Urban planning plot ratio automatic correction method and system

Abstract

The present application relates to the technical field of urban planning, and specifically provides a kind of urban planning volume rate automatic correction method and system, method includes: the multi-source data of target plot is collected to construct basic data set and construct associated model, the associated relationship data of target plot volume rate and city operation index quantification is output by model, to establish calculation rule base according to basic data set and associated relationship data;Based on rule base, the spatial characteristic parameters of target plot and user input parameters are combined to calculate initial benchmark volume rate, introduce dynamic influence factor to correct initial benchmark volume rate and output preliminary result;For preliminary result, eliminate invalid results through multidimensional check, output final scheme containing adaptive adjustment strategy;According to development life cycle feedback data, dynamically update model and rule base parameters.The method realizes the automatic correction of volume rate, dynamic, improves calculation accuracy and adaptability, and is suitable for volume rate planning correction of various urban plots.

Description

Technical Field

[0001] This invention relates to the field of urban planning technology, and specifically to an automatic correction method and system for urban planning floor area ratio. Background Technology

[0002] Floor area ratio (FAR) is a core indicator in urban planning used to regulate land development intensity. Its value directly relates to the construction scale, spatial form, and supporting infrastructure capacity of a plot of land. In scenarios such as urban renewal and the construction of affordable housing, determining the FAR requires comprehensive consideration of multiple factors, including higher-level planning requirements and the spatial characteristics of the plot. It is a key link in balancing land use efficiency, living environment quality, and urban interests, and is of great significance in guiding the orderly development of cities.

[0003] Existing technologies for calculating floor area ratio (FAR) have significant limitations. For example, traditional methods often determine FAR based on fixed data from the planning stage (such as preset traffic capacity and service scale), failing to respond to dynamic changes in urban operations (such as population flow, traffic upgrades, and increased service demand). This leads to a disconnect between FAR and the actual urban situation, potentially causing congestion and inadequate facilities. While some improvement schemes incorporate factors such as traffic and ecology, they are mostly qualitative analyses of a single dimension (such as reducing FAR during congestion) and lack a quantitative correlation model between FAR and various urban operation indicators, making it difficult to achieve multi-factor synergistic optimization. Furthermore, the weighting of multiple factors and correction coefficients rely on manual judgment, resulting in strong subjectivity, a lack of standardized calculation rule bases and automatic verification mechanisms, low efficiency, and susceptibility to errors.

[0004] Therefore, there is an urgent need for an automated method that can dynamically correct the floor area ratio in order to solve the problems in the existing technology. Summary of the Invention

[0005] To overcome the shortcomings of existing technologies, this invention provides an automatic correction method and system for urban planning floor area ratio, in order to solve the problems in existing technologies.

[0006] One embodiment of the present invention provides an automatic correction method for urban planning floor area ratio, comprising the following steps:

[0007] Collect multi-source data of the target plot, extract core parameters from the multi-source data to construct a basic dataset, build an association model based on the basic dataset, calculate the correlation between the plot ratio and urban operation indicators through the association model, and output quantitative association data with the goal of adapting the plot ratio to the urban operation status. Based on the basic dataset and the association data, establish a calculation rule base.

[0008] Based on the aforementioned calculation rule base, combined with the spatial characteristic parameters of the target plot and the user input parameters, the initial benchmark plot ratio is calculated. The initial benchmark plot ratio is then dynamically corrected by incorporating dynamic influencing factors, and the preliminary correction result is output.

[0009] Based on the constraints and quantitative correlation of the relationship data in the calculation rule base, the preliminary correction results are checked in multiple dimensions, and the parameters of the correction results that do not meet the constraints are corrected and the rules are rematched to eliminate invalid correction results.

[0010] The final floor area ratio correction scheme is output based on the verification results. The correction scheme includes at least the corrected floor area ratio value, the rule matching basis, and supporting optimization implementation suggestions, and includes adaptive adjustment strategies corresponding to dynamic influencing factors.

[0011] Based on feedback data throughout the entire development lifecycle of the target land parcel, the calculation rule base, correlation model, quantitative correlation parameters of correlation relationship data, and weight parameters of dynamic influencing factors are dynamically updated.

[0012] By adopting the above scheme, a correlation model and calculation rule base can be constructed through multi-source data to achieve a quantitative correlation between plot ratio and urban operation indicators. The initial benchmark plot ratio is dynamically corrected and verified in multiple dimensions by combining dynamic influencing factors, which improves the accuracy and adaptability of plot ratio calculation. At the same time, by outputting a correction scheme that includes adaptive adjustment strategies and a dynamic update mechanism throughout the entire life cycle, the problems of static lag, lack of systematic correlation, reliance on manual labor, and difficulty in long-term adaptation of traditional methods are effectively solved. This realizes the automated and dynamic correction of plot ratio and ensures the scientific nature and sustainability of the planning scheme.

[0013] In one embodiment, the step of collecting multi-source data of the target plot and extracting core parameters from the multi-source data to construct a basic dataset specifically includes the following steps:

[0014] The multi-source data of the target plot is divided into static basic data and dynamic supplementary data according to data attributes. The static basic data includes at least the statutory planning parameters, spatial attribute data and fixed control indicators of the target plot. The dynamic supplementary data includes at least the real-time urban operation monitoring data within the preset range of the target plot and the full life cycle prediction data within the preset period after the development of the target plot.

[0015] Static core indicators are extracted from static basic data, and corresponding dynamic related indicators are extracted from dynamic supplementary data. A mapping relationship between the two types of indicators is established through quantitative analysis algorithms to generate a correlation map, thereby realizing the correlation and fusion of static rules and dynamic influences.

[0016] By integrating static basic data, dynamic supplementary data, and quantitative relationships in the correlation graph, core parameters are selected according to data cleaning rules and organized by label according to scene characteristics to construct a basic dataset.

[0017] By adopting the above scheme and constructing a comprehensive and hierarchical basic dataset, standardized and highly reliable data support is provided for the training of correlation models and the establishment of a calculation rule base. By integrating statutory planning parameters, spatial attribute data and real-time urban operation monitoring data, the problems of single data source, static and fixed data and disconnection from actual scenarios in traditional methods are solved. This ensures that the data source for plot ratio correction not only meets the rigid constraints of planning but also responds to dynamic changes in the city, providing a solid data foundation for subsequent quantitative correlation and dynamic correction, and improving the scientific nature and data adaptability of the overall correction scheme.

[0018] In one embodiment, the step of establishing a calculation rule base based on the basic dataset and related relationship data specifically includes:

[0019] The basic rules layer is built on the basic dataset and quantified relational data, including the association rules between spatial features and basic volume benchmarks, as well as the quantified correspondence rules between urban operation indicators and volume changes.

[0020] The constraint rule layer is constructed based on the statutory planning parameters in the basic dataset. It includes the sum constraint rules of the basic volume, the transfer volume and the bonus volume, the proportional constraint rules of a single volume type and the adaptation range constraint rules of user input parameters.

[0021] The dynamic adjustment rule layer is built based on dynamically supplemented data and includes weight allocation rules for different types of dynamic influencing factors, cross-regional adjustment rules for transfer volume, positive incentive rules for reward volume, and inter-layer correction rules when the basic rule layer and constraint rule layer trigger linkage.

[0022] By adopting the above scheme and constructing a three-layer calculation rule base comprising a basic rule layer, a constraint rule layer, and a dynamic adjustment rule layer, the differentiated control logic of each layer for basic volume, transfer volume, and bonus volume is clarified: the basic rule layer provides a benchmark calculation basis for basic volume based on spatial characteristics; the dynamic adjustment rule layer provides standardized logic for cross-regional adjustment and positive incentives for transfer volume and bonus volume; and the constraint rule layer ensures the compliance of the three types of volume through summation and single ratio constraints. This system realizes full-process layered control from determining the benchmark value of volume ratio to dynamic incremental adjustment and total boundary control. It not only solves the problems of ambiguous volume ratio composition and lack of structured rule support in traditional methods, but also improves the accuracy of dynamic adjustment and the rigidity of legal constraints through the synergistic optimization of the three types of volume. It provides a logically clear and reusable rule framework for automated volume ratio correction, further enhancing the standardization of the correction process and the reliability of the results.

[0023] In one embodiment, the step of calculating the initial benchmark floor area ratio based on the calculation rule base, combined with the spatial characteristic parameters of the target plot and the user input parameters, dynamically correcting the initial benchmark floor area ratio by combining dynamic influencing factors, and outputting the preliminary correction result specifically includes the following steps:

[0024] Spatial feature parameters of the target plot are extracted from the spatial attribute data in the basic dataset. User input parameters are received, the basic rule layer of the calculation rule base is called, and the spatial feature parameters are substituted into the association rule between spatial features and basic floor area ratio benchmark to generate the initial floor area ratio candidate interval.

[0025] Based on the initial floor area ratio candidate interval, combined with user input parameters and user input adaptation range constraint rules of the constraint rule layer, values ​​that meet the requirements are selected from the initial floor area ratio candidate interval as the initial benchmark floor area ratio;

[0026] The dynamically supplemented data is called to extract the dynamic influencing factors related to the transfer volume and the reward volume. Based on the dynamic adjustment rule layer of the calculation rule base, the corresponding weights are assigned according to the weight allocation rules of different types of dynamic influencing factors. The correction values ​​of the transfer volume and the reward volume are determined by combining the cross-regional adjustment rules of the transfer volume and the positive incentive rules of the reward volume.

[0027] Based on the initial benchmark floor area ratio, the correction value of the transfer floor area ratio, and the correction value of the bonus floor area ratio, a preliminary correction result of the initial benchmark floor area ratio is calculated using a preset correction formula.

[0028] For the preliminary correction result, the sum constraint rules of the basic volume, transfer volume and reward volume of the constraint rule layer and the proportional constraint rules of a single volume type are called for verification; if the preliminary correction result exceeds the constraint threshold, the inter-layer correction rules of the dynamic adjustment rule layer are automatically called back to meet the constraint requirements, and the final preliminary correction result is output.

[0029] By adopting the above scheme, and by clarifying the entire process of generating the basic floor area ratio (FAR), dynamically correcting the transfer / bonus FAR, and verifying the overlay of the three types of FAR, the FAR correction process strictly corresponds to the control logic of the three types of FAR in the calculation rule base: the basic FAR is accurately generated through spatial feature matching and user parameter adaptation; the transfer FAR and bonus FAR are quantitatively calculated based on dynamic influencing factors and specific rules; and finally, compliance is ensured through summation and proportional constraint verification. This process not only solves the problems of subjective setting of FAR benchmark values ​​and lack of clear basis for dynamic adjustment in traditional methods, but also, through the structured decomposition and collaborative calculation of the three types of FAR, enables the correction results to simultaneously respond to the attributes of the land parcel itself, regional balance needs, and rule incentive guidance, improving the accuracy, scenario adaptability, and legal compliance of the initial correction results, and laying a more reliable foundation for subsequent multi-dimensional verification.

[0030] In one embodiment, the step of constructing a correlation model based on a basic dataset, calculating the correlation between the plot ratio of the target plot and urban operation indicators through the correlation model, and outputting quantified correlation data with the goal of adapting the plot ratio to the urban operation status, specifically includes the following steps in the construction of the correlation model:

[0031] Core data from the basic dataset used to characterize the plot ratio features and urban operation status of the target plot are collected and preprocessed to obtain a standardized feature dataset that can be used for model training.

