Housing site selection map generation method and device and computer readable medium

Abstract

The embodiment of the invention discloses a housing site selection map generation method and device and a computer readable medium. A specific embodiment of the method comprises the following steps: acquiring regional basic data of each housing demand point in a city map; performing data processing on the basic data of each region to obtain a preprocessed basic data set; a housing comprehensive score is determined according to each piece of preprocessed basic data, and a housing comprehensive score set is obtained; performing multi-objective optimization on each housing comprehensive score to obtain an optimized housing score set; determining the housing demand points meeting a preset condition as alternative housing site selection points, and obtaining an alternative housing site selection point set; and according to the coordinate of each alternative housing site selection point, performing image rendering on a map corresponding to the alternative housing site selection point to obtain a housing site selection map, and displaying the housing site selection map. The method can be used for generating the housing site selection map, and avoiding unreasonable housing planning, thereby reducing the waste of building resources.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the fields of computer science and urban planning, and in particular to a housing site selection map generation method, device, and computer-readable medium. Background Art

[0002] The generation of housing site selection maps is the process of determining housing construction locations and integrating them into maps. Before building housing (such as affordable housing and resettlement housing), site selection is crucial, and multiple factors such as land cost, transportation convenience, surrounding environment and facilities must be considered comprehensively. At present, when generating housing site selection maps, the usual method is to determine the appropriate housing address based on expert experience and generate the corresponding housing site selection map.

[0003] However, when the above method is used to generate a housing site selection map, the following technical problems often occur: First, the site selection of experts may be affected by subjective factors, resulting in low effectiveness of housing address selection and difficulty in generating accurate housing site selection maps, which in turn leads to unreasonable subsequent housing planning and waste of construction resources; Second, there are many different types of data involved in housing site selection. Directly using uncleaned data for housing site selection may lead to site selection errors, thereby reducing the accuracy of generating housing site selection maps and leading to a waste of construction resources.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose a housing site selection map generation method, device and computer-readable medium to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a method for generating a housing site selection map, the method comprising: obtaining a city map and dividing the city map into natural zones to generate natural zones, thereby obtaining a natural zone set, wherein the natural zones are areas divided by roads in the city as boundary lines; according to a pre-acquired residents' housing expectation table, each natural zone in the natural zone set that meets preset conditions is determined as a housing demand point, thereby obtaining a housing demand point set, wherein the coordinates of the housing demand points are the centroid coordinates of the corresponding natural zones; obtaining land cost data, traffic facility data, and regional facility data of the area where each housing demand point is located as regional basic data, thereby obtaining a regional basic data set, wherein the area is an area within a preset range around the housing demand point, and the land cost data includes Average housing price; performing data processing on each regional basic data in the above regional basic data set to obtain a preprocessed basic data set; determining the housing comprehensive score of each housing demand point according to each preprocessed basic data in the above preprocessed basic data set to obtain a housing comprehensive score set; performing multi-objective optimization on each housing comprehensive score in the above housing comprehensive score set to generate an optimized housing score to obtain an optimized housing score set; determining the housing demand point corresponding to each optimized housing score that meets the preset conditions in the above optimized housing score set as an alternative housing site point to obtain an alternative housing site point set; performing image rendering on the map corresponding to the alternative housing site point according to the coordinates of each alternative housing site point in the above alternative housing site point set to obtain a housing site map and displaying the above housing site map.

[0008] In a second aspect, some embodiments of the present disclosure provide a housing site selection map generation device, the device comprising: an acquisition and zoning unit, configured to acquire a city map and perform natural zoning on the city map to generate natural zoning, and obtain a natural zoning set, wherein the natural zoning is an area divided by roads in the city as boundary lines; a first determination unit, configured to determine each natural zoning in the natural zoning set that meets preset conditions as a housing demand point according to a pre-acquired resident housing expectation table, and obtain a housing demand point set, wherein the coordinates of the housing demand points are the centroid coordinates of the corresponding natural zoning; an acquisition unit, configured to acquire land cost data, traffic facility data, and regional facility data of the area where each housing demand point is located as regional basic data, and obtain a regional basic data set, wherein the area is an area within a preset range around the housing demand point, and the land cost data includes the average housing price; a data processing unit, configured to The method comprises the following steps: a first determining unit is configured to perform data processing on each regional basic data in the above-mentioned regional basic data set to obtain a preprocessed basic data set; a second determining unit is configured to determine the housing comprehensive score of each housing demand point according to each preprocessed basic data in the above-mentioned preprocessed basic data set to obtain a housing comprehensive score set; a multi-objective optimization unit is configured to perform multi-objective optimization on each housing comprehensive score in the above-mentioned housing comprehensive score set to generate an optimized housing score to obtain an optimized housing score set; a third determining unit is configured to determine the housing demand point corresponding to each optimized housing score that meets the preset conditions in the above-mentioned optimized housing score set as an alternative housing site point to obtain an alternative housing site point set; an image rendering and display unit is configured to perform image rendering on the map corresponding to the alternative housing site point according to the coordinates of each alternative housing site point in the above-mentioned alternative housing site point set to obtain a housing site map and display the above-mentioned housing site map.

