Health grading-based home-based care nurse scheduling method and corresponding equipment

Abstract

The embodiment of the invention provides a home-based care personnel scheduling method and corresponding equipment based on health grading, and the method comprises the steps: building an old people nursing demand based on the physical condition, residence coordinates and reservation time window of the old people and the grading service duration based on the health condition; constructing a nursing delay risk function and a service satisfaction function according to nursing requirements of old people; establishing a nursing personnel scheduling model aiming at minimizing the nursing delay risk and maximizing the service satisfaction; and solving the nurse scheduling model through the whale optimization algorithm to obtain the service path of the nurse, so that the method has the beneficial effect of improving the service quality, and is suitable for the field of pension services.

Description

Technical Field

[0001] The present application relates to the technical field of elderly care services, and in particular, to a method and corresponding equipment for scheduling home-based elderly care staff based on health grading. Background Art

[0002] As my country's aging population accelerates, the size of its elderly population continues to expand. By the end of 2023, my country's population aged 60 and over will be approximately 297 million, accounting for 21.1% of the total population. This large elderly population has brought about a diverse demand for elderly care services, especially the annual increase in the proportion of elderly people requiring certain nursing support. According to statistics, approximately 20% of my country's elderly are disabled or semi-disabled and require long-term professional nursing services. However, in the face of growing demand, my country's elderly care resources are severely insufficient. As of 2021, there are only fewer than 3 caregivers per 1,000 elderly people, far lower than the level of 20-50 caregivers per 1,000 elderly people in developed countries. This nursing resource gap not only limits the accessibility of elderly care services, but also poses severe challenges to the efficiency and quality of elderly care services.

[0003] The "9073" elderly care model means: 90% of the elderly are self-cared for by their families, adopting family-based home care; 7% of the elderly enjoy community home care services, providing day care; and 3% of the elderly enjoy institutional elderly care services.

[0004] Home-based care, as the most crucial component of my country's "9073" elderly care model, meets the needs of over 90% of seniors and has become a core component of the current elderly care service system. Unlike centralized institutional care, home-based care relies on the elderly's families and communities. While meeting the psychological and emotional needs of seniors, it also faces challenges such as fragmented services and inefficient resource utilization. This is particularly true for seniors with varying health conditions, with significant variations in service content and time requirements, from daily care to medical support. This poses significant challenges to resource allocation for service agencies.

[0005] How to rationally allocate nursing staff to ensure timely provision of elderly care services and improve the quality of home-based elderly care services is a key issue that needs to be addressed in community-based home-based elderly care.

[0006] In 1997, scholars Begur et al. first defined the home healthcare and scheduling problem for caregiver scheduling in the home-based elderly care model. The home healthcare scheduling problem has garnered significant attention from the academic community. Existing research considers this problem within the scope of the vehicle routing problem (VRP) and the traveling salesman problem (TSP). Most literature considers factors such as service time windows, care cycles, and satisfaction, and uses precise and intelligent algorithms to solve it.

[0007] However, this type of approach only considers operating costs, service satisfaction, and service duration, and lacks consideration of the risks borne by the elderly during the service process. Studies have shown that if the home care needs of disabled elderly people cannot be met in a timely manner, adverse home care events will occur. Unmet daily life needs will increase the incidence of falls and readmissions of disabled elderly people. Unmet drug management needs will lead to worsening of the disease, increased risk of hospitalization and irreversible damage, resulting in prolonged recovery period of elderly disabled patients, deterioration of health status, and serious impact on their quality of life.

[0008] Therefore, in home-based elderly care services, it is particularly important to adopt a nursing staff scheduling method that comprehensively considers the satisfaction of the elderly and the risk of adverse nursing events to improve the overall service quality. Summary of the Invention

[0009] In order to solve one of the above-mentioned technical defects, the embodiments of the present application provide a method and corresponding equipment for scheduling home-based elderly care staff based on health grading.

[0010] A first aspect of the embodiments of the present application provides a method for scheduling home-based elderly care workers based on health grading, including: Constructing elderly care needs based on their physical condition, residence coordinates, appointment time windows, and graded service duration based on health status; According to the nursing needs of the elderly, a nursing delay risk function and a service satisfaction function are constructed; Establish a nursing staff scheduling model with the goal of minimizing the risk of care delay and maximizing service satisfaction; The nursing staff scheduling model is solved using the whale optimization algorithm to obtain the nursing staff's service path.

