Method for identifying and configuring micro school-route environment types based on children's multi-dimensional perception

Abstract

The present invention discloses a method for identifying and configuring micro school commuting environment types based on children's multi-dimensional perception, including: constructing several theoretical micro school commuting paths according to the micro school commuting environment and commuting environment data; calculating children's actual micro school commuting paths to determine the commuting environment data actually used by children; obtaining children's perception data in three dimensions; using the perception data of all children as the dependent variable and the commuting environment data actually used as the independent variable to construct a multiple linear regression model for correlation analysis and matching, identifying the key influencing factors in the commuting environment data; performing clustering identification on the key influencing factors in the micro school commuting environment to identify the children's perception paths to be configured; performing targeted configuration and update on the children's perception paths to be configured, so as to realize the adjustment and optimization of the micro school commuting environment in the target school district. The method of the present invention completes the identification of micro school commuting environment types based on children's perception, and can improve the accuracy and comprehensiveness of type identification.

Description

Technical Field

[0001] The present invention relates to the technical fields of big data and urban renewal, and particularly relates to a method for identifying and configuring micro school-route environment types based on children's multi-dimensional perception. Background Art

[0002] The school-route behavior refers to the dynamic behavior process of children going to school and coming home from school, and essentially is a necessary commuting behavior. However, in the actual school-route process, children have diverse social activities: such as stopping, observing, socializing, etc., which also stimulate complex perception types: such as self-efficacy perception of children's psychological independence ability, children's sense of security perception, affordance perception of children's social interaction willingness, etc.

[0003] The school-route environment is a linear built path closely related to children's school-route behavior. The micro school-route environment is the path segment around primary schools, providing a service public space for children to use when going to school and coming home from school. It is a high-frequency place for children's daily travel activities and plays an important role in shaping the healthy development of children's perception. In the context of urban renewal and the construction of child-friendly cities, the micro school-route environment is an important starting point for space renewal. Depicting children's needs through their school-route perception is the key point and difficulty of the renewal implementation: understanding children's psychological needs and capturing the key elements affecting perception, so as to refine the delineation of the renewal area and direction of the micro school-route environment is the practical path to achieve people-oriented urban renewal.

[0004] However, the existing micro school-route environment types and configuration schemes still have the following problems: 1) The existing identification of micro school-route environment types mostly depends on the environmental types of their affiliated streets. For example, traffic-type streets - traffic-type micro school-route environments. In the classification process, the perspective of children as the main body is ignored, and the corresponding configuration methods cannot directly respond to children's environmental needs. 2) Most of the environmental type identification methods for children's perception adopt the path of "single-dimensional perception - type identification". This path lacks consideration of the comprehensive perception process of children, ignores the superposition and mutual exclusion processes of children's multi-dimensional perception, resulting in the "one-sidedness" and "singularity" of the micro school-route environment configuration. 3) In terms of the consideration of technical details, the identification method usually establishes a "general association" between children's perception and school-route environment data, lacking an "individualized" and "path-based" description of the school-route environment actually used by children, resulting in fuzzy association results, unable to directly guide the delineation of the area for school-route environment configuration, and lacking pertinence. The above problems lead to a single analysis dimension and poor accuracy in the process of identifying micro school-route environment types based on children's perception, unable to formulate a micro-environment configuration scheme of "determining the type, delimiting the domain, and determining the direction", and lacking the feasibility of renewal implementation. Summary of the Invention

[0005] In view of the deficiencies of the above-mentioned prior art, the technical problem to be solved by the present invention is: how to provide a method for identifying and configuring the types of micro school-route environments based on children's multi-dimensional perception, by depicting the actual school-route environments used by each child, matching the multi-dimensional school-route perception data of each child, establishing a multiple linear regression model between children's multi-dimensional perception and school-route environments, so as to delimit the types of micro school-route environments according to the associated factors affecting perception and formulate a differential configuration plan for micro school-route environments.

[0006] To solve the above technical problems, the present invention adopts the following technical solutions:

[0007] A method for identifying and configuring the types of micro school-route environments based on children's multi-dimensional perception includes:

[0008] S1: Obtain the micro school-route environment of the target school district and the actual travel data of all children;

[0009] S2: Construct several theoretical micro school-route paths according to the micro school-route environment and obtain the school-route environment data of each theoretical micro school-route path;

[0010] S3: Calculate the actually used micro school-route paths according to the actual travel data of children, and then determine the school-route environment data actually used by children by the proportion of each theoretical micro school-route path in the actually used micro school-route paths;

[0011] S4: Obtain the perception data of three dimensions: children's self-efficacy perception, sense of security perception, and affordance perception;

[0012] S5: Construct a multiple linear regression model with the perception data of all children as the dependent variable and the actually used school-route environment data as the independent variable;

[0013] S6: Conduct a correlation analysis and matching on the perception data and school-route environment data through the multiple linear regression model to identify the key influencing factors in the school-route environment data;

[0014] S7: Conduct a clustering identification on the key influencing factors in the micro school-route environment to identify the children's perception paths to be configured in the micro school-route environment;

[0015] S8: Conduct targeted configuration and update on the children's perception paths to be configured to realize the adjustment and optimization of the micro school-route environment of the target school district.

[0016] Preferably, in step S2, the theoretical micro school-route paths are constructed through the following steps:

[0017] S201: Retrieve the grid data of the school district management unit from the micro school-route environment of the target school district;

[0018] S202: Extract the geographical coordinates of residential areas and school gate entrances from the grid data of the school district management unit;

[0019] S203: Obtain the walking route planning from the school gate entrance to the residential area as the theoretical micro commuting path.

[0020] Preferably, in step S2, the commuting environment data of the micro commuting path includes data of any one or more dimensions among spatial scale, spatial facilities, spatial functions, and landscape environment;

[0021] The data of the spatial scale dimension includes path continuity and / or path carrying capacity;

[0022] The data of the spatial facilities dimension includes motor vehicle traffic exposure during commuting hours, pedestrian-vehicle separation facilities, and / or night light intensity;

[0023] The data of the spatial function dimension includes interface transparency, children's facility density, and / or children's facility diversity;

[0024] The data of the landscape environment dimension includes green view rate, sky openness, and / or street noise.

