Community embedded nursing home site selection method and system

Abstract

The embodiment of the application provides a community embedded pension institution site selection method and system, and belongs to the technical field of pension services.The method comprises the following steps: obtaining supply and demand information of pension services; wherein the supply and demand information comprises multiple pension institution candidate point information and pension service demand information; defining a candidate pension institution selection probability according to the supply and demand information of the pension services; constructing a pension institution site selection model based on the candidate pension institution selection probability; and solving the pension institution site selection model based on a preset genetic algorithm, and outputting pension institution candidate point combination information that meets the pension service demand.The present application solves the problems of poor precision and single consideration of the existing pension facility site selection method.

Description

Technical Field

[0001] This invention relates to the field of elderly care service technology, specifically to a method and system for selecting locations of community-embedded elderly care institutions. Background Technology

[0002] As my country enters an aging society and the function of family-based elder care weakens, elder care service facilities are closely related to the lives of the elderly. Given the current trend, and addressing the lack of new and old community-based elder care institutions and their chaotic classification, it is necessary to vigorously develop community-based elder care service institutions and actively improve the supporting facilities through measures such as new construction and renovation. Against this backdrop, community-embedded elder care institutions, as a new model of elder care, are characterized by their small scale and high integration with the community. They integrate home-based, community-based, and institutional elder care service models, allowing the elderly to enjoy high-quality elder care services in a familiar environment. Simultaneously, to accurately meet the increasingly diverse needs of the elderly, community-embedded elder care institutions provide differentiated elder care services, categorized into multiple levels. The rationality of their site selection and layout affects the quality of life of the elderly. Currently, research on facility site selection in the elder care field is mostly qualitative, with limited quantitative research literature. There is insufficient consideration of the different levels of needs of the elderly, the level of elder care facilities, and the elderly's choice of facilities. Given the shortcomings of existing facility site selection methods in terms of accuracy and limited consideration, a new method for selecting community-embedded elder care institutions is needed. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for site selection of community-embedded elderly care institutions, so as to at least solve the problems of poor accuracy and limited consideration in existing site selection methods for elderly care facilities.

[0004] To achieve the above objectives, the first aspect of the present invention provides a method for selecting locations of community-embedded elderly care institutions. The method includes: acquiring supply and demand information for elderly care services; wherein the supply and demand information includes information on multiple candidate locations for elderly care institutions and information on the demand for elderly care services; defining the selection probability of candidate elderly care institutions based on the supply and demand information for elderly care services; constructing a location selection model for elderly care institutions based on the selection probability of candidate elderly care institutions; solving the location selection model for elderly care institutions based on a preset genetic algorithm, and outputting information on combinations of candidate locations for elderly care institutions that meet the demand for elderly care services.

[0005] Optionally, the elderly care service demand information includes: elderly care demand level information and elderly care demand location information; wherein, the elderly care demand level information includes: Level 1 elderly care demand, including one or more of the following: dining hall demand, rest demand, hairdressing demand, and reading demand; Level 2 elderly care demand, including one or more of the following: psychological counseling demand, medical demand, and health care demand; the Level 2 elderly care demand may or may not include the content of Level 1 elderly care demand, and the Level 1 elderly care demand does not include the content of Level 2 elderly care demand; the elderly care demand location information is the geometric center of multiple areas divided based on the community area.

[0006] Optionally, the step of defining the selection probability of candidate elderly care institutions based on the supply and demand information of the elderly care services includes: the selection probability of the candidate elderly care institution is:

[0007] Where i∈I, I is the set of demand points; j∈J, J is the set of candidate elderly care institutions; s∈S, S is the set of elderly care demand levels, S={1,2}, 1 is level 1 elderly care demand, 2 is level 2 elderly care demand; h∈H, H is the set of elderly care institution levels, H={1,2}, 1 is level 1 elderly care institution that can only provide level 1 elderly care demand, 2 is level 2 elderly care institution that can provide both level 1 and level 2 elderly care demand; A isjh Let A be the amount of resources that the S-level elderly care demand at demand point i can obtain from the h-level elderly care institution j; is Total available resources for all elderly care facilities.

[0008] Optionally, the amount of resources A that the s-level elderly care demand of demand point i can obtain from h-level elderly care institution j is... isjh The function is:

[0009]

[0010] The total available resources A for all elderly care institutions is The function is:

[0011]

[0012] Among them, E jh To serve as a factor affecting population size; M ijh β is the level influence factor; β is the travel friction coefficient.