[0011] A second aspect of the embodiments of the present application provides a device for scheduling home-based elderly care workers based on health grading, including: Demand construction unit, used to construct elderly care needs based on the elderly's physical condition, residence coordinates, appointment time window and graded service duration based on health status; The scheduling model establishment unit is used to construct a care delay risk function and a service satisfaction function based on the care needs of the elderly; and to establish a caregiver scheduling model with the goal of minimizing the care delay risk and maximizing the service satisfaction; The service path solving unit is used to solve the nursing staff scheduling model through the whale optimization algorithm to obtain the nursing staff's service path.

[0012] According to a third aspect of an embodiment of the present application, a computer device is provided, comprising: a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0013] By adopting the home-based elderly care nursing staff scheduling method and corresponding equipment based on health grading provided in this application, a nursing staff scheduling model is established with the goal of minimizing the risk of nursing delay and maximizing service satisfaction; by introducing constraints such as the physical condition of the elderly's nursing needs, appointment time windows, and graded service duration based on health status, while ensuring that nursing services are carried out on time, the risk of delayed nursing for the elderly is reduced, the elderly's service satisfaction is increased, and a decision-making basis is provided for the scheduling of nursing staff in community home-based elderly care service centers. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 Schematic diagram of the service model for nursing staff; Figure 2 A flowchart of a method for scheduling home-based elderly care workers based on health grading provided in one embodiment of the present application; Figure 3 This is a schematic diagram of a service satisfaction function in one embodiment of the present application; Figure 4 This is a schematic diagram of a service waiting time risk function in one embodiment of the present application; Figure 5 This is a schematic diagram of the encoding method in the whale optimization algorithm in one embodiment of the present application; Figure 6 In one embodiment of the present application, the nursing staff scheduling model is solved by using the whale optimization algorithm to obtain a flow chart of the nursing staff's service path; Figure 7 This is a diagram of the service path of the nursing staff in a small-scale example; Figure 8 Schematic diagram of the iteration of the whale optimization algorithm in a small-scale example; Figure 9 A schematic diagram showing the comparison of satisfaction results among the elderly in multiple scale examples; Figure 10 A schematic diagram showing the comparison of the elderly care risk calculation results in multiple scale examples; Figure 11 A schematic diagram showing the comparison of solution time results in multi-scale examples. DETAILED DESCRIPTION

[0015] The solutions in the embodiments of the present application can be implemented using various computer languages, for example, the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0016] In order to make the technical solutions and advantages of the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, and are not an exhaustive list of all the embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other unless they conflict.

[0017] like Figure 1 As shown in the figure, in home-based elderly care services, caregivers provide door-to-door services based on the elderly's appointment needs, and return to the home-based elderly care service center after completing daily tasks; the service content covers daily life care (such as: assistance with washing, meals, etc.), basic medical care (such as: blood pressure monitoring, drug injections, etc.), rehabilitation care (such as: sports recovery guidance, etc.) and specialist medical care (such as: chronic disease management, postoperative recovery, etc.).

[0018] In the process of realizing this application, the inventors found that the care needs of the elderly are affected by their health status. As their physical functions decline, the complexity and time requirements of nursing services increase significantly. Especially for disabled and semi-disabled elderly people, their care not only involves longer service time, but also puts higher requirements on the strictness of the service time window.

[0019] To ensure service quality and efficient use of resources, home-based elderly care services need to reasonably arrange the nursing staff's nursing tasks and service routes before the service begins based on the elderly's physical condition and appointment time window; the service time window is an important constraint in scheduling. Different elderly people have different requirements for the timeliness of services due to physical limitations and service expectations. The scheduling plan must meet the time window requirements as much as possible to avoid delays that lead to decreased service satisfaction or increased health risks.

[0020] In response to the above problems, such as Figure 2As shown, the embodiment of the present application provides a method for scheduling home-based elderly care staff based on health grading, including: S10, constructs the elderly care needs based on their physical condition, residence coordinates, appointment time window, and graded service duration based on health status; S20, constructing a care delay risk function and a service satisfaction function based on the care needs of the elderly; S30, establish a nursing staff scheduling model with the goal of minimizing the risk of nursing delay and maximizing service satisfaction; S40, solving the nursing staff scheduling model through the whale optimization algorithm to obtain the nursing staff's service path.

[0021] In the embodiment of the present application, a nursing staff scheduling model is established with the goal of minimizing the risk of nursing delay and maximizing service satisfaction; by introducing constraints such as the physical condition of the elderly's nursing needs, appointment time windows, and graded service duration based on health status, while ensuring that nursing services are carried out on time, the risk of delayed nursing for the elderly is reduced, the elderly's service satisfaction is increased, and a decision-making basis is provided for the scheduling of nursing staff in community home-based elderly care service centers.