[0009] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0010] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0011] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the housing site selection map generation method of some embodiments of the present disclosure, it is possible to avoid unreasonable subsequent housing planning and reduce the waste of construction resources. Specifically, the reason for the low accuracy of generating a housing site selection map is that the site selection of experts may be affected by subjective factors, resulting in low effectiveness of housing address selection, and it may be difficult to generate an accurate housing site selection map. Based on this, the housing site selection map generation method of some embodiments of the present disclosure first obtains a city map and divides the above city map into natural zones to generate natural zones, and obtains a natural zone set. Among them, the above-mentioned natural zone is an area divided by a road in the city as a boundary line. Then, according to the pre-acquired resident housing expectation table, each natural zone in the above-mentioned natural zone set that meets the preset conditions is determined as a housing demand point, and a housing demand point set is obtained. Among them, the coordinates of the above-mentioned housing demand point are the centroid coordinates of the corresponding natural zone. Afterwards, the land cost data, traffic facility data, and regional facility data of the area where each housing demand point is located are obtained as regional basic data to obtain a regional basic data set. Among them, the above-mentioned area is an area within a preset range around the housing demand point. The above-mentioned land cost data includes the average housing price. By obtaining sufficient basic data, the site selection deviation caused by lack of key information can be avoided. Secondly, each regional basic data in the above regional basic data set is processed to obtain a preprocessed basic data set. In this way, the inconsistency and redundancy of the data can be effectively eliminated and the availability of the data can be improved. Then, according to each preprocessed basic data in the above preprocessed basic data set, the housing comprehensive score of each housing demand point is determined to obtain a housing comprehensive score set. Thus, a quantifiable score is given to each housing demand point, which helps to screen out relatively high-quality site selection points, thereby improving the objectivity and effectiveness of site selection. Then, each housing comprehensive score in the above housing comprehensive score set is multi-objective optimized to generate an optimized housing score, and an optimized housing score set is obtained. By comprehensively considering the weights and influences of multiple factors, a balance can be achieved between different goals, avoiding excessive bias towards a single factor or interference from subjective factors. Then, the housing demand point corresponding to each optimized housing score in the above optimized housing score set that meets the preset conditions is determined as an alternative housing site selection point, and an alternative housing site selection point set is obtained. By deleting areas that do not meet the conditions or have low value, the pertinence and effectiveness of the site selection results can be effectively improved, the rationality of subsequent housing planning based on the site selection results can be improved, and the waste of construction resources can be reduced. Finally, according to the coordinates of each alternative housing site selection point in the above-mentioned alternative housing site selection point set, the map corresponding to the alternative housing site selection point is rendered to obtain a housing site selection map and display the above-mentioned housing site selection map. By presenting complex data information in a visual way, it is convenient for users to intuitively understand and analyze the spatial distribution and advantages of each site selection point. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0013] Figure 1 is a flow chart of some embodiments of a housing site selection map generation method according to the present disclosure; Figure 2 is an example diagram of a housing site selection map obtained according to some embodiments of the housing site selection map generation method disclosed herein; Figure 3 It is a structural schematic diagram of some embodiments of the housing site selection map generation device according to the present disclosure; Figure 4 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0014] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0015] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information. The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0019] Figure 1 The process 100 of some embodiments of the housing site selection map generation method according to the present disclosure is shown. The housing site selection map generation method comprises the following steps: Step 101, obtaining a city map and dividing the city map into natural partitions to generate natural partitions, thereby obtaining a natural partition set.

[0020] In some embodiments, the execution subject of the housing site selection map generation method may obtain a city map and divide the city map into natural zones to generate natural zones, thereby obtaining a natural zone set. The natural zones are regions divided by roads in the city as boundary lines.

[0021] In practice, compared to dividing the city map into grids of uniform size, dividing the city map into natural divisions according to roads is more in line with the actual scenario, which can better reflect the city’s transportation network and regional distribution.

[0022] Step 102, according to the pre-acquired residents' housing expectation table, each natural partition in the natural partition set that meets the preset conditions is determined as a housing demand point, and a housing demand point set is obtained.

[0023] In some embodiments, the execution subject may determine each natural partition in the natural partition set that meets preset conditions as a housing demand point based on a pre-acquired residents' housing expectation table, and obtain a housing demand point set. Among them, first, the residents' housing expectation table may be acquired in advance. Here, the residents' housing expectation table may contain information such as the ID number, expected residence point, number of family members, etc. of each resident who applies for housing. Afterwards, the natural partition in the natural partition set corresponding to the expected residence point of each resident in the residents' housing expectation table may be determined as a housing demand point, and a housing demand point set is obtained. Among them, the coordinates of the housing demand point are the centroid coordinates of the corresponding natural partition.

[0024] Step 103, obtaining land cost data, transportation facility data, and regional facility data of the area where each housing demand point is located as regional basic data to obtain a regional basic data set.

[0025] In some embodiments, the execution subject may obtain the land cost data, traffic facility data, and regional facility data of the area where each housing demand point is located as regional basic data to obtain a regional basic data set. The area is an area within a preset range around the housing demand point. For example, the area may be an area within a radius of 2 kilometers around each housing demand point. The land cost data includes the average housing price. The average housing price may be the average price of all housing in the area where the housing demand point is located. First, the Point of Interest (POI) data of the current city may be obtained, which records the type, name, and coordinates of each facility in the city. Secondly, the traffic facility data and regional facility data within a preset range around the coordinates of the housing demand point may be recorded based on the data of the facilities of interest. The traffic facility data may include but is not limited to at least one of the following: the number of bus stops, the average distance of bus stops, the number of subway stations, the average distance of subway stations, and the number of shared bicycles. The average distance of bus stops is the average distance between the housing demand point and each bus stop in the area where it is located, and the average distance of subway stations is the average distance between the housing demand point and each subway station in the area where it is located. The regional facility data may include but is not limited to at least one of the following: the number of facility types, the type of facility, the distance of the facility, etc. The number of facility types is the number of facility types covered by all facilities in the area where the housing demand point is located. The above-mentioned facility types may include hospitals, supermarkets, schools, etc. Finally, the above-mentioned land cost data, transportation facility data, and regional facility data are used as regional basic data to obtain a regional basic data set.

