and 0.35 < W5 < 0.56, 0.35 < W6 < 0.76, 0.85 < W7 < 0.96, and W5 + W6 = W7 ≥ 1.65.

[0113] In this embodiment, the facility demand coefficient Sx of the system can better understand the demand degree of the elderly for different facilities, so as to provide a more comfortable and satisfactory environment and reduce the risks caused by insufficient facilities.

[0114] Embodiment 9

[0115] This embodiment is an explanatory description carried out in Embodiment 1. Please refer to Figure 1 , specifically, the correlation formulas of the fall factor U1, the protection factor U2, and the demand degree factor T3 are obtained as follows:

[0116] U1 = Njd * Sd

[0117] U2 = Fh * Yw

[0118] U3 = Zc + Sx

[0119] The fall factor U1, the protection factor U2 and the demand factor T3 are compared with the preset thresholds, wherein the preset thresholds include the fall threshold T d , protection threshold T f and the demand threshold T s ;

[0120] When the fall factor U1> fall threshold T d When the risk of falling is

[0121] When the protection factor U2> protection threshold T f When the risk is , it is considered as a protection risk;

[0122] When the demand factor T3> the demand threshold T s When , it is determined to be demand risk.

[0123] The early warning unit includes an alarm triggering unit, an enhanced monitoring unit and an auxiliary providing unit;

[0124] The trigger alarm unit is used to generate corresponding alarm notifications based on the risk of falling, protection risk and demand risk, and remind the staff of the risk situation in the corresponding area; different from the traditional universal alarm system, this solution triggers the alarm mechanism in a targeted manner according to the specific environment of the elderly. For example, in areas with insufficient light or water stains, the system can adopt different alarm methods, such as sound alarm, notification of staff, etc., to ensure that a quick response can be made when risks occur.

[0125] The enhanced monitoring unit is used to increase the monitoring frequency of the corresponding areas of the current fall risk, protection risk and demand risk, so as to facilitate the timely discovery of problems;

[0126] The auxiliary unit is used to provide the elderly with caring handrails, railings and facilities, providing better support and protection.

[0127] In this embodiment, based on the comparison of the fall factor U1, the protection factor U2 and the demand factor T3, the system can draw a risk judgment on falls, protection and demand. Through the collaboration of these early warning units, the system can better protect the safety and needs of the elderly, timely remind and respond to potential risk situations, and provide auxiliary support to provide a better living environment for the elderly.

[0128] 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. The safety risk management and control system for nursing homes based on digital twin technology is characterized by: It includes area division unit, digital twin modeling unit, park facility collection unit, facility feature extraction unit, behavior collection unit, correlation unit, analysis unit and early warning unit; The area division unit is used to divide the nursing home park into several functional areas, including a living area, a leisure area, an activity area and a dining area; The digital twin modeling unit is used to establish a three-dimensional model of the nursing home through digital twin technology, three-dimensional composition, point cloud modeling and panoramic modeling technology; and map several parks in the digital twin modeling unit to mark the area of ​​each region; The park facility acquisition unit is used to deploy several sensor groups and monitoring equipment to cover several areas, and is used to acquire video images and meteorological data of several areas of the park in real time to establish a data set A; The feature extraction unit is used to extract features from the sub-dataset A, and identify the first area danger feature and the second area danger feature; the analysis unit performs fitting analysis on the first area danger feature and the corresponding second area danger feature, and calculates the water vapor visibility coefficient Njd, the protection factor Fh and the support factor Zc; the water vapor visibility coefficient Njd is calculated by the following formula: Wherein, wd represents the indoor temperature value, sd represents the indoor air humidity value, wc represents the difference between the outdoor temperature and the indoor temperature, Gz represents the light intensity value, dxc represents the density value of the surrounding obstructions, and MJ represents the indoor area value of the current area; α represents the visibility value of the elderly in a normal environment; T1, T2 and T3 represent the weight coefficient values ​​of the indoor temperature value wd, the indoor air humidity value sd and the difference between the outdoor temperature and the indoor temperature wc, and T1+T2+T3=1.0; the meaning of the formula is that the water vapor visibility coefficient Njd can be calculated in areas with large outdoor temperature differences, fog or bathrooms. For people with reduced vision, it refers to the prediction of visibility based on the weather conditions at the time, which reduces the possibility of the elderly slipping, falling and hitting the glass door due to poor visibility; The behavior collection unit is used to extract the behavior characteristics of the elderly through the data set A, including the characteristics of falls and slips, the characteristics of accidents, the characteristics of exercise habits and the characteristics of facility preferences; The analysis unit analyzes and calculates the behavior characteristics of the elderly to obtain the fall coefficient Sd, accident coefficient Yw and facility demand coefficient Sx; The correlation unit is used to correlate the water vapor visibility coefficient Njd with the fall coefficient Sd to obtain the fall factor U1; to correlate the protection factor Fh with the accident coefficient Yw to calculate the protection factor U2; to correlate the support coefficient Zc with the facility demand coefficient Sx to calculate the demand factor T3; The fall factor U1, protection factor U2 and demand factor T3 are compared with the preset thresholds to obtain an evaluation result, and the early warning unit sets corresponding control instructions according to the evaluation result.