[0032] The standardized feature dataset is used to train an association model using an algorithm to obtain a trained association model, which is then used for:

[0033] Real-time calculation of the correlation between the plot ratio of the target land parcel and urban operation indicators;

[0034] With the goal of adapting the plot ratio to the city's operational status, quantitative correlation data is output based on the aforementioned correlation degree.

[0035] By adopting the above scheme, core data representing plot ratio characteristics and urban operation status are collected and a standardized feature dataset is generated. Combined with algorithm training, a model capable of real-time calculation of correlation is obtained, achieving accurate quantification of the correlation between plot ratio and urban operation indicators. With adaptation as the goal, the quantitative correlation data is output, providing standardized and reusable basic model support for subsequent dynamic correction. This enhances the operability of the overall scheme and the reliability of the model output, and solves the problem of correlation calculation deviation caused by fuzzy data range and unclear training process in traditional model construction.

[0036] In one embodiment, the step of preprocessing the core data in the collected basic dataset used to characterize the plot ratio features and urban operation status of the target plot to obtain a standardized feature dataset that can be used for model training specifically includes the following steps:

[0037] Historical data for characterizing the plot ratio characteristics of the target plot, historical data of indicators for characterizing the urban operation status, and plot spatial characteristic data are extracted from the basic dataset. The historical data of indicators for characterizing the urban operation status includes at least real-time urban operation monitoring data with time-series dimensions for transportation, services, and ecological environment.

[0038] The extracted representative data are preprocessed, including missing value interpolation and imputation, outlier identification and removal, and time scale unification of multi-source data;

[0039] Based on the dynamic interaction mechanism between the plot ratio of the target plot and urban operation indicators, feature mapping is performed on the preprocessed characterization data to generate a model input feature set containing plot ratio gradient features, urban operation indicator response features and spatial interaction features.

[0040] The input feature set is standardized by normalizing each feature value to the interval [0, 1] to obtain a standardized feature dataset.

[0041] By adopting the above scheme, the specific types of representative data (historical floor area ratio data, urban operational sequence data, and spatial feature data) were clarified. Preprocessing, such as missing value imputation and time scale unification, ensured data quality. Based on dynamic interaction mechanisms, targeted features (floor area ratio gradient, operational response, and spatial interaction features) were generated, ultimately resulting in a standardized feature dataset. Feature mapping strengthened the correlation between data and floor area ratio-urban operation, solving the problem of unreliable model input caused by loose correlation between features and targets and poor data quality in traditional data processing. This provides a high-quality data foundation for high-precision training of the correlation model and improves the accuracy of subsequent correlation calculations.

[0042] In one embodiment, the step of training an association model using an algorithm on the standardized feature dataset to obtain a trained association model specifically includes the following steps:

[0043] The standardized feature dataset is divided into a model training set and a validation set according to a preset ratio;

[0044] An initial correlation model is constructed based on the training set. The initial correlation model takes traffic carrying capacity adaptability, service supply and demand balance and ecological constraint satisfaction as the core evaluation dimensions, and sets corresponding quantitative indicators and influence weights for each dimension.

[0045] The quantitative results of each dimension under different plot ratio values ​​are calculated using the initial correlation model, and a comprehensive correlation score is generated by weighted summation.

[0046] The output accuracy of the initial association model is verified using a validation set, requiring that the prediction error of the core evaluation dimensions does not exceed a preset threshold. The weight coefficients and feature parameters of the initial association model are iteratively optimized based on the validation results.

[0047] A trained association model is generated based on the optimized parameters, and the association model is configured as follows:

[0048] Receive real-time urban operation indicator data and candidate plot ratio values ​​for the target plot, and output a comprehensive correlation score between the two.

[0049] With the goal of matching plot ratio with urban operation status, the optimal quantitative correlation relationship that matches urban operation status is selected based on the comprehensive correlation score, forming a quantitative correlation relationship data matrix that includes the influence coefficients of each indicator.

[0050] By adopting the above approach, an initial model is constructed based on core evaluation dimensions (transportation, services, and ecology), and the comprehensive correlation degree is calculated. The model accuracy is ensured through iterative optimization of weight coefficients and feature parameters, ultimately generating a trained model that can output comprehensive correlation scores and a quantified relationship matrix. Through multi-dimensional evaluation, weighted calculation, and parameter optimization, the model can accurately select the optimal correlation relationships that are suitable for the city's operational status. This solves the problem of inaccurate correlation quantification caused by a single evaluation dimension and blind parameter adjustments in traditional model training. Dynamic correction of the floor area ratio provides a reliable quantitative basis, further enhancing the scientific rigor and adaptability of the overall solution.

[0051] This application also relates to an automatic correction system for urban planning floor area ratio, comprising:

[0052] The rule base establishment module is used to collect multi-source data of the target plot, extract core parameters from the multi-source data to construct a basic dataset, build an association model based on the basic dataset, calculate the correlation between the plot ratio and urban operation indicators through the association model, and the association model aims to achieve the adaptation between plot ratio and urban operation status, output quantitative association data, and establish a calculation rule base based on the basic dataset and association data.

[0053] The preliminary correction module is used to calculate the initial benchmark floor area ratio based on the calculation rule base, combined with the spatial characteristic parameters of the target plot and the user input parameters, dynamically correct the initial benchmark floor area ratio in combination with dynamic influencing factors, and output the preliminary correction result.

[0054] The multi-dimensional verification module is used to perform multi-dimensional verification on the preliminary correction results based on the constraints and quantitative association of the correlation data in the calculation rule base, and to perform parameter correction and rule re-matching on the correction results that do not meet the constraints, and to remove invalid correction results.

[0055] The scheme output module is used to output the final plot ratio correction scheme based on the verification results. The correction scheme includes at least the corrected plot ratio value, rule matching basis, supporting optimization implementation suggestions, and includes adaptive adjustment strategies corresponding to dynamic influencing factors.

[0056] The dynamic optimization module is used to dynamically update the calculation rule base, the quantitative correlation parameters of the correlation model and the correlation relationship data, as well as the weight parameters of dynamic influencing factors, based on the feedback data of the entire development life cycle of the target plot.

[0057] This application also relates to a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for automatic correction of urban planning floor area ratio.

[0058] This application also relates to a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for automatic correction of urban planning floor area ratio.

[0059] The urban planning floor area ratio automatic correction method and system provided in the above embodiments have the following beneficial effects:

[0060] By constructing a correlation model and calculation rule base using multi-source data, a quantitative correlation between plot ratio and urban operation indicators is achieved. The initial benchmark plot ratio is dynamically corrected and verified in multiple dimensions by combining dynamic influencing factors, which improves the accuracy and adaptability of plot ratio calculation. At the same time, by outputting a correction scheme that includes adaptive adjustment strategies and a dynamic update mechanism throughout the entire life cycle, the problems of static lag, lack of systematic correlation, reliance on manual labor, and difficulty in long-term adaptation of traditional methods are effectively solved. This achieves automated and dynamic correction of plot ratio, ensuring the scientific nature and sustainability of planning schemes. Attached Figure Description

[0061] Figure 1 A flowchart of an automatic correction method for urban planning floor area ratio provided in an embodiment of the present invention;

[0062] Figure 2 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0063] The technical solutions in the embodiments of the present invention will now be clearly and completely described in conjunction with the accompanying drawings.

[0064] Reference Figure 1 One embodiment of the present invention provides an automatic correction method for urban planning floor area ratio, comprising the following steps:

[0065] S10. Collect multi-source data of the target plot, extract core parameters from the multi-source data to construct a basic dataset, construct an association model based on the basic dataset, calculate the correlation between the plot ratio and urban operation indicators through the association model, and output quantitative association data with the goal of adapting the plot ratio to the urban operation status. Based on the basic dataset and the association data, establish a calculation rule base.

[0066] In this embodiment, this step aims to build a foundational framework of "data support + quantitative model + rule basis" for subsequent correction processes, avoiding distorted results or inapplicability due to "lack of data anchors, lack of related logic, and lack of constraint standards" in subsequent calculations. For input data, multi-source data of the target plot is used (including static basic data: statutory planning parameters such as land use nature and maximum floor area ratio; spatial attribute data such as plot area and shape; and dynamic supplementary data: real-time urban operation monitoring data such as traffic flow and service facility usage frequency; and post-development life-cycle prediction data such as population growth prediction during the planning period). Specifically:

[0067] Construct a basic dataset and extract core parameters from multi-source data (such as "land use is residential + plot area is 50,000 square meters"). +Morning rush hour traffic flow 3000 vehicles / hour +800 meters from XX station of Metro Line 2”, after data cleaning (missing values ​​are filled with the average of the past 3 days, and outliers such as extreme traffic data are removed), it is organized into a structured basic dataset according to the "static-dynamic" classification.

[0068] Construct a correlation model and output quantitative correlation data. With the goal of "adapting plot ratio to urban operation status" (e.g., plot ratio needs to match traffic capacity and service supply and demand), train the correlation model (e.g., random forest model that integrates time series analysis), calculate the correlation between plot ratio and urban operation indicators (e.g., "for every 0.5 increase in plot ratio, the morning rush hour traffic delay in the surrounding area increases by 15%; within 1 kilometer of a subway station, for every 0.3 increase in plot ratio, the public transportation modal share increases by 8%), and finally output a quantitative correlation data matrix containing correlation coefficients.

[0069] Establish a calculation rule base, based on the static constraints of the basic dataset (such as the upper limit of the plot ratio in the control plan of 1.8) and the quantitative logic of the correlation data, and construct three layers of rules: basic calculation rules (such as "the plot ratio benchmark of rectangular plots is 0.2 higher than that of irregular plots; within 1 kilometer of municipal transportation facilities (such as subway stations), the plot ratio benchmark can be increased by an additional 0.1"), constraint rules (such as "basic plot + transfer plot + bonus plot ≤ upper limit of the control plan"), and dynamic adjustment rules (such as "when the traffic carrying capacity adaptability is <0.7, the plot ratio needs to be reduced by 0.1").

[0070] The output basic dataset, quantitative correlation data, and calculation rule base provide "traceable and reusable" underlying support for the subsequent preliminary calculation of S20 and compliance verification of S30, and are the core foundation of the entire automatic calibration process.

[0071] It should be noted that this data can be obtained by those skilled in the art through online open data platforms, the official websites of relevant industry authorities, and professional data service platforms (such as geographic information service platforms and corresponding urban operation monitoring platforms).

[0072] S20. Based on the calculation rule base, combined with the spatial characteristic parameters of the target plot and the user input parameters, the initial benchmark plot ratio is calculated, and the initial benchmark plot ratio is dynamically corrected in combination with dynamic influencing factors, and the preliminary correction result is output.

[0073] In this embodiment, this step aims to generate a "preliminary adaptation value" from the "static benchmark value" based on the rule base of S10, combined with the actual characteristics and dynamic changes of the land parcel, to avoid the problem of "detachment from the actual scenario" caused by calculating only according to fixed standards. For the input data, on the one hand, the calculation rule base output by S10 is called, and on the other hand, the spatial characteristic parameters of the target land parcel (such as a street-facing length of 300 meters, a rectangular shape, and a distance of 800 meters from XX station of Metro Line 2), user input parameters (such as the developer's expectation to build one kindergarten), and dynamic influencing factors (such as real-time morning peak traffic flow exceeding the capacity limit by 10%, the daily passenger flow of the metro station reaching 90% of the design capacity, and a certain gap in the service capacity of surrounding kindergartens, such as 200 kindergartens); specifically:

[0074] Calculate the initial benchmark plot ratio by calling the basic calculation rules in the rule base and substituting the spatial feature parameters into the "spatial feature - plot ratio benchmark" association formula (e.g., "rectangular plot + street frontage ≥ 200 meters + within 1 kilometer of a subway station → plot ratio benchmark 1.6") to generate an initial plot ratio candidate range (1.3-1.6). Combined with the user input parameters (the supporting kindergarten meets the "service supporting reward rules"), select the upper limit value of 1.6 from the candidate range as the initial benchmark plot ratio.

