Facility construction intelligent recommendation method for community pension service

Abstract

The invention discloses an intelligent recommendation method for facility construction of community pension service. The method comprises the following steps: S1, acquiring a community three-dimensional space distribution map; s2, performing questionnaire survey on community residents, analyzing intention demands of the residents on facilities which are expected to be perfected in the community according to survey results, and performing scoring by adopting an AHP-fuzzy comprehensive evaluation method to obtain intention demands with demand value scores ranking the first three; s3, according to the intention demand result of the demand value score ranked first three and in combination with the community three-dimensional space distribution diagram, a multi-objective optimization algorithm is adopted to analyze the construction site selection of the facility in the community and the feasibility and budget analysis of the construction, a plurality of recommendation schemes of facility construction are obtained, and a recommendation scheme candidate set is generated; and S4, analyzing and outputting an optimal recommendation scheme of facility construction from the recommendation scheme candidate set by adopting an improved NSGA-II algorithm.

Description

Technical Field

[0001] This invention relates to the field of community-based elderly care service technology, and in particular to an intelligent recommendation method for the construction of community-based elderly care service facilities. Background Technology

[0002] With the increasing aging of the population, the importance of community-based elderly care services is becoming increasingly prominent. Currently, many communities lack scientific site selection criteria and needs analysis in the planning and construction of elderly care facilities, leading to unreasonable resource allocation and an inability to effectively meet the actual needs of residents. Therefore, there is an urgent need for an intelligent facility construction recommendation method to achieve scientific and rational facility site selection, meet residents' actual needs, and improve their quality of life. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent recommendation method for the construction of community elderly care service facilities, so as to solve the problems mentioned in the background art.

[0004] This invention is achieved through the following technical solution:

[0005] A method for intelligent recommendation of facility construction for community-based elderly care services, the method comprising:

[0006] Step S1: Obtain a 3D spatial distribution map of the community;

[0007] Step S2: Conduct a questionnaire survey of community residents. Based on the survey results, analyze the residents' desired needs for facilities that they hope to improve in the community. Use the AHP-fuzzy comprehensive evaluation method to score the needs and obtain the top three desired needs in terms of demand value.

[0008] Step S3: Based on the top three intended needs in terms of demand value score and combined with the community's three-dimensional spatial distribution map, a multi-objective optimization algorithm is used to analyze the site selection for facility construction in the community, as well as the feasibility and budget analysis of construction, to obtain multiple recommended solutions for facility construction and generate a candidate set of recommended solutions.

[0009] Step S4: Analyze and output the optimal recommended scheme for facility construction from the candidate set of recommended schemes using the improved NSGA-II algorithm.

[0010] As a preferred embodiment of the present invention, the process of obtaining the three-dimensional spatial distribution map of the community in step S1 specifically includes: data collection, point cloud data processing, three-dimensional model construction and visualization display using UAV and LiDAR technology.

[0011] As a preferred embodiment of the present invention, the questionnaire design for the community residents' intentions and needs in step S2 adopts a multi-level structure, including residents' basic information, facility preferences and functional needs.

[0012] As a preferred embodiment of the present invention, the AHP-fuzzy comprehensive evaluation method in step S2 includes: performing pairwise comparisons of residents' needs, introducing fuzzy linguistic variables for scoring, and finally forming a comprehensive score. The specific process includes the following steps:

[0013] Step S21: Use the AHP method (Analytic Hierarchy Process) to construct a pairwise comparison matrix containing all facility needs. Residents will make pairwise comparisons of their needs for different facilities.

[0014] Step S22: Convert the pairwise comparison matrix into a weight score for each facility requirement using the eigenvalue method;

[0015] Step S23: Combine the weight of each facility with the residents' demand for each facility to form a fuzzy evaluation matrix;

[0016] Step S24: Using the weighted calculation formula of fuzzy numbers, the fuzzy evaluations of different facilities are integrated to obtain the final fuzzy comprehensive score;

[0017] Step S25: Defuzzify the results of the fuzzy comprehensive evaluation to obtain the final comprehensive score for each facility requirement; based on the final comprehensive score, rank all facility requirements and select the top three with the highest scores as residents' desired facilities for improvement in the community.

