POI density index generation method and system and population spatial distribution simulation method

Abstract

The invention discloses a POI density index generation method and system and a population spatial distribution simulation method, and particularly relates to the technical field of population spatial distribution, and the technical key points are as follows: obtaining a scale correction coefficient of each POI energy level by utilizing POI attraction indexes for generating different energy levels and a pre-constructed energy level weight coefficient; and calculating the density index of each POI category by using the optimal bandwidth index of each POI category, the scale correction coefficient of each energy level corresponding to each POI category and the number of POIs. POI attraction is quantified by combining multiple pieces of online platform data, POI attraction indexes of different energy levels are obtained, a scale correction coefficient of each POI energy level is obtained by combining a constructed energy level weight coefficient, individual differences of POI points of interest are considered, loss of semantic details and peak smoothness of density indexes are avoided, and the POI attraction degree is improved. Meanwhile, density bandwidth testing is carried out on different types of POIs, and the optimal bandwidth index of each POI category is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of population spatial distribution, and in particular to a POI density index generation method and system, and a population spatial distribution simulation method. Background Art

[0002] Population spatialization simulates real population distribution data by allocating the statistical population of administrative units to regular grids. It is one of the effective means to obtain fine (high spatial resolution) and accurate population distribution data. Relevant institutions have conducted corresponding research and released data products, but the existing products are mainly concentrated at the global and national levels, and there are three problems: first, the resolution is still coarse (mostly kilometer-level products), which is difficult to support high-precision urban internal research and application; second, the influencing factors selected for simulation tend to be natural macro factors (such as temperature, precipitation, slope, etc.), and the daily activity characteristics of urban residents are weak; third, the simulation method is relatively simple (such as the GPW data set directly uses area weighting to estimate population density), without considering the relationship between indicator data, and it is difficult to reflect the complex changes in the local area.

[0003] Therefore, simulating high-precision population spatial distribution data at the city level requires solving two problems: one is the selection of multiple factors that can reflect the characteristics of citizen activities, and the other is the construction of scientific and reasonable data integration and simulation methods. From existing research, in addition to natural factors such as land cover data, night lights and POI data that affect the characteristics of citizen activities have been often used in recent years to reflect the vitality of the city's commercial economy. Their spatial resolution can reach the meter level, which can reflect the fine-grained characteristics of urban activities;

[0004] In addition, when considering the socioeconomic activity factors that affect the spatial distribution of the population, existing technologies often use the number or density indicators of POIs as independent variables in regression modeling, and homogenize the same type of POIs, ignoring the differences in individual scale and level, resulting in the loss of POI semantic details and causing deviations in population estimates between regions with different economic levels. Quantifying the scale and level of POIs of the same type plays a key role in the detailed description of population distribution.

[0005] Therefore, the present invention aims to provide a POI density index generation method, system and population spatial distribution simulation method to solve the above-mentioned related problems. Summary of the invention

[0006] The technical problem to be solved by the present invention is that the prior art ignores the differences in individual scale and energy level, resulting in the loss of POI semantic details and the related problems that the population estimation is biased between regions with different economic levels. The purpose is to provide a POI density index generation method, system and population spatial distribution simulation method. The POI attractiveness is quantified by combining multiple online platform data to obtain POI attractiveness indexes of different energy levels, and then the scale correction coefficient of each POI energy level is obtained by combining the constructed energy level weight coefficient to consider the individual differences of POI points of interest, avoid the loss of semantic details and the peak smoothing of density indicators, and at the same time, perform density bandwidth tests on different types of POIs to obtain the optimal bandwidth index of each POI category, and take into account the scale effect of POI to generate density indicators of different POI categories to assist in realizing accurate and objective population distribution simulation on a small scale.

[0007] The present invention is achieved through the following technical solutions:

[0008] A method for generating a POI density index, the method comprising:

[0009] Classifying the POIs based on the POI attributes to obtain a plurality of POI categories, wherein each POI category includes a plurality of POI energy levels;

[0010] The data from multiple online platforms are used to generate POI attractiveness indexes of different energy levels. The scale correction coefficient of each POI energy level is obtained through the POI attractiveness indexes of different energy levels and the pre-constructed energy level weight coefficients.

