Spatial reachability factor analysis method and system based on two-step mobile search method

Abstract

The invention discloses a spatial reachability factor analysis method and system based on a two-step mobile search method, and the method comprises the steps: building a comprehensive evaluation index model based on a Shannon diversity index and a multi-source index deviation; determining influence factors to be analyzed through a gravity type two-step mobile search model; obtaining a comprehensive evaluation index based on the comprehensive evaluation index model, and determining an optimal combination of the influence factors to be analyzed through a response surface method in combination with the comprehensive evaluation index; and analyzing the sensitivity of the to-be-analyzed influence factors to obtain an analysis result. According to the method, the sensitivity of a plurality of influence factors in the gravity type two-step mobile search model is explored, the defects of advantages and disadvantages of a traditional qualitative evaluation reachability result and method can be overcome through the proposed comprehensive evaluation index model, and a brand new quantitative evaluation reference basis is provided for improving the gravity type two-step mobile search model.

Description

Technical Field

[0001] The present invention relates to the field of geographic information technology, and in particular to a spatial accessibility factor analysis method and system based on a two-step mobile search method. Background Art

[0002] The spatial accessibility of public service facilities is an important indicator to measure the fairness of the layout of urban public service facilities, and is widely used in the layout planning of public service facilities such as medical care, education, and leisure. In the prior art, it is usually measured by different methods, but the most commonly used is the two-step mobile search method and its extended form (such as the gravity-based two-step mobile search method). The two-step mobile search method calculates the accessibility of each demand point through a two-step search process, specifically: search for demand points within its service range with the supply point as the center, and calculate the supply-demand ratio; search for supply points within its service range with the demand point as the center, and accumulate the supply-demand ratios of all supply points to obtain the accessibility of the demand point. The gravity-based two-step mobile search model is based on the traditional two-step mobile search method and introduces the distance decay function of the gravity model to more accurately reflect the characteristic that the attractiveness of service facilities decreases with increasing distance.

[0003] In the evaluation of spatial accessibility of public service facilities, factor sensitivity analysis is a key link, which helps to identify and understand the key parameters affecting accessibility evaluation and provide a more scientific basis for practical research. Factor sensitivity is of great significance for improving the gravity-based two-step mobile search model and improving the accuracy of its measurement results.

[0004] At present, single factor analysis is basically used to explore the impact of a single factor on the measurement results of the gravity-based two-step mobile search model, and most of them use qualitative analysis to evaluate the gravity-based two-step mobile search model and its measurement results. Although the single factor analysis method can explore the impact of a single factor on the spatial accessibility results, in fact, the spatial accessibility results may be affected by the interaction of multiple factors; in addition, in the process of measuring spatial accessibility results and spatial accessibility methods, qualitative evaluation is mainly used, and there is a lack of complete quantitative evaluation indicators. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a spatial accessibility factor analysis method and system based on a two-step mobile search method.

[0006] In order to solve the above technical problems, the present invention is solved by the following technical solutions:

[0007] A spatial accessibility factor analysis method based on a two-step mobile search method comprises the following steps:

[0008] Based on Shannon diversity index and multi-source index deviation, a comprehensive evaluation index model was constructed;

[0009] Through the gravity-type two-step moving search model, the influencing factors to be analyzed are determined;

[0010] Based on the comprehensive evaluation index model, the comprehensive evaluation index is obtained, and the best combination of the influencing factors to be analyzed is determined by combining the comprehensive evaluation index with the response surface method;

[0011] The sensitivity of the influencing factors to be analyzed is analyzed to obtain the analysis results.

[0012] As an implementable method, the comprehensive evaluation index model is expressed as follows:

[0013] H=w k S+w j (YA)

[0014] Among them, H represents the value of the comprehensive evaluation index, S represents the Shannon diversity index, A represents the multi-source index deviation, and w k represents the Shannon diversity index weight, w j represents the multi-source index deviation weight, Y represents a constant, S = -∑P v ln(P v ), A=|A' max -A max |+|A' min -A min |+|A' avg -A avg |,P v Indicates the proportion of the number of measurements equal to v to the total number, A' max , A' min and A' avg Respectively represent the maximum, minimum and average values ​​of accessibility measurements; A max , A min and A avg Represent the maximum, minimum and average values ​​in the validation data respectively.