[0013] Optionally, the population size influence factor E jh The E function is:

[0014]

[0015] The level of influence factor M ijhThe function is:

[0016]

[0017] Where, ω is The demand for elderly care at level i is the demand at demand point i relative to level s.

[0018] d ij d represents the distance between demand point i and candidate elderly care institution point j; h This represents the theoretical maximum distance for h-level elderly care facilities.

[0019] Optionally, the step of constructing a location model for elderly care institutions based on the selection probabilities of the candidate institutions includes: the functional expression of the location model for elderly care institutions is:

[0020]

[0021] Optionally, the constraint function of the elderly care facility site selection model is:

[0022]

[0023]

[0024]

[0025]

[0026]

[0027]

[0028] Where P represents the number of elderly care facilities built; X isjh Y is the evaluation index for satisfying the S-level elderly care needs at demand point i by h-level elderly care institution j; jh This is a location selection variable.

[0029] Optionally, the step of solving the elderly care facility site selection model based on a preset genetic algorithm and outputting candidate site combination information for elderly care services that meet the needs of elderly care services includes: chromosome encoding of the site selection variables; generating an initial population based on the chromosome encoding results; determining the objective function and fitness value of each individual based on the initial population, and selecting individuals using a roulette wheel algorithm based on the fitness values; performing a crossover operation between the currently selected individual and its neighboring individuals to obtain offspring individuals; determining whether the objective function of the current individual has better convergence characteristics based on the offspring individuals; if so, adopting an elite retention strategy, removing a certain number of new offspring individuals with poor fitness values ​​and retaining a certain number of parent individuals with good fitness values; and updating the initial population based on the retained individuals; otherwise, performing a mutation operation on the offspring individuals to obtain new individuals. Based on the new offspring individuals, determine whether the objective function of the current individual has better convergence characteristics. If so, remove a certain number of the new offspring individuals with poor fitness values ​​and retain a certain number of parent individuals with good fitness values. Then, update the initial population based on the retained individuals. Iterate the elderly care facility site selection model based on the updated initial population or the retained individuals, and determine whether the number of iterations has reached the maximum value. If so, stop the iteration and output the result; otherwise, repeat the initial population update steps until the maximum number of iterations is reached, and output the result.

[0030] A second aspect of the present invention provides a community-embedded elderly care facility site selection system, the system comprising: a data acquisition unit for acquiring supply and demand information for elderly care services; wherein the supply and demand information includes information on multiple candidate elderly care facility locations and elderly care service demand information; a model building unit for: defining the selection probability of candidate elderly care facilities based on the supply and demand information for elderly care services; and constructing an elderly care facility site selection model based on the selection probability of candidate elderly care facilities; and a processing unit for solving the elderly care facility site selection model based on a preset genetic algorithm, and outputting information on combinations of candidate elderly care facility locations that meet the demand for elderly care services.

[0031] On the other hand, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described community-embedded elderly care facility site selection method.

[0032] This technical solution addresses the site selection problem of community-embedded elderly care facilities with multiple needs and levels. It combines spatial interactions, considers the competitive impact of the service population and the influence of facility level, introduces service population size and level influence factors, constructs selection probabilities based on the available facility resources for the elderly, establishes a site selection model with the objective of minimizing travel costs based on the elderly's selection probabilities, and designs a genetic algorithm to solve the problem. This solution resolves the problems of poor accuracy and limited consideration in existing site selection methods for elderly care facilities.

[0033] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0034] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0035] Figure 1 This is a flowchart of the steps of a community-embedded elderly care facility site selection method provided in one embodiment of the present invention;

[0036] Figure 2 This is a flowchart of the execution steps of a genetic algorithm provided in one embodiment of the present invention;

[0037] Figure 3 This is a schematic diagram of chromosome coding rules provided in one embodiment of the present invention;

[0038] Figure 4 This is a flowchart of the iterative genetic algorithm provided in one embodiment of the present invention;

[0039] Figure 5 This is a schematic diagram of the structure of a community-embedded elderly care facility site selection system provided in one embodiment of the present invention. Detailed Implementation

