Digital-based nursing home operation management method and system

Abstract

The application is specifically a digital-based operation management method and system for old-age homes, and relates to the technical field of smart old-age care, comprising: setting environment evolution parameters and old-age state degradation parameters, and performing forward time deduction in a home environment digital twin to generate a risk evolution time sequence curve.In the application, a three-layer coupled structure of a home environment digital twin is established, including an environment element layer, a behavior simulation layer and a risk calculation layer, the environment space data is associated with the old-age behavior ability data, the dynamic interaction process of the human body and the environment elements in the virtual environment is simulated, the technical problem that the traditional static assessment method cannot capture the dynamic coupling relationship between the environment elements and the old-age state is solved, and the technical effects of being able to predict the risk evolution trend, identify hidden risk points related to specific activities, prioritize the reconstruction scheme based on quantitative data, and realize active prevention and control of the home environment risk are achieved.

Description

Technical Field

[0001] This invention relates to the field of smart elderly care technology, and in particular to a digital-based method and system for the operation and management of elderly care institutions. Background Technology

[0002] In the field of smart elderly care, home safety assessment is a crucial step in ensuring the quality of life for seniors. Existing smart elderly care platforms typically employ regular manual inspections or environmental monitoring based on fixed sensors for home safety assessments. Safety assessors score the home environment according to a standard checklist, or the system uses sensor data such as temperature, humidity, and smoke to determine the presence of immediate hazards. The assessment results reflect the environmental conditions at the time of the assessment.

[0003] However, the risks in the home environment for older adults are dynamic and evolving: changes in furniture placement may create new tripping hazards, seasonal changes affect the slipperiness of the floor, and the decline in the mobility of older adults alters their interaction with the environment.

[0004] The aforementioned static assessment methods cannot capture the dynamic coupling relationship between environmental factors and the elderly's condition, nor can they predict the evolution trend of risks. As a result, safety renovation recommendations lag behind risk development, making it difficult to achieve proactive prevention and control of home environment risks. Summary of the Invention

[0005] The purpose of this invention is to propose a digital-based operation and management method and system for elderly care institutions in order to solve the above-mentioned problems.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: Digital-based operational management methods for elderly care institutions include: Acquire spatial structure data of the elderly’s home environment, and generate a static spatial model of the home environment based on the spatial structure data; Acquire mobility assessment data and daily activity trajectory data of the elderly, and generate a digital profile of the elderly’s behavioral capabilities based on the mobility assessment data and daily activity trajectory data; The static spatial model of the home environment is associated with the digital profile of the elderly’s behavioral abilities to establish a digital twin of the home environment. The digital twin of the home environment includes a three-layer coupled structure of environmental element layer, behavior simulation layer and risk calculation layer. The process of elderly people performing typical daily activities is simulated in the digital twin of the home environment. The interaction risk value between the human body and environmental elements during each activity is calculated, and an activity-risk mapping matrix is ​​generated. By setting environmental evolution parameters and elderly person status degradation parameters, forward time extrapolation is performed in the digital twin of the home environment to generate a risk evolution time series curve; The risk inflection points and key risk factors in the risk evolution time series curve are analyzed. Based on the intervention effect, the risk reduction amount of different renovation schemes is simulated and calculated, and a list of home environment age-friendly renovation recommendations is generated in order of priority.

[0007] Preferably, the spatial structure data includes room layout dimensions, furniture location coordinates, floor material distribution, lighting equipment location and brightness parameters; the home environment static space model uses a three-dimensional coordinate system to represent the positional relationships and physical attributes of various environmental elements within the home space.

[0008] Preferably, the mobility assessment data includes gait characteristic parameters, balance ability indicators, visual and hearing levels, and cognitive function scores; the daily activity trajectory data is represented by a heat map to characterize the frequency distribution of activities of the elderly in different areas of their home.

[0009] Preferably, the environmental element layer is used to store and manage various environmental element data in the static space model of the home environment; the behavior simulation layer is used to load the digital profile of the elderly's behavioral abilities and drive the virtual human body to simulate movement in the environmental element layer based on the parameters of the digital profile of the elderly's behavioral abilities; the risk calculation layer is used to receive data from the environmental element layer and the behavior simulation layer and calculate the risk value in the process of the virtual human body interacting with environmental elements.

