A city dissipation space discrimination method and system based on spatial clustering features

Abstract

The application provides a kind of urban dissipative space discrimination method and system based on spatial aggregation characteristics, it is related to spatial quality measure technical field.The urban dissipative space discrimination method based on spatial aggregation characteristics, comprising: obtaining city basic geographic space data and its geographic coordinates, form city space information integrated platform;According to the pre-set city dissipative space determination index library, the basic characteristic element data of city dissipative space is calculated, and the basic characteristic element data of city dissipative space is loaded into city space information integrated platform for spatial positioning calibration;Select appropriate grid scale to divide measure area;Each characteristic element data in grid unit is graded assignment;The order of city space is measured to calculate the aggregation;Establish determination rule to obtain four kinds of dissipative space characteristic element data set.The application improves the accuracy and efficiency of city dissipative space identification, and provides targeted guidance and power point for city renewal design and decision control.

Description

Technical Field

[0001] This invention relates to the field of spatial quality measurement technology, specifically to a method and system for identifying urban dissipative spaces based on spatial clustering characteristics. Background Technology

[0002] The urban spatial system is a dynamic, constantly evolving, complex, and open mega-system composed of various interrelated material elements, exhibiting a unified and highly concentrated nature of multidimensional elements within a certain geographical area. When the differentiated development of multiple subsystems creates a significant potential difference, it triggers dynamic evolution within the system, which is the intrinsic driving mechanism for the continuous development of the urban system. In the process of urbanization in my country, past expansion models have led to the diversification and complexity of the urban spatial system, while also resulting in a tendency towards separation, mechanization, and isolated fragmentation in the relationships between urban systems and their elements. Current urban construction has entered a phase of stock renewal, aiming to transform the previously extensive and disordered space into a relatively balanced and stable dissipative space. Therefore, identifying the prevalent disordered spaces and key influencing factors in cities, and guiding the targeted spatial transformation of these key influencing factors to promote the evolution and development of the urban spatial system, has become a key focus in the current urban development process.

[0003] Dissipative space refers to the transformation of urban open systems from a disordered and chaotic state to a dynamic, stable, and ordered state through the organization of material resources. This transformation is primarily characterized by a gradually improving spatial structure and a continuous enhancement of the spatial system's quality, vitality, orderliness, and attractiveness. Conversely, spaces in a chaotic state are considered disordered spaces. Based on research in urban spatial geography, the formation of dissipative space exhibits a clustering effect in the geographical dimension. The core of the urban spatial system achieves self-growth through energy and material exchange with the surrounding environment. The centripetal and centrifugal forces generated by this clustering work together to promote urban expansion and development, gradually forming relatively stable, high-quality, and orderly urban dissipative space. Objectively and accurately measuring urban spatial order and identifying dissipative spaces within cities can improve the efficiency and accuracy of project managers and designers in analyzing and judging spaces to be transformed, reducing the manpower and effort burden of site surveys. This is of great significance for promoting refined urban renewal and high-quality development.

[0004] Currently, common methods for measuring the order and dissipative space of urban spatial systems mainly involve selecting an indicator system that leads to the evolution of the urban spatial system, calculating the entropy weights of each indicator through entropy analysis, and exploring key indicators that promote the evolution of the spatial system in conjunction with changes in entropy ("Spatial Evolution Characteristics of Shanghai Urban and Rural Green Space System Based on Dissipative Structure Theory," Jin Yunfeng, 2019). These methods primarily focus on the influencing factors leading to spatial disorder under different time series, but they cannot identify, from a spatial perspective, which specific areas within the urban space are in a state of disorder.

[0005] For identifying spaces with low quality or even disorder, the main approach involves conducting site surveys and data collection in the study area. This is combined with professional understanding of disordered spaces to establish an evaluation index system. After subjective auditing and scoring, key areas for renovation are manually delineated. Finally, based on the survey findings, renewal design strategies are proposed (see "Identification, Measurement, Externalities, and Intervention of Disordered Elements in Urban Public Spaces," Chen Jingjia, 2021; "Evaluation of Inefficiency of Open Spaces in Urban Street and Alley Systems," Chen Long, 2019; "Research on Urban Inefficient Land Renewal Planning from the Perspective of Stock Planning—Taking Weifang High-tech Zone as an Example," Zeng Qingmei, 2020). These methods require significant manpower and effort to obtain data for evaluating disordered spaces. Furthermore, the disordered spaces identified through subjective judgment may not be comprehensive, failing to accurately pinpoint "where to change," meaning some spaces may be overlooked. Additionally, subjective scoring methods can only preliminarily determine "what to change," but cannot specify the appropriate "how much to change."