2. The digital twin technology-based security risk management and control system for nursing homes according to claim 1 is characterized by: It further includes a configuration unit, which is used to configure a health positioning bracelet on each elderly person and display each positioning bracelet in real time in the digital twin modeling unit; when the behavior acquisition unit acquires fall and slip features and accident features, a first warning instruction is generated, and the warning unit receives the first warning instruction and performs corresponding warning control.

3. The digital twin technology-based security risk management and control system for nursing homes according to claim 1 is characterized by: The dataset A includes a sub-dataset B1 and a sub-dataset B2; the sub-dataset B1 includes video image data of several regions, and the dataset B2 includes meteorological data of several regions; The first regional hazard feature is obtained by the feature extraction unit performing feature recognition on the video images in the sub-dataset B1, and the first regional hazard feature includes ground water stain features, glass door features, socket features, handrail support features, and rest seat features; the second hazard feature is obtained by the feature extraction unit identifying and extracting the sub-dataset B2; the second hazard feature includes meteorological data features of the area related to the glass door.

4. The digital twin technology-based security risk management and control system for nursing homes according to claim 1 is characterized by: The digital twin modeling unit is used to model various facilities in the elderly care institution; including rooms, equipment, furniture, glass doors, park facilities, the state, operation status, and maintenance status of simulation equipment.

5. The digital twin technology-based security risk management and control system for nursing homes according to claim 1 is characterized by: Identify the video images of several regions, and extract the socket protection features, and monitor the socket positions in the video images through the target monitoring algorithm; For each detected socket, further analyze the image to judge the safety cover status of the socket; use image processing techniques, including image segmentation and feature extraction, to identify the status of the safety cover, including whether the socket protective cover is intact and whether the protective cover is in an open state. For each socket, analyze the moisture susceptibility, and set the judgment method as whether it is more than 1 meter above the ground. If the socket is less than 1 meter, it is determined that there is moisture susceptibility, and safety protection for closing the protective cover is required; Through the safety modification status, position, and moisture susceptibility features, the protection coefficient Fh of the current area is calculated, and the protection coefficient Fh is calculated through the following formula: In the formula, SYpL represents the usage frequency value of the sockets in the current area, FGL represents the coverage rate of the sockets covered by the safety cover in the current area, YssL represents the coverage rate of the sockets more than 1 meter above the ground in the current area, W1 and W2 represent the weight values of FGL and YssL, and 0.65 < W1 < 0.85, 0.25 < W2 < 0.55, and W1 + W2 ≥ 1.

15.