[0040] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0041] As my country enters an aging society and the function of family-based elder care weakens, elder care service facilities are closely related to the lives of the elderly. Under current trends, to address the lack of new and old community-based elder care institutions and their chaotic classification, it is necessary to vigorously develop community-based elder care service institutions and actively improve the supporting facilities through measures such as new construction and renovation. Against this backdrop, community-embedded elder care institutions, as a new model of elder care, are characterized by their small scale and high integration with the community. They integrate home-based, community-based, and institutional elder care service models, allowing the elderly to enjoy high-quality elder care services in a familiar environment. Simultaneously, to accurately meet the increasingly diverse needs of the elderly, community-embedded elder care institutions provide differentiated elder care services, categorized into multiple levels. The rationality of their site selection and layout affects the quality of life of the elderly. Currently, site selection for elder care facilities is mostly focused on qualitative research, with limited quantitative research literature, and little consideration given to the different levels of needs of the elderly, the level of elder care facilities, and the elderly's choice of facilities. Based on the problems of poor accuracy and limited consideration in existing site selection methods for elder care facilities, this invention proposes a new method for site selection of community-embedded elder care institutions.

[0042] The proposed method for site selection of community-embedded elderly care institutions addresses the multi-demand, multi-level problem by combining spatial interactions, considering the competitive impact of the service population and the influence of institution level. It introduces service population size and level influence factors, constructs selection probabilities based on the available institutional resources for the elderly, establishes a site selection model with the goal of minimizing travel costs based on the elderly's selection probabilities, and designs a genetic algorithm to solve the problem.

[0043] Figure 5 This is a system structure diagram of a community-embedded elderly care facility site selection system provided in one embodiment of the present invention. Figure 5 As shown, this invention provides a community-embedded elderly care facility site selection system. The system includes: a data acquisition unit for acquiring supply and demand information for elderly care services; wherein the supply and demand information includes information on multiple candidate elderly care facility locations and elderly care service demand information; a model building unit for: defining the selection probability of candidate elderly care facilities based on the supply and demand information for elderly care services; and constructing an elderly care facility site selection model based on the selection probability of candidate elderly care facilities; and a processing unit for solving the elderly care facility site selection model based on a preset genetic algorithm, and outputting information on combinations of candidate elderly care facility locations that meet the demand for elderly care services.

[0044] Figure 1 This is a flowchart of a community-embedded elderly care facility site selection method provided in one embodiment of the present invention. Figure 1As shown, this invention provides a method for selecting locations for community-embedded elderly care facilities, the method comprising:

[0045] Step S10: Obtain supply and demand information for elderly care services.

[0046] Specifically, as mentioned above, existing methods for selecting locations for elderly care institutions suffer from poor accuracy. This is because people have diverse needs for elderly care services. Given these varied needs, a uniform calculation would inevitably result in configuration requirements failing to accurately match user needs. Therefore, this application divides community-embedded elderly care institutions into two levels. Level 1 elderly care needs include one or more of the following: dining needs, rest needs, hairdressing needs, and reading needs. Level 2 elderly care needs include one or more of the following: psychological counseling needs, medical needs, and health care needs. Correspondingly, due to differences in the health conditions, consumption habits, and environments of the elderly, their needs are divided into two tiers: the first tier is the need for Level 1 elderly care services, and the second tier is the need for Level 2 elderly care services. The Level 2 elderly care needs may include the content of Level 1 elderly care needs, but Level 1 elderly care needs do not include the content of Level 2 elderly care needs.

[0047] In short, this application's solution addresses the primary and secondary living needs of elderly residents within a community by using the resources available to them from institutions at each level to determine their choice probability. While meeting the needs of the elderly, it identifies the optimal location and level of community-embedded elderly care institutions from candidate nodes, minimizing travel costs based on the elderly's choice probability. To achieve this, accurate information on the level and location of elderly residents' needs is required. The level of needs determines the level of elderly care institution construction, while the location information determines the construction location. By limiting the location and level of elderly care institutions, a unified, parallel site selection for elderly care institutions within the community can be achieved. This means comprehensively considering the actual situation of the community and outputting a one-time determination of the location and level of all elderly care institutions that meet the community's needs.

[0048] Step S20: Define the probability of selecting candidate elderly care institutions based on the supply and demand information of the elderly care services.

