A Method and System for Site Selection and Planning of Public Service Sites

Abstract

This invention discloses a method for planning the site selection of public service stations, comprising: selecting a candidate public service station dataset from a dataset of residential units not yet covered by public services based on a greedy algorithm; and selecting a dataset of public service stations to be built from the candidate public service station dataset based on a clustering algorithm or a binary classification algorithm. This invention's method comprehensively considers factors such as the distribution of urban residential units, population distribution, and cost investment. It selects a candidate public service station dataset from residential units not yet covered by public services based on a greedy algorithm as alternative public service stations to be built. Then, it selects the final public service stations to be built from the alternative public service stations based on a clustering algorithm or a binary classification algorithm as the basis for construction. This allows for a more objective, scientific, and rational planning of public service station sites, reducing reliance on experience and subjectivity.

Description

Technical Field

[0001] This invention relates to the field of urban planning technology, and more specifically, to a method and system for site selection and planning of public service stations. Background Technology

[0002] Hospitals, schools, banks, large shopping malls, and even small nucleic acid sampling sites and virus sample collection sites provide a variety of public services to every resident in the surrounding area.

[0003] However, the distribution of existing urban public service stations in my country is uneven, and in particular, the cooperation and scheduling system among the stations is imperfect, which restricts mutual cooperation and makes it impossible to achieve a scientific, effective and rational allocation of urban public service stations.

[0004] Due to my country's vast territory and the significant differences in population and urban distribution density, there are substantial differences in the site selection and planning of public service stations in different regions, cities, and even different areas within the same city.

[0005] Therefore, the planning of urban public service stations in my country currently faces the following problems: the site selection criteria are too broad, which can only meet the most basic public service needs, and cannot achieve differentiated planning and design based on factors such as regional economy and population density, resulting in a strong subjectivity in the selection of urban public service station locations. Summary of the Invention

[0006] In response to at least one defect or improvement requirement in the prior art mentioned in the background section, the present invention provides a method and system for planning the site selection of public service sites, which can be used to plan the site selection of public service sites to be built in a more objective, scientific and rational way, and reduce the reliance on experience and subjectivity.

[0007] To achieve the above objectives, in a first aspect, the present invention provides a method for site selection and planning of public service stations, comprising:

[0008] Candidate public service site datasets are selected from residential unit datasets that have never been covered by public services based on a greedy algorithm;

[0009] The dataset of public service sites to be built is selected from the candidate public service site dataset based on clustering or binary classification algorithms.

[0010] Furthermore, the candidate public service site datasets selected from the residential unit dataset that has never been covered by public services based on a greedy algorithm include:

[0011] Based on the preset coverage distance of public services, obtain the coverage index of each residential unit in the dataset of residential units that are not covered by public services;

[0012] The residential units with the highest coverage index in this round are selected for elimination and placed in the candidate public service site dataset. The residential unit dataset covered by the residential unit with the highest coverage index in this round is also removed from the residential unit dataset that has never been covered by public services.

[0013] If it is determined that there is at least one residential unit in the residential unit dataset of uncovered public services after this round of elimination, then the next round of selection of the residential unit with the largest coverage index and elimination of the corresponding residential unit dataset will continue.

[0014] If it is determined that there are no residential units in the dataset of residential units without covered public services after one or more rounds of elimination, then the residential unit with the largest coverage index selected in each round is output as the candidate public service site dataset.

[0015] Furthermore, selecting the dataset of public service sites to be built from the candidate public service site dataset based on the clustering algorithm includes:

[0016] Randomly select a preset number of candidate public service sites from the candidate public service site dataset as initial cluster centers;

[0017] Cluster each site in the candidate public service site dataset, obtain the distance of each site in the candidate public service site dataset to each initial cluster center, and assign each site in the candidate public service site dataset to the corresponding class with its nearest initial cluster center;

[0018] For the above clustering results, the mean value of each distance sample in each class is taken as the new cluster center;

[0019] Determine whether the above iteration convergence meets the iteration conditions; if not, continue to randomly select a preset number of candidate public service sites from the candidate public service site dataset as the initial cluster centers; if yes, output the candidate public service site dataset.