[0075] Dynamic correction calculations are performed, dynamic influencing factors are extracted, and weights are assigned according to the dynamic adjustment rules in the rule base (traffic factors weight 40%, service factors weight 35%). The correction values ​​are calculated as follows: traffic congestion needs to be reduced by 0.1, subway station passenger flow is close to saturation and needs to be reduced by an additional 0.05, and the service capacity gap of surrounding kindergartens can be increased by 0.2 due to the construction of supporting kindergartens. At the same time, the transfer volume (transfer from low-density areas to the area by 0.1) is added to obtain the preliminary correction result (1.6-0.1-0.05+0.2+0.1=1.75).

[0076] For preliminary constraint verification, the total constraint rule ("Basic + Transfer + Reward ≤ Control Planning Upper Limit 1.8") is called from the rule base. If 1.75 meets the constraint, the preliminary correction result is directly output. If the calculation result exceeds the upper limit (such as 1.9), it will automatically revert to 1.8.

[0077] The output of preliminary correction results takes into account legal constraints, user needs, and dynamic changes in the city, reducing the amount of invalid work for subsequent S30 verification and ensuring that the preliminary results have "basic compliance".

[0078] It should be noted that the non-core execution steps involved in this step, such as the basic data call operation of substituting parameters into the rule base, the basic calculation of the correction range (such as percentage conversion), and the structured recording of preliminary results, are all conventional technical means in the field of data processing and rule application. Those skilled in the art can flexibly adjust them according to the actual scenario of the land parcel.

[0079] S30. Based on the constraints and quantitative association of the relationship data in the calculation rule base, the preliminary correction results are checked in multiple dimensions, and the correction results that do not meet the constraints are corrected by parameters and rematched by rules, and invalid correction results are eliminated.

[0080] In this embodiment, this step aims to perform a triple check of "legality, adaptability, and logic" on the preliminary results of S20 using the constraint rules of S10 and the quantitative correlation data, eliminating invalid solutions and avoiding "implementation risks" (such as exceeding the control requirements of ecologically sensitive areas or the inability of transportation to carry the load) due to calculation deviations. For the input data, on the one hand, the preliminary correction result output by S20 (e.g., 1.75) is called, and on the other hand, the calculation rule base constraints of S10 (the upper limit of the control plan is 1.8, and the plot ratio in ecologically sensitive areas shall not exceed 1.5) and the quantitative correlation data of S10 (the traffic carrying capacity adaptability and service supply and demand balance corresponding to a plot ratio of 1.75) are used; specifically:

[0081] Multi-dimensional verification: legality verification (1.75 ≤ the upper limit of the control plan 1.8, and the plot is not located in an ecologically sensitive area, meeting the requirements); adaptability verification (based on correlation data, the traffic carrying capacity adaptability of a plot ratio of 1.75 is 0.75 ≥ the threshold of 0.7, the passenger flow carrying capacity adaptability of subway stations is 0.8 ≥ the threshold of 0.7, and the service supply and demand balance is 0.85 ≥ the threshold of 0.7, adapting to urban operation); logical verification (the transfer volume of 0.1 ≤ 20% of the basic volume of 1.6, and the bonus volume of 0.2 comply with the rule of "building a kindergarten", and are logically compliant).

[0082] Parameter correction and rule rematching: If the initial results show that the adaptability is not up to standard (e.g., the passenger flow carrying capacity adaptability of subway stations is 0.65 < 0.7), then the weight of dynamic influencing factors will be adjusted (the weight of subway traffic factors will be increased to 45%), and the correction value will be recalculated (e.g., reduced from 0.1 to 1.65); if the logic is inconsistent (e.g., the transfer volume exceeds 30%), then the "cross-regional transfer rule" will be rematched, and the transfer volume will be reduced to 0.15.

[0083] Invalid results are removed. Results that still exceed legal constraints (such as exceeding the upper limit of the control plan) or whose fit is consistently below 0.6 after correction are directly removed, and only valid results that meet all conditions (such as 1.75) are retained.

[0084] The effective correction results ensured the "legality and compliance + urban adaptability" of the plot ratio scheme, laying a reliable foundation for the subsequent output of the S40 scheme.

[0085] It should be noted that the non-core execution steps involved in this process, such as the basic sequence control of the verification process, the basic numerical calculation of parameter correction, and the marking and storage of invalid results, are all conventional technical means in the field of data verification and rule application. Those skilled in the art can flexibly adjust the operation details according to the specific constraint type of the land parcel (such as ecological constraints or traffic constraints).

[0086] S40. Output the final floor area ratio correction scheme based on the verification results. The correction scheme shall include at least the corrected floor area ratio value, the rule matching basis, and the supporting optimization implementation suggestions, and shall include adaptive adjustment strategies corresponding to dynamic influencing factors.

[0087] In this embodiment, this step aims to transform the effective results of S30 into a complete solution that is "executable, interpretable, and adjustable," solving the problem of traditional solutions that "only provide numerical values ​​without supporting evidence," and providing clear guidance for planning and implementation. For the input data, on the one hand, the effective correction results output by S30 (such as 1.75) are called; on the other hand, the calculation rule base of S10 (rule matching basis) and the dynamic influencing factors of S20 (adaptive adjustment strategy basis) are used; specifically:

[0088] The integrated plan's core content is defined by three main modules: the corrected plot ratio (1.75); the rule matching basis ("Based on the basic rule of 'rectangular plot + 300 meters from the street + close to Metro Line 2 XX station,' a baseline of 1.6 is obtained. Combined with '0.2 bonus for supporting kindergarten construction + 0.1 reduction for traffic congestion + 0.05 reduction for metro passenger flow saturation + 0.1 transfer plot ratio,' the final result is 1.75, which meets the upper limit of 1.8 in the control plan"); and supporting optimization implementation suggestions ("A plot ratio of 1.75 requires the simultaneous construction of 200 parking spaces and a 6-class kindergarten; optimize the pedestrian corridor design from the plot to the metro station to improve public transportation accessibility").

[0089] Develop a dynamic adaptive adjustment strategy and clarify subsequent adjustment rules for the dynamic influencing factors of S20 ("If the Metro Line 3 opens in the future, the public transportation modal share around the plot will increase to 60%, and the plot ratio can be increased to 1.8; if the passenger flow of Metro Line 2 Station XX exceeds the design capacity by 15%, it needs to be reduced to 1.65 to alleviate traffic pressure").

[0090] The final floor area ratio correction scheme output provides specific values, as well as clarifies the "calculation basis" and "subsequent adjustment direction," ensuring that the scheme is flexible and operable during the implementation phase.

[0091] S50. Based on feedback data throughout the entire development lifecycle of the target land parcel, dynamically update the calculation rule base, the quantitative correlation parameters of the correlation model and correlation relationship data, as well as the weight parameters of dynamic influencing factors.

[0092] In this embodiment, this step aims to iteratively optimize the basic data, correlation model, and calculation rules of S10 through actual feedback from the entire development lifecycle of the target plot, avoiding the "poor long-term adaptability" problem caused by "using the calculation once and for all," and achieving self-upgrading of the correction method. For the input data, feedback data from the entire development lifecycle of the target plot is used (construction phase: actual plot ratio deviation, such as 1.75→1.7; operation phase: real-time traffic flow changes, such as peak hour traffic decreasing to 2500 vehicles / hour, daily passenger flow at Metro Line 2 station XX increasing to 110% of design capacity, service facility usage data, such as the gap in the service capacity of kindergartens decreasing to 50; 5 years later: Metro Line 3 opens, and the public transportation modal share within 1 kilometer of the plot increases to 55%). Specifically:

[0093] Update the calculation rule base and correlation data, adjust the rules based on feedback data (e.g., "the floor area ratio benchmark correction coefficient within 1 kilometer of municipal transportation facilities (such as subway stations) is increased from 0.1 to 0.15, because the accessibility of public transportation has been significantly improved after the opening of Metro Line 3"; the bonus floor area ratio for supporting kindergartens is decreased from 0.2 to 0.15, because the actual service capacity gap of kindergartens is smaller than predicted), and correct the correlation data (e.g., "for every 0.5 increase in floor area ratio, the actual traffic delay increases by 12%, and the original correlation coefficient is corrected from 15% to 12%)).

[0094] Optimize the correlation model by retraining it with feedback data (such as actual data on "plot ratio-metro passenger flow-service" over the past 5 years) and adjusting feature weights (such as increasing the weight of metro traffic factors from 40% to 45%, because the metro has a greater impact on residents' travel in actual operation).

[0095] The updated calculation rule base, correlation model, and quantitative correlation parameters output will be fed back to S10, providing more accurate basic support for the subsequent plot ratio correction of similar plots, and realizing the long-term adaptation and iterative upgrade of the correction method.

[0096] In one embodiment, step S10 involves collecting multi-source data of the target plot and extracting core parameters from the multi-source data to construct a basic dataset, specifically including the following steps:

[0097] S101. Divide the multi-source data of the target plot into static basic data and dynamic supplementary data according to data attributes. The static basic data includes at least the statutory planning parameters, spatial attribute data and fixed control indicators of the target plot. The dynamic supplementary data includes at least the real-time urban operation monitoring data within the preset range of the target plot and the full life cycle prediction data within the preset period after the development of the target plot.

[0098] S102. Extract static core indicators from static basic data and corresponding dynamic related indicators from dynamic supplementary data. Establish the mapping relationship between the two types of indicators through quantitative analysis algorithms, generate a correlation map, and realize the correlation fusion of static rules and dynamic influences.

[0099] S103. Integrate static basic data, dynamic supplementary data, and quantitative relationships in the correlation graph. Select core parameters according to data cleaning rules and organize them by label according to scene characteristics to build a basic dataset.

