A system and method for spatial building site planning

Abstract

The application discloses a kind of space building land planning system and method, it is related to building land planning technical field, including the following steps: obtaining the plot boundary data of planning area, plot is coded as functional unit, and construct plot function proportion vector;K order neighborhood structure of functional unit is constructed, and neighborhood aggregation is carried out to plot function proportion vector, obtain neighborhood function proportion vector;Based on neighborhood function proportion vector, clustering and anomaly detection are carried out to functional unit, obtain several imbalance units;The plot function proportion vector of imbalance unit is disturbed and adjusted, and several function proportion adjustment path sequences are obtained based on preset path generation algorithm;The neighborhood disturbance cost of function proportion adjustment path sequence is evaluated, and land planning album is updated according to the evaluation result, solve the problem that neighborhood relationship is ignored in traditional urban land planning to the influence of land, leading to the accuracy and rationality of planning adjustment reduce.

Description

Technical Field

[0001] This invention relates to the field of building land planning technology, and more specifically, to a spatial building land planning system and method. Background Technology

[0002] With the development of urban construction, land use planning plays a crucial role in the spatial layout and functional coordination of cities. Traditional urban land use planning mostly adopts static master plan zoning or artificial rule formulation methods, which are difficult to cope with rapidly changing urban functional needs. Especially during urban renewal, industrial transformation, or expansion of urban fringe areas, it can easily lead to an imbalance in the proportion of land used for different functions. For example, excessive expansion of industrial land may squeeze public service facilities and residential space, resulting in a decline in residents' quality of life and urban environmental degradation.

[0003] In recent years, with the development of technologies such as Geographic Information Systems (GIS), spatial data analysis, and machine learning, urban land use planning is gradually transforming towards data-driven and intelligent decision-making. Existing research attempts to introduce proportional control models or plot-level land redevelopment models for regulation, but these generally suffer from the following problems: First, most methods adjust planning based on the plot's own indicators, ignoring the functional dependencies within the spatial neighborhood structure; second, the detection methods for land use ratio deviations are relatively simple, lacking in-depth analysis of the disturbance mechanisms behind the imbalance; and third, most planning adjustment paths do not consider the stability of disturbances during spatial diffusion, easily triggering chain spatial conflicts.

[0004] To address the above problems, this invention proposes a solution. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a spatial building land use planning system and method. By dynamically adjusting the proportion of urban land use functions, it identifies areas of functional imbalance and simultaneously uses a multi-path disturbance strategy and a neighborhood cost assessment mechanism to address the problem of neglecting the impact of neighborhood relations on land use in traditional urban land planning, which leads to a decrease in the accuracy and rationality of land use planning.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A spatial building land use planning method includes the following steps: acquiring land parcel boundary data of the planning area, encoding the parcels into functional units, and constructing a parcel functional proportion vector based on a preset urban spatial database; constructing a k-order neighborhood structure for the functional units, and performing neighborhood aggregation on the parcel functional proportion vectors to obtain a neighborhood functional proportion vector; performing clustering and anomaly detection on the functional units based on the neighborhood functional proportion vectors to obtain several imbalanced units; perturbing and adjusting the parcel functional proportion vectors of the imbalanced units, and obtaining several functional proportion adjustment path sequences based on a preset path generation algorithm; evaluating the neighborhood perturbation cost of the functional proportion adjustment path sequences, and updating the land use planning atlas based on the evaluation results.

[0008] In a preferred embodiment, the step of obtaining land parcel boundary data of the planning area, encoding the land parcels into functional units, and constructing a land parcel function ratio vector based on a preset urban spatial database specifically involves: obtaining vector land parcel boundary data of the planning area and marking each land parcel with a unique code; encoding each land parcel into a functional unit containing several land use function types according to historical land use function classification data stored in the preset urban spatial database; calculating the area proportion of each land use function type within each functional unit, and constructing a land parcel function ratio vector with function type as the dimension and area proportion as the value.

[0009] In a preferred embodiment, the construction of the k-order neighborhood structure of the functional units and the neighborhood aggregation of the plot functional proportion vectors to obtain the neighborhood functional proportion vector specifically involves: obtaining a spatial topology map of the plots and constructing a k-order neighborhood structure based on each functional unit and its adjacent k-level plots that are directly or indirectly connected; extracting the plot functional proportion vectors of all functional units within the k-order neighborhood based on the k-order neighborhood structure; using the reciprocal of the distance between each plot within the k-order neighborhood and the central functional unit as the first weight; weighting and summing the plot functional proportion vectors according to the functional type based on the first weight; and normalizing the weighted summation result to obtain the neighborhood functional proportion vector.