[0010] Preferably, the behavior simulation layer drives virtual human movement based on the parameters of the digital profile of the elderly's behavioral abilities, including: determining the walking movement mode of the virtual human body using gait feature parameters, determining the posture stability constraints of the virtual human body when switching actions using balance ability indicators, and determining the perception response distance of the virtual human body to obstacles using visual acuity values.

[0011] Preferably, the method for calculating the interactive risk value is as follows: for each type of activity in each region, the weighted risk contribution values ​​of multiple risk factors are summed to obtain the interactive risk value; the risk contribution value of each risk factor is obtained by dividing the product of the normalized value of the corresponding environmental element parameter and the normalized value of the human behavioral ability parameter by the safety threshold of the risk factor; the weight coefficient of each risk factor is determined by the analytic hierarchy process.

[0012] Preferably, the typical daily activities include nighttime getting up routes, toilet use, and kitchen operation scenarios; the row dimension of the activity-risk mapping matrix is ​​the activity type, the column dimension is the environmental region, and the matrix element values ​​are the risk values ​​of the corresponding activities in the corresponding regions.

[0013] Preferably, the forward time extrapolation includes: dividing a preset period into multiple time steps; within each time step, updating the attribute values ​​of each element in the environmental element layer according to the environmental evolution parameters, and updating the behavioral ability parameters in the behavioral simulation layer according to the elderly person's state deterioration parameters; re-executing the activity simulation process and calculating the comprehensive risk index corresponding to the time step; and connecting the comprehensive risk indices of each time step in chronological order to form the risk evolution time series curve.

[0014] Preferably, the method for identifying the risk inflection point is as follows: calculate the first derivative value of each point on the risk evolution time series curve, and mark the point where the first derivative value exceeds a preset threshold as the risk inflection point; the method for identifying the key risk factor is as follows: at the risk inflection point, fix each individual parameter in the environmental evolution parameter and the elderly state degradation parameter respectively, recalculate the change in risk value, and determine the element corresponding to the parameter with the largest change in risk value as the key risk factor.

[0015] A digital-based operation and management system for elderly care institutions includes: The static space model generation module is used to acquire spatial structure data of the elderly’s home environment and generate a static space model of the home environment based on the spatial structure data. The behavioral ability profile generation module is used to acquire the mobility assessment data and daily activity trajectory data of the elderly, and generate a digital profile of the elderly's behavioral ability based on the mobility assessment data and the daily activity trajectory data. The digital twin creation module is used to associate the static spatial model of the home environment with the digital profile of the elderly's behavioral abilities, and to create a digital twin of the home environment with a three-layer coupled structure including an environmental element layer, a behavior simulation layer, and a risk calculation layer. The activity risk simulation module is used to simulate the process of elderly people performing typical daily activities in the digital twin of the home environment, calculate the interaction risk value between the human body and environmental elements during each activity, and generate an activity-risk mapping matrix. The risk evolution simulation module is used to set environmental evolution parameters and elderly status degradation parameters, and to perform forward time simulation in the digital twin of the home environment to generate risk evolution time series curves. The renovation suggestion generation module is used to analyze the risk inflection point and key risk factors in the risk evolution time series curve, simulate and calculate the risk reduction of different renovation schemes based on the intervention effect, and generate a list of home environment age-friendly renovation suggestions sorted by priority.

[0016] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. This invention establishes a digital twin of the home environment with a three-layer coupled structure, including an environmental element layer, a behavior simulation layer, and a risk calculation layer. It links environmental spatial data with the behavioral ability data of the elderly and simulates the dynamic interaction process between the human body and environmental elements in a virtual environment. This solves the technical problem that traditional static assessment methods cannot capture the dynamic coupling relationship between environmental elements and the state of the elderly. It achieves the technical effects of being able to predict the evolution trend of risks, identify hidden risk points related to specific activities, prioritize renovation plans based on quantitative data, and realize proactive prevention and control of home environment risks.