[0100] In this embodiment, the core purpose of steps S101 to S103 is to solve the problems of "disorganized classification, static and dynamic separation, and parameter redundancy" in multi-source data. Through a three-layer process of "data classification → static and dynamic fusion → integration, cleaning, and labeling," the scattered raw data is transformed into a "structured, relational, and directly callable" basic dataset. This provides high-quality data support for the subsequent construction of the association model and establishment of the calculation rule base in S10, avoiding distortion or inefficiency in subsequent quantitative analysis due to data quality issues. Specifically, as follows:

[0101] Step S101 aims to classify and organize multi-source data by clarifying the differences in the "long-term stability / short-term change" attributes of the data, avoiding the omission of key information when extracting core parameters due to data type confusion (such as misclassifying static data like subway station locations as dynamic data, leading to duplicate collection or omissions). For input data, multi-source raw data of the target site are used (such as statutory planning documents issued by the Municipal Natural Resources Bureau, spatial layer data from the geographic information platform, real-time data from the Municipal Transportation Operation Monitoring Platform, and full life-cycle prediction reports prepared by the development unit, etc.); specifically:

[0102] The static basic data is divided into categories, and core data that are "unchanged for a long period of time or have a change cycle of more than 5 years" are selected. This data must include at least three types of information: statutory planning parameters (such as land use nature as "Class II residential land", maximum plot ratio of 1.8, and land use term of 70 years); spatial attribute data (such as plot area of ​​50,000 square meters). The plot is rectangular in shape, 800 meters from XX Station on Metro Line 2, with a street frontage of 300 meters and a building height limit of 60 meters; fixed control indicators (such as the 100-meter west side of the plot being an ecologically sensitive area, and the prohibition of constructing high-pollution facilities within the plot);

[0103] The data is categorized into dynamically supplemented data, and core data that is "updated in real time or changes in short term (cycle ≤ 1 year)" is selected. This data must include at least two types of information: real-time urban operation monitoring data (e.g., morning peak traffic flow of 3000 vehicles / hour around the site, daily passenger flow of XX station on Metro Line 2 of 25,000, service capacity gap of 200 kindergartens in the surrounding area, daily average PM2.5 concentration of 35 μg / L around the site). Full life-cycle forecast data (such as a 15% increase in the surrounding population during the planning period after the land is developed, a 40% increase in passenger flow at XX station after the opening of Metro Line 3, and a 90% saturation of surrounding commercial facilities in 5 years).

[0104] At the same time, separate data catalogs were established for the two types of data, marking the data source (such as statutory planning parameters from the official website of the Municipal Bureau of Natural Resources and subway passenger flow data from the monitoring platform of the Municipal Transportation Commission) and update cycle (static data "updated on demand" and dynamic data "updated in real time / daily").

[0105] The output of classified static basic data and dynamic supplementary data clearly defines the scope of different attribute data. It retains long-term stable basic information such as "legal constraints and spatial characteristics" while incorporating dynamic variables such as "real-time operation and future prediction". This lays the classification foundation for subsequent static and dynamic data fusion and avoids the inefficiency caused by "mixing them up" in traditional data processing.

[0106] Step S102 aims to break down the disconnect between static and dynamic data by establishing a logical association between "static basic features → dynamic operational response" through a quantification algorithm (e.g., the association between "static distance of the land parcel from the subway" and "dynamic changes in subway passenger flow"), thus avoiding biased results from subsequent calculations relying solely on either static or dynamic data. For the input data, it utilizes both the static basic data segmented in S101 and the dynamic supplementary data output from S101; specifically:

[0107] Extract core indicators from static basic data (such as "distance to subway station 800 meters", "land use (residential)", "land area 50,000 square meters"). “Building height limit 60 meters”, and extract corresponding dynamic correlation indicators from the dynamic supplementary data (such as “average daily passenger flow of subway stations is 25,000 people”, “morning peak traffic flow of surrounding areas is 3,000 vehicles / hour”, “kindergarten service capacity saturation is 85%”).

[0108] Establish a quantitative mapping relationship, and use quantitative analysis algorithms (such as Pearson correlation analysis and time series data matching algorithms) to calculate the correlation strength between the two types of indicators, forming a traceable mapping relationship:

[0109] Example 1: The mapping relationship between "800 meters away from the subway station" (static) and "25,000 passengers per day at the subway station" (dynamic) is "For every 100 meters the distance between the plot and the subway station decreases, the subway's passenger flow attraction to the plot increases by 12%";

[0110] Example 2: The mapping relationship between "the land use is residential" (static) and "the surrounding morning peak traffic flow is 3,000 vehicles / hour" (dynamic) is "for every 0.1 increase in the plot ratio of residential land, the surrounding morning peak traffic flow increases by 8%";

[0111] Generate a correlation graph that presents static indicators, dynamic indicators, and quantitative mapping relationships (correlation coefficients, influence ratios) in a visual graph format. The graph nodes are various indicators (such as "subway distance", "subway passenger flow", "traffic flow"), and the lines between nodes indicate the mapping relationship (such as "800 meters away → passenger flow attraction +12%)", intuitively presenting the correlation logic between static and dynamic data.

[0112] The output correlation graph and quantitative mapping relationship break down the separation between static and dynamic data, providing a direct quantitative correlation basis for the subsequent construction of correlation models in S10 and the calculation of the "correlation degree between plot ratio and urban operation indicators", avoiding the subjectivity of correlation logic (such as judging the impact of subway on plot ratio based on experience).

[0113] Step S103 aims to remove redundant data, correct outlier data, and select parameters that have a core impact on "floor area ratio correction." It also uses scenario-based labels to make the dataset easier to access, preventing subsequent model and rule base computational inefficiencies or result deviations due to "parameter redundancy and data errors." For the input data, it utilizes both the static basic data and dynamic supplementary data from S101, and the correlation graph and quantized mapping relationships output from S102; specifically:

[0114] Data integration involves combining static basic data and dynamic supplementary data according to "indicator categories" (such as "transportation", "service", "spatial", "ecological"). The quantitative mapping relationship in the correlation map is attached to the corresponding indicator as "data description" (such as "800 meters from the subway" followed by "corresponding subway passenger flow attraction +12%)).

[0115] Data cleaning involves processing data according to preset cleaning rules, including:

[0116] Missing values ​​are imputed (e.g., if passenger flow data for a certain station on Metro Line 2 is missing on a certain day, it is filled with the average of 25,000 passengers over the past 3 days); outliers are removed (e.g., if traffic flow reaches an abnormal 10,000 vehicles / hour at a certain moment, it is determined to be equipment malfunction data and removed, and replaced with the average of 3,000 vehicles / hour during the morning rush hour of that day); redundant values ​​are deleted (e.g., parameters such as "plot perimeter" and "plot soil pH value" that are not related to the calculation of plot ratio are deleted).

[0117] Core parameter screening and tagging: Screening is performed on core parameters that directly impact plot ratio correction (such as "land use, maximum plot ratio in the control plan, distance to subway stations, average daily subway passenger flow, traffic flow, and gaps in school service capacity"), and then tagging them according to scenario characteristics.

[0118] Example: Label the combination of parameters "800 meters from the subway + residential land use + daily subway passenger flow of 25,000" as "residential plot along the subway line";

[0119] The parameter combination of "traffic flow of 3,000 vehicles / hour + control plan upper limit of 1.8" is labeled as "traffic-sensitive plot";

[0120] Output a structured basic dataset, organized hierarchically by “scene label → indicator category → specific parameter → relationship” (e.g., “residential plots along the subway line → transportation category → distance from the subway 800 meters (related passenger flow attraction +12%)”).

[0121] The output structured basic dataset combines "accuracy (after cleaning), correlation (including mapping relationships), and ease of use (scene labels)", providing directly usable core data for the subsequent S10 to build correlation models (requiring the calling of correlation parameters between subway passenger flow and plot ratio) and establish a calculation rule base (requiring the calling of static constraints such as the upper limit of the control plan). It is the data cornerstone of the entire automatic correction process.

[0122] In one embodiment, in step S10, the step of establishing a calculation rule base based on the basic dataset and the associated relationship data, specifically includes:

[0123] The basic rules layer is built on the basic dataset and quantified relational data, including the association rules between spatial features and basic volume benchmarks, as well as the quantified correspondence rules between urban operation indicators and volume changes.

[0124] The constraint rule layer is constructed based on the statutory planning parameters in the basic dataset. It includes the sum constraint rules of the basic volume, the transfer volume and the bonus volume, the proportional constraint rules of a single volume type and the adaptation range constraint rules of user input parameters.

[0125] The dynamic adjustment rule layer is built based on dynamically supplemented data and includes weight allocation rules for different types of dynamic influencing factors, cross-regional adjustment rules for transfer volume, positive incentive rules for reward volume, and inter-layer correction rules when the basic rule layer and constraint rule layer trigger linkage.

[0126] In this embodiment, the core purpose of "establishing a calculation rule base" in step S10 is to solve the problems of traditional rule bases being "static and singular, lacking hierarchical constraints, and having poor dynamic adaptability." By constructing a three-layer structured system of "basic rule layer + constraint rule layer + dynamic adjustment rule layer," it integrates "basic calculation logic, legally binding constraints, and dynamic adaptation strategies," providing a "quantifiable, constrainable, and dynamically adjustable" rule basis for subsequent initial floor area ratio calculation in S20 and multi-dimensional verification in S30. This avoids the floor area ratio correction results from exceeding legal requirements and deviating from the actual operation of the city due to chaotic or missing rules. Specifically, as follows:

[0127] The basic rules layer aims to establish a quantitative correlation logic between "spatial characteristics → basic floor area ratio" and "urban operation indicators → floor area ratio changes," providing an initial benchmark for floor area ratio calculation and avoiding calculation deviations caused by setting the basic floor area ratio solely based on experience. Its construction is based on the basic dataset generated in S10 (including spatial attribute data and urban operation indicator data) and quantitative correlation data (such as the mapping relationship between spatial characteristics and urban operation indicators); specifically:

[0128] Association rules between spatial features and basic volume benchmarks: Based on the spatial attribute data in the basic dataset, establish the correspondence between "spatial feature parameters → basic volume benchmarks" to clarify the initial volume benchmark values ​​under different spatial conditions, for example:

[0129] Land parcel shape characteristics: The basic floor area ratio of rectangular land parcels is 0.2 higher than that of irregular land parcels (e.g., 1.5 for rectangular land parcels and 1.3 for irregular land parcels).

[0130] Municipal transportation facilities associated characteristics: If the plot is located within 1 kilometer of a subway station, the basic floor area ratio benchmark will be increased by 0.1 (e.g., the benchmark for plots not along the subway line is 1.5, and the benchmark for plots along the subway line is 1.6).

[0131] Street-front length characteristics: For plots with a street-front length of ≥300 meters, the basic floor area ratio benchmark is 0.15 higher than that for plots with a street-front length of <200 meters (e.g., benchmark is 1.6 for 300-meter street-front plots and 1.45 for 150-meter street-front plots).

[0132] Quantitative Correspondence Rules between Urban Operation Indicators and Floor Area Ratio Changes: Based on quantitative correlation data, establish a quantitative relationship of "changes in urban operation indicators → floor area ratio adjustment range" to clarify the impact of urban operation status on floor area ratio. For example:

[0133] Subway passenger flow indicators: For every 10% increase in the average daily passenger flow of a subway station over its design capacity, the plot floor area needs to be reduced by 0.05 (e.g., if the passenger flow exceeds the capacity by 20%, the plot floor area will be reduced from 1.6 to 1.5).

[0134] Traffic flow indicators: For every 15% increase in the surrounding morning peak traffic flow over the capacity limit, the volume needs to be reduced by 0.08 (e.g., if the traffic flow exceeds the capacity by 30%, the volume will be reduced from 1.5 to 1.34).

[0135] Service indicators: For every 10% reduction in the gap in the capacity of surrounding kindergartens, the floor area ratio can be increased by 0.03 (e.g., if the gap decreases from 20% to 10%, the floor area ratio can be increased from 1.5 to 1.53).

[0136] The quantitative correlation rules output by the basic rule layer provide the core calculation logic of "spatial adaptation and operational correlation" for S20 to calculate the initial benchmark floor area ratio, ensuring that the initial floor area ratio not only conforms to the spatial characteristics of the plot, but also matches the actual state of urban operation.