[0018] As a preferred embodiment of the present invention, step S3 specifically includes the following steps:

[0019] Step S31: Obtain the intended demand obtained in step S2, obtain the three-dimensional spatial distribution map of the community, specifically including the coordinates, area, type information of available plots, and the distribution of residents; add cost data, including construction and operation costs, as input data.

[0020] Step S32: Use a genetic algorithm to randomly generate a set of decision schemes based on different combinations of facility locations and scales, and calculate the objective function value for each scheme. The objective function value includes cost, coverage rate, and resident satisfaction.

[0021] Step S33: For the obtained site selection plan, assess the service range of the facilities, including whether each facility can effectively cover densely populated areas;

[0022] Step S34: Calculate the overall cost of each recommended option, including construction cost, operating cost and maintenance cost, and compare it with the budget constraint;

[0023] Step S35: Based on the site selection, scale and cost information of each scheme, output multiple recommended schemes and combine the multiple recommended schemes into a candidate set of recommended schemes. The content of the recommended schemes specifically includes the specific location and required area of ​​the facility construction, the estimated construction cost and operating budget, the service population coverage of the facility and the expected resident satisfaction.

[0024] As a preferred embodiment of the present invention, step S4 specifically includes the following steps:

[0025] Step S41: Using the improved NSGA-II algorithm (non-dominated sorting genetic algorithm), an initial population is randomly generated based on the candidate set of recommended solutions. Each individual in the population represents a facility recommendation solution, which is encoded as three-dimensional coordinates + facility type + budget cost.

[0026] Step S42: Perform a fast non-dominated ordination on the population, divide it into multiple front layers, calculate the crowding distance of individuals within the same front layer, and ensure diversity;

[0027] Step S43: Select high-quality individuals from the parent generation according to their crowding; perform crossover on the selected individuals to generate offspring; perturb the offspring genes with probability P to enhance population diversity;

[0028] Step S44: Merge the parent and offspring populations, perform a new non-dominated sort, and select the top N individuals as the new generation population;

[0029] Step S45: Set dynamic penalty weight ω in the new generation population i It calculates the relative proximity of individuals in the population and selects the individuals with the highest relative proximity as the optimal recommended scheme for facility construction.

[0030] As a preferred embodiment of the present invention, step S4 further includes: visually displaying the three-dimensional coordinates and required area of ​​the optimal recommended scheme for facility construction in a three-dimensional spatial distribution map of the community.

[0031] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0032] This invention provides an intelligent recommendation method for the construction of community-based elderly care service facilities. By acquiring a three-dimensional spatial distribution map of the community, analyzing residents' intended needs, and employing a multi-objective optimization algorithm, the method intelligently recommends suitable elderly care service facility construction plans for the community. This method obtains demand scores through fuzzy comprehensive evaluation and optimizes facility site selection using an improved NSGA-II algorithm, thereby enhancing the scientific rigor and effectiveness of elderly care service facility construction. This improves the quality of life and satisfaction of community residents, optimizes resource allocation, and through intelligent recommendation decision-making, effectively reduces unnecessary resource waste, improves the utilization efficiency and service quality of completed facilities, and ultimately enhances the overall elderly care service capacity of the community. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only preferred embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 A flowchart illustrating the steps of the intelligent recommendation method for community elderly care service facility construction provided by this invention. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of the present invention, and not all of the embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of the present invention.

[0036] In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described in order to avoid obscuring the invention.

[0037] It should be understood that the invention can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0038] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and / or “including,” when used in this specification, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.

[0039] To fully understand this invention, a detailed structure will be presented in the following description to illustrate the technical solution proposed by this invention. Optional embodiments of the invention are described in detail below; however, in addition to these detailed descriptions, the invention may have other embodiments.

[0040] See Figure 1 A method for intelligent recommendation of community elderly care service facility construction, the method comprising:

[0041] Step S1: Obtain a 3D spatial distribution map of the community;

[0042] Step S2: Conduct a questionnaire survey of community residents. Based on the survey results, analyze the residents' desired needs for facilities that they hope to improve in the community. Use the AHP-fuzzy comprehensive evaluation method to score the needs and obtain the top three desired needs in terms of demand value.