[0017] 2. This invention constructs a digital twin of the home environment and a digital profile of the elderly's behavioral abilities to accurately simulate interactive risks in daily activities, generating an activity-risk mapping matrix. Simultaneously, it uses forward time extrapolation to predict risk evolution trends, identify risk inflection points and key risk-causing factors, and then output priority modification suggestions. This process achieves a shift from "passively responding to risks" to "proactively predicting and precisely intervening," which can not only specifically reduce safety risks for the elderly in their home activities and improve the safety and suitability of elderly care services, but also optimize the allocation of operational resources in elderly care institutions, reduce resource waste caused by blind modifications, improve operational management efficiency, provide more personalized and refined elderly care services, and effectively guarantee the quality of life for the elderly at home. Attached Figure Description

[0018] Further details, features, and advantages of this application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 This is a flowchart of the method of the present invention; Figure 2 A sub-flowchart for performing forward time extrapolation and generating risk evolution time-series curves in a digital-based elderly care institution operation and management method provided in an embodiment of the present invention; Figure 3 This is a sub-flowchart for analyzing risk inflection points and generating a list of age-friendly renovation suggestions in the digital-based operation and management method for elderly care institutions provided in this embodiment of the invention. Detailed Implementation

[0019] Several embodiments of this application will now be described in more detail with reference to the accompanying drawings to enable those skilled in the art to implement this application. This application may be embodied in many different forms and for various purposes and should not be limited to the embodiments set forth herein. These embodiments are provided to make this application thorough and complete, and to fully convey the scope of this application to those skilled in the art. The embodiments described do not limit this application.

[0020] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It will be further understood that terms such as those defined in commonly used dictionaries shall be interpreted as having a meaning consistent with their meaning in the relevant field and / or the context of this specification, and shall not be interpreted in an idealized or overly formal sense unless expressly defined herein.

[0021] Example 1

[0022] Its specific implementation method is combined with the appendix Figure 1 To be continued Figure 3 Please provide a detailed explanation.

[0023] In this embodiment, it includes: Step 1: Obtain home environment space data and generate a static space model: This study acquires spatial structure data of the home environment for elderly individuals and generates a static spatial model based on this data. The spatial structure data includes room layout dimensions, furniture location coordinates, floor material distribution, and lighting fixture location and brightness parameters. The static spatial model uses a three-dimensional coordinate system to represent the positional relationships and physical attributes of various environmental elements within the home space.

[0024] It should be noted that the above room layout dimensions include the length, width, and height of each room, as well as the location and opening size of doors and windows; the above furniture location coordinates include the center point coordinates and outer contour boundaries of furniture such as beds, tables, chairs, and cabinets; the above floor material distribution includes the boundary division of different material areas such as tiles, wood flooring, and carpets, and the corresponding coefficients of friction; the above lighting equipment location and brightness parameters include the installation location, illumination range, and brightness values ​​of each lighting equipment at different times.

[0025] In this embodiment of the application, in order to improve the accuracy of the spatial model, obstacle distribution data in the home environment is also obtained. The obstacle distribution data includes the location information of elements that may affect passage safety, such as the direction of ground cables, threshold height, and step position. The obstacle distribution data is superimposed on the static spatial model of the home environment to form an enhanced static spatial model with obstacle annotations.

[0026] Step 2: Obtain mobility data of the elderly and generate a digital profile of their behavioral abilities: The study acquires mobility assessment data and daily activity trajectory data for older adults, and generates digital profiles of their behavioral abilities based on these data. Mobility assessment data includes gait characteristics, balance indicators, visual and hearing levels, and cognitive function scores. Daily activity trajectory data is presented as heatmaps to represent the frequency distribution of older adults' activities in different areas of their home.

[0027] It should be noted that the above gait characteristic parameters include gait frequency, stride length, gait cycle, and gait symmetry indicators; the above balance ability indicators include static balance score and dynamic balance score; the above vision and hearing levels include corrected visual acuity value and hearing loss in decibels; and the above cognitive function scores are obtained based on standardized cognitive scales. The above daily activity trajectory heatmap is generated by statistically aggregating the location data of the elderly within a preset time period, and the heatmap value represents the activity frequency at that location.