[0137] The constraint rules layer aims to establish a triple rigid boundary for floor area ratio (FAR) calculation based on statutory planning parameters: total volume constraints, proportional constraints, and parameter constraints. This prevents FAR from exceeding statutory requirements or logical contradictions due to calculation errors, ensuring the legality and compliance of the correction results. Its construction is based on the statutory planning parameters in the basic dataset (such as the upper limit of the control plan's FAR and land use constraints); specifically:

[0138] The rule governing the sum of basic floor area ratio, transferred floor area ratio, and bonus floor area ratio is as follows: It is explicitly stated that the sum of "basic floor area ratio (calculated at the basic rule level) + transferred floor area ratio (floor area transferred across regions) + bonus floor area ratio (additional floor area ratio obtained from the construction of public facilities)" must not exceed the statutory maximum floor area ratio stipulated in the control plan. For example:

[0139] If the maximum floor area ratio in the control plan is 1.8, the basic floor area ratio is 1.6, the transfer floor area ratio is 0.1, and the bonus floor area ratio is 0.1, then the total is 1.8 (1.6 + 0.1 + 0.1), which meets the constraints; if the bonus floor area ratio is 0.2, then the total is 1.9 > 1.8, which exceeds the constraints.

[0140] Single-unit floor area ratio constraint rules: Clearly define the maximum proportion of transferable floor area and bonus floor area to the basic floor area ratio to avoid an excessively high proportion of a single floor area type leading to an unbalanced floor area structure. For example:

[0141] The transfer volume is ≤ 20% of the basic volume (e.g., if the basic volume is 1.6, the maximum transfer volume is 0.32; exceeding this is a violation); the bonus volume is ≤ 15% of the basic volume (e.g., if the basic volume is 1.6, the maximum bonus volume is 0.24; exceeding this is a violation).

[0142] User input parameter adaptation range constraints rules: It is clearly stipulated that parameters such as "expected plot ratio" and "requirements for supporting business types" input by the developer must be within the legal and regulatory limits to prevent user demands from exceeding rigid constraints. For example:

[0143] If the upper limit of the control plan is 1.8, and the user inputs "expected plot ratio 2.0", then the constraint will be triggered, and the user parameters will be automatically adapted to within 1.8; if the user proposes "50% of the supporting commercial area", but the legal land use nature is "mainly residential (commercial area ≤ 30%)", then the user parameters will be constrained to within 30%.

[0144] The rigid constraint rules output by the constraint rule layer provide a legal basis for the preliminary constraint verification of S20 and the legality verification of S30, ensuring that the plot ratio calculation results do not exceed the legal planning boundaries, which is the core guarantee for the legal implementation of the correction scheme.

[0145] The dynamic adjustment rule layer aims to establish flexible rules based on dynamically supplemented data (such as real-time urban operation monitoring data and short-term forecast data), including "dynamic factor weight allocation, cross-regional adjustment, positive incentives, and inter-layer linkage correction." This avoids the inability to adapt to dynamic changes in urban operations (such as sudden increases in subway passenger flow or changes in service gaps) due to fixed rules. Its construction is based on the dynamically supplemented data (including real-time monitoring and full lifecycle forecast data) defined in S10; specifically:

[0146] Weighting rules for different types of dynamic influencing factors: Differential weights are assigned based on the degree of impact of dynamic factors on the floor area ratio, ensuring that key dynamic factors are given priority consideration. For example:

[0147] Transportation factors (such as subway passenger flow and morning rush hour traffic flow) have a weight of 45%, service factors (such as gaps in school service capacity) have a weight of 35%, and ecological factors (such as PM2.5 concentration) have a weight of 20%. If subway passenger flow exceeds capacity by 30% during a certain period (far exceeding the normal 10%), the weight of transportation factors will be temporarily increased to 60%, and traffic pressure will be alleviated first by reducing the capacity.

[0148] Cross-regional adjustment rules for transferred volume: Clearly define the "transfer-in conditions and transfer-out restrictions" for cross-regional transferred volume to avoid blind transfers leading to regional volume imbalances. For example:

[0149] Transfer conditions: The transfer area must meet the following requirements: "Service facility carrying capacity ≥ the needs of the next 3 years" (e.g., if a new primary school is planned around the transfer area, it can accommodate the transferred floor area) and "Traffic carrying capacity adaptability ≥ 0.7" (e.g., if the transfer area is close to Metro Line 3 and the traffic pressure is low).

[0150] Transfer restrictions: The floor area ratio of the area to be transferred out shall not be lower than the statutory minimum (e.g., if the minimum floor area ratio for residential land is 1.0, it shall not be lower than 1.0 after the transfer).

[0151] Positive incentive rules for bonus floor area ratio: Clearly define the bonus floor area ratio that can be obtained for the construction of "high-priority public facilities" to guide developers to cooperate with the improvement of urban services. For example: a bonus floor area ratio of 0.1 is given for the construction of a pedestrian corridor from the plot to the subway station; a bonus floor area ratio of 0.15 is given for the construction of a public-benefit kindergarten (6 classes or more).

[0152] Inter-layer correction rules when the basic rule layer and constraint rule layer trigger linkage: When the calculation result of the basic rule layer exceeds the boundary of the constraint rule layer, the correction logic is automatically triggered to ensure that the result is compliant. For example:

[0153] If the basic rule layer calculates "basic volume 1.6 + transfer volume 0.3 + bonus volume 0.2 = 2.1" (exceeding the upper limit of constraint rule layer 1.8), it will automatically correct in the order of "first subtracting bonus volume (from 0.2 to 0.1), then subtracting transfer volume (from 0.3 to 0.1)" until the sum of 1.8 (1.6 + 0.1 + 0.1) meets the constraint.

[0154] The flexible adaptation rules output by the dynamic adjustment rule layer provide a dynamic basis for the dynamic correction of the initial floor area ratio in S20 and the parameter correction in S30, ensuring that the floor area ratio calculation can be adjusted in real time according to the city's operating status, taking into account both compliance and dynamic adaptability.

[0155] In summary, the three rule layers work together to form a complete calculation rule base that is "logical in basic calculations, bounded by legal constraints, and adaptable to dynamic changes." This provides full-process rule support for the subsequent S20~S40 floor area ratio correction, and the layered design ensures that the rules are "traceable, adjustable, and reusable," avoiding the limitations of traditional single rule bases.

[0156] In one embodiment, step S20 specifically includes the following steps:

[0157] S201. Extract spatial feature parameters of the target plot from the spatial attribute data in the basic dataset, receive user input parameters, call the basic rule layer of the calculation rule base, substitute the spatial feature parameters into the association rule between spatial features and basic floor area ratio benchmark, and generate initial floor area ratio candidate intervals.

[0158] S202. Based on the initial floor area ratio candidate interval, and in combination with the user input parameters and the user input adaptation range constraint rules of the constraint rule layer, select the values ​​that meet the requirements from the initial floor area ratio candidate interval as the initial benchmark floor area ratio.

[0159] S203. Call the dynamically supplemented data, extract the dynamic influencing factors related to the transfer volume and the reward volume, assign corresponding weights according to the weight allocation rules of different types of dynamic influencing factors based on the dynamic adjustment rule layer of the calculation rule base, and determine the correction value of the transfer volume and the correction value of the reward volume by combining the cross-regional adjustment rule of the transfer volume and the positive incentive rule of the reward volume respectively.

[0160] S204. Based on the initial benchmark floor area ratio, the correction value of the transfer floor area ratio, and the correction value of the bonus floor area ratio, a preliminary correction result of the initial benchmark floor area ratio is calculated using a preset correction formula.

[0161] S205. Based on the preliminary correction result, the sum constraint rules of the basic volume, transfer volume and reward volume of the constraint rule layer and the proportional constraint rules of a single volume type are called for verification; if the preliminary correction result exceeds the constraint threshold, the inter-layer correction rules of the dynamic adjustment rule layer are automatically called back to meet the constraint requirements, and the final preliminary correction result is output.

[0162] In this embodiment, steps S201 to S205 are the detailed execution flow of S20, "calculating the initial benchmark floor area ratio and dynamically correcting it." The core purpose is to solve the problems of "no basis for the initial floor area ratio, no rules for dynamic correction, and results that are prone to exceeding constraints." Through a closed loop of "extracting parameters → filtering benchmarks → dynamically calculating corrections → superimposing results → verification callbacks," "spatial characteristics, user needs, dynamic factors, and legal constraints" are integrated into the floor area ratio calculation. This provides a preliminary correction result that is "basically compliant and in line with reality" for the subsequent multi-dimensional verification in S30, avoiding results that are out of context or illegal due to missing calculation procedures. Specifically, as follows:

[0163] Step S201 aims to determine the initial selectable range of floor area ratio (FAR) based on the spatial characteristics and fundamental rules of the land parcel, avoiding range deviations caused by initial calculations relying on experience without a benchmark. Its input data comes from two sources: the basic dataset generated in S10 (spatial attribute data, such as land parcel shape, subway distance, and street frontage length), and user parameters input by the developer (such as required supporting facilities and desired FAR direction). Simultaneously, it calls the basic rule layer of the calculation rule base established in S10; specifically:

[0164] Parameter extraction: Extract spatial feature parameters from the basic dataset, such as: target plot is "rectangular shape + distance from XX station of Metro Line 2 + street length of 300 meters"; receive user input parameters: "expect to build a 6-class kindergarten, with priority given to residential functions";

[0165] Rule Invocation and Interval Generation: Invoke the "Spatial Features and Basic Volume Benchmark Association Rules" of the basic rule layer and match spatial parameters one by one: Rectangular plot → Basic volume benchmark 1.5; Within 1 km of subway station → Increase by an additional 0.1, benchmark becomes 1.6; Street length 300 meters (≥300 meters) → Increase by an additional 0.1, benchmark becomes 1.7;

[0166] Based on comprehensive spatial characteristics, an initial candidate range for floor area ratio is generated: 1.3-1.7 (the lower limit is the minimum basic floor area ratio of similar plots in the same area, and the upper limit is the benchmark value for matching the current spatial characteristics).

[0167] The output initial floor area ratio candidate range (1.3-1.7) provides a spatial adaptation range for subsequent selection of initial benchmark floor area ratios, ensuring that the initial value does not deviate from the spatial conditions of the plot itself.

[0168] Step S202 aims to select initial baseline values ​​from the candidate intervals that meet "user needs + legal constraints," avoiding user parameters exceeding the rules or arbitrary values ​​within the interval. Its input data consists of the initial floor area ratio candidate interval (1.3-1.7) output from S201, the user input parameters, and simultaneously calls the "user input parameter adaptation range constraint rule" in the constraint rule layer of the calculation rule base; specifically:

[0169] User parameters and constraints match: The user inputs "build 1 six-class kindergarten", and the constraint rule is invoked: "The tolerance area for building a public-benefit kindergarten can be relaxed, but it shall not exceed the upper limit of the initial candidate interval"; the user did not make a "exceeding the upper limit of the interval" requirement, so the constraint is met;

[0170] Benchmark value selection: Combining the user demand of "prioritizing residential functions" and the implicit rule of "the floor area ratio of residential land should be taken from the middle to high range to meet residential needs", a value of 1.6 near the upper limit of the benchmark for spatial characteristics matching is selected from the range of 1.3-1.7 as the initial benchmark floor area ratio (which both fits the spatial characteristics and meets the user's needs for residential functions).

[0171] The output initial benchmark floor area ratio (1.6) achieves a balance between "spatial feature benchmark + user needs + constraint rules", providing a stable initial anchor point for subsequent dynamic correction.