[0020] Furthermore, selecting the dataset of public service sites to be built from the candidate public service site dataset based on the binary classification algorithm includes:

[0021] Obtain the pairwise distances between all candidate public service sites in the candidate public service site dataset;

[0022] Select the center point of the two candidate public service stations with the shortest distance as the new candidate public service station, and remove the two candidate public service stations with the shortest distance.

[0023] Determine whether the number of remaining candidate public service sites in the candidate public service site dataset is equal to the preset number of public service sites to be built; if not, continue to obtain the distance between each pair of all remaining candidate public service sites in the candidate public service site dataset; if yes, output the public service site dataset to be built.

[0024] Furthermore, the coverage index of residential units refers to:

[0025] The number of residential units in the residential unit dataset contained within a circle drawn with any residential unit in the residential unit dataset as the center and the preset coverage distance of the public service as the radius.

[0026] Furthermore, the methods for obtaining datasets of residential units not covered by public services include:

[0027] Based on the existing public service site dataset and the preset coverage distance of public services, obtain the residential unit dataset that covers public services that can be covered by the existing public service site dataset;

[0028] Remove the residential unit datasets that are covered by public services from the residential unit dataset to obtain the residential unit datasets that are not covered by public services.

[0029] To achieve the above objectives, in a second aspect, the present invention also provides a public service site selection and planning system, comprising:

[0030] The candidate public service site dataset acquisition module is used to select candidate public service site datasets from residential unit datasets that have never been covered by public services based on a greedy algorithm.

[0031] The module for acquiring datasets of public service sites to be built is used to select datasets of public service sites to be built from the candidate public service site datasets based on clustering algorithms or binary classification algorithms.

[0032] Furthermore, the candidate public service site dataset acquisition module includes:

[0033] The coverage index acquisition module is used to obtain the coverage index of each residential unit in the dataset of residential units that are not covered by public services, based on the preset coverage distance of public services.

[0034] The maximum coverage index selection module is used to select the residential units with the largest coverage index in this round, remove them and place them in the candidate public service site dataset, and remove the residential unit dataset covered by the residential unit with the largest coverage index in this round from the residential unit dataset that has never been covered by public services.

[0035] The first judgment module is used to determine if there is at least one residential unit in the residential unit dataset of uncovered public services after this round of elimination. If so, the next round of selection of the residential unit with the largest coverage index and elimination of the corresponding residential unit dataset will continue.

[0036] The second judgment module is used to determine if there are no residential units in the residential unit dataset of uncovered public services after one or more rounds of elimination. If so, it outputs the residential unit with the largest coverage index selected in each round as the candidate public service site dataset.

[0037] Furthermore, the public service site dataset acquisition module includes a first public service site dataset acquisition module;

[0038] The first public service site dataset acquisition module includes:

[0039] The initial cluster center acquisition module is used to randomly select a preset number of candidate public service sites from the candidate public service site dataset as initial cluster centers;

[0040] The clustering module is used to cluster each site in the candidate public service site dataset, obtain the distance of each site in the candidate public service site dataset to each initial cluster center, and assign each site in the candidate public service site dataset to the corresponding class with its nearest initial cluster center;

[0041] The new cluster center acquisition module is used to obtain the mean value of each distance sample in each class as the new cluster center for the above clustering results.

[0042] The third judgment module is used to determine whether the above iteration convergence meets the iteration conditions; if not, it continues to randomly select a preset number of candidate public service sites from the candidate public service site dataset as the initial cluster centers; if yes, it outputs the public service site dataset.

[0043] Furthermore, the public service site dataset acquisition module includes a second public service site dataset acquisition module;

[0044] The second public service site dataset acquisition module includes:

[0045] The site distance acquisition module is used to acquire the distance between each pair of all candidate public service sites in the candidate public service site dataset;

[0046] The new candidate public service site acquisition module is used to select the center point of the two candidate public service sites with the shortest distance as the new candidate public service site, and to remove the two candidate public service sites with the shortest distance.