[0043] Step S3: Based on the top three intended needs in terms of demand value score and combined with the community's three-dimensional spatial distribution map, a multi-objective optimization algorithm is used to analyze the site selection for facility construction in the community, as well as the feasibility and budget analysis of construction, to obtain multiple recommended solutions for facility construction and generate a candidate set of recommended solutions.

[0044] Step S4: Analyze and output the optimal recommended scheme for facility construction from the candidate set of recommended schemes using the improved NSGA-II algorithm.

[0045] For example, in the specific implementation of this invention, step S1 utilizes UAV and LiDAR technology for high-precision three-dimensional spatial data acquisition, a process including flight path planning, data acquisition, and point cloud processing. Step S2, the analysis of residents' intentions and needs, employs a standardized multi-level questionnaire design, combined with the AHP (Analytic Hierarchy Process) method, and uses fuzzy theory for scoring to ensure objectivity and accuracy. Step S3, the multi-objective optimization algorithm, enables a reasonable evaluation of the construction site selection scheme, ensuring that the final recommended scheme achieves the best balance among multiple objectives such as cost and social benefits. Furthermore, in step S4, the improved NSGA-II algorithm (Non-Dominated Sorting Genetic Algorithm) improves the efficiency of the solution through an adaptive mechanism, making the recommended scheme more practical.

[0046] As a preferred embodiment of the present invention, the process of obtaining the three-dimensional spatial distribution map of the community in step S1 specifically includes: data collection, point cloud data processing, three-dimensional model construction and visualization display using UAV and LiDAR technology.

[0047] For example, select a suitable drone, typically equipped with a high-resolution camera and LiDAR sensor, to ensure the acquisition of high-quality surface and building data. Plan the flight path to ensure coverage of the entire community area, avoiding omissions of important locations. Consider flight altitude and overlap, typically choosing a flight altitude of 100-150 meters and an overlap of 70%-80% to ensure data integrity and continuity. Conduct the drone flight, capturing terrain, building, and other feature information using LiDAR. Simultaneously, use the camera to capture high-resolution images for subsequent texture mapping.

[0048] Point cloud data generated using lidar, including the spatial coordinates (X, Y, Z) and reflection intensity information of each point, reflects the three-dimensional features of the ground surface and surrounding facilities. The acquired point cloud data is filtered to remove noise and outliers to improve its quality. Ground classification algorithms are used to categorize ground points, building points, and vegetation points to ensure the accuracy of subsequent processing. Data from different flight paths or different sensors are registered to generate a unified point cloud model, and the ICP (Iterative Closest Point) algorithm is used for precise alignment.

[0049] Surface reconstruction techniques (such as Delaun triangulation or Poisson Surface Reconstruction) are used to convert point clouds into 3D mesh models, forming the terrain and building structures of the community. Various elements, including building outlines, roads, and green spaces, are identified and extracted to establish the community's 3D geographic information. Attributes are assigned to each element in the 3D model, such as building type, use, number of floors, and green space area, to enrich the information content.

[0050] The generated 3D model is visualized using Geographic Information System (GIS) software or specialized 3D modeling software (such as SketchUp, Blender, etc.). Texture mapping is applied to the 3D model, and photo data is used to color the model, improving the visualization effect and making it intuitive and easy to understand.

[0051] Through the above steps, the 3D spatial distribution map of the community obtained by applying UAV and LiDAR technology not only provides detailed information on the community's geospatial location, but also provides reliable spatial foundation data for subsequent steps (such as resident demand analysis, facility site selection, budget analysis, etc.).

[0052] As a preferred embodiment of the present invention, the questionnaire design for the community residents' intentions and needs in step S2 adopts a multi-level structure, including residents' basic information, facility preferences and functional needs.

[0053] For example, by combining residents' basic information with their facility preferences, the needs of specific groups can be identified, making researchers more accurate in subsequent analyses and ensuring that recommendations are more targeted.

[0054] By collecting functional requirements, decision-makers can be encouraged to consider the actual needs of the community when designing facilities, thereby avoiding waste of resources and improving facility utilization and satisfaction.