[0006] Regarding existing patents, there is a technology for spatial identification called "A Method for Identifying Damaged Ecological Space in Urban Agglomerations" (authorization announcement number: CN110298411B). However, this type of technology mainly focuses on the ecological space of urban agglomerations, and the scale of its spatial unit division is relatively large (20km*20km). The resolution of the identified spatial units is low. In contrast, the scale of dissipative spaces in cities is usually small. Therefore, the accuracy of the analysis results of this type of technology is low and insufficient to support the refined identification of urban dissipative spaces.

[0007] Therefore, in the actual construction process, existing technologies and related research have certain limitations. There is a lack of an efficient method for identifying urban dissipative spaces, which can help determine the clustering areas of urban dissipative spaces, so as to scientifically formulate spatial quality improvement and renewal plans, conduct refined organization of urban spaces to be transformed, and achieve efficient and accurate assessment and quality improvement of urban dissipative and disordered spaces. Summary of the Invention

[0008] (a) Technical problems to be solved

[0009] To address the shortcomings of existing technologies, this invention provides a method and system for identifying urban dissipative spaces based on spatial clustering characteristics, which improves the accuracy and efficiency of urban dissipative space identification and provides targeted guidance and focus for urban renewal design and decision-making.

[0010] (II) Technical Solution

[0011] To achieve the above objectives, the present invention provides the following technical solution: a method for identifying urban dissipative space based on spatial clustering characteristics, comprising:

[0012] Acquire urban basic geospatial data and geographic coordinates of each city's basic geospatial data, wherein the urban basic geospatial data includes urban vector data and satellite remote sensing image data; unify the geographic coordinates and projected coordinate systems of each city's basic geospatial data, and perform spatial positioning calibration in conjunction with satellite remote sensing image data to form an urban spatial information integration platform; calculate the basic characteristic element data of urban dissipation space based on a preset urban dissipation space judgment index library, and load the basic characteristic element data of urban dissipation space into the urban spatial information integration platform for spatial positioning calibration;

[0013] Select an appropriate grid scale to divide the measurement area, and map the basic feature data of urban dissipation space to the grid cells. Standardize the feature data mapped to the grid cells to obtain the feature set, and calculate and extract the key role dimensions and weight matrix of the basic feature elements of urban dissipation space.

[0014] The data of each feature element in the grid cell are assigned a level, and the leveled feature elements are weighted by a weight matrix to obtain the urban spatial order measurement result. The urban spatial order measurement result is then subjected to clustering calculation, and the value obtained from the clustering calculation is used to distinguish the urban dissipation space, thus obtaining the urban disorder space and the urban dissipation space.

[0015] Based on the urban disorder space and urban dissipation space, we retrospectively analyze the numerical levels of various characteristic elements of the corresponding geographical locations, establish judgment rules, and obtain four types of dissipation space characteristic element datasets. We then map the urban dissipation space dataset and the four types of dissipation space characteristic element datasets to the geographic space and display them.

[0016] Preferably, the standardization process of the feature feature data mapped to the grid cells to obtain the feature feature set specifically includes:

[0017] Feature set f after grid cell mapping and standardization i =(r i1 ,r i2 ,…r in), (i=1,2,…,d,n=1,2,…,N), which contains a total of N grids and d feature elements;

[0018] The standardized calculation formula for grid cell data is as follows:

[0019]

[0020] Where, r in This represents the original value of the nth grid cell for the i-th feature element. and Let R represent the maximum and minimum values ​​under the i-th feature element. in This represents the standardized feature value of the nth grid cell of the i-th feature feature;

[0021] Perform an adaptability test on the feature set to determine whether the feature set meets the conditions. If it does, it is suitable for the next step of weight measurement; otherwise, reselect the feature set.

[0022] Preferably, the calculation and extraction of the key role dimensions and weight matrices of the basic feature elements of urban dissipation space specifically includes:

[0023] Let F = (f1, f2, ..., f i The covariance matrix of (i = 1, 2, ..., d) is Σ, and the eigenvalues ​​of Σ are a1 ≥ a2 ≥ ... ≥ a d μ1, μ2, ... μ d Given its corresponding standardized feature vector, then:

[0024]

[0025] Extract the first m terms from the above equation as the common factors of the key explanatory feature set, that is:

[0026]

[0027]

[0028] in These are the estimated common factors. It is the estimated variance of a specific factor;

[0029] Using the maximum variance selection method, by maximizing the spacing between the loadings on each factor, we obtain a weight matrix W for m key dimensions:

[0030]

[0031] Weights λ of each feature element under each key dimension x The calculation is performed using the following formula:

[0032]

[0033]

[0034]

[0035] Where k is a constant, p is the total number of cells in the p-th cell (p = 1, 2, ..., n), R in Let d be the standardized feature value of the nth grid cell of the i-th feature (i = 1, 2, ..., d; n = 1, 2, ..., N), and x be the x-th feature index under the e-th action dimension (e = 1, 2, ..., m). There are y indices under this dimension (x = 1, 2, ..., y), and d = mx is satisfied.

