A method for predicting urban population distribution trends based on geographic probes

Abstract

The application provides a city resident population distribution trend prediction method based on a geographic detector, comprising the following steps: acquiring panoramic street view data of a research area; performing semantic segmentation to obtain visual perception elements and establish visual perception factors; establishing spatial perception factors through the accessibility of different facility types under different travel modes; using the geographic detector to calculate the explanation rate of the visual perception factors and the spatial perception factors on the resident population distribution density; obtaining several high-explanation-rate perception factors, obtaining corresponding weights based on a judgment matrix, establishing a resident intention index, and predicting the city resident population distribution trend. The prediction method is based on the perception of people to the real city environment, takes into account the subjectivity and objectivity of evaluation, and has high reference value for city planning related to city resident population distribution.

Description

Technical Field

[0001] This invention relates to the field of urban remote sensing technology, and in particular to a method for predicting the distribution trend of urban settled population based on geographic detectors. Background Technology

[0002] Urbanization is accompanied by large-scale population migration, which constantly reshapes the urban population structure. This massive influx of people puts enormous pressure on limited urban resources and environmental capacity. Currently, the precise prediction of the distribution of the settled population at a fine scale remains a significant unresolved issue.

[0003] People's perception of the urban environment profoundly influences their settlement choices and the stability of their residence. The quality of public spaces and the construction of service facilities in the urban environment positively affect people's settlement intentions and are closely related to the distribution of the resident population. Research on population settlement is mostly based on questionnaire survey data analysis of people's residential preferences for the urban environment; quantitative measurement research on urban environmental perception is still incomplete. The increase in the types of geospatial data and the development of processing technologies have greatly enriched the methods for characterizing the above-mentioned urban environmental characteristics from a human perspective. In recent years, emerging data have been widely used in urban environmental characterization research related to human activities. For example, POIs (points of information or points of interest, any non-geographically significant point on a map) are often used for urban morphology characterization, urban functional area identification, and gridded population mapping; street view data is widely used for street quality evaluation and urban functional morphology characterization; in addition, network location service platforms are an important supplement to current accessibility research. The significance of POIs lies in connecting users with geographically significant points when their perception of their geographical location and surrounding information is inaccurate, and in transforming them into further behavioral patterns.

[0004] Settled population data largely relies on manual surveys, which cannot guarantee spatial continuity and are difficult to collect over a large area in a short period. Current spatial population distribution predictions primarily focus on the total population, neglecting settled and transient populations. The grid cells used in population mapping cannot match the irregularly shaped street blocks where people live. Due to privacy concerns or unclear boundaries between geographical units, census data often covers a large area of ​​total population. Taking China as an example, the spatial precision of urban studies related to human activities is mostly limited to the street scale, the highest precision of a census. With the increasing precision of urban environmental research, street blocks are gradually being used as representative, refined research units within cities in urban landscape and urban planning analyses. As land units with relatively homogeneous socio-economic functions, defined by road networks, street blocks are fundamental components of urban structure and important dividing units related to population activities.

[0005] In conclusion, given the diverse and complex urban environment, there is an urgent need for a quantitative analysis-based method for predicting the distribution trends of urban settled population at a fine scale, in order to provide more scientific and objective guidance for urban planning and contribute to sustainable urban development. Summary of the Invention

[0006] The purpose of this application is to address the deficiencies in the existing technology.

[0007] To address the insufficient quantitative analysis of the spatial distribution of urban settled populations in existing research, this application aims to propose a method for predicting urban settled population distribution trends based on geographic detectors. Based on a quantitative analysis of urban environmental perception factors and urban settled population distribution, a settlement intention index that balances subjectivity and objectivity is constructed.

[0008] In a first aspect, this application provides a method for predicting the distribution trend of urban settled population based on a geographic detector, comprising: acquiring panoramic street view data of the study area; performing semantic segmentation on the panoramic street view data to obtain visual perception elements and establishing at least one urban environment visual perception factor; based on the panoramic street view data, obtaining the accessibility of at least one facility type under at least one mode of transportation (accessibility in graph theory refers to the ease of getting from one vertex to another in a graph; in an undirected graph, accessibility between all vertex pairs can be determined by identifying the connectivity components of the graph), and establishing at least one urban environment spatial perception factor; using a geographic detector, calculating the explanatory power of the at least one urban environment visual perception factor and the at least one urban environment spatial perception factor for the distribution density of settled population; based on the explanatory power, determining at least one high-explanatory-power perception factor from the at least one urban environment visual perception factor and the at least one urban environment spatial perception factor, and obtaining the weight corresponding to the high-explanatory-power perception factor based on a judgment matrix; and establishing a settlement intention index based on the high-explanatory-power perception factor and its corresponding weight to predict the distribution trend of urban settled population.