[0010] In a preferred embodiment, the step of clustering and anomaly detection of functional units based on neighborhood functional proportion vectors to obtain several imbalanced units specifically involves: using the K-means clustering algorithm to cluster the neighborhood functional proportion vectors of all functional units to obtain several functional distribution pattern categories; calculating the Euclidean distance between each functional unit and the cluster center of its respective functional distribution pattern category; and determining an imbalanced unit if the Euclidean distance is greater than a preset threshold.

[0011] In a preferred embodiment, the perturbation adjustment of the functional proportion vector of the imbalanced unit specifically involves: calculating the dimensional difference between the functional proportion vector of the imbalanced unit and a preset target vector to obtain a first perturbation direction vector; calculating the target offset direction for each functional dimension based on the first perturbation direction vector; perturbing the functional proportion vector of the imbalanced unit stepwise according to the gradient direction based on the target offset direction for each functional dimension to obtain several first perturbation vectors, while keeping the sum of the proportions after perturbation equal to 1; and obtaining several candidate combinations for functional proportion adjustment based on several first perturbation vectors and controlling the perturbation step size and number of perturbations in each round.

[0012] In a preferred embodiment, the method of obtaining several functional ratio adjustment path sequences based on a preset path generation algorithm is as follows: the functional ratio vector of the current imbalanced unit is taken as the starting point of the path, and the first disturbance vector of each functional ratio adjustment candidate combination is taken as the potential path ending point.

[0013] Set the number of path generation cycles and calculate the change in the functional proportion from the starting point of the path to the potential end point of the path.

[0014] The change in the functional ratio is weighted and decomposed according to the number of path generation cycles to obtain the adjustment range of each path generation stage. Based on the adjustment range, each functional ratio vector is adjusted to obtain the first adjustment vector, which is recorded as the node of the current path generation stage until the endpoint is reached. The above adjustment steps are repeated to obtain several functional ratio adjustment path sequences.

[0015] In a preferred embodiment, the evaluation of the neighborhood disturbance cost of the functional proportion adjustment path sequence and the updating of the land use planning atlas based on the evaluation results specifically involves: extracting the current functional proportion vector of each node in the functional proportion adjustment path sequence at each path generation stage; calculating the current functional proportion vector of the node and the neighborhood average value of the functional units within the K-order neighborhood structure; calculating the neighborhood difference value based on the Euclidean distance between the current functional proportion vector of the node and the neighborhood average value; calculating the adjustment amplitude ratio between adjacent path stages and using it as the path stability evaluation value; weighting and aggregating the neighborhood difference value and the path stability evaluation value to obtain the path disturbance cost evaluation value; filtering the functional proportion adjustment path sequences based on the path disturbance cost evaluation value; selecting the adjustment path sequence with the smallest path disturbance cost evaluation value, updating the land parcel functional proportion vector of the imbalanced unit, and simultaneously modifying the functional distribution data in the land use planning atlas.

[0016] The technical effects and advantages of the spatial building land use planning system and method of the present invention are as follows:

[0017] 1. This invention constructs a land use function ratio vector by vectorizing and functionally encoding land parcel boundary data, thereby achieving a quantitative expression of land use functions. Based on this, a k-order neighborhood structure is introduced to fully consider the spatial correlation between land parcels. Neighborhood function ratio vectors are generated through neighborhood aggregation, making planning decisions more holistic and collaborative. Furthermore, cluster analysis and anomaly detection techniques are employed to accurately identify functionally imbalanced units, providing a scientific basis for subsequent adjustments. For imbalanced areas, the system generates adjustment candidates by perturbing the target function ratio and constructs multiple path sequences, simulating different adjustment schemes while maintaining the consistency of the total function ratio. By quantitatively evaluating the neighborhood perturbation cost and path stability of each path, the optimal path is ultimately selected for updating the land use planning map. This multi-dimensional, multi-stage dynamic optimization method overcomes the limitations of traditional static adjustments and reliance on manual judgment, effectively improving the rationality, continuity, and spatial coordination of land use function distribution. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a spatial building land use planning method according to the present invention.