[0055] As a preferred embodiment of the present invention, the AHP-fuzzy comprehensive evaluation method in step S2 includes: performing pairwise comparisons of residents' needs, introducing fuzzy linguistic variables for scoring, and finally forming a comprehensive score. The specific process includes the following steps:

[0056] Step S21: Construct a pairwise comparison matrix containing all facility needs using the AHP method. Residents will make pairwise comparisons of their needs for different facilities. Using the scale in AHP, typically rated from 1 to 9, where 1 indicates that both are equally important and 9 indicates that one need is extremely important to the other.

[0057] Step S22: Convert the pairwise comparison matrix into a weight score for each facility requirement using the eigenvalue method; calculate the eigenvalues ​​and eigenvectors of the pairwise comparison matrix to find the weight score for each requirement.

[0058] Step S23: Combine the weight of each facility with the degree of residents' demand for each facility to form a fuzzy evaluation matrix; each element in the matrix represents the fuzzy evaluation level of facility demand.

[0059] Step S24: Using the weighted calculation formula of fuzzy numbers, the fuzzy evaluations of different facilities are synthesized to obtain the final fuzzy comprehensive score; the specific process is as follows:

[0060]

[0061] In the formula, F i Represented as the fuzzy number after synthesis, ω j F represents the weight of facility acquisition. ij This indicates the fuzzy assessment level of facility requirements, where m represents the total number of facility requirements.

[0062] Step S25: Defuzzify the results of the fuzzy comprehensive evaluation to obtain the final comprehensive score for each facility requirement; based on the final comprehensive score, rank all facility requirements and select the top three with the highest scores as residents' desired facilities for improvement in the community.

[0063] For example, by using pairwise comparisons and fuzzy evaluations, the relative importance of various facility requirements can be systematically assessed, thereby forming a scientific and reasonable comprehensive score, making decision-making more data-driven and rational.

[0064] Using fuzzy linguistic variables (such as "very important," "important," "general," etc.) can better reflect residents' true needs, capture the ambiguity caused by individual differences, and avoid the limitations of traditional quantitative methods. The AHP method effectively transforms the relative relationships between various facility needs through weight transformation, ensuring that the impact of different needs on decision-making is reasonably allocated, and helping to identify the most critical facility needs. After comprehensive scoring and defuzzification, the needs of various facilities can be clearly ranked, accurately identifying the top three types of facilities that residents most want to add or improve, providing a clear direction for construction.

[0065] As a preferred embodiment of the present invention, step S3 specifically includes the following steps:

[0066] Step S31: Obtain the intended needs obtained in step S2. The intended needs mainly refer to the types of facilities that residents hope to build or improve, such as elderly care centers, activity venues, and medical facilities; obtain a three-dimensional spatial distribution map of the community, which specifically includes the coordinates, area, and type information of available plots, as well as the distribution of residents; add cost data, including construction and operation costs, as input data.

[0067] Step S32: Use a genetic algorithm to randomly generate a set of decision schemes based on different combinations of facility locations and scales, and calculate the objective function value for each scheme. The objective function value includes three dimensions: cost, coverage, and resident satisfaction.

[0068] For example, a genetic algorithm is used to optimize facility location and scale combinations. The basic process of a genetic algorithm includes:

[0069] Initialize the population: Randomly generate multiple possible facility site configurations, including different numbers of facilities, combinations of site plots, facility sizes, etc.

[0070] Each individual (scheme) is represented as a coded sequence, containing the type, location, and size of each facility.

[0071] Step S33: For the obtained site selection plan, evaluate the service range of the facilities, including whether each facility can effectively cover densely populated areas; calculate the service range that each facility can effectively cover based on the type and size of the facilities and the geographical distribution of residents.

[0072] Using resident distribution maps and facility locations, evaluate the service radius of each facility.

[0073] Step S34: Calculate the overall cost of each recommended option, including construction cost, operating cost and maintenance cost, and compare it with the budget constraint;

[0074] Step S35: Based on the site selection, scale and cost information of each scheme, output multiple recommended schemes and combine the multiple recommended schemes into a candidate set of recommended schemes. The content of the recommended schemes specifically includes the specific location and required area of ​​the facility construction, the estimated construction cost and operating budget, the service population coverage of the facility and the expected resident satisfaction.

[0075] For example, multiple recommendation schemes are output:

[0076] Based on the comprehensive evaluation, several recommended solutions are output, each of which includes the following details:

[0077] The specific location of the facility is marked on the distribution map using coordinate mapping.

