A digital planning method for low-efficient land in territorial space based on improved comprehensive evaluation

Abstract

The application relates to the technical field of land planning and design and evaluation, and discloses a land space low-efficiency land digital planning method based on an improved comprehensive evaluation, which comprises the following steps: extracting features of time sequence data of crowd flow based on land information of land use, and generating land space utilization rate evaluation indexes; adopting a time-space clustering mode for clustering, generating clustering density information and converting the clustering density information into a space low-efficiency land index; marking land low-efficiency land, and setting adjustable design parameters of the land low-efficiency land; and optimizing the adjustable design parameters of the land low-efficiency land by using an improved particle swarm algorithm, so as to obtain an optimal design scheme of the land low-efficiency land. The space low-efficiency land index is generated based on the evaluation indexes and clustering information, the land low-efficiency land is marked, and the adjustable design parameters are set; through construction of a fitness function and combination of the improved particle swarm algorithm, the optimal design scheme is generated, and efficient utilization and intelligent planning of the land low-efficiency land are realized.

Description

Technical Field

[0001] This invention relates to the field of land use planning, design, and assessment, and in particular to a digital planning method for inefficient land use in national land space based on an improved comprehensive evaluation. Background Technology

[0002] With the accelerating pace of urbanization, the efficient allocation and intensive use of land resources have become key tasks in current national spatial governance. Especially against the backdrop of urban renewal and industrial restructuring, scientifically identifying inefficient land use and achieving differentiated and intelligent planning and design has become an important aspect of modernizing the spatial governance system. Traditional land use assessment methods largely rely on static land use types and current status survey data, neglecting the patterns of human activity and spatial usage intensity during actual land use. This makes it difficult to dynamically and objectively reflect land use efficiency, resulting in the irrational development and utilization of some potential land and affecting the overall efficiency of spatial resource allocation.

[0003] Existing research has proposed several methods for identifying and planning inefficient land use. For example, patent CN1186079

[0004] Paper 49B discloses a planning method for inefficient village construction land. It utilizes a deep learning model combined with a dual-stack depth-first search algorithm to perform combined planning analysis on village network maps. By comparing the land use potential of multiple combinations, it provides a decision-making basis for target village planning. This method achieves combined planning judgment of inefficient land use at the village scale, improving the ability to coordinate and optimize multiple land uses. However, this method is based on static macro-indicators such as land classification, land price, and construction intensity, lacking a deep integration of "dynamic population behavior flow" and "temporal land use efficiency." It struggles to reflect actual use intensity and lacks a unified standard for quantifying spatial inefficiency, often relying on manual judgment or subjective setting of administrative indicators. This makes it difficult to objectively reflect the actual comprehensive land use efficiency. Subsequent planning lacks a design mechanism centered on goal-driven optimization algorithms, resulting in the inability to achieve globally optimal allocation under multiple constraints.

[0005] To address this problem, this invention proposes a digital planning method for inefficient land use in national land space based on an improved comprehensive evaluation. By analyzing user behavior, it can more accurately identify land demand in different regions, thereby optimizing land use efficiency. Summary of the Invention

[0006] This invention provides a digital planning method for inefficient land use based on an improved comprehensive evaluation, addressing technical problems in existing land use assessments such as inaccurate identification of spatiotemporal utilization rates, inconsistent standards for identifying land inefficiency, and a lack of targeted design optimization mechanisms. By collecting and analyzing temporal data on population flow in land use, and extracting key spatial utilization characteristics from land information, a scientific land space utilization rate assessment index is constructed, improving the accuracy of land use efficiency analysis. Furthermore, a spatiotemporal clustering approach is adopted to model the cluster density of adjacent land uses, effectively quantifying the spatial correlation and inefficiency characteristics between different land uses, establishing a unified spatial inefficiency land use index, thereby objectively identifying inefficient land use with insufficient utilization. Based on this identification, a fitness function aimed at improving land utilization is constructed by combining basic control parameters and adjustable design parameters of inefficient land use. An improved particle swarm optimization algorithm is introduced to intelligently optimize the adjustable parameters, ultimately generating an implementable optimal design scheme, realizing an integrated digital transformation process for inefficient land use from assessment to design.

