Site selection method and system for community health service center in urban high-density environment

Abstract

The present disclosure relates to a community health service center site selection method and system in a high-density urban environment, comprising: obtaining data of a target area in a high-density urban environment to form a first sample data set; organizing the first sample data set to obtain a second sample data set; obtaining community health service center site selection related indicators from the second sample data set to further obtain a third sample data set; sampling the third sample data set to obtain a fourth sample data set, and through parameter optimization and feature combination optimization, obtaining a community health service center site selection model; and inputting the feature value data set of the third sample data set into the model to obtain a candidate point, and using a maximum coverage model to determine a service center site selection point set that can cover the most demand points. The method of the present disclosure can effectively improve the site selection accuracy and service coverage of the health service center.

Description

Technical Field

[0001] The present disclosure relates to the technical field of urban planning big data information processing, and in particular to a method and system for site selection of community health service centers in a high-density urban environment. Background Art

[0002] Community health service centers are the foundation of urban medical and health service systems and the gatekeepers of public health. Establishing public health units within a community's 15-minute living area, strengthening the planning and construction of community health service centers, and optimizing the allocation of primary health service facilities and resources are crucial for meeting public health needs and improving residents' health. Existing research has primarily focused on proposing site selection strategies for community health service centers, focusing on qualitative exploration of factors influencing site selection or basic analysis using ArcGIS for basic geographic information, such as surrounding transportation networks and land use efficiency. However, quantitative research and application of multi-source data systems within the study area are insufficient. In addition, existing site selection methods mainly use measurement factors such as accessibility, population density, and service scope. These factors are not comprehensive when considering the site selection of community health service centers in high-density urban built-up environments, and fail to consider multi-dimensional factors such as population characteristics, natural environment, resident accessibility, built environment, and urban functions. In quantitative research on site selection decisions, existing studies have mostly used the subjective Analytic Hierarchy Process (AHP) as a multi-objective decision-making method, lacking the systematic and objective use of multi-dimensional and multi-source data, the consideration of multiple machine learning algorithms combined with the maximum coverage model for modeling and site selection, and the application exploration of model parameter and feature selection and combination optimization.

[0003] Therefore, it is necessary to propose a site selection method for community health service centers in high-density urban environments to effectively improve the accuracy of site selection and service coverage of community health service centers. Summary of the Invention

[0004] To address the problem of inaccurate service center location selection in traditional site selection methods, which leads to low health service coverage, this paper proposes a site selection method for community health service centers in high-density urban environments. This method comprehensively considers factors in five dimensions: population characteristics, accessibility, built environment, natural environment, and urban functions. It uses "multi-source data + machine learning + maximum coverage model" combined with "algorithm optimization + parameter tuning + feature combination optimization" to make more systematic and accurate decisions on the site selection of community health service centers.

[0005] According to one aspect of the present disclosure, a method for selecting a site for a community health service center in a high-density urban environment is provided, comprising:

[0006] S10, obtaining network open source data, population grid data, mobile phone signaling data, point of interest / area of ​​interest data, night light data, building unit data, normalized difference vegetation index data, PM2.5 concentration data, and urban road data of the target area in a high-density urban environment to form a first sample data set;

[0007] S20: Arrange and correct the data in the first sample data set to obtain a second sample data set;

[0008] S30. Calculate community health service center site selection-related indicators based on the second sample data set, and normalize the relevant indicators to obtain a third sample data set, where the relevant indicators include one or more of the following indicators: population density index, population structure index, general hospital accessibility index, public transportation convenience index, subway convenience index, residential area accessibility index, building density index, floor area ratio index, night light index, normalized vegetation index, surrounding functional density index, surrounding functional diversity index, general hospital index, and residential area index.

[0009] S40, sampling according to the target values ​​of the samples in the third sample data set to obtain a fourth sample data set, and based on the fourth sample data set, using an optimal machine learning algorithm to construct a preliminary model for the site selection of community health service centers, using grid search to perform parameter tuning, and outputting the optimal parameter combination through K-fold cross-validation to obtain the preliminary model for the site selection of community health service centers;

[0010] S50, evaluating the preliminary model for site selection of the community health service center, calculating the contribution of relevant indicators in the preliminary model for site selection of the community health service center, and optimizing feature selection and combination using Monte Carlo simulation to obtain the optimal feature combination for the preliminary model for site selection of the community health service center;

[0011] S60. Based on the optimal feature combination, the optimal machine learning algorithm is used to construct a community health service center site selection model, parameters of the community health service center site selection model are optimized, and the optimal parameter combination is output through K-fold cross validation to obtain the community health service center site selection model trained with the optimal feature combination and the optimal parameter combination;

[0012] S70, evaluating the obtained community health service center site selection model, and calculating the contribution of relevant indicators in the community health service center site selection model;

[0013] S80. Export and save the community health service center site selection model, input the eigenvalue dataset in the third sample dataset in the target area into the community health service center site selection model, obtain alternative site selection points for the community health service center, determine the number of community health service centers to be added based on the population size of the target area, and use the maximum coverage model to determine a set of community health service center site selection points that can cover the most demand points among the alternative site selection points for the community health service center.

[0014] Preferably, arranging and correcting the data in the first sample data set includes:

[0015] A first sample data set is input, and mobile phone signaling data in the first sample data set is randomly assigned; a line chart is used to draw the data of each feature in the first sample data set to determine whether there are outliers in the data of each feature that deviate far from the normal range, and the outliers are deleted; duplicate operations are performed on the same data in the first sample set; and the urban road data in the first sample data set are checked and corrected.

[0016] Preferably, the community health service center site selection related indicators calculated based on the second sample data set specifically include:

[0017] Converting building unit surface data into geometric center point data of the building unit surface;

[0018] According to the population grid data, the population in the grid is counted to obtain the population density index;

[0019] According to the mobile phone signaling data, the user age structure distribution is counted to obtain the population structure index;

[0020] Based on the data of points of interest / areas of interest, calculate the accessibility index of general hospitals, bus convenience index, subway convenience index and residential accessibility index;

[0021] Calculate building density index and volume ratio index based on building unit data;

[0022] Calculate the night light index based on the night light data;

[0023] According to the normalized vegetation index data, a grid layer containing normalized vegetation index information is obtained, and the normalized vegetation index index is calculated;

[0024] Based on the data of points of interest / areas of interest, the surrounding functional density index, surrounding functional diversity index, comprehensive hospital index and residential community index are calculated.

[0025] Preferably, the relevant indicators are normalized to obtain a third sample data set, which is expressed as:

[0026] ,

[0027] Where, X is the original data, For normalized data, and are the maximum and minimum values ​​in the original data, respectively.

[0028] Preferably, the fourth sample data set is obtained by sampling the target values ​​of the samples in the third sample data set, and based on the fourth sample data set, an optimal machine learning algorithm is used to construct a preliminary model for site selection of community health service centers, including:

[0029] Importing the third sample data set into the table, oversampling the samples with a target value of 1 in the third sample data set, undersampling the samples with a target value of 0, and sorting the samples with target values ​​of 1 and 0 to generate a fourth sample data set;

[0030] 80% of the fourth sample data set is used as the training set and 20% as the test set;

[0031] A variety of machine learning algorithms were used to conduct model construction tests. The optimal machine learning algorithm with the best goodness of fit and root mean square error was determined based on the test results. The optimal machine learning algorithm was selected to construct a preliminary model for the site selection of community health service centers.