[0025] Preferably, in step S2, a sample point is set at a preset distance interval on the theoretical micro commuting path, and the commuting environment data at the sample point is obtained; the average value of the commuting environment data at all sample points is used as the commuting environment data of the corresponding theoretical micro commuting path;

[0026] Among them, each item of data in the commuting environment data at the sample point is calculated by the following formula:

[0027] 1) Path continuity

[0028]

[0029] In the formula: Connect represents the path continuity of the sample point; W yx represents the path length from the sample point to the effective walking space of the school gate; l represents the actual path length from the sample point to the school gate;

[0030] 2) Path carrying capacity

[0031]

[0032] In the formula: Capacity represents the path carrying capacity of the sample point; S i represents the area from the curb edge line to the building edge line within the interval between adjacent sample points; sl represents the actual length of the interval between adjacent sample points;

[0033] 3) Motor vehicle traffic exposure

[0034]

[0035] Where: Exposure represents the motorized traffic exposure during the school commute period of the sample point; H yd represents the length of the congested section; sl represents the actual length of the interval between adjacent sample points;

[0036] 4) Pedestrian-vehicle separation facilities

[0037]

[0038] Where: SF represents the completeness of the pedestrian-vehicle separation facilities at the sample point; lf represents the length occupied by the pixels of the pedestrian-vehicle separation facilities in the street view image; Gl represents the length of the street view image;

[0039] 5) Nighttime light intensity

[0040]

[0041] Where: Light represents the nighttime light intensity of the sample point; ∑lg represents the sum of the nighttime light raster pixel values in the buffer area of the sample point; sl represents the actual length of the interval between adjacent sample points; l represents the actual length of the buffer area of the sample point;

[0042] 6) Interface transparency

[0043]

[0044] Where: Pratio represents the interface transparency of the sample point; P zp represents the number of pixels of the vitreous body in the street view image; S ZP represents the total number of pixels in the street view image;

[0045] 7) Children's facility density

[0046]

[0047] Where: DP represents the children's facility density of the sample point; Nump represents the number of points of interest of all parent-child facility types and children's facility types within the buffer range of the sample point; sl represents the actual length of the interval between adjacent sample points;

[0048] 8) Children's facility diversity

[0049]

[0050] Where: DV represents the children's facility diversity of the sample point; pi represents the proportion of the number of children's facilities of the i-th type of point of interest in the buffer area of the sample point to the total number of points of interest;

[0051] 9) Green view rate

[0052]

[0053] Where: Greenratio represents the green view ratio of the sample point; G zp represents the number of pixels of green plants in the street view image of the sample point; S ZP represents the total number of pixels of the street view image;

[0054] 10) Sky openness

[0055]

[0056] Where: Skyratio represents the sky openness of the sample point; S 2p represents the number of pixels of the sky in the street view image of the sample point; S ZP represents the total number of pixels of the street view image of the sample point;

[0057] 11) Street noise

[0058]

[0059] Where: RT represents the street noise of the sample point; ∑Rg represents the equivalent sound level within the adjacent sample point interval; sl represents the actual length of the adjacent sample point interval.

[0060] Preferably, in step S3, the data of the commuting environment actually used by children is calculated through the following steps:

[0061] S301: Obtain the school gate point coordinates, and obtain the actual residential area point coordinates and passing point coordinates according to the actual travel data of the children;

[0062] S302: Taking the school gate entrance point coordinates as the starting point, the actual residential area point coordinates of the children as the end point, and the passing point coordinates as the intermediate points, construct the actual micro commuting path used by the children;

[0063] S303: Match the actual micro commuting path used by the children with all the theoretical micro commuting paths, and determine the proportion of each theoretical micro commuting path involved in the actual micro commuting path;

[0064] S304: Through the proportion of each theoretical micro commuting path in the actual micro commuting path, calculate the data of the commuting environment actually used by all children in combination with the following formula;

[0065] Ti = k1*r1 + k2*r2,…,kn*rn, 0 ≤ n;

[0066] Where: Ti represents the data of the commuting environment actually used by the i-th child; r1 to rn represent the commuting environment data of the 1st to the nth theoretical micro commuting paths; k1 to kn represent the proportion of each theoretical micro commuting path in the actual micro commuting path.

[0067] Preferably, in step S4, the perception data of children includes self-efficacy perception data, sense of security perception data, and / or affordance perception data;

[0068] The self-efficacy perception data includes the efficacy level of children's independent school commuting, the efficacy level of children's overcoming environmental obstacles, and / or the efficacy level of children's self-adjustment;

[0069] The sense of security perception data includes the sense of security perception level during commuting and / or the sense of security perception level when encountering strangers;

[0070] The affordance perception data includes the affordance perception level during commuting and / or the affordance perception level in social interactions.

[0071] Preferably, in step S4, the perception data of children is obtained through a questionnaire survey, and at the same time, the numerical value of the children's perception level is evaluated by a Likert five-level perception scale to realize the quantification of the perception data.

[0072] Preferably, in step S5, the perception data of all children is input into the modeling software. Through the modeling software, the commuting environment data actually used by all children is used as the independent variable, and the self-efficacy perception data, sense of security perception data, and affordance perception data in the perception data of all children are used as the dependent variables respectively to construct three multiple linear regression models;

[0073] The formula of the multiple linear regression model is expressed as follows:

[0074]

[0075] In the formula: y 1 , y 2 , y 3 respectively represent the self-efficacy perception data, sense of security perception data, and affordance perception data in the perception data; x 1 to x 11 respectively represent the path continuity, path carrying capacity, motor vehicle traffic exposure, pedestrian-vehicle separation facilities, night light intensity, interface transparency, children's facility density, children's facility diversity, green view rate, sky openness, and street noise in the commuting environment data; β 0 represents the intercept term of the model; β 1 , β 2 ,…β 11 represent the regression coefficients of their respective independent variables.

[0076] Preferably, in step S6, first, obtain the significance level, i.e., the p-value, of each school commuting environment data in the three multiple linear regression models in the modeling software; then, regard the school commuting environment data with a p-value less than the preset value as having a significant correlation with the corresponding perception data; next, judge the influence direction of the school commuting environment data on the perception data according to the regression coefficient of the school commuting environment data: if the regression coefficient is positive, the influence direction of the corresponding school commuting environment data on the perception data is positive, otherwise it is negative; finally, determine the key influencing factors according to the significant correlation and influence direction between the school commuting environment data and the perception data;

[0077] The key influencing factors include comprehensive influencing factors, single influencing factors, and / or mutually exclusive influencing factors;

[0078] Comprehensive influencing factor: Environmental data in the school commuting environment that has a significant positive correlation with two or more types of perception data;

[0079] Single influencing factor: Environmental data in the school commuting environment that has a significant correlation with a single type of perception data;

[0080] Mutually exclusive influencing factor: Environmental data in the school commuting environment that has a positive correlation with one type of perception data and a negative correlation with another type of perception data.