[0009] In one feasible embodiment, acquiring panoramic street view data of the study area includes: acquiring panoramic street view data of the study area by setting sampling points with equal or unequal spacing.

[0010] In one feasible embodiment, the step of obtaining panoramic street view data of the study area by setting sampling points with equal or unequal spacing includes: obtaining Baidu street view panoramic data of the study area by setting sampling points with equal spacing of 200m in the road network, and cropping and extracting the middle 1 / 3 in the vertical direction.

[0011] In one feasible embodiment, the step of semantically segmenting the panoramic street view data to obtain visual perception elements and establishing at least one urban environment visual perception factor includes: using a neural network model to perform semantic segmentation on the panoramic street view data to obtain visual perception elements; and establishing at least one urban environment visual perception factor based on the type and diversity characteristics of the visual perception elements.

[0012] In one feasible embodiment, the step of using a neural network model to perform semantic segmentation on the panoramic street view data to obtain visual perception elements includes: using a DeepLabV3 model trained on the Cityscape training set to perform semantic segmentation on the panoramic street view data to obtain visual perception elements.

[0013] In one feasible embodiment, the establishment of at least one urban environment visual perception factor based on the type and diversity characteristics of visual perception elements includes: establishing seven urban environment visual perception factors based on the type and diversity characteristics of visual perception elements, namely, greening, openness, enclosure, motorization, humanization, SIDI diversity and SHDI diversity.

[0014] In one feasible embodiment, obtaining the accessibility of at least one facility type under at least one mode of transportation based on the panoramic street view data and establishing at least one urban environmental spatial perception factor includes: obtaining isochronous travel range based on the panoramic street view data to obtain the accessibility of at least one facility type under at least one mode of transportation; and establishing at least one urban environmental spatial perception factor based on the accessibility of at least one facility type under at least one mode of transportation.

[0015] In one feasible embodiment, the step of obtaining isochronous travel range based on the panoramic street view data and obtaining the accessibility of at least one facility type under at least one mode of travel includes: calling the Isochrone API to obtain the 15-minute isochronous travel range of each block under the three modes of walking, cycling, and driving; counting the number of POI points of each type within each isochronous travel range; and calculating the accessibility of the block for different facility types under different modes of travel based on the cumulative opportunity method.

[0016] In a feasible embodiment, establishing at least one urban environmental spatial perception factor based on the accessibility of at least one facility type under the at least one mode of travel includes: calculating the accessibility of six types of service facilities (office, transportation, commerce, residence, science and education, health, and green space and square) under different modes of travel, cycling, and driving, for a total of 18 urban environmental spatial perception factors.

[0017] In a feasible embodiment, determining at least one high-explanation-rate perception factor based on the explanation rate and obtaining the weight corresponding to the high-explanation-rate perception factor based on the judgment matrix includes: selecting at least one high-explanation-rate perception factor from the at least one urban environment visual perception factor and at least one urban environment spatial perception factor for constructing a hierarchical model; determining the judgment matrix scale between each pair of corresponding perception factors according to the magnitude of the explanation rate difference to obtain the judgment matrix of the high-explanation-rate perception factor; and obtaining the weight corresponding to the high-explanation-rate perception factor by solving the judgment matrix.

[0018] Secondly, this application provides an electronic device for predicting the distribution trend of urban settled population based on a geographic detector, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the aforementioned method for predicting the distribution trend of urban settled population based on a geographic detector.

[0019] Thirdly, this application provides a medium for a method of predicting the distribution trend of urban settled population based on a geographic detector, wherein a computer program is stored thereon, characterized in that the program, when executed by a processor, implements the aforementioned method of predicting the distribution trend of urban settled population based on a geographic detector.