[0019] Figure 2 This is a schematic diagram of the spatial building land use planning system of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] Example 1, Figure 1 This invention provides a spatial building land use planning method, comprising the following steps:

[0022] S1, Obtain the land parcel boundary data of the planning area, encode the land parcels into functional units, and construct the land parcel functional proportion vector based on the preset urban spatial database;

[0023] In this example, the boundary data of the planned area is obtained, the plots are encoded into functional units, and a plot function ratio vector is constructed based on a preset urban spatial database, specifically as follows:

[0024] Obtain vector plot boundary data for the planning area and mark each plot with a unique code;

[0025] Based on the historical land use function classification data stored in the pre-set urban spatial database, each plot is coded into a functional unit containing several land use function types;

[0026] Calculate the area ratio of each land use function type within each functional unit, and construct a land use function ratio vector with function type as the dimension and area ratio as the numerical value.

[0027] It should be noted that land parcel boundary data typically includes the following: the two-dimensional spatial geometry data of each parcel (such as polygon vector data), the parcel's unique identifier, the parcel's area information, the spatial topological relationship between the parcel and surrounding parcels (such as adjacency relationships, connecting boundary lengths, etc.), and attribute information such as the administrative division and geographic coordinates of the parcel. This data generally originates from urban planning management systems, geographic information systems (GIS), or real estate management platforms, and is stored and processed in vector format.

[0028] Furthermore, land use categories include, but are not limited to, the following: residential land (such as Class I and Class II residential buildings), commercial land (such as retail, catering, and office), industrial land (such as light industry, heavy industry, and warehousing and logistics), public service facilities land (such as education, medical care, culture, and sports), green space and open space (such as parks and green belts), transportation facilities land (such as roads, public transport hubs, and parking lots), and municipal public utility land (such as water supply and drainage, electricity, and communications). If a plot of land contains both residential and commercial land, its functional ratio vector is expressed as: [Residential: 0.7, Commercial: 0.3], that is, the residential function accounts for 70% of the total area of ​​the plot, and the commercial function accounts for 30%.

[0029] Furthermore, the aforementioned method, by structuring the land parcel boundary data of urban planning areas and performing functional coding and proportion calculation based on the urban spatial database, achieves high-precision modeling and quantitative expression of building land information, demonstrating significant application advantages. Firstly, the introduction of vector land parcel boundary data enables precise positioning and management of spatial data; each parcel is identified by a unique code, ensuring clarity and traceability in the data processing process. Secondly, historical land use function classification data is used to divide parcels into multi-functional units, breaking through the traditional single classification method of "one land, one use," and better aligning with the current trend of urban land use diversification. By calculating area proportions, a land parcel function proportion vector is constructed, allowing the functional distribution characteristics of each parcel to be clearly expressed in multiple dimensions, providing a solid data foundation for subsequent spatial analysis, cluster identification, and functional optimization. In addition, this method supports the integrated processing of multi-source data, possesses good versatility and scalability, and can be applied to land use planning tasks of varying urban scales and complexities. By using quantitative functional vectors, planners can conduct scientific analysis and intelligent adjustments to land use structure based on numerical models, significantly improving the accuracy, scientific nature, and intelligence of urban land use decisions, and promoting the transformation of urban spatial structure from traditional static planning to dynamic and intelligent optimization.

[0030] S2, construct the k-order neighborhood structure of the functional unit, and perform neighborhood aggregation on the plot functional proportion vector to obtain the neighborhood functional proportion vector.

[0031] In this example, a k-order neighborhood structure for functional units is constructed, and neighborhood aggregation is performed on the plot function ratio vector to obtain the neighborhood function ratio vector, specifically:

[0032] Obtain the spatial topology map of the plots, and construct a k-order neighborhood structure based on each functional unit and the plots directly or indirectly connected to its adjacent k layers;

[0033] Based on the k-order neighborhood structure, extract the plot function ratio vector of all functional units within the k-order neighborhood;

[0034] The reciprocal of the distance between each plot in the k-th order neighborhood and the central functional unit is used as the first weight;

[0035] The functional proportion vectors of land parcels are weighted and summed according to the first weight based on their functional types;

[0036] The weighted summation result is normalized to obtain the neighborhood function ratio vector.

[0037] It should be noted that if a certain central functional unit is plot i, its functional proportion vector is represented as:

[0038]

[0039] in, Let represent the area ratio of the j-th land use function on plot i, and n represent the total number of function categories.