[0047] The fourth judgment module is used to determine whether the number of remaining candidate public service sites in the candidate public service site dataset is equal to the preset number of public service sites to be built; if not, it continues to obtain the distance between each pair of all remaining candidate public service sites in the candidate public service site dataset; if yes, it outputs the public service site dataset to be built.

[0048] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects:

[0049] The public service site selection and planning method or system of the present invention comprehensively considers factors such as the distribution of urban residential units, population distribution, and cost investment. Based on a greedy algorithm, it selects a dataset of candidate public service sites from residential units that are not yet covered by public services as alternative public service sites to be built. Then, based on a clustering algorithm or a binary classification algorithm, it selects the final public service sites to be built from the above-mentioned alternative public service sites as the basis for construction. This enables more objective, scientific and rational planning of public service site selection, reducing reliance on experience and subjectivity. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A flowchart illustrating a public service site selection and planning method provided in an embodiment of the present invention;

[0052] Figure 2 A flowchart illustrating a method for planning the location of a virus sample collection site provided in an embodiment of the present invention;

[0053] Figure 3 A schematic diagram of the process for determining candidate virus sample sampling sites based on a greedy algorithm, provided in an embodiment of the present invention;

[0054] Figure 4 This is a schematic diagram illustrating the process of optimizing candidate virus sample sampling sites based on a clustering algorithm, as provided in an embodiment of the present invention.

[0055] Figure 5This is a schematic diagram illustrating the process of optimizing candidate virus sample sampling sites based on a binary classification algorithm, as provided in an embodiment of the present invention.

[0056] Figure 6 This is a schematic diagram of the system structure of a virus sample sampling site selection and planning system provided in an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0058] The terms "first," "second," or "third," etc., used in the specification, claims, or accompanying drawings of this application are used to distinguish different objects, not to describe a particular order. Furthermore, the terms "comprising" or "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0059] Hospitals, schools, banks, large supermarkets, and even small nucleic acid sampling sites and virus sample collection sites provide various public services to every resident in the surrounding area. The following example illustrates this with a virus sample collection site.

[0060] Urban public health emergencies pose enormous challenges to the national economy, people's lives and health. In order to effectively curb the spread of infectious diseases, virus samples need to be collected in a timely and efficient manner, and the rational planning and layout of virus sample collection sites directly affects the efficiency of virus sampling.

[0061] Overall, the distribution of virus sampling sites in my country's cities during outbreaks of infectious diseases is uneven. In particular, the coordination and scheduling system among the sampling sites is imperfect, and mutual cooperation is restricted, making it impossible to achieve a scientific, effective, and rational allocation of virus sampling sites. This makes it difficult to make timely and rational arrangements of virus sampling sites in the event of various public health emergencies.

[0062] Due to my country's vast territory and the significant differences in population and urban distribution density, there are substantial differences in the site selection and planning of virus sample collection sites in different regions, cities, and even different areas within the same city.

[0063] Currently, the planning of urban virus sampling sites in my country mainly faces the following problems: the site selection criteria are too broad, which can only meet the most basic sampling needs and cannot achieve differentiated planning and design based on factors such as regional economy and population density, resulting in a strong subjectivity in the selection of virus sampling site locations.

[0064] Therefore, establishing a mathematical analysis model that can comprehensively consider cost economy, population distribution, and building residential unit distribution is the key to achieving scientific and rational site selection for virus sample collection sites.

[0065] refer to Figure 1 and Figure 2 In one embodiment, a method for planning the location of virus sample collection sites for configurable public health emergencies may include several steps, S101-S104.

[0066] S101: Determine the latitude and longitude information of the residential buildings through the map interface based on the building names.

[0067] First, the list of residential buildings in the city's administrative district is obtained from the third-party big data management platform via API. Then, the names of the residential buildings are obtained from the list. Finally, the specific geographical location (i.e., latitude and longitude information) of the residential building is determined through the map interface to prepare for subsequent distance calculations.