[0028] In this embodiment of the application, in order to enable the digital profile of the elderly’s behavioral abilities to reflect the time-related differences of the elderly, the mobility fluctuation data of the elderly at different time periods are also obtained. The mobility fluctuation data includes the gait stability difference values ​​of the morning, night and daytime periods. The mobility fluctuation data is incorporated into the digital profile of the elderly’s behavioral abilities to form a multi-dimensional digital profile of behavioral abilities that includes the time period dimension.

[0029] Step 3, Create a digital twin of your home environment: A digital twin of the home environment is created by linking a static spatial model of the home environment with a digital profile of the elderly's behavioral abilities. The digital twin of the home environment comprises a three-layer coupled structure: an environmental element layer, a behavioral simulation layer, and a risk calculation layer.

[0030] It should be noted that the aforementioned environmental element layer is used to store and manage various environmental element data in the static space model of the home environment, including spatial geometric data, material attribute data, and lighting data; the aforementioned behavior simulation layer is used to load the digital profile of the elderly's behavioral abilities and drive the virtual human body to simulate movement in the environmental element layer based on the parameters of the digital profile of the elderly's behavioral abilities; the aforementioned risk calculation layer is used to receive data from the environmental element layer and the behavior simulation layer and calculate the risk value in the process of the virtual human body interacting with environmental elements.

[0031] It should be noted that in the above three-layer coupling structure, the environmental element layer provides spatial constraints and material property parameters to the behavior simulation layer, the behavior simulation layer provides human motion trajectory and posture data to the risk calculation layer, and the risk calculation layer performs risk quantification calculation by combining the hazard source distribution of the environmental element layer and the human state of the behavior simulation layer.

[0032] Furthermore, the specific method by which the aforementioned behavioral simulation layer drives virtual human movement based on the parameters of the digital profile of elderly behavioral abilities is as follows: Gait characteristic parameters (step frequency, stride length, gait cycle, gait symmetry) determine the virtual human's walking movement pattern; balance ability indicators (static balance score, dynamic balance score) determine the virtual human's posture stability constraints during transitions such as turning and stopping; and visual acuity values ​​determine the virtual human's perception response distance to obstacles. This ensures that the virtual human's movement behavior matches the actual mobility of the corresponding elderly person. When the digital profile of elderly behavioral abilities includes time-period dimension data, the corresponding time-period mobility parameters are loaded during simulations at different time periods to reflect the impact of time-period differences on movement behavior.

[0033] In this embodiment of the application, in order to achieve dynamic synchronization between the digital twin of the home environment and the actual environment, a data update interface is also established. The data update interface is used to receive real-time data collected by sensors in the home environment. When a change in environmental elements is detected, the corresponding data of the environmental element layer in the digital twin of the home environment is automatically updated to maintain the consistency between the digital twin of the home environment and the physical environment.

[0034] Step 4: Simulate daily activities and generate an activity-risk mapping matrix: The process of elderly people performing typical daily activities is simulated in a digital twin of their home environment. The interaction risk values ​​between the human body and environmental elements during each activity are calculated, generating an activity-risk mapping matrix. Typical daily activities include nighttime getting up routes, toileting actions, and kitchen operation scenarios. The row dimension of the activity-risk mapping matrix represents the activity type, the column dimension represents the environmental region, and the matrix element values ​​are the risk values ​​of the corresponding activities in the corresponding regions.

[0035] It should be noted that the simulation process for the aforementioned nighttime getting-up path includes: based on the nighttime gait parameters and balance ability indicators in the digital profile of elderly behavioral abilities, driving virtual human movement along the bedroom-to-bathroom path in the environmental element layer, and calculating the tripping risk value and fall risk value at each location along the path by the risk calculation layer. The simulation process for the aforementioned toileting action includes: simulating the sitting and standing sequence of the virtual human body, and calculating the instability risk value caused by insufficient support or narrow space during the action. The simulation process for the aforementioned kitchen operation scenario includes: simulating the standing operation and item retrieval actions of the virtual human body in the kitchen area, and calculating the slipping risk value and falling object risk value caused by slippery floors or retrieving items from heights.