[0040] Construct a k-order neighborhood set centered on plot i, denoted as This includes all the plot nodes in the spatial topology graph that are connected to plot i within order k by a path.

[0041] For any neighboring plot Let the spatial geometric center distance between it and plot i be . Then the weight of the plot in the neighborhood aggregation. The calculation formula is as follows:

[0042]

[0043] in, To prevent small constants with a denominator of zero.

[0044] Obtain the functional proportion vector of all neighboring plots and corresponding weights Then, calculate the weighted sum, using the following formula:

[0045]

[0046] in, This is the vector obtained by weighting and summing the functional proportion vectors of the land parcels according to the first weight.

[0047] It should be noted that the above method, by introducing a k-order neighborhood structure and combining it with a spatial distance-weighted aggregation mechanism, effectively enhances the understanding and expression of the surrounding spatial environment of building land planning, demonstrating significant advantages. First, the k-order neighborhood structure breaks through the limitations of traditional "single-plot" analysis, systematically introducing the topological relationships between adjacent multi-level plots, enabling the capture of complex regional linkages and functional permeability in urban space. Compared to first-order or simple adjacency analysis, the k-order structure is more suitable for identifying regional functional distribution trends and the evolutionary potential of local spaces. Second, by quantifying the spatial geometric distance between neighboring plots and the central plot, and using the reciprocal of the distance as a weighting factor, the actual influence of spatial neighbors on the central plot can be more accurately reflected, improving the spatial sensitivity of the aggregation results. Furthermore, the weighted summation and normalization of the functional proportion vector ensures that the results not only consider the functional composition of neighboring plots but also maintain proportional consistency and data structure stability, facilitating efficient algorithmic processing for subsequent clustering, anomaly detection, and planning adjustments. This method, based on spatial topology, expressed by functional proportions, and adjusted by distance weights, achieves quantitative modeling of urban functional spaces. It provides a scientific basis and scalable analytical tools for multi-scale, dynamic urban land use optimization, and significantly enhances the data-driven capabilities and intelligence level of urban planning.

[0048] S3, based on the neighborhood functional ratio vector, cluster the functional units and detect anomalies to obtain several imbalanced units;

[0049] In this example, based on the neighborhood functional proportion vector, clustering and anomaly detection are performed on the functional units to obtain several imbalanced units, specifically:

[0050] The K-means clustering algorithm was used to cluster the neighborhood function proportion vectors of all functional units to obtain several functional distribution pattern categories;

[0051] Calculate the Euclidean distance between each functional unit and the cluster center of its corresponding functional distribution pattern category;

[0052] If the Euclidean distance is greater than a preset threshold, it is determined to be an unbalanced unit.

[0053] It should be noted that an imbalanced unit differs significantly from its surrounding neighborhood in terms of functional structure. Specifically, if the functional proportions of a unit (e.g., the ratio of residential, commercial, and public service functions) deviate significantly from those of its neighboring areas, it is considered "imbalanced." This is typically determined by measuring the Euclidean distance from its cluster center to a value greater than a certain threshold, indicating that the unit does not belong to any mainstream functional distribution pattern or deviates from the characteristic center of that pattern.

[0054] Imbalanced units often reflect "discontinuities" or "abrupt changes" in urban planning. These areas are functionally incompatible with their surrounding environment, easily leading to traffic inconvenience, lack of supporting facilities, or uneven resource allocation. Identifying and optimizing these units can improve the coherence and intensification of the entire urban space. Some imbalanced units may reveal inadequate planning implementation, historical legacies, or market failures, such as large areas of industrial land interspersed in densely populated residential areas, or urban nodes lacking commercial facilities. Identifying these areas helps in early warning and planning correction.

[0055] Furthermore, firstly, by employing the K-means clustering algorithm to cluster the neighborhood function proportion vectors of all functional units, the functional distribution patterns in urban space can be fully explored, identifying regional groups with similar functional structures and providing a scientific basis for macro-level land use coordination. Secondly, by calculating the Euclidean distance between each functional unit and its cluster center, the dispersion of the unit within its functional category can be quantified, objectively reflecting its deviation in functional structure. This measurement method is more refined and repeatable compared to traditional land use assessment methods based on subjective judgment. Furthermore, by setting a threshold for judging the Euclidean distance, "unbalanced units" that are incompatible with their surroundings in terms of functional composition can be efficiently screened, providing precise targets for subsequent functional optimization and adjustment, and avoiding large-scale ineffective interventions.