[0020] This application proposes a quantitative analysis of urban settlement population distribution using a geographic detector, and based on this, constructs a Settlement Intention Index (SII) that integrates multiple urban environmental perception factors to predict urban settlement population distribution trends. Addressing the insufficient quantitative level of existing research on the spatial distribution of urban settlement population, this application aims to propose a method for predicting urban settlement population distribution trends based on a geographic detector. Based on a quantitative analysis of urban environmental perception factors and urban settlement population distribution, a settlement intention index that balances subjectivity and objectivity is constructed.

[0021] This application proposes a method for predicting the distribution trend of urban settled population using a geographic detector. The explanatory power of various human-centered perception factors on the spatial distribution of the settled population can be obtained through a geographic detector model, and a settlement intention index can be constructed based on this. This method is based on quantitative research on people's perception of the real urban environment, taking into account both the subjectivity and objectivity of the evaluation, and has high reference value for urban planning related to the distribution of urban settled population. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating a method for predicting the distribution trend of urban settled population based on a geographic detector, according to an embodiment of the present invention.

[0023] Figure 2 This is a schematic diagram of a Baidu Street View panoramic view of the Beijing study area according to an embodiment of the present invention;

[0024] Figure 3 This is a schematic diagram illustrating the calculation of urban environmental visual perception factors in the Beijing study area according to an embodiment of the present invention.

[0025] Figure 4 This is a schematic diagram illustrating the isochronous travel range of facility accessibility under different travel modes in the Beijing study area according to an embodiment of the present invention.

[0026] Figure 5 This is a map showing the settlement intention index (SII) and the distribution of hot and cold spots between ring roads in the Beijing study area, as well as the distribution of settlement intention index (SII) in this invention embodiment. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0028] To provide the public with a better understanding of this invention, certain specific details are described in detail below. However, those skilled in the art will fully understand this invention even without these detailed descriptions.

[0029] Figure 1 This is a flowchart illustrating a method for predicting the distribution trend of urban settled population based on a geographic detector, according to an embodiment of the present invention. Figure 1 As shown in the figure, this invention provides a method for predicting the distribution trend of urban settled population based on a geographic detector, which mainly includes the following steps:

[0030] Step S110: Obtain panoramic street view data of the study area;

[0031] Step S120: Semantic segmentation is performed on the panoramic street view data to obtain visual perception elements and establish at least one urban environment visual perception factor.

[0032] Step S130: Based on the panoramic street view data, obtain the accessibility of at least one facility type under at least one mode of transportation, and establish at least one urban environmental spatial perception factor.

[0033] Step S140: Using a geographic detector, calculate the explanatory power of the at least one urban environment visual perception factor and the at least one urban environment spatial perception factor on the distribution density of the settled population.

[0034] Step S150: Based on the explanatory rate, determine at least one high explanatory rate perception factor from the at least one urban environment visual perception factor and the at least one urban environment spatial perception factor, and obtain the weight corresponding to the high explanatory rate perception factor based on the judgment matrix.

[0035] Step S160: Based on the high explanatory power perception factor and its corresponding weight, establish a settlement intention index to predict the distribution trend of urban settlement population.

[0036] In step S110, Baidu panoramic street view data is obtained by setting equal-spaced sampling points on the road network, and Baidu panoramic street view data of the study area is obtained by setting equal-spaced sampling points on the road network at 200m intervals. The middle 1 / 3 in the vertical direction is then cropped and extracted.

[0037] In step S120, semantic segmentation is used to extract landscape information from the street view image. A DeepLabV3 model trained on the Cityscape training set is used to perform semantic segmentation on the street view data. The proportion of visual perception elements extracted by semantic segmentation is exported. Based on the types and diversity characteristics of visual perception elements, seven visual perception factors are calculated: greening, openness, enclosure, motorization, humanization, SIDI diversity, and SHDI diversity.

[0038] In step S130, firstly, the centroid of each block within the study area is extracted as the starting point representing the smallest block unit. Secondly, the Isochrone API is called to obtain the 15-minute isochronous travel range of each block under the three travel modes of walking, cycling, and driving. Finally, the number of POIs of each type within each isochronous circle is counted, and the accessibility of different facilities for different travel modes in each block is calculated based on the cumulative opportunity method.