[0078] Required area: The area calculated based on the type of facility and the expected population to be served.

[0079] Estimated construction costs and operating budget: A detailed list of all expenses related to implementation.

[0080] Service population coverage: Indicates the number of residents and the corresponding area that the facility can affect and cover.

[0081] Resident satisfaction expectations: Based on demand assessment and coverage assessment, provide residents' satisfaction indicators for the type and scale of the facility.

[0082] For example, through step S3, genetic algorithms and multidimensional evaluation methods are used to effectively integrate resident needs, spatial resources, and cost data, providing a scientific, reasonable, and flexible site selection scheme for the construction of community-based elderly care facilities. This not only maximizes resident satisfaction but also enhances the economic efficiency and sustainability of facility construction, thereby promoting the overall development of the community.

[0083] As a preferred embodiment of the present invention, step S4 specifically includes the following steps:

[0084] Step S41: Using the improved NSGA-II algorithm, an initial population is randomly generated based on the candidate set of recommended solutions. Each individual in the population represents a facility recommendation solution, which is encoded as three-dimensional coordinates + facility type + budget cost.

[0085] Step S42: Perform a fast non-dominated ordination on the population, divide it into multiple front layers, calculate the crowding distance of individuals within the same front layer, and ensure diversity;

[0086] Step S43: Select high-quality individuals from the parent generation according to their crowding; perform crossover on the selected individuals to generate offspring; perturb the offspring genes with probability P to enhance population diversity;

[0087] Step S44: Merge the parent and offspring populations, perform a new non-dominated sort, and select the top N individuals as the new generation population;

[0088] Step S45: Set dynamic penalty weight ω in the new generation population i The algorithm calculates the relative proximity of individual i in the population and selects the individual with the highest relative proximity as the optimal recommended solution for facility construction.

[0089] For specific constraints, including budget restrictions and construction area restrictions, a dynamic penalty mechanism is introduced into the fitness function to penalize individuals that do not meet the constraints.

[0090] The penalty weights can be dynamically adjusted based on the urgency and importance of the goal, thereby optimizing the individual's fitness score.

[0091] Calculating relative proximity: Based on the proximity between the target solution and the ideal solution, the formula for calculating relative proximity is defined:

[0092]

[0093] In the formula, D i f represents the similarity between individuals. ij This represents the value of individual i for the j-th objective. This represents the objective value of the ideal solution.

[0094] For example, through step S4, the improved NSGA-II algorithm can be used to effectively explore and optimize different facility recommendation schemes, achieving a balance and optimal configuration across multiple objectives. This process ensures the diversity and adaptability of the schemes, ultimately providing high-quality intelligent recommendations for facility construction. This not only improves the scientific rigor of facility site selection but also enhances the responsiveness to residents' needs, making the schemes more closely aligned with actual requirements.

[0095] As a preferred embodiment of the present invention, step S4 further includes: visually displaying the three-dimensional coordinates and required area of ​​the optimal recommended scheme for facility construction in a three-dimensional spatial distribution map of the community.

[0096] For example, the required 3D coordinates of the facilities and the required construction area are extracted from the optimal recommended solution. This step ensures that all relevant data is accurate, which is beneficial for subsequent spatial design.

[0097] Using computer graphics software or a Geographic Information System (GIS), the extracted 3D coordinates and facility area information of the optimal solution are mapped and marked on a 3D spatial distribution map of the community. The specific locations of the facilities are displayed on the map using markers (such as icons or symbols). Based on the area required by the facilities, areas are drawn with appropriate shapes (such as rectangles or polygons) to clearly show the space occupied by each facility.

[0098] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligently recommending facilities for community-based elderly care services, characterized in that, The method includes: Step S1: Obtain a 3D spatial distribution map of the community; Step S2: Conduct a questionnaire survey of community residents. Based on the survey results, analyze the residents' desired needs for facilities that they hope to improve in the community. Use the AHP-fuzzy comprehensive evaluation method to score the needs and obtain the top three desired needs in terms of demand value. Step S3: Based on the top three intended needs in terms of demand value score and combined with the community's three-dimensional spatial distribution map, a multi-objective optimization algorithm is used to analyze the site selection for facility construction in the community, as well as the feasibility and budget analysis of construction, to obtain multiple recommended solutions for facility construction and generate a candidate set of recommended solutions. Step S4: Analyze and output the optimal recommended scheme for facility construction from the candidate set of recommended schemes using the improved NSGA-II algorithm.