[0056] S4, the functional proportion vector of the unbalanced unit is perturbed and adjusted, and several functional proportion adjustment path sequences are obtained based on the preset path generation algorithm.

[0057] In this example, the functional proportion vector of the unbalanced unit is adjusted by perturbation, specifically as follows:

[0058] The first disturbance direction vector is obtained by calculating the dimensional difference between the land parcel function ratio vector of the unbalanced unit and the preset target vector.

[0059] Calculate the target offset direction for each functional dimension based on the first perturbation direction vector;

[0060] Based on the target offset direction of each functional dimension, the functional proportion vector of the unbalanced unit is perturbed stepwise according to the gradient direction to obtain several first perturbation vectors, and the sum of the proportions after perturbation is kept equal to 1.

[0061] Based on several first perturbation vectors and by controlling the perturbation step size and number of perturbations in each round, several candidate combinations for functional ratio adjustment are obtained.

[0062] Specifically, the first disturbance direction vector is obtained by calculating the dimensional difference between the land parcel function ratio vector of the imbalanced unit and the preset target vector. The specific calculation formula is as follows:

[0063]

[0064] in, This is the first disturbance direction vector. For the preset target vector, This is the functional scaling vector.

[0065] It should be noted that, firstly, this method can accurately identify and resolve imbalances in urban space, ensuring that the functional proportions of each plot are more rationally adapted to the surrounding environment and overall planning goals. By calculating the difference with the preset target vector, the system can quantify the difference between the imbalanced unit and the ideal target, and formulate a precise adjustment strategy based on this difference. Secondly, using gradient-direction step-by-step perturbation adjustment allows the functional proportion vector of the plot to gradually approach the target, avoiding the risk of over-adjustment or deviation from the target. The magnitude of each adjustment is controlled by the step size, effectively avoiding excessive perturbation during the adjustment process, making the adjustment smoother and more in line with actual needs.

[0066] Furthermore, by maintaining a total ratio of 1 during the perturbation process, the adjusted functional proportions are ensured to always conform to the actual constraints of land use, thus preventing any violation of basic planning requirements. The path generation method based on multi-round perturbation not only effectively solves the problem of imbalanced units but also provides multiple adjustment schemes, allowing subsequent decision-makers to choose the most suitable path based on the actual situation.

[0067] In this example, several functional proportion adjustment path sequences are obtained based on a preset path generation algorithm, specifically:

[0068] The functional ratio vector of the current imbalanced unit is taken as the starting point of the path, and the first perturbation vector of each candidate combination of functional ratio adjustment is taken as the potential ending point of the path.

[0069] Set the number of path generation cycles and calculate the change in the functional proportion from the starting point of the path to the potential end point of the path.

[0070] The change in the functional ratio is weighted and decomposed according to the number of path generation cycles to obtain the adjustment range of each path generation stage.

[0071] Based on the adjustment range, each functional proportion vector is adjusted to obtain the first adjustment vector, which is recorded as the current path generation stage node until the destination is reached;

[0072] Repeat the above adjustment steps to obtain several functional ratio adjustment path sequences.

[0073] It should be noted that, based on a pre-defined path generation algorithm, the functional proportions of imbalanced units can be effectively adjusted step by step, ultimately resulting in several functional proportion adjustment path sequences. In this process, the functional proportion vector of the current imbalanced unit is first used as the starting point of the path, and then the perturbation vector of each candidate combination of functional proportion adjustments is used as the endpoint of the potential path. By setting the number of path generation cycles and calculating the change in functional proportion from the starting point to the endpoint of the potential path, the magnitude of each adjustment step can be precisely controlled. Next, this change is weighted and decomposed according to the number of cycles to obtain the adjustment magnitude for each path generation stage, thus ensuring that the functional proportion change at each stage is smooth and controllable. Based on these adjustment magnitudes, the system adjusts each functional proportion vector and records the adjustment nodes at each stage until the endpoint of the potential path is reached. By continuously repeating the above adjustment steps, several functional proportion adjustment path sequences are ultimately generated. The advantage of this method is that it can provide choices from multiple possible adjustment paths, avoiding the limitations that a single adjustment path might bring. Meanwhile, the weighted decomposition of the path generation cycle ensures that the step size of each adjustment is moderate, avoiding excessive adjustments or overly drastic changes in functional proportions, thus ensuring the stability and rationality of the planning adjustment process. Furthermore, the repeatability and flexibility of the path generation process provide planners with more room for adjustment, enabling them to select the most suitable path according to different actual needs, thereby effectively optimizing spatial layout and improving the efficiency and scientific nature of land use planning.