[0015] As an implementable method, determining the influencing factors to be analyzed by using a gravity-type two-step moving search model includes the following steps:

[0016] Construct a gravity-based two-step mobile search model, which is expressed as follows:

[0017]

[0018] in, A i represents the spatial accessibility measurement value of research object i, S j represents the service capability of the supplier, C j Indicates the scale of the supplier, D krepresents the demand of the demand side at k, t ij represents the time taken to get from point i to point j, f(t ij ) represents the distance decay function, β represents the distance decay exponent, and t0 represents the search time range;

[0019] Based on the gravity-type two-step mobile search model, the spatial accessibility measurement value is obtained, and the spatial unit size, distance decay index and search time range of the object to be studied are taken as influencing factors to be analyzed.

[0020] As an implementable method, the optimal combination of influencing factors to be analyzed is determined by combining the response surface method with the comprehensive evaluation index, comprising the following steps:

[0021] The direction of the comprehensive evaluation index is determined through the steepest climbing experiment, and the maximum change direction and maximum change degree of the comprehensive evaluation index are determined under the current direction;

[0022] The central composite design experiment is used to explore in detail the changes of the response variables in the local optimal area, and the regression model of the influencing factors can be accurately fitted to determine the optimal parameter combination of the influencing factors to be analyzed.

[0023] As an implementable method, analyzing the sensitivity of the influencing factors to be analyzed and obtaining the analysis results includes the following steps:

[0024] The regression model of influencing factors was obtained by fitting the comprehensive evaluation index, spatial unit size, distance decay index and search time range;

[0025] Through the influencing factor regression model, the influence degree of the interaction effect of multiple influencing factors on the comprehensive evaluation index is analyzed to obtain the corresponding analysis results;

[0026] The influencing factor regression model is expressed as follows:

[0027]

[0028] Among them, Y represents the comprehensive evaluation index, X1 represents the size of the spatial unit, X2 represents the distance decay index and X3 represents the search time range, A0...A 11 Indicates the corresponding coefficients, and A1>A3>A9>A 11 >A2>A8.

[0029] As a possible implementation method, the interaction effect includes bilateral interaction and trilateral interaction;

[0030] When it is a bilateral interaction, the spatial unit size and the distance decay index are positive, the spatial unit size and the search time range, the distance decay index and the search time range are negative, and the comprehensive evaluation index increases as the interaction effect of the spatial unit size and the distance decay index and the interaction effect of the distance decay index and the search time range decreases;

[0031] When all coefficients are positive for bilateral interactions, the comprehensive evaluation index increases with the enhancement of the trilateral interaction effect.

[0032] As an implementable method, the following steps are also included:

[0033] The influence of a single influencing factor on the comprehensive evaluation index is analyzed. Specifically, when the size of the spatial unit is changed, the impact on the comprehensive evaluation index is the greatest; when the search time range is changed, the impact on the comprehensive evaluation index is second only to the impact of changing the size of the spatial unit.

[0034] A spatial accessibility factor analysis system based on a two-step mobile search method, comprising a first construction module, a first determination module, a second determination module and an analysis result module;

[0035] The first construction module constructs a comprehensive evaluation index model based on the Shannon diversity index and multi-source index deviation;

[0036] The first determination module is used to determine the influencing factors to be analyzed through a gravity-type two-step moving search model;

[0037] The second determination module obtains a comprehensive evaluation index based on the comprehensive evaluation index model, and determines the best combination of the influencing factors to be analyzed by combining the comprehensive evaluation index with the response surface method;

[0038] The analysis result module is used to analyze the sensitivity of the influencing factors to be analyzed and obtain analysis results.