[0026] As an example, the above regional basic data may include the average housing price, number of bus stops, average distance of bus stops, number of subway stations, average distance of subway stations, number of shared bicycles, number of facility types, facility types, facility distances, etc. of the corresponding housing demand point. For example, the regional basic data of the first housing demand point may be: [2000 yuan, 2, 438 meters, 1, 983 meters, 230, 3 types, hospital, 1900 meters, school, 200 meters, park, 500 meters].

[0027] In practice, multiple factors such as land cost, transportation convenience, and regional facilities are taken into consideration as the basic data for housing site selection. This multi-dimensional data can improve the accuracy and rationality of site selection decisions.

[0028] Step 104 , performing data processing on each regional basic data in the regional basic data set to obtain a preprocessed basic data set.

[0029] In some embodiments, the execution entity may perform data processing on each regional basic data set in the regional basic data set to obtain a preprocessed basic data set.

[0030] In some optional implementations of some embodiments, the execution subject performs data processing on each regional basic data in the regional basic data set to obtain a preprocessed basic data set, which may include the following steps: The first step is to unify the format of each regional basic data in the above regional basic data set to generate unified regional basic data and obtain a unified regional basic data set. Among them, each regional basic data may have a different data format. First, the feature value of the non-numeric type can be converted to a numeric type through one-hot encoding. Then, all feature values ​​of the same feature of each regional basic data in the regional basic data set are unified into the same unit to obtain a unified regional basic data set.

[0031] For example, the facility types "hospital", "school", "park", etc. can be converted to "0", "1", "2". After that, the data unit of the average distance of the above subway stations can be unified into kilometers.

[0032] In the second step, data cleaning is performed on each unified regional basic data in the unified regional basic data set to generate cleaned regional basic data, thereby obtaining the cleaned regional basic data set.

[0033] Optionally, the execution subject performs data cleaning on each unified regional basic data in the unified regional basic data set to generate cleaned regional basic data, and obtaining the cleaned regional basic data set may include the following steps: In the first sub-step, missing values ​​are filled for each unified regional basic data in the above-mentioned unified regional basic data set to generate complete regional data and obtain a complete regional data set. Among them, first, missing values ​​can be marked for each unified regional basic data in the above-mentioned unified regional basic data set to generate regional basic data with missing marks, and obtain a regional basic data set with missing marks. Here, the regional basic data with missing marks includes regional basic data and corresponding missing marks. Among them, the above-mentioned missing marks can be an array composed of housing demand point serial numbers and feature serial numbers. For example, the missing mark can be the sixth feature of the second housing demand point (such as the number of shared bicycles). Secondly, the missing value filling algorithm can be used to fill the missing values ​​of each regional basic data with missing marks corresponding to the missing marks in the above-mentioned regional basic data set with missing marks to generate complete regional data and obtain a complete regional data set.

[0034] As an example, the missing value filling algorithm may include but is not limited to at least one of the following: mean interpolation, median interpolation, K nearest neighbor interpolation, etc.

[0035] The second sub-step is to perform outlier detection on each complete region data in the complete region data set to obtain a region data set containing anomaly marks, wherein one complete region data corresponds to one region data containing anomaly marks.

[0036] Optionally, the execution subject performs outlier detection on each complete region data in the complete region data set to obtain a region data set containing abnormality marks, which may include the following steps: Step 1: Perform the following steps on each complete regional data in the above complete regional data set to obtain a regional data density value set: Sub-step 1: taking the complete area data as the target complete area data, determining the data point distance from the target complete area data to each complete area data in the above complete area data set, and obtaining a data point distance set. First, the complete area data can be determined as a vector, and the dimension of the vector is the number of features corresponding to the complete area data. After that, the current complete area data can be determined as the target complete area data. Then, the Euclidean distance between the above target complete area data and other complete area data in the above complete area data set can be determined as the data point distance, and a data point distance set can be obtained.

[0037] Sub-step 2: The data point distances satisfying the preset conditions in the above data point distance set are taken as the neighborhood data point distances to obtain the neighborhood data point distance set. Among them, the preset number of data point distances corresponding to the shortest distance in the above data point distance set can be taken as the neighborhood data point distances to obtain the neighborhood data point distance set. Secondly, the neighborhood data point distance corresponding to the longest distance in the neighborhood data point distance set can be determined as the maximum neighbor distance of the target complete area data.

[0038] For example, the first five data point distances with the shortest corresponding distances in the above data point distance set can be used as the neighborhood data point distances to obtain the neighborhood data point distance set. Then, the neighborhood data point distance with the largest value in the neighborhood data point distance set is used as the maximum nearest neighbor distance.

[0039] Sub-step three, taking the complete area data corresponding to each neighborhood data point distance in the above neighborhood data point distance set as the neighborhood data point of the target complete area data, and obtaining the neighborhood data point set. The neighborhood data point set is a set of each complete area data in the above complete area data set whose data point distance with the target complete area data is less than the above maximum nearest neighbor distance.

[0040] Sub-step four, determine the neighborhood reachable distance between each neighborhood data point in the above-mentioned domain data point set and the target complete area data, and obtain a neighborhood reachable distance set. Among them, first, the neighborhood maximum neighbor distance corresponding to each neighborhood data point can be determined by the above-mentioned scheme for determining the maximum neighbor distance, and a neighborhood maximum neighbor distance set can be obtained. I will not go into details here. Afterwards, for each neighborhood data point, the maximum value between the data point distance between the neighborhood data point and the target complete area data and the neighborhood maximum neighbor distance is determined as the neighborhood reachable distance, and a neighborhood reachable distance set is obtained.