[0039] Based on travel mode and facility type, the accessibility of six types of service facilities (office, transportation, commerce, residence, science and education, health, and green space and plaza) is calculated for three travel modes (walking, cycling, and driving), totaling 18 spatial perception factors.

[0040] In step S140, firstly, Pearson correlation analysis is used to determine the direction of the influence of each perception factor on the distribution of the urban settled population. Then, the factor detection module of the geographic detector is applied to measure the degree of spatial heterogeneity caused by various perception factors on the distribution of the urban settled population. This can be quantitatively described using the q statistic.

[0041]

[0042] In Equation 1, N and σ 2 These represent the number of study units and the variance of Y (settled population density) across the entire study area, respectively; the population Y has L strata (h = 1, 2, ..., L), and each stratum h is determined by N... h Composed of units, σ h 2 q represents the variance of Y values ​​within layer h. The value of q is [0,1]. q=0 indicates that there is no coupling relationship between Y and X (each perceptual factor); q=1 indicates that Y is completely determined by the explanatory factor X; the value of q (0,1) indicates that X explains 100q% of Y.

[0043] In step S150, several indices with the highest q-values ​​are selected from all perceptual factors (including visual perception and spatial perception) to construct a hierarchical model. Based on the magnitude of the q-value differences, the 1-9 scale method of analytic hierarchy process is used to determine the pairwise judgment matrix scale between the landscape indices, thus obtaining the judgment matrix for all perceptual factors. By solving the judgment matrix, the weight of each perceptual factor is obtained.

[0044] Table 1. Determining the significance of matrix scaling

[0045]

[0046] In step S160, a settlement intention index is constructed based on the indexes (perception factors) with the highest q values ​​and the weights corresponding to each landscape index.

[0047] The present invention also provides an electronic device for predicting the distribution trend of urban settled population through quantitative analysis, including at least one processor, the processor being configured to execute a program stored in a memory, which, when executed, causes the device to perform the prediction method of steps S110 to S160.

[0048] This invention also provides a non-transitory computer-readable storage medium for quantitative analysis of urban settlement population distribution trend prediction, on which a computer program is stored, which, when executed by a processor, implements the prediction method described in steps S110 to S160.

[0049] Example 1

[0050] The following explanation will be further elaborated using the Beijing study area as an example.

[0051] (I) Extraction of visual perception elements

[0052] First, set up sampling points at 200m intervals along the road network to obtain data such as... Figure 2The study area is shown using Baidu Street View panoramic data, with the middle third cropped vertically. Next, the DeepLabV3 model trained on the Cityscape training set is used to perform semantic segmentation on the street view data. The semantic segmentation results are shown below. Figure 3 As shown. Finally, the feature proportion results extracted by semantic segmentation are exported.

[0053] (II) Extraction of Spatial Perception Elements

[0054] First, the centroid of each block within the study area is extracted as the starting point representing the smallest block unit. Second, the Isochrone API is used to obtain the 15-minute isochronous travel range for each block under three travel modes: walking, cycling, and driving. Finally, the number of POIs of each type within each isochronous circle is counted, such as... Figure 4 As shown, the accessibility of different facilities in a neighborhood is calculated based on different travel modes using the cumulative opportunity method.

[0055] (III) Construction of Perceptual Factors

[0056] Based on the types and diversity characteristics of visual perception elements, seven visual perception factors were calculated: greening, openness, enclosure, motorization, humanization, SIDI diversity, and SHDI diversity.

[0057] Based on travel mode and facility type, the accessibility of six types of service facilities (office, transportation, commerce, residence, science and education, health, and green space and plaza) is calculated for three travel modes (walking, cycling, and driving), totaling 18 spatial perception factors.

[0058] (iv) Quantitative Analysis of Geographic Detectors

[0059] First, Pearson correlation analysis is used to determine the direction of the influence of each perception factor on the distribution of the urban settled population. Then, the factor detection module of the geographic detector is used to measure the degree of spatial heterogeneity caused by various perception factors on the distribution of the urban settled population. The q statistic can be used to achieve quantitative description.