[0036] The feature weights under each key dimension are then:

[0037] Calculate the weight matrix of each element: K e =W e ×Λ e .

[0038] Preferably, the step of assigning grade values ​​to each feature element data within the grid cell is calculated using the following formula:

[0039]

[0040] R in This represents the standardized value of the nth cell grid of the i-th feature element. and Let represent the maximum and minimum values ​​of all grid cells under the i-th feature, respectively. Let c be the 25th, 50th, 75th, and 90th quantiles of all grid cells under the i-th feature, respectively. in This represents the level of the i-th feature element after it has been assigned a value;

[0041] The dataset C of each feature element after classification is obtained. i ={c i1 ,c i2 ,…c in ,};

[0042] The urban spatial order measurement result is obtained by weighting the hierarchical feature elements using a weight matrix. The formula for measuring urban spatial order is as follows:

[0043]

[0044] Preferably, the agglomeration calculation of the urban spatial order measurement results is performed using the following formula:

[0045]

[0046] Q p A represents the urban spatial order measure value of the p-th grid, where n is the total number of all cell grids. p Let be the cluster value of the p-th grid, and its value range is [-1, 1]. The adjacency judgment matrix between the p-th and q-th grids is specifically represented as follows:

[0047]

[0048] Preferably, the step of determining the level of urban dissipation space based on the value obtained from the agglomeration calculation specifically includes:

[0049] Choose A p Grid cells with values ​​less than 0 are classified as disordered space A. low The closer the value is to -1, the more disordered the space A is. low The disordered space A exhibits low-value clustering in spatial order measurement results, similar to its neighboring spaces. low Poor quality; when A p If the value is greater than 0, it is determined to be a dissipative space. The closer the value is to 1, the higher the value of the dissipative space and its neighboring spaces are in terms of spatial order measurement results. The quality of the dissipative space is relatively stable and can maintain the current level.

[0050] Preferably, the establishment of the judgment rules yields four types of dissipative spatial feature element datasets, specifically including:

[0051] Choose C that satisfies K→1. i →1, and A p The dataset with a value of →-1 is identified as a problem area that urgently needs to be prioritized for renovation during the process of urban quality improvement and renewal. As a disordered space, the focus is on reconstructing and transforming the low-value clustered areas of low-value characteristic elements.

[0052] When K→0, C i →1, and A p →-1, or K→1, C i →1, and A p →1 indicates that the area is a secondary priority area for urban quality improvement and renewal, and low-value characteristic elements are upgraded and renewed.

[0053] When K→1, C i →5, and A p →-1, or K→0, C i →1, and A p→1 indicates an area that needs continuous monitoring during urban quality improvement and renewal. The quality level of this area is relatively weakly related to the value of the element. The corresponding low-value elements should be optimized and adjusted according to the actual construction situation of the area.

[0054] When K→0, C i →5, and A p →-1, or K→0, C i →5, and A p →1, or K→1, C i →5, and A p →1 indicates that the area is considered to be relatively stable in terms of overall quality and characteristic element order during urban quality improvement and renewal, and its current status is maintained as a dissipative space.

[0055] Secondly, a spatial discrimination system for urban dissipation based on spatial clustering characteristics is provided, including the following modules:

[0056] The spatial information integration module is used to acquire urban basic geospatial data and the geographic coordinates of each city's basic geospatial data, wherein the urban basic geospatial data includes urban vector data and satellite remote sensing image data; unify the geographic coordinates and projected coordinate systems of each city's basic geospatial data, and perform spatial positioning calibration in conjunction with satellite remote sensing image data to form an urban spatial information integration platform;

[0057] The feature element analysis module is used to calculate the basic feature element data of urban dissipation space based on the preset urban dissipation space judgment index library, and load the basic feature element data of urban dissipation space into the urban spatial information integration platform for spatial positioning calibration; select an appropriate grid scale to divide the measurement area, and map the basic feature element data of urban dissipation space into the grid cell; standardize the feature element data mapped into the grid cell to obtain the feature element set; and calculate and extract the key function dimension and weight matrix of the basic feature elements of urban dissipation space.

[0058] The dissipative space identification module is used to assign hierarchical values ​​to the feature element data within the grid cell, and to perform weighted calculations on the hierarchical feature elements through a weight matrix to obtain the urban spatial order measurement results; to perform clustering calculations on the urban spatial order measurement results, and to determine the level of the urban dissipative space based on the level of the clustering calculations, thus obtaining the urban disordered space and the urban dissipative space.

[0059] The results output and display module is used to analyze the numerical levels of various feature elements of the corresponding geographical locations based on the obtained urban disorder space and urban dissipation space, establish judgment rules to obtain four types of dissipation space feature element datasets, and map the urban dissipation space dataset and the four types of dissipation space feature element datasets to the geographic space and display them respectively.