[0011] The optimal bandwidth index of each POI category is obtained, and the density index of each POI category is calculated using the optimal bandwidth index of each POI category, the scale correction coefficient of each energy level corresponding to each POI category, and the number of POIs.

[0012] Furthermore, the POI attractiveness index includes a POI online attractiveness index and a POI offline attractiveness index.

[0013] Furthermore, the data obtained from multiple online platforms are used to generate POI attractiveness indexes of different levels, specifically:

[0014] Obtaining first platform data and second platform data of different POI levels, and calculating the POI online attraction index of each POI level using the first platform data, and calculating the POI offline attraction index of each POI level using the second platform data;

[0015] The POI attraction index of each POI level is generated through the POI online attraction index and the POI offline attraction index of each POI level.

[0016] Furthermore, the scale correction coefficient of each POI energy level is obtained through the POI attractiveness index of different energy levels and the pre-constructed energy level weight coefficient, which is:

[0017] X i =a i ·δ i

[0018] Among them, X i represents the scale correction coefficient of the i-th POI energy level; a i represents the POI attractiveness index of the i-th POI level; δ i Represents the energy level weight coefficient of the i-th POI energy level, where i is a positive integer.

[0019] Furthermore, the density index of each POI category is calculated by using the optimal bandwidth index of each POI category, the scale correction coefficient of each energy level corresponding to each POI category, and the number of POIs, which is specifically:

[0020]

[0021] Among them, Z j represents the density index of the j-th POI category; n i represents the number of POIs of the i-th POI level in the j-th POI category; X i represents the scale correction coefficient of the i-th POI level in the j-th POI category; R j represents the optimal bandwidth index of the j-th POI category.

[0022] Furthermore, the method further includes: performing principal component analysis on all POI density indicators using a principal component analysis method to obtain a plurality of principal components of POI density indicators.

[0023] The present invention further provides a POI density index generation system, which is used in any one of the above-mentioned POI density index generation methods, and the system comprises:

[0024] The first module is used to classify POIs based on POI attributes to obtain multiple POI categories, wherein each POI category includes multiple POI energy levels;

[0025] The second module is used to generate POI attractiveness indexes of different energy levels using the data obtained from multiple online platforms, and obtain the scale correction coefficient of each POI energy level through the POI attractiveness indexes of different energy levels and the pre-constructed energy level weight coefficients;

[0026] The third module is used to obtain the optimal bandwidth index of each POI category, and calculate the density index of each POI category using the optimal bandwidth index of each POI category, the scale correction coefficient of each energy level corresponding to each POI category, and the number of POIs.

[0027] The present invention also provides a population spatial distribution simulation method, characterized in that the method comprises:

[0028] Based on the spatial distribution influencing factors, the population distribution influencing factors are selected, and the historical data corresponding to the population distribution influencing factors are obtained; wherein the population distribution influencing factors include the natural geographical environment influencing factors and the social and economic activity influencing factors;

[0029] The natural geographical environment influencing factors include topographic data, land cover data, vegetation index data and river network distance data; the topographic data include elevation and slope; the land cover data include the distance to the nearest construction land; the vegetation index data include NDVI data; the river network distance data include the nearest distance to the main river;

[0030] The social and economic activity influencing factors include traffic accessibility data, economic activity data and life convenience data; the traffic accessibility data includes subway station density, distance to the nearest subway station, bus station density, distance to the nearest bus station, municipal road density and distance to the nearest municipal road; economic activity data includes night light intensity index; life convenience data includes density indexes of multiple POI categories generated by any one of the POI density index generation methods described above;

[0031] Based on the population distribution influencing factors and the historical data corresponding to the population distribution influencing factors, the spatial distribution simulation of the population in the urban area is completed.

[0032] The present invention also provides a computer device, comprising a system memory and a processor, wherein the system memory stores a computer program, and the processor implements the steps of any one of the methods described above when executing the computer program.

[0033] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any one of the methods described above are implemented.