[0068] S102: Based on the existing virus sample collection site configuration information, the walking time from the building to the site, and the residents' walking speed requirements, determine the list of residential buildings that can be covered by the existing virus sample collection sites. Remove the list of residential buildings that can be conveniently covered by the existing virus sample collection sites from the list of residential buildings in the selected planning administrative area (all residential buildings in the area). The remaining list represents the residential buildings that are not conveniently covered by the existing virus sample collection sites. These buildings are temporarily unable to conveniently enjoy virus sample collection services. The purpose of building new virus sample collection sites is to meet the virus sample collection needs of residents in these residential buildings.

[0069] The existing virus sample collection site configuration information reveals the specific geographical location (latitude and longitude) distribution of the existing virus sample collection sites. The walking time from the residential buildings to the sampling site is generally controlled within a preset time (e.g., within 15 minutes). Assuming that the average walking speed of residents is 100 meters per minute, the area that the virus sample collection site can conveniently cover is a circle with itself as the center and a radius of 1.5 kilometers. The residential buildings within this circle can be covered by the convenient sampling service of the virus sample collection site.

[0070] S103: Based on the list of residential buildings not covered by convenient sampling services, candidate virus sample sampling sites are determined using a greedy algorithm. (Reference) Figure 3 Specifically, it may include:

[0071] S201: Based on the list of residential buildings not covered by the convenient sampling service, the walking time from the building to the sampling site and the residents' walking speed requirements (the walking time from the building to the sampling site multiplied by the residents' walking speed is actually the distance that the sampling service can conveniently cover), calculate the coverage index of all residential buildings. That is, assuming that the residential building is a virus sample sampling site, calculate the number of residential buildings that can be covered by the residential building to meet the walking time and residents' walking speed requirements. In other words, calculate the number of residential buildings within the circle drawn with the residential building as the center and the distance that the sampling service can conveniently cover as the radius.

[0072] S202: Select the residential buildings with the highest coverage index in this round as candidate virus sample collection sites and remove them from the list of residential buildings. Also remove those residential buildings that the selected residential buildings can conveniently cover.

[0073] S203: Determine if all buildings in the community have been covered by the convenience service. If not, proceed to the next round of selecting the community building with the highest coverage index and removing the corresponding community buildings covered by the convenience service. If, after one or more rounds of removal, no more community buildings are covered by the convenience service, output the community building with the highest coverage index selected in each round as a candidate virus sample sampling site.

[0074] S104: Based on the candidate virus sampling sites, calculate the planned location of the new site using a clustering algorithm or a binary classification algorithm.

[0075] refer to Figure 4 The results of calculating the planned locations of new sites based on clustering algorithms specifically include:

[0076] S301: Randomly select K sites (K is the number of virus sample sampling sites to be rebuilt) from the candidate virus sample sampling sites selected in step S203 as the initial cluster centers.

[0077] S302: Cluster all candidate virus sample sampling sites, calculate the distance from each candidate virus sample sampling site to each cluster center, and assign the candidate virus sample sampling site to the cluster with the nearest cluster center.

[0078] S303: For the above clustering results, calculate the mean of each distance sample in the current class as the new cluster center.

[0079] S304: Determine whether the iteration convergence meets the iteration conditions. If not, proceed to step S301 again. If yes, end the process and output the specific information of the virus sample collection site to be built.

[0080] refer to Figure 5 The results of calculating the planned location of the new site based on the binary classification algorithm specifically include:

[0081] S401: Calculate the distance between each pair of sampling sites for all candidate virus samples.

[0082] S402: The center point of the two candidate virus sample sampling sites with the shortest distance becomes the new candidate virus sample sampling site, and the two candidate virus sample sampling sites are eliminated.

[0083] S403: Determine if the number of remaining candidate virus sample sampling sites is equal to the number of virus sample sampling sites to be newly established. If not, proceed to step S401 for filtering and elimination. If yes, end the process and output the specific information of the virus sample sampling sites to be established.

[0084] In another embodiment, a virus sample sampling site selection and planning system is provided, with reference to Figure 6 The system as a whole may include: a configuration prefabrication module, a configuration parsing module, a population and building data access module, a planning site calculation module, a planning site output module, a core algorithm module, a greedy algorithm module, a clustering algorithm module, and a binary classification algorithm module.