6. The digital twin technology-based security risk management and control system for nursing homes according to claim 1 is characterized by: Identify the video images of several regions, and extract the number of supports in the current area; monitor the support positions in the video images through the target monitoring algorithm; For each detected seat, the image is further analyzed to monitor the position of the supports, which include the seat, railing, and armrest; the armrest, seat, or railing is used to provide additional support, and the distance between the supports is identified. The elderly are frail and need support after taking a few steps. Identifying the specific distance between the supports reduces the risk of the elderly falling due to fatigue without support; the single support load-bearing value zcz of the support is collected, and the area of the current region is calculated to calculate the support quantity coverage rate zfg and the average adjacent distance value JL of the supports, and the support coefficient Zc is obtained through fitting calculation. The support coefficient Zc is calculated by the following formula: In the formula, SLZ represents the total number of supports in the current region, W3 and W4 respectively represent the weight values of the total load-bearing support value of the current region and the average adjacent distance value JL of the supports, and 0.55 < W3 < 0.75, 0.45 < W5 < 0.55, and W1 + W2 ≥ 1.10; the single support load-bearing value zcz of the support is obtained by calculating the load weight in the middle of the support design.

7. The digital twin technology-based security risk management and control system for nursing homes according to claim 1 is characterized by: The behavior acquisition unit includes a fall and slip feature monitoring unit and an accident feature monitoring unit; The fall and slip feature monitoring unit is used to monitor the posture and gait of the elderly, and judge the characteristics of falling or slipping by analyzing sudden posture changes and staggering. The formula for calculating the fall coefficient Sd by identifying the number of times of the elderly's fall characteristics in the current region on a single day is: In the formula, rs represents the historical number of falls in the current area, N fall It is expressed as the number of fall characteristics, and sjT is the observation period, including single day, week and month; to quantify the number of fall characteristics in a period of time N fall The value of The accident feature monitoring unit is used to monitor the environmental changes around the elderly, including sudden object movement, falling sound, and arguing sound, and detect accidents caused by the elderly arguing; set the number of times of the elderly's accident characteristics in the current region on a single day, and the formula for calculating the accident coefficient Yw is: Where LS represents the probability value of historical accidents in the current region, N accident It is represented by the number of characteristic accident events of the elderly in the current region, and sjT is represented by the observation period, including single day, week and month; to quantify the characteristic of accident events of the elderly in the current region within a period of time N accident The value of the number of times.

8. The digital twin technology-based security risk management and control system for nursing homes according to claim 1 is characterized by: The behavior acquisition unit further includes a facility demand acquisition unit, which is used to collect the preference data of the elderly for different facilities, obtained through survey documents, and calculate the implementation hobby grading and data; And it is used to monitor the usage frequency of the facilities in the elderly's leisure area, including the daily occupancy time of the facilities, obtained by using sensors or timers, and calculate the facility demand coefficient Sx through the overall facility usage coverage; In the formula, FF represents the usage coverage value of the facilities in the current region, FU represents the facility usage frequency value, and DHRS represents the number of people waiting for the facility usage by the elderly; W5, W6, and W7 respectively represent the weight values of the usage coverage value FF of the facilities in the current region, the facility usage frequency value FU, and the number of people DHRS waiting for the facility usage by the elderly, and 0.35 < W5 < 0.56, 0.35 < W6 < 0.76, 0.85 < W7 < 0.96, and W5 + W6 = W7 ≥ 1.

65.

9. The digital twin technology-based security risk management and control system for nursing homes according to claim 8 is characterized by: The associated formulas for the fall factor U1, protection factor U2, and demand factor T3 are obtained as follows: U1 = Njd * Sd U2 = Fh * Yw U3 = Zc + Sx The fall factor U1, the protection factor U2 and the demand factor T3 are compared with the preset thresholds, wherein the preset thresholds include the fall threshold T d , protection threshold T f and the demand threshold T s ; When the fall factor U1> fall threshold T d When the risk of falling is When the protection factor U2> protection threshold T f When the risk is , it is considered as a protection risk; When the demand factor T3> the demand threshold T s When , it is determined to be demand risk.

10. The digital twin technology-based security risk management and control system for nursing homes according to claim 9 is characterized by: The warning unit includes a trigger alarm unit, a strengthened monitoring unit, and an assistance providing unit; The trigger alarm unit is used to generate corresponding alarm notifications according to the fall risk, protection risk and demand risk, and remind the staff of the risk situation in the corresponding area; The enhanced monitoring unit is used to increase the monitoring frequency of the corresponding areas of the current fall risk, protection risk and demand risk, so as to facilitate the timely discovery of problems; The auxiliary unit is used to provide the elderly with caring handrails, railings and facilities to provide support and protection.

Images