[0039] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method is implemented:

[0040] Based on Shannon diversity index and multi-source index deviation, a comprehensive evaluation index model was constructed;

[0041] Through the gravity-type two-step moving search model, the influencing factors to be analyzed are determined;

[0042] Based on the comprehensive evaluation index model, the comprehensive evaluation index is obtained, and the best combination of the influencing factors to be analyzed is determined by combining the comprehensive evaluation index with the response surface method;

[0043] The sensitivity of the influencing factors to be analyzed is analyzed to obtain the analysis results.

[0044] A spatial accessibility factor analysis device based on a two-step mobile search method comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the following method when executing the computer program:

[0045] Based on Shannon diversity index and multi-source index deviation, a comprehensive evaluation index model was constructed;

[0046] Through the gravity-type two-step moving search model, the influencing factors to be analyzed are determined;

[0047] Based on the comprehensive evaluation index model, the comprehensive evaluation index is obtained, and the best combination of the influencing factors to be analyzed is determined by combining the comprehensive evaluation index with the response surface method;

[0048] The sensitivity of the influencing factors to be analyzed is analyzed to obtain the analysis results.

[0049] The present invention has significant technical effects due to the adoption of the above technical solution:

[0050] The present invention realizes the sensitivity exploration of multiple influencing factors in the gravity-type two-step mobile search model, and the proposed comprehensive evaluation index model can overcome the shortcomings of traditional qualitative evaluation of reachability results and methods, providing a new quantitative evaluation reference for improving the gravity-type two-step mobile search model. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0052] Figure 1 It is a schematic diagram of the overall process of the method of the present invention;

[0053] Figure 2 An implementation roadmap for the method of the present invention;

[0054] Figure 3 This is a schematic diagram of the results of the analysis based on contour lines;

[0055] Figure 4 It is a schematic diagram of the results of the analysis based on the three-dimensional surface;

[0056] Figure 5 It is a schematic diagram of the overall structure of the system of the present invention. DETAILED DESCRIPTION

[0057] The present invention is further described in detail below in conjunction with embodiments. The following embodiments are for explanation of the present invention but the present invention is not limited to the following embodiments.

[0058] Embodiment 1:

[0059] A spatial accessibility factor analysis method based on a two-step moving search method, such as Figure 1 As shown, the following steps are included:

[0060] S100, based on Shannon diversity index and multi-source index deviation, construct a comprehensive evaluation index model;

[0061] S200, determining the influencing factors to be analyzed through a gravity-type two-step mobile search model;

[0062] S300, obtaining a comprehensive evaluation index based on the comprehensive evaluation index model, and determining the best combination of the influencing factors to be analyzed by combining the comprehensive evaluation index with the response surface method;

[0063] S400. Analyze the sensitivity of the influencing factors to be analyzed and obtain analysis results.

[0064] The comprehensive evaluation index model of this application is constructed based on the Shannon diversity index and multi-source index deviation, H = w k S+w j (YA), the comprehensive evaluation index obtained is the response value (comprehensive evaluation index)

[0065] The comprehensive evaluation index model is expressed as follows:

[0066] H=w k S+w j (YA)

[0067] Among them, H represents the value of the comprehensive evaluation index, S represents the Shannon diversity index, A represents the multi-source index deviation, and w k represents the Shannon diversity index weight, w j represents the multi-source index deviation weight, Y represents a constant, S = -∑P v ln(P v ), A=|A' max -A max |+|A' min -A min |+|A' avg -A avg |,P v Indicates the proportion of the number of measurements equal to v to the total number, A' max , A' min and A' avg Respectively represent the maximum, minimum and average values ​​of accessibility measurements; Amax , A min and A avg Represent the maximum, minimum and average values ​​in the validation data respectively.