[0032] Preferably, the maximum coverage model is used to determine a set of community health service center site selection points that can cover the most demand points among the community health service center site selection candidate points. The maximum coverage model is expressed as:

[0033] ,

[0034] The constraint formula of the maximum coverage model is:

[0035] ,

[0036] ,

[0037] ,

[0038] In the formula, max S is the sum of the covered demand points, i As demand points, take residential areas as demand points, j Select alternative sites for community health service centers, Whether the demand point is covered, To cover the demand points i The set of candidate points, m is the number of alternative points, M Limit the number of sites for community health service centers. Whether to use the alternative point as the site selection point.

[0039] According to one aspect of the present disclosure, a system for selecting a site for a community health service center in a high-density urban environment is provided, comprising:

[0040] The data acquisition module acquires network open source data, population grid data, mobile phone signaling data, point of interest / area of ​​interest data, night light data, building unit data, normalized difference vegetation index data, PM2.5 concentration data, and urban road data of the target area in a high-density urban environment to form the first sample data set;

[0041] A second sample set acquisition module, which organizes and corrects the data in the first sample set to obtain a second sample set;

[0042] a related indicator processing module, which calculates community health service center site selection related indicators based on the second sample data set, and normalizes the related indicators to obtain a third sample data set, wherein the related indicators include one or more of the following indicators: population density index, population structure index, general hospital accessibility index, public transportation convenience index, subway convenience index, residential area accessibility index, building density index, floor area ratio index, night light index index, normalized vegetation index index, surrounding function density index, surrounding function diversity index, general hospital index, and residential area index;

[0043] a preliminary model construction module for site selection of community health service centers, which samples a fourth sample data set according to the target values ​​of the samples in the third sample data set, constructs a preliminary model for site selection of community health service centers based on the fourth sample data set using an optimal machine learning algorithm, performs parameter tuning using grid search, and outputs the optimal parameter combination through K-fold cross-validation to obtain a preliminary model for site selection of community health service centers;

[0044] Optimizing the feature selection and combination module, evaluating the preliminary model for site selection of community health service centers, calculating the contribution of relevant indicators in the preliminary model for site selection of community health service centers, and optimizing the feature selection and combination using Monte Carlo simulation to obtain the optimal feature combination for the preliminary model for site selection of community health service centers;

[0045] A community health service center site selection model construction module, based on the optimal feature combination, uses the optimal machine learning algorithm to construct a community health service center site selection model, performs parameter tuning on the community health service center site selection model, and outputs the optimal parameter combination through K-fold cross-validation to obtain the community health service center site selection model under the optimal feature combination and optimal parameter combination training;

[0046] The model evaluation module evaluates the obtained community health service center site selection model and calculates the contribution of the related indicators in the community health service center site selection model.

[0047] The site set determination module exports and saves the community health service center site selection model, inputs the feature value data set in the third sample data set in the target region into the community health service center site selection model, obtains community health service center site selection candidate points, determines the number of community health service centers to be newly added according to the population size of the target region, and uses the maximum coverage model to determine a community health service center site set that can cover the most demand points from the community health service center site selection candidate points.

[0048] According to an aspect of the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the above-mentioned community health service center site selection method in a high-density urban environment.

[0049] According to an aspect of the present disclosure, a computer-readable storage medium having computer program instructions stored thereon is provided, the computer program instructions being executed by a processor to implement the above-mentioned community health service center site selection method in a high-density urban environment.

[0050] Compared with the prior art, the present disclosure has the following beneficial effects:

[0051] 1) The present disclosure proposes a community health service center site selection method in a high-density urban environment, obtains multi-source data of five dimensions of target region population characteristics, accessibility, built environment, natural environment and urban function in a high-density built urban environment, and obtains a fourth sample data set by processing the data, to build a comprehensive feature index system for a community health service center site selection model based on machine learning.

[0052] 2) The present disclosure tests the model construction by using five machine learning regression algorithms, LightGBM, XGBoost, CatBoost, NGBoost and random forest, obtains the optimal machine learning algorithm with the best R-squared (fitting degree) and RMSE (root mean square error), and uses network search to optimize the parameters, and based on the shap value obtained by calculating the contribution of each feature, the feature selection and combination are optimized by Monte Carlo simulation, and then the community health service center site selection model is obtained, which can effectively improve the accuracy of community health service center site selection.

[0053] 3) The present disclosure inputs the characteristic value data set in the third sample data set in the target area into the community health service center site selection model to obtain alternative site selection points for the community health service center, and uses the maximum coverage model to determine the set of community health service center site selection points that can cover the most demand points among the alternative site selection points for the community health service center. This process can ensure the coverage rate of community health services in the target area.

[0054] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

[0055] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solutions of the present disclosure.

[0057] Figure 1 Shows the flow chart of the site selection method for community health service centers in high-density urban environments;

[0058] Figure 2 A schematic diagram showing the contribution of each feature in the preliminary model for site selection of a community health service center in an embodiment of the present disclosure is shown;

[0059] Figure 3 A schematic diagram of the cross-validation score of the model under different feature combinations in the embodiment of the present disclosure is shown;

[0060] Figure 4 A schematic diagram showing the contribution of each feature in the community health service center site selection model according to an embodiment of the present disclosure is shown;

[0061] Figure 5 A schematic diagram of a set of community health service center locations that can cover the most demand points in an embodiment of the present disclosure is shown;

[0062] Figure 6 The structural block diagram of the community health service center site selection system in a high-density urban environment is shown. DETAILED DESCRIPTION

[0063] Various exemplary embodiments, features, and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0064] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0065] The term "and / or" herein simply describes an association relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent the existence of three situations: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0066] In addition, numerous specific details are provided in the following detailed description to better illustrate the present disclosure. Those skilled in the art will appreciate that the present disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art are not described in detail in order to highlight the main points of the present disclosure.

[0067] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0068] Example 1

[0069] Based on the above ideas, the present invention proposes a site selection method for community health service centers in a high-density urban environment. Figure 1 A flow chart illustrating a method for selecting a site for a community health service center in a high-density urban environment. The method includes:

[0070] S10, obtaining network open source data, population grid data, mobile phone signaling data, point of interest / area of ​​interest data, night light data, building unit data, normalized difference vegetation index data, PM2.5 concentration data, and urban road data of the target area in a high-density urban environment to form a first sample data set;

[0071] S20: Arrange and correct the data in the first sample data set to obtain a second sample data set;

[0072] S30. Calculate community health service center site selection-related indicators based on the second sample data set, and normalize the relevant indicators to obtain a third sample data set, where the relevant indicators include one or more of the following indicators: population density index, population structure index, general hospital accessibility index, public transportation convenience index, subway convenience index, residential area accessibility index, building density index, floor area ratio index, night light index, normalized vegetation index, surrounding functional density index, surrounding functional diversity index, general hospital index, and residential area index.

[0073] S40, sampling according to the target values ​​of the samples in the third sample data set to obtain a fourth sample data set, and based on the fourth sample data set, using an optimal machine learning algorithm to construct a preliminary model for the site selection of community health service centers, using grid search to perform parameter tuning, and outputting the optimal parameter combination through K-fold cross-validation to obtain the preliminary model for the site selection of community health service centers;

[0074] S50, evaluating the preliminary model for site selection of the community health service center, calculating the contribution of relevant indicators in the preliminary model for site selection of the community health service center, and optimizing feature selection and combination using Monte Carlo simulation to obtain the optimal feature combination for the preliminary model for site selection of the community health service center;

[0075] S60. Based on the optimal feature combination, the optimal machine learning algorithm is used to construct a community health service center site selection model, parameters of the community health service center site selection model are optimized, and the optimal parameter combination is output through K-fold cross validation to obtain the community health service center site selection model trained with the optimal feature combination and the optimal parameter combination;

[0076] S70, evaluating the obtained community health service center site selection model, and calculating the contribution of relevant indicators in the community health service center site selection model;

[0077] S80. Export and save the community health service center site selection model, input the eigenvalue dataset in the third sample dataset in the target area into the community health service center site selection model, obtain candidate site selection points for the community health service centers, determine the number of community health service centers to be added based on the population size of the target area, and use the maximum coverage model to determine a set of community health service center site selection points that can cover the most demand points among the candidate site selection points for the community health service centers;

[0078] The present disclosure provides a method for selecting a site for a community health service center in a high-density urban environment. The method targets Yuexiu District, Guangzhou, and includes the following steps:

[0079] S10, acquire network open source data, population quantity grid data, mobile phone signaling data, point of interest / surface of interest data, night light data, building unit data, normalized vegetation index data, PM2.5 concentration data and urban road data of a target area in a high-density urban environment to form a first sample data set.