[0074] S5. Assess the neighborhood disturbance costs of the functional proportion adjustment path sequence and update the land use planning map based on the assessment results.

[0075] In this example, the neighborhood disturbance cost of the functional proportion adjustment path sequence is evaluated, and the land use planning atlas is updated based on the evaluation results, specifically as follows:

[0076] Extract the current function ratio vector of the function ratio adjustment path sequence at each path generation stage node;

[0077] Calculate the current functional proportion vector of the node and the neighborhood average of the functional units within the K-order neighborhood structure;

[0078] Calculate the neighborhood difference value based on the Euclidean distance between the node's current functional proportion vector and the neighborhood average value;

[0079] Calculate the ratio of adjustment magnitudes between adjacent path stages and use it as a path stability assessment value;

[0080] The neighborhood difference value and the path stability assessment value are weighted and aggregated to obtain the path disturbance cost assessment value.

[0081] Based on the path disturbance cost assessment value, the functional proportion adjustment path sequence is screened;

[0082] Select the adjustment path sequence with the lowest path disturbance cost assessment value, update the land function ratio vector of the imbalanced unit, and simultaneously modify the functional distribution data in the land use planning atlas.

[0083] It should be noted that the current functional proportion vector of each node in the functional proportion adjustment path sequence at each path generation stage is extracted, and the Euclidean distance between the functional proportion vector of that node and the neighborhood average value of functional units within the K-order neighborhood structure is calculated to obtain the neighborhood difference value. The neighborhood difference value reflects the difference between the current functional proportion vector and the surrounding functional units; the smaller the value, the more the adjusted functional proportion is consistent with the characteristics of the neighborhood environment. Next, the adjustment amplitude ratio between adjacent path stages is calculated and used as the path stability assessment value to evaluate whether the path adjustment is smooth and avoid excessive fluctuations or discontinuous changes. Then, the neighborhood difference value and the path stability assessment value are weighted and aggregated to obtain the path disturbance cost assessment value. Through this assessment process, different adjustment path sequences can be screened, and the adjustment path sequence with the smallest disturbance cost assessment value can be selected as the final adjustment path, thereby ensuring the stability and neighborhood consistency of spatial functional proportion adjustment. Finally, the plot functional proportion vector of the imbalanced unit is updated according to the optimal adjustment path, and the functional distribution data in the land use planning atlas is modified simultaneously. The advantage of this method is that it avoids unreasonable or excessive adjustments by comprehensively considering changes in the neighborhood environment and the smoothness of the adjustment process, thus ensuring the scientific and rational nature of the planning results.

[0084] Example 2, Figure 2 The present invention provides a spatial building land use planning system, comprising a data acquisition module, a neighborhood analysis module, an anomaly detection module, a path generation module, and an evaluation and update module.

[0085] The data acquisition module is used to acquire the land parcel boundary data of the planning area, encode the land parcels into functional units, and construct the land parcel functional proportion vector based on the preset urban spatial database.

[0086] The neighborhood analysis module is used to construct the k-order neighborhood structure of functional units and perform neighborhood aggregation on the plot function ratio vector to obtain the neighborhood function ratio vector.

[0087] The anomaly detection module is used to cluster functional units and detect anomalies based on the neighborhood functional ratio vector to obtain several imbalanced units.

[0088] The path generation module is used to perturb and adjust the functional proportion vector of the unbalanced unit, and obtain several functional proportion adjustment path sequences based on the preset path generation algorithm.

[0089] The assessment and update module is used to assess the neighborhood disturbance costs of the functional proportion adjustment path sequence and update the land use planning map based on the assessment results.