[0068] Shannon diversity index S can quantitatively describe the distribution of accessibility results from a spatial level, that is, describe the diversity of spatial accessibility results. The larger its value, the more diverse the spatial accessibility results, which reflects that the corresponding spatial accessibility calculation method can better identify the details of accessibility differences between regions; multi-source index deviation A is based on multiple indicators (i.e., maximum value, minimum value and average value) to calculate the absolute difference between the measured value and the verification value and sum them to evaluate the accuracy of spatial accessibility calculation results; H is an indicator used to measure the quality of spatial accessibility results and methods. The Shannon diversity index S and multi-source index deviation A are combined through the entropy weight method to construct a comprehensive evaluation index model. Based on the comprehensive evaluation index model, the comprehensive evaluation index H is obtained as the response value of the response surface method.

[0069] In one embodiment, the influencing factors to be analyzed are determined by a gravity-type two-step moving search model. The gravity-type two-step moving search model is expressed as follows:

[0070]

[0071] Among them, A i is the spatial accessibility measurement value of research object i; S j and C j are the service capability and grade scale of the supplier respectively; D k is the demand of the demand side at k; t ij is the time taken to travel from point i to point j; f(t ij ) distance decay function, β is the distance decay exponent; t0 is the search time range.

[0072] In this invention, the focus is on the sensitivity of three influencing factors: the spatial unit size, the distance decay index (β) in the gravity-type two-step mobile search model, and the search time range (R). The spatial unit size refers to the size of the research object, and the distance decay index (β) and the search time range (R) correspond to the distance decay index β and the search time range t0 in the gravity-type two-step mobile search model, respectively. The remaining variables are measured values ​​and are not subject to human subjective interference, so there is no need to examine their sensitivity.

[0073] In a specific embodiment, a comprehensive evaluation index is obtained based on a comprehensive evaluation index model, and the influencing factors to be analyzed and the optimal combination of the influencing factors to be analyzed are determined by combining the comprehensive evaluation index with the response surface method. The method mainly includes the following steps:

[0074] The steepest climb experiment can quickly find the direction of improving the response value in the experimental design space. It can identify the direction and degree of the maximum change in the response value under the current conditions. In addition, by moving in the direction of the steepest rise / descent, a better value for the response value can be quickly found. This helps to narrow the experimental scope and can approach the local optimal value within a fewer number of experiments, providing guidance for subsequent central composite design experiments. The results of the steepest climb experiment are shown in Table 1:

[0075]

[0076]

[0077] Table 1

[0078] From the results of the steepest climbing experiment, we can see that H is 3.3195, which is the local optimal value, and its corresponding combination of influencing factors is the local optimal combination. The subsequent central composite design experiment is based on the local optimal combination.

[0079] The central composite design experiment is used to explore in detail the changes of the response variables in the local optimal area, which can accurately fit the regression model of the influencing factors and identify the best parameter combination. In addition, the central composite design experiment uses more experimental combination data to capture complex nonlinear relationships, thereby accurately describing the change law of the response value in the experimental space. If the central composite design experiment is carried out directly, a lot of resources and time may be wasted in a larger experimental space. Through the steepest climbing experiment, it can be ensured that the central composite design experiment is concentrated in a more promising area, thereby effectively utilizing experimental resources. The results of the central composite design experiment are shown in Table 2:

[0080]

[0081] Table 2

[0082] Sensitivity analysis of influencing factors mainly includes: variance analysis, regression equation fitting, sensitivity analysis of single (multiple) influencing factors, and drawing contour maps and 3D response surfaces.