[0049] Specifically, the commonly used site selection model is the P-median model, which aims to minimize the total travel distance. Distance plays a strong dominant role in the demand-candidate point allocation relationship, exhibiting a clear limitation of "proximity allocation." However, according to existing research, elderly people consider not only distance but also facility size and grade when choosing service facilities. Based on this, the concept of free choice probability has emerged to measure the demand point's choice of facility location. The expression of choice probability involves the concept of potentiality models. Currently, potentiality models are frequently used to measure the amount of resources available to an object. Potentiality refers to the energy that one object can generate for another, and its general expression is:

[0050]

[0051] Among them, A i It is the sum of the energy generated by other objects j on i within the study area, and its dimension should be the facility service capacity available per person, which can be the number of beds per person, the number of medical and technical personnel per person, etc.; M j It refers to the scale of facility j; d ij β is the distance from i to j, and β is the travel friction coefficient.

[0052] However, even for two supply points in the same location and of the same size, serving different numbers of people in need, the resources available to the demand point from these two supply points should also be different. That is, considering the competition among demand points for the limited resources of the same supply point, the influence factor of the size of the service population is introduced, and the expression of the potential model becomes:

[0053]

[0054]

[0055] Finally, the spatial interaction between supply and demand is combined with the P-median model, and then introduced... To express the probability of free choice, a location selection model that minimizes travel costs based on the probability of free choice is constructed.

[0056] Building upon the aforementioned prior art, this application, considering the varying maximum travel distances required by different service population levels, introduces a service population size influencing factor M. ijh And the grade influence factor E jh Let A represent the amount of resources that level s-level elderly care needs at demand point i can obtain from level h elderly care institution j. isjh and with A isjh And the total amount of resources A available from all institutions is The probability of choosing a demand level h for demand point i is constructed by the ratio of the demand level h to the demand level j.

[0057]

[0058] Where i∈I, I is the set of demand points; j∈J, J is the set of candidate elderly care institutions; s∈S, S is the set of elderly care demand levels, S={1,2}, 1 is level 1 elderly care demand, 2 is level 2 elderly care demand; h∈H, H is the set of elderly care institution levels, H={1,2}, 1 is level 1 elderly care institution that can only provide level 1 elderly care demand, 2 is level 2 elderly care institution that can provide level 2 elderly care demand; A isjh Let A be the amount of resources that the S-level elderly care demand at demand point i can obtain from the h-level elderly care institution j; is The total amount of resources available to all institutions. The amount of resources A that the s-level elderly care need at demand point i can obtain from s-level elderly care institution j is. isjh The function is:

[0059]

[0060] The total resource A available to all the institutions is The function is:

[0061]

[0062] Among them, E jh To serve the population size impact factor, it is introduced to consider the competition from different demand points for the same institution. When an institution is competed for by many demand points, it affects the amount of resources that each demand point can obtain from that institution; M ijh β is the level-based influence factor, introduced to account for institutions with different levels. Institutions of different levels have different minimum distances and sizes, which affect the amount of resources available at the demand point; β is the travel friction coefficient. Here, d is used. h This represents the theoretical maximum distance to a community-based elderly care facility at level h. When the travel distance from a certain point of need to the elderly care facility exceeds this maximum distance, M... ijh If M ≤ 0, it is considered that elderly care institution j is not attractive to elderly people with need point i, and M will be included in the calculation. ijh Set to 0.

[0063] Step S30: Construct a site selection model for elderly care institutions based on the selection probabilities of the candidate elderly care institutions.

[0064] Specifically, the functional expression of the elderly care facility site selection model is:

[0065]

[0066] The constraint function of the elderly care facility site selection model is as follows:

[0067]

[0068]

[0069]

[0070]

[0071]

[0072]

[0073] Where P represents the number of elderly care facilities built; X isjh Y is the decision variable for whether the elderly care demand at level s of demand point i is satisfied by elderly care institution j of level h; jh Equation (1) ensures that the elderly care needs at each level of the demand point are met; Equation (2) indicates that the elderly care needs at level s of demand point i can only be served by community elderly care institutions of the same or higher level; Equation (3) indicates that the demand allocated to institution j at level h does not exceed the maximum capacity of that level of elderly care institution; Equation (4) indicates the establishment of P institution points. Equations (5) and (6) define 0-1 variables.

[0074] Step S40: Solve the elderly care institution site selection model based on the preset genetic algorithm, and output the candidate site combination information of elderly care institutions that meet the needs of elderly care services.