[0007] To achieve the above objectives, this invention provides a digital planning method for inefficient land use in national land space based on improved comprehensive evaluation, comprising the following steps:

[0008] S1: Collect time-series data on population flow in the land area, and extract features from the time-series data on population flow based on the land information of the land area to generate land space utilization evaluation indicators.

[0009] S2: Use spatiotemporal clustering to cluster land space utilization rate assessment indicators of multiple adjacent land areas, generate land area cluster density information, and convert land space utilization rate assessment indicators and cluster density information into spatial inefficient land use index.

[0010] S3: Land use with a spatial inefficiency index lower than the permissible land use index is marked as inefficient land use, basic control parameters of inefficient land use are collected, and adjustable design parameters of inefficient land use are set.

[0011] S4: Construct a fitness function with the goal of improving the utilization rate of inefficient land use, and use an improved particle swarm optimization algorithm to optimize the adjustable design parameters of inefficient land use, so as to obtain the optimal design scheme for inefficient land use and carry out planning and design for inefficient land use.

[0012] As a further improvement of the present invention:

[0013] Optionally, time-series data on population flow in the land area can be collected, and features can be extracted from the time-series data on population flow based on the land information of the land area, including:

[0014] The signaling data generated during the interaction between the communication base station and the mobile terminal device is acquired, and the daily population flow information of the land is extracted from the signaling data. The population flow information includes the number of people entering the land, the average dwell time of the people, and the activity frequency within a preset time window. The preset time window is from 9:00 to 17:00. The number of people entering the land is the number of people entering the land. The average dwell time of the people is the average dwell time of the people entering the land. The activity frequency is the proportion of people who repeatedly enter the land within a unit of time, and the unit of time is 3 days.

[0015] The daily population flow information of the land is used to construct the time series data of population flow of the land, and the land information of the land is obtained, including the planned plot ratio and land area.

[0016] Based on land information, features are extracted from time-series data of population flow to obtain land space utilization rate assessment indicators. These indicators include population density, space utilization rate, space dwell density index, and space reuse rate. Population density represents the carrying capacity of population per unit area of ​​land. Space utilization rate represents the ratio of actual space utilization rate to planned space utilization rate. Space dwell density index represents the average dwell time of population per unit area of ​​land per unit time. Space reuse rate represents the proportion of people repeatedly entering land in the time-series data of population flow.

[0017] Optionally, a spatiotemporal clustering method can be used to cluster land space utilization assessment indicators of multiple adjacent land areas to generate land area cluster density information, including:

[0018] Obtain the geographic coordinates of any two land parcels, calculate the distance between the geographic coordinates of the land parcels, and use this distance as the distance between the land parcels.

[0019] For any land use loc, select the K land uses closest to land use loc as the land uses adjacent to land use loc, and set K to 10;

[0020] Clustering is performed on the land use loc and the land space utilization evaluation indicators of K adjacent land uses loc to generate cluster density information of land use loc:

[0021] ;

[0022] ;

[0023] ;

[0024] ;

[0025] ;

[0026] in, This represents the cluster density information of land use location (loc). The land space utilization rate assessment index represents the land use area (loc). These represent, in order, the pedestrian density, space utilization rate, space occupancy density index, and space reuse rate of land use area (loc). Indicates the first adjacent land use area (loc). Land space utilization rate assessment indicators for each type of land use, These represent the adjacent land parcels loc, respectively. The population density, space utilization rate, space occupancy density index, and space reuse rate of adjacent land use areas. ;

[0027] Indicates land use location (loc) and the first The distance between adjacent land parcels Indicates the distance attenuation coefficient, set It is 0.1. This represents an exponential function with the natural constant as its base. Indicates land use location (loc) and the first Differences in indicators between adjacent land uses Represents the L2 norm. This represents the maximum index difference between the national land use area (loc) and adjacent national land use areas. Indicates the selection of a set The biggest difference in indicators, Indicates land use location (loc) and the first Distance attenuation coefficient between adjacent land uses;

[0028] The higher the cluster density information, the more obvious the spatiotemporal homogeneity of the land use loc and the adjacent land use in terms of pedestrian behavior patterns, and the more similar the land functions.