[0022] In an optional embodiment of the present application, based on the care needs of the elderly, the following assumptions are made: (1) Nursing staff use home-based elderly care service centers as their starting and ending points; (2) Based on the elderly’s needs for appointment services, the risks incurred during the service process are graded into health categories: healthy, mildly disabled, moderately disabled, and severely disabled; (3) Each caregiver can provide services to elderly people of different health levels at the same speed during the journey without considering special circumstances such as weather and traffic; (4) The service time window of each elderly person is independent and due to different physical conditions, the acceptable waiting time is different, that is, the tolerable time window is different; if the caregiver arrives early, waiting time will be generated; if the caregiver arrives later than the tolerable time window, risks will be generated; (5) The distance between the elderly’s residences was calculated using Euclidean distance; In the above assumptions, the symbols and variable descriptions involved are shown in Table 1.

[0023] Table 1 Symbols and variable descriptions

[0024] In an optional embodiment of the present application, a nursing staff scheduling model is constructed to minimize the risk of nursing delays and maximize service satisfaction while meeting diverse nursing needs, thereby improving the overall effect of home-based elderly care services.

[0025] Specifically, the calculation expression of the nursing staff scheduling model is: (1); (2); in, represents minimizing the risk of delayed care, Start serving the elderly i time, Indicates the i The risk function for an elderly person, Indicates the risk level of delayed care for the elderly; N The total number of all older people who indicated they had care needs; Maximizing service satisfaction, represents the service satisfaction function of the i-th elderly person.

[0026] Since each elderly person has different physical conditions and faces different risks while waiting for services, in the embodiment of the present application, the health classification includes 4 levels as shown in Table 2; Indicates, corresponding to {healthy, mild disability, moderate disability, severe disability} respectively.

[0027] Table 2 Disability status definition table

[0028] The physical condition of the elderly determines the service time and the acceptable waiting time; therefore, the tolerable lateness and service time of different levels of elderly people need to be differentiated, as shown in Table 3.

[0029] Table 3 Service time and tolerable lateness

[0030] In an optional embodiment of the present application, the calculation expression of the care delay risk function is: (3); The calculation expression of the service satisfaction function is: (4); in, represents the time sensitivity coefficient of the elderly; represents the time risk coefficient of the elderly; Indicates elderly people iThe earliest service moment of the expected best service time, Indicates elderly people i The latest service moment of the expected best service time; Indicates elderly people i The earliest service moment of the tolerable service time, Indicates elderly people i The latest service time that can be tolerated.

[0031] As the main body of the service, the elderly need to consider their satisfaction with the service. Due to physical and emotional reasons, the elderly are more concerned about whether the home service can be carried out within the expected time period. Fuzzy theory is used to fuzzify the events, so as to establish the elderly service satisfaction function. , defined as the fuzzy membership function of the elderly service waiting time.

[0032] The expected service time window for each elderly person is , the satisfaction of serving the elderly in this time window is 1; the tolerable service time window is , the elderly satisfaction will decrease when the service is provided within this time window; when the service time is not within this time period, the elderly satisfaction is 0. The service satisfaction function is as follows Figure 3 shown.

[0033] If each elderly person receives service within their expected service time window or in advance, the risk they bear is 0; when they receive service within the tolerable service time window, the risk gradually increases over time; after exceeding the tolerable service time window, the risk they bear is 1; if the elderly person does not receive service due to the scheduling of caregivers, their risk is considered to be 1; the service waiting time risk function is as follows: Figure 4 shown.

[0034] In an optional embodiment of the present application, the constraints of the nursing staff scheduling model include: service number constraints, path constraints and time constraints.

[0035] Specifically, the service times constraint condition includes: Each elderly person can only be served once by a caregiver, and the expression is: ; Each elderly person receives a service once and is provided by a caregiver, which is expressed as: ; The path constraints include: The nursing staff starts from the community home-based elderly care service center, serves multiple elderly people and then returns to the starting point. The expression is: ; ; ; in, After completing the service needs of elderly person j, caregiver k arrives at elderly person i and starts the service. ,otherwise ; When the elderly person is on the path of caregiver k, caregiver k provides services to the elderly person, which is expressed as: ; ; The time constraints include: Nursing staff k From the elderly i Reaching the elderly j The time required is , whose expression is: ; Nursing staff k From the elderly i Get along with the elderly j The travel time at , whose expression is: ; in, Indicates nursing staff k Reaching the elderly i The time required, Indicates elderly people i The time required for the service, From the elderly i Get along with the elderly j The travel time at the location; Indicates elderly people i Get along with the elderly j The distance between the two places.