[0075] Specifically, this application proposes a genetic algorithm to solve a multi-demand, multi-level community-embedded elderly care facility site selection model based on selection probability. Based on the model characteristics, chromosome coding rules are designed to generate an initial population. The fitness value of each individual in the population is calculated. According to the evolutionary rules of survival of the fittest and natural selection, the population is continuously updated, and the best individual in the optimized population is recorded to obtain the optimal solution that meets the requirements. Specifically, such as... Figure 2 The solution algorithm steps are as follows:

[0076] Step S401: Chromosome encoding.

[0077] Specifically, such as Figure 3 For the addressing variable Y jh In the application scenario of this application model, the consideration levels of each candidate institution in the community are given; therefore, it is only necessary to consider Y. j Encode Y. jA binary encoding method is used, where 1 indicates the establishment of a community-embedded elderly care facility at that point, and 0 indicates no establishment. The length of the encoding is J, the number of candidate points. Since the number of selected sites is P, P elements in the encoding should be 1. y represents the encoding of the correspondence between secondary needs and the secondary facilities selected from x, with a length N, the number of secondary need points, and random numbers between 0 and 1 for each element. z represents the encoding of the correspondence between primary needs and the P facilities selected from x, with a length N, the number of primary need points, and random integers between 1 and P for each element.

[0078] Step S402: Generate the initial population.

[0079] Specifically, based on the above encoding rules, x, y, and z are generated. The candidate institution index corresponding to the element value of 1 in x is stored in the array hub, and the candidate institution index of the element value of 1 in x and the level of level two is stored in the array hub1. hub1 represents the level two institutions in the preliminary site selection scheme, and the length P1 of hub1 represents the number of level two institutions to be built in the preliminary site selection scheme. The element value in y is multiplied by P1 and rounded down to obtain the index of the level two institution corresponding to the N level two demand points in hub1, ​​thus establishing the correspondence between the N level two demand points and the level two institutions in the x site selection scheme. The element value in z represents the index of the institution allocated to the level one demand in hub.

[0080] For each element in x with a value of 1, calculate the demand it is allocated to. If the demand it covers does not exceed the maximum capacity of the organization at that level, [xyz] constitutes an individual. Randomly generate enough individuals to form the initial population.

[0081] Step S403: Determine the objective function and fitness function.

[0082] Specifically, the elite characteristics of individuals need to be determined based on fitness values ​​and objective functions, so the corresponding objective function and fitness function must first be determined. The objective function value of the k-th individual in the initial population is:

[0083]

[0084] The corresponding fitness value is calculated as follows:

[0085] fit = max(fx0) - fx0(k)

[0086] Once the fitness function is determined, individuals are selected using a combination of editing and roulette wheel selection. The probability of each individual being selected is proportional to the value of its fitness function, thus simulating genetic characteristics.

[0087] Step S404: Perform a crossover operation.

[0088] Specifically, based on the pre-set crossover probability P c The crossover operation is performed on the x, y, and z parts of individuals i and i+1 in the population.

[0089] The first step is location crossover, which uses partial matching crossover. First, a random position r is generated, and two parent individuals exchange parts of the chromosomes before and after position r to form a new offspring individual.

[0090] Next is the second-level demand crossover, which generates a random 1xN matrix a with values ​​between (0,1). The crossover operators are: a*y1+(1-a)*y2 and a*y2+(1-a)*y1, which form new offspring individuals. After the transformation, points less than 0 are assigned a value of 0, and points greater than 1 are assigned a value of 1.

[0091] After the crossover operation is completed, the fitness value of the current individual is calculated, and then it is determined whether the objective function is better. If so, an elite retention strategy is adopted, retaining a certain number of the best parent individuals, removing the same number of the worst offspring individuals, and updating the population. Otherwise, the following steps are continued.

[0092] Step S405: Perform mutation operation.

[0093] Specifically, based on the pre-set mutation probability P m The offspring are generated by performing mutation operations on the parent individuals.

[0094] For the location selection part, random positions r1 and r2 are generated. If the original element value at both positions is 1, it is mutated to 0; if the original value is 0, it is mutated to 1.