[0085] The configuration pre-built module generates corresponding configuration files based on the configuration information of existing virus sample sampling sites (mainly including site latitude and longitude information), walking time from residential buildings to sampling sites, residents' walking speed, and the number of newly built virus sample sampling sites.

[0086] The configuration parsing module is used to load pre-built configuration files, parse the configuration files, and instantiate the parsed configuration information into object structure variables.

[0087] The first end of the residential building data access module connects to a third-party big data management platform, obtaining a list of residential buildings in the selected planning administrative region via an API, and generating a residential building list information table. Data fields include building number and building name. The second end of the residential building data access module connects to the second end of the planning site calculation module, transmitting the residential building list information table to the planning site calculation module.

[0088] The first end of the planning site calculation module connects to the configuration parsing module to obtain the instantiated object structure variables of the configuration parsing module. The second end of the planning site calculation module connects to the second end of the community building data access module to obtain the community building list information table. The third end of the planning site calculation module connects to the core algorithm module and passes the instantiated object structure variables of the configuration parsing module and the community building list information table to the core algorithm module for calculation. The fourth end of the planning site calculation module connects to the planning site output module and passes the final calculation results to the planning site output module.

[0089] The site planning output module displays the calculation results obtained by the site planning calculation module and outputs a virus sample sampling site planning report.

[0090] The core algorithm modules of the above system include a greedy algorithm module, a clustering algorithm module, and a binary classification algorithm module. These three algorithm modules are the core modules of this system.

[0091] The greedy algorithm module, based on the location information of residential buildings, the walking time from the buildings to the sampling sites configured in the parsing module, and the walking speed parameters of residents, determines candidate virus sample sampling sites and transmits the calculation results to the planning site calculation module. This greedy algorithm module is the candidate virus sample sampling site acquisition module, used to select candidate virus sample sampling sites from residential buildings that are not conveniently covered by the greedy algorithm for sampling. The greedy algorithm module may also include:

[0092] The coverage index acquisition module is used to obtain the coverage index of buildings in communities that are not covered by convenient sampling of virus samples, based on a preset coverage distance for convenient sampling of virus samples (such as the 1.5 km convenient sampling distance mentioned above).

[0093] The maximum coverage index selection module is used to select the community buildings with the largest coverage index in this round for removal and place them in the candidate virus sample sampling sites. It also removes the community building set covered by the community building with the largest coverage index in this round from the community buildings that have never been covered by virus samples.

[0094] The first judgment module is used to determine if there is at least one building in the community building set that is convenient for sampling the uncovered virus samples after this round of elimination. If so, the next round of selection of the community building with the largest coverage index and elimination of the corresponding covered community building set will continue.

[0095] The second judgment module is used to determine whether there are no buildings in the community buildings that are convenient for sampling after one or more rounds of elimination of uncovered virus samples. If so, it outputs the community building with the largest coverage index selected in each round as the candidate virus sample sampling site.

[0096] The module for acquiring virus sample sampling sites to be built specifically includes a clustering algorithm module and a binary classification algorithm module. Based on the candidate virus sample sampling sites and the number of virus sample sampling sites to be newly built by the configuration parsing module, it determines the final site planning result and transmits the calculation result to the planning site calculation module.

[0097] The clustering algorithm module is the same as the module for acquiring the first virus sample sampling site to be built, and may specifically include:

[0098] The initial cluster center acquisition module is used to randomly select a preset number of sites from the candidate virus sample sampling sites as initial cluster centers.

[0099] The clustering module is used to cluster each site in the candidate virus sample sampling sites, obtain the distance of each site in the candidate virus sample sampling sites to each initial cluster center, and assign each site in the candidate virus sample sampling sites to the corresponding class with the nearest initial cluster center.

[0100] The new cluster center acquisition module is used to obtain the mean value of each distance sample in each class as the new cluster center for the above clustering results.

[0101] The third judgment module is used to determine whether the above iteration convergence meets the iteration conditions; if not, it continues to randomly select a preset number of sites from the candidate virus sample sampling sites as the initial cluster centers; if yes, it outputs the specific information of the virus sample sampling sites to be built.