[0083] In order to determine whether each component or its combination will affect the response value at different scales, this patent conducted a variance analysis on the results of the central composite design experiment. The unilateral effects of spatial unit size (X1), distance decay index (X2) and search time range (X3) on the comprehensive evaluation index are very significant (P<0.0001), showing strong scale sensitivity. The quadratic term ( as well as ) also had significant effects (P<0.0001), indicating that they are all scale-sensitive. In addition, their bilateral interaction effects (X1X2, X1X3, and X2X3) and their three-way interaction effects (X1X2X3 and ) are highly significant (P<0.05). The results of variance analysis are shown in Table 3:

[0084]

[0085] Table 3

[0086] In one embodiment, analyzing the sensitivity of the influencing factors to be analyzed to obtain the analysis results includes the following steps:

[0087] The regression model of influencing factors was obtained by fitting the comprehensive evaluation index, spatial unit size, distance decay index and search time range;

[0088] Through the influencing factor regression model, the influence degree of the interaction effect of multiple influencing factors on the comprehensive evaluation index is analyzed to obtain the corresponding analysis results;

[0089] The influencing factor regression model is expressed as follows:

[0090]

[0091] Among them, Y represents the comprehensive evaluation index, X1 represents the size of the spatial unit, X2 represents the distance decay index and X3 represents the search time range, A0...A 11 Indicates the corresponding coefficients, and A1>A3>A9>A 11 >A2>A8.

[0092] In one embodiment, the specific coefficients obtained through some data and the equation obtained by fitting are expressed as follows:

[0093]

[0094] In fact, the Y in the formula is the comprehensive evaluation index, which is represented by Y in this regression equation. After obtaining the regression equation between the comprehensive evaluation index and the spatial unit size, distance decay index and search time range, the regression equation can be used to quantitatively describe the correlation between various influencing factors and their interactions on the comprehensive evaluation index.

[0095] The specific analysis is as follows:

[0096] The sensitivity analysis of a single influencing factor is arranged in descending order according to the absolute value of the coefficient: This shows that changing the scale of the spatial unit size has the greatest impact on the comprehensive evaluation index; changes in the search time range also have a significant impact on the comprehensive evaluation index.

[0097] When exploring the influence of the interaction effects of multiple influencing factors on the comprehensive evaluation index H, bilateral interaction effects and trilateral interaction effects are included.

[0098] For the bilateral interaction effect, X1X2 is positive, while X1X3 and X2X3 are negative, indicating that the comprehensive evaluation index increases as the interaction between the spatial unit size and the distance decay index, as well as the interaction between the distance decay index and the search time range, decreases; according to the absolute value of the coefficient, X1X2 and X1X3 are much larger than X2X3, indicating that the bilateral interaction effect combined with X1 is generally larger. When using the gravity-type two-step mobile search model to measure spatial accessibility, more attention should be paid to the spatial unit size of the research object.

[0099] For the three-way interaction effect, its coefficient is positive, which means that the comprehensive evaluation index increases with the enhancement of the three-way interaction; however, the coefficient of the three-way interaction is much smaller than the unilateral effect.

[0100] Based on the above analysis, we can see that the impact of a single influencing factor is greater than that of the bilateral interaction effect and the three-way interaction effect, but the impact of the bilateral interaction effect cannot be ignored (for example, the absolute values ​​of the coefficients of X1X2 and X1X3 are greater than those of X2 and Therefore, in order to optimize the spatial accessibility measurement method, in addition to fully understanding the impact of a single influencing factor, we must also have a deeper understanding of the impact of its combined interaction effect.

[0101] In addition, if Figure 3 (a), (b), (c) and Figure 4 As described in (a), (b), and (c) in Figure 1, the changes of the comprehensive evaluation index with the size of the spatial unit, the distance decay index, and the search time range are intuitively displayed through contour lines and three-dimensional surfaces. Red, green, and blue respectively indicate that the value of the comprehensive evaluation index is high, relatively high, and low, that is, the corresponding spatial accessibility measurement results are good, relatively good, and relatively poor. Contour map (corresponding to Figure 3 (a), (b), (c)) and 3D response surface (corresponding to Figure 4 (a), (b), (c) in the figure.