[0060] Thirdly, a computer-readable storage medium is provided for storing one or more programs, the one or more programs including instructions that, when executed by a computing device, cause the computing device to perform any of the methods described.

[0061] Fourthly, a computing device is provided, comprising:

[0062] One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods described.

[0063] (III) Beneficial Effects

[0064] (1) The present invention provides a method and system for identifying urban dissipative space based on spatial agglomeration characteristics. It constructs an urban spatial information integration platform and an urban dissipative space identification index library, extracts key feature elements that affect the identification of urban dissipative space, simplifies the calculation of numerous and complex feature elements through factor analysis, and obtains the weight matrix of key feature elements. This improves the accuracy of urban dissipative space identification from the perspective of feature indicators, while reducing the complexity of feature element calculation.

[0065] (2) The present invention provides a method and system for identifying urban dissipative space based on spatial clustering characteristics. After obtaining the urban order measurement results, it extracts a dataset of feature elements with clustering characteristics, identifies the dataset with low-value clustering as urban disordered space, and integrates the three dimensions of the importance of feature elements for the identification of urban dissipative space, the measurement results of each feature element, and the measurement results of urban spatial order to further establish discrimination rules and update strategies for dissipative space, thereby achieving accurate identification of urban dissipative space and ensuring the accuracy of measurement results in multiple dimensions.

[0066] (3) The present invention provides a method and system for identifying urban dissipative space based on spatial clustering characteristics. Based on the measurement of urban dissipative space and regional identification, it realizes the geographic visualization of the measurement results, enables rapid identification of urban dissipative space, and can immediately, accurately and efficiently identify key areas, priority levels and key elements of urban renewal and transformation, thereby improving the decision-making efficiency of relevant staff. Attached Figure Description

[0067] Figure 1 This is a flowchart of the urban dissipation space discrimination method based on spatial clustering characteristics of the present invention;

[0068] Figure 2 This is a diagram showing the identification results of dissipated space and disordered space in an embodiment of the present invention;

[0069] Figure 3 This is a diagram showing the hierarchical results of four types of urban quality improvement and renewal models according to an embodiment of the present invention. Detailed Implementation

[0070] The technical solutions in the embodiments of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0071] Example

[0072] like Figure 1 As shown, this embodiment of the invention provides a method for identifying urban dissipation space based on spatial clustering characteristics, including:

[0073] This process involves acquiring basic urban geospatial data and the geographic coordinates of each city's basic geospatial data. The basic urban geospatial data includes urban vector data and satellite remote sensing imagery data. Urban vector data includes vector data such as urban administrative boundaries, roads, topography, water bodies, green spaces, buildings, land use, and points of interest. The process unifies the geographic coordinates and projected coordinate systems of all city basic geospatial data and performs spatial positioning calibration using satellite remote sensing imagery data, forming an integrated urban spatial information platform. Based on a pre-defined urban dissipation space assessment index library, the urban dissipation space is calculated. Basic characteristic element data of urban dissipative space is collected and loaded into the urban spatial information integration platform for spatial positioning calibration. Based on the current situation and practical needs of the city within the research scope, 15 basic characteristic elements for judging urban dissipative space are identified: street width, building height, street width-to-height ratio, relative pedestrian width, sky openness, street length, connectivity, through traffic, integration, topological depth, green view rate, POI mixing degree, POI density, road intersection density, and public transportation density. This forms an index library for judging urban dissipative space, and an index calculation module is loaded to calculate the values ​​of each characteristic element. Subsequently, all characteristic element data are loaded into the urban spatial information platform, and each characteristic element is spatially positioned and calibrated against the urban basic spatial data.

[0074] Taking into account factors such as the area of ​​the measurement region, the accuracy of feature element data characterization, the ease of obtaining feature element data, and the efficiency of data computation, an appropriate grid scale is selected to divide the measurement region. The basic feature element data of urban dissipative space is mapped to grid cells. The feature element data mapped to the grid cells is standardized to obtain a feature element set. The key function dimensions and weight matrices of the basic feature elements of urban dissipative space are calculated and extracted. In this embodiment, the measurement area is approximately 593 hectares; therefore, a 50-meter grid cell is selected to divide the measurement region, resulting in a total of 2382 grid cells. The feature element data is mapped to the grid cells, so that the attribute data of each feature element is attached to the grid cell whose geographical location overlaps with it.

[0075] The data of each feature element in the grid cell are assigned a level, and the leveled feature elements are weighted by a weight matrix to obtain the urban spatial order measurement result. The urban spatial order measurement result is then subjected to clustering calculation, and the value obtained from the clustering calculation is used to distinguish the urban dissipation space, thus obtaining the urban disorder space and the urban dissipation space.