[0041] Sub-step 5: determining the inverse of the mean between each neighborhood reachable distance in the neighborhood reachable distance set as the target local density value of the target complete area data, wherein the target local density value represents the density between the target complete area data and the data points in the neighborhood.

[0042] In practice, the distance between data points is inversely proportional to the density. Therefore, the density between the target complete area data and the data points in the neighborhood is represented by the inverse of the average distance.

[0043] Sub-step six, determining the neighborhood local density value of each domain data point in the above domain data point set, and obtaining a neighborhood local density value set. Among them, the neighborhood local density value of each domain data point in the above domain data point set can be determined by the above scheme for determining the target local density value, and the neighborhood local density value set can be obtained. No further details will be given here.

[0044] Sub-step seven, determining the neighborhood density mean between each neighborhood local density value in the above neighborhood local density value set.

[0045] Sub-step eight: taking the ratio between the neighborhood density mean and the target local density value as the regional data density value to generate the regional data density value, wherein the regional data density value represents the relative density between the target complete regional data and the data points in the neighborhood.

[0046] In practice, the relative density between the target complete area data and the data points in the neighborhood is represented by the ratio between the neighborhood density mean and the target local density value. If the above ratio is less than or equal to 1, it indicates that the density of the target complete area data is higher or similar to the density of the data points in the neighborhood, and it is a normal point. If the above ratio is much greater than 1, it indicates that the target complete area data is an abnormal point.

[0047] Step 2: Determine each regional data density value in the regional data density value set that is greater than a preset threshold as a regional data outlier, and obtain a regional data outlier value set. The preset threshold may be a natural number greater than 1. For example, the preset threshold may be 1.5.

[0048] Step 3: According to the regional data abnormal value set, each complete regional data in the complete regional data set is abnormally marked to obtain a regional data set containing abnormal marks. The complete regional data corresponding to each regional data abnormal value in the regional data abnormal value set in the complete regional data set can be abnormally marked to obtain a regional data set containing abnormal marks.

[0049] In practice, the complete regional data corresponding to each housing demand point usually has many features and is unevenly distributed. Identifying outliers by comparing the density difference between the current complete regional data and its neighborhood data points is more suitable for high-dimensional data and unevenly distributed data sets. Therefore, the above outlier detection can better detect abnormal data in the complete regional data set and improve the effect of data cleaning in the housing site selection scenario.

[0050] The third sub-step is to perform data processing on each abnormally marked region data corresponding to the abnormal mark in the abnormally marked region data set to generate processed region data, and obtain the processed region data set. For each abnormally marked region data in the abnormally marked region data set, the mean of each neighborhood data point in the neighborhood data point set corresponding to the abnormally marked region data can be determined as the processed region data, and the processed region data set is obtained.

[0051] The fourth sub-step is to remove duplicate data from each processed regional data in the processed regional data set to obtain a deduplicated regional data set. The processed regional data in the processed regional data set that are the same as other processed regional data can be deleted to obtain a deduplicated regional data set.

[0052] In a fifth sub-step, the above-mentioned deduplicated regional data set is determined as the cleaned regional basic data set.

[0053] The first to fifth sub-steps and their related contents are an inventive point of an embodiment of the present disclosure, which solves the above-mentioned technical problem 2 "reducing the accuracy of generating housing site selection maps, thereby leading to waste of construction resources". The factors that lead to the above technical problems are often as follows: there are many different types of data involved in housing site selection, and directly using uncleaned data for housing site selection may lead to site selection errors. If the above factors are solved, the accuracy of generating housing site selection maps can be improved. In order to achieve this effect, first, the missing values ​​of the regional basic data are filled to obtain complete regional basic data. In this way, the integrity of the data can be guaranteed. Secondly, outlier detection is performed on the complete regional data set to obtain a regional data set containing abnormal marks. The relative density between the current complete regional data and each of its neighborhood data points reflects the abnormal degree of the current complete regional data, which can better identify unreasonable abnormal data. After that, the abnormal data is replaced with the mean of the neighborhood data in the neighborhood data point, which can reduce the impact of the abnormal data on the accuracy of subsequent housing site selection. Finally, the duplicate data in the regional data set is removed to obtain the cleaned regional basic data set. Therefore, the regional basic data after data cleaning can be used as the data set for subsequent housing site selection, which can improve the accuracy of housing site selection, thereby improving the accuracy of generating housing site selection maps and avoiding the waste of construction resources.

[0054] In the third step, each of the cleaned regional basic data in the above-mentioned cleaned regional basic data set is normalized to generate preprocessed basic data, thereby obtaining a preprocessed basic data set. In particular, each of the cleaned regional basic data in the above-mentioned cleaned regional basic data set can be normalized to generate preprocessed basic data, thereby obtaining a preprocessed basic data set, by using a preset normalization algorithm.

[0055] As an example, the normalization algorithm may include but is not limited to at least one of the following: standard deviation normalization (Z-Score Normalization), minimum and maximum normalization (Min-Max Normalization), and the like.

[0056] In practice, data processing techniques such as data cleaning, format conversion and data normalization are used to ensure data quality and consistency, which can improve data availability and the reliability of housing location models.

[0057] Step 105, determining the housing comprehensive score of each housing demand point according to each preprocessed basic data in the preprocessed basic data set, and obtaining a housing comprehensive score set.

[0058] In some embodiments, the execution subject may determine the housing comprehensive score of each housing demand point according to each preprocessed basic data in the preprocessed basic data set to obtain a housing comprehensive score set, wherein the housing comprehensive score may be used to characterize the residents' satisfaction at the corresponding housing demand point.