[0036] It should be noted that the calculation method for the above-mentioned interaction risk value is as follows: ; in, Indicates the first Class of activities in the Regional interaction risk value, Indicates the number of risk factors. Indicates the sequence number of the risk factor. Indicates the first The weighting coefficients of each risk factor Indicates the first The dimensionless values ​​of the environmental element parameters corresponding to each risk factor after normalization. Indicates the first The dimensionless values ​​of the human behavioral ability parameters corresponding to each risk factor after normalization. Indicates the first Risk calculation function for each risk factor.

[0037] The above The calculation method is as follows: ; in, Indicates the first The safety threshold for each risk factor is derived from historical risk data and is a normalized dimensionless value; when When it exceeds 1, it indicates that the first... The risk factors have exceeded the safe range given the current combination of environment and behavioral capabilities.

[0038] Furthermore, The values ​​are derived from the attribute values ​​of the corresponding elements in the environmental element layer, such as the ground friction coefficient, obstacle height, and lighting brightness. The values ​​are derived from corresponding ability parameters in the digital profile of elderly behavioral abilities, such as gait stability score, balance score, and visual acuity level. Because... and Since physical quantities originate from different types and have inconsistent dimensions, they must be considered before being included in the calculations of the above formulas. and Each parameter is mapped to a mean normalization method based on the range. Intervals are used to eliminate the influence of dimensional differences on the calculation results; Based on the statistical analysis of the normalized data, and also being dimensionless, its value range is as follows: .

[0039] Furthermore, the aforementioned weighting coefficients The determination method is as follows: using the analytic hierarchy process (AHP), domain experts compare the relative importance of each risk factor pairwise to construct a judgment matrix. The eigenvector corresponding to the largest eigenvalue of the judgment matrix is ​​calculated, and the weight coefficients of each risk factor are obtained after normalization. Furthermore, the logical consistency of the judgment matrix is ​​verified through the consistency ratio to ensure the rationality of the weight allocation.

[0040] In this embodiment of the application, in order to identify continuous risk changes during the activity, the instantaneous risk values ​​of each sampling point on the virtual human motion trajectory during the simulation are also recorded to generate an activity risk time series sequence. The risk peak point and its corresponding position coordinates and action stage are identified from the activity risk time series sequence, and the risk peak point is marked in the activity-risk mapping matrix as a high-risk interaction point.

[0041] Step 5: Perform forward time extrapolation and generate risk evolution time series curves: By setting environmental evolution parameters and elderly person's condition deterioration parameters, forward time extrapolation is performed in a digital twin of the home environment to simulate the cumulative impact of environmental changes and capacity degradation on risks within a preset future period, generating a risk evolution time series curve. The risk evolution time series curve uses time as the horizontal axis and a comprehensive risk index as the vertical axis to represent the overall risk level of the home environment at each time point within the preset period.

[0042] It should be noted that the aforementioned environmental evolution parameters include furniture wear coefficient, floor material aging coefficient, and lighting equipment attenuation coefficient, which respectively characterize the rate of degradation of environmental elements over time. The aforementioned elderly person's condition degradation parameters include gait ability degradation coefficient, balance ability degradation coefficient, and vision degradation coefficient, which respectively characterize the rate of decline in various mobility abilities of the elderly person over time. The aforementioned preset period can be set to three months, six months, or one year.

[0043] It should be noted that the specific process of the above forward time extrapolation includes the following steps: Step 5.1: Divide the preset period into multiple time steps; Step 5.2: Within each time step, update the attribute values ​​of each element in the environmental element layer according to the environmental evolution parameters; Step 5.3: Update the behavioral ability parameters in the behavioral simulation layer based on the elderly person's state deterioration parameters; Step 5.4: Re-execute the activity simulation process in Step 4 and calculate the comprehensive risk index corresponding to this time step; Step 5.5: Connect the comprehensive risk indices of each time step in chronological order to form a risk evolution time series curve.

