Residential Outdoor Environment Decision-making Method and System Based on Landscape Proximity Motivation

Abstract

The present invention discloses a method and system for making decisions on the outdoor environment of a residential area based on landscape approach motivation, and relates to the technical field of improving the quality and efficiency of the built environment. The method and system include: collecting engineering drawing data and environmental element material test data of the outdoor environment of the residential area, translating the test results of the outdoor environmental elements of the residential area into landscape approach motivation structure information; delineating landscape nodes in the outdoor environment of the residential area, building an initial decision matrix for the change state of the environmental element approach motivation corresponding to the landscape nodes, and decomposing the change state of the landscape approach motivation into an evolutionary state and a similarity state; geographically mapping the position and change state data of the landscape nodes, building a landscape approach motivation distribution adjacency network decision matrix, and calculating the driving degree of the residential area outdoor environment distribution adjacency network; distinguishing the hierarchical pattern of the landscape approach motivation change state, generating a residential area outdoor environment decision network, and clarifying the priority of the residential area outdoor environment renewal and management.

Description

Technical Field

[0001] The present invention relates to the technical field of improving the quality and efficiency of built environments, and in particular to a method and system for making decisions about the outdoor environment of residential areas based on landscape approach motivation. Background Art

[0002] Landscape approach motivation is one of the main factors influencing the use of residential outdoor environments, playing a decisive role in influencing residents' behavior and attitudes. Residential areas lacking psychological tendencies and behavioral drivers have lower rates of landscape use and satisfaction. Landscape approach motivation manifests itself as an "approach-avoidance" cognitive response, reflecting intuitive decisions about the attraction and repulsion of environmental elements. Related research shows that environmental governance decision-making processes guided by landscape approach motivation emphasize data-driven and integrated evaluation to adapt to complex and changing environmental conditions, thereby maximizing the satisfaction of residents' expectations and needs. Objective and rational brain cognitive data analysis and decision-making can help technology developers, environmental designers, residential area managers, and others accurately and in real time capture landscape environmental characteristics, providing fundamental data for refined residential outdoor environmental renewal and management.

[0003] Currently, analytical methods combining landscape elements and cognitive assessment include: "Cognitive Evaluation of Landscape Elements Based on Touch Thermal Analysis (2022)," a landscape preference decision-making method that uses real-world photography, element touch rate calculation, and thermal aggregation statistics; "Study on Emotional Characteristics and Influencing Factors of Urban Park Users (2021)," a landscape emotion cognitive pathway method that uses park emotion questionnaires, structural equation modeling, and factor influence identification; and "Comparative Study on Landscape Preferences and Landscape Cognition of Urban Park Users (2020)," a landscape cognitive assessment method that uses landscape preference questionnaires, element sample combination analysis, and park cognitive map generation. These methods often rely on user self-reports when processing cognitive data, which is susceptible to memory bias and personal interpretation, affecting the accuracy and reliability of cognitive data analysis. Furthermore, these methods are often static in their analytical approach and fail to fully capture the spatial fluidity and temporal evolution of the landscape environment and its components, limiting their effectiveness in cognitive decision-making.

[0004] Existing technologies include: a community public space renewal design method based on node information collection, daily dwell analysis, interaction network generation, and spatial group comparison (Application No. CN202010088995.7); a residential space network construction method based on service scope acquisition, residential area classification, and adjacency matrix relationship analysis (Application No. CN202310898451.0); and a public space optimization method based on material and behavioral network modeling and "settlement-district-single-point" hierarchical analysis (Application No. CN202310061699.1). Although these technical methods have developed, they still have certain limitations: insufficient attention is paid to residents' cognitive feedback on the outdoor environment of residential areas; the hierarchical scale and analytical accuracy of outdoor environmental elements in residential areas need to be improved; and the low integration of network decision-making functions from environmental cognition to environmental change characteristics makes it difficult for existing methods to provide effective guidance for the renewal and management of residential outdoor environments. Summary of the Invention

[0005] In order to solve the deficiencies mentioned in the above background technology, the purpose of the present invention is to provide a method and system for determining the outdoor environment of a residential area based on landscape proximity motivation.

[0006] In a first aspect, the purpose of the present invention can be achieved by the following technical solution: a method for determining the outdoor environment of a residential area based on landscape proximity motivation, the method comprising the following steps:

[0007] Acquiring engineering drawing data and material test data of the outdoor environment of the residential area, performing a landscape proximity test on the material test data of the outdoor environment of the residential area, and obtaining environmental element data that passes the test, wherein the engineering drawing data of the outdoor environment of the residential area includes plane vector data of the outdoor environment of the residential area and GPS positioning data, and the material test data includes standard image data of elements of the outdoor environment of the residential area;

[0008] Based on the engineering drawing data of the outdoor environment of the residential area and the verified environmental element data, the landscape nodes in the outdoor environment of the residential area are delineated, and the evolution and similar change status of the landscape nodes are determined according to the landscape proximity motivation information of the corresponding environmental elements in the outdoor environment of the residential area;

[0009] Based on the GPS positions and change states of landscape nodes in the outdoor environment of residential areas, the landscape proximity motivation initial decision matrix of landscape nodes and their corresponding environmental elements is generated. The discrete variables of the GPS positions and change states of landscape nodes in the outdoor environment of residential areas are encoded, and the distribution adjacency network of landscape nodes is constructed based on the landscape proximity motivation initial decision matrix of landscape nodes.

[0010] The distributed adjacent network of landscape nodes is processed for environmental graded decision-making to obtain the outdoor environmental decision results of the residential area.

[0011] In conjunction with the first aspect, in certain implementations of the first aspect, the method further includes: a process of performing landscape proximity motivation testing on material test data of the outdoor environment of the residential area:

[0012] Idle state debugging, Stroop effect test and random playback of standard images of outdoor environmental elements in residential areas;

[0013] Among them, the Stroop effect test results are subjected to hypothesis testing to obtain the fitted landscape approach motivation evaluation index, which is then normalized to finally obtain the environmental factor data that passes the test.

[0014] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: a formula for normalizing the fitted landscape proximity motivation evaluation index:

[0015]

[0016] in, represents the normalized landscape proximity motivation evaluation index value of the outdoor environmental elements of the i-th residential area in period t; It represents the value of the original landscape approach motivation evaluation index of the i-th type of environmental element in period t; represents the mean value of the original landscape approach motivation evaluation index of the i-th type of environmental element in period t; The standard deviation of the original landscape proximity motivation evaluation index of the i-th type of environmental element in period t.