[0059] In some optional implementations of some embodiments, the execution subject determines the housing comprehensive score of each housing demand point according to each preprocessed basic data in the preprocessed basic data set to obtain the housing comprehensive score set, which may include the following steps: In the first step, for each preprocessed basic data in the above preprocessed basic data set, the following steps are performed to generate a housing comprehensive score, thereby obtaining a housing comprehensive score set: Sub-step 1: Input the pre-processed basic data into each trained decision sub-model to generate a decision score and obtain a decision score set. The above-mentioned decision sub-model is a component of the housing site selection model, and the above-mentioned housing site selection model includes a decision sub-model set and a decision combiner. Here, one decision sub-model corresponds to one decision score. The above-mentioned decision score can be used to represent the comprehensive score of the housing demand point corresponding to the above-mentioned pre-processed basic data.

[0060] Sub-step 2: input each decision score in the decision score set into the decision combiner to obtain a housing comprehensive score. The decision combiner may be used to determine the housing comprehensive score as the average value of each decision score in the decision score set.

[0061] Optionally, each decision sub-model in the above decision sub-model set is trained by the following steps: The first step is to obtain a sample training data set. The sample training data includes sample area basic data of sample housing and corresponding sample housing scores. First, each historical planned housing can be used as a sample housing to obtain a sample housing set. Secondly, the regional basic data of the area where each sample housing in the above sample housing set is located is used as the sample area basic data to obtain a sample area basic data set. Finally, the pre-acquired expert scores and questionnaire scores can be used as sample housing scores of historical planned housing.

[0062] The second step is to sample the sample training data set according to a preset number of times to generate a sample training data subset, and obtain a preset number of sample training data subsets. Among them, the sample training data set can be sampled according to a preset number of times by a preset sampling algorithm to generate a sample training sub-data set, and obtain a preset number of sample training sub-data sets. Here, the sampling algorithm can be a bootstrapping algorithm. Secondly, the preset number of times and the preset number are the same as the number of initial decision sub-models in the initial decision sub-model set.

[0063] The third step is to train each initial decision sub-model in the initial decision sub-model set by taking each sample area basic data corresponding to each sample training data subset in a preset number of sample training data subsets as the input of the initial decision sub-model, and taking each corresponding sample housing score as the output of the initial decision sub-model, to obtain the decision sub-model to generate the decision sub-model set. The initial decision sub-model can be a decision tree. Here, one sample training data subset corresponds to one initial decision sub-model.

[0064] In practice, updated historical planned residential data can be obtained regularly to obtain updated sample training data sets. After that, the above first step to third step and related steps are executed again to obtain an updated decision sub-model set. By training and verifying the continuously updated historical planned residential data, the accuracy of the decision scores output by the decision sub-model can be improved, thereby achieving more accurate housing site selection.

[0065] Step 106, performing multi-objective optimization on each housing comprehensive score in the housing comprehensive score set to generate an optimized housing score, thereby obtaining an optimized housing score set.

[0066] In some embodiments, the execution entity may perform multi-objective optimization on each housing comprehensive score in the housing comprehensive score set to generate an optimized housing score, thereby obtaining an optimized housing score set.

[0067] In some optional implementations of some embodiments, the execution subject performs multi-objective optimization on each housing comprehensive score in the housing comprehensive score set to generate an optimized housing score, and obtaining the optimized housing score set may include the following steps: The first step is to determine the expected resident value of each housing demand point in the housing demand point set according to the above-mentioned resident housing expectation table, and obtain the expected resident value set of the housing point. Among them, the expected resident value of each housing demand point in the housing demand point set can be determined according to the expected residence point and the number of family members in the above-mentioned resident expectation table, and obtain the expected resident value set of the housing point.

[0068] The second step is to cluster the housing demand points in the housing demand point set to obtain a cluster center point set. The housing demand points can be clustered according to the coordinates of the housing demand points in the housing demand point set using a preset clustering algorithm to obtain multiple cluster subsets and cluster center points of each cluster subset to generate a cluster center point set.

[0069] As an example, the clustering algorithm may include but is not limited to at least one of the following: Hierarchical Clustering, Fuzzy C-Means Clustering, and the like.

[0070] The third step is to determine the minimum distance value between each housing demand point in the housing demand point set and each cluster center point in the cluster center point set to obtain a minimum distance value set. Among them, the cluster center distance between the housing demand point and each cluster center point in the cluster center point set can be determined to obtain a cluster center distance set. Secondly, the cluster center distance with the smallest value in the above cluster center distance set can be used as the minimum distance value of the housing demand point.

[0071] Step 4: For each housing comprehensive score in the housing comprehensive score set, perform the following optimization steps to generate an optimized housing score, thereby obtaining an optimized housing score set: Sub-step 1, obtaining a multi-objective optimization function and determining the weight of the multi-objective optimization function. The output of the multi-objective optimization function is the weighted sum of the housing comprehensive score, the expected resident value of the housing point, the minimum distance value and the average housing price. Here, firstly, the initial weight of the multi-objective optimization function can be determined by the Analytic Hierarchy Process. Secondly, the initial weight can be corrected by the entropy weight coefficient method to obtain the weight of the multi-objective optimization function.

[0072] Sub-step 2: Input the comprehensive housing score into the above multi-objective optimization function to obtain the optimized housing score. The weighted sum of the comprehensive housing score of the housing demand point, the expected resident value of the housing point, the minimum distance value, the average housing price and the weight of the above multi-objective optimization function can be determined as the optimized housing score.