[0102] The binary classification algorithm module is the module for acquiring the second virus sample collection site to be built, and it may specifically include:

[0103] The site distance acquisition module is used to obtain the distance between all pairs of sites in the candidate virus sample sampling sites.

[0104] The new candidate virus sample sampling site acquisition module is used to select the center point of the two candidate virus sample sampling sites with the shortest distance as the new candidate virus sample sampling site, and to remove the two candidate virus sample sampling sites with the shortest distance.

[0105] The fourth judgment module is used to determine whether the number of remaining candidate virus sample sampling sites in the candidate virus sample sampling site set is equal to the preset number of virus sample sampling sites to be built; if not, it continues to obtain the distance between each pair of all remaining sites in the candidate virus sample sampling site set and performs selection and elimination operations; if yes, it outputs the specific information of the virus sample sampling sites to be built.

[0106] The configuration information of the existing virus sample collection sites in the above system includes site number, site name, site location, site longitude, and site latitude; the walking parameters from the community building to the site, the residents' walking speed, and the number of newly built sites include parameter item number, parameter item name, parameter value, parameter unit, and parameter remarks.

[0107] Table 1 shows the parameters of walking time from residential buildings to the stations, residents' walking speed, and the number of newly built stations.

[0108] Table 1 Basic Condition Parameters Table

[0109]

[0110] The public service site selection and planning method or system of the present invention comprehensively considers factors such as the distribution of urban residential units, population distribution, and cost investment. Based on a greedy algorithm, it selects a dataset of candidate public service sites from residential units that are not yet covered by public services as alternative public service sites to be built. Then, based on a clustering algorithm or a binary classification algorithm, it selects the final public service sites to be built from the above-mentioned alternative public service sites as the basis for construction. This enables more objective, scientific and rational planning of public service site selection, reducing reliance on experience and subjectivity.

[0111] It should be noted that the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product.

[0112] The flowcharts or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. Furthermore, it should be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0113] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure, and all such combinations and / or combinations fall within the scope of this disclosure.

[0114] Although this disclosure has been shown and described with reference to specific exemplary embodiments thereof, those skilled in the art will understand that various changes in form and detail may be made to this disclosure without departing from the spirit and scope of the disclosure as defined by the appended claims and their equivalents. Therefore, the scope of this disclosure should not be limited to the above embodiments, but should be defined not only by the appended claims, but also by their equivalents.

Claims

1. A public service site siting planning method characterized by, The method comprises the following steps: selecting a candidate public service site dataset from the residential unit dataset not covered by the public service based on a greedy algorithm; selecting a to-be-built public service site dataset from the candidate public service site dataset based on a clustering algorithm or a binary classification algorithm; selecting a candidate public service site dataset from the residential unit dataset not covered by the public service based on a greedy algorithm comprises the following steps: obtaining a coverage index of each residential unit in the residential unit dataset not covered by the public service based on a preset coverage distance of the public service; selecting a residential unit with the largest coverage index in this round for elimination and placing it in the candidate public service site dataset, and eliminating the residential unit dataset covered by the residential unit with the largest coverage index in this round from the residential unit dataset not covered by the public service; if there is at least one residential unit in the residential unit dataset not covered by the public service after elimination in this round, the next round of selection of the residential unit with the largest coverage index and elimination of the corresponding residential unit dataset are continued; if there is no residential unit in the residential unit dataset not covered by the public service after one or more rounds of elimination, the residential unit with the largest coverage index selected in each round is output as the candidate public service site dataset; selecting a to-be-built public service site dataset from the candidate public service site dataset based on a clustering algorithm comprises the following steps: randomly selecting a preset number of candidate public service sites in the candidate public service site dataset as initial clustering centers; clustering each site in the candidate public service site dataset to obtain the distance of each site in the candidate public service site dataset to each initial clustering center, and assigning each site in the candidate public service site dataset to the class corresponding to the initial clustering center closest to it; for the clustering result, the mean of each distance sample in each class is obtained as a new clustering center; it is judged whether the iteration converges according to the iteration condition; if not, a preset number of candidate public service sites in the candidate public service site dataset are randomly selected as initial clustering centers; if yes, the to-be-built public service site dataset is output; selecting a to-be-built public service site dataset from the candidate public service site dataset based on a binary classification algorithm comprises the following steps: obtaining the distance between each pair of candidate public service sites in the candidate public service site dataset; selecting the center point of the two candidate public service sites with the shortest distance as a new candidate public service site, and eliminating the two candidate public service sites with the shortest distance; it is judged whether the number of remaining candidate public service sites in the candidate public service site dataset is equal to a preset number of to-be-built public service sites; if not, the distance between each pair of remaining candidate public service sites in the candidate public service site dataset is continuously obtained; if yes, the to-be-built public service site dataset is output.