[0080] Further, step S10 specifically comprises:

[0081] S101, acquire network open source data: obtain the community health service center information table of Yuexiu District, Guangzhou from the Guangzhou Health Commission webpage, and acquire the basic administrative map from the national geographic information public service platform;

[0082] S102, acquire population quantity grid data: acquire the population quantity grid data with a precision of 100 meters nationwide from worldpop;

[0083] S103, acquire mobile phone signaling data: apply for relevant mobile phone signaling data to the China Unicom Wisdom Footprint;

[0084] S104, acquire point of interest / surface of interest data: acquire the Baidu Map Guangzhou POI data information based on the Python web crawler technology, and the data includes leisure activity facilities, cultural and sports facilities, transportation auxiliary facilities, catering service facilities, hotel accommodation facilities, commercial facilities, government agencies, etc.;

[0085] S105, acquire urban road data: acquire road line elements and road name and type data from the OSM open source wiki map;

[0086] S106, acquire building unit data: acquire building unit surface data and height data from the Guangzhou building CAD data;

[0087] S107, acquire night light data: acquire the global 500-meter precision night light data from the national earth system science data center sharing service platform open source;

[0088] S108, acquire PM2.5 concentration data: acquire the national 1-kilometer precision PM2.5 concentration data from the national earth system science data center sharing service platform open source;

[0089] S109, acquire normalized vegetation index data: acquire the national 30-meter precision normalized vegetation index data from the national science and technology infrastructure platform-national ecological science data center open source;

[0090] S20, correct the data in the first sample data set to obtain a second sample data set.

[0091] In this embodiment, the data in the first sample data set is corrected and modified, including:

[0092] A first sample data set is input, and mobile phone signaling data in the first sample data set is randomly assigned; a line chart is used to draw the data of each feature in the first sample data set to determine whether there are outliers in the data of each feature that deviate far from the normal range, and the outliers are deleted; duplicate operations are performed on the same data in the first sample set; and the urban road data in the first sample data set are checked and corrected.

[0093] In this embodiment, step S20 specifically includes:

[0094] S201. Data input: Enter the collected community health service center information into an Excel spreadsheet. Write a Python program to read the information in the Excel spreadsheet. Use the geocoding application on the AutoNavi open platform to batch-acquire the GCJ-02 geographic coordinates of the community health service centers. Convert the GCJ-02 geographic coordinates to WGS-1984 geographic coordinates. After data correction and cleaning, obtain a list of community health service center coordinates.

[0095] S202, random value processing: If the population of a single grid in the mobile phone signaling data is less than 5, it is uniformly represented by "<5". Therefore, this embodiment performs random value processing on this part of the data and takes a random value between 0 and 5;

[0096] S203, outlier deletion: Draw a line chart for the data value of each feature, determine whether there are outliers that deviate far from the normal range in each feature, and delete the outliers;

[0097] S204, duplicate value processing: performing a deduplication operation on the same data in the first sample set;

[0098] S205. Urban road data processing: Remove data on non-walkable roads such as highways, expressways, viaducts, and tunnels. Use ArcGIS software to construct a road network buffer and vectorize the road network centerline to construct a single-line road network. Perform a topological check on the road data to correct double-line overlap and pseudo-node errors.

[0099] S206 , sorting to obtain a second sample data set: sorting the preprocessed first sample data set and visualizing it in ArcGIS to obtain a second sample data set.

[0100] Furthermore, step S206 specifically includes:

[0101] S20601. Use the "Add XY Data" tool in ArcGIS software to export the community health service center coordinate data, urban road data, building unit data, point of interest / area of ​​interest data, and mobile phone signaling data. Set the X field to "lon" and the Y field to "lat". Export the data to a Shapefile and visualize it in ArcGIS software.

[0102] S20602. Use the "Create NetCDF Raster Layer" tool in ArcGIS software for the PM2.5 concentration data, set the X field to "lon" and the Y field to "lat", export the raster file, further define the raster file as WGS-1984 geographic coordinates, convert it to a TIFF file, and visualize it in ArcGIS software;

[0103] S20603. Visualize the TIFF files of Normalized Difference Vegetation Index (NDVI) data and night light data in ArcGIS software.

[0104] S30. Calculate the community health service center site selection related indicators based on the second sample data set, and normalize the related indicators to obtain a third sample data set, wherein the related indicators include one or more of the following indicators: population density index, population structure index, general hospital accessibility index, public transportation convenience index, subway convenience index, residential area accessibility index, building density index, floor area ratio index, night light index index, normalized vegetation index index, surrounding functional density index, surrounding functional diversity index, general hospital index and residential area index.

[0105] In this embodiment, step S30 specifically includes:

[0106] S301, using the "Feature to Point" tool in ArcGIS software to convert the building unit surface data into the geometric center point data of the building unit surface;

[0107] S302. Use the service area analysis tool in the "Network Analysis" toolbar of ArcGIS software to construct a network dataset using urban road data. Assign a walking speed of 60 m / min to the community health service center as a supporting facility within the 15-minute community living circle. Use the 15-minute walking distance of the community health service center as its service radius. Construct a 900 m service area around the geometric center of each building unit in the target area as the 15-minute walking service area based on the road network data. Calculate the area of ​​the 900 m service area around the geometric center of each building unit.

[0108] Furthermore, step S302 specifically includes:

[0109] S30201. Create a new feature dataset in ArcGIS software, and import the processed urban road data in the second sample dataset into the new feature dataset;

[0110] S30202. Create a new network dataset in the feature dataset and set the value of the cost attribute to the "Shape_Length" field;

[0111] S30203. Use the Service Area Analysis tool on the Network Analysis toolbar, set the facility point to the geometric center point of each building unit in the target area, set the impedance in the analysis settings to Length (meters), set the cutoff value to 900, set the Multiple Facility option to Overlay, and run the solution to obtain a 900-meter service area around the geometric center point of each building unit in the target area.

[0112] S303. Create a 100m*100m grid for the target area based on the population raster data. Use the "Display Zonal Statistics as Table" tool in ArcGIS to obtain a population table for each grid and connect the grids to obtain a grid layer containing population information. Use the "Spatial Join" tool in ArcGIS to calculate the total population of the grids within the 900m service area and divide it by the area of ​​the 900m service area to obtain the population density, which is used as the population density indicator within the 900m service area.

[0113] S304. Calculate the ratio of the number of residents to the number of working people, the proportion of the juvenile population, and the proportion of the elderly population within each grid cell based on the mobile phone signaling data. Use the "Spatial Join" tool in ArcGIS to calculate the average ratio of the number of residents to the number of working people, the proportion of the juvenile population, and the proportion of the elderly population for the grid cells within the 900-meter service area, and use this as the population structure indicator within the 900-meter service area.