[0081] Preferably, in step S7, it specifically includes the following steps:

[0082] 1) In the micro school commuting environment of the target school district, extract the area with the preset percentage before the positive distribution of the comprehensive influencing factor as the school commuting path of the child perception hot spot type;

[0083] 2) In the micro school commuting environment of the target school district, extract the area with the preset percentage after the negative distribution of the single influencing factor as the school commuting path of the child perception improvement type;

[0084] 2.1) In the school commuting path of the child perception improvement type, the area that has a single influence on the self-efficacy perception data of the child and is in the area with the preset percentage after the negative distribution within the area is the school commuting path of the child efficacy improvement;

[0085] 2.2) In the school commuting path of the child perception improvement type, the area that has a single influence on the sense of security perception data of the child and is in the area with the preset percentage after the negative distribution within the area is the school commuting path of the child safety improvement;

[0086] 2.3) In the school commuting path of the child perception improvement type, the area that has a single influence on the affordance perception data of the child and is in the area with the preset percentage after the negative distribution within the area is the school commuting path of the child activity improvement;

[0087] 3) In the micro school commuting environment of the target school district, extract the school commuting path of the child perception contradiction type through the following steps:

[0088] 3.1) Draw a binary scatter fitting graph of the school commuting environment data and the corresponding perception data with mutually exclusive influences based on the mutually exclusive influencing factors;

[0089] 3.2) Extract the optimal distribution threshold interval of the school commuting environment data with mutually exclusive influences from the binary scatter fitting graph;

[0090] 3.3) Calculate the degree of deviation between the mutually exclusive influencing factors and the optimal threshold interval in the micro school commuting path;

[0091] 3.4) In the micro school commuting environment of the target school district, extract the area with the preset percentage of the degree of deviation of the mutually exclusive influencing factors as the children's perception - contradictory school commuting path.

[0092] Compared with the prior art, the method for identifying and configuring the micro school commuting environment types based on children's multi - dimensional perception in the present invention has the following beneficial effects:

[0093] 1) By analyzing the actual travel data of children, the present invention depicts the micro school commuting paths actually used by children; establishes a school commuting environment database for the theoretical micro school commuting paths, and determines the school commuting environment actually used by each child through the comparison of "actual and theoretical", improving the pertinence and accuracy of the description of the micro school commuting environment.

[0094] 2) By obtaining children's perception data from multiple dimensions, the present invention expands the technical limitations of children's single - dimension perception and the school commuting environment. Based on the theory of children's cognitive development, it measures children's self - efficacy perception, sense of security perception, and affordance perception, achieving a comprehensive and all - round assessment of children's mental health and providing a multi - perspective view for the identification of micro school commuting environment types.

[0095] 3) The present invention establishes a multiple linear regression model of children's multi - dimensional perception and the school commuting environment, and delimits the micro school commuting environment types according to the associated factors affecting perception. During the identification process, it considers the mutually exclusive influence, single influence, and comprehensive influence processes between multi - dimensional perception and the school commuting environment, and feeds them back to the clustering process, realizing the identification of micro school commuting environment types based on children's multi - dimensional perception, delimiting the boundaries of different environment types, and further guiding the update direction.

[0096] 4) The present invention establishes a differential environment configuration plan according to the types of micro school commuting environments: formulates the environment configuration plans for the areas of perception - hot - spot school commuting paths, children's perception - enhanced school commuting paths, and children's perception - contradictory school commuting paths, realizing the refined and targeted optimization of the micro school commuting environment based on children's multi - dimensional perception, and having strong implementation feasibility. Description of the Drawings

[0097] To make the objectives, technical solutions and advantages of the invention more clear, the following will further describe the present invention in detail with reference to the accompanying drawings, where:

[0098] Figure 1 is a logic block diagram of a method for identifying and configuring micro school commuting environment types based on children's multi-dimensional perception;

[0099] Figure 2 is a schematic diagram of partial school commuting environment data;

[0100] Figure 3 is a geographical information set based on micro school commuting paths;

[0101] Figure 4 is a schematic diagram of a children's actual usage route map;

[0102] Figure 5 is a binary scatter plot fitting graph of green view rate and affordance perception data;

[0103] Figure 6 is a binary scatter plot fitting graph of green view rate and self-efficacy perception data;

[0104] Figure 7 is a schematic diagram of a school commuting perception path to be configured and its type;

[0105] Figure 8 is a schematic diagram of the identification and configuration of the micro school commuting environment type of Primary School Y. Specific Embodiments

[0106] To make the objectives, technical solutions and advantages of the embodiments of the present invention more clear, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Generally, the components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0107] The following will be further described in detail through specific embodiments:

[0108] Embodiment:

[0109] This embodiment discloses a method for identifying and configuring micro school commuting environment types based on children's multi-dimensional perception.

[0110] As Figure 1As shown, a method for identifying and configuring micro school commuting environment types based on children's multi-dimensional perception includes:

[0111] S1: Obtain the micro school commuting environment of the target school district and the actual travel data of all children;

[0112] S2: Construct several theoretical micro school commuting paths based on the micro school commuting environment and obtain the commuting environment data of each theoretical micro school commuting path;

[0113] S3: Calculate the actually used micro school commuting paths according to the actual travel data of children, and then determine the commuting environment data actually used by children by the proportion of each theoretical micro school commuting path in the actually used micro school commuting paths;

[0114] S4: Obtain the perception data of three dimensions: children's self-efficacy perception, sense of security perception, and affordance perception;

[0115] S5: Construct a multiple linear regression model with the perception data of all children as the dependent variable and the actually used commuting environment data as the independent variable;

[0116] S6: Conduct a correlation analysis and matching on the perception data and the commuting environment data through the multiple linear regression model to identify the key influencing factors in the commuting environment data;

[0117] S7: Conduct a clustering identification on the key influencing factors in the micro school commuting environment to identify the children's perception paths to be configured in the micro school commuting environment;

[0118] S8: Conduct targeted configuration and update on the children's perception paths to be configured to realize the adjustment and optimization of the micro school commuting environment of the target school district.

[0119] The method for identifying and configuring micro school commuting environment types of the present invention has the following beneficial effects:

[0120] 1) By analyzing the actual travel data of children, the present invention depicts the actually used micro school commuting paths of children; establishes a commuting environment database for theoretical micro school commuting paths, and determines the commuting environment actually used by each child through the comparison of "actual and theoretical", improving the pertinence and accuracy of the description of the micro school commuting environment.

[0121] 2) By obtaining the perception data of multiple dimensions of children, the present invention expands the technical limitations of the single-dimensional perception of children and the commuting environment. Based on the theory of children's cognitive development, it measures children's self-efficacy perception, sense of security perception, and affordance perception, realizing a comprehensive and all-round evaluation of children's mental health and providing a multi-dimensional perspective for the identification of micro school commuting environment types.