[0029] Optionally, the land space utilization rate assessment indicators and cluster density information of national land use can be converted into a spatial inefficiency land use index, including:

[0030] Land space utilization rate assessment indicators for obtaining land use quota and cluster density information ;

[0031] Land space utilization rate assessment indicators and cluster density information The data is normalized and converted into the spatial inefficiency land use index of land use loc.

[0032] Optionally, calculate the spatial inefficiency index of all land use, mark land use with a spatial inefficiency index lower than the permissible land use index as inefficient land use, and include inefficient land use in the digital planning and design land use database.

[0033] Optionally, inefficient land use can be extracted sequentially from the digital planning and design land use database, basic control parameters of inefficient land use can be collected, and adjustable design parameters of inefficient land use can be set, including:

[0034] The basic control parameters for inefficient land use include the area, length and width, lower limit of plot ratio, upper limit of plot ratio, maximum building height and maximum building density of inefficient land use, where the building density is the building land area / the land area of ​​inefficient land use.

[0035] The adjustable design parameters for the inefficient use of land include building function type, plot ratio, building density, number of buildings, building height, green space ratio, and building spacing. The building function type includes {residential, office, commercial, green space}. The building function type is discretely coded to obtain a discrete code set for the building function type.

[0036] The basic control parameters of inefficient land use are used as constraints to filter design schemes that do not conform to the basic control parameters. Initially, H groups of different adjustable design parameters are generated as H group design schemes, and H is set to 20.

[0037] Optionally, a fitness function can be constructed with the goal of improving the utilization rate of inefficient land use, including:

[0038] The fitness function takes the design scheme as input, and the fitness function value corresponding to the design scheme is the utilization rate of inefficient land use under the design scheme. The constructed fitness function is expressed as follows:

[0039] ;

[0040] ;

[0041] ;

[0042] ;

[0043] ;

[0044] in, Indicate the design scheme, For design scheme Discrete coding form of building function type in China The design schemes are represented in sequence. Medium plot ratio, building density, number of buildings, building height, green space ratio, and building spacing;

[0045] This represents the maximum building density among the basic control parameters;

[0046] Indicate design scheme Increase in land space utilization This represents the preset maximum gain in land space utilization.

[0047] Indicate design scheme Green space friendly benefits, Indicates the green space control weight, and sets... It is 0.6. Indicates ventilation control weight, setting It is 0.4. Indicates the preset maximum building spacing;

[0048] Indicate design scheme Building functional gains Indicates building function type Functional score, This represents the maximum score for the function.

[0049] Indicate design scheme Development costs, This represents the cost coefficient for building quantity. This represents the cost coefficient for building height. This indicates the preset maximum development cost.

[0050] Optionally, an improved particle swarm optimization algorithm is used to optimize the design scheme with the objective of maximizing the fitness function value corresponding to the design scheme, including:

[0051] The design scheme is used as the particle position, and the update speed of the design scheme is generated as the particle speed. The particle position and the corresponding speed are used as particles to obtain H groups of particles. The positions of the H groups of particles are sequentially input into the fitness function to obtain the fitness function value of each group of particle positions. The particle swarm algorithm is used to iterate each group of particles until the preset maximum number of iterations Max is reached. Max is set to 50. The design scheme with the largest fitness function value after reaching the maximum number of iterations and meeting the basic control parameters is selected as the optimal design scheme for inefficient land use. The planning and design of inefficient land use is carried out.

[0052] In each iteration, the inertial weight of the particle velocity and the learning factor are optimized using an iterative strategy. The optimization formula for the inertial weight is as follows:

[0053] ;

[0054] in, This represents the inertial weight of the particle's velocity during the t-th iteration. This represents the upper limit of the inertia weight. This represents the lower bound of the inertia weight. This represents the mean fitness function value of the particle positions in group H after the (t-1)th iteration. Let represent the maximum fitness function value of the particle position in group H after the (t-1)th iteration, where t represents the number of iterations for the particle. ;

[0055] Represents the nonlinear control factor, set It is 2;

[0056] The iterative strategy optimization formula for the learning factor is:

[0057] ;

[0058] ;

[0059] in, The individual learning factor represents the particle velocity at the t-th iteration. The group learning factor represents the particle velocity when the particle undergoes the t-th iteration;

[0060] These represent the preset maximum and minimum individual learning factors, respectively.