[0017] In conjunction with the first aspect, in certain implementations of the first aspect, the method further includes: the process of generating an initial decision matrix of landscape approach motivations of landscape nodes and their corresponding environmental elements:

[0018] Structural landscape approach motivation information R based on outdoor environmental elements of residential areas in landscape nodes id , for w landscape nodes A l ={a w ,w=1,2,3,…,l} The landscape proximity motivation evaluation index in the tth period constitutes the initial decision matrix Z wt , calculate the initial decision matrix Z in turn wt The probability matrix P wi , the calculation process is:

[0019] Where i = 1, 2, 3…, m, d = 1, 2, 3…, n

[0020] in, It represents the uncertainty of the landscape proximity motivation information of the w-th landscape node in the t-th period on the outdoor environmental element of the n-th residential area at the m-th level.

[0021] In combination with the first aspect, in some implementations of the first aspect, the method further includes: referring to the information entropy principle to calculate the entropy value E of the outdoor environmental elements of the residential area id and landscape proximity motivation information utility value O id , get the weight T of environmental factors id , specifically:

[0022]

[0023] in, represents the amount of landscape approach motivation information of the outdoor environmental elements of the nth residential area in the tth period; w represents the number of landscape nodes in the outdoor environment of the residential area;

[0024] The changing state of the landscape proximity motivation information of the landscape nodes corresponding to the environmental elements in the outdoor environment of the residential area is decomposed into evolutionary state and similarity state, among which the evolutionary state EVO wt It represents the degree of dominance of the outdoor environmental elements in the residential area and reflects the vector space distance between the environmental elements and their optimal values. The calculation process is as follows:

[0025] Where i = 1, 2, 3…, m, d = 1, 2, 3…, n

[0026]

[0027] Among them, B wt A comprehensive variable representing the landscape approach motivation of the outdoor environmental elements of the residential area, It represents the landscape approach motivation evaluation index of the dth environmental element of the i-th level corresponding to the w-th landscape node in the outdoor environment of the residential area in the t-th period; Represents the evolution coefficient of the landscape proximity motivation evaluation index.

[0028] Among them, the similarity state SIM wt It represents the correlation trend of outdoor environmental elements in residential areas and reflects the coordinated change trend of environmental elements. The calculation process is as follows:

[0029]

[0030] Where i = 1, 2, 3, ..., m, d = 1, 2, 3, ..., n, w = 1, 2, 3, ..., l

[0031] in, It represents the correlation coefficient of the w-th landscape node in the outdoor environment of the residential area to the most ideal node regarding the d-th environmental factor of the i-th level; σ is the resolution coefficient, which indicates the importance of the max calculation.

[0032] In combination with the first aspect, in some implementations of the first aspect, the method further includes: when encoding the GPS positions and change states of landscape nodes in the outdoor environment of the residential area, integrating the hierarchical levels of outdoor environmental elements in the residential area, category names, change states of landscape proximity motivations, and GPS position attributes. The organizational structure of the preset geographical concept set of the outdoor environment of the residential area is a K-layer structure tree. When 1 < k ≤ K, the maximum number of branches included in the k-th layer is defined as Then the encoding of this classification hierarchical structure tree has K + bits.

[0033] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the process of constructing the distribution adjacency network of landscape nodes based on the initial decision matrix of landscape proximity motivations of landscape nodes:

[0034] Based on the evolutionary state and similarity state results of environmental element landscape proximity motivations, construct the distribution adjacency network decision matrix S. The distribution adjacency network C = (w, e) consists of w landscape nodes and e edges, forming an undirected network, which serves as the distribution adjacency network of landscape nodes.

[0035] In combination with the first aspect, in some implementations of the first aspect, the method further includes: according to the actual geographical distances of landscape nodes in the outdoor environment of the residential area, for the local adjacency indices of the evolutionary state and similarity state of environmental element landscape proximity motivations of landscape node q in the t-th period and calculate, as:

[0036]

[0037] where and respectively represent the evolutionary state and similarity state attribute values of landscape node q in the q-th outdoor environment of the residential area in the t-th period; represents the spatial weight between landscape node q and landscape node h in the t-th period, which is determined by the actual geographical distance between landscape nodes; and respectively represent the average values of the evolutionary state and similarity state attribute values of all landscape nodes; S _EVO and S _SIM respectively represent the standard deviations of the evolutionary state and similarity state attribute values of all landscape nodes; w represents the number of landscape nodes;

[0038] [[ID=​​​​

[0040] in, and They represent the landscape proximity motivation evolution state and similarity adjacency distribution network driving degree between landscape nodes q and h in the outdoor environment of the residential area in the tth period respectively; represents the non-normalized symmetric spatial interaction matrix between landscape nodes q and h in the tth period; T _SE and T _SS Represent the equal distance weights of the driving degree of the neighbor distribution network of the evolutionary state and the similar state respectively.

[0041] In conjunction with the first aspect, in certain implementations of the first aspect, the method further includes: performing environmental hierarchical decision processing on the distributed adjacent network of the landscape nodes to obtain a decision result on the outdoor environment of the residential area:

[0042] The evolution state and similarity state data of the approach motivation information of the outdoor environment landscape of the residential area are analyzed. By calculating the intra-class sum of squares of the evolution state and the similarity state WSS and the inter-class sum of squares of the deviations BSS, the level with the smallest WSS and the largest BSS is selected as the optimal level. Thus, the evolution state and the similarity state are divided into f levels, and a total of f is obtained. 2 The hierarchical pattern of the change state of the outdoor environment landscape approach motivation in each residential area;

[0043] Based on the hierarchical model of the outdoor environment change state in the residential area, the driving degree of the landscape approach motivation change state of the landscape nodes and their corresponding environmental elements is used to analyze the driving degree of the landscape approach motivation change state. As edge weights, the adjacency between landscape nodes is used as the basis for connecting the landscape nodes, and the driving degree geographical relationship of the outdoor environment nodes of the residential area is mapped with engineering drawing elements to generate a decision network of the outdoor environment of the residential area that represents the spatial distribution of the adjacent landscape nodes.

[0044] The spatial effect intensity of the landscape proximity motivation distribution adjacency network of the outdoor landscape nodes in the residential area is analyzed, and the outdoor landscape nodes in the residential area to be improved are obtained as follows:

[0045]

[0046] Among them, SEI t represents the spatial effect intensity of the landscape nodes in the outdoor environment of the residential area in the tth period; Indicates the driving degree assignment of the landscape node q and node h in the tth period to the state of the landscape approach motivation change. hour, when hour, represents the number of edges connecting the qth landscape node to other nodes in the tth period;

[0047] Normalize the spatial effect intensity value, calculate the intra-class sum of squares WSS and inter-class sum of squares BSS of the normalized spatial effect intensity, select the grade with the smallest WSS and the largest BSS as the optimal grade, and obtain u grades of spatial effect intensity, and assign u grades to u i =j, for j = 1, 2, ..., u. At the same time, the f of the landscape node 2 The level model of the outdoor environment change state of each residential area is assigned a value of g i =i,for i=1,2,…,f 2 , thus obtaining the landscape node update governance priority Pr _nod ,for:

[0048] Pr _nod =u i ·g i .