[0095] For the secondary demand allocation part, a 1xN 0-1 matrix r is generated and mutated using the mutation operator: y*(1+randn(1,N)*r);

[0096] The mutation idea of ​​the first-level demand part is similar to that of the location selection part: for the z part of the chromosome, generate a random position r, and replace the element value at position r with a random integer between 1 and P.

[0097] like Figure 4 After the mutation operation is completed, the objective function of the current individual is judged to have better convergence characteristics based on the offspring individuals. If so, an elite retention strategy is adopted to retain a certain number of optimal parent individuals, remove the worst offspring individuals with the same data, and update the initial population based on the retained offspring individuals. Based on the updated initial population or retained individuals, an iteration of the elderly care facility site selection model is performed, and it is judged whether the number of iterations has reached the maximum value. If so, the iteration is stopped and the result is output; otherwise, the initial population update steps are repeated until the maximum number of iterations is reached, and the result is output.

[0098] Example:

[0099] Based on the distribution and needs of the elderly in a certain community, the community was divided into 15 areas, with the geometric center of each area taken as the demand center. The survey yielded the demand for basic and secondary elderly care services among the elderly in these 15 areas. The coordinates of the demand centers on a 100x100 plane and the demand for the two types of services are shown in Table 1.

[0100]

[0101] Table 1. Location of demand points and demand for the two services

[0102] Demand is measured in beds. Taking into account factors such as environment, area, demand, and construction standards for elderly care facilities, this application selected 15 candidate sites, including 6 Level 1 candidate sites and 9 Level 2 candidate sites.

[0103] The limit distance of the primary mechanism is set to 300m, with a mechanism size of 40 beds; the limit distance of the secondary mechanism is set to 1000m, with a mechanism size of 80 beds. The travel friction coefficient β is determined to be 1 in this embodiment.

[0104] The population size is set to 100, the maximum number of iterations is 800, and the crossover probability is P. c =0.9, mutation probability P m =0.1, Elite Ratio P e =0.1. The genetic algorithm was used to solve the model, selecting 7 sites for construction from 15 candidate sites for community-embedded elderly care institutions. Based on the optimal site selection scheme obtained above, the site selection and the coverage requirements of each site were analyzed, as shown in Table 2: Two primary elderly care institutions need to be established within the community: 3 and 6; five secondary elderly care institutions need to be established: 1, 2, 9, 10, and 15.

[0105]

[0106] Table 2. Overview of Site Selection and Allocation of Community-Embedded Elderly Care Institutions

[0107] It is evident that the demand for basic living services among the elderly in this community is higher than that for secondary services. The optimal site selection plan indicates that the number of secondary community-embedded elderly care institutions providing both levels of services is higher than that of primary institutions offering only basic elderly care services. Therefore, for this community, building more and larger-scale secondary community-embedded elderly care institutions with a wider range of services would better meet the needs of the elderly. However, the construction cost of secondary institutions is higher than that of primary institutions, and cost is also a factor worth considering.

[0108] According to statistics on optimal site selection, only 26.2% of basic living needs are met by primary community elderly care institutions, while the remaining primary needs are met by secondary institutions. This statistic indicates that most elderly people with only primary needs tend to choose secondary community elderly care institutions that are larger in scale, higher in level, and have more complete supporting facilities. This also verifies the point made earlier that the elderly consider not only distance factors but also factors such as scale when choosing facilities.

[0109] Furthermore, the site selection results of this application's model are compared and analyzed with those of the traditional P-median model. Table 3 shows the optimal site selection scheme obtained by optimizing this problem using the traditional P-median model. The results show that when the optimization objective is to minimize the total travel distance, one primary elderly care institution (7) and six secondary elderly care institutions (1, 9, 10, 11, 12, 15) need to be established within the community.

[0110]

[0111] Table 3. Site selection and allocation results of the traditional P-median model.

[0112] Furthermore, Table 4 presents a comparative analysis of the optimal location schemes of the model in this application and the P-median model.

[0113]

[0114] Table 4 Comparison of site selection results with the traditional P-median model.

[0115] It is evident that the total travel distance of the optimal site selection scheme in the P-median model is shorter than that in the proposed model, resulting in lower total travel costs for the elderly. When minimizing travel distance is the optimization objective, six primary community-based elderly care institutions need to be constructed, which incurs higher construction costs than the proposed model. Statistical analysis shows that only 8% of the primary demand in the optimal site selection scheme of the P-median model is met by primary elderly care institutions, resulting in a vacancy rate of 55% for primary institutions, significantly higher than that in the proposed model; the vacancy rate for secondary elderly care institutions is also slightly higher than that in the proposed model. Therefore, compared to the P-median model, the proposed model, which considers selection probability, improves the utilization rate of institutions and reduces wasted bed vacancies.