[0061] These represent the preset maximum group learning factor and minimum group learning factor, respectively.

[0062] Compared with existing technologies, this invention proposes a digital planning method for inefficient land use in national land space based on improved comprehensive evaluation. This technology has the following beneficial effects:

[0063] Firstly, this application constructs a land space utilization evaluation index system centered on pedestrian density, space utilization rate, spatial dwelling density index, and spatial reuse rate, achieving a quantitative analysis of the actual land use efficiency, which has significant practical value and promotional significance. Compared with traditional methods that rely on static land use or development intensity for evaluation, this application introduces temporal data of pedestrian flow to dynamically capture the actual land use behavior characteristics, obtaining land space utilization evaluation indicators that can more realistically reflect the land use status. Specifically, the pedestrian density index reveals the activity carrying capacity per unit area, the space utilization rate measures the degree of matching between pedestrian behavior and planned capacity, the spatial dwelling density index characterizes the stickiness of people within the land, and the spatial reuse rate reflects the intensity of repeated use of space. The land space utilization evaluation indicators together constitute a multi-dimensional, spatiotemporally integrated land use efficiency evaluation system, which can effectively identify inefficient land with low flow, low stickiness, and low intensity but high planned intensity, providing precise support for urban renewal, land redevelopment, and optimal resource allocation.

[0064] Meanwhile, this application comprehensively measures the suitability and merits of different adjustable design parameter combinations under planning constraints by integrating land development indicators and spatial utilization efficiency assessment elements, thereby obtaining the optimal utilization scheme for inefficient land use. Specifically, by quantifying and modeling parameters such as plot ratio, building density, number of buildings, building height, green space ratio, and building spacing, and introducing penalty terms for exceeding limits (such as the penalty for exponential growth when building density far exceeds the control line), the algorithm's ability to judge design feasibility can be significantly enhanced, avoiding the generation of solutions that do not conform to urban design specifications. Furthermore, the fitness function sets dynamically adjustable boundaries based on basic land attributes (such as area, side length, upper and lower limits of plot ratio, building height restrictions, etc.), ensuring that the scheme is always deduced under realistic conditions during the optimization process. Attached Figure Description

[0065] Figure 1 A flowchart illustrating a digital planning method for inefficient land use in national land space based on an improved comprehensive evaluation, as provided in an embodiment of the present invention;

[0066] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0067] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0068] This application provides a digital planning method for inefficient land use in national land space based on improved comprehensive evaluation. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0069] Reference Figure 1 Embodiment 1 of the present invention is as follows:

[0070] S1: Collect time-series data on population flow in the land area, and extract features from the time-series data on population flow based on the land information of the land area to generate land space utilization evaluation indicators.

[0071] Collect time-series data on population flow in the land use area, and extract features from the time-series data on population flow based on the land use information, including:

[0072] The signaling data generated during the interaction between the communication base station and the mobile terminal device is acquired, and the daily population flow information of the land is extracted from the signaling data. The population flow information includes the number of people entering the land, the average dwell time of the people, and the activity frequency within a preset time window. The preset time window is from 9:00 to 17:00. The number of people entering the land is the number of people entering the land. The average dwell time of the people is the average dwell time of the people entering the land. The activity frequency is the proportion of people who repeatedly enter the land within a unit of time, and the unit of time is 3 days.

[0073] In this embodiment of the application, the signaling data includes information such as the user equipment's access base station, cell handover, dwell time, and timestamp, reflecting how many people are active in a certain area during a certain time period;

[0074] Specifically, the formula for calculating the average dwell time of the crowd is as follows:

[0075] ;

[0076] in, This indicates the average dwell time of people. This indicates the time when the nth person in the inflow of people enters the land use area. This indicates the time when the nth person in the inflow leaves the land, where N represents the number of people entering the land within a preset time window; as an embodiment of this application, if the time when the nth person in the inflow leaves the land... If the preset time window is exceeded, then... Set to 17:00;

[0077] The formula for calculating the activity frequency is:

[0078] ;

[0079] Where U represents the frequency of activity, This indicates the number of people who repeatedly enter the land use market within a unit of time period within the inflow population;

[0080] The daily population flow information of the land is used to construct the time series data of population flow of the land, and the land information of the land is obtained, including the planned plot ratio and land area.