[0049] In a second aspect, in order to achieve the above-mentioned purpose, the present invention discloses a residential outdoor environment decision-making system based on landscape proximity motivation, comprising:

[0050] a data translation module for acquiring engineering drawing data and material test data of the outdoor environment of the residential area, performing a landscape proximity test on the material test data of the outdoor environment of the residential area, and obtaining environmental element data that passes the test, wherein the engineering drawing data of the outdoor environment of the residential area includes plane vector data of the outdoor environment of the residential area and GPS positioning data, and the material test data includes standard image data of elements of the outdoor environment of the residential area;

[0051] A state recognition module is used to delineate landscape nodes in the outdoor environment of the residential area based on engineering drawing data of the outdoor environment of the residential area and verified environmental element data, and to determine the evolution and similar change states of the landscape nodes based on landscape proximity motivation information of the corresponding environmental elements of the landscape nodes in the outdoor environment of the residential area;

[0052] The network construction module generates an initial decision matrix of landscape proximity motivations for landscape nodes and their corresponding environmental elements based on the GPS locations and change states of landscape nodes in the outdoor environment of the residential area. The discrete variables of the GPS locations and change states of landscape nodes in the outdoor environment of the residential area are encoded, and a distribution adjacency network of landscape nodes is constructed based on the initial decision matrix of landscape proximity motivations for landscape nodes.

[0053] The environmental decision module is used to perform environmental hierarchical decision processing on the distributed adjacent network of landscape nodes to obtain the decision results of the outdoor environment of the residential area.

[0054] Beneficial effects of the present invention:

[0055] The present invention:

[0056] (1) In order to solve the problem that the measurement method of outdoor environment cognitive data in residential areas is subjective and the processing process is cumbersome, the present invention combines brain cognitive test analysis technology to record the EEG signals of instantaneous stimulation of environmental elements in residential areas in real time; by setting the EEG "approach-avoidance" cognitive response judgment rules, the required environmental element landscape approach motivation cognitive feature information is extracted from the complex and changeable EEG signals, realizing the objective collection and rational analysis of environmental cognitive data, and improving the accuracy of the extraction of outdoor environment cognitive features in residential areas.

[0057] (2) In order to solve the problem of insufficient analysis of the differences, mobility and evolution of outdoor environmental elements in residential areas, the present invention, based on the results of the landscape proximity motivation index of environmental elements, comprehensively considers the spatiotemporal extreme data of the elements, establishes the landscape proximity motivation initial decision matrix of the outdoor environmental landscape nodes and their corresponding environmental elements in the residential area, determines the evolution and similarity change state of the landscape nodes, realizes the spatiotemporal change state analysis of multi-dimensional environmental elements, and ensures the efficiency and accuracy of the matrix operation of the outdoor environmental elements in the residential area.

[0058] (3) In order to solve the problems of low integration, low spatial resolution and lack of docking with environmental renewal management applications in the decision-making of the residential landscape proximity motivation network, the present invention maps the spatiotemporal change state of the landscape node proximity motivation into the geographic space, combines the distributed adjacency network decision matrix to generate the residential outdoor environment decision network, determines the hierarchical pattern and spatial effect intensity of the landscape node change state, and provides the residential outdoor environment landscape node renewal management priority, thereby improving the ability of accurate decision-making and integrated analysis of the residential outdoor environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0060] Figure 1 It is a schematic flow chart of the method of the present invention;

[0061] Figure 2 This is a development trend diagram of the evolution of the outdoor environment landscape approaching motivation of the residential area according to an embodiment of the present invention;

[0062] Figure 3 This is a similarity state development trend diagram of the residential area outdoor environment landscape approach motivation according to an embodiment of the present invention;

[0063] Figure 4 This is a decision network diagram of the outdoor environment of a residential area in summer, autumn and winter according to an embodiment of the present invention;

[0064] Figure 5 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0066] Example 1:

[0067] like Figure 1 As shown, the residential area outdoor environment decision-making method based on landscape proximity motivation is characterized in that the method includes the following steps:

[0068] S101: Acquire engineering drawing data and material test data of the outdoor environment of the residential area, perform a landscape proximity test on the material test data of the outdoor environment of the residential area, and obtain environmental element data that passes the test, wherein the engineering drawing data of the outdoor environment of the residential area includes plane vector data of the outdoor environment of the residential area and GPS positioning data, and the material test data includes standard image data of elements of the outdoor environment of the residential area;

[0069] The process of examining the landscape approach motivation of material test data for the outdoor environment of residential areas:

[0070] Idle state debugging, Stroop effect test and random playback of standard images of outdoor environmental elements in residential areas;

[0071] Among them, the Stroop effect test results are used for hypothesis testing to obtain the fitted landscape approach motivation evaluation index, which is then normalized to finally obtain the environmental factor data that passes the test;

[0072] Specifically, the present invention will be further described below through examples:

[0073] The prefrontal EEG signals of standard images of outdoor environmental elements in residential areas are obtained, and the EEG signals are precisely cut according to the environmental element category and acquisition period. A data cleaning process of bandpass filtering, noise artifact removal, ICA analysis, and spectrum analysis is adopted, and significance tests and internal consistency reliability tests are performed. Then, the power spectral density of the α, θ, and γ bands of the prefrontal EEG of the environmental elements that pass the test is calculated.

[0074] According to the principle of frontal lobe asymmetry of the brain, the ratio of the power spectrum density of the EEG α, θ, and γ rhythm bands is used to generate a landscape approach motivation disturbance index (x1; x2; x3) that can represent the landscape "approach-avoidance" reaction. The calculation process is as follows:

[0075]

[0076]

[0077] Where n represents the number of EEG channels in the prefrontal lobe; PSD(α), PSD(θ), and PSD(γ) represent the power spectral densities of the α, θ, and γ rhythm bands, respectively; left and right represent the EEG channels on the left and right sides of the prefrontal lobe, respectively.