[0076] Based on the identification of urban disordered space and urban dissipative space, a retrospective analysis of the numerical levels of various characteristic elements corresponding to the geographical locations is conducted to establish judgment rules and obtain four types of dissipative space characteristic element datasets. The urban dissipative space dataset and the four types of dissipative space characteristic element datasets are then mapped to geographic space and displayed. The plan view of the urban disordered space and urban dissipative space identified in this embodiment mapped to geographic space is shown below. Figure 2 The results of the classification of the four models for urban quality improvement and renewal are shown below. Figure 3 .

[0077] Furthermore, the feature data mapped to the grid cells is standardized to obtain a feature set, specifically including:

[0078] Feature set f after grid cell mapping and standardization i =(r i1 ,r i2 ,…r in ), (i=1,2,…,d,n=1,2,…,N), which contains a total of N grids and d feature elements;

[0079] The standardized calculation formula for grid cell data is as follows:

[0080]

[0081] Where, r in This represents the original value of the nth grid cell for the i-th feature element. and Let R represent the maximum and minimum values ​​under the i-th feature element. in This represents the standardized feature value of the nth grid cell of the i-th feature feature;

[0082] Perform an adaptability test on the feature set to determine whether the feature set meets the conditions. If it does, it is suitable for the next step of weight measurement; otherwise, reselect the feature set.

[0083] In this embodiment, after standardizing the data of each feature element, and after KMO test and Bartlett's sphericity test, 12 feature elements are finally retained, namely: street width, building height, street width-to-height ratio, sky openness, street length, connectivity, through traffic, integration, topological depth, green view rate, POI mixing degree, and road intersection density. KMO = 0.567 and p = 0, which meets the weighting measure conditions.

[0084] Furthermore, the key role dimensions and weight matrices of the basic characteristic elements of urban dissipation space are calculated and extracted, specifically including:

[0085] Let F = (f1, f2, ..., f i The covariance matrix of (i = 1, 2, ..., d) is Σ, and the eigenvalues ​​of Σ are a1 ≥ a2 ≥ ... ≥ a d μ1, μ2, ... μ d Given its corresponding standardized feature vector, then:

[0086]

[0087] Extract the first m terms from the above equation as the common factors of the key explanatory feature set, that is:

[0088]

[0089]

[0090] in These are the estimated common factors. It is the estimated variance of a specific factor;

[0091] Using the maximum variance selection method, by maximizing the spacing between the loadings on each factor, we obtain a weight matrix W for m key dimensions:

[0092]

[0093] Weights λ of each feature element under each key dimension x The calculation is performed using the following formula:

[0094]

[0095]

[0096]

[0097] Where k is a constant, p is the total number of cells in the p-th cell (p = 1, 2, ..., n), R in Let d be the standardized feature value of the nth grid cell of the i-th feature (i = 1, 2, ..., d; n = 1, 2, ..., N), and x be the x-th feature index under the e-th action dimension (e = 1, 2, ..., m). There are y indices under this dimension (x = 1, 2, ..., y), and d = mx is satisfied.

[0098] The feature weights under each key dimension are then:

[0099] Calculate the weight matrix of each element: K e =W e ×Λ e .

[0100] In this embodiment, the first 5 items are extracted as common factors of the key explanatory feature set, and the weight matrix W = [0.309 0.265 0.145 0.142 0.139] of the 5 key dimensions is calculated;

[0101] Secondly, the weights λ of each feature element under each key dimension. x The calculations show that the feature weights for each key dimension are as follows:

[0102]

[0103] Finally, the weight matrix K for all feature elements is calculated:

[0104]

[0105] Furthermore, the feature data within each grid cell are assigned a level value, calculated using the following formula:

[0106]

[0107] R in This represents the standardized value of the nth cell grid of the i-th feature element. and Let represent the maximum and minimum values ​​of all grid cells under the i-th feature, respectively. Let c be the 25th, 50th, 75th, and 90th quantiles of all grid cells under the i-th feature, respectively. inThis represents the level of the i-th feature element after it has been assigned a value;

[0108] The dataset C of each feature element after classification is obtained. i ={c i1 ,c i2 ,…c in ,};

[0109] The urban spatial order measurement result is obtained by weighting each feature element after classification using a weight matrix. The formula for measuring urban spatial order is as follows:

[0110]

[0111] The percentile data of each feature element in this embodiment are shown in Table 1. Based on this, the classification result C of each feature element dataset is obtained. i ={c i1 ,c i2 ,…c i2382 ,};

[0112] Table 1 Percentile values ​​of each feature element

[0113]

[0114]

[0115] By combining the obtained weight matrix K with the weighted calculations of each feature element after classification, the urban spatial order measurement results are obtained.