[0122] 3) The present invention establishes a multiple linear regression model for children's multi-dimensional perception and the micro school-route environment, and delimits the types of micro school-route environments according to the associated factors affecting perception. During the recognition process, the mutually exclusive effects, single effects, and comprehensive effects between multi-dimensional perception and the school-route environment are considered and fed back into the clustering process, realizing the recognition of the types of micro school-route environments based on children's multi-dimensional perception, the delimitation of the boundaries of different environmental types, and further guiding the update direction.

[0123] 4) The present invention establishes a differential environmental configuration plan according to the types of micro school-route environments: formulates the environmental configuration plans for the areas of the school-route with perception hotspots, the school-route for enhancing children's perception, and the school-route with contradictory children's perception, realizing the refined and targeted optimization of the micro school-route environment based on children's multi-dimensional perception, and having strong implementation feasibility.

[0124] To better introduce the technical solution of the present invention, this embodiment is introduced through the following several parts.

[0125] I. Theoretical micro school-route

[0126] Specifically, in step S2, the theoretical micro school-route is constructed through the following steps:

[0127] S201: Retrieve the grid data of the school district management unit from the micro school-route environment of the target school district;

[0128] S202: Extract the geographical coordinates of the residential area and the school gate entrance from the grid data of the school district management unit;

[0129] S203: Obtain the walking planning route with the school gate entrance as the starting point and the residential area as the ending point as the theoretical micro school-route.

[0130] In this embodiment, based on the ArcGIS platform, the primary school service area is drawn and overlaid and analyzed with the Gaode walking planning route, so as to obtain the relevant geographical information data of the micro school-route of the primary school.

[0131] II. School-route environment data

[0132] In this embodiment, the school-route environment data of the micro school-route includes data in multiple dimensions such as spatial scale, spatial facilities, spatial functions, and landscape environment. The data in the spatial scale dimension includes path continuity and path carrying capacity; the data in the spatial facilities dimension includes motor vehicle exposure during school-route periods, pedestrian-vehicle separation facilities, and night light intensity; the data in the spatial functions dimension includes interface transparency, children's facility density, and children's facility diversity; the data in the landscape environment dimension includes green view rate, sky openness, and street noise. Some of the school-route environment data is as Figure 2 shown.

[0133] The applicant's research found that the above multi-dimensional data is often used to describe the key features of the school travel environment in research and is a practical starting point for the path configuration and optimization of the school travel environment. The spatial scale can intuitively reflect the layout and morphological characteristics of the walking path, and the spatial facilities are an important guarantee for children's walking safety and the order of people and vehicles. On the one hand, the spatial function supports the diversity of children's activity behaviors during school travel. The spatial function is reflected in the social supervision of children's walking by the "street eyes". The richer the spatial function, the more "street eyes", and the higher the interaction frequency between children and the street environment. The street view images and street noises in the landscape environment can reflect children's spatial feelings at the visual and auditory levels. On the other hand, this data has the advantages of "large scale, accessible, and refined", providing more accurate and diversified spatial information, supporting more complex correlation models, and supporting intelligent decision-making judgments.

[0134] Specifically, a sample point is set at every preset distance (set to 50 meters to 100 meters in this embodiment) on the theoretical micro school travel path, and the school travel environment data at the sample point is obtained; the average value of the school travel environment data at all sample points is used as the school travel environment data corresponding to the theoretical micro school travel path, forming a geographic information set based on the micro school travel path, as Figure 3 shown.

[0135] Calculate each item of data in the school travel environment data at the sample point through the following formula:

[0136] 1) Path continuity

[0137]

[0138] In the formula: Connect represents the path continuity of the sample point; W yx represents the path length from the sample point to the effective walking space of the school gate (width greater than or equal to 1.5 meters in this embodiment); l represents the actual path length from the sample point to the school gate;

[0139] 2) Path carrying capacity

[0140]

[0141] In the formula: Capacity represents the path carrying capacity of the sample point; S i represents the area from the curbstone edge line to the building edge line within the interval between adjacent sample points; sl represents the actual length of the interval between adjacent sample points;

[0142] 3) Motor vehicle exposure

[0143]

[0144] In the formula: Exposure represents the motor vehicle exposure during the school travel period of the sample point; H ydIndicates the length of the congested section; sl indicates the actual length of the adjacent sample point interval;

[0145] Among them, for the length of the congested section, on the Amap Open Platform, the API interface is retrieved, and a traffic real-time situation collection program is written in Python. The traffic real-time situation map application apkey is used as the user access key (ak) parameter; the "longitude" and "latitude" of the vector point graphic "school commuting environment sample point.shp" are used as the traffic situation location parameter; the "average speed" field of the sample points passed during the school commuting period is obtained; the construction line tool is used to identify the sample points with an average speed ≤ 6 m / s and generate a path; the length of the generated path is statistically calculated as the length of the congested path.

[0146] 4) Pedestrian and vehicle separation facilities

[0147]

[0148] In the formula: SF represents the completeness of the pedestrian and vehicle separation facilities at the sample point; lf represents the length occupied by the pixels of the pedestrian and vehicle separation facilities in the street view image; Gl represents the length of the street view image;

[0149] 5) Nighttime light intensity

[0150]

[0151] In the formula: Light represents the nighttime light intensity of the sample point; ∑lg represents the sum of the nighttime light raster pixel values in the buffer area of the sample point; sl represents the actual length of the adjacent sample point interval; l represents the actual length of the buffer area of the sample point;

[0152] The method for obtaining the nighttime light raster pixel value: Obtain the raster of the Luojia-1 nighttime light image (LJ1-01) on the Hubei Data and Application Network of the High-Resolution Earth Observation System (www.hbeos.rog.cn); use the nearest neighbor method in the ArcGIS platform to extract the "nighttime light raster pixel value" at the "longitude" and "latitude" positions corresponding to the sample points; use the add field tool to add the "nighttime light raster pixel value" attribute field to the vector point graphic "school commuting environment sample point.shp".

[0153] 6) Interface transparency

[0154]

[0155] In the formula: Pratio represents the interface transparency of the sample point; P zp represents the number of pixels of the vitreous body in the street view image; S ZP represents the total number of pixels of the street view image;

[0156] The method for obtaining the number of vitreous pixels is as follows: a street view batch collection program is written in Python, and apkey is used as the user access key (ak) parameter for the panoramic static image of the Baidu map open platform; the "longitude" and "latitude" of the "school environment sample point.shp" are used as the location parameters of the panoramic point respectively; a street view panoramic image with a head-on perspective, a field of view of 360 degrees, and a photo height and width of 1024:512 pixels respectively is obtained for each sampling point; the image processing OpenCV tool is used to apply edge detection, and the closed contour of the vitreous body is screened out through the "strong edge" and "high reflection" conditions; the number of pixels within the closed contour in the street view image is calculated.