[0078] The Stroop effect test results were statistically verified using hypothesis testing (t-value and two-tailed p-value), confidence intervals, and effect sizes to screen for valid landscape approach motivation disturbance index values. On this basis, the stable EEG signals obtained during the idle state debugging phase were used to calibrate the baseline of landscape approach motivation changes, and the fitted landscape approach motivation evaluation index AW was obtained, specifically:

[0079]

[0080] Among them, x 1_pre 、x 2_pre 、x 3_pre , x 1_post 、x 2_post 、x 3_post They represent the average values of the landscape approach motivation disturbance index in the 30-second idle state debugging phase and the last minute of the random playback phase of the outdoor environmental elements in the residential area; a, b, and v represent the coefficients of the landscape approach motivation disturbance index in the linear combination. Represents random error; the larger the AW value, the stronger the cognitive motivation to approach the landscape environment.

[0081] Normalize the landscape proximity motivation evaluation index value to obtain the structural information of the outdoor environmental elements of the residential area in period t It contains m levels and n elements. The calculation formula for normalizing the outdoor environmental elements of residential areas is as follows:

[0082]

[0083] in, represents the normalized landscape proximity motivation evaluation index value of the outdoor environmental elements of the i-th residential area in period t; It represents the original landscape approach motivation evaluation index value of the i-th type of environmental element in period t; represents the mean value of the original landscape approach motivation evaluation index of the i-th type of environmental element in period t; The standard deviation of the original landscape proximity motivation evaluation index of the i-th type of environmental element in period t.

[0084] In this embodiment, AutoCAD software is used to organize the plane vector data of the outdoor environment of the residential area, specifically including the red line range of the residential area, geographic elevation data, road flow data, green space planting data, hard space data, building vector data, and GPS positioning data of the outdoor environmental elements of the residential area. At the same time, according to the construction status of the outdoor environment of the residential area and the needs of landscape renewal and management, the system collects image data of the environmental elements in summer, autumn and winter. The actual pixel percentage of the environmental elements represented by the outdoor environment image of the residential area is greater than 70%, ensuring that the image standards of the environmental elements in different periods are consistent. A hierarchical system of elements including node patterns, morphological structures and landscape monomers is constructed, wherein the functional hierarchical elements include gathering and distribution open spaces, recreational gardens and functional places; the morphological hierarchical elements include enclosure, sequence, shape and signs; and the monomer hierarchical elements include vegetation, water bodies, structures and facilities.

[0085] EEG data from transient stimulation of outdoor environmental elements in residential areas were processed using the Eegomylab portable EEG acquisition system and the MNE-Python EEG cleaning toolkit. All environmental elements passed significance tests with P values < 0.05, and the internal consistency of each category of elements was > 0.65. Based on the number of trials for the subject population and experimental materials, G*Power software was used to verify that the transient stimulation results met the following criteria: a significance P value ≤ 0.05, a power > 0.5, a confidence interval excluding zero, and a Cohen's d ≥ 0.2, indicating that further investigation was conducted to identify changes in landscape approach motivation associated with outdoor environmental elements in residential areas.

[0086] S102: Delineating landscape nodes in the outdoor environment of the residential area based on engineering drawing data of the outdoor environment of the residential area and verified environmental element data, and determining the evolution and similarity change states of the landscape nodes based on landscape proximity motivation information corresponding to environmental elements in the outdoor environment of the residential area;

[0087] S103: generating an initial decision matrix of landscape proximity motivations of landscape nodes and their corresponding environmental elements based on the GPS positions and change states of landscape nodes in the outdoor environment of the residential area, encoding discrete variables of the GPS positions and change states of landscape nodes in the outdoor environment of the residential area, and constructing a distribution adjacency network of landscape nodes based on the initial decision matrix of landscape proximity motivations of landscape nodes;

[0088] The process of generating the initial decision matrix of landscape proximity motivations of landscape nodes and their corresponding environmental elements:

[0089] Structural landscape approach motivation information R based on outdoor environmental elements of residential areas in landscape nodes id , for w landscape nodes A l ={a w ,w=1,2,3,…,l} The landscape proximity motivation evaluation index in the tth period constitutes the initial decision matrix Z wt , calculate the initial decision matrix Z in turn wt The probability matrix P wi , the calculation process is:

[0090] Where i = 1, 2, 3…, m, d = 1, 2, 3…, n

[0091] in, It represents the uncertainty of the landscape proximity motivation information of the w-th landscape node in the t-th period on the outdoor environmental element of the n-th residential area at the m-th level.

[0092] Using the information entropy principle, we calculate the entropy value E of the outdoor environmental elements in the residential area. id and landscape proximity motivation information utility value O id , get the weight T of environmental factors id , specifically:

[0093]

[0094] in, represents the amount of landscape approach motivation information of the outdoor environmental elements of the nth residential area in the tth period; w represents the number of landscape nodes in the outdoor environment of the residential area.

[0095] The changing state of the landscape proximity motivation information of the landscape nodes corresponding to the environmental elements in the outdoor environment of the residential area is decomposed into evolutionary state and similarity state, among which the evolutionary state EVO wt It represents the degree of dominance of the outdoor environmental elements in the residential area and reflects the vector space distance between the environmental elements and their optimal values. The calculation process is as follows:

[0096] Where i = 1, 2, 3…, m, d = 1, 2, 3…, n

[0097]

[0098] Among them, B wt A comprehensive variable representing the landscape approach motivation of the outdoor environmental elements of the residential area, It represents the landscape approach motivation evaluation index of the dth environmental element of the i-th level corresponding to the w-th landscape node in the outdoor environment of the residential area in the t-th period; Represents the evolution coefficient of the landscape proximity motivation evaluation index.

[0099] Similarity SIM wt It represents the correlation trend of outdoor environmental elements in residential areas and reflects the coordinated change trend of environmental elements. The calculation process is as follows:

[0100]

[0101] Where i = 1, 2, 3, ..., m, d = 1, 2, 3, ..., n, w = 1, 2, 3, ..., l

[0102] in, It represents the correlation coefficient of the w-th landscape node in the outdoor environment of the residential area to the most ideal node regarding the d-th environmental factor of the i-th level; σ is the resolution coefficient, which indicates the importance of the max calculation.

[0103] In this example, GIS software was used to perform kernel density analysis on GPS location data of outdoor environmental elements in residential areas to identify high-frequency, multi-type clusters of these elements. A map plot method was used to determine the frequency and intensity of residents' outdoor use. Based on the overlay of these high-frequency, multi-type clusters and the range of residents' use frequency and intensity, and in conjunction with the results of the aforementioned environmental element landscape proximity motivation test, 15 representative landscape nodes were selected.