[0081] Based on land information, features are extracted from time-series data of population flow to obtain land space utilization rate assessment indicators. These indicators include population density, space utilization rate, space dwell density index, and space reuse rate. Population density represents the carrying capacity of population per unit area of ​​land. Space utilization rate represents the ratio of actual space utilization rate to planned space utilization rate. Space dwell density index represents the average dwell time of population per unit area of ​​land per unit time. Space reuse rate represents the proportion of people repeatedly entering land in the time-series data of population flow.

[0082] In this embodiment of the application, the population density is calculated as the ratio between the average number of people flowing into the land in the time series data of population flow and the land area. The space utilization rate is calculated as (average number of people flowing into the land in the time series data of population flow * average average dwell time of people in the time series data of population flow) / (planned plot ratio * land area). The space dwell density index is calculated as the average average dwell time of people in the time series data of population flow / (land area * duration of preset time window). The space reuse rate is calculated as the average activity frequency in the time series data of population flow.

[0083] S2: Use spatiotemporal clustering to cluster land space utilization rate assessment indicators of multiple adjacent land areas, generate land area cluster density information, and convert land space utilization rate assessment indicators and cluster density information into spatial inefficient land use index.

[0084] A spatiotemporal clustering method is used to cluster land space utilization assessment indicators of multiple adjacent land areas to generate land area cluster density information, including:

[0085] Obtain the geographic coordinates of any two land parcels, calculate the distance between the geographic coordinates of the land parcels, and use this distance as the distance between the land parcels.

[0086] For any land use loc, select the K land uses that are closest to land use loc as the land uses adjacent to land use loc;

[0087] Clustering is performed on the land use loc and the land space utilization evaluation indicators of K adjacent land uses loc to generate cluster density information of land use loc:

[0088] ;

[0089] ;

[0090] ;

[0091] ;

[0092] ;

[0093] in, This represents the cluster density information of land use location (loc). The land space utilization rate assessment index represents the land use area (loc). These represent, in order, the pedestrian density, space utilization rate, space occupancy density index, and space reuse rate of land use area (loc). Indicates the first adjacent land use area (loc). Land space utilization rate assessment indicators for each type of land use, These represent the adjacent land parcels loc, respectively. The population density, space utilization rate, space occupancy density index, and space reuse rate of adjacent land use areas. ;

[0094] Indicates land use location (loc) and the first The distance between adjacent land parcels Indicates the distance attenuation coefficient, set It is 0.1. This represents an exponential function with the natural constant as its base. Indicates land use location (loc) and the first Differences in indicators between adjacent land uses Represents the L2 norm. This represents the maximum index difference between the national land use area (loc) and adjacent national land use areas. Indicates the selection of a set The biggest difference in indicators, Indicates land use location (loc) and the first Distance attenuation coefficient between adjacent land uses;

[0095] The higher the cluster density information, the more significant the spatiotemporal homogeneity in pedestrian behavior patterns between the land use area (loc) and adjacent land use areas, indicating more similar land functions. Specifically, if the pedestrian density is high, the land use area with high cluster density information is often functionally mature and has a high utilization rate, and may not be suitable for further high-intensity development.

[0096] It should be noted that the cluster density information, by introducing a distance-weighted mechanism for adjacent land use, further integrates the geographical proximity topology on the basis of traditional population flow similarity assessment. This allows for a more comprehensive reflection of the spatial rationality and functional attractiveness of a land use as a cluster center. Specifically, the distance attenuation coefficient effectively weakens the noise impact that distant adjacent land use may bring to the cluster density information estimation, thereby improving the accuracy of cluster boundary delineation. On the other hand, based on the differences in indicators among adjacent land use, it can reflect the synergy in functional utilization among multiple adjacent land use in a certain area, significantly improving the sensitivity and applicability of land use efficiency assessment.

[0097] The land space utilization rate assessment indicators and cluster density information of national land use are converted into a spatial inefficiency land use index, including:

[0098] Land space utilization rate assessment indicators for obtaining land use quota and cluster density information ;

[0099] Land space utilization rate assessment indicators and cluster density information Normalization was performed, and the data was converted into a spatial inefficiency land use index (loc).