[0172] Step S203 aims to calculate specific correction values ​​for the transfer volume and reward volume based on dynamic data and dynamic adjustment rules, avoiding the neglect of dynamic factors that could lead to unrealistic corrections. Its input data consists of the dynamic supplementary data from S10 (such as subway passenger flow and service gaps), and it also calls the dynamic adjustment rule layer (weight allocation, cross-regional adjustment, and positive incentive rules) from the calculation rule base; specifically:

[0173] Dynamic Influencing Factor Extraction: Extracting key factors from dynamically supplemented data:

[0174] Transfer volume related: 0.1 of the low-density area (surrounding plots) can be transferred across regions (meeting the condition of "transfer area traffic capacity adaptability ≥ 0.7" in the "cross-regional adjustment rules", the subway passenger flow of the target plot is not over-capacity, and the capacity adaptability is 0.8).

[0175] Regarding the bonus volume: If a user "builds a 6-class kindergarten", it meets the requirement of "building a 6-class or more inclusive kindergarten, and will receive a bonus volume of 0.2" in the "positive incentive rules".

[0176] Dynamic adjustment factor: The average daily passenger flow of XX Station on Metro Line 2 exceeds the design capacity by 10%. The weight allocation rule is: transportation factors account for 45% of the weight. The dynamic adjustment value needs to be calculated according to "passenger flow exceeds 10% → capacity reduction of 0.05".

[0177] Correction value determined:

[0178] Transfer volume correction: +0.1 (positive for transfer in);

[0179] Bonus volume adjustment: +0.2 (bonus is positive);

[0180] Dynamic downward adjustment value: -0.05 (adjustment required when passenger flow exceeds capacity, resulting in a negative value).

[0181] The output of the transfer volume correction value (+0.1), bonus volume correction value (+0.2), and dynamic downward adjustment correction value (-0.05) provides a dynamic adjustment basis for subsequent overlay calculations, reflecting "the impact of urban operation status on volume".

[0182] Step S204 aims to generate preliminary results by superimposing the initial benchmark and various correction values ​​using a preset formula, avoiding calculation chaos caused by disordered superposition of correction values. Its input data includes the initial benchmark floor area ratio (1.6) from S202 and the three types of correction values ​​(+0.1, +0.2, -0.05) from S203. The preset correction formula is "Preliminary Correction Result = Initial Benchmark Floor Area Ratio + Transfer Floor Area Correction Value + Bonus Floor Area Correction Value + Dynamic Downward Adjustment Correction Value"; specifically:

[0183] Substituting the values ​​into the calculation: 1.6 + 0.1 + 0.2 - 0.05 = 1.85, we obtain the preliminary corrected result of 1.85.

[0184] The initial correction result (1.85) is a direct reflection of "initial baseline + dynamic adjustment". Although it includes dynamic factors, it has not been verified by legal constraints and needs to be further verified by the total amount constraint and proportional constraint of S205 to ensure compliance of the result.

[0185] Step S205 aims to verify the preliminary results through constraint rules, automatically triggering a callback when limits are exceeded, to ensure the legality and compliance of the output results. Its input data is the preliminary corrected result (1.85) from S204, and it simultaneously calls the "inter-layer correction rules" of the constraint rule layer (total constraint, proportional constraint) and the dynamic adjustment rule layer of the calculation rule base; specifically:

[0186] Total volume constraint verification: The rule "basic volume + transfer volume + bonus volume ≤ regulatory planning limit" is applied. The regulatory planning limit is 1.8. The preliminary result is 1.85 > 1.8, which exceeds the constraint.

[0187] Proportional constraint verification: Transfer volume 0.1 ≤ 20% of initial baseline 1.6 (0.32), bonus volume 0.2 ≤ 15% of initial baseline 1.6 (0.24), both proportions meet the constraints, the only reason for the breach is that the total amount exceeds the upper limit;

[0188] Automatic callback: Invokes the inter-layer correction rule "When the total limit is exceeded, prioritize reducing the reward volume, then reduce the transfer volume":

[0189] First, reduce the reward volume from 0.2 to 0.15 (still meeting the proportional constraint: 0.15≤0.24);

[0190] Recalculated: 1.6 + 0.1 + 0.15 - 0.05 = 1.8, which meets the upper limit of 1.8 in the control plan;

[0191] The final preliminary correction result is 1.8.

[0192] The final preliminary correction result (1.8) incorporates spatial characteristics, user needs, and dynamic factors, while strictly complying with legal constraints, providing a "basically compliant and further verifiable" foundation for subsequent S30 multi-dimensional verification.

[0193] In summary, S201 to S205 form a complete closed loop of "scope → benchmark → correction → result → verification". Each step takes the previous output as input and the rule base as the basis to ensure that the initial correction results are "based on evidence, in accordance with rules, and in line with reality", effectively supporting the in-depth verification work of S30.

[0194] As needed, the dynamic adjustment rule layer presets a spatiotemporal parameter mapping table, which includes calculation parameters for the transfer volume correction value and the reward volume correction value corresponding to different combinations of spatial and temporal labels. Before step S204, the method further includes spatiotemporal heterogeneity differentiation processing for the correction values ​​of the transfer volume and the reward volume, specifically including the following steps:

[0195] S203a. Extract spatial features of the target plot from the spatial attribute data in the basic dataset, and generate spatial labels related to transfer volume and bonus volume;

[0196] S203b: Extract the time dimension information of real-time urban operation monitoring data from the dynamically supplemented data in the basic dataset, and generate time labels related to transfer volume and bonus volume;

[0197] S203c: Call the spatiotemporal parameter mapping table, and filter the transfer volume differentiation calculation parameters and reward volume differentiation calculation parameters in the current scenario according to the time label and spatial label, respectively, so as to adjust the rule parameters on which the correction value of transfer volume and the correction value of reward volume are determined in step S203.

[0198] S203d: Based on the differentiated calculation parameters of the screening, redetermine the correction values ​​of the transfer volume and the bonus volume, and optimize the preset correction formula;

[0199] S203e. Based on the newly determined preliminary correction results, the quantitative correspondence rules between urban operation indicators and volume changes in the basic rule layer and the total constraint rules of basic volume, transfer volume and bonus volume in the constraint rule layer, as well as the proportional constraint rules of a single volume type, are called to verify whether the newly determined transfer volume correction value and bonus volume correction value meet the threshold and constraint requirements of urban operation indicators under the current spatiotemporal label.

[0200] S203f If the threshold or constraint requirements are not met, return to step S203c to rematch the spatiotemporal differential calculation parameters until the redefined transfer volume correction value and reward volume correction value both meet the requirements, and then execute step S204.

[0201] In this embodiment, steps S2031 to S2036 are the spatiotemporal heterogeneity optimization process for the "transfer volume and bonus volume correction value" in S203. The core purpose is to solve the problems of "poor adaptability of static correction parameters and neglect of spatiotemporal scene differences". Through the logic of "spatial label extraction → time label generation → parameter mapping → correction value recalculation → verification callback", the correction value is made to better fit the actual scenario of "specific spatial characteristics + specific time state", avoiding the result deviating from the actual carrying capacity of the land due to "one-size-fits-all" correction parameters. The details are as follows:

[0202] Step S2031 aims to define the scene type of the land parcel through spatial features, providing a spatial dimension basis for subsequent differential parameter matching and preventing spatial attribute differences from being masked. Its input data consists of spatial attribute data (such as land parcel location, surrounding facilities, and land use) from the basic dataset generated in S10; specifically:

[0203] Key features are extracted from spatial attribute data: the target plot is "Class II residential land + 800 meters from XX station of Metro Line 2 (within the 1-kilometer radius of the metro) + 300 meters of street frontage + 100 meters to the west is an ecologically sensitive area". Based on these features, a spatial label is generated: residential plot along the metro line (adjacent to an ecologically sensitive area); the label must simultaneously reflect the three core spatial elements of "metro connection", "land use nature" and "ecological constraints".

[0204] The output spatial labels accurately define the spatial scene attributes of the plot, providing a basis for subsequent matching of "specific correction parameters for this space".

[0205] Step S2032 aims to define the time-period characteristics of urban operation through time information, providing a time dimension basis for differentiated parameter matching and preventing dynamic changes over time from being ignored. Its input data is the real-time urban operation monitoring data (including timestamp information) from the dynamic supplementary data in S10; specifically:

[0206] Extract time dimension information from the dynamically supplemented data: The current time is "the third quarter of 20XX (back-to-school season) + weekday morning peak hours (7:30-9:00)", and the subway passenger flow data shows that "this period is the annual peak passenger flow season". Based on this, generate the time label: back-to-school season morning peak (peak passenger flow period); the label should reflect "quarter characteristics", "time period characteristics", and "operational status characteristics".

[0207] The output time stamp clearly defines the current time and the city's operational status, providing a basis for subsequent matching of "specific correction parameters for this time".

[0208] Step S2033 aims to match specific calculation parameters from a preset mapping table based on spatiotemporal labels, replacing general parameters and improving the scenario adaptability of the correction values. Its input data consists of the spatial label from S2031 (residential plots along the subway line (adjacent to ecologically sensitive areas)) and the time label from S2032 (morning rush hour during the school season (peak passenger flow)), while simultaneously calling the preset "spatiotemporal parameter mapping table" of the dynamic adjustment rule layer; specifically:

[0209] Example of a spatiotemporal parameter mapping table structure (partial):

[0210]

[0211] Match the current tag: Filter the corresponding parameters from the table - transfer volume correction factor 0.8 (due to the proximity to an ecologically sensitive area, the transfer volume needs to be reduced by 20%), bonus volume reduction ratio 10% (due to the high passenger flow pressure during the morning rush hour, the bonus volume needs to be reduced by 10%).

[0212] The output differentiated calculation parameters (transfer coefficient 0.8, reward reduction 10%) will be used to adjust the original correction value calculation rules in S203, so that the parameters are more in line with the current spatiotemporal scenario.

[0213] Step S2034 aims to optimize the "transfer volume and reward volume correction values" output by S203 based on spatiotemporal differentiation parameters, making them suitable for specific scenarios (such as subway lines + morning rush hour). Its input data includes the differentiation calculation parameters from S2033 and the initially determined correction values ​​from S203 (transfer volume +0.1, reward volume +0.2, and dynamically adjusted correction value -0.05), specifically:

[0214] Optimization of transfer volume adjustment value: Since the target plot is "adjacent to an ecologically sensitive area", it is calculated according to "original transfer adjustment value × spatial adjustment coefficient", that is, 0.1 (original value of S203) × 0.8 (transfer coefficient of S2033) = 0.08, which is adjusted from +0.1 in the basic plan to +0.08 to ensure that the transfer volume is adapted to ecological constraints;

[0215] Optimization of the bonus volume adjustment value: Since the current period is the "morning peak passenger flow period", it is calculated according to "original bonus adjustment value × (1 - time reduction ratio)", that is, 0.2 (original value of S203) × (1 - 10%) = 0.18, which is adjusted from the original value of S203 + 0.2 to + 0.18, to balance the bonus incentive and traffic carrying capacity pressure;

[0216] The dynamic downward adjustment value remains unchanged: The dynamic downward adjustment value (-0.05) has been calculated in S203 based on the real-time monitoring data of "overcapacity of passenger flow at XX station of Metro Line 2". It contains time dynamic characteristics and does not need to be superimposed with additional spatiotemporal parameters, so it remains at -0.05.