2. The intelligent recommendation method for the construction of community elderly care service facilities according to claim 1, characterized in that, The process of obtaining the community's three-dimensional spatial distribution map in step S1 specifically includes: using UAV and LiDAR technology for data collection, point cloud data processing, three-dimensional model construction, and visualization.

3. The intelligent recommendation method for the construction of community elderly care service facilities according to claim 2, characterized in that, The questionnaire design for community residents' intentions and needs in step S2 adopts a multi-level structure, including residents' basic information, facility preferences, and functional needs.

4. The intelligent recommendation method for the construction of community elderly care service facilities according to claim 3, characterized in that, The AHP-fuzzy comprehensive evaluation method in step S2 includes: performing pairwise comparisons of residents' needs, introducing fuzzy linguistic variables for scoring, and finally forming a comprehensive score. The specific process involves the following steps: Step S21: Use the AHP method to construct a pairwise comparison matrix containing all facility requirements, and perform pairwise comparisons of the requirements for different facilities; Step S22: Convert the pairwise comparison matrix into a weight score for each facility requirement using the eigenvalue method; Step S23: Combine the weight of each facility with the residents' demand for each facility to form a fuzzy evaluation matrix; Step S24: Using the weighted calculation formula of fuzzy numbers, the fuzzy evaluations of different facilities are integrated to obtain the final fuzzy comprehensive score; Step S25: Defuzzify the results of the fuzzy comprehensive evaluation to obtain the final comprehensive score for each facility requirement; based on the final comprehensive score, rank all facility requirements and select the top three with the highest scores as residents' desired facilities for improvement in the community.

5. The intelligent recommendation method for the construction of community elderly care service facilities according to claim 4, characterized in that, Step S3 specifically includes the following steps: Step S31: Obtain the intended demand obtained in step S2, obtain the three-dimensional spatial distribution map of the community, specifically including the coordinates, area, type information of available plots, and the distribution of residents; add cost data, including construction and operation costs, as input data. Step S32: Use a genetic algorithm to randomly generate a set of decision schemes based on different combinations of facility locations and scales, and calculate the objective function value for each scheme. The objective function value includes cost, coverage rate, and resident satisfaction. Step S33: For the obtained site selection plan, assess the service range of the facilities, including whether each facility can effectively cover densely populated areas; Step S34: Calculate the overall cost of each recommended option, including construction cost, operating cost and maintenance cost, and compare it with the budget constraint; Step S35: Based on the site selection, scale and cost information of each scheme, output multiple recommended schemes and combine the multiple recommended schemes into a candidate set of recommended schemes. The content of the recommended schemes specifically includes the specific location and required area of ​​the facility construction, the estimated construction cost and operating budget, the service population coverage of the facility and the expected resident satisfaction.

6. The intelligent recommendation method for the construction of community elderly care service facilities according to claim 5, characterized in that, Step S4 specifically includes the following steps: Step S41: Using the improved NSGA-II algorithm, an initial population is randomly generated based on the candidate set of recommended solutions. Each individual in the population represents a facility recommendation solution, which is encoded as three-dimensional coordinates + facility type + budget cost. Step S42: Perform a fast non-dominated ordination on the population, divide it into multiple front layers, calculate the crowding distance of individuals within the same front layer, and ensure diversity; Step S43: Select high-quality individuals from the parent generation according to their crowding; perform crossover on the selected individuals to generate offspring; perturb the offspring genes with probability P to enhance population diversity; Step S44: Merge the parent and offspring populations, perform a new non-dominated sort, and select the top N individuals as the new generation population; Step S45: Set dynamic penalty weight ω in the new generation population i It calculates the relative proximity of individuals in the population and selects the individuals with the highest relative proximity as the optimal recommended scheme for facility construction.

7. The intelligent recommendation method for the construction of community elderly care service facilities according to claim 6, characterized in that, Step S4 further includes: visualizing the three-dimensional coordinates and required area of ​​the optimal recommended plan for facility construction in a three-dimensional spatial distribution map of the community.

Images