[0102] In addition, the present invention is described in the form of specific embodiments, see the attached Figure 3As shown, in the steepest climbing experiment, the pixel size ranges from 300m to 800m, with a step length of 100m; the effective service radius of the supplier ranges from 10min to 70min, with a step length of 10min; the distance attenuation index ranges from 0.2 to 2.0, with a step length of 0.2. After using the gravity-type two-step mobile search model to measure the spatial accessibility of these influencing factors under different combinations, the potential center point under the optimal scale is determined by the value of the comprehensive evaluation index. Then, a central composite experiment is carried out based on these center points to obtain 19 groups of experiments composed of these influencing factors under different values, and the comprehensive evaluation index corresponding to each group of experiments is calculated. The rationality of the entire model, single factors and multi-factor interactions is judged by variance analysis, P value and the value of the lack of fit term, and then a comprehensive analysis is carried out using contour lines and three-dimensional response diagrams to obtain the optimal scale combination, and the interaction effect between single factors and multi-factor combinations is explored. The overall technical roadmap of the present invention is shown in the figure. Figure 2 shown.

[0103] Embodiment 2:

[0104] A spatial accessibility factor analysis system based on a two-step mobile search method, such as Figure 5 As shown, it includes a first construction module 100, a first determination module 200, a second determination module 300 and an analysis result module 400;

[0105] The first construction module 100 constructs a comprehensive evaluation index model based on the Shannon diversity index and multi-source index deviation;

[0106] The first determination module 200 is used to determine the influencing factors to be analyzed through a gravity-type two-step moving search model;

[0107] The second determination module 300 obtains a comprehensive evaluation index based on the comprehensive evaluation index model, and determines the best combination of the influencing factors to be analyzed by combining the comprehensive evaluation index with the response surface method;

[0108] The analysis result module 400 is used to analyze the sensitivity of the influencing factors to be analyzed and obtain analysis results.

[0109] Various changes and modifications can be made without departing from the spirit and scope of the present invention, and all equivalent technical solutions also belong to the scope of the present invention.

[0110] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0111] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0112] The present invention is described with reference to the flowcharts and / or block diagrams of the method, terminal device (system), and computer program product according to the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0113] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0115] It should be noted that:

[0116] The "one embodiment" or "embodiment" mentioned in the specification means that the specific features, structures or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present invention. Therefore, the phrases "one embodiment" or "embodiment" appearing in various places throughout the specification do not necessarily refer to the same embodiment.

[0117] In addition, it should be noted that the shapes and names of the parts and components of the specific embodiments described in this specification may be different. Any equivalent or simple changes made based on the structure, features and principles described in the patent concept of the present invention are included in the protection scope of the patent of the present invention. The technicians in the technical field of the present invention can make various modifications or supplements to the specific embodiments described or replace them in a similar manner, as long as they do not deviate from the structure of the present invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A spatial accessibility factor analysis method based on a two-step mobile search method, characterized in that: The following steps are involved: Based on Shannon diversity index and multi-source index deviation, a comprehensive evaluation index model was constructed; Through the gravity-type two-step moving search model, the influencing factors to be analyzed are determined; Based on the comprehensive evaluation index model, the comprehensive evaluation index is obtained, and the best combination of the influencing factors to be analyzed is determined by combining the comprehensive evaluation index with the response surface method; The sensitivity of the influencing factors to be analyzed is analyzed to obtain the analysis results.

2. The spatial accessibility factor analysis method based on the two-step mobile search method according to claim 1 is characterized in that: The comprehensive evaluation index model is expressed as follows: H=w k S+w j (Y-A) Among them, H represents the value of the comprehensive evaluation index, S represents the Shannon diversity index, A represents the multi-source index deviation, and w k represents the Shannon diversity index weight, w j represents the multi-source index deviation weight, Y represents a constant, S = -∑P v ln(P v ), A=|A' max -A max |+|A' min -A min |+|A' avg -A avg |,P v Indicates the proportion of the number of measurements equal to v to the total number, A' max , A' min and A' avg Respectively represent the maximum, minimum and average values ​​of accessibility measurements; A max , A min and A avg Represent the maximum, minimum and average values ​​in the validation data respectively.