[0116] Furthermore, the clustering calculation of the urban spatial order measurement results is performed, using the following formula:

[0117]

[0118] Q p A represents the urban spatial order measure value of the p-th grid, where n is the total number of all cell grids. p Let be the cluster value of the p-th grid, and its value range is [-1, 1]. The adjacency judgment matrix between the p-th and q-th grids is specifically represented as follows:

[0119]

[0120] This embodiment performs clustering calculation on the urban spatial order measurement result Q obtained from the above steps, using the following formula:

[0121]

[0122] Furthermore, the values ​​obtained from agglomeration calculations are used to determine the spatial dissipation of urban energy, specifically including:

[0123] Choose A p Grid cells with values ​​less than 0 are classified as disordered space A. low The closer the value is to -1, the more disordered the space A is. low The disordered space A exhibits low-value clustering in spatial order measurement results, similar to its neighboring spaces. low Poor quality; when A p If the value is greater than 0, it is determined to be a dissipative space. The closer the value is to 1, the higher the value of the dissipative space and its neighboring spaces are in terms of spatial order measurement results. The quality of the dissipative space is relatively stable and can maintain the current level.

[0124] After spatial order clustering calculation, this embodiment yielded 437 grid cells that conform to A. p A value less than 0 indicates identified disordered urban spaces that require renovation and upgrading; there are also 412 grid units A. p >0 indicates the identified urban dissipation space.

[0125] Furthermore, decision rules are established to obtain four types of dissipative spatial feature element datasets, specifically including:

[0126] Choose C that satisfies K→1. i →1, and A p The dataset with a value of →-1 is identified as a problem area that urgently needs to be prioritized for renovation during the process of urban quality improvement and renewal. As a disordered space, the focus is on reconstructing and transforming the low-value clustered areas of low-value characteristic elements.

[0127] When K→0, C i →1, and A p →-1, or K→1, C i →1, and A p →1 indicates that the area is a secondary priority area for urban quality improvement and renewal, and low-value characteristic elements are upgraded and renewed.

[0128] When K→1, C i →5, and A p →-1, or K→0, C i →1, and A p →1 indicates an area that needs continuous monitoring during urban quality improvement and renewal. The quality level of this area is relatively weakly related to the value of the element. The corresponding low-value elements should be optimized and adjusted according to the actual construction situation of the area.

[0129] When K→0, C i →5, and A p →-1, or K→0, C i →5, and Ap →1, or K→1, C i →5, and A p →1 indicates that the area is considered to be relatively stable in terms of overall quality and characteristic elements during urban quality improvement and renewal, and its current status is maintained as a dissipative space.

[0130] The above four types of areas correspond to four models of urban quality improvement and renewal.

[0131] After identifying urban dissipation space, this embodiment iterates through the feature element data according to the above rules and extracts the four types of urban renewal patterns. The specific rules are as follows:

[0132] Select the option that simultaneously satisfies K≥0.1, C i <3, and A p Data sets with values ​​<0 are identified as problem areas that urgently need to be prioritized for urban quality improvement and renewal. It is necessary to focus on reconstructing and transforming low-value clustered areas of low-value feature elements.

[0133] When K < 0.1, C i <3, and A p <0, or K≥0.1, C i <3, and A p =0, it is determined as a secondary priority area for urban quality improvement and renewal, and the low-value characteristic elements are upgraded and renewed.

[0134] When K ≥ 0.1, C i ≥3, and A p <0, or K<0.1, C i <3, and A p If the value is ≥0, it is identified as an area that needs to be continuously monitored in the process of urban quality improvement and renewal. The relationship between the level of order in this area and the value of the element is relatively weak. The corresponding low-value elements can be optimized and adjusted according to the actual construction situation of the area.

[0135] When K < 0.1, C i ≥3, and A p <0, or K<0.1, C i ≥3, and A p ≥0, or K≥0.1, C i ≥3, and A p If the value is ≥0, the area is considered to be a region with relatively stable overall quality and characteristic elements during urban quality improvement and renewal, and its current status can be maintained.

[0136] Another embodiment of the present invention provides an urban dissipation spatial discrimination system based on spatial clustering characteristics, comprising the following modules:

[0137] The spatial information integration module is used to acquire urban basic geospatial data and the geographic coordinates of each city's basic geospatial data. The urban basic geospatial data includes urban vector data and satellite remote sensing image data. It unifies the geographic coordinates and projected coordinate systems of the basic geospatial data of each city and performs spatial positioning calibration in conjunction with satellite remote sensing image data to form an urban spatial information integration platform.

[0138] The feature element analysis module is used to calculate the basic feature element data of urban dissipation space based on the preset urban dissipation space judgment index library, and load the basic feature element data of urban dissipation space into the urban spatial information integration platform for spatial positioning calibration; select an appropriate grid scale to divide the measurement area, and map the basic feature element data of urban dissipation space into the grid cell; standardize the feature element data mapped into the grid cell to obtain the feature element set; and calculate and extract the key function dimension and weight matrix of the basic feature elements of urban dissipation space.