[0060] (V) Construction of Settlement Intention Index

[0061] From all perceptual factors (including visual perception and spatial perception), several indices with the highest q-values ​​were selected to construct the hierarchical model as shown in Table 2. Based on the magnitude of the q-value differences, the judgment matrix scale between each pair of landscape indices was determined using the 1-9 scale method of analytic hierarchy process, resulting in the judgment matrix shown in Table 3. By solving the judgment matrix, the weights of each landscape index as shown in Table 2 were obtained, and the settlement intention index SII as shown in Formula 2 was constructed.

[0062] Table 2 Hierarchical Model of Evaluation Indicators

[0063]

[0064] Table 3 Evaluation Index Judgment Matrix

[0065]

[0066]

[0067] To eliminate the influence of dimensions, when performing SII calculations, all perspective perception factors must be standardized to the range of 0 to 1 before input.

[0068] To address the insufficient quantitative analysis of the spatial distribution of urban settled population in existing research, this invention aims to propose a method for predicting urban settled population distribution trends based on a geographic detector. Based on a quantitative analysis of urban environmental perception factors and settled population distribution, a settlement intention index that balances subjectivity and objectivity is constructed. This invention achieves its objective through the following technical steps: acquiring Baidu panoramic street view data by setting up equally spaced sampling points in the road network; extracting landscape information from the street view images using semantic segmentation; extracting accessibility of various service facilities for walking, cycling, and driving modes using the Isochrone API and POIs; establishing urban environmental visual perception factors based on landscape type, proportion, and diversity; establishing urban environmental spatial perception factors based on differences in travel modes and service facility types; using street blocks as the calculation unit for each perception factor, statistically analyzing the street unit factor mean as the independent variable, and performing geographic detector factor detection with the street-level population density of "local population, settled here" based on census data, calculating the explanatory power q of each perception factor on the urban settled population distribution; constructing a hierarchical structure and prioritizing elements using the analytic hierarchy process (AHP) based on the explanatory power q; obtaining the weights of each perception factor by solving the judgment matrix, and constructing the settlement intention index.

[0069] Not limited to the embodiments of this invention, the collected SVI data may come from different seasons, and the resulting differences in urban landscape are a significant source of error in the quantification of visual perception of urban public spaces. While the technical solutions of the embodiments of this invention have strong regional applicability, the SII index calculation model constructed based on quantitative analysis of geographic detectors is only applicable to the current study area. This limitation can be addressed by conducting experiments in multiple different types of study areas: exploring the mechanisms of action of urban environmental characteristics, and summarizing general or applicable index calculation models for specific city types.

[0070] Not limited to the embodiments of the present invention, when calculating the spatial perception factors used for analysis, the starting point for accessibility measurement should be the smallest divisible scale (such as blocks, buildings) of mass points, or street view sampling points can be set on finer road intervals; the perception factors for constructing the SII calculation model can be added or deleted according to the application purpose and urban landscape planning characteristics, and the principle of establishing the judgment matrix can be adjusted according to the differences in q values ​​of each factor in the factor detection results.

[0071] This invention is not limited to the embodiments described herein. It utilizes open-source data and automated processing tools to create a detailed and comprehensive depiction of the urban environment as perceived by humans. DeepLabV3 and the Isochrone API expand the use cases for street view and POI, enabling automated large-scale quantitative calculation of perception factors. By using factor detection and Pearson correlation coefficients to guide the establishment of the AHP judgment matrix, it cleverly avoids weight calculation errors caused by excessive subjectivity, increasing the credibility and objectivity of the indicator construction.

[0072] The population migration accompanying urbanization has led to a significant increase in urban population; however, quantitative research on the distribution of urban settled population at a fine scale still lacks. People's subjective perception of the urban environment directly influences their settlement choices. To quantify the impact of human perception factors on the distribution of settled population, this study proposes a method for predicting the distribution trend of urban settled population based on quantitative analysis using a geographic detector. The method includes the following steps: 1) Using street blocks as units, semantic segmentation of street view images and accessibility calculation based on the Isochrone API and POIs are performed to obtain the visual and spatial features of the urban environment perceived by people and construct human perception factors; 2) The mean of the street block factor calculation results within the street unit is calculated, and the explanatory power q of each human perception factor on the distribution of settled population is detected using a geographic detector; 3) Based on the explanatory power q, a judgment matrix is ​​constructed using the analytic hierarchy process (AHP) to obtain the weights of each perception factor and construct an urban population settlement intention index.