[0044] Furthermore, the specific method for updating the environmental element layer attribute values ​​based on environmental evolution parameters in step 5.2 above is as follows: multiply the cumulative duration corresponding to the current time step by the degradation coefficient of the corresponding element to obtain the degradation amount of the corresponding element relative to the initial state, and subtract the degradation amount from the initial attribute value to obtain the updated value for the current time step; the method for updating the behavioral ability parameters based on the elderly's state degradation parameters in step 5.3 above is the same: subtract the cumulative degradation amount from the initial assessment value of each action ability to obtain the updated value for the current time step, and substitute the updated environmental element attribute values ​​and behavioral ability parameters into the risk calculation formula in step 4 to calculate the comprehensive risk index for that time step.

[0045] Furthermore, the comprehensive risk index in step 5.4 above is calculated as follows: the interaction risk values ​​of all activity types and environmental areas in the activity-risk mapping matrix generated in step 4 are calculated. A weighted summation is performed, with the weights determined based on the actual frequency of each activity type within the corresponding time period of that time step. Activity types with higher frequency of occurrence are given higher weights, so that the comprehensive risk index can reflect the impact of the activity distribution characteristics at different time points on the overall risk level, and realize the specific embodiment of the time dimension in risk quantification.

[0046] In this embodiment of the application, in order to improve the accuracy of forward time extrapolation, seasonal factor parameters are also introduced. The seasonal factor parameters include the range of indoor temperature and humidity changes and the ground dryness coefficient corresponding to different seasons. During the forward time extrapolation process, the ground friction coefficient and lighting demand parameters in the environmental element layer are adjusted according to the season corresponding to the extrapolation time point, so that the risk evolution time series curve can reflect seasonal risk fluctuations.

[0047] Step 6: Analyze risk inflection points and generate a list of age-friendly renovation recommendations: This study analyzes the risk inflection point and key risk factors in the risk evolution time series curve. Based on the intervention effect, it simulates and calculates the risk reduction of different renovation schemes, generating a priority-ranked list of home environment aging-friendly renovation recommendations and quantitative indicators of expected risk improvement. The risk inflection point is the point in time in the risk evolution time series curve where the risk growth rate changes significantly. Key risk factors are the environmental elements or capacity degradation items that contribute the most to the risk inflection point.

[0048] It should be noted that the method for identifying the aforementioned risk inflection points is as follows: Calculate the first derivative value of each point on the risk evolution time series curve, and mark the points where the first derivative value exceeds a preset threshold as risk inflection points. The preset threshold is determined based on the statistical distribution of the overall slope of the risk evolution time series curve, specifically by adding one standard deviation to the mean of the first derivative values ​​of each point on the risk evolution time series curve to distinguish between normal fluctuations and significant abrupt changes. The method for identifying the aforementioned key risk factors is as follows: At the risk inflection point, fix each individual parameter in the environmental evolution parameters and the elderly's state degradation parameters, recalculate the change in risk value, and determine the element corresponding to the parameter with the largest change in risk value as the key risk factor.

[0049] It should be noted that the specific process of simulating the above intervention effect includes the following steps: Step 6.1: For each key risk factor, set up a corresponding renovation plan, which includes measures such as adding handrails, replacing non-slip flooring, adding night lights, and adjusting furniture layout; Step 6.2: Simulate the environmental state after implementing each renovation plan in the digital twin of the home environment; Step 6.3: Re-execute the forward timeline to calculate the risk evolution timeline curve after the modification; Step 6.4: Compare the risk evolution time series curves before and after the modification, and calculate the risk reduction amount of each modification scheme; Step 6.5: Prioritize the risks based on the ratio of risk reduction to renovation costs; the higher the ratio, the higher the priority.