[0104] The weights of the outdoor environmental elements in the residential area for the three periods of summer, autumn, and winter were calculated using the initial decision matrix of the landscape approach motivation of the outdoor environmental elements in the residential area (Table 1). The weight coefficients for the three periods at the functional level were 27.52%, 34.45%, and 41.42%, respectively; the weight coefficients for the three periods at the morphological level were 36.31%, 30.37%, and 24.73%, respectively; and the weight coefficients for the three periods at the unit level were 36.18%, 35.19%, and 33.86%, respectively. The resolution coefficient σ was set to 0.5, and the evolutionary and similar states of the landscape approach motivation of the environmental elements were identified, and the dynamic development trend of the landscape nodes in the outdoor environment of the residential area was obtained ( Figure 2 、 Figure 3 ).

[0105] Table 1 Weights of outdoor environmental factors in residential areas

[0106]

[0107]

[0108] When encoding the GPS positions and change states of landscape nodes in the outdoor environment of a residential area, the hierarchy, category names, change states of landscape proximity motivations, and GPS position attributes of the outdoor environment elements of the residential area are integrated. The preset organizational structure of the geographical concept set of the outdoor environment of the residential area is a structure tree with K layers. When 1 < k ≤ K, the maximum number of branches contained in the k-th layer is defined as Then the encoding of this classification hierarchy tree has bits.

[0109] According to the attribute thresholds of the hierarchy and category of the outdoor environment elements of the residential area, the element attributes are converted into visual variables by means of conditional judgment, and the mapping relationship of the objective real outdoor environment of the residential area is output through drawing parameters. The visual variable is the vector symbol of the graphic element, including graphic elements such as straight lines, ellipses, polygons, etc. Each type of graphic element has its own drawing parameters

[0110] In this embodiment, referring to the One-Hot encoding method, the structure tree of the geographical concept set of the outdoor environment of the residential area is designed to have 4 layers. The first layer is the landscape node, the 2nd and 3rd layers are the element hierarchy and category, and the 4th layer is the change state of the landscape proximity motivation with a time series, with a total of two branches: the evolutionary state and the similarity state. On this basis, according to the visualization goal of the decision-making network of the outdoor environment of the residential area, a conversion format comparison table (Table 2) of the drawing parameters and visual variables of the element attributes of the outdoor environment of the residential area is formulated.

[0111] Table 2 Conversion Format Comparison Table of Drawing Parameters and Visual Variables

[0112]

[0113]

[0114] Based on the results of the evolutionary state and similarity state of the landscape proximity motivation of the landscape node and its corresponding environmental elements, a distributed adjacency network decision matrix S is constructed. The distributed adjacency network C = (w, e) is composed of w landscape nodes and e edges, forming an undirected network as the distributed adjacency network of the landscape nodes.

[0115] According to the actual geographical distance of the landscape nodes in the outdoor environment of the residential area, the local adjacency indices and of the evolutionary state and similarity state of the environmental element landscape proximity motivation of the q-th landscape node in the t-th period are calculated, specifically as follows:

[0116]

[0117] Among them, and respectively represent the evolutionary state and similarity state attribute values of the q-th landscape node in the t-th period in the outdoor environment of the residential area; represents the spatial weight between landscape node q and landscape node h in period t, which is determined by the actual geographical distance between landscape nodes; and Represent the average values of the evolutionary state and similarity state attributes of all landscape nodes; S _EVO and S _SIM Respectively represent the standard deviation of the evolutionary state and similarity state attribute values of all landscape nodes; w represents the number of landscape nodes;

[0118] when or When , the adjacent areas of landscape nodes have a higher clustered distribution of environmental element evolutionary or similar attribute values; when or When , the evolutionary state or similarity attribute values of the environmental elements in the adjacent areas of the landscape nodes are less concentrated.

[0119] Load the local adjacency index of the residential outdoor environment geographical concept set and landscape nodes into the distribution adjacency network decision matrix S, and calculate the driving degree of the edge connecting landscape node q and landscape node h in the tth period Where, q≤w,h≤w, is:

[0120]

[0121] in, and They represent the landscape proximity motivation evolution state and similarity adjacency distribution network driving degree between landscape nodes q and h in the outdoor environment of the residential area in the tth period respectively; represents the non-normalized symmetric spatial interaction matrix between landscape nodes q and h in the tth period; T _SE and T _SS Represent the equal distance weights of the driving degree of the neighbor distribution network of the evolutionary state and the similar state respectively.

[0122] when When , the driving degree of the landscape proximity motivation change state distribution network between landscape node q and node h is larger, indicating that landscape node q and node h contribute more to the spatial pattern of landscape proximity motivation in the common adjacent area of the outdoor environment of the residential area; when The network driving degree of the landscape approach motivation change state distribution between landscape node q and node h is small, indicating that landscape node q and node h contribute little to the spatial pattern of landscape approach motivation in the common adjacent area of the residential outdoor environment.

[0123] S104: Performing environmental classification decision processing on the distributed adjacent network of the landscape nodes to obtain a decision result of the outdoor environment of the residential area.

[0124] Retrospective analysis of the evolutionary state and similarity data of the outdoor environment landscape approach motivation of the residential area was conducted. By calculating the intra-class sum of squares (WSS) and inter-class sum of squares (BSS) of the evolutionary state and similarity, the class with the smallest WSS and the largest BSS was selected as the optimal class. Thus, the evolutionary state and similarity were divided into f classes, and a total of f were obtained. 2 A hierarchical model of the changing state of the outdoor environment in a residential area.

[0125] Based on the hierarchical model of the outdoor environment change state in the residential area, the driving degree of the landscape approach motivation change state of the landscape nodes and their corresponding environmental elements is used to analyze the driving degree of the landscape approach motivation change state. The edge weight is used, the adjacency between landscape nodes is used as the basis for connecting the landscape nodes, and the driving degree geographical relationship of the outdoor environment nodes of the residential area is mapped with engineering drawing elements to generate a decision network of the outdoor environment of the residential area that shows the spatial distribution of the adjacent landscape nodes.

[0126] The spatial effect intensity of the landscape proximity motivation distribution adjacency network of the outdoor landscape nodes in the residential area is analyzed, and the outdoor landscape nodes in the residential area to be improved are obtained as follows:

[0127]

[0128] Among them, SEI t represents the spatial effect intensity of the landscape nodes in the outdoor environment of the residential area in the tth period; Indicates the driving degree assignment of the landscape node q and node h in the tth period to the state of the landscape approach motivation change. hour, when hour, represents the number of edges connecting the qth landscape node to other nodes in the tth period;

[0129] Normalize the spatial effect intensity value, calculate the intra-class sum of squares WSS and inter-class sum of squares BSS of the normalized spatial effect intensity, select the grade with the smallest WSS and the largest BSS as the optimal grade, and obtain u grades of spatial effect intensity, and assign u grades to u i =j, for j = 1, 2, ..., u. At the same time, the f of the landscape node 2 The level model of the outdoor environment change state of each residential area is assigned g i =i,for i=1,2,…,f 2 , thus obtaining the landscape node update governance priority Pr _nod ,for:

[0130] Pr _nod =u i ·g i .