[0100] ;

[0101] in, The spatial inefficiency index of land use (loc) represents the total land use area. Indicators representing land space utilization rate The j-th index value The normalized results show that the first four index values ​​represent pedestrian density, space utilization rate, space occupancy density index, and space reuse rate, respectively. Representing cluster density information The normalization result, This represents the index weight coefficient for the j-th index value. The weighting coefficients representing cluster density are set. Specifically, the normalization method is the Min-Max normalization method, which sets... In order to be .

[0102] It should be noted that by organically integrating land space utilization assessment with cluster density information, the index identifies potentially structurally idle or functionally inefficient land use through the synergistic analysis of low values ​​of multi-dimensional features. Compared to traditional methods relying on single indicators, this index is better able to capture resource-dormant areas in urban spaces caused by insufficient pedestrian traffic, low reuse efficiency, and sparse activity and residence. Furthermore, the introduction of cluster density information further enhances the ability to identify agglomeration characteristics in local spaces, enabling the spatial inefficiency land use index to not only discover discrete inefficient land use but also identify inefficient land use areas or potential redevelopment areas.

[0103] S3: Land use with a spatial inefficiency index lower than the permissible land use index is marked as inefficient land use, basic control parameters of inefficient land use are collected, and adjustable design parameters of inefficient land use are set.

[0104] Calculate the spatial inefficiency index for all land use, and mark land use with a spatial inefficiency index lower than the permissible land use index as inefficient land use, and include inefficient land use in the digital planning and design land use database. Specifically, set the permissible land use index to 0.4 as a reference benchmark for classifying land use efficiency.

[0105] Inefficient land use is extracted sequentially from the digital planning and design land use database, basic control parameters of inefficient land use are collected, and adjustable design parameters of inefficient land use are set, including:

[0106] The basic control parameters for inefficient land use include the area, length and width, lower limit of plot ratio, upper limit of plot ratio, maximum building height and maximum building density of inefficient land use, where the building density is the building land area / the land area of ​​inefficient land use.

[0107] The adjustable design parameters for the inefficient use of land include building function type, plot ratio, building density, number of buildings, building height, green space ratio, and building spacing. The building function type includes {residential, office, commercial, green space}. The building function type is discretely coded to obtain a discrete code set for the building function type.

[0108] The basic control parameters of inefficient land use are used as constraints to filter design schemes that do not conform to the basic control parameters, and H groups of different adjustable design parameters are initially generated as H group design schemes. Specifically, among the adjustable design parameters, plot ratio, building density, number of buildings, building height, green space ratio, and building spacing are all discrete numerical forms, and the discrete coding forms of building function types are residential (0), office (1), commercial (2), and green space (3).

[0109] S4: Construct a fitness function with the goal of improving the utilization rate of inefficient land use, and use an improved particle swarm optimization algorithm to optimize the adjustable design parameters of inefficient land use, so as to obtain the optimal design scheme for inefficient land use and carry out planning and design for inefficient land use.

[0110] A fitness function is constructed with the goal of improving the utilization rate of inefficient land use, including:

[0111] The fitness function takes the design scheme as input, and the fitness function value corresponding to the design scheme is the utilization rate of inefficient land use under the design scheme. The constructed fitness function is expressed as follows:

[0112] ;

[0113] ;

[0114] ;

[0115] ;

[0116] ;

[0117] in, Indicate the design scheme, For design scheme Discrete coding form of building function type in China The design schemes are represented in sequence. Medium plot ratio, building density, number of buildings, building height, green space ratio, and building spacing;

[0118] This represents the maximum building density among the basic control parameters;

[0119] Indicate design scheme Increase in land space utilization This indicates the preset maximum gain in land space utilization (e.g., 100%).

[0120] Indicate design scheme Green space friendly benefits, Indicates the green space control weight, and sets... It is 0.6. Indicates ventilation control weight, setting It is 0.4. This indicates the preset maximum building spacing (e.g., 10 meters).

[0121] Indicate design scheme Building functional gains Indicates building function type Functional score, This indicates the maximum score for the function (e.g., 10 points).

[0122] Indicate design scheme Development costs, This represents the cost coefficient for building quantity. This represents the cost coefficient for building height. This indicates the preset maximum development cost (e.g., 50).