[0073] In practice, multiple objectives in the housing site selection process often conflict with each other and cannot be optimal at the same time. For example, the site selection point with a higher expected resident value of the housing point usually has a higher average housing price. Through the multi-objective optimization function, it is possible to find the best balance between different objectives and find the optimal housing site selection point that simultaneously satisfies the requirements of a higher housing comprehensive score, a larger expected resident value of the housing point, a smaller minimum distance value, and a lower average housing price.

[0074] Step 107, determining the housing demand point corresponding to each optimized housing score that meets the preset conditions in the optimized housing score set as an alternative housing site selection point, and obtaining a set of alternative housing site selection points.

[0075] In some embodiments, the above-mentioned execution entity may determine the housing demand point corresponding to each optimized housing score that meets the preset conditions in the above-mentioned optimized housing score set as an alternative housing site selection point, and obtain a set of alternative housing site selection points. Among them, each of the first preset number of optimized housing scores with the highest scores in the optimized housing score set may be used as an alternative housing site selection point to obtain a set of alternative housing site selection points. Here, the above-mentioned preset number may be 3, which is not specifically limited here. Secondly, each optimized housing score in the optimized housing score set that is greater than the preset score may also be used as an alternative housing site selection point to obtain a set of alternative housing site selection points. Here, the above-mentioned preset score may be 95 points, which is not specifically limited here.

[0076] Step 108, based on the coordinates of each candidate housing site point in the candidate housing site point set, image rendering is performed on the map corresponding to the candidate housing site point to obtain a housing site map and display the housing site map.

[0077] In some embodiments, the execution entity may render an image of a map corresponding to each alternative housing site point in the set of alternative housing site points according to the coordinates of each alternative housing site point, obtain a housing site map, and display the housing site map.

[0078] In some optional implementations of some embodiments, the execution subject performs image rendering on a map corresponding to the candidate housing site selection point according to the coordinates of each candidate housing site selection point in the candidate housing site selection point set to obtain a housing site selection map and displays the housing site selection map, which may include the following steps: The first step is to render the map corresponding to the alternative housing site point according to the coordinates of each alternative housing site point in the above-mentioned alternative housing site point set, so as to obtain a housing site map. Among them, the map corresponding to the alternative housing site point can be rendered by a Geographic Information System (GIS) according to the coordinates of each alternative housing site point in the above-mentioned alternative housing site point set, so as to obtain a housing site map. Here, the example of the above-mentioned housing site map can be as follows Figure 2 shown.

[0079] In practice, the spatial analysis capabilities of geographic information systems are combined to intuitively display the locations of alternative housing sites, facilitating user reference and implementation of building plans based on the site selection points.

[0080] The second step is to generate a housing site selection report text based on the regional basic data, housing comprehensive score, optimized comprehensive score and the housing site selection map corresponding to each alternative housing site selection point in the above-mentioned alternative housing site selection point set. The above-mentioned housing site selection report text is a text file composed of the above-mentioned housing site selection map and each alternative housing site selection point and its corresponding regional basic data, housing comprehensive score and optimized comprehensive score.

[0081] The third step is to transmit the housing site selection map and the housing site selection report text to a display device for display. The housing site selection map and the housing site selection report text may be transmitted to a local display device or a remote display device for display.

[0082] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the housing site selection map generation method of some embodiments of the present disclosure, it is possible to avoid unreasonable subsequent housing planning and reduce the waste of construction resources. Specifically, the reason for the low accuracy of generating a housing site selection map is that the site selection of experts may be affected by subjective factors, resulting in low effectiveness of housing address selection, and it may be difficult to generate an accurate housing site selection map. Based on this, the housing site selection map generation method of some embodiments of the present disclosure first obtains a city map and divides the above city map into natural zones to generate natural zones, and obtains a natural zone set. Among them, the above-mentioned natural zone is an area divided by a road in the city as a boundary line. Then, according to the pre-acquired resident housing expectation table, each natural zone in the above-mentioned natural zone set that meets the preset conditions is determined as a housing demand point, and a housing demand point set is obtained. Among them, the coordinates of the above-mentioned housing demand point are the centroid coordinates of the corresponding natural zone. Afterwards, the land cost data, traffic facility data, and regional facility data of the area where each housing demand point is located are obtained as regional basic data to obtain a regional basic data set. Among them, the above-mentioned area is an area within a preset range around the housing demand point. The above-mentioned land cost data includes the average housing price. By obtaining sufficient basic data, the site selection deviation caused by lack of key information can be avoided. Secondly, each regional basic data in the above regional basic data set is processed to obtain a preprocessed basic data set. In this way, the inconsistency and redundancy of the data can be effectively eliminated and the availability of the data can be improved. Then, according to each preprocessed basic data in the above preprocessed basic data set, the housing comprehensive score of each housing demand point is determined to obtain a housing comprehensive score set. Thus, a quantifiable score is given to each housing demand point, which helps to screen out relatively high-quality site selection points, thereby improving the objectivity and effectiveness of site selection. Then, each housing comprehensive score in the above housing comprehensive score set is multi-objective optimized to generate an optimized housing score, and an optimized housing score set is obtained. By comprehensively considering the weights and influences of multiple factors, a balance can be achieved between different goals, avoiding excessive bias towards a single factor or interference from subjective factors. Then, the housing demand point corresponding to each optimized housing score in the above optimized housing score set that meets the preset conditions is determined as an alternative housing site selection point, and an alternative housing site selection point set is obtained. By deleting areas that do not meet the conditions or have low value, the pertinence and effectiveness of the site selection results can be effectively improved, the rationality of subsequent housing planning based on the site selection results can be improved, and the waste of construction resources can be reduced. Finally, according to the coordinates of each alternative housing site selection point in the above-mentioned alternative housing site selection point set, the map corresponding to the alternative housing site selection point is rendered to obtain a housing site selection map and display the above-mentioned housing site selection map. By presenting complex data information in a visual way, it is convenient for users to intuitively understand and analyze the spatial distribution and advantages of each site selection point.