[0114] S305. Based on the point of interest data, the closest facility tool of the ArcGIS "Network Analysis" tool is used to construct a network dataset using the urban road data. All points of interest of general hospitals in the target area are used as facility points, and the geometric center points of all building units in the target area are used as event points. The distance from the geometric center point of each building unit to the nearest general hospital is calculated as the general hospital accessibility index.

[0115] S306. Based on the point of interest data, use the closest facility tool in the ArcGIS "Network Analysis" tool to construct a network dataset using the urban road data. All bus stops in the target area are used as facility points, and the geometric center points of all building units in the target area are used as event points. The distance from the geometric center point of each building unit to the nearest bus stop is calculated as the public transportation convenience index.

[0116] S307. Based on the point of interest data, the closest facility tool of the ArcGIS "Network Analysis" tool is used to construct a network dataset using the urban road data. All subway stations in the target area are used as facility points, and the geometric center points of all building units in the target area are used as event points. The distance from the geometric center point of each building unit to the nearest subway station is calculated as the subway convenience index.

[0117] S308. Based on the point of interest data, use the OD cost matrix tool of the "Network Analysis" tool in ArcGIS to construct a network dataset using the urban road data. Take the geometric center points of all building units in the target area as the starting point and all residential areas in the target area as the destination point. Set the cutoff value to 900m. Calculate the sum of the distances from the geometric center point of each building unit to all residential areas within the 900m service area, and divide it by the number of residential areas within the 900m service area to obtain the residential area accessibility index.

[0118] S309. Use the "Buffer Analysis" tool in ArcGIS software to construct a 300m buffer zone around the geometric center of each building unit;

[0119] S310. Based on the building unit data, use the "Spatial Join" tool of ArcGIS to calculate the total ground floor area of ​​all building units within a 300-meter buffer zone of the geometric center of each building unit, and divide it by the area of ​​the 300-meter buffer zone to obtain the building density as the building density indicator;

[0120] S311. Based on the building unit data, add a "Building Area" field to the attribute table, calculate the product of the ground floor area and the number of floors of each building unit to obtain the building area of ​​each building unit, use the "Spatial Join" tool in ArcGIS to calculate the total building area of ​​all building units within a 300-meter buffer zone of the geometric center of each building unit, and divide this sum by the area of ​​the 300-meter buffer zone to obtain the floor area ratio, which is used as the floor area ratio indicator;

[0121] S312. Create a 100m*100m grid for the target area based on the nighttime light data. Use the ArcGIS "Display Zonal Statistics as Table" tool to obtain a nighttime light index table for each grid and connect it to the grids to obtain a grid layer containing nighttime light index information. Use the ArcGIS "Spatial Join" tool to calculate the average nighttime light index of the grids within the 900m service area as the nighttime light index indicator.

[0122] S313. Based on the Normalized Difference Vegetation Index (NDVI) data, create a 30m*30m grid in the target area. Use the "Display Zonal Statistics as Table" tool in ArcGIS to obtain a table of NDVI data for each grid and connect it to the grid to obtain a grid layer containing NDVI data information. Use the "Spatial Join" tool in ArcGIS to calculate the average NDVI data of the grids within the 900m service area of ​​the geometric center of each building unit as the NDVI indicator.

[0123] S314. Based on the POI data, use the “Spatial Join” tool of ArcGIS to count the number of all POIs of each type within the 900m service area of ​​the geometric center of each building unit as the peripheral functional density indicator;

[0124] S315. Create a 200m*200m grid within the target area based on the POI data. Use the "Generate Neighbor Table" tool in ArcGIS to search for POI data within a 900m buffer zone of the grid. Export the POI neighbor table to Excel and calculate the POI mixing degree (FD) around each grid. The calculation formula is:

[0125] ,

[0126] Where FD is the POI mixing degree around each grid, For type i The proportion of points of interest in all points of interest, m is the number of POI types;

[0127] The “Spatial Join” tool of ArcGIS was used to calculate the average POI mixing degree in the grid within the 900m service area of ​​the geometric center of each building unit as an indicator of surrounding functional diversity;

[0128] S316. Based on the point of interest data, use the "Spatial Join" tool of ArcGIS to count the number of general hospital points of interest within the 900m service area of ​​the geometric center of each building unit as the general hospital index;

[0129] S317. Based on the point of interest data, use the "Spatial Join" tool of ArcGIS to count the number of residential area points of interest within the 900m service area of ​​the geometric center point of each building unit as the residential area index;

[0130] S318. Summarize and organize the above indicators. The indicator system table is shown in Table 1.

[0131]

[0132] S319. Normalize the above indicators and calculate them as follows:

[0133] ,

[0134] Where, X is the original data, For normalized data, and are the maximum and minimum values ​​in the original data, respectively.

[0135] S320. Based on the open source data on the Internet, the target value of the geometric center point of the building unit where the community health service center is located is assigned to 1, and the target values ​​of the geometric center points of other building units are assigned to 0, as the target value data of the community health service center characteristics.

[0136] S321. Summarize and organize the above data to obtain a third sample data set, and divide the third sample data set into a characteristic value data set and a target value data set, wherein the characteristic value data set includes population density, ratio of resident population to working population, proportion of children and adolescents, proportion of elderly population, accessibility of general hospitals, convenience of public transportation, convenience of subway, accessibility of residential areas, distance to walkable roads, floor area ratio, building density, night light index, PM2.5 concentration, normalized difference vegetation index data, surrounding functional density, surrounding functional diversity (POI mixing degree), number of general hospitals in the service area, and number of residential communities in the service area, represented by the letter X, and ; The target value data set includes the target value data of the community health service center characteristics, represented by the letter y.

[0137] S40. A fourth sample data set is obtained by sampling according to the target values ​​of the samples in the third sample data set. Based on the fourth sample data set, an optimal machine learning algorithm is used to construct a preliminary model for the site selection of community health service centers. Grid search is used for parameter tuning, and the optimal parameter combination is output through K-fold cross validation to obtain a preliminary model for the site selection of community health service centers.

[0138] In this embodiment, step S40 specifically includes:

[0139] S401. Import the third sample data set into an Excel spreadsheet. Since the number of building units where community health service centers are located in the target area is significantly smaller than the number of other building units, to avoid data set imbalance, oversample the samples with a target value of 1 in the third sample data set, and undersample the samples with a target value of 0.

[0140] Furthermore, step S401 specifically includes:

[0141] S40101. Duplicate 50 samples with a target value of 1, so that the number of the original 24 samples with a target value of 1 is expanded to 1200 as oversampling samples.

[0142] S40102. For all samples with a target value of 0, use Excel's RAND function to generate random numbers in a new column, and use Excel's sort function to sort the random numbers. Select the first 2,400 samples as under-sampling samples according to the ratio of 1:2 between the number of samples with a target value of 1 and 0.

[0143] S40103. Arrange samples with target values ​​of 1 and 0 to generate a fourth sample data set.

[0144] S402: Use the sklearn library in Python and call the model_selection module to use 80% of the fourth sample data set as a training set and 20% as a test set.

[0145] S403. Use five machine learning algorithms, including LightGBM, XGBoost, CatBoost, NGBoost, and random forest, to build and test the model, and select the optimal machine learning algorithm with the best R-squared (goodness of fit) and RMSE (root mean square error) to build a preliminary model for the site selection of community health service centers.