[0123] An improved particle swarm optimization algorithm is used to optimize the design scheme by maximizing the fitness function value corresponding to the design scheme, including:

[0124] The design scheme is used as the particle position, and the update speed of the design scheme is generated as the particle speed. The particle position and the corresponding speed are used as particles to obtain H groups of particles. The positions of the H groups of particles are sequentially input into the fitness function to obtain the fitness function value of each group of particle positions. The particle swarm algorithm is used to iterate each group of particles until the preset maximum number of iterations Max is reached. Max is set to 50. The design scheme with the largest fitness function value after reaching the maximum number of iterations and meeting the basic control parameters is selected as the optimal design scheme for inefficient land use. The planning and design of inefficient land use is carried out. In this embodiment of the application, the basic control parameters include the plot ratio being between the upper and lower limits of the plot ratio, the building area and the length and width not exceeding the area, length and width of the inefficient land use, and not exceeding the maximum building height and the maximum building density.

[0125] In each iteration, the inertial weight of the particle velocity and the learning factor are optimized using an iterative strategy. The optimization formula for the inertial weight is as follows:

[0126] ;

[0127] in, This represents the inertial weight of the particle's velocity during the t-th iteration. This represents the upper limit of the inertia weight. This represents the lower bound of the inertia weight. This represents the mean fitness function value of the particle positions in group H after the (t-1)th iteration. Let represent the maximum fitness function value of the particle position in group H after the (t-1)th iteration, where t represents the number of iterations for the particle. ;

[0128] Represents the nonlinear control factor, set It is 2;

[0129] Specifically, for the iterative strategy optimization formula of the inertia weight, in the early stage of optimization, when the fitness differences of the population are large, a higher weight value is assigned to enhance the global search capability; while in the later stage, when the fitness tends to converge, the weight is automatically reduced to enhance the local search capability, thereby effectively solving the problems of insufficient exploration in the early stage of convergence and easy getting trapped in local optima in the later stage of convergence of the particle swarm algorithm. This strategy can achieve a dynamic balance between population search quality and search speed, improve convergence accuracy and global optimization capability, and has significant advantages in optimization stability and convergence efficiency.

[0130] The iterative strategy optimization formula for the learning factor is:

[0131] ;

[0132] ;

[0133] in, The individual learning factor represents the particle velocity at the t-th iteration. The group learning factor represents the particle velocity when the particle undergoes the t-th iteration;

[0134] These represent the preset maximum individual learning factor and minimum individual learning factor (e.g., 1.5), respectively.

[0135] These represent the preset maximum group learning factor and minimum group learning factor (e.g., 1.5), respectively.

[0136] In this embodiment, by introducing a dynamically changing learning factor, the adaptive adjustment capability of the particles is effectively enhanced. In the early stage of the search, setting a larger individual learning factor can encourage particles to rely more on their own historical experience to explore, thereby expanding the search space. In the later stage of the search, by gradually increasing the group learning factor, the particles are more inclined to gather towards the global optimal position, improving the local convergence accuracy. This mechanism significantly improves the optimization efficiency and convergence stability of the algorithm and reduces the risk of getting trapped in local extrema.

[0137] It should be noted that the iterative formula for the particle velocity is:

[0138] ;

[0139] in, Let represent the particle velocity of the h-th group of particles during the t-th iteration. Let represent the particle velocity of the h-th group of particles obtained through iteration, when it undergoes the (t+1)-th iteration. Represents a random number between 0 and 1. This represents the position of the particles in the h-th group after the t-th iteration. This represents the position of the particle with the highest fitness function value in group H after the t-th iteration. This represents the position of the particle with the highest fitness function value in the h-th group of particles during the t-th iteration. .