[0217] The optimized correction values ​​output (transfer volume correction value +0.08, bonus volume correction value +0.18, dynamic downward adjustment correction value -0.05) not only fit the specific scenario of "residential plots along the subway line (adjacent to ecologically sensitive areas) + morning rush hour during the school season", but also retain the real-time nature of the dynamic downward adjustment correction value. This provides accurate correction value data for the subsequent "urban operation indicator threshold verification + constraint rule verification" of S2035, avoiding repeated verification due to poor parameter adaptability.

[0218] Step S2035 aims to ensure that the recalculated correction value neither exceeds the city's operational carrying capacity threshold nor violates legal constraints, thus avoiding "violations for the sake of adapting to time and space." Its input data is the new correction value from S2034 (transfer +0.08, reward +0.18), while simultaneously invoking the "Urban Operation Indicators and Volume Change Quantification Rules" from the basic rule layer and the "Total Constraints" and "Proportional Constraints" from the constraint rule layer; specifically:

[0219] City operation indicator threshold verification: The rule "If the subway passenger flow exceeds the capacity by 10%, the volume should be reduced by 0.05" is called. The total volume after the current new correction value is added is 1.6 + 0.08 + 0.18 - 0.05 = 1.81, which does not cause the subway passenger flow to exceed the capacity threshold (the upper limit is 1.85), and meets the operation indicator requirements;

[0220] Constraint rule validation:

[0221] Total quantity constraint: 1.81 ≤ upper limit of the control plan 1.8? No, 1.81 is slightly exceeded;

[0222] Proportional constraints: Transfer volume 0.08 ≤ 1.6 × 20% (0.32), bonus volume 0.18 ≤ 1.6 × 15% (0.24), both proportions are met.

[0223] Verification result: The total amount slightly exceeds the constraint threshold and further adjustments are needed.

[0224] Step S2036 aims to resolve validation failures by cyclically matching parameters, ensuring that the final corrected value simultaneously satisfies both spatiotemporal adaptability and compliance. Its input data is the validation result from S2035 (total exceeding the upper limit); specifically:

[0225] Because the total amount exceeds the upper limit (1.81>1.8), return to S2033 to rematch the spatiotemporal parameters and select stricter adjustment parameters from the mapping table: under the same spatiotemporal label, "transfer volume correction coefficient 0.7, bonus volume reduction ratio 15%";

[0226] Recalculate the correction values: Transfer volume 0.1 × 0.7 = 0.07, Bonus volume 0.2 × (1 - 15%) = 0.17, Total volume 1.6 + 0.07 + 0.17 - 0.05 = 1.79;

[0227] Re-verification: 1.79≤1.8 (total amount meets requirements), all proportions meet requirements, and the operating indicators have not exceeded the thresholds;

[0228] If the requirements are met, proceed with S204.

[0229] The final correction values ​​output (transfer +0.07, reward +0.17) not only fit the spatiotemporal scenario of "residential plots along the subway line (adjacent to ecologically sensitive areas) + morning rush hour during the school season", but also strictly comply with legal constraints, providing more accurate dynamic parameters for the preliminary correction results of S204.

[0230] In summary, S2031~S2036, through the design of "spatiotemporal labeling → parameter differentiation → closed-loop verification", enables the correction values ​​of transfer volume and reward volume to have both "scenario adaptability" and "compliance", solving the problem of insufficient accuracy caused by the "one-size-fits-all spatiotemporal" correction in traditional correction, and providing support for the S20 overall process to output more realistic preliminary correction results.

[0231] In one embodiment, the construction of the association model specifically includes the following steps:

[0232] S110. Collect core data from the basic dataset used to characterize the plot ratio features and urban operational status of the target land parcel, and preprocess this data to obtain a standardized feature dataset that can be used for model training. Specifically:

[0233] S111. Extract historical data for characterizing the plot ratio characteristics of the target plot, historical data of indicators for characterizing the urban operation status, and plot spatial characteristic data from the basic dataset. The historical data of indicators for characterizing the urban operation status includes at least real-time urban operation monitoring data with time-series dimensions for transportation, services, and ecological environment.

[0234] S112. Preprocess the extracted representative data, including missing value interpolation and imputation, outlier identification and removal, and time scale unification of multi-source data;

[0235] S113. Based on the dynamic interaction mechanism between the plot ratio of the target plot and urban operation indicators, feature mapping is performed on the preprocessed characterization data to generate a model input feature set containing plot ratio gradient features, urban operation indicator response features and spatial interaction features.

[0236] S114. Standardize the input feature set by normalizing each feature value to the interval [0, 1] to obtain a standardized feature dataset.

[0237] S120. The standardized feature dataset is used to train a correlation model through an algorithm to obtain a trained correlation model. The trained correlation model is used to: calculate the correlation degree between the plot ratio of the target plot and urban operation indicators in real time, and to achieve the adaptation of plot ratio and urban operation status as the goal, outputting quantified correlation data based on the correlation degree. Specifically:

[0238] S121. Divide the standardized feature dataset into a model training set and a validation set according to a preset ratio;

[0239] S122. Construct an initial association model based on the training set. The initial association model takes traffic carrying capacity adaptability, service supply and demand balance and ecological constraint satisfaction as the core evaluation dimensions, and sets corresponding quantitative indicators and influence weights for each dimension.

[0240] S123. Calculate the quantitative results of each dimension under different plot ratio values ​​through the initial correlation model, and generate a comprehensive correlation score by weighted summation.

[0241] S124. Use the validation set to verify the output accuracy of the initial association model. The prediction error of the core evaluation dimension should not exceed the preset threshold. Iteratively optimize the weight coefficients and feature parameters of the initial association model based on the validation results.

[0242] S125. Generate a trained association model based on the optimized parameters, wherein the association model is configured as follows:

[0243] Receive real-time urban operation indicator data and candidate plot ratio values ​​for the target plot, and output a comprehensive correlation score between the two.

[0244] With the goal of matching plot ratio with urban operation status, the optimal quantitative correlation relationship that matches urban operation status is selected based on the comprehensive correlation score, forming a quantitative correlation relationship data matrix that includes the influence coefficients of each indicator.

[0245] In this embodiment, the core objective of building a correlation model based on a basic dataset is to achieve a quantitative adaptation between plot ratio and urban operational status. Through a closed-loop process of data preprocessing → model training and optimization, the raw data in the basic dataset is transformed into trainable, high-precision model input, ultimately outputting accurate quantitative correlation data. This provides a reliable basis for the subsequent establishment of a rule base. Specifically:

[0246] Using three core data types from the basic dataset as input, and through a standardized process of data preprocessing → feature engineering → model training → iterative optimization, the correlation between "plot ratio - urban operation indicators - spatial attributes" is established. The focus is on calculating the correlation between different plot ratio candidate values ​​and urban operation indicators. The specific operations are as follows:

[0247] Core data extraction: Three types of representative data were extracted from the basic dataset: historical data representing plot ratio characteristics (e.g., plot ratio values ​​of 1.5-2.8 for the target plot over the past 5 years); historical data representing indicators of urban operation status (including time-series dimensions, such as morning peak traffic flow of 2000-3500 vehicles / hour, daily passenger flow of XX station on Metro Line 2 of 20,000-28,000 passengers, school service capacity load rate of 70%-95%, and PM2.5 concentration of 25-40). Spatial characteristic data of the plot (such as suburban location, street frontage of 300 meters, distance from XX station of Metro Line 2 of 800 meters, plot area of ​​50,000 square meters). (There are 2 primary schools and 1 kindergarten within 1 kilometer of the surrounding area).

[0248] Data preprocessing: The extracted data is standardized; missing values ​​are filled by linear interpolation (e.g., the traffic flow during the morning rush hour on XX / XX / 20XX is missing, and is filled by the average of 2750 vehicles / hour for the same period of the three days before and after, consistent with the data cleaning logic of S103), outliers are removed by the 3σ rule (e.g., traffic flow of 5000 vehicles / hour at a certain moment exceeds the mean ± 3σ range, which is judged as equipment failure data and removed), and the time scale is unified (hourly traffic data and monthly school service carrying capacity data are converted to monthly averages). Then, "plot ratio gradient features + urban operation index response features + spatial interaction features" are generated by feature mapping (e.g., "for every 0.1 increase in plot ratio, morning rush hour traffic flow increases by 8%, passenger flow at subway station XX increases by 5%, and school service carrying capacity load rate increases by 3%", "within a 1-kilometer radius of the subway + 300 meters from the street → traffic sensitivity 0.6"). Finally, all feature values ​​are normalized to the [0,1] interval to obtain a standardized feature dataset.

[0249] Model Training and Optimization: The standardized feature dataset is divided into a training set and a validation set in a 7:3 ratio. An initial model is built based on the training set. Using "traffic capacity adaptability, service supply and demand balance, and ecological constraint satisfaction" as the core evaluation dimensions (with weights of 0.4, 0.3, and 0.3 respectively), the quantitative results of each dimension for different candidate plot ratios are calculated. A comprehensive correlation score is generated through weighted summation (e.g., a plot ratio of 1.6 corresponds to a comprehensive score of 0.8; the calculation logic is: traffic adaptability 0.8 × 0.4 + service adaptability 0.75 × 0.3 + ecological adaptability 0.85 × 0.3 = 0.8). The model accuracy is verified using the validation set (requiring the prediction error of the core dimensions to be ≤10%). If the error exceeds the standard (e.g., a service dimension error of 15%), the dimension weights are adjusted (e.g., the service weight is increased to 0.35), and the correlation coefficient of "plot ratio - school service capacity load rate" is simultaneously corrected. After iterative optimization, the finally trained correlation model is obtained.

[0250] The trained association model achieves the complete "input → calculation → output" function, providing a quantitative basis for the establishment of the calculation rule base, as detailed below:

[0251] Input content: Receive real-time urban operation index data for the target site (such as current morning peak traffic flow of 3000 vehicles / hour, school service capacity load rate of 85%, PM2.5 concentration of 32μg / L). (and different candidate values ​​for plot ratio (e.g., 1.5, 1.6, 1.7);

[0252] Relevance Calculation: Based on the optimized evaluation dimension weights and feature parameters, the model calculates the comprehensive relevance score corresponding to each candidate plot ratio. For example, inputting "plot ratio 1.7 + real-time traffic 3000 vehicles / hour" will output a comprehensive relevance score of 0.83 (calculation logic: traffic adaptability 0.75 × 0.4 + service adaptability 0.65 × 0.3 + subway station XX passenger flow adaptability 0.72 × 0.3 = 0.83).

[0253] Output results: With the goal of "adapting plot ratio to urban operation status", quantitative correlation data is output based on the comprehensive correlation score (adaptation value ≥ 0.8 is selected); the form is "plot ratio-urban operation index correlation matrix" (e.g., "plot ratio 1.6 → traffic flow adaptation 0.8, subway passenger flow adaptation 0.78; plot ratio 1.7 → traffic flow adaptation 0.75, subway passenger flow adaptation 0.72").

[0254] It should be noted that the data filtering, data integration, and model core logic construction involved in the process of multi-source data collection, core parameter extraction, basic dataset construction, preliminary construction of the association model, and establishment of the calculation rule base framework are all conventional technical means in the field of data processing and algorithm application. Those skilled in the art can flexibly adjust them according to the actual scenario of the target plot (such as core area / suburb, residential / commercial land), and will not be elaborated here.