[0146] Furthermore, step S403 specifically includes:

[0147] S40301. Use the LightGBM library in Python and call the LGBMRegressor method to build a LightGBM regression model. The model parameters are as follows:

[0148] params_LightGBM{learning_rate, boosting_type, objective, metric, num_leaves, verbose, seed, n_jobs, feature_fraction, bagging_fraction, bagging_freq}

[0149] Among them, learning_rate represents the learning rate, boosting_type represents the boosting method, objective represents the loss function, metric represents the evaluation index, num_leaves represents the number of leaf nodes in each decision tree, seed represents the random seed, feature_fraction represents the subsampling of features, bagging_fraction and bagging_freq are used to use the bagging method.

[0150] In this example, a set of initial parameters for the LightGBM algorithm are defined:

[0151] params_lgb = {learning_rate: 0.02, boosting_type: gbdt, objective:mse, metric: rmse, num_leaves: 127, verbose: -1,seed: 42, n_jobs: -1,feature_fraction: 0.8, bagging_fraction: 0.9, bagging_freq: 4}

[0152] The MSE (mean square error) of the model built by the LightGBM algorithm is 0.09825647850032115, the RMSE (root mean square error) is 0.3134588944348543, the MAE (mean absolute error) is 0.24379498997769858, and the R-squared (goodness of fit) is 0.9051377686179084.

[0153] S40302. Use the XGBoost library in Python and call the XGBRegressor method to build an XGBoost regression model. The model parameters are as follows:

[0154] params_XGBoost{learning_rate, booster, objective, max_leaves, verbosity, seed, nthread, colsample_bytree, subsample, early_stopping_rounds, eval_metric}

[0155] Among them, learning_rate represents the learning rate, booster represents the boosting method, objective represents the loss function, max_leaves represents the number of leaf nodes in each decision tree, verbosity is used to control the level of detail of the output information, seed represents the random seed, nthread represents the number of threads for parallel computing, colsample_bytree represents the proportion of randomly selected features for each decision tree, subsample represents the proportion of randomly selected samples in each iteration, and eval_metric represents the evaluation metric.

[0156] In this embodiment, a set of XGBoost algorithm initial parameters are defined:

[0157] params_XGBoost={learning_rate: 0.02, booster: gbtree, objective: reg:squarederror, max_leaves: 127, verbosity: 1, seed: 42, nthread: -1, colsample_bytree: 0.6, subsample: 0.7, early_stopping_rounds: 100, eval_metric: rmse}

[0158] The model built by the XGBoost algorithm has an MSE (mean square error) of 0.14852525526041624, a RMSE (root mean square error) of 0.385389744622786, a MAE (mean absolute error) of 0.3201391679162975, and an R-squared (goodness of fit) of 0.8566055150190248.

[0159] S40303. Use the sklearn library in Python and call the RandomForestRegressor method to build a random forest regression model. The model parameters are as follows:

[0160] params_RandomForest{n_estimators, max_depth, max_features, min_samples_leaf, random_state}

[0161] Among them, n_estimators represents the number of decision trees, max_depth represents the maximum depth of the decision tree, max_features represents the number of features to be considered for optimal segmentation, min_samples_leaf represents the minimum number of samples at the leaf node, and random_state represents the random seed.

[0162] In this embodiment, a set of initial parameters of the random forest algorithm is defined:

[0163] params_RandomForest={n_estimators=1000, max_depth=8, max_features=10, min_samples_leaf=7, random_state=42}

[0164] The model constructed by the random forest algorithm has an MSE (mean square error) of 0.03637238490928531, an RMSE (root mean square error) of 0.19071545534980983, a MAE (mean absolute error) of 0.1369673173794692, and an R-squared (goodness of fit) of 0.8420415687901608.

[0165] S40304. Use the NGBoost library in Python and call the NGBRegressor method to build an NGBoost regression model. The model parameters are as follows:

[0166] params_ngb{learning_rate, n_estimator, verbose, random_state, natural_gradient}

[0167] Among them, learning_rate represents the learning rate, n_estimator represents the number of decision trees, verbose is used to control the level of detail of the output information, random_state represents the random seed, and natural_gradient represents the use of the natural gradient method.

[0168] In this embodiment, a set of initial parameters of the NGBoost algorithm are defined:

[0169] params_ngb = {learning_rate: 0.02, n_estimators: 1000, verbose: False, random_state: 42, natural_gradient: True}

[0170] The model built by the NGBoost algorithm has an MSE (mean square error) of 0.09544001627059343, a RMSE (root mean square error) of 0.3089336761678685, a MAE (mean absolute error) of 0.2235466115673266, and an R-squared (goodness of fit) of 0.9078569368172296.

[0171] S40305. Use the catboost library in Python and call the CatboostRegressor method to build a CatBoost regression model. The model parameters are as follows:

[0172] params_Catboost{learning_rate, iterations, depth, eval_metric,random_seed, verbose}

[0173] Among them, learning_rate represents the learning rate, iterations represents the number of decision trees, depth represents the depth of the decision tree, eval_metric represents the evaluation metric, random_seed represents the random seed, and verbose is used to control the level of detail of the output information.

[0174] In this embodiment, a set of CatBoost algorithm initial parameters are defined:

[0175] params_Catboost={learning_rate: 0.02, iterations: 1000, depth: 8, eval_metric: RMSE, random_seed: 42, verbose: 500}

[0176] The MSE (mean square error) of the model built by the CatBoost algorithm is 0.0302320406812082, the RMSE (root mean square error) is 0.17387363423247412, the MAE (mean absolute error) is 0.09504162218148243, and the R-squared (goodness of fit) is 0.9508123181084268.

[0177] S40306. The R-squared (goodness of fit) and RMSE (root mean square error) of the models constructed by the above five machine learning algorithms are shown in Table 2.

[0178]

[0179] According to the R-squared (goodness of fit) and RMSE (root mean square error) of the above five machine learning algorithms, the CatBoost algorithm with the best R-squared (goodness of fit) and RMSE (root mean square error) was selected to construct the community health service center location selection model.

[0180] S404, use the CatBoost model built in step S40305 as the community health service center site selection initialization model, define the parameter grid of the grid search, respectively optimize the learning_rate, depth and iterations parameters in the CatBoost model, use the 5-fold cross-validation method to find the parameter values corresponding to the model with the highest score in the cross-validation, form the best parameter combination, and obtain the community health service center site selection preliminary model trained under the best parameter combination.

[0181] Further, step S404 specifically comprises:

[0182] S40401, define the parameter grid of the grid search as follows:

[0183] param_grid {learning_rate: [0.01, 0.02, 0.05, 0.1], depth: [4, 6, 8, 10, 12], iterations: [800, 1000, 1200, 1400, 1600, 2000]}

[0184] S40402, use the sklearn library in Python to call the GridSearchCV method in the model_selection module for grid search and K-fold cross-validation, and the GridSearchCV method parameters are as follows:

[0185] GridSearchCV (estimator = model, param_grid = param_grid, scoring = neg_root_mean_squared_error, cv = 5, n_jobs = -1, verbose = 1)

[0186] Among them, scoring = neg_root_mean_squared_error means taking the negative value of RMSE (root mean square error) as the evaluation index, and cv = 5 means performing 5-fold cross-validation.

[0187] S40403. Substitute the eigenvalue dataset X and target value dataset y from the training set into the CatBoost regression model for training. Using a 5-fold cross-validation method, divide the eigenvalue dataset X and target value dataset from the training set into five subsets. In each validation run, four of these subsets are used to train the model, and the remaining subset is used to test the model. This validation process is repeated five times, with a different subset selected as the test set each time. Each parameter combination in the parameter grid is evaluated using the 5-fold cross-validation method, and the optimal parameter combination is output. A preliminary model for community health service center site selection based on the optimal parameter combination is obtained.