[0090] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0091] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0092] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0093] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0094] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A spatial building land use planning method, characterized in that, Includes the following steps: Obtain the land parcel boundary data of the planning area, encode the parcels into functional units, and construct a land parcel functional proportion vector based on a pre-set urban spatial database, specifically as follows: Obtain vector plot boundary data of the planning area and mark each plot with a unique code; based on the historical land use function classification data stored in the preset urban spatial database, encode each plot into a functional unit containing several land use function types; calculate the area proportion of each land use function type in each functional unit, and construct a plot function proportion vector with function type as the dimension and area proportion as the value. Construct a k-order neighborhood structure for functional units, and perform neighborhood aggregation on the functional proportion vector of land parcels to obtain the neighborhood functional proportion vector, specifically: Obtain the spatial topology map of the land parcels, and construct a k-order neighborhood structure based on each functional unit and its adjacent k-level directly or indirectly connected land parcels; based on the k-order neighborhood structure, extract the land parcel function proportion vector of all functional units within the k-order neighborhood; use the reciprocal of the distance between each land parcel within the k-order neighborhood and the central functional unit as the first weight; perform a weighted summation of the land parcel function proportion vectors according to the first weight based on the function type; normalize the weighted summation result to obtain the neighborhood function proportion vector; Based on the neighborhood functional proportion vector, clustering and anomaly detection are performed on functional units to obtain several imbalanced units, specifically: The K-means clustering algorithm is used to cluster the neighborhood function ratio vectors of all functional units to obtain several functional distribution pattern categories; the Euclidean distance between each functional unit and the cluster center of its functional distribution pattern category is calculated; if the Euclidean distance is greater than a preset threshold, it is determined to be an imbalanced unit. The functional proportion vectors of the imbalanced units are perturbed and adjusted, and several functional proportion adjustment path sequences are obtained based on a preset path generation algorithm, specifically: The first disturbance direction vector is obtained by calculating the dimensional difference between the functional proportion vector of the imbalanced unit and the preset target vector. Based on the first disturbance direction vector, the target offset direction of each functional dimension is calculated. Based on the target offset direction of each functional dimension, the functional proportion vector of the imbalanced unit is perturbed stepwise according to the gradient direction to obtain several first disturbance vectors, while keeping the sum of the proportions after perturbation equal to 1. Based on several first disturbance vectors and controlling the perturbation step size and number of perturbations in each round, several candidate combinations of functional proportion adjustment are obtained. The functional proportion vector of the current imbalanced unit is used as the starting point of the path, and the first disturbance vector of each candidate combination of functional proportion adjustment is used as the potential ending point of the path. Set the number of path generation cycles and calculate the change in the functional proportion from the starting point of the path to the potential end point of the path. The change in the functional ratio is weighted and decomposed according to the number of path generation cycles to obtain the adjustment range of each path generation stage; based on the adjustment range, each functional ratio vector is adjusted to obtain the first adjustment vector, which is recorded as the node of the current path generation stage, until the end point is reached; repeat the above adjustment steps to obtain several functional ratio adjustment path sequences. The neighborhood disturbance costs of the functional proportion adjustment path sequence are assessed, and the land use planning atlas is updated based on the assessment results, specifically as follows: Extract the current functional proportion vector of each node in the functional proportion adjustment path sequence at each path generation stage; calculate the current functional proportion vector of the node and the average value of the functional units within the K-order neighborhood structure; calculate the neighborhood difference value based on the Euclidean distance between the current functional proportion vector of the node and the average value of the neighborhood; calculate the adjustment amplitude ratio between adjacent path stages and use it as the path stability assessment value; weight and aggregate the neighborhood difference value and the path stability assessment value to obtain the path disturbance cost assessment value; filter the functional proportion adjustment path sequences based on the path disturbance cost assessment value; select the adjustment path sequence with the smallest path disturbance cost assessment value, update the plot functional proportion vector of the unbalanced unit, and simultaneously modify the functional distribution data in the land use planning atlas.

2. A spatial building land use planning system, characterized in that, The spatial building land use planning method according to claim 1 is characterized by comprising a data acquisition module, a neighborhood analysis module, an anomaly detection module, a path generation module, and an evaluation and update module. The data acquisition module is used to acquire the land parcel boundary data of the planning area, encode the land parcels into functional units, and construct the land parcel functional proportion vector based on the preset urban spatial database. The neighborhood analysis module is used to construct the k-order neighborhood structure of functional units and perform neighborhood aggregation on the plot function ratio vector to obtain the neighborhood function ratio vector. The anomaly detection module is used to cluster functional units and detect anomalies based on the neighborhood functional ratio vector to obtain several imbalanced units. The path generation module is used to perturb and adjust the functional proportion vector of the unbalanced unit, and obtain several functional proportion adjustment path sequences based on the preset path generation algorithm. The assessment and update module is used to assess the neighborhood disturbance costs of the functional proportion adjustment path sequence and update the land use planning map based on the assessment results.

Images