[0036] In an embodiment of the present application, the scheduling problem of home-based elderly care services is transformed into a multi-objective path optimization problem with time window constraints; caregivers need to start from the community home-based elderly care service center, provide door-to-door care services to the elderly who have made appointments in turn, and return to the community home-based elderly care service center after completing the task; in this process: it is necessary to comprehensively consider various constraints such as the different service needs of the elderly, the limitations of the service time window, and the workload and path planning optimization of caregivers. Due to the complexity of the solution space and the conflict of objectives, this problem is a typical NP-hard problem, and it is difficult to obtain the global optimal solution within an acceptable time through traditional precise algorithms; to address this problem, an embodiment of the present application designs a whale optimization algorithm, and solves the caregiver scheduling model through the whale optimization algorithm.

[0037] In an embodiment of the present application, the solution to the problem is expressed by the location where the whale captures its prey, that is, the order in which the caregivers provide services, and the quality of the service plan is reflected by the fitness function value; on the premise that the service plan meets the constraints of the problem, the better the fitness function value, the better the quality of the solution obtained by the algorithm, and the more the service plan meets the needs of the elderly.

[0038] This application takes minimizing the risk of the elderly as the main goal and maximizing the elderly's satisfaction as the secondary goal. The formula of the fitness function is: (5); in, F represents the fitness function value, 、 represents the target weight, Q represents the total risk value of the elderly, It represents the overall dissatisfaction of the elderly; therefore, the smaller the fitness value, the better the service plan.

[0039] The following is an explanation of the principle of the whale optimization algorithm.

[0040] According to the characteristics of whale predation, the whale optimization algorithm is divided into three stages: First, the stage of surrounding the prey This stage simulates the behavior of whales surrounding their prey during hunting. Since the initial position of the prey is unknown, the current optimal solution is assumed to be the target prey. After determining the best search agent, the whale updates its own position by surrounding the prey, that is: ; ; in, t Indicates the current iteration number, represents the current position vector, represents the current optimal position vector, Indicates absolute value operation; A and C represent coefficient vectors, D represents vector dimension; A·D represents the bracketing step size; The coefficient vectors A and C are defined as follows: ; ; ; in, and Represents a random number between [0,1]; Represents the convergence factor, which decreases from 2 to 0 as the number of iterations increases; Indicates the maximum number of iterations.

[0041] Second, the prey capture stage Whales attack their prey through spiral upward motion when capturing their prey. In order to mathematically describe the hunting behavior of whales, two methods, the shrinking and encircling mechanism and the position spiral update, are designed.

[0042] The shrinking and encircling mechanism is achieved by reducing the formula In the example, the convergence factor is set to 0.

[0043] In the position spiral update method, its mathematical model is as follows: ; ; in Represents the distance between the whale and the current optimal individual, express A random number between b is a constant defining the spiral equation; in this embodiment, b =1; Whales perform spiral movements while contracting their positions. To simulate this behavior, we assume that the probability of a whale choosing both contraction and spiral position updates during hunting is 0.5.

[0044] Third, the prey search phase In the process of searching for prey, in order to find a better solution, when | When , a whale individual is randomly selected as the pursuit target, and other individuals update their positions and swim towards the random whale to conduct a global search. The mathematical model is: ; ; in, represents the position vector of a randomly selected individual whale.

[0045] Since the numbering method of the elderly demand points is integer type, in order to generate a corresponding relationship between the whale position and the elderly number, this application adopts a natural number encoding method, and uses a one-dimensional vector to represent the scheduling plan. The vector length represents the total number of elderly people, and each character represents the elderly demand point; the whale position is decoded and converted into a specific plan for the nursing staff service path.

[0046] like Figure 5 As shown, if there are 3 caregivers and 7 elderly people, 0 represents the community home-based elderly care service center, and the elderly demand point set is , it means that the nursing staff starts from the community home-based elderly care service center, visits the elderly from left to right to provide services, and then returns to the community home-based elderly care service center.

[0047] In an optional embodiment of the present application, Figure 6 As shown, the S40 solves the nursing staff scheduling model by using the whale optimization algorithm to obtain the nursing staff's service path, including: S401, using a chaotic mapping algorithm to initialize the position of the whale population; S402, based on the fitness function, calculating the fitness value of each individual whale in the whale population, and obtaining the current optimal individual position and the global optimal position; S403, updating the position of the individual whale within the maximum number of iterations to obtain the global optimal solution; S404, converting the global optimal solution of the whale population into the order in which the caregivers provide services, and obtaining the caregiver's service path.

[0048] Specifically, the global convergence speed and solution quality in the whale optimization algorithm are affected by the quality of the initial whale population. The randomly generated group positions in the initialized population can easily lead to uneven distribution of initial whale positions and a narrow search range, thereby reducing search efficiency. Chaos has the characteristics of randomness, ergodicity, and orderliness, which enables it to traverse all states within a certain range according to its own rules without repeating. Therefore, the embodiment of the present application adopts the properties of chaotic motion to initialize the whale population to ensure population diversity.