[0188] In this example, the optimal parameter combination is {depth:10, iterations:2000, learning_rate:0.02}. Under this parameter combination, the best RMSE in the 5-fold cross validation is 0.08446205914955598.

[0189] S50. Evaluate the preliminary model for site selection of community health service centers, calculate the contribution of relevant indicators in the preliminary model for site selection of community health service centers, and use Monte Carlo simulation to optimize feature selection and combination to obtain the optimal feature combination of the preliminary model for site selection of community health service centers.

[0190] In this embodiment, step S50 specifically includes:

[0191] S501. Call the metrics module in the sklearn library and substitute the test set into the preliminary model for community health service center site selection obtained in S40 for model evaluation. The R-squared (goodness of fit) of the preliminary model is evaluated as a comparison benchmark value for Monte Carlo simulation optimization feature selection and combination.

[0192] In this example, the R-squared (goodness of fit) of the preliminary model for site selection of community health service centers is 0.9606862717050595.

[0193] S502. Call shap (a method for explaining model prediction results based on Shapley value theory) to calculate the shap value of each feature in the test set and explain the contribution of each feature to the community health service center location selection model. The contribution (shap value) of each feature in the preliminary model for community health service center location selection is as follows: Figure 2 shown.

[0194] S503. Based on the contribution (shap value) of each feature, call the abs module in the numpy library to calculate the average absolute shap value of each feature, obtain the feature label, call the argsort module in the numpy library to sort the average absolute shap values ​​of each feature and correspond them to the feature label, re-sort the eigenvalue dataset X according to the model feature contribution, and obtain a new eigenvalue dataset X'.

[0195] S504. Call the cross_val_score of the model_selection module in the sklearn library to perform Monte Carlo simulation and cross validation on the new feature value dataset X' and the target value dataset y. Set the number of Monte Carlo simulations to 20 and define the cv_scores variable to record the cross validation scores.

[0196] S505. Use the optimal parameter combination obtained in step S405 to set the model for Monte Carlo simulation. In each simulation, the data set is re-divided to achieve the purpose of random sampling, effectively dealing with the uncertainty in the data. In each simulation, the number of features is gradually increased from large to small according to the feature contribution, and cross-validation is performed. The number of cross-validation iterations cv is set to 5, the evaluation effect scoring is 'r2' (goodness of fit), and the average cross-validation score is calculated.

[0197] S506. Draw a line graph of the cross-validation scores of the model under different feature combinations, such as Figure 3 As shown, the number and name of the features that performed best in the Monte Carlo simulation were obtained.

[0198] In this example, the best-performing features are 17: accessibility to general hospitals, distance to walkable roads, accessibility to residential areas, number of residential communities, floor area ratio, public transportation accessibility, proportion of elderly people, public transportation accessibility, number of general hospitals, ratio of resident to working population, population density, nighttime light index, PM2.5 concentration, proportion of children and adolescents, surrounding functional density, surrounding functional diversity, and NDVI (Normalized Difference Vegetation Index). The cv_score (measured by goodness of fit (R-squared)) for this optimal feature combination is 0.9677246949050842.

[0199] S60. Based on the optimal feature combination, the optimal machine learning algorithm is used to construct a community health service center site selection model, the parameters of the community health service center site selection model are tuned, and the optimal parameter combination is output through K-fold cross-validation to obtain the community health service center site selection model under the optimal feature combination and optimal parameter combination training.

[0200] In this embodiment, step S60 specifically includes:

[0201] S601. Use the best feature combination obtained in step S50 to filter the feature values ​​in the fourth sample data set, and filter out 17 features in the combination as a new feature value data set X_2. The target value data set is the target value data including the community health service center features, represented by the letter y.

[0202] S602. Use the preliminary model parameter combination of the community health service center as the initialization CatBoost model, define the parameter grid of the grid search, tune the learning_rate, depth, and iterations parameters in the CatBoost model respectively, use the 5-fold cross-validation method to find the parameter values ​​corresponding to the model with the highest score in the cross-validation, form the optimal parameter combination, and obtain the community health service center site selection model under the optimal parameter combination training.

[0203] Furthermore, step S602 specifically includes:

[0204] S60201. Define the grid search parameters as follows:

[0205] param_grid{learning_rate:[0.01,0.02,0.05,0.1],depth:[4,6,8,10,12],iterations:[800,1000,1200,1400,1600,2000]}

[0206] S60202. Use the sklearn library in Python and call the GridSearchCV method in the model_selection module to perform grid search and K-fold cross validation. The parameters of the GridSearchCV method are as follows:

[0207] GridSearchCV(estimator=model, param_grid=param_grid, scoring=neg_root_mean_squared_error, cv=5, n_jobs=-1, verbose=1)

[0208] Among them, scoring=neg_root_mean_squared_error means that the negative value of RMSE (root mean square error) is used as the evaluation indicator, and cv=5 means 5-fold cross validation.

[0209] S60203. Substitute the eigenvalue dataset X_2 and target value dataset y in the training set into the CatBoost regression model for training. Use the 5-fold cross-validation method to evaluate each parameter combination in the parameter grid, output the optimal parameter combination, and obtain the community health service center site selection model under the optimal feature combination and optimal parameter combination training.

[0210] In this example, the optimal parameter combination is {depth:10, iterations:2000, learning_rate:0.05}. Under this parameter combination, the best RMSE in the 5-fold cross validation is 0.08292214473600664.

[0211] S70, evaluating the obtained community health service center site selection model, and calculating the contribution of relevant indicators in the community health service center site selection model;

[0212] In this embodiment, step S70 specifically includes:

[0213] S701: Call the metrics module in the sklearn library, substitute the test set into the community health service center location selection model obtained in step S60 to perform model evaluation, and calculate the output evaluation indicators as follows:

[0214] MSE (mean square error), RMSE (root mean square error), MAE (mean absolute error), R-squared (goodness of fit)

[0215] In this example, the MSE (mean square error) of the community health service center location selection model is 0.004625254626564098, the RMSE (root mean square error) is 0.07800922456964274, the MAE (mean absolute error) is 0.02818615846819666, and the R-squared (goodness of fit) is 0.9699133885066853, which proves the accuracy of the CatBoost model in predicting the location of community health service centers.

[0216] S702: Call shap (a model prediction result interpretation method based on Shapley value theory) to calculate the shap value of each feature in the test set and interpret the contribution of each feature in the preliminary model.

[0217] The contribution of each feature in the site selection model of community health service centers is shown in the figure below: Figure 4 As shown in the figure, we can see that the ten characteristics of accessibility to general hospitals, distance to walkable roads, accessibility to residential areas, number of residential communities, proportion of elderly population, floor area ratio, subway convenience, bus convenience, population density, and number of general hospitals have the greatest contribution.

[0218] S80. Export and save the community health service center site selection model, input the eigenvalue dataset in the third sample dataset in the target area into the community health service center site selection model, obtain alternative site selection points for the community health service center, determine the number of community health service centers to be added based on the population size of the target area, and use the maximum coverage model to determine a set of community health service center site selection points that can cover the most demand points among the alternative site selection points for the community health service center.

[0219] In this embodiment, step S80 specifically includes:

[0220] S801. Call the joblib library to save the community health service center site selection model and export it to a pkl format file.

[0221] S802: Input the feature value dataset in the third sample dataset in the target area into the model to obtain a predicted target value result. Connect the predicted target value result table to the building unit geometric center point data in ArcGIS and visualize it.

[0222] In this embodiment, the predicted target value results range is [-0.176866, 1.003224]. Building units with predicted target values ​​greater than 0.2 are selected as candidate sites for community health service centers.