[0116] Furthermore, to further verify the effectiveness of the genetic algorithm designed in this application in solving this problem, ant colony optimization and particle swarm optimization were used sequentially for experimental comparison. The experiment was conducted 10 times, and the optimal results were recorded. The results are shown in Table 5:

[0117]

[0118] Table 5 Comparison of solution results from different algorithms

[0119] It is evident that the genetic algorithm outperforms the other two algorithms in solving the practical problem presented in this application, achieving the lowest total travel cost based on selection probability. The optimal results of the particle swarm optimization algorithm and the genetic algorithm are closest, with a difference of only 2.35%. This comparative result demonstrates that the genetic algorithm designed in this application performs well in solving the problem of multi-level community-embedded elderly care institutions that consider the selection probability of the elderly.

[0120] The present invention also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described community-embedded elderly care facility site selection method.

[0121] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a microcontroller, chip, or processor to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0122] The optional embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details described above. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe the various possible combinations.

[0123] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the embodiments of the present invention, they should also be regarded as the content disclosed by the embodiments of the present invention.

Claims

1. A method for site selection of community-embedded elderly care institutions, characterized in that, The method includes: Obtain supply and demand information for elderly care services; wherein, the supply and demand information includes information on multiple candidate elderly care institutions and information on the demand for elderly care services; The probability of selecting candidate elderly care institutions is defined based on the supply and demand information of the elderly care services. A site selection model for elderly care institutions is constructed based on the selection probabilities of the candidate elderly care institutions. The site selection model for elderly care institutions is solved based on a preset genetic algorithm, and the combination information of candidate sites for elderly care institutions that meet the needs of elderly care services is output. The information regarding the demand for elderly care services includes: Information on the level of elderly care needs and the location information of elderly care needs; among which, The information on the level of elderly care needs includes: Primary elderly care needs include: One or more of the following: dining hall needs, rest needs, haircut needs, and reading needs; Secondary elderly care needs include: One or more of the following: psychological counseling needs, medical needs, and health care needs; The secondary elderly care needs include the content of the primary elderly care needs, but the primary elderly care needs do not include the content of the secondary elderly care needs. The location information of elderly care needs is the geometric center of multiple areas divided based on the community area; The definition of the probability of selecting candidate elderly care institutions based on the supply and demand information of the elderly care services includes: The probability of selecting the candidate elderly care institution is: Where i∈I, I is the set of demand points; j∈J, where J is the set of candidate sites for elderly care institutions; s∈S, where S is the set of levels of elderly care needs. ={1,2}, where 1 represents primary elderly care needs and 2 represents secondary elderly care needs; h∈H, where H is the set of levels of elderly care institutions, H={1,2}, where 1 is a level 1 elderly care institution that can only provide level 1 elderly care needs, and 2 is a level 2 elderly care institution that can provide both level 1 and level 2 elderly care needs. Let i be the amount of resources that the s-level elderly care needs of demand point i can obtain from h-level elderly care institution j. Let i be the total amount of resources that demand point i can obtain from all elderly care institutions; The amount of resources that the S-level elderly care needs at demand point i can obtain from the h-level elderly care institution j. The function is: The total amount of resources available to all elderly care institutions The function is: in, To serve as a factor influencing population size; As the grade influence factor; β is the coefficient of friction during travel; Population size influencing factors The E function is: The level of influence factor The function is: in, The demand for elderly care at level i is the demand at demand point i relative to level s. Let i be the distance between demand point i and candidate elderly care institution j; This represents the theoretical maximum distance for h-level elderly care institutions. The process of constructing a site selection model for elderly care institutions based on the selection probabilities of the candidate institutions includes: The functional expression of the site selection model for elderly care institutions is: ； The constraint function of the elderly care facility site selection model is: Where P represents the number of elderly care facilities built; The decision variable is whether the elderly care demand at level i (s-level) is satisfied by elderly care institution j (h-level); This is a location selection variable.