[0083] Further references Figure 3 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a housing site selection map generation device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0084] like Figure 3 As shown, the housing site selection map generating device 300 of some embodiments includes: an acquisition and zoning unit 301, a first determination unit 302, an acquisition unit 303, a data processing unit 304, a second determination unit 305, a multi-objective optimization unit 306, a third determination unit 307, and an image rendering and display unit 308. Among them, the acquisition and zoning unit 301 is configured to acquire a city map and perform natural zoning division on the above city map to generate natural zoning, and obtain a natural zoning set, wherein the above natural zoning is an area divided by roads in the city as boundary lines; the first determination unit 302 is configured to determine each natural zoning in the above natural zoning set that meets preset conditions as a housing demand point according to a pre-acquired resident housing expectation table, and obtain a housing demand point set, wherein the coordinates of the above housing demand points are the centroid coordinates of the corresponding natural zoning; the acquisition unit 303 is configured to acquire land cost data, traffic facility data, and regional facility data of the area where each housing demand point is located as regional basic data, and obtain a regional basic data set, wherein the above area is an area within a preset range around the housing demand point, and the above land cost data includes the average housing price; the data processing unit 304 is configured to process each housing demand point in the above regional basic data set. The first step is to process the regional basic data to obtain a preprocessed basic data set; the second determining unit 305 is configured to determine the housing comprehensive score of each housing demand point according to each preprocessed basic data in the above-mentioned preprocessed basic data set to obtain a housing comprehensive score set; the multi-objective optimization unit 306 is configured to perform multi-objective optimization on each housing comprehensive score in the above-mentioned housing comprehensive score set to generate an optimized housing score to obtain an optimized housing score set; the third determining unit 307 is configured to determine the housing demand point corresponding to each optimized housing score that meets the preset conditions in the above-mentioned optimized housing score set as an alternative housing site point to obtain an alternative housing site point set; the image rendering and display unit 308 is configured to perform image rendering on the map corresponding to the alternative housing site point according to the coordinates of each alternative housing site point in the above-mentioned alternative housing site point set to obtain a housing site map and display the above-mentioned housing site map.

[0085] It is understood that the units described in the device 300 are similar to those described in the reference Figure 1Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 300 and the units contained therein, and will not be described in detail here.

[0086] Reference below Figure 4 , which shows a structural schematic diagram of an electronic device (eg, a computing device) 400 suitable for implementing some embodiments of the present disclosure. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0087] like Figure 4 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory 402 or a program loaded from a storage device 408 to a random access memory 403. Various programs and data required for the operation of the electronic device 400 are also stored in the random access memory 403. The processing device 401, the read-only memory 402, and the random access memory 403 are connected to each other via a bus 404. An input / output interface 405 is also connected to the bus 404.

[0088] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 4 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0089] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the read-only memory 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0090] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0091] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0092] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently and not be installed in the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains a city map and divides the above-mentioned city map into natural zones to generate natural zones, and obtains a natural zone set, wherein the above-mentioned natural zones are areas divided by roads in the city as boundary lines; according to the pre-acquired residents' housing expectation table, each natural zone in the above-mentioned natural zone set that meets the preset conditions is determined as a housing demand point to obtain a housing demand point set, wherein the coordinates of the above-mentioned housing demand points are the centroid coordinates of the corresponding natural zones; obtains the land cost data, transportation facility data, and regional facility data of the area where each housing demand point is located as regional basic data to obtain a regional basic data set, wherein the above-mentioned area is the area within a preset range around the housing demand point, and the above-mentioned land cost data, transportation facility data, and regional facility data are obtained as regional basic data. The land cost data includes the average housing price; each regional basic data in the above regional basic data set is processed to obtain a preprocessed basic data set; the housing comprehensive score of each housing demand point is determined according to each preprocessed basic data in the above preprocessed basic data set to obtain a housing comprehensive score set; each housing comprehensive score in the above housing comprehensive score set is multi-objective optimized to generate an optimized housing score to obtain an optimized housing score set; the housing demand point corresponding to each optimized housing score in the above optimized housing score set that meets preset conditions is determined as an alternative housing site point to obtain an alternative housing site point set; according to the coordinates of each alternative housing site point in the above alternative housing site point set, the map corresponding to the alternative housing site point is rendered to obtain a housing site map and the above housing site map is displayed.

[0093] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0094] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0095] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition and partitioning unit, a first determination unit, an acquisition unit, a data processing unit, a second determination unit, a multi-objective optimization unit, a third determination unit, an image rendering and display unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the acquisition unit may also be described as a "unit for acquiring basic regional data".

[0096] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0097] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for generating a housing site selection map, comprising: Obtaining a city map and dividing the city map into natural zones to generate natural zones, thereby obtaining a natural zone set, wherein the natural zones are regions divided by using roads in the city as boundary lines; According to the pre-acquired residents' housing expectation table, each natural partition in the natural partition set that meets the preset conditions is determined as a housing demand point to obtain a housing demand point set, wherein the coordinates of the housing demand point are the centroid coordinates of the corresponding natural partition; Obtaining land cost data, transportation facility data, and regional facility data in the area where each housing demand point is located as regional basic data to obtain a regional basic data set, wherein the area is an area within a preset range around the housing demand point, and the land cost data includes an average housing price; Performing data processing on each regional basic data in the regional basic data set to obtain a preprocessed basic data set; Determine the housing comprehensive score of each housing demand point according to each preprocessed basic data in the preprocessed basic data set to obtain a housing comprehensive score set; Performing multi-objective optimization on each housing comprehensive score in the housing comprehensive score set to generate an optimized housing score, thereby obtaining an optimized housing score set; Determine the housing demand point corresponding to each optimized housing score that meets the preset conditions in the optimized housing score set as an alternative housing site selection point to obtain an alternative housing site selection point set; According to the coordinates of each alternative housing site point in the set of alternative housing site points, an image rendering is performed on the map corresponding to the alternative housing site point to obtain a housing site map and display the housing site map.