[0131] In this embodiment, the change state of the outdoor environment landscape of the residential area is divided into three levels, wherein the evolution state includes three levels of low [0, 0.332], medium [0.332, 0.523], and high [0.523, 1]; the similarity state includes three levels of low [0, 0.566], medium [0.566, 0.702], and high [0.702, 1]. A total of 9 residential area outdoor environment change state level standards and their corresponding 5 combination modes are obtained (Table 3). Through the implementation of the decision network, the distribution adjacency network of the outdoor environment landscape nodes of the residential area is drawn ( Figure 4 ), where the solid and dashed forms of the edges represent the distribution adjacency network driving degrees of landscape nodes greater than 1 and less than 1, respectively.

[0132] Table 3 Level model of the change state of the outdoor environment in the residential area

[0133]

[0134]

[0135] The spatial effect intensity of the distribution adjacency network of the outdoor landscape nodes in the residential area was calculated, and three level intervals of spatial effect intensity were obtained: [0, 0.498), [0.498, 0.811), and [0.811, 1]. At the same time, the natural breakpoint method was used to divide the landscape nodes into The data is classified and the cluster center is about 4.871. t ≥0.8 and The landscape nodes of SEI occupy an important position in the decision-making network and have a great influence on decision-making; t <0.5 and The landscape nodes need to be improved, resulting in four combination patterns and their values (Table 4).

[0136] Table 4 Hierarchical pattern of spatial effect intensity of outdoor landscape nodes in residential areas

[0137]

[0138] The priority ranking of the outdoor landscape nodes in the residential area during summer, autumn and winter is calculated respectively. The top three priority rankings of the landscape nodes during summer are node 4 (Pr _nod =15; decay type, renewal type), node 2 (Pr _nod =12; antagonistic, updating), and nodes 7, 9, 10, 11, 12 (Pr _nod =10; decline type, improvement type); the top three priorities for landscape node renewal management in autumn are nodes 2, 4, 5, 7, 9, and 10 (Pr_nod =15; decay type, renewal type), node 11 (Pr _nod = 10; decline type, promotion type), and nodes 1, 8, 12, 14 (Pr _nod =6; critical type, promotion type); the top three priorities of landscape node renewal management in winter are node 5 (Pr _nod =12; antagonistic, updating), node 7 (Pr _nod = 10; decline type, promotion type), and node 11 (Pr _nod = antagonistic type; decline type, promotion type).

[0139] Example 2: The second aspect, as Figure 5 As shown in the figure, the residential outdoor environment decision-making system based on landscape approach motivation includes:

[0140] The data translation module 11 is used to obtain engineering drawing data and material test data of the outdoor environment of the residential area, perform a landscape proximity test on the material test data of the outdoor environment of the residential area, and obtain environmental element data that passes the test, wherein the engineering drawing data of the outdoor environment of the residential area includes plane vector data of the outdoor environment of the residential area and GPS positioning data, and the material test data includes standard image data of elements of the outdoor environment of the residential area;

[0141] A state recognition module 12 is configured to delineate landscape nodes in the outdoor environment of the residential area based on engineering drawing data of the outdoor environment of the residential area and verified environmental element data, and to determine the evolution and similar change states of the landscape nodes based on landscape proximity motivation information of the corresponding environmental elements of the landscape nodes in the outdoor environment of the residential area;

[0142] The network construction module 13 is used to generate an initial decision matrix of landscape proximity motivations of landscape nodes and their corresponding environmental elements based on the GPS locations and change states of landscape nodes in the outdoor environment of the residential area, encode the discrete variables of the GPS locations and change states of landscape nodes in the outdoor environment of the residential area, and construct a distribution adjacency network of landscape nodes based on the initial decision matrix of landscape proximity motivations of landscape nodes;

[0143] The environmental decision module 14 is used to perform environmental hierarchical decision processing on the distributed adjacent network of landscape nodes to obtain a decision result of the outdoor environment of the residential area.

[0144] Based on the same inventive concept, the present invention also provides a computer device, which includes: one or more processors and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is used to implement one or more instructions, specifically for loading and executing one or more instructions in a computer storage medium to implement the above method.

[0145] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium having a computer program stored thereon, which executes the above method when executed by a processor. The storage medium can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component.

[0146] Throughout this specification, references to terms such as "one embodiment," "example," and "specific example" indicate that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0147] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present disclosure. Various changes and improvements may be made to the present disclosure without departing from the spirit and scope of the present disclosure, and such changes and improvements shall fall within the scope of the present disclosure.