[0157] 7) Density of children's facilities

[0158]

[0159] Where: DP represents the density of children's facilities at the sample point; Nump represents the number of points of interest (POI) of all Baidu parent-child facilities and children's facilities within the buffer range of the sample point; sl represents the actual length of the interval between adjacent sample points;

[0160] The method for obtaining POIs (points of interest) of parent-child facilities and children's facilities is as follows: in the Baidu Map or Amap open platform, call the API interface, use the "longitude" and "latitude" of the vector point graphic "school environment sample point.shp" as the location parameters, obtain the POI (points of interest) data around the sample point, and filter and count: the number and sum of the second-level classification points of interest of parent-child facilities and children's facilities under the first-level categories of life services and cultural education.

[0161] 8) Diversity of children's facilities

[0162]

[0163] Where: DV represents the diversity of children's facilities at the sample point; Pi represents the proportion of the number of children's facilities at the i-th interest point in the sample point buffer zone to the total number of interest points;

[0164] 9) Green View Rate

[0165]

[0166] Where: Greenratio represents the green viewing rate of the sample point; G zp represents the number of pixels of green plants in the street view image of the sample point; S ZP Represents the total number of pixels in the street view image;

[0167] 10) Sky openness

[0168]

[0169] In the formula: Skyratio represents the sky openness of the sample point; S zp represents the number of pixels of the sky in the street view image of the sample point; S ZP represents the total number of pixels of the street view image of the sample point;

[0170] 11) Street noise

[0171]

[0172] In the formula: RT represents the street noise of the sample point; ∑Rg represents the equivalent sound level within the adjacent sample point interval; sl represents the actual length of the adjacent sample point interval;

[0173] Among them, the equivalent sound level is measured using an AWA6228 + Class I sound level meter for the equivalent sound level during the school commute period of the sample point, and a G659 plus type GPS (positioning accuracy RTK ≤ 0.1 m) is used for "geographic information marking" of the sample point; on the ArcGIS platform, the spatial join tool is used to match the "geographic information marking" with the "longitude" and "latitude" of the sample point; the add field tool is used to add a street noise attribute field to the vector point graphic "school commute environment sample point.shp".

[0174] Combined with Table 1, the school commute environment data of the theoretical micro school commute path is as follows:

[0175] Table 1

[0176]

[0177]

[0178] III. School commute environment data actually used by children

[0179] Specifically, in step S3, the school commute environment data actually used by children is calculated through the following steps:

[0180] S301: Obtain the school gate point coordinates, and obtain the actual residential area point coordinates and passing point coordinates according to the actual travel data of the children;

[0181] In this embodiment, the actual travel data of the children includes the gender, age, residential area, daily after-school passing points, and / or school commute travel mode (walking / motorized traffic / bus) of the children. Semantic recognition is performed on the actual travel data of the children, and the actual travel data of the children with travel modes of taking motor vehicles and buses is screened and excluded.

[0182] S302: Taking the coordinates of the school gate entrance point as the starting point, the coordinates of the actual residential area point of the child as the end point, and the coordinates of the passing points as the intermediate points, (combining the road topological network and based on the ArcGIS platform) construct the microscopic commuting path actually used by the child;

[0183] S303: Match the microscopic commuting path actually used by the child with all the theoretical microscopic commuting paths, and determine the proportion of each theoretical microscopic commuting path involved in the actually used microscopic commuting path;

[0184] S304: Through the proportion of each theoretical microscopic commuting path in the actually used microscopic commuting path, combined with the following formula (using the principle of maximizing co-occurrence to match the actually used commuting environment data for each child) to calculate the actually used commuting environment data for all children;

[0185] Ti = k1 * r1 + k2 * r2, …, kn * rn, 0 ≤ n;

[0186] In the formula: Ti represents the commuting environment data actually used by the i-th child; r1 to rn represent the commuting environment data of the 1st to the nth theoretical microscopic commuting paths; k1 to kn represent the proportion of each theoretical microscopic commuting path in the actually used microscopic commuting path.

[0187] Take Figure 4 as an example. The actual microscopic commuting path of the i-th child involves three theoretical microscopic commuting paths, and the proportions in the three theoretical microscopic commuting paths are 70%, 10%, and 25% respectively (another 5% does not belong to any theoretical microscopic commuting path). Among them, the commuting environment data (matrix) of the three theoretical microscopic commuting paths are r1, r2, and r4 respectively. Then the commuting environment data actually used by this child is expressed as: Ti = 70% * r1 + 10% * r2 + 25% * r4.

[0188] IV. Perception data of children

[0189] Specifically, in step S4, the perception data of children includes self-efficacy perception data, sense of security perception data, and affordance perception data; obtain the perception data of children through questionnaire surveys, and at the same time use the Likert five-level perception scale to evaluate the numerical value of the children's perception level to achieve the quantification of perception data.

[0190] The three perception dimensions used in the present invention cover the children's psychological independence ability, emotional stability, and perception willingness of social interaction; the three perception dimensions can comprehensively and all-round evaluate the mental health of children, so as to coordinately configure the commuting environment elements, which helps to construct a commuting environment with a comprehensive positive perception for children.

[0191] 1. Self-efficacy perception data

[0192] Self-efficacy perception data includes the efficacy level of children commuting to school independently, the efficacy level of children overcoming environmental obstacles, and the efficacy level of children's self-adjustment; self-efficacy perception represents an individual's confidence and belief in completing specific tasks or behaviors. During the process of commuting to school, self-efficacy represents the degree of confidence of children in getting rid of parental dependence and independently overcoming path obstacles, which is an objective reflection of children's psychological independence.

[0193] Self-efficacy mainly includes three aspects: the efficacy level of children commuting to school independently, the efficacy level of children overcoming environmental obstacles, and the efficacy level of children's self-adjustment. As shown in Table 2, the Likert 5-level perception scale is used to evaluate the perception level of children's self-efficacy. The overall evaluation of children's self-efficacy perception takes the average value of the above three aspects.

[0194] Table 2

[0195]

[0196] 2. Sense of security perception data

[0197] Sense of security perception data includes the sense of security perception level during passage and / or the sense of security perception level when encountering strangers; a sense of security is a subjective judgment of the prediction of external risk factors and environmental pressure. During the process of commuting to school, children may encounter physical risks such as falling and bumping, and at the same time, it also includes the fear and anxiety of being victimized after meeting strangers.