[0034] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0035] In the present invention, the attractiveness of POIs is quantified by combining data from multiple online platforms to obtain POI attractiveness indexes of different energy levels, and then the scale correction coefficient of each POI energy level is obtained in combination with the constructed energy level weight coefficient to take into account the individual differences of POI points of interest, avoid the loss of semantic details and the peak smoothing of density indicators, and at the same time, perform density bandwidth tests on different types of POIs to obtain the optimal bandwidth indicator for each POI category, and take into account the scale effect of POIs to generate density indicators of different POI categories, so as to assist in achieving accurate and objective population distribution simulation on a small scale. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0037] Figure 1 A schematic diagram of a method flow of a POI density index generating method in this embodiment;

[0038] Figure 2 This is a schematic diagram of module connections of a POI density index generating system in this embodiment;

[0039] Figure 3 It is a structural schematic diagram of a computer device in this embodiment. DETAILED DESCRIPTION

[0040] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0041] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0042] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0043] Example 1

[0044] See also Figure 1 As shown, this embodiment provides a method for generating a POI density index, the method comprising:

[0045] S1: Classify POIs (Point of Interest) based on POI attributes to obtain multiple POI categories, wherein each POI category includes multiple POI energy levels;

[0046] Specifically, in this embodiment, POIs are classified into ten POI categories based on POI attributes, wherein each POI category includes multiple POI energy levels, as shown in the following Table 1:

[0047] Table 1 POI category classification table

[0048]

[0049]

[0050] S2: Generate POI attractiveness indexes of different energy levels using the data obtained from multiple online platforms, and obtain the scale correction coefficient of each POI energy level through the POI attractiveness indexes of different energy levels and the pre-constructed energy level weight coefficients;

[0051] It should be noted that, in this embodiment, the POI attractiveness index includes a POI online attractiveness index and a POI offline attractiveness index.

[0052] Specifically, in this embodiment, the first platform data and the second platform data of different POI levels are obtained, and the POI online attraction index of each POI level is calculated using the first platform data, and the POI offline attraction index of each POI level is calculated using the second platform data;

[0053] It should be noted that, in this embodiment, the first platform data includes the average number of Weibo check-ins per hour on weekdays, the total number of Weibo check-ins per hour on weekdays of the POI level to which it belongs, the average number of Weibo check-ins per hour on weekends, and the total number of Weibo check-ins per hour on weekends of the POI level to which it belongs; the second platform data includes the average number of online ride-hailing orders per hour on weekdays, the total number of online ride-hailing orders per hour on weekdays of the POI level to which it belongs, the average number of online ride-hailing orders per hour on weekends, and the total number of online ride-hailing orders per hour on weekends of the POI level to which it belongs.

[0054] At the same time, it should be noted that Weibo check-in data is matched with place names and POI level names. Unmatched Weibo check-in data is parsed according to the place name address. If the obtained location longitude and latitude is within the 100-meter buffer zone of the POI, it is identified as a valid check-in record; online car-hailing order data is based on the terminal location. If the terminal location is within the 100-meter buffer zone of the POI, it is identified as a valid order.

[0055] The POI online attractiveness index of each POI level is calculated using the data from the first platform, specifically:

[0056]

[0057] The offline attraction index of each POI level is calculated using the data from the second platform, specifically:

[0058]

[0059] The POI attractiveness index of each POI level is generated through the POI online attractiveness index and the POI offline attractiveness index of each POI level, specifically:

[0060] Through the POI attractiveness index of different energy levels and the pre-constructed energy level weight coefficient, the scale correction coefficient of each POI energy level is obtained, specifically:

[0061] X i =a i ·δ i

[0062] Among them, X i represents the scale correction coefficient of the i-th POI energy level; a i represents the POI attractiveness index of the i-th POI level; δ i Represents the energy level weight coefficient of the i-th POI energy level, where i is a positive integer.

[0063] It should be noted that, in this embodiment, the pre-constructed energy level weight coefficients are shown in Table 2 below:

[0064] Table 2 POI energy level weight coefficient table

[0065]

[0066]

[0067] S3: Obtain an optimal bandwidth index for each POI category, and use the optimal bandwidth index for each POI category, as well as the scale correction coefficient of each energy level corresponding to each POI category and the number of POIs to calculate a density index for each POI category.

[0068] It should be noted that, in this embodiment, since the prior art often sets a fixed bandwidth based on common sense when performing density index analysis on POIs of different categories, a bandwidth that is too small will cause the kernel density function of the POI to be too sharp, and a bandwidth that is too large will cause the kernel density function of the POI to be too smooth. Both cannot reflect the real impact of POI facility density on population distribution and the differences in the impact of different types of POIs on population distribution. Determining the appropriate bandwidth for POI types is of great significance for population estimation at a fine spatial scale.