[0139] The dissipative space identification module is used to assign hierarchical values ​​to the feature element data within the grid cell, and to perform weighted calculations on the hierarchical feature elements through a weight matrix to obtain the urban spatial order measurement results; to perform clustering calculations on the urban spatial order measurement results, and to determine the level of the urban dissipative space based on the level of the clustering calculations, thus obtaining the urban disordered space and the urban dissipative space.

[0140] The results output and display module is used to analyze the numerical levels of various feature elements of the corresponding geographical locations based on the obtained urban disorder space and urban dissipation space, establish judgment rules to obtain four types of dissipation space feature element datasets, and map the urban dissipation space dataset and the four types of dissipation space feature element datasets to the geographic space and display them respectively.

[0141] Embodiments of this application may be provided as methods or computer program products. Therefore, this application may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application may be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0142] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0143] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0144] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0145] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for identifying urban dissipative space based on spatial clustering characteristics, characterized in that, include: Acquire urban basic geospatial data and geographic coordinates of each city's basic geospatial data, wherein the urban basic geospatial data includes urban vector data and satellite remote sensing image data; unify the geographic coordinates and projected coordinate systems of each city's basic geospatial data, and perform spatial positioning calibration in conjunction with satellite remote sensing image data to form an urban spatial information integration platform; calculate the basic characteristic element data of urban dissipation space based on a preset urban dissipation space judgment index library, and load the basic characteristic element data of urban dissipation space into the urban spatial information integration platform for spatial positioning calibration; Select an appropriate grid scale to divide the measurement area, and map the basic feature data of urban dissipation space to the grid cell. Standardize the feature data mapped to the grid cell to obtain the feature set, and calculate and extract the role dimension and weight matrix of the basic feature elements of urban dissipation space. The data of each feature element in the grid cell are assigned a level, and the leveled feature elements are weighted by a weight matrix to obtain the urban spatial order measurement result. The urban spatial order measurement result is then subjected to clustering calculation, and the value obtained from the clustering calculation is used to distinguish the urban dissipation space, thus obtaining the urban disorder space and the urban dissipation space. Based on the urban disorder space and urban dissipation space, we retrospectively analyze the numerical levels of various characteristic elements of the corresponding geographical locations, establish judgment rules, and obtain four types of dissipation space characteristic element datasets. We then map the urban dissipation space dataset and the four types of dissipation space characteristic element datasets to geographic space and display them. The calculation and extraction of the basic feature elements of urban dissipation space, including their role dimensions and weight matrices, specifically includes: set up , ; The eigenvalues ​​are ; Given its corresponding standardized feature vector, then: Extract the first part of the above formula The terms serve as common factors in the key explanatory feature set, namely: in These are the estimated common factors. It is the estimated variance of a specific factor; By using the maximum variance selection method, and ensuring that the loadings on each factor are spaced out, we obtain... Weight matrix of each action dimension : Weights of each feature element under each dimension of action The calculation is performed using the following formula: in, It is a constant. , For the first Total number of cell grids, For the first The first feature element The standardized feature values ​​of each grid cell For the first The first action dimension Individual characteristic indicators, There are a total of [number] under this dimension Individual indicators And satisfy ; The feature weights under each functional dimension are then: Calculate the weight matrix for each element: .

2. The urban dissipation space discrimination method based on spatial clustering characteristics according to claim 1, characterized in that: The process of standardizing the feature feature data mapped to the grid cells to obtain the feature feature set specifically includes: Feature set after grid cell mapping and standardization It contains a total of One grid, One characteristic element; The standardized calculation formula for grid cell data is as follows: in, Indicates the first The first feature element The original values ​​of each grid cell. and Indicates the first Maximum and minimum values ​​under each feature element Indicates the first The first feature element The standardized feature values ​​of each grid cell; Perform an adaptability test on the feature set to determine whether the feature set meets the conditions. If it does, it is suitable for the next step of weight measurement; otherwise, reselect the feature set.