3. The spatial accessibility factor analysis method based on the two-step mobile search method according to claim 1 is characterized in that: The method of determining the influencing factors to be analyzed by using the gravity-type two-step moving search model includes the following steps: Construct a gravity-based two-step mobile search model, which is expressed as follows: in, A i represents the spatial accessibility measurement value of research object i, S j represents the service capability of the supplier, C j Indicates the scale of the supplier, D k represents the demand of the demand side at k, t ij represents the time taken to get from point i to point j, f(t ij ) represents the distance decay function, β represents the distance decay exponent, and t0 represents the search time range; Based on the gravity-type two-step mobile search model, the spatial accessibility measurement value is obtained, and the spatial unit size, distance decay index and search time range of the object to be studied are taken as influencing factors to be analyzed.

4. The spatial accessibility factor analysis method based on the two-step mobile search method according to claim 1 is characterized in that: The method of determining the optimal combination of influencing factors to be analyzed by combining the response surface method with comprehensive evaluation indicators comprises the following steps: The direction of the comprehensive evaluation index is determined through the steepest climbing experiment, and the maximum change direction and maximum change degree of the comprehensive evaluation index are determined under the current direction; The central composite design experiment is used to explore in detail the changes of the response variables in the local optimal area, and the regression model of the influencing factors is fitted to determine the optimal parameter combination of the influencing factors to be analyzed.

5. The spatial accessibility factor analysis method based on the two-step mobile search method according to claim 1 is characterized in that: The sensitivity of the influencing factors to be analyzed is analyzed to obtain the analysis results, including the following steps: The regression model of influencing factors was obtained by fitting the comprehensive evaluation index, spatial unit size, distance decay index and search time range; Through the influencing factor regression model, the influence degree of the interaction effect of multiple influencing factors on the comprehensive evaluation index is analyzed to obtain the corresponding analysis results; The influencing factor regression model is expressed as follows: Among them, Y represents the comprehensive evaluation index, X1 represents the size of the spatial unit, X2 represents the distance decay index and X3 represents the search time range, A0...A 11 Indicates the corresponding coefficients, and A1>A3>A9>A 11 >A2>A8.

6. The spatial accessibility factor analysis method based on the two-step mobile search method according to claim 5 is characterized in that: The interaction effects include bilateral interactions and trilateral interactions; When it is a bilateral interaction, the spatial unit size and the distance decay index are positive, the spatial unit size and the search time range, the distance decay index and the search time range are negative, and the comprehensive evaluation index increases as the interaction effect of the spatial unit size and the distance decay index and the interaction effect of the distance decay index and the search time range decreases; When all coefficients are positive for bilateral interactions, the comprehensive evaluation index increases with the enhancement of the trilateral interaction effect.

7. The spatial accessibility factor analysis method based on the two-step mobile search method according to claim 5 is characterized in that: The following steps are also included: The influence of a single influencing factor on the comprehensive evaluation index is analyzed. Specifically, when the size of the spatial unit is changed, the impact on the comprehensive evaluation index is the greatest; when the search time range is changed, the impact on the comprehensive evaluation index is second only to the impact of changing the size of the spatial unit.

8. A spatial accessibility factor analysis system based on a two-step mobile search method, characterized in that: It includes a first construction module, a first determination module, a second determination module and an analysis result module; The first construction module constructs a comprehensive evaluation index model based on the Shannon diversity index and multi-source index deviation; The first determination module is used to determine the influencing factors to be analyzed through a gravity-type two-step moving search model; The second determination module obtains a comprehensive evaluation index based on the comprehensive evaluation index model, and determines the influencing factors to be analyzed and the optimal combination of the influencing factors to be analyzed by combining the comprehensive evaluation index through the response surface method; The analysis result module is used to analyze the sensitivity of the influencing factors to be analyzed and obtain analysis results.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A spatial accessibility factor analysis device based on a two-step mobile search method, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images