[0255] In one embodiment, an automatic urban planning floor area ratio correction system is also provided, which corresponds to the automatic urban planning floor area ratio correction method described in the above embodiments. This automatic urban planning floor area ratio correction system includes:

[0256] The rule base establishment module is used to collect multi-source data of the target plot, extract core parameters from the multi-source data to construct a basic dataset, build an association model based on the basic dataset, calculate the correlation between the plot ratio and urban operation indicators through the association model, and the association model aims to achieve the adaptation between plot ratio and urban operation status, output quantitative association data, and establish a calculation rule base based on the basic dataset and association data.

[0257] The preliminary correction module is used to calculate the initial benchmark floor area ratio based on the calculation rule base, combined with the spatial characteristic parameters of the target plot and the user input parameters, dynamically correct the initial benchmark floor area ratio in combination with dynamic influencing factors, and output the preliminary correction result.

[0258] The multi-dimensional verification module is used to perform multi-dimensional verification on the preliminary correction results based on the constraints and quantitative association of the correlation data in the calculation rule base, and to perform parameter correction and rule re-matching on the correction results that do not meet the constraints, and to remove invalid correction results.

[0259] The scheme output module is used to output the final plot ratio correction scheme based on the verification results. The correction scheme includes at least the corrected plot ratio value, rule matching basis, supporting optimization implementation suggestions, and includes adaptive adjustment strategies corresponding to dynamic influencing factors.

[0260] The dynamic optimization module is used to dynamically update the calculation rule base, the quantitative correlation parameters of the correlation model and the correlation relationship data, as well as the weight parameters of dynamic influencing factors, based on the feedback data of the entire development life cycle of the target plot.

[0261] Specific limitations regarding an automatic urban planning floor area ratio correction system can be found in the above description of an automatic urban planning floor area ratio correction method, and will not be repeated here. Each module in the aforementioned automatic urban planning floor area ratio correction system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0262] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows. Figure 2 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database is used for data storage, data processing, and data analysis. The network interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements an automatic urban planning floor area ratio correction method.

[0263] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement an automatic correction method for urban planning floor area ratio.

[0264] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements an automatic correction method for urban planning floor area ratio.

[0265] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0266] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0267] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for automatically correcting plot ratio in urban planning, characterized by, The method comprises the following steps: Collecting multi-source data of the target plot, extracting core parameters in the multi-source data to construct a basic data set, constructing a correlation model based on the basic data set, calculating the correlation degree of the plot volume rate and the city operation index through the correlation model, and the correlation model taking the adaptation of the plot volume rate and the city operation state as the goal, outputting quantitative correlation data, establishing a calculation rule library based on the basic data set and the correlation data; Based on the calculation rule library, the spatial feature parameters of the target plot and the user input parameters are combined to calculate the initial reference volume rate, and the initial reference volume rate is dynamically corrected combined with dynamic influence factors to output the preliminary correction result; Based on the constraint conditions of the calculation rule library and the quantitative correlation of the correlation data, the preliminary correction result is multi-dimensionally checked, and the correction result that does not meet the constraint condition is parameter-corrected and rule-re-matched to eliminate invalid correction results; According to the checking result, a final volume rate correction scheme is output, which at least includes the corrected volume rate value, the rule matching basis, the supporting optimization implementation suggestion, and contains adaptive adjustment strategies corresponding to dynamic influence factors; According to the feedback data of the whole life cycle of the target plot development, the calculation rule library, the correlation model and the quantitative correlation parameters of the correlation data, and the weight parameters of the dynamic influence factors are dynamically updated; The calculation rule library specifically includes: A basic rule layer is constructed based on the basic data set and the quantitative correlation data, and contains the correlation rules of spatial features and basic volume reference and the quantitative corresponding rules of city operation indexes and volume changes; A constraint rule layer is constructed based on the legal planning parameters in the basic data set, and contains the sum constraint rules of basic volume, transfer volume and reward volume, the proportion constraint rules of single volume type and the adaptive range constraint rules of user input parameters; A dynamic adjustment rule layer is constructed based on dynamic supplementary data, and contains the weight distribution rules of different types of dynamic influence factors, the cross-regional adjustment rules of transfer volume, the positive incentive rules of reward volume and the interlayer correction rules when the basic rule layer and the constraint rule layer trigger linkage.

2. The urban planning bulk rate automatic correction method of claim 1, wherein, In the step of collecting multi-source data of the target plot, extracting core parameters in the multi-source data to construct a basic data set, the following steps are specifically included: The multi-source data of the target plot is divided into static basic data and dynamic supplementary data according to data attributes, wherein the static basic data at least contains legal planning parameters, spatial attribute data and solidified control indexes of the target plot, and the dynamic supplementary data at least contains real-time city operation monitoring data within a preset range of the target plot and whole life cycle prediction data within a preset period after development of the target plot; Static core indexes are extracted from the static basic data, and corresponding dynamic correlation indexes are extracted from the dynamic supplementary data, a mapping relationship between the two types of indexes is established through quantitative analysis algorithm, an association graph is generated, and the correlation fusion of static rules and dynamic influences is realized; The quantitative relationships in the static basic data, the dynamic supplementary data and the association graph are integrated, the core parameters are selected according to data cleaning rules, and are labeled and organized according to scene characteristics to construct a basic data set.

3. The urban planning bulk rate automatic correction method of claim 2, wherein, The step of calculating the initial benchmark volume rate based on the calculation rule base, combining the spatial feature parameters of the target plot and the user input parameters, dynamically correcting the initial benchmark volume rate based on the dynamic influencing factors, and outputting the preliminary correction result specifically includes the following steps: Extract the spatial feature parameters of the target plot from the spatial attribute data in the basic data set, receive the user input parameters, call the basic rule layer of the calculation rule base, substitute the spatial feature parameters into the association rule of the spatial feature and the basic volume benchmark, and generate the initial volume rate candidate interval; Based on the initial volume rate candidate interval, combine the user input parameters and the user input adaptation range constraint rule of the constraint rule layer to filter the required values from the initial volume rate candidate interval as the initial benchmark volume rate; Call the dynamic supplementary data, extract the dynamic influencing factors related to the transfer volume and the reward volume, assign corresponding weights based on the dynamic adjustment rule layer of the calculation rule base according to the weight distribution rules of different types of dynamic influencing factors, and determine the correction value of the transfer volume and the correction value of the reward volume by combining the cross-region adjustment rule of the transfer volume and the positive incentive rule of the reward volume, respectively; Based on the initial benchmark volume rate, the correction value of the transfer volume, and the correction value of the reward volume, the preliminary correction result of the initial benchmark volume rate is calculated through a preset correction formula; For the preliminary correction result, call the sum constraint rule of the basic volume, the transfer volume, and the reward volume and the proportion constraint rule of a single volume type in the constraint rule layer for verification; If the preliminary correction result breaks through the constraint threshold, it is automatically recalled to meet the constraint requirements according to the interlayer correction rule of the dynamic adjustment rule layer, and the final preliminary correction result is output.

4. The urban planning bulk rate automatic correction method of claim 1, wherein, The step of constructing an association model based on the basic data set, calculating the correlation degree of the volume rate of the target plot and the urban operation index through the association model, and outputting the quantified association relationship data with the goal of adapting the volume rate to the urban operation state, the construction of the association model specifically includes the following steps: Collect and preprocess the core data in the basic data set that represents the volume rate characteristics of the target plot and the urban operation state to obtain a standardized feature data set that can be used for model training; Train the association model through the standardized feature data set to obtain a trained association model, which is used to: Real-time calculation of the correlation degree of the volume rate of the target plot and the urban operation index; With the goal of adapting the volume rate to the urban operation state, output the quantified association relationship data according to the correlation degree.

5. The urban planning bulk rate automatic correction method of claim 4, wherein, The step of collecting and preprocessing the core data in the basic data set that represents the volume rate characteristics of the target plot and the urban operation state to obtain a standardized feature data set that can be used for model training specifically includes the following steps: Extract the historical data representing the volume rate characteristics of the target plot, the index historical data representing the urban operation state, and the plot spatial feature data from the basic data set, wherein the index historical data representing the urban operation state at least includes real-time urban operation monitoring data of traffic, service, and ecological environment with time sequence dimension; The preprocessed characteristic data is preprocessed, including missing value interpolation, outlier identification and elimination, and time scale unification of multi-source data; Based on the dynamic action mechanism of the target plot volume rate and the city operation index, the preprocessed characteristic data is feature mapped to generate a model input feature set containing volume rate gradient features, city operation index response features, and spatial interaction features; The input feature set is standardized to normalize each feature value to the interval [0, 1] to obtain a standardized feature data set.

6. The urban planning bulk rate automatic correction method of claim 5, wherein, In the step of training the standardized feature data set through an algorithm to obtain a trained correlation model, the following steps are included: The standardized feature data set is divided into a model training set and a validation set according to a predetermined proportion; An initial correlation model is constructed based on the training set, which takes traffic load adaptation, service supply-demand balance, and ecological constraint satisfaction as core evaluation dimensions, and sets corresponding quantitative indicators and influence weights for each dimension; The initial correlation model is used to calculate the quantitative results of each dimension under different volume rate values, and a weighted sum method is used to generate a comprehensive correlation score; The output accuracy of the initial correlation model is verified using the validation set, which requires that the prediction error of the core evaluation dimensions does not exceed a predetermined threshold, and the weight coefficients and feature parameters of the initial correlation model are iteratively optimized based on the verification results; Based on the optimized parameters, a trained correlation model is generated, which is configured to: Receive real-time city operation index data and volume rate candidate values of the target plot, and output the comprehensive correlation score of the two; To achieve the adaptation of volume rate and city operation state, the optimal quantitative correlation relationship that adapts to the city operation state is selected according to the comprehensive correlation score, and a quantitative correlation relationship data matrix containing the influence coefficients of each index is formed.

7. A system for implementing the steps of the method for automatically correcting the plot ratio of a city plan according to any one of claims 1 to 6, characterized in that, It includes: A rule base establishment module is used to collect multi-source data of the target plot, extract core parameters from the multi-source data to construct a basic data set, and construct a correlation model based on the basic data set. The correlation model is used to calculate the correlation between the volume rate of the target plot and the city operation index, and the correlation model aims to achieve the adaptation of the volume rate and the city operation state, and outputs the quantitative correlation relationship data. Based on the basic data set and the correlation relationship data, a calculation rule base is established; A preliminary correction module is used to calculate an initial reference volume rate based on the calculation rule base and combining the spatial feature parameters and user input parameters of the target plot, and dynamically corrects the initial reference volume rate based on dynamic influencing factors to output a preliminary correction result; A multi-dimensional checking module is used to perform multi-dimensional checking on the preliminary correction result based on the constraint conditions of the calculation rule base and the quantitative correlation of the correlation relationship data, and to perform parameter correction and rule re-matching on the correction results that do not meet the constraint conditions to eliminate invalid correction results; A scheme output module is used to output a final volume rate correction scheme according to the checking result, which at least includes the corrected volume rate value, the rule matching basis, and the supporting optimization implementation suggestion, and contains adaptive adjustment strategies corresponding to dynamic influencing factors. A dynamic optimization module is configured to dynamically update the quantified correlation parameters of the calculation rule library, the correlation model and the correlation data, and the weight parameters of the dynamic influence factors according to the feedback data of the whole life cycle of the target plot development.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The computer program is executed by the processor to implement the steps of the urban planning volume rate automatic correction method according to any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to implement the steps of the urban planning volume rate automatic correction method according to any one of claims 1-6.

Images