2. The method according to claim 1, characterized in that, The process of solving the elderly care facility site selection model based on a preset genetic algorithm and outputting candidate site combinations for elderly care facilities that meet the needs of elderly care services includes: The location variables are chromosomally encoded; An initial population is generated based on chromosome coding results; Based on the initial population, the objective function and fitness value of each individual are determined, and the individual is selected using the roulette wheel algorithm based on the fitness value; Perform crossover operations between the currently selected individual and its adjacent individuals to obtain offspring individuals; Based on the offspring individuals, it is determined whether the objective function of the current individual has better convergence characteristics. If so, an elite retention strategy is adopted, removing a certain number of offspring individuals with poor fitness values ​​and retaining a certain number of parent individuals with good fitness values; and the initial population is updated based on the retained individuals; otherwise, a mutation operation is performed on the offspring individuals to obtain new offspring individuals. Based on the offspring individuals, determine whether the objective function of the current individual has better convergence characteristics. If so, remove a certain number of offspring individuals with poor fitness values ​​and retain a certain number of parent individuals with good fitness values; and perform the initial population update based on the retained individuals. The model for selecting locations for elderly care facilities is iterated based on the updated initial population or retained individuals. It is determined whether the number of iterations has reached the maximum value. If so, the iteration is stopped and the result is output. Otherwise, the initial population update step is repeated until the maximum number of iterations is reached and the result is output.

3. A community-embedded site selection system for elderly care institutions, characterized in that, The system includes: The data collection unit is used to acquire supply and demand information for elderly care services; wherein, the supply and demand information includes information on multiple candidate elderly care institutions and information on the demand for elderly care services; Model building unit, used for: The probability of selecting candidate elderly care institutions is defined based on the supply and demand information of the elderly care services. A site selection model for elderly care institutions is constructed based on the selection probabilities of the candidate elderly care institutions. The processing unit is used to solve the elderly care institution site selection model based on a preset genetic algorithm and output the candidate site combination information of elderly care institutions that meet the needs of elderly care services. The information regarding the demand for elderly care services includes: Information on the level of elderly care needs and the location information of elderly care needs; among which, The information on the level of elderly care needs includes: Primary elderly care needs include: One or more of the following: dining hall needs, rest needs, haircut needs, and reading needs; Secondary elderly care needs include: One or more of the following: psychological counseling needs, medical needs, and health care needs; The secondary elderly care needs include the content of the primary elderly care needs, but the primary elderly care needs do not include the content of the secondary elderly care needs. The location information of elderly care needs is the geometric center of multiple areas divided based on the community area; The definition of the probability of selecting candidate elderly care institutions based on the supply and demand information of the elderly care services includes: The probability of selecting the candidate elderly care institution is: Where i∈I, I is the set of demand points; j∈J, where J is the set of candidate sites for elderly care institutions; s∈S, where S is the set of levels of elderly care needs. ={1,2}, where 1 represents primary elderly care needs and 2 represents secondary elderly care needs; h∈H, where H is the set of levels of elderly care institutions, H={1,2}, where 1 is a level 1 elderly care institution that can only provide level 1 elderly care needs, and 2 is a level 2 elderly care institution that can provide both level 1 and level 2 elderly care needs. Let i be the amount of resources that the s-level elderly care needs of demand point i can obtain from h-level elderly care institution j. Let i be the total amount of resources that demand point i can obtain from all elderly care institutions; The amount of resources that the S-level elderly care needs at demand point i can obtain from the h-level elderly care institution j. The function is: The total amount of resources available to all elderly care institutions The function is: in, To serve as a factor influencing population size; As the grade influence factor; β is the coefficient of friction during travel; Population size influencing factors The E function is: The level of influence factor The function is: in, The demand for elderly care at level i is the demand at demand point i relative to level s. Let i be the distance between demand point i and candidate elderly care institution j; This represents the theoretical maximum distance for h-level elderly care institutions. The process of constructing a site selection model for elderly care institutions based on the selection probabilities of the candidate institutions includes: The functional expression of the site selection model for elderly care institutions is: ； The constraint function of the elderly care facility site selection model is: Where P represents the number of elderly care facilities built; The decision variable is whether the elderly care demand at level i (s-level) is satisfied by elderly care institution j (h-level); This is a location selection variable.

4. A computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the community-embedded elderly care facility site selection method according to any one of claims 1-2.

Images