[0050] Furthermore, the specific method for simulating the environmental state after implementing the renovation plan in the digital twin of the home environment in step 6.2 above is as follows: For each renovation measure, the attribute values ​​of the corresponding elements in the environmental element layer are directly modified to reflect the physical state after the renovation. For example, the measure of adding handrails corresponds to adding handrail support point markings in the spatial geometry data along the toilet area and the nighttime path, and updating the support condition parameters in the instability risk calculation of this area to the state with handrail support; the measure of replacing non-slip flooring corresponds to updating the floor friction coefficient of the corresponding area to the friction coefficient value of the non-slip material; the measure of adding nightlights corresponds to updating the lighting brightness parameters of the corresponding area to the brightness value after the addition; the measure of adjusting furniture layout corresponds to updating the furniture position coordinates and passage width data. After the above attribute values ​​are modified, the activity simulation and risk calculation in step 4 are re-executed with the updated environmental element layer data as the initial state for the risk extrapolation after the renovation.

[0051] In this embodiment of the application, in order to provide an evaluation of the effectiveness of the combined renovation scheme, a multi-scheme joint simulation is also performed. Multiple individual renovation schemes are combined, and the environmental state after the implementation of the combined renovation scheme is simulated in the digital twin of the home environment. The comprehensive risk reduction of the combined renovation scheme is calculated, and scheme combinations with synergistic or conflicting effects are identified. The evaluation results of the combined renovation scheme are included in the list of home environment age-friendly renovation recommendations, providing a combined optimization reference for renovation decisions.

[0052] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0053] It should be noted that, in this document, the use of relational terms such as "first" and "second" is merely for distinguishing one entity or operation from another, and does not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0054] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0055] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0056] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0057] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0058] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0059] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0060] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A digital-based method for the operation and management of elderly care institutions, characterized in that: include: Acquire spatial structure data of the elderly’s home environment, and generate a static spatial model of the home environment based on the spatial structure data; Acquire mobility assessment data and daily activity trajectory data of the elderly, and generate a digital profile of the elderly’s behavioral capabilities based on the mobility assessment data and daily activity trajectory data; The static spatial model of the home environment is associated with the digital profile of the elderly’s behavioral abilities to establish a digital twin of the home environment. The digital twin of the home environment includes a three-layer coupled structure of an environmental element layer, a behavioral simulation layer, and a risk calculation layer. The process of elderly people performing typical daily activities is simulated in the digital twin of the home environment. The interaction risk value between the human body and environmental elements during each activity is calculated, and an activity-risk mapping matrix is ​​generated. Environmental evolution parameters and elderly person condition deterioration parameters are set, and forward time extrapolation is performed in the digital twin of the home environment to generate a risk evolution time series curve. The forward time extrapolation includes: dividing a preset period into multiple time steps; updating the attribute values ​​of each element in the environmental element layer according to the environmental evolution parameters, and updating the behavioral ability parameters in the behavioral simulation layer according to the elderly person condition deterioration parameters; re-executing the activity simulation process and calculating the comprehensive risk index corresponding to that time step; and connecting the comprehensive risk indices of each time step in chronological order to form the risk evolution time series curve. The risk inflection point and key risk factors in the risk evolution time series curve are analyzed. Based on the intervention effect, the risk reduction of different renovation schemes is simulated and calculated, and a list of home environment age-friendly renovation suggestions is generated in order of priority. The method for identifying the risk inflection point is as follows: calculate the first derivative value of each point on the risk evolution time series curve, and mark the point where the first derivative value exceeds a preset threshold as the risk inflection point. The method for identifying the key risk factors is as follows: at the risk inflection point, fix each individual parameter in the environmental evolution parameter and the elderly person's state deterioration parameter, recalculate the change in risk value, and determine the element corresponding to the parameter with the largest change in risk value as the key risk factor.

2. The digital-based operation and management method for elderly care institutions according to claim 1, characterized in that, The spatial structure data includes room layout dimensions, furniture location coordinates, floor material distribution, lighting equipment location and brightness parameters; the home environment static space model uses a three-dimensional coordinate system to represent the positional relationships and physical attributes of various environmental elements within the home space.

3. The digital-based operation and management method for elderly care institutions according to claim 1, characterized in that, The mobility assessment data includes gait characteristic parameters, balance ability indicators, visual and hearing levels, and cognitive function scores; the daily activity trajectory data is represented by a heat map to depict the frequency distribution of elderly people's activities in different areas of their home.