2. The method according to claim 1, wherein: The step of performing data processing on each regional basic data in the regional basic data set to obtain a preprocessed basic data set includes: Unifying the format of each regional basic data in the regional basic data set to generate unified regional basic data, thereby obtaining a unified regional basic data set; Performing data cleaning on each unified regional basic data set in the unified regional basic data set to generate cleaned regional basic data, thereby obtaining the cleaned regional basic data set; Each cleaned region basic data in the cleaned region basic data set is normalized to generate preprocessed basic data, thereby obtaining a preprocessed basic data set.

3. The method according to claim 1, wherein: The method of determining the housing comprehensive score of each housing demand point according to each preprocessed basic data in the preprocessed basic data set to obtain a housing comprehensive score set includes: For each preprocessed basic data in the preprocessed basic data set, the following steps are performed to generate a housing comprehensive score, thereby obtaining a housing comprehensive score set: Inputting the preprocessed basic data into each trained decision sub-model to generate a decision score, thereby obtaining a decision score set, wherein the decision sub-model is a component of a housing location selection model, and the housing location selection model includes a decision sub-model set and a decision combiner; Each decision score in the decision score set is input into the decision combiner to obtain a comprehensive housing score.

4. The method according to claim 3, wherein: Each decision sub-model in the decision sub-model set is trained by the following steps: Obtain a sample training data set, wherein the sample training data includes sample area basic data of sample housing and corresponding sample housing scores; Sampling the sample training data set according to a preset number of times to generate a sample training data subset, and obtaining a preset number of sample training data subsets; For each initial decision sub-model in the initial decision sub-model set, each sample area basic data corresponding to each sample training data subset in a preset number of sample training data subsets is used as the input of the initial decision sub-model, and each corresponding sample housing score is used as the output of the initial decision sub-model, and the decision sub-model is trained to generate a decision sub-model set.

5. The method according to claim 1, wherein: The multi-objective optimization is performed on each housing comprehensive score in the housing comprehensive score set to generate an optimized housing score, and the optimized housing score set is obtained, including: According to the resident housing expectation table, determining the housing point expected resident value corresponding to each housing demand point in the housing demand point set, and obtaining a housing point expected resident value set; Clustering each housing demand point in the housing demand point set to obtain a cluster center point set; Determine the minimum distance value between each housing demand point in the housing demand point set and each cluster center point in the cluster center point set to obtain a minimum distance value set; For each housing comprehensive score in the housing comprehensive score set, the following optimization steps are performed to generate an optimized housing score, thereby obtaining an optimized housing score set: Obtaining a multi-objective optimization function and determining a weight of the multi-objective optimization function, wherein the output of the multi-objective optimization function is a weighted sum of a housing comprehensive score, an expected resident value of a housing point, a minimum distance value, and an average housing price; The comprehensive housing score is input into the multi-objective optimization function to obtain the optimized housing score.

6. The method according to claim 1, wherein: The method of rendering an image of a map corresponding to the candidate housing site selection point according to the coordinates of each candidate housing site selection point in the candidate housing site selection point set, obtaining a housing site selection map, and displaying the housing site selection map comprises: According to the coordinates of each candidate housing site point in the candidate housing site point set, an image rendering is performed on a map corresponding to the candidate housing site point to obtain a housing site map; Generate a housing site selection report text according to the regional basic data corresponding to each candidate housing site selection point in the candidate housing site selection point set, the housing comprehensive score, the optimized comprehensive score and the housing site selection map; The housing site selection map and the housing site selection report text are transmitted to a display device for display.

7. A housing site selection map generation device, comprising: An acquisition and partition division unit is configured to acquire a city map and perform natural partition division on the city map to generate natural partitions, thereby obtaining a natural partition set, wherein the natural partition is an area divided by using roads in the city as boundary lines; A first determining unit is configured to determine, according to a pre-acquired residents' housing expectation table, each natural partition in the natural partition set that meets preset conditions as a housing demand point, thereby obtaining a housing demand point set, wherein the coordinates of the housing demand point are the centroid coordinates of the corresponding natural partition; An acquisition unit is configured to acquire land cost data, traffic facility data, and regional facility data of the area where each housing demand point is located as regional basic data to obtain a regional basic data set, wherein the area is an area within a preset range around the housing demand point, and the land cost data includes an average housing price; A data processing unit is configured to perform data processing on each regional basic data set in the regional basic data set to obtain a preprocessed basic data set; A second determination unit is configured to determine a housing comprehensive score for each housing demand point according to each preprocessed basic data in the preprocessed basic data set to obtain a housing comprehensive score set; A multi-objective optimization unit is configured to perform multi-objective optimization on each housing comprehensive score in the housing comprehensive score set to generate an optimized housing score, thereby obtaining an optimized housing score set; A third determining unit is configured to determine the housing demand point corresponding to each optimized housing score that meets the preset conditions in the optimized housing score set as an alternative housing site selection point to obtain an alternative housing site selection point set; The image rendering and display unit is configured to render an image of a map corresponding to each alternative housing site point in the set of alternative housing site points according to the coordinates of each alternative housing site point, obtain a housing site map, and display the housing site map.

8. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images