[0198] Sense of security perception mainly includes two aspects: the sense of security perception level during passage and the sense of security perception level when encountering strangers. As shown in Table 3, the Likert 5-level perception scale is used to evaluate the perception level of children's sense of security. The evaluation of children's sense of security perception takes the average value of the above two aspects.

[0199] Table 3

[0200]

[0201]

[0202] 3. Affordance perception data

[0203] Affordance perception data includes the affordance perception level during passage and / or the affordance perception level in social interactions. Affordance perception is the cognitive situation of the maturity of conditions for an individual to carry out activities in the environment. During the process of commuting to school, the main types of children's activities can be mainly divided into two categories: passage activities and social activities. Therefore, affordance perception mainly includes two aspects: the affordance perception level during passage and the affordance perception level in social interactions. As shown in Table 4, the Likert 5-level perception scale is used to evaluate the perception level of children.

[0204] Table 4

[0205]

[0206] V. Multiple Linear Regression Model

[0207] Specifically, in S5, first establish an associated database of children's multi-dimensional perception evaluation and the actual micro school commuting environment used, as shown in Table 5.

[0208] Table 5

[0209]

[0210]

[0211] Then, input the perception data of all children into Matlab software. Using Matlab software, take the data of the school commuting environment actually used by all children as independent variables, and take the self-efficacy perception data, sense of security perception data, and affordance perception data in the perception data of all children as dependent variables respectively to construct three multiple linear regression models;

[0212] The formula of the multiple linear regression model is expressed as follows:

[0213]

[0214] In the formula: y 1 , y 2 , y 3 respectively represent the self-efficacy perception data, sense of security perception data, and affordance perception data in the perception data; x 1 to x 11 respectively represent the path continuity, path carrying capacity, motor traffic exposure, pedestrian-vehicle separation facilities, night light intensity, interface transparency, children's facility density, children's facility diversity, green view rate, sky openness, and street noise in the school commuting environment data; β 0 represents the intercept term of the model; β 1 , β 2 ,…β 11 represent the regression coefficients of their respective independent variables.

[0215] VI. Key Influencing Factors

[0216] Specifically, in S6, based on Matlab software, analyze the fitting situation of each model according to the mean square error (MSE) / root mean square error (rMSE). The smaller the mean square error (MSE) / root mean square error (rMSE), the better the fitting situation (in this embodiment, it is set that when MSE is less than 0.09 and RMSE is less than 0.3, it is considered that the fitting situation is good).

[0217] Under the condition of good model fitting, first obtain the significance level, i.e., the p-value, of each school travel environment data in the three multiple linear regression models in Matlab software; then consider the school travel environment data with a p-value less than the preset value (set to 0.05) as having a significant correlation with the corresponding perception data; and then according to the regression coefficients β 1 , β 2 , … β 11 Judge the influence direction of the school travel environment data on the perception data: if the regression coefficient is positive, the influence direction of the corresponding school travel environment data on the perception data is positive, otherwise it is negative; finally, determine the key influencing factors according to the significant correlation and influence direction between the school travel environment data and the perception data.

[0218] The key influencing factors include comprehensive influencing factors, single influencing factors, and / or mutually exclusive influencing factors;

[0219] Comprehensive influencing factors: Environmental data in the school travel environment data that have a significant positive correlation with two or more types of perception data.

[0220] Single influencing factors: Environmental data in the school travel environment data that have a significant correlation with a single type of perception data.

[0221] Mutually exclusive influencing factors: Environmental data in the school travel environment data that have a positive correlation with one type of perception data and a negative correlation with another type of perception data.

[0222] In this embodiment, the key influencing factors can be determined by establishing a differential ranking map. The differential ranking map is a commonly used tool for systematically analyzing and displaying multiple factors and their interrelationships. The differential ranking map classifies different factors according to their influence types (such as comprehensive influence, single influence, mutually exclusive influence) and significance, helping users intuitively understand the cross-effects and importance of school travel environment factors on children's multi-dimensional perception.

[0223] The method for constructing the differential ranking map is as follows:

[0224] 1) First, establish a table of significance level - influence direction of school travel environment data and children's multi-dimensional perception, as shown in Table 6.

[0225] Table 6

[0226]

[0227] 2) Establish a differential map

[0228] Identification of comprehensive influencing factors: Retrieve and mark environmental data in children's school travel environment data that have a significant positive correlation with two or more types of perception data.

[0229] Single influencing factor identification: Retrieve and mark the environmental data in the children's school commute environment that has a significant correlation with the perception data of a single category;

[0230] Mutually exclusive influencing factor identification: Retrieve and mark the environmental data in the children's school commute environment that has a positive significant correlation with one type of perception data and a negative significant correlation with another type of perception data.

[0231] Integrate and classify the school commute environment data with the three types of identifications to establish Table 7 as follows.

[0232] Table 7

[0233]

[0234]

[0235] VII. Children's Perception Paths to be Configured

[0236] Specifically, the method for clustering and identifying the micro school commute environment of the target school district in S7 is as follows:

[0237] 1) In the micro school commute environment of the target school district, (using the natural breaks method, based on the ArcGIS platform) extract the area with the preset percentage (set to 10% in this embodiment) before the positive distribution of the comprehensive influencing factors as the children's perception hot spot type school commute path;

[0238] 2) In the micro school commute environment of the target school district, extract the area with the preset percentage (set to 10% in this embodiment) after the negative distribution of the single influencing factor as the children's perception improvement type school commute path;

[0239] 2.1) In the children's perception improvement type school commute path, the area that has a single influence on the children's self-efficacy perception data and is within the preset percentage (set to 10% in this embodiment) after the negative distribution in the area is the children's efficacy improvement school commute path;

[0240] 2.2) In the children's perception improvement type school commute path, the area that has a single influence on the children's sense of security perception data and is within the preset percentage (set to 10% in this embodiment) after the negative distribution in the area is the children's safety improvement school commute path;

[0241] 2.3) In the children's perception improvement type school commute path, the area that has a single influence on the children's affordance perception data and is within the preset percentage (set to 10% in this embodiment) after the negative distribution in the area is the children's activity improvement school commute path;

[0242] 3) In the micro school commute environment of the target school district, extract the children's perception contradictory type school commute path through the following steps:

[0243] 3.1) Plot a binary scatter fitting graph of the school commuting environment data and perception data with mutually exclusive influencing factors;

[0244] The binary scatter fitting graph is a commonly used data visualization method for showing the relationship between two variables. As Figure 5 and Figure 6 shown, with the data having mutually exclusive influencing factors as the horizontal axis and the corresponding perception data as the vertical axis, plot a scatter distribution graph and draw a fitting curve (linear fitting curve, exponential fitting curve, etc.).