[0069] For POI kernel density measurement, the selection of bandwidth indicators is particularly critical, and the optimal bandwidths corresponding to different categories of facilities are different. In order to determine the optimal bandwidth for each type of POI, this technical solution follows the following steps: for each type of POI category, within the range of 100 to 5000m, with a step length of 100m, a total of 50 different bandwidth indicators are set, and the corresponding 50 density indicators are calculated in turn; then the average kernel density corresponding to each township unit in Chengdu under different categories and different bandwidths is statistically analyzed, and then the relationship between the POI kernel density and population density of each category with different bandwidths is established based on the regression model. The bandwidth indicator corresponding to the kernel density indicator with the highest factor importance is the optimal bandwidth indicator for this category;

[0070] Meanwhile, in this embodiment, the optimal broadband indicators of the 10 POI categories are shown in Table 3 below:

[0071] Table 3 Optimal broadband index table for POI categories

[0072] POI Category Optimal bandwidth / meter POI Category Optimal bandwidth / meter Government Services 1700 Medical Services 1500 Transport 600 Residential Business 3700 Financial Services 2900 Shopping Services 1600 Accommodation Services 3900 Leisure Services 2100 Food and Beverage 1400 Educational Services 1800

[0073] Specifically, in this embodiment, the density index of each POI category is calculated using the optimal bandwidth index of each POI category, the scale correction coefficient of each energy level corresponding to each POI category, and the number of POIs, which is specifically:

[0074]

[0075] Among them, Z j represents the density index of the j-th POI category; n i represents the number of POIs of the i-th POI level in the j-th POI category; X i represents the scale correction coefficient of the i-th POI level in the j-th POI category; R j represents the optimal bandwidth index of the j-th POI category.

[0076] In another embodiment, the method further includes: performing principal component analysis on all POI density indicators using a principal component analysis method to obtain a plurality of principal components of the POI density indicators.

[0077] It should be noted that in this embodiment, in order to reduce the training complexity and overfitting risk in the model training of population distribution simulation, increase the generalization ability of the model, and integrate the indicators and reduce the dimension of the features of the POI-related indicators. Since there are more than 20 density indicators and distance indicators related to POI, and there is a certain correlation between the indicator factors, integrating the indicator factors of different categories of POI is an important link to reduce redundant information. Therefore, in addition to the principal component analysis of all POI density indicators mentioned above, principal component analysis is also performed on all POI distance indicators. Based on principal component analysis (PCA), the main features of POI-related indicators are concentrated on the principal component with the largest eigenvalue, followed by the second principal component, and then decrease in turn. Through PCA, the POI-related indicator data set is linearly transformed and converted into a set of new variables, and the first four principal components are selected. While fully integrating the single-category POI indicator information, it is ensured that the integrated indicators are better than the combination of single indicators, thereby reducing the dimension of the data and the complexity of model training, specifically:

[0078] PCA (Principal Component Analysis), also known as principal component analysis, is the most widely used data dimensionality reduction algorithm in the industry. Its calculation process is as follows:

[0079] Assume that there are n POI related indicators: X = {X1, X2, …X n};

[0080] 1) Standardize the data of each indicator so that its mean is 0 and its variance is 1:

[0081]

[0082] Among them, i=1,2…n, μ is the mean of each indicator, and σ is the standard deviation.

[0083] 2) Calculate the covariance matrix C of each indicator i, and then perform eigendecomposition to obtain eigenvalues ​​λ={λ1,λ2…,λ n}

[0084] and eigenvector v = {v1,v2…,v n},in:

[0085]

[0086] 3) Select the eigenvectors corresponding to the first four eigenvalues ​​as the principal components to form the projection matrix W:

[0087] W = [v1, v2, v3, v4]

[0088] 4) Based on the principal component, the original index data is linearly transformed to obtain the new index Y after dimensionality reduction:

[0089]

[0090] Specifically, in this embodiment, the attractiveness of POIs is quantified by combining data from multiple online platforms to obtain POI attractiveness indexes of different energy levels, and then the scale correction coefficient of each POI energy level is obtained by combining the constructed energy level weight coefficient to take into account the individual differences of POI points of interest, avoid the loss of semantic details and the peak smoothing of density indicators, and perform density bandwidth tests on different types of POIs to obtain the optimal bandwidth indicator for each POI category, and take into account the scale effect of POIs to generate density indicators for different POI categories, so as to assist in achieving accurate and objective population distribution simulation on a small scale.