[0049] The chaotic mapping currently available in the optimization field mainly includes: Logistic mapping, Tent mapping, and Circle mapping. In this embodiment of the application, the Circle chaotic mapping is used for population initialization. The process is defined as follows: ; in, To find the remainder function, the chaotic orbit state value range is (0,1).

[0050] In an optional embodiment of the present application, the step S403 of updating the position of the individual whale within the maximum number of iterations to obtain a global optimal solution includes: S4031, updating the convergence factor and calculation coefficient vector according to the current optimal individual position; S4032, updating the position of the individual whale according to the indicated parameters and the calculated coefficient vector to obtain the optimal individual position; S4033, using chaotic perturbation to optimize the optimal individual position and obtain the current optimal solution; S4034, using the relevant destruction operator and the optimal repair operator to perform a large neighborhood operator search on the current optimal solution to obtain a new solution; S4035, determining whether the maximum number of iterations has been reached, and if so, outputting the global optimal solution; Otherwise, continue the iteration and update the convergence factor and calculation coefficient vector according to the current optimal individual position.

[0051] Furthermore, the step S4032 updates the position of the individual whale according to the indication parameter and the calculation coefficient vector to obtain the optimal individual position; including: S4032-1, comparing the value of the indicated parameter with a preset threshold; S4032-2, if the value of the indicator parameter is less than the preset threshold, then determine whether the value of the calculated coefficient vector is less than 1. If so, select the risk difference-based encirclement method to update the position of the individual whale; otherwise, select the risk difference-based search method to update the position of the individual whale S4032-3, if the value of the indicator parameter is greater than or equal to the preset threshold, select a capture method based on risk difference to update the position of the individual whale; S4032-4, calculate the fitness value of the individual whale at the new position and compare it with the fitness value of the original position. If the fitness value of the new position is better than the fitness value of the original position, update the best position of the individual whale population to obtain the global optimal solution.

[0052] In the embodiment of the present application, the preset threshold is 0.5. When , the calculation coefficient vector is determined If yes, then the encirclement method based on risk difference is selected to update the position of the individual whale. Otherwise, the search method based on risk difference is selected to update the position of the individual whale. When the indicated parameter When the capture method based on risk difference is selected, the position of individual whales is updated.

[0053] Specifically, the solving ability of the WOA algorithm depends to a large extent on the convergence factor In the standard WOA algorithm, the convergence factor It decreases linearly from 2 to 0 with the number of iterations; in the early stage, the algorithm has good global search ability, but the convergence speed is slow; in the later stage, the convergence speed is too fast, it is easy to fall into the local optimum, and cannot fully reflect the actual optimization search process; design convergence factor In the early stage of the algorithm, the convergence factor increases with the number of iterations at a small value, decreases after reaching a large value, and finally increases at a slower rate. The embodiment of the present application proposes an update method in which the convergence factor changes non-linearly with the increase in the number of iterations, and the formula is: ; in, 、 Represent the convergence factors The initial and final values of represents the nonlinear convergence factor, Indicates the current iteration number, Indicates the maximum number of iterations.

[0054] The standard whale algorithm is used to solve problems with continuity, but when solving the VRP problem, the encoding of the demand nodes is discrete. Therefore, the embodiment of the present application redefines the operations of the whale optimization algorithm in the prey encirclement stage, prey capture stage, and prey search stage.

[0055] In order to ensure the security of the service after the update operation, this application adopts the insertion, reversal and exchange operations based on the lowest risk for the path update method; assuming: ; ; represents the risk difference between elderly i and elderly j. In an optional embodiment of the present application, the position of individual whales is updated using the risk difference-based encirclement method, and the update formula is: (5-1); Formula (5-1) means: In the stage of whales surrounding prey, a demand point is randomly selected in a path. , and then traverse the remaining demand points; if there is a demand point To the demand point The risk difference is less than the original access path To the next adjacent demand point The risk difference is Insert into After that, the remaining demand points move backward.

[0056] The risk difference-based search method updates the position of individual whales, and its update formula is: (5-2); Formula (5-2) means: In the whale's prey search phase, a demand point is randomly selected in a path. , and then traverse the remaining demand points; if there is a demand point To the demand point The risk difference is less than the original access path To the next adjacent demand point The risk difference is and The next demand point Exchange positions.

[0057] The capture method based on risk difference updates the position of individual whales, and its update formula is: (5-3); Formula (5-3) means: In the whale's prey search phase, a demand point is randomly selected in a path. , and then traverse the remaining demand points; if there is a demand point To the demand point The risk difference is less than the original access path To the next adjacent demand point The risk difference is arrive The demand points between them are reversed.