[0245] 3.2) Extract the optimal distribution threshold interval of the school commuting environment data with mutually exclusive influences;

[0246] In the binary fitting graph, calculate the residuals of the school commuting environment data for the two mutually exclusive perception data, and set the residual range of the two to read the distribution interval of the school commuting environment data under the condition of 2 times the standard deviation as the optimal distribution threshold interval.

[0247] 3.3) Calculate the deviation degree d between the mutually exclusive influencing factors and the optimal threshold interval in the micro school commuting path;

[0248] The calculation formula for the deviation degree is as follows:

[0249] d = (∑|x_i - a| + ∑|x_j - b|) / n;

[0250] In the formula: d represents the deviation degree; the optimal distribution interval is [a, b]; x_i represents the data less than the lower limit of the interval; x_j represents the data greater than the upper limit of the interval; n represents the number of deviation data;

[0251] 3.4) In the micro school commuting environment of the target school district, extract the area with the preset percentage (set to 10% in this embodiment) of the deviation degree d of the mutually exclusive influencing factors as the children's perception contradictory school commuting path.

[0252] In this embodiment, the schematic diagrams of the children's perception enhanced school commuting path, the children's perception enhanced school commuting path, and the children's perception contradictory school commuting path are as Figure 7 shown.

[0253] VIII. Configuration and Update of the Children's Perception Path to be Configured

[0254] Specifically, the targeted configuration and update in S8 according to the type of the school commuting perception path include:

[0255] 1) Children's perception hot spot school commuting path: Add children's rest facilities, children's service facilities, and signs for children's comprehensive influencing factors; Expand children's comprehensive services and strengthen the iconicity of the perception hot spot to make this path a leading demonstration section for children's multi-dimensional perception.

[0256] 2) Child perception-enhanced path: Complement the distribution level of a single influencing factor to the range of the path mean value; for the corresponding perception, add corresponding single influencing factors and set up supplementary facilities for children's perception. For example, for safety perception, provide children with alarm facilities; for affordance perception, add environmental interaction facilities; make this path a potential updated section for children's multi-dimensional perception.

[0257] 3) Child perception-contradictory school commuting path: Adjust the distribution level of mutually exclusive influencing factors to the optimal threshold range; add facilities for children's perception expression and children's participation, such as perception opinion columns, etc.; to encourage children's perception expression and refine perception needs, make this path a finely optimized section for children's multi-dimensional perception.

[0258] In this embodiment, taking the child perception hot spot school commuting path, child safety-enhanced school commuting path, child efficiency-enhanced school commuting path, and child perception-contradictory school commuting path as examples, a configuration plan for the school commuting environment in key areas of School Y is established, as Figure 8 shown.

[0259] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the technical solutions. Those of ordinary skill in the art should understand that any modifications or equivalent replacements made to the technical solutions of the present invention without departing from the purpose and scope of the present technical solution shall be covered by the scope of the claims of the present invention.

Claims

1. A method for identifying and configuring micro-school environment types based on children's multi-dimensional perception, characterized in that: include: S1: Obtain the micro-school environment of the target school district and the actual travel data of all children; S2: Construct several theoretical micro-learning paths according to the micro-learning environment, and obtain the learning environment data of each theoretical micro-learning path; S3: Calculate the actual micro-paths used to go to school based on the children’s actual travel data, and then determine the actual school environment data used by the children by calculating the proportion of each theoretical micro-path in the actual micro-paths used to go to school; S4: Obtaining perceptual data on the three dimensions of children’s self-efficacy perception, safety perception, and affordance perception; S5: Construct a multiple linear regression model with all children’s perception data as the dependent variable and the actual school environment data as the independent variable; S6: Use multiple linear regression models to conduct correlation analysis and matching between perception data and school environment data, and identify key influencing factors in school environment data; S7: Cluster and identify key influencing factors in the micro-school environment, and identify the children's perception paths to be configured in the micro-school environment; S8: Targetedly configure and update the children's perception pathways to be configured to achieve adjustment and optimization of the micro-school environment in the target school district.

2. The method for identifying and configuring micro-school environment types based on children's multi-dimensional perception as claimed in claim 1, characterized in that: In step S2, a theoretical micro-learning path is constructed through the following steps: S201: Retrieve school district management unit grid data from the micro-school environment of the target school district; S202: extracting geographic coordinates of residential areas and school gate entrances from school district management unit grid data; S203: Obtain a walking plan route starting from the school gate entrance and ending in the residential area as a theoretical micro-path to school.

3. The method for identifying and configuring micro-school environment types based on children's multi-dimensional perception as claimed in claim 1, characterized in that: In step S2, the school environment data of the micro-school path includes data of any one or more dimensions of spatial scale, spatial facilities, spatial functions and landscape environment; Data on spatial scale dimensions include path continuity and / or path carrying capacity; Data on spatial facilities include exposure to motorized traffic during school hours, facilities for separating people from vehicles, and / or nighttime light intensity; Data on spatial functional dimensions include interface transparency, density of children’s facilities, and / or diversity of children’s facilities; Data on landscape environment dimensions include green view ratio, sky openness, and / or street noise.

4. The method for identifying and configuring micro-school environment types based on children's multi-dimensional perception as claimed in claim 3, characterized in that: In step S2, a sample point is set at a preset distance on the theoretical micro-school path, and the school environment data at the sample point is obtained; the average value of the school environment data at all the sample points is used as the school environment data corresponding to the theoretical micro-school path; The following formula is used to calculate the various data in the school environment data at the sample point: 1) Path continuity Where: Connect represents the path continuity of the sample point; W yx represents the path length from the sample point to the effective walking space of the school gate; l represents the actual path length from the sample point to the school gate; 2) Path carrying capacity Where: Capacity represents the path carrying capacity of the sample point; S i represents the area from the curb edge to the building edge within the interval of adjacent sample points; sl represents the actual length of the interval of adjacent sample points; 3) Exposure to motorized traffic Where: Exposure represents the exposure to motorized traffic during the school hours at the sample point; H yd represents the length of the congested road section; sl represents the actual length of the interval between adjacent sample points; 4) Facilities for separating people and vehicles Where: SF represents the completeness of the pedestrian-vehicle isolation facilities at the sample point; lf represents the length of the pedestrian-vehicle isolation facilities pixels in the street view image; Gl represents the length of the street view image; 5) Night light intensity Where: Light represents the nighttime light intensity of the sample point; ∑lg represents the sum of the nighttime light grid pixel values ​​in the sample point buffer; sl represents the actual length of the interval between adjacent sample points; l represents the actual length of the sample point buffer; 6) Interface transparency Where: Pratio represents the interface transparency of the sample point; P zp represents the number of pixels of vitreous body in the street view image; S ZP Represents the total number of pixels in the street view image; 7) Density of children's facilities Where: DP represents the density of children's facilities at the sample point; Nump represents the number of interest points of all parent-child facilities and children's facilities within the buffer range of the sample point; sl represents the actual length of the interval between adjacent sample points; 8) Diversity of children's facilities Where: DV represents the diversity of children's facilities at the sample point; Pi represents the proportion of the number of children's facilities at the i-th interest point in the sample point buffer zone to the total number of interest points; 9) Green View Rate Where: Greenratio represents the green viewing rate of the sample point; G zp represents the number of pixels of green plants in the street view image of the sample point; S ZP Represents the total number of pixels in the street view image; 10) Sky openness Where: Skyratio represents the sky openness of the sample point; S zp represents the number of sky pixels in the street view image of the sample point; S ZP Represents the total number of pixels of the street view image at the sample point; 11) Street noise Where: RT represents the street noise at the sample point; ∑Rg represents the equivalent sound level within the interval between adjacent sample points; sl represents the actual length of the interval between adjacent sample points.