[0223] S803. Based on the permanent population data for Yuexiu District, Guangzhou, which has a population of 960,000, and one community health service center for every 30,000 people, 32 community health service centers are required. Based on a 15-minute walking distance, a community health service center service radius of 900 meters is set. Given the known number and radius of community health service centers, use the maximum coverage model to determine the set of community health service center locations that covers the greatest number of demand points.

[0224] The maximum coverage model is used to determine a set of community health service center site selection points that can cover the most demand points among the community health service center site selection candidate points. The maximum coverage model is expressed as:

[0225] ,

[0226] The constraint formula of the maximum coverage model is:

[0227] ,

[0228] ,

[0229] ,

[0230] In the formula, max S is the sum of the covered demand points, iFor the demand point, the residential area is taken as the demand point, j For the community health service center site selection candidate point, For whether the demand point is covered, For the candidate point set capable of covering the demand point i , m For the number of candidate points, M For the number limit of community health service center site selection points, For whether the candidate point is taken as the site selection point.

[0231] The purpose of the maximum coverage model is to maximize the covered demand points and max S. Using the "location matching" tool in the "network analysis" tool bar of ArcGIS, taking the community health service center site selection candidate point as the facility point, and taking the existing community health service center as the required item, taking the residential area in the target area as the demand point, and taking the road data as the line data, setting the impedance as 900m, the number of facility points as 32, running the solution to generate the community health service center site selection point set capable of covering the most demand points, as shown in Figure 5 .

[0232] Through the community health service center site selection method in the high-density urban environment in the embodiment, the site selection accuracy of the health service center can be effectively improved, and the coverage rate of the health service can be improved.

[0233] Embodiment 2

[0234] As another aspect of the embodiments of the present disclosure, a community health service center site selection system 100 in a high-density urban environment is also provided, as shown in Figure 6 , comprising:

[0235] A data acquisition module 1 acquires network open source data, population quantity raster data, mobile phone signaling data, point of interest / surface of interest data, night light data, building unit data, normalized vegetation index data, PM2.5 concentration data and urban road data of a target area in a high-density urban environment, to constitute a first sample data set;

[0236] A second sample set acquisition module 2 corrects the data in the first sample data set to obtain a second sample data set;

[0237] Related indicator processing module 3 calculates community health service center site selection related indicators based on the second sample data set, and normalizes the related indicators to obtain a third sample data set, wherein the related indicators include one or more of the following indicators: population density index, population structure index, general hospital accessibility index, public transportation convenience index, subway convenience index, residential area accessibility index, building density index, floor area ratio index, night light index, normalized vegetation index, surrounding functional density index, surrounding functional diversity index, general hospital index, and residential area index;

[0238] A preliminary model construction module 4 for community health service center site selection is configured to obtain a fourth sample data set based on the target values ​​of the samples in the third sample data set, and to construct a preliminary model for community health service center site selection based on the fourth sample data set using an optimal machine learning algorithm. Grid search is used for parameter tuning, and the optimal parameter combination is output through K-fold cross-validation to obtain a preliminary model for community health service center site selection.

[0239] Optimizing feature selection and combination module 5, evaluating the preliminary model for site selection of community health service centers, calculating the contribution of relevant indicators in the preliminary model for site selection of community health service centers, optimizing feature selection and combination using Monte Carlo simulation, and obtaining the optimal feature combination for the preliminary model for site selection of community health service centers;

[0240] A community health service center site selection model construction module 6 is configured to construct a community health service center site selection model based on the optimal feature combination using the optimal machine learning algorithm, perform parameter tuning on the community health service center site selection model, and output the optimal parameter combination through K-fold cross-validation to obtain a community health service center site selection model trained with the optimal feature combination and the optimal parameter combination;

[0241] Model evaluation module 7, evaluating the obtained community health service center location selection model and calculating the contribution of relevant indicators in the community health service center location selection model;

[0242] A site selection point set determination module 8 exports and saves a community health service center site selection model, inputs the characteristic value dataset in the third sample dataset in the target area into the community health service center site selection model, obtains candidate site selection points for community health service centers, determines the number of community health service centers to be added based on the population size of the target area, and uses a maximum coverage model to determine a set of community health service center site selection points that can cover the most demand points among the candidate site selection points for community health service centers;

[0243] In the absence of any contradiction, the above modules in the system of the embodiment of the present disclosure can implement any implementation of the above method.

[0244] Based on the description of the above embodiments, it can be seen that the embodiments of the present disclosure can achieve the following technical effects:

[0245] 1) This paper proposes a site selection method for community health service centers in high-density urban environments. It obtains multi-source data on five dimensions: population characteristics, accessibility, built environment, natural environment, and urban functions in the target area under high-density urban built environments. By performing multiple processing on the data, a fourth sample data set is obtained, and a systematic, objective and comprehensive characteristic indicator system is constructed for the community health service center site selection model based on machine learning.

[0246] 2) This paper uses five machine learning regression algorithms, LightGBM, XGBoost, CatBoost, NGBoost and random forest, to build and test the model, and obtains the optimal machine learning algorithm with the best R-squared (goodness of fit) and RMSE (root mean square error). It also uses network search for parameter tuning, and uses Monte Carlo simulation to optimize feature selection and combination based on the contribution of each feature obtained by calculating the shap value, and then obtains the community health service center site selection model. This process can effectively improve the accuracy of community health service center site selection.

[0247] 3) The present disclosure inputs the characteristic value data set in the third sample data set in the target area into the community health service center site selection model to obtain alternative site selection points for the community health service center, and uses the maximum coverage model to determine the set of community health service center site selection points that can cover the most demand points among the alternative site selection points for the community health service center. This process can ensure the coverage rate of community health services in the target area.

[0248] The present disclosure also provides an electronic device comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the aforementioned method for selecting a site for a community health service center in a high-density urban environment. The electronic device can be provided as a terminal, server, or other device.

[0249] The present disclosure also provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implements the above-mentioned method for selecting a site for a community health service center in a high-density urban environment. The computer-readable storage medium may be a non-volatile computer-readable storage medium.

[0250] Those skilled in the art will understand that in the specific implementation method and system for community health service center site selection in a high-density urban environment, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0251] The computer program product of the second aspect can include a computer readable storage medium. The computer readable storage medium can include instructions. The instructions can include one or both of: instructions for causing a computer to enable a user equipment device to receive a configuration message from a base station, the configuration message comprising an indication of a set of one or more parameters for a first type of hybrid automatic repeat request process, the first type of hybrid automatic repeat request process being associated with a first type of data; and instructions for causing a computer to enable a user equipment device to receive a configuration message from a base station, the configuration message comprising an indication of a set of one or more parameters for a first type of hybrid automatic repeat request process, the first type of hybrid automatic repeat request process being associated with a first type of data.