3. The urban dissipation space discrimination method based on spatial clustering characteristics according to claim 2, characterized in that: The step of assigning hierarchical values ​​to the feature element data within the grid cell is calculated using the following formula: Indicates the first The first feature element Standardized values ​​for each cell grid. and They represent the first The maximum and minimum values ​​of all grid cells under each feature element. , , , The first The 25th, 50th, 75th, and 90th quantiles of all grid cells under each feature element. Indicates the first The level of each feature element after being assigned a value; Obtain the dataset of each feature element after classification ; The urban spatial order measurement result is obtained by weighting the hierarchical feature elements using a weight matrix. The formula for measuring urban spatial order is as follows: 。 4. The urban dissipation space discrimination method based on spatial clustering characteristics according to claim 3, characterized in that: The formula for calculating the clustering of urban spatial order measurement results is as follows: in Indicates the first Urban spatial order measurement value of each grid The total number of all cell grids, For the first The cluster value of each grid, with a value range of . ; For the first The grid and the first The adjacency judgment matrix for each grid is specifically represented as follows: 。 5. The urban dissipation space discrimination method based on spatial clustering characteristics according to claim 4, characterized in that: The determination of urban dissipation space based on the magnitude of the values ​​obtained from the agglomeration calculation specifically includes: Select The grid cells are classified as disordered space. The closer the value is to -1, the more disordered the space. The space adjacent to it exhibits low-value clustering in spatial order measurement results, indicating disordered space. Poor quality; when If the value is close to 1, it is determined to be a dissipative space. The closer the value is to 1, the higher the value of the dissipative space and its neighboring spaces are in terms of spatial order measurement results. The quality of the dissipative space is relatively stable and can maintain the current level.

6. The urban dissipation space discrimination method based on spatial clustering characteristics according to claim 5, characterized in that: The established judgment rules yield four types of dissipative spatial feature element datasets, specifically including: Select the one that satisfies , ,and The dataset was identified as a problem area that urgently needs to be prioritized for transformation during the process of urban quality improvement and renewal. As a disordered space, the focus was on reconstructing and transforming the low-value clustered areas of low-value characteristic elements. when , ,and ,or , ,and If so, it is determined to be a secondary priority area for urban quality improvement and renewal, and the low-value characteristic elements are upgraded and renewed. when , ,and ,or , ,and If the area is identified as an area that needs to be continuously monitored during the urban quality improvement and renewal process, the quality level of this area is relatively weakly related to the value of the elements. The corresponding low-value elements should be optimized and adjusted according to the actual construction situation of the area. when , ,and ,or , ,and If a region is deemed to have a relatively stable overall quality and characteristic element order in urban quality improvement and renewal, it will be considered a dissipative space and its current status will be maintained.

7. A spatial discrimination system for urban dissipation based on spatial clustering characteristics, characterized in that, Includes the following modules: The spatial information integration module is used to acquire urban basic geospatial data and the geographic coordinates of each city's basic geospatial data, wherein the urban basic geospatial data includes urban vector data and satellite remote sensing image data; unify the geographic coordinates and projected coordinate systems of each city's basic geospatial data, and perform spatial positioning calibration in conjunction with satellite remote sensing image data to form an urban spatial information integration platform; The feature element analysis module is used to calculate the basic feature element data of urban dissipation space based on the preset urban dissipation space judgment index library, and load the basic feature element data of urban dissipation space into the urban spatial information integration platform for spatial positioning calibration; select an appropriate grid scale to divide the measurement area, and map the basic feature element data of urban dissipation space into the grid cell; standardize the feature element data mapped into the grid cell to obtain the feature element set; and calculate and extract the function dimension and weight matrix of the basic feature elements of urban dissipation space. The dissipative space identification module is used to assign hierarchical values ​​to the feature element data within the grid cell, and to perform weighted calculations on the hierarchical feature elements through a weight matrix to obtain the urban spatial order measurement results; to perform clustering calculations on the urban spatial order measurement results, and to determine the level of the urban dissipative space based on the level of the clustering calculations, thus obtaining the urban disordered space and the urban dissipative space. The results output and display module is used to retrospectively analyze the numerical levels of various characteristic elements of the corresponding geographical locations based on the obtained urban disorder space and urban dissipation space, and establish judgment rules to obtain four types of dissipation space characteristic element datasets. Map the urban dissipation space dataset and the four types of dissipation space feature datasets to geospatial data and display them respectively; The calculation and extraction of the basic feature elements of urban dissipation space, including their role dimensions and weight matrices, specifically includes: set up , ; The eigenvalues ​​are ; Given its corresponding standardized feature vector, then: Extract the first part of the above formula The terms serve as common factors in the key explanatory feature set, namely: in These are the estimated common factors. It is the estimated variance of a specific factor; By using the maximum variance selection method, and ensuring that the loadings on each factor are spaced out, we obtain... Weight matrix of each action dimension : Weights of each feature element under each dimension of action The calculation is performed using the following formula: in, It is a constant. , For the first Total number of cell grids, For the first The first feature element The standardized feature values ​​of each grid cell For the first The first action dimension Individual characteristic indicators, There are a total of [number] under this dimension Individual indicators And satisfy ; The feature weights under each functional dimension are then: Calculate the weight matrix for each element: .

8. A computer-readable storage medium for storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods according to claims 1-6.

9. A computing device for a spatial discrimination method of urban dissipation based on spatial clustering characteristics, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the methods according to claims 1-6.

Images