[0091] Example 2

[0092] The present invention also provides a population spatial distribution simulation method, characterized in that the method comprises:

[0093] Based on the spatial distribution influencing factors, the population distribution influencing factors are selected, and the historical data corresponding to the population distribution influencing factors are obtained; wherein the population distribution influencing factors include the natural geographical environment influencing factors and the social and economic activity influencing factors;

[0094] The natural geographical environment influencing factors include topographic data, land cover data, vegetation index data and river network distance data; the topographic data include elevation and slope; the land cover data include the distance to the nearest construction land; the vegetation index data include NDVI data; the river network distance data include the nearest distance to the main river;

[0095] The social and economic activity influencing factors include traffic accessibility data, economic activity data and life convenience data; the traffic accessibility data includes subway station density, distance to the nearest subway station, bus station density, distance to the nearest bus station, municipal road density and distance to the nearest municipal road; economic activity data includes night light intensity index; life convenience data includes density indexes of multiple POI categories generated by a POI density index generation method described in the above embodiment 1;

[0096] Based on the population distribution influencing factors and the historical data corresponding to the population distribution influencing factors, the spatial distribution simulation of the population in the urban area is completed.

[0097] It should be noted that, in this embodiment, the specific technical solution for simulating the spatial distribution of population can be found in the technical solution of patent publication number CN118365156A, which will not be described in detail here.

[0098] Example 3

[0099] See also Figure 2 As shown, the present invention further provides a POI density index generation system, which is used in any one of the above-mentioned POI density index generation methods, and the system includes:

[0100] The first module 100 is used to classify POIs based on POI attributes to obtain multiple POI categories, wherein each POI category includes multiple POI energy levels;

[0101] The second module 200 is used to generate POI attraction indexes of different energy levels by using the obtained data from multiple online platforms, and obtain the scale correction coefficient of each POI energy level through the POI attraction indexes of different energy levels and the pre-constructed energy level weight coefficients;

[0102] The third module 300 is used to obtain the optimal bandwidth index of each POI category, and calculate the density index of each POI category using the optimal bandwidth index of each POI category, the scale correction coefficient of each energy level corresponding to each POI category, and the number of POIs.

[0103] It should be noted that the modules in the system of Example 3 correspond to the steps in a POI density index generating method of Example 1. The steps in the method of Example 1 have been described in detail in Example 1, and the contents of the modules in the system will not be described in detail in this Example 3.

[0104] Example 4

[0105] See also Figure 3As shown, this embodiment further provides a computer device, including a system memory 1005 and a processor 1001, wherein the system memory 1005 stores a computer program, and the processor 1001 implements the steps of any of the above methods when executing the computer program.

[0106] It should be noted that the processor 1001 is used to execute the steps in the above method embodiments according to the instructions in the program code. Alternatively, the processor 1001 implements the functions of each module / unit in the above system / device embodiments when executing the computer program.

[0107] Specifically, in this embodiment, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the system memory 1005, and are executed by the processor 1001 to complete the present application. One or more modules / units may be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0108] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor 1001 and a system memory 1005. Those skilled in the art will appreciate that this does not constitute a limitation on the terminal device, and may include more or less components than shown in the figure, or combine certain components, or different components. For example, the terminal device may also include an input / output device 1003, a network access device 1002, a bus 1006, etc.

[0109] The processor 1001 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0110] The system memory 1005 may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The system memory 1005 may also be a storage device 1004 of the terminal device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the terminal device. Further, the system memory 1005 may also include both the internal storage unit of the terminal device and the storage device 1004. The system memory 1005 is used to store computer programs and other programs and data required by the terminal device. The system memory 1005 may also be used to temporarily store data that has been output or is to be output.

[0111] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0112] Example 5

[0113] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the above methods are implemented.

[0114] Among them, the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, system or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk. Random Access Memory (RAM), Read-Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM), registers, hard disks, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above, or any other form of computer-readable storage medium known in the art.