2. The public service site siting planning method of claim 1, wherein, The coverage index of a residential unit is The number of residential unit data sets contained in a circle drawn with any residential unit in the residential unit data set as the center and the preset coverage distance of the public service as the radius.

3. The public service site siting planning method of claim 2, wherein, The obtaining method of the residential unit data set not covered by the public service includes: Based on the existing public service site data set and the preset coverage distance of the public service, the residential unit data set covered by the public service that can be covered by the existing public service site data set is obtained. The residential unit data set not covered by the public service is obtained by excluding the residential unit data set covered by the public service from the residential unit data set.

4. A public service site siting planning system characterized by, It includes: The candidate public service site data set obtaining module is configured to select the candidate public service site data set from the residential unit data set not covered by the public service based on the greedy algorithm. The to-be-built public service site data set obtaining module is configured to select the to-be-built public service site data set from the candidate public service site data set based on the clustering algorithm or the binary classification algorithm. The candidate public service site data set obtaining module includes: a coverage index obtaining module configured to obtain the coverage index of each residential unit in the residential unit data set not covered by the public service based on the preset coverage distance of the public service; a maximum coverage index selection module configured to select the residential unit with the maximum coverage index in this round, remove the residential unit from the residential unit data set not covered by the public service, and place the residential unit in the candidate public service site data set; a first judgment module configured to judge whether there is at least one residential unit in the residential unit data set not covered by the public service after the removal in this round, and if so, continue to select the residential unit with the maximum coverage index in the next round and remove the residential unit data set covered by the residential unit; and a second judgment module configured to judge whether there is no residential unit in the residential unit data set not covered by the public service after one or more rounds of removal, and if so, output the residential unit with the maximum coverage index selected in each round as the candidate public service site data set. The to-be-built public service station dataset obtaining module comprises a first to-be-built public service station dataset obtaining module; the first to-be-built public service station dataset obtaining module comprises: an initial clustering center obtaining module, configured to randomly select a preset number of to-be-built public service stations from the candidate public service station dataset as initial clustering centers; a clustering module, configured to cluster each station in the candidate public service station dataset, obtain distances from all stations in the candidate public service station dataset to each initial clustering center, and assign each station in the candidate public service station dataset to a class corresponding to the initial clustering center closest to the station; a new clustering center obtaining module, configured to obtain, for the clustering result, a mean of each distance sample in each class as a new clustering center; and a third judging module, configured to judge whether iteration convergence meets an iteration condition; if not, the initial clustering center is continuously selected from the candidate public service station dataset; and if yes, the to-be-built public service station dataset is output. The to-be-built public service station dataset obtaining module comprises a second to-be-built public service station dataset obtaining module; the second to-be-built public service station dataset obtaining module comprises: a station distance obtaining module, configured to obtain distances between all candidate public service stations in the candidate public service station dataset; a new candidate public service station obtaining module, configured to select a center point of two candidate public service stations with the shortest distance as a new candidate public service station, and remove the two candidate public service stations; and a fourth judging module, configured to judge whether a remaining number of candidate public service stations in the candidate public service station dataset is equal to a preset number of to-be-built public service stations; if not, distances between all remaining candidate public service stations in the candidate public service station dataset are continuously obtained; and if yes, the to-be-built public service station dataset is output.

Images