[0073] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. Therefore, it should be understood that the above description is only one 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 within the scope of protection of the present invention.

Claims

1. A method for predicting the distribution trend of urban settled population based on geographic detectors, characterized in that, include: Acquire panoramic street view data of the study area; Semantic segmentation is performed on the panoramic street view data to obtain visual perception elements, and at least one urban environment visual perception factor is established. Specifically, a neural network model is used to perform semantic segmentation on the panoramic street view data to obtain visual perception elements; the neural network model is a DeepLabV3 model trained using the Cityscape training set. Based on the type and diversity characteristics of the visual perception elements, at least one urban environment visual perception factor is established; the urban environment visual perception factor includes seven urban environment visual perception factors: greening, openness, enclosure, motorization, humanization level, SIDI diversity, and SHDI diversity. Based on the panoramic street view data, the accessibility of at least one facility type under at least one mode of transportation is obtained, and at least one urban environmental spatial perception factor is established. Specifically, based on the panoramic street view data, isochronous travel range is obtained, and the accessibility of at least one facility type under at least one mode of transportation is obtained; based on the accessibility of at least one facility type under at least one mode of transportation, at least one urban environmental spatial perception factor is established. Using a geographic detector, calculate the explanatory power of the at least one urban environmental visual perception factor and the at least one urban environmental spatial perception factor on the distribution density of the settled population. Based on the explanatory rate, at least one high explanatory rate perception factor is determined from the at least one urban environment visual perception factor and the at least one urban environment spatial perception factor, and the weight corresponding to the high explanatory rate perception factor is obtained based on the judgment matrix. Based on the high explanatory power of the perception factor and its corresponding weight, a settlement intention index is established to predict the distribution trend of urban settlement population.

2. The prediction method according to claim 1, characterized in that, The acquisition of panoramic street view data of the study area includes: By setting sampling points with equal or unequal spacing, panoramic street view data of the study area is obtained.

3. The prediction method according to claim 2, characterized in that, The process of acquiring panoramic street view data of the study area by setting sampling points at equal or unequal intervals includes: By setting up sampling points at 200m intervals along the road network, we obtained panoramic data of Baidu Street View for the study area, and then cropped and extracted the middle third of the data in the vertical direction.

4. The prediction method according to claim 1, characterized in that, The step of obtaining isochronous travel range based on the panoramic street view data and determining the accessibility of at least one facility type under at least one mode of transportation includes: Call the Isochrone API to obtain the 15-minute isochronous travel range of each block under the three modes of travel: walking, cycling, and driving. The number of POIs of each type within the travel range at each time period is counted, and the accessibility of different facilities in the block is calculated based on the cumulative opportunity method under different travel modes. The establishment of at least one urban environmental spatial perception factor based on the accessibility of at least one facility type under at least one mode of transportation includes: Based on different modes of transportation and facility types, the accessibility of six types of service facilities—office, transportation, commerce, residence, science and education, health, and green space and square—was calculated for three modes of transportation: walking, cycling, and driving, resulting in a total of 18 urban environmental spatial perception factors.

5. The prediction method according to claim 1, characterized in that, Based on the explanatory power, at least one high-explanatory-power perception factor is determined from the at least one urban environment visual perception factor and the at least one urban environment spatial perception factor. The weight corresponding to the high-explanatory-power perception factor is obtained based on a judgment matrix, including: At least one high-explanation-rate perception factor is selected from the at least one urban environment visual perception factor and the at least one urban environment spatial perception factor to construct a hierarchical model; Based on the magnitude of the difference in explanatory power, the scale of the judgment matrix between each pair of corresponding perceptual factors is determined, and the judgment matrix of the high explanatory power perceptual factor is obtained. By solving the judgment matrix, the weights corresponding to the high explanatory power perception factors are obtained.

6. An electronic device for predicting urban settlement population distribution trends based on geographic detectors, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the prediction method as described in any one of claims 1 to 5.

7. A medium for a method of predicting the distribution trend of urban settled population based on geographic detectors, wherein a computer program is stored thereon, characterized in that, When the program is executed by the processor, it implements the prediction method as described in any one of claims 1 to 5.

Images