[0115] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (ASIC). In an embodiment of the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system, or device.

[0116] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for generating a POI density index, characterized in that: Methods include: Classifying the POIs based on the POI attributes to obtain a plurality of POI categories, wherein each POI category includes a plurality of POI energy levels; The data from multiple online platforms are used to generate POI attractiveness indexes of different energy levels. The scale correction coefficient of each POI energy level is obtained through the POI attractiveness indexes of different energy levels and the pre-constructed energy level weight coefficients. The optimal bandwidth index of each POI category is obtained, and the density index of each POI category is calculated using the optimal bandwidth index of each POI category, the scale correction coefficient of each energy level corresponding to each POI category, and the number of POIs.

2. A POI density index generation method according to claim 1, characterized in that: The POI attractiveness index includes the POI online attractiveness index and the POI offline attractiveness index.

3. A POI density index generation method according to claim 2, characterized in that: The data from multiple online platforms are used to generate POI attractiveness indexes of different levels, specifically: Obtaining first platform data and second platform data of different POI levels, and calculating the POI online attraction index of each POI level using the first platform data, and calculating the POI offline attraction index of each POI level using the second platform data; The POI attraction index of each POI level is generated through the POI online attraction index and the POI offline attraction index of each POI level.

4. A POI density index generation method according to any one of claims 1 or 3, characterized in that: Through the POI attractiveness index of different energy levels and the pre-constructed energy level weight coefficient, the scale correction coefficient of each POI energy level is obtained, specifically: X i =a i ·d i Among them, X i represents the scale correction coefficient of the i-th POI energy level; a i represents the POI attractiveness index of the i-th POI level; δ i Represents the energy level weight coefficient of the i-th POI energy level, where i is a positive integer.

5. A POI density index generation method according to any one of claim 1, characterized in that: Using the optimal bandwidth index of each POI category, as well as the scale correction coefficient and the number of POIs at each energy level corresponding to each POI category, the density index of each POI category is calculated, specifically: Among them, Z j represents the density index of the j-th POI category; n i represents the number of POIs of the i-th POI level in the j-th POI category; X i represents the scale correction coefficient of the i-th POI level in the j-th POI category; R j represents the optimal bandwidth index of the j-th POI category.

6. A method for generating a POI density index according to any one of claim 1, characterized in that: The method also includes: performing principal component analysis on all POI density indicators using a principal component analysis method to obtain a plurality of principal components of POI density indicators.

7. A POI density index generation system, characterized in that: The system is used in a POI density index generation method according to any one of claims 1 to 6, and the system comprises: The first module is used to classify POIs based on POI attributes to obtain multiple POI categories, wherein each POI category includes multiple POI energy levels; The second module is used to generate POI attractiveness indexes of different energy levels using the data obtained from multiple online platforms, and obtain the scale correction coefficient of each POI energy level through the POI attractiveness indexes of different energy levels and the pre-constructed energy level weight coefficients; The third module is used to obtain the optimal bandwidth index of each POI category, and calculate the density index of each POI category using the optimal bandwidth index of each POI category, the scale correction coefficient of each energy level corresponding to each POI category, and the number of POIs.

8. A method for simulating population spatial distribution, characterized in that: include: Based on the spatial distribution influencing factors, the population distribution influencing factors are selected, and the historical data corresponding to the population distribution influencing factors are obtained; wherein the population distribution influencing factors include the natural geographical environment influencing factors and the social and economic activity influencing factors; The natural geographical environment influencing factors include topographic data, land cover data, vegetation index data and river network distance data; the topographic data include elevation and slope; the land cover data include the distance to the nearest construction land; the vegetation index data include NDVI data; the river network distance data include the nearest distance to the main river; The social and economic activity influencing factors include traffic accessibility data, economic activity data and life convenience data; the traffic accessibility data include subway station density, distance to the nearest subway station, bus station density, distance to the nearest bus station, municipal road density and distance to the nearest municipal road; economic activity data include night light intensity index; life convenience data include density indicators of multiple POI categories generated by a POI density indicator generation method described in any one of claims 1 to 6; Based on the population distribution influencing factors and the historical data corresponding to the population distribution influencing factors, the spatial distribution simulation of the population in the urban area is completed.

9. A computer device comprising a system memory and a processor, wherein the system memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images