Claims

1. A residential outdoor environment decision-making method based on landscape approach motivation, characterized by: The method comprises the following steps: Acquiring engineering drawing data and material test data of the outdoor environment of the residential area, performing a landscape proximity test on the material test data of the outdoor environment of the residential area, and obtaining environmental element data that passes the test, wherein the engineering drawing data of the outdoor environment of the residential area includes plane vector data of the outdoor environment of the residential area and GPS positioning data, and the material test data includes standard image data of elements of the outdoor environment of the residential area; The process of testing the material test data of the outdoor environment of the residential area for the landscape approach motivation is as follows: Idle state debugging, Stroop effect test and random playback of standard images of outdoor environmental elements in residential areas; Among them, the Stroop effect test results are used for hypothesis testing to obtain the fitted landscape approach motivation evaluation index, which is then normalized to finally obtain the environmental factor data that passes the test; The process is as follows: The prefrontal EEG signals of standard images of outdoor environmental elements in residential areas are acquired, and the EEG signals are precisely cut according to the environmental element category and acquisition period. A data cleaning process using bandpass filtering, noise artifact removal, ICA analysis, and spectral analysis is performed. Significance tests and internal consistency reliability tests are performed, and then the power spectral density of the α, θ, and γ bands of the prefrontal EEG of the environmental elements that pass the test are calculated. Based on the principle of frontal lobe asymmetry, the ratio of the power spectral density of the EEG α, θ, and γ rhythm bands is used to generate the landscape approach motivation disturbance index (x1; x2; x3) representing the landscape "approach-avoidance" reaction. The calculation process is as follows: Where n represents the number of EEG channels in the prefrontal lobe; PSD(α), PSD(θ), and PSD(γ) represent the power spectral density of the α, θ, and γ rhythm bands, respectively; left and right represent the EEG channels on the left and right sides of the prefrontal lobe, respectively; The results of the Stroop effect test were subjected to hypothesis testing, including statistical verification of t-values and two-tailed p-values, confidence intervals, and effect sizes. Valid values of the landscape approach motivation disturbance index were screened. The stable EEG signals obtained during the idle state debugging phase were used to calibrate the baseline of landscape approach motivation changes. The fitted landscape approach motivation evaluation index AW was obtained, specifically: Among them, x 1_pre 、x 2_pre 、x 3_pre , x 1_post 、x 2_post 、x 3_post They represent the average values of the landscape approach motivation disturbance index in the 30-second idle state debugging stage and the last minute of the random playback stage of the outdoor environmental elements of the residential area; a, b, and c represent the coefficients of each landscape approach motivation disturbance index in the linear combination, Represents random error; the larger the AW value, the stronger the cognitive motivation to approach the landscape environment; Based on the engineering drawing data of the outdoor environment of the residential area and the verified environmental element data, the landscape nodes in the outdoor environment of the residential area are delineated, and the evolution and similar change status of the landscape nodes are determined according to the landscape proximity motivation information of the corresponding environmental elements in the outdoor environment of the residential area; Based on the GPS positions and change states of landscape nodes in the outdoor environment of residential areas, the landscape proximity motivation initial decision matrix of landscape nodes and their corresponding environmental elements is generated. The discrete variables of the GPS positions and change states of landscape nodes in the outdoor environment of residential areas are encoded, and the distribution adjacency network of landscape nodes is constructed based on the landscape proximity motivation initial decision matrix of landscape nodes. The distributed adjacent network of landscape nodes is processed with environmental graded decision-making to obtain the decision results of the outdoor environment of the residential area.

2. The residential outdoor environment decision-making method based on landscape proximity motivation according to claim 1 is characterized in that: The formula for normalizing the fitted landscape proximity motivation evaluation index is: in, represents the normalized landscape proximity motivation evaluation index value of the outdoor environmental elements of the i-th residential area in period t; It represents the original landscape approach motivation evaluation index value of the i-th type of environmental element in period t; represents the mean value of the original landscape approach motivation evaluation index of the i-th type of environmental element in period t; The standard deviation of the original landscape proximity motivation evaluation index of the i-th type of environmental element in period t.

3. The residential outdoor environment decision-making method based on landscape proximity motivation according to claim 1 is characterized in that: The process of generating the landscape proximity motivation initial decision matrix of landscape nodes and their corresponding environmental elements is as follows: Structural landscape approach motivation information R based on outdoor environmental elements of residential areas in landscape nodes id , for w landscape nodes A l ={a w ,w=1,2,3,…,l} The landscape proximity motivation evaluation index in the tth period constitutes the initial decision matrix Z wt , calculate the initial decision matrix Z in turn wt The probability matrix P wt , the calculation process is: Where i = 1, 2, 3…, m, d = 1, 2, 3…, n in, It represents the uncertainty of the landscape proximity motivation information of the w-th landscape node in the t-th period on the outdoor environmental element of the n-th residential area at the m-th level.

4. The method for determining the outdoor environment of a residential area based on landscape proximity motivation according to claim 3, characterized in that: Using the information entropy principle, we calculate the entropy value E of the outdoor environmental elements in the residential area. id and landscape proximity motivation information utility value O id , get the weight T of environmental factors id , specifically: in, represents the amount of landscape approach motivation information of the outdoor environmental elements of the nth residential area in the tth period; w represents the number of landscape nodes in the outdoor environment of the residential area; The changing state of the landscape proximity motivation information of the landscape nodes corresponding to the environmental elements in the outdoor environment of the residential area is decomposed into evolutionary state and similarity state, among which the evolutionary state EVO wt It represents the degree of dominance of the outdoor environmental elements in the residential area and reflects the vector space distance between the environmental elements and their optimal values. The calculation process is as follows: Where i = 1, 2, 3…, m, d = 1, 2, 3…, n Among them, B wt A comprehensive variable representing the landscape approach motivation of the outdoor environmental elements of the residential area, It represents the landscape approach motivation evaluation index of the dth environmental element of the i-th level corresponding to the w-th landscape node in the outdoor environment of the residential area in the t-th period; represents the evolution coefficient of the landscape proximity motivation evaluation index; Among them, the similarity state SIM wt It represents the correlation trend of outdoor environmental elements in residential areas and reflects the coordinated change trend of environmental elements. The calculation process is as follows: Where i = 1, 2, 3, ..., m, d = 1, 2, 3, ..., n, w = 1, 2, 3, ..., l in, It represents the correlation coefficient of the w-th landscape node in the outdoor environment of the residential area to the most ideal node regarding the d-th environmental factor of the i-th level; σ is the resolution coefficient, which indicates the importance of the max calculation.

5. The residential outdoor environment decision-making method based on landscape proximity motivation according to claim 1 is characterized in that: When encoding the GPS positions and change states of landscape nodes in the outdoor environment of the residential area, the hierarchical levels, category names, change states of landscape proximity motivations, and GPS position attributes of the outdoor environment elements of the residential area are integrated. The organizational structure of the preset geographical concept set of the outdoor environment of the residential area is a structure tree with K layers. When 1 < k ≤ K, the maximum number of branches contained in the k-th layer is defined as Then the encoding of the classification hierarchical structure tree has bits.

6. The method for determining the outdoor environment of a residential area based on landscape proximity motivation according to claim 1, characterized in that: The process of constructing a distribution adjacency network of landscape nodes based on the landscape proximity motivation initial decision matrix of landscape nodes and their corresponding environmental elements is as follows: Based on the evolutionary state and similarity results of the landscape proximal motivations of landscape nodes and their corresponding environmental elements, a distributed adjacency network decision matrix S is constructed. The distributed adjacency network C = (w, e) consists of w landscape nodes and e edges, forming an undirected network as the distributed adjacency network of landscape nodes.