[0058] in, represents the risk difference between elderly i and elderly j, represents the risk difference between elderly person i and elderly person N.

[0059] Since the WOA algorithm is prone to falling into local optimality in the later stages of iteration, this application uses chaotic perturbation to optimize the current optimal individual position, thereby improving the global search capability of the algorithm. The perturbation strategy is as follows: ; in, Represents the chaotic variables generated after the disturbance: Represents the chaotic variable generated after the current optimal individual mapping of the algorithm; Represents iteration t The subsequent chaotic variables, represents the disturbance intensity, n represents the population size, which is calculated as follows: .

[0060] In the embodiment of the present application, based on the whale algorithm, the population is initialized by Circle chaotic mapping, a nonlinear convergence factor is introduced, and a chaotic perturbation mechanism is added to increase the global search capability of the algorithm. The effectiveness of the method of the present application is verified through case experiments and sensitivity analysis, in order to improve the efficiency of nursing homes.

[0061] It should be understood that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0062] The following is a specific case to verify and illustrate the technical effects of this application.

[0063] The experimental environment of this application is: Intel(R) Core(TM) i5-1035G1 CPU, 8GB memory, Windows11, 64-bit operating system, and the home care staff scheduling method based on health classification is written using MATLABR2021a; the experimental population size is 50, and the nonlinear convergence factor is 0. The maximum number of iterations is 1000, and the speed of the paramedic is V =2, the initial and final values of the convergence factor are: 、 ; Time sensitivity coefficient of the elderly , the time risk coefficient of the elderly .

[0064] In order to verify the universality and effectiveness of the method of this application, this application conducted multiple small, medium and large-scale case tests, and compared the results of the whale optimization algorithm with the whale algorithm and the improved ant colony algorithm (ACO) that performed well in the TSP problem to verify the effectiveness and superiority of the method of this application.

[0065] (1) Small-scale case analysis In a specific case, a small-scale test case of 12 elderly people was constructed. Three caregivers were set up in the case, and the location coordinates of the home-based elderly care service center were (43, 60). The results in Table 4 show that the results obtained by the proposed method are the same as those obtained by CPLEX, which proves the reliability of the proposed method in solving small-scale examples and that the proposed method is faster.

[0066] Table 4 Results of the improved whale algorithm and Cplex solution examples

[0067] like Figure 7 and Figure 8 As shown in the figure, the whale optimization algorithm obtains the optimal solution when the number of iterations is low, which proves that the method of this application has good global search capability under small scale conditions.

[0068] Because the ant colony algorithm has good solving capabilities for discrete combinatorial optimization problems, in a specific case, the improved ant colony algorithm was compared with a small example. Both methods were run 100 times, and the average value was taken after running 10 times. The comparison results are shown in Table 5. Table 5 Comparison of solution results between the improved whale algorithm and the ant colony algorithm

[0069] As shown in Table 5, the average satisfaction of the elderly is improved by 4.489%, the total risk value of the elderly is reduced by 20.136%, and the solution time is reduced by 33.191%.

[0070] (2) Multi-scale case analysis Taking into account the fact that the elderly are distributed in clusters in the community, the C and RC data sets in the Solomon standard data set are selected for testing. 25 and 50 demand points in the standard data sets C106, C107, RC206, and RC207 are randomly selected as small-scale and medium-scale case tests; 100 demand points in the entire set of C106, C107, RC206, and RC207 are used as a large-scale data set for testing. The coordinates of home-based elderly care services remain unchanged, and the number of caregivers is 6, 8, and 12 according to the case scale. The solution results are compared with the standard whale algorithm and the improved ant colony algorithm. The comparison results are shown in Table 6.

[0071] It can be concluded from Table 6 that the advantages of the proposed method become more obvious as the number of demand points increases. Based on the Class C data, the proposed method can reduce the total risk value by up to 1.054 compared with the standard whale algorithm and the improved ant colony algorithm, and the solution time can be reduced by up to 35.255s. The average satisfaction is not much different from that of the improved ant colony algorithm, and is improved compared with the standard whale algorithm.

[0072] Table 6 Solution results of different scale examples

[0073] like Figures 9 to 11 As shown in the figure, in order to more intuitively show the comparison of algorithm results, 106 C-type and 106 RC-type data sets are selected for comparison in terms of average satisfaction, total risk value and solution time. Comparing the C-type data, it can be seen that the solution results of the proposed method are significantly better than those of the other two algorithms; compared with the RC-type data, the proposed method is superior in solution speed, but the average satisfaction and total risk value solution results have little advantage. It can be seen that the algorithm in this article is more suitable for clustered demand points, that is, it has greater advantages in solving nursing staff scheduling in the context of community home-based elderly care.