[0252] Embodiments of the present disclosure have been described above, with the understanding that these embodiments are exemplary only, and are not restrictive, in terms of the scope of the disclosure. Many modifications and variations of the described embodiments are possible, without departing from the scope and spirit of the described embodiments. The choice of words in the specification is intended to best explain the principles of the embodiments, practical application, or technical improvement in the art, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. The site selection method for community health service centers in high-density urban environments is characterized by: The steps include: S10, obtaining network open source data, population grid data, mobile phone signaling data, point of interest / area of ​​interest data, night light data, building unit data, normalized difference vegetation index data, PM2.5 concentration data, and urban road data of the target area in a high-density urban environment to form a first sample data set; S20: Arrange and correct the data in the first sample data set to obtain a second sample data set; S30. Calculate community health service center site selection-related indicators based on the second sample data set, and normalize the relevant indicators to obtain a third sample data set, where the relevant indicators include one or more of the following indicators: population density index, population structure index, general hospital accessibility index, public transportation convenience index, subway convenience index, residential area accessibility index, building density index, floor area ratio index, night light index, normalized vegetation index, surrounding functional density index, surrounding functional diversity index, general hospital index, and residential area index. S40. Sampling the target values ​​of the samples in the third sample data set to obtain a fourth sample data set, constructing a preliminary model for the site selection of a community health service center based on the fourth sample data set using an optimal machine learning algorithm, performing parameter tuning using grid search, and outputting an optimal parameter combination through K-fold cross-validation to obtain a preliminary model for the site selection of a community health service center; wherein, sampling the target values ​​of the samples in the third sample data set to obtain a fourth sample data set, constructing a preliminary model for the site selection of a community health service center based on the fourth sample data set using an optimal machine learning algorithm, comprises: Importing the third sample data set into the table, oversampling the samples with a target value of 1 in the third sample data set, undersampling the samples with a target value of 0, and sorting the samples with target values ​​of 1 and 0 to generate a fourth sample data set; 80% of the fourth sample data set is used as the training set and 20% as the test set; A variety of machine learning algorithms were used to conduct model construction tests, and the optimal machine learning algorithm with the best goodness of fit and root mean square error was determined based on the test results. The optimal machine learning algorithm was selected to construct a preliminary model for the site selection of community health service centers; S50, evaluating the preliminary model for site selection of the community health service center, calculating the contribution of relevant indicators in the preliminary model for site selection of the community health service center, and optimizing feature selection and combination using Monte Carlo simulation to obtain the optimal feature combination for the preliminary model for site selection of the community health service center; S60. Based on the optimal feature combination, the optimal machine learning algorithm is used to construct a community health service center site selection model, parameters of the community health service center site selection model are optimized, and the optimal parameter combination is output through K-fold cross validation to obtain the community health service center site selection model trained with the optimal feature combination and the optimal parameter combination; S70, evaluating the obtained community health service center site selection model, and calculating the contribution of relevant indicators in the community health service center site selection model; S80. Export and save the community health service center site selection model, input the eigenvalue dataset in the third sample dataset in the target area into the community health service center site selection model, obtain alternative site selection points for the community health service center, determine the number of community health service centers to be added based on the population size of the target area, and use the maximum coverage model to determine a set of community health service center site selection points that can cover the most demand points among the alternative site selection points for the community health service center.

2. The method according to claim 1, characterized in that Arranging and correcting the data in the first sample data set includes: A first sample data set is input, and mobile phone signaling data in the first sample data set is randomly assigned; a line chart is used to draw the data of each feature in the first sample data set to determine whether there are outliers in the data of each feature that deviate far from the normal range, and the outliers are deleted; duplicate operations are performed on the same data in the first sample set; and the urban road data in the first sample data set are checked and corrected.

3. The method according to claim 2, characterized in that The community health service center site selection related indicators calculated based on the second sample data set specifically include: Converting building unit surface data into geometric center point data of the building unit surface; According to the population grid data, the population in the grid is counted to obtain the population density index; According to the mobile phone signaling data, the user age structure distribution is counted to obtain the population structure index; Based on the data of points of interest / areas of interest, calculate the accessibility index of general hospitals, bus convenience index, subway convenience index and residential accessibility index; Calculate building density index and volume ratio index based on building unit data; Calculate the night light index based on the night light data; According to the normalized vegetation index data, a grid layer containing normalized vegetation index information is obtained, and the normalized vegetation index data index is calculated; Based on the data of points of interest / areas of interest, the surrounding functional density index, surrounding functional diversity index, comprehensive hospital index and residential community index are calculated.

4. The method according to any one of claims 1 or 3, characterized in that The relevant indicators are normalized to obtain a third sample data set, which is expressed as: ， Where, X is the original data, For normalized data, and are the maximum and minimum values ​​in the original data, respectively.

5. The method according to claim 1, wherein The maximum coverage model is used to determine a set of community health service center site selection points that can cover the most demand points among the community health service center site selection candidate points. The maximum coverage model is expressed as: ， The constraint formula of the maximum coverage model is: ， ， ， In the formula, max S is the sum of the covered demand points, i As demand points, take residential areas as demand points, j Select alternative sites for community health service centers, Whether the demand point is covered, To cover the demand points i The set of candidate points, m is the number of alternative points, M Limit the number of sites for community health service centers. Whether to use the alternative point as the site selection point.

6. The site selection system for community health service centers in high-density urban environments is characterized by: include: The data acquisition module acquires network open source data, population grid data, mobile phone signaling data, point of interest / area of ​​interest data, night light data, building unit data, normalized difference vegetation index data, PM2.5 concentration data, and urban road data of the target area in a high-density urban environment to form the first sample data set; A second sample set acquisition module, which organizes and corrects the data in the first sample set to obtain a second sample set; a related indicator processing module, which calculates community health service center site selection related indicators based on the second sample data set, and normalizes the related indicators to obtain a third sample data set, wherein the related indicators include one or more of the following indicators: population density index, population structure index, general hospital accessibility index, public transportation convenience index, subway convenience index, residential area accessibility index, building density index, floor area ratio index, night light index index, normalized vegetation index index, surrounding function density index, surrounding function diversity index, general hospital index, and residential area index; The module for constructing a preliminary model for site selection of a community health service center includes: sampling a fourth sample data set according to the target values ​​of the samples in the third sample data set; constructing a preliminary model for site selection of a community health service center based on the fourth sample data set using an optimal machine learning algorithm; performing parameter tuning using grid search; and outputting an optimal parameter combination through K-fold cross-validation to obtain a preliminary model for site selection of a community health service center; wherein, sampling a fourth sample data set according to the target values ​​of the samples in the third sample data set; and constructing a preliminary model for site selection of a community health service center based on the fourth sample data set using an optimal machine learning algorithm, including: Importing the third sample data set into the table, oversampling the samples with a target value of 1 in the third sample data set, undersampling the samples with a target value of 0, and sorting the samples with target values ​​of 1 and 0 to generate a fourth sample data set; 80% of the fourth sample data set is used as the training set and 20% as the test set; A variety of machine learning algorithms were used to conduct model construction tests, and the optimal machine learning algorithm with the best goodness of fit and root mean square error was determined based on the test results. The optimal machine learning algorithm was selected to construct a preliminary model for the site selection of community health service centers; Optimizing the feature selection and combination module, evaluating the preliminary model for site selection of community health service centers, calculating the contribution of relevant indicators in the preliminary model for site selection of community health service centers, and optimizing the feature selection and combination using Monte Carlo simulation to obtain the optimal feature combination for the preliminary model for site selection of community health service centers; A community health service center site selection model construction module, based on the optimal feature combination, uses the optimal machine learning algorithm to construct a community health service center site selection model, performs parameter tuning on the community health service center site selection model, and outputs the optimal parameter combination through K-fold cross-validation to obtain the community health service center site selection model under the optimal feature combination and optimal parameter combination training; A model evaluation module is used to evaluate the community health service center site selection model obtained above and calculate the contribution of relevant indicators in the community health service center site selection model; The site selection point set determination module exports and saves the community health service center site selection model, inputs the characteristic value data set in the third sample data set in the target area into the community health service center site selection model, obtains the community health service center site selection candidate points, determines the number of community health service centers to be added according to the population size of the target area, and uses the maximum coverage model to determine the community health service center site selection point set that can cover the most demand points among the community health service center site selection candidate points.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for selecting a site for a community health service center in a high-density urban environment as described in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for selecting a site for a community health service center in a high-density urban environment as described in any one of claims 1 to 5 is implemented.

Images