4. The digital-based operation and management method for elderly care institutions according to claim 1, characterized in that, The environmental element layer is used to store and manage various environmental element data in the static space model of the home environment; the behavior simulation layer is used to load the digital profile of the elderly's behavior ability and drive the virtual human body to simulate movement in the environmental element layer based on the parameters of the digital profile of the elderly's behavior ability; the risk calculation layer is used to receive data from the environmental element layer and the behavior simulation layer and calculate the risk value in the process of the virtual human body interacting with environmental elements.

5. The digital-based operation and management method for elderly care institutions according to claim 4, characterized in that, The behavior simulation layer drives virtual human movement based on parameters of the digital profile of the elderly's behavioral abilities, including: determining the walking movement pattern of the virtual human body using gait feature parameters, determining the posture stability constraints of the virtual human body when switching actions using balance ability indicators, and determining the perception response distance of the virtual human body to obstacles using visual acuity values.

6. The digital-based operation and management method for elderly care institutions according to claim 1, characterized in that, The method for calculating the interaction risk value is as follows: for each type of activity in each region, the weighted risk contribution values ​​of multiple risk factors are summed to obtain the interaction risk value; the risk contribution value of each risk factor is obtained by dividing the product of the normalized value of the corresponding environmental element parameter and the normalized value of the human behavioral ability parameter by the safety threshold of the risk factor; the weight coefficient of each risk factor is determined by the analytic hierarchy process.

7. The digital-based operation and management method for elderly care institutions according to claim 1, characterized in that, The typical daily activities include nighttime getting up routes, toilet use, and kitchen operation scenarios; the row dimension of the activity-risk mapping matrix is ​​the activity type, the column dimension is the environmental region, and the matrix element values ​​are the risk values ​​of the corresponding activities in the corresponding regions.

8. A digital-based operation and management system for elderly care institutions, wherein the system is implemented according to any one of claims 1-7, characterized in that, include: The static space model generation module is used to acquire spatial structure data of the elderly’s home environment and generate a static space model of the home environment based on the spatial structure data. The behavioral ability profile generation module is used to acquire the mobility assessment data and daily activity trajectory data of the elderly, and generate a digital profile of the elderly's behavioral ability based on the mobility assessment data and the daily activity trajectory data. The digital twin creation module is used to associate the static spatial model of the home environment with the digital profile of the elderly's behavioral abilities, and to create a digital twin of the home environment with a three-layer coupled structure including an environmental element layer, a behavioral simulation layer, and a risk calculation layer. The activity risk simulation module is used to simulate the process of elderly people performing typical daily activities in the digital twin of the home environment, calculate the interaction risk value between the human body and environmental elements during each activity, and generate an activity-risk mapping matrix. The risk evolution simulation module is used to set environmental evolution parameters and elderly person status degradation parameters, and to perform forward time-series simulation in the digital twin of the home environment to generate a risk evolution time-series curve. The forward time-series simulation includes: dividing a preset period into multiple time steps; updating the attribute values ​​of each element in the environmental element layer according to the environmental evolution parameters, and updating the behavioral ability parameters in the behavioral simulation layer according to the elderly person status degradation parameters; re-executing the activity simulation process and calculating the comprehensive risk index corresponding to that time step; and connecting the comprehensive risk indices of each time step in chronological order to form the risk evolution time-series curve. The renovation suggestion generation module is used to analyze the risk inflection points and key risk factors in the risk evolution time series curve, simulate and calculate the risk reduction of different renovation schemes based on the intervention effect, and generate a list of home environment age-friendly renovation suggestions sorted by priority. The method for identifying the risk inflection point is as follows: calculate the first derivative value of each point on the risk evolution time series curve, and mark the point where the first derivative value exceeds a preset threshold as the risk inflection point. The method for identifying the key risk factor is as follows: at the risk inflection point, fix each individual parameter in the environmental evolution parameter and the elderly person's state deterioration parameter, recalculate the change in risk value, and determine the element corresponding to the parameter with the largest change in risk value as the key risk factor.

Images