7. The residential outdoor environment decision-making method based on landscape proximity motivation according to claim 6 is characterized in that: According to the actual geographical distance of the landscape nodes in the outdoor environment of the residential area, the local adjacency index of the evolution state and similarity state of the landscape proximity motivation of the landscape node q in the tth period and Calculate it as: in, and They represent the evolutionary state and similarity attribute values of the landscape nodes in the outdoor environment of the qth residential area in the tth period respectively; represents the spatial weight between landscape node q and landscape node h in period t, which is determined by the actual geographical distance between landscape nodes; and Represent the average values of the evolutionary state and similarity state attributes of all landscape nodes; S _EVO and S _SIM Respectively represent the standard deviation of the evolutionary state and similarity state attribute values of all landscape nodes; w represents the number of landscape nodes; Load the local adjacency index of the residential outdoor environment geographical concept set and landscape nodes into the distribution adjacency network decision matrix S, and calculate the driving degree of the edge connecting landscape node q and landscape node h in the tth period , where q≤w,h≤w, is: in, and They represent the landscape proximity motivation evolution state and similarity adjacency distribution network driving degree between landscape nodes q and h in the outdoor environment of the residential area in the tth period respectively; represents the non-normalized symmetric spatial interaction matrix between landscape nodes q and h in the tth period; T _SE and T _SS Represent the equal distance weights of the driving degree of the neighbor distribution network of the evolutionary state and the similar state respectively.

8. The residential outdoor environment decision-making method based on landscape proximity motivation according to claim 1 is characterized in that: The process of performing environmental graded decision processing on the distributed adjacent network of landscape nodes to obtain the decision result of the outdoor environment of the residential area: The evolution state and similarity state data of the approach motivation information of the outdoor environment landscape of the residential area are analyzed. By calculating the intra-class sum of squares of the evolution state and the similarity state WSS and the inter-class sum of squares of the deviations BSS, the level with the smallest WSS and the largest BSS is selected as the optimal level. Thus, the evolution state and the similarity state are divided into f levels, and a total of f is obtained. 2 The hierarchical pattern of the change state of the outdoor environment landscape approach motivation in each residential area; Based on the hierarchical model of the outdoor environment change state in the residential area, the driving degree of the landscape approach motivation change state of the landscape nodes and their corresponding environmental elements is used to analyze the driving degree of the landscape approach motivation change state. As edge weights, the adjacency between landscape nodes is used as the basis for connecting the landscape nodes, and the driving degree geographical relationship of the outdoor environment nodes of the residential area is mapped with engineering drawing elements to generate a decision network of the outdoor environment of the residential area that represents the spatial distribution of the adjacent landscape nodes. The spatial effect intensity of the landscape proximity motivation distribution adjacency network of the outdoor landscape nodes in the residential area is analyzed, and the outdoor landscape nodes in the residential area to be improved are obtained as follows: Among them, SEI t represents the spatial effect intensity of the landscape nodes in the outdoor environment of the residential area in the tth period; Indicates the driving degree assignment of the landscape node q and node h in the tth period to the state of the landscape approach motivation change. hour, when hour, represents the number of edges connecting the qth landscape node to other nodes in the tth period; Normalize the spatial effect intensity value, calculate the intra-class sum of squares WSS and inter-class sum of squares BSS of the normalized spatial effect intensity, select the grade with the smallest WSS and the largest BSS as the optimal grade, and obtain u grades of spatial effect intensity, and assign u grades to u i =j, for j = 1, 2, ..., u, and at the same time, the f of the landscape node 2 The level model of the outdoor environment change state of each residential area is assigned g i =i,for i=1,2,…,f 2 , thus obtaining the landscape node update governance priority Pr _nod ,for: Pr _nod =u i ·g i , 9. A residential outdoor environment decision-making system based on landscape proximity motivation, characterized by: include: a data translation module for acquiring engineering drawing data and material test data of the outdoor environment of the residential area, performing a landscape proximity test on the material test data of the outdoor environment of the residential area, and obtaining environmental element data that passes the test, wherein the engineering drawing data of the outdoor environment of the residential area includes plane vector data of the outdoor environment of the residential area and GPS positioning data, and the material test data includes standard image data of elements of the outdoor environment of the residential area; The process of testing the material test data of the outdoor environment of the residential area for the landscape approach motivation is as follows: Idle state debugging, Stroop effect test and random playback of standard images of outdoor environmental elements in residential areas; Among them, the Stroop effect test results are used for hypothesis testing to obtain the fitted landscape approach motivation evaluation index, which is then normalized to finally obtain the environmental factor data that passes the test; The process is as follows: The prefrontal EEG signals of standard images of outdoor environmental elements in residential areas are acquired, and the EEG signals are precisely cut according to the environmental element category and acquisition period. A data cleaning process using bandpass filtering, noise artifact removal, ICA analysis, and spectral analysis is performed. Significance tests and internal consistency reliability tests are performed, and then the power spectral density of the α, θ, and γ bands of the prefrontal EEG of the environmental elements that pass the test are calculated. Based on the principle of frontal lobe asymmetry, the ratio of the power spectral density of the EEG α, θ, and γ rhythm bands is used to generate the landscape approach motivation disturbance index (x1; x2; x3) representing the landscape "approach-avoidance" reaction. The calculation process is as follows: Where n represents the number of EEG channels in the prefrontal lobe; PSD(α), PSD(θ), and PSD(γ) represent the power spectral density of the α, θ, and γ rhythm bands, respectively; left and right represent the EEG channels on the left and right sides of the prefrontal lobe, respectively; The results of the Stroop effect test were subjected to hypothesis testing, including statistical verification of t-values and two-tailed p-values, confidence intervals, and effect sizes. Valid values of the landscape approach motivation disturbance index were screened. The stable EEG signals obtained during the idle state debugging phase were used to calibrate the baseline of landscape approach motivation changes. The fitted landscape approach motivation evaluation index AW was obtained, specifically: Among them, x 1_pre 、x 2_pre 、x 3_pre , x 1_pre 、x 2_post 、x 3_post They represent the average values of the landscape approach motivation disturbance index in the 30-second idle state debugging stage and the last minute of the random playback stage of the outdoor environmental elements of the residential area; a, b, and c represent the coefficients of each landscape approach motivation disturbance index in the linear combination, Represents random error; the larger the AW value, the stronger the cognitive motivation to approach the landscape environment; A state recognition module is used to delineate landscape nodes in the outdoor environment of the residential area based on engineering drawing data of the outdoor environment of the residential area and verified environmental element data, and to determine the evolution and similar change states of the landscape nodes based on landscape proximity motivation information of the corresponding environmental elements of the landscape nodes in the outdoor environment of the residential area; The network construction module generates an initial decision matrix of landscape proximity motivations for landscape nodes and their corresponding environmental elements based on the GPS locations and change states of landscape nodes in the outdoor environment of the residential area. The discrete variables of the GPS locations and change states of landscape nodes in the outdoor environment of the residential area are encoded, and a distribution adjacency network of landscape nodes is constructed based on the initial decision matrix of landscape proximity motivations for landscape nodes. The environmental decision module is used to perform environmental hierarchical decision processing on the distributed adjacent network of landscape nodes to obtain the decision results of the outdoor environment of the residential area.

Images