[0074] (3) Sensitivity analysis In a specific case, the time sensitivity coefficient of the elderly and the time risk coefficient of the elderly The average value is 1, indicating a baseline situation where satisfaction decreases and risk increases linearly over time. This setting facilitates the basic functionality and effectiveness of the method of this application.

[0075] The adaptability of the method of the present application to different time sensitivities is analyzed below by changing these parameter values.

[0076] The time sensitivity coefficient of the elderly is an important factor affecting their satisfaction and risk. In order to analyze the impact of time-sensitive parameters on solving scheduling problems, a specific case is based on the small example C106-25. On the basis of the original parameter settings, different The optimal value is obtained ten times by using the method of this application; the nursing staff is in the expected service time window of the elderly. The service is provided within the time window that the elderly can tolerate. Internal service is recorded as early arrival; and subsequent services are recorded as late, with the results shown in the following table.

[0077] Table 7 Sensitivity analysis and operation results of service satisfaction

[0078] Table 8 Risk sensitivity analysis and operation results

[0079] From Table 7, we can see that as the time sensitivity coefficient increases, the number of nurses arriving early or late increases. α 、 β The larger the value is, the more sensitive the elderly are to time and the stricter they are about the punctuality of service time. Whether the caregivers can arrive on time has a greater impact on their service satisfaction.

[0080] From Table 8, we can see that γ Increasing the sensitivity factor reduces the number of late arrivals but increases the number of early arrivals. While this ensures the safety of elderly care workers and reduces the incidence of adverse care events caused by lateness, early arrivals can reduce elderly satisfaction with the service and waste nursing resources. Therefore, home-based elderly care centers should rationally select the sensitivity factor to reduce elderly health risks and improve service satisfaction.

[0081] (IV) Time window interval analysis The time window interval is the main factor affecting service waiting time. To analyze the impact of the time window interval on this application method, the time window interval setting and solution results are shown in the following table. The example uses C106-25 for analysis, and other parameter settings remain unchanged.

[0082] Table 9 Time window interval analysis

[0083] Table 9 shows that the time window interval is inversely proportional to the caregiver's waiting time. Specifically, in real-world scheduling tasks, the more tolerant the elderly are of the caregiver's waiting time for home services, the fewer caregivers arrive early. This allows caregivers to complete services within the expected service time, improving elderly satisfaction. Setting the time window interval too tight reduces solution time but fails to meet all elderly needs, increasing caregiver waiting time. As the time window interval increases, solution time increases. Therefore, home-based elderly care service centers should consider appropriately expanding the range of appointment time windows while meeting the actual needs of the elderly, reducing caregiver waiting time and lateness, and improving the efficiency of home services.

[0084] The embodiment of the present application also provides a device for scheduling home-based elderly care staff based on health grading, including: Demand construction unit, used to construct elderly care needs based on the elderly's physical condition, residence coordinates, appointment time window and graded service duration based on health status; The scheduling model establishment unit is used to construct a care delay risk function and a service satisfaction function based on the care needs of the elderly; and to establish a caregiver scheduling model with the goal of minimizing the care delay risk and maximizing the service satisfaction; The service path solving unit is used to solve the nursing staff scheduling model through the whale optimization algorithm to obtain the nursing staff's service path.

[0085] For the specific definition of the above-mentioned device, please refer to the definition of the method above and will not be repeated here. Each module in the above-mentioned device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software so that the processor can call and execute the operations corresponding to each of the above modules.

[0086] An embodiment of the present application also provides a computer device, which includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method as described above. It includes: a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it implements any step in the method as described above.

[0087] An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any step in the above method can be implemented.

[0088] In summary, this application explores the issue of nursing staff scheduling in community home-based elderly care services from the dual perspectives of nursing delay risk and service satisfaction. The research results have important implications for improving the operational management efficiency of elderly care services. The risk assessment system constructed based on fuzzy theory provides a new approach for elderly care service institutions to quantitatively assess nursing delay risks, and helps elderly care service institutions establish a scientific risk prevention and control mechanism. The research results show that the correlation between time window setting and nursing staff scheduling efficiency has a significant impact on service quality and resource utilization. The application of the multi-objective planning model further reveals the systematic relationship between risk control and satisfaction improvement, providing a theoretical basis for the standardized management of home-based elderly care services.

[0089] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0093] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0094] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A method for scheduling home-based elderly care staff based on health grading, characterized in that: include: Constructing elderly care needs based on their physical condition, residence coordinates, appointment time windows, and graded service duration based on health status; According to the nursing needs of the elderly, a nursing delay risk function and a service satisfaction function are constructed; Establish a nursing staff scheduling model with the goal of minimizing the risk of care delay and maximizing service satisfaction; The nursing staff scheduling model is solved using the whale optimization algorithm to obtain the nursing staff's service path.