5. The method for identifying and configuring micro-school environment types based on children's multi-dimensional perception as claimed in claim 1, characterized in that: In step S3, the school environment data actually used by the children is calculated by the following steps: S301: Obtain the coordinates of the school gate point, and obtain the coordinates of the actual residential area point and the passing point according to the actual travel data of the child; S302: Construct the micro-path of children's actual schooling using the school gate entrance coordinates as the starting point, the children's actual residential area coordinates as the end point, and the passing point coordinates as the middle point; S303: Match the micro-learning paths actually used by the children with all the theoretical micro-learning paths, and determine the proportion of each theoretical micro-learning path involved in the micro-learning paths actually used; S304: Calculate the actual school environment data used by all children by combining the following formula with the proportion of each theoretical micro-school path in the actual micro-school path; Ti=k1*r1+k2*r2+…+kn*rn, 0≤n; In the formula: Ti represents the data of the school environment actually used by the i-th child; r1 to rn represent the data of the school environment of the 1st to the nth theoretical micro-school paths; k1 to kn represent the proportion of each theoretical micro-learning path in the actually used micro-learning path.

6. The method for identifying and configuring micro-school environment types based on children's multi-dimensional perception as claimed in claim 1, characterized in that: In step S4, the child's perception data includes self-efficacy perception data, sense of security perception data and / or affordance perception data; The self-efficacy perception data include the child's efficacy level in going to school independently, the child's efficacy level in overcoming environmental barriers, and / or the child's efficacy level in self-adjustment; Safety perception data include the perceived safety level of passage and / or the perceived safety level of stranger encounter; The affordance perception data includes a traffic affordance perception level and / or a social affordance perception level.

7. The method for identifying and configuring micro-school environment types based on children's multi-dimensional perception as claimed in claim 6, characterized in that: In step S4, the children's perception data are obtained through a questionnaire survey, and the children's perception level is evaluated using the Likert five-level perception scale to quantify the perception data.

8. The method for identifying and configuring micro-school environment types based on children's multi-dimensional perception as claimed in claim 1, characterized in that: In step S5, all the children's perception data are input into the modeling software, and three multiple linear regression models are constructed by using the modeling software to take the school environment data actually used by all the children as independent variables and the self-efficacy perception data, sense of security perception data and affordance perception data in all the children's perception data as dependent variables; The formula of the multiple linear regression model is as follows: Where: y1, y2, y3 represent the self-efficacy perception data, security perception data and affordance perception data in the perception data respectively; x1 to x 11 They represent path continuity, path carrying capacity, exposure to motor traffic, pedestrian-vehicle isolation facilities, nighttime light intensity, interface transparency, density of children's facilities, diversity of children's facilities, green view rate, sky openness and street noise in the school environment data; β0 represents the intercept term of the model; β1, β2, … β 11 represents the regression coefficient of each variable.

9. The method for identifying and configuring micro-school environment types based on children's multi-dimensional perception as claimed in claim 8, characterized in that: In step S6, firstly, the significance level, i.e., p-value, of each school environment data in the three multivariate linear regression models is obtained in the modeling software; then, the school environment data with a p-value less than a preset value is regarded as having a significant correlation with the corresponding perception data; then, the direction of influence of the school environment data on the perception data is determined based on the regression coefficient of the school environment data: if the regression coefficient is a positive number, the direction of influence of the corresponding school environment data on the perception data is positive, otherwise it is negative; finally, the key influencing factors are determined based on the significant correlation and influence direction between the school environment data and the perception data; Key influencing factors include comprehensive influencing factors, single influencing factors and / or mutually exclusive influencing factors; Comprehensive influencing factors: environmental data in the school environment data that have a significant correlation with two or more types of perception data in the same direction; Single influencing factor: environmental data that has a significant correlation with a single type of perception data in the school environment data; Mutually exclusive influencing factors: environmental data in the general environment data that has a positive correlation with one type of perception data and a negative correlation with another type of perception data.

10. The method for identifying and configuring micro-school environment types based on children's multi-dimensional perception as claimed in claim 9, characterized in that: Step S7 specifically includes the following steps: 1) In the micro-school environment of the target school district, extract the area with a preset percentage before the positive distribution of comprehensive influencing factors as the children's perceived hot spot school path; 2) In the micro-school environment of the target school district, extract the area with a preset percentage of negative distribution of a single influencing factor as the children's perception-enhancing school path; 2.1) In the child perception enhancement type school path, the area with a single impact on the child's self-efficacy perception data and a preset percentage of negative distribution in the region is the child efficacy enhancement school path; 2.2) In the child perception enhancement type school path, the area with a single impact on the child's sense of security perception data and a preset percentage of negative distribution in the area is the child safety enhancement school path; 2.3) In the child perception enhancement type school path, the area with a single impact on the child's affordance perception data and a preset percentage of negative distribution in the area is the child activity enhancement school path; 3) In the micro-schooling environment of the target school district, extract the children’s perceived contradictory schooling paths through the following steps: 3.1) Based on mutually exclusive influencing factors, a binary scatter point fitting diagram of mutually exclusive influencing school environment data and corresponding perception data is drawn; 3.2) Extract the optimal distribution threshold interval of mutually exclusive impact school environment data from the binary scatter fitting diagram; 3.3) Calculate the degree of deviation between the mutually exclusive influencing factors in the micro-learning path and the optimal threshold interval; 3.4) In the micro-school environment of the target school district, extract the area with a preset percentage of deviation of mutually exclusive influencing factors as the children’s perceived contradictory school path.

Images