2. The method for scheduling home-based elderly care staff based on health grading according to claim 2 is characterized in that: The calculation expression of the nursing staff scheduling model is: （1）； （2）； in, represents minimizing the risk of delayed care, Start serving the elderly i time, Indicates the i The risk function for an elderly person, Indicates the risk level of delayed care for the elderly; N The total number of all older people who indicated they had care needs; Maximize service satisfaction. represents the service satisfaction function of the i-th elderly person.

3. The method for scheduling home-based elderly care staff based on health grading according to claim 2 is characterized in that: The calculation expression of the nursing delay risk function is: （3）； The calculation expression of the service satisfaction function is: （4）； in, represents the time sensitivity coefficient of the elderly; represents the time risk coefficient of the elderly; Indicates elderly people i The earliest service moment of the expected optimal service time, indicating that the elderly i The latest service moment of the expected best service time; Indicates elderly people i The earliest service moment of the tolerable service time, Indicates elderly people i The latest service time that can be tolerated.

4. The method for scheduling home-based elderly care staff based on health grading according to claim 2 is characterized in that: The formula of the fitness function is: （5）； in, F represents the fitness function value, 、 represents the target weight, Q represents the total risk value of the elderly, Indicates the overall dissatisfaction of the elderly.

5. The method for scheduling home-based elderly care staff based on health grading according to claim 1 is characterized in that: The method of solving the nursing staff scheduling model by using the whale optimization algorithm to obtain the nursing staff's service path includes: Adopt the chaotic mapping algorithm to initialize the position of the whale population; Based on the fitness function, the fitness value of each whale in the whale population is calculated to obtain the current optimal individual position and the global optimal position; Update the position of individual whales within the maximum number of iterations to obtain the global optimal solution; The global optimal solution of the whale population is converted into the order in which the caregivers provide services, and the service path of the caregivers is obtained.

6. The method for scheduling home-based elderly care staff based on health grading according to claim 5 is characterized in that: The method of updating the position of individual whales within the maximum number of iterations to obtain the global optimal solution includes: According to the current optimal individual position, update the convergence factor and calculation coefficient vector; According to the indicated parameters and the calculated coefficient vector, the position of the individual whale is updated to obtain the optimal individual position; Use chaotic perturbation to optimize the optimal individual position and obtain the current optimal solution; Use the relevant destruction operator and the optimal repair operator to search the current optimal solution in a large neighborhood to obtain a new solution; Determine whether the maximum number of iterations has been reached. If so, output the global optimal solution. Otherwise, continue the iteration and update the convergence factor and calculation coefficient vector according to the current optimal individual position.

7. The method for scheduling home-based elderly care staff based on health grading according to claim 6 is characterized in that: The method of updating the position of the individual whale according to the indication parameter and the calculation coefficient vector to obtain the optimal individual position includes: comparing the value of the indicated parameter with a preset threshold; If the value of the indicator parameter is less than the preset threshold, then determine whether the value of the calculated coefficient vector is less than 1. If so, select the encirclement method based on risk difference; otherwise, select the search method based on risk difference to update the position of the individual whale. If the value of the indicator parameter is greater than or equal to the preset threshold, the capture method based on risk difference is selected to update the position of the individual whale; The fitness value of the individual whale at the new position is calculated and compared with the fitness value of the original position. If the fitness value of the new position is better than the fitness value of the original position, the best position of the individual whale population is updated to obtain the global optimal solution.

8. The method for scheduling home-based elderly care staff based on health grading according to claim 7 is characterized in that: The risk difference-based encirclement method updates the position of individual whales, and the update formula is: （5-1）； The risk difference-based search method updates the position of individual whales, and its update formula is: （5-2）； The capture method based on risk difference updates the position of individual whales, and its update formula is: （5-3）； represents the risk difference between elderly i and elderly j, Indicates elderly people i and the elderly N The risk difference between them.

9. A device for scheduling home-based elderly care staff based on health grading, characterized in that: include: Demand construction unit, used to construct elderly care needs based on the elderly's physical condition, residence coordinates, appointment time window and graded service duration based on health status; The scheduling model establishment unit is used to construct a care delay risk function and a service satisfaction function based on the care needs of the elderly; and to establish a caregiver scheduling model with the goal of minimizing the care delay risk and maximizing the service satisfaction; The service path solving unit is used to solve the nursing staff scheduling model through the whale optimization algorithm to obtain the nursing staff's service path.

10. A computer device comprising: The method comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that the processor implements the steps of the method according to any one of claims 1 to 8 when executing the computer program.

Images