[0140] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0141] It should be noted that the sequence numbers of the above embodiments of the present invention are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0142] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0143] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A digital planning method for inefficient land use in national land space based on improved comprehensive evaluation, characterized in that, The method includes: S1: Collect time-series data on population flow in the land area, and extract features from the time-series data on population flow based on the land information of the land area to generate land space utilization evaluation indicators. S2: Use spatiotemporal clustering to cluster land space utilization rate assessment indicators of multiple adjacent land areas, generate land area cluster density information, and convert land space utilization rate assessment indicators and cluster density information into spatial inefficient land use index. A spatiotemporal clustering method is used to cluster land space utilization assessment indicators of multiple adjacent land areas to generate land area cluster density information, including: Obtain the geographic coordinates of any two land parcels, calculate the distance between the geographic coordinates of the land parcels, and use this distance as the distance between the land parcels. For any land use loc, select the K land uses closest to land use loc as the land uses adjacent to land use loc, and set K to 10; Clustering is performed on the land use loc and the land space utilization evaluation indicators of K adjacent land uses loc to generate cluster density information of land use loc: ； ； ； ； ； in, This represents the cluster density information of land use location (loc). The land space utilization rate assessment index represents the land use area (loc). These represent, in order, the pedestrian density, space utilization rate, space occupancy density index, and space reuse rate of land use area (loc). Indicates the first adjacent land use area (loc). Land space utilization rate assessment indicators for each type of land use, These represent the adjacent land parcels loc, respectively. The population density, space utilization rate, space occupancy density index, and space reuse rate of adjacent land use areas. ; Indicates land use location (loc) and the first The distance between adjacent land parcels Indicates the distance attenuation coefficient, set It is 0.

1. This represents an exponential function with the natural constant as its base. Indicates land use location (loc) and the first Differences in indicators between adjacent land uses Represents the L2 norm. This represents the maximum index difference between the national land use area (loc) and adjacent national land use areas. Indicates the selection of a set The biggest difference in indicators, Indicates land use location (loc) and the first Distance attenuation coefficient between adjacent land uses; The higher the cluster density information, the more obvious the spatiotemporal homogeneity of the land use loc and the adjacent land use in terms of human traffic behavior patterns, and the more similar the land functions. Land space utilization assessment indicators include pedestrian density, space utilization rate, space dwell density index, and space reuse rate. Among them, pedestrian density represents the carrying capacity of pedestrian flow per unit area of ​​land, space utilization rate represents the ratio of actual space utilization rate to planned space utilization rate, space dwell density index represents the average dwell time of pedestrian flow per unit area of ​​land per unit time, and space reuse rate represents the proportion of people repeatedly entering land in the time series data of pedestrian flow. The land space utilization rate assessment indicators and cluster density information of national land use are converted into a spatial inefficiency land use index, including: Land space utilization rate assessment indicators for obtaining land use quota and cluster density information ; Land space utilization rate assessment indicators and cluster density information Normalization was performed, and the data was converted into a spatial inefficiency land use index (loc). ； in, The spatial inefficiency index of land use (loc) represents the total land use area. Indicators representing land space utilization rate The j-th index value The normalized results show that the first four index values ​​represent pedestrian density, space utilization rate, space occupancy density index, and space reuse rate, respectively. Representing cluster density information The normalization result, This represents the index weight coefficient for the j-th index value. Weighting coefficients representing cluster density; S3: Land use with a spatial inefficiency index not lower than the permissible land use index is marked as inefficient land use, basic control parameters of inefficient land use are collected, and adjustable design parameters of inefficient land use are set. S4: Construct a fitness function with the goal of improving the utilization rate of inefficient land use, and use an improved particle swarm optimization algorithm to optimize the adjustable design parameters of inefficient land use, so as to obtain the optimal design scheme for inefficient land use and carry out planning and design for inefficient land use.

2. The digital planning method for inefficient land use in national land space based on improved comprehensive evaluation as described in claim 1, characterized in that, Collect time-series data on population flow in the land use area, and extract features from the time-series data on population flow based on the land use information, including: The signaling data generated during the interaction between the communication base station and the mobile terminal device is acquired, and the daily population flow information of the land is extracted from the signaling data. The population flow information includes the number of people entering the land, the average dwell time of the people, and the activity frequency within a preset time window. The preset time window is from 9:00 to 17:

00. The number of people entering the land is the number of people entering the land. The average dwell time of the people is the average dwell time of the people entering the land. The activity frequency is the proportion of people who repeatedly enter the land within a unit of time, and the unit of time is 3 days. The daily population flow information of the land is used to construct the time series data of population flow of the land, and the land information of the land is obtained, including the planned plot ratio and land area. Based on land information of national land use, feature extraction is performed on time-series data of population flow to obtain land space utilization evaluation indicators of national land use.

3. The digital planning method for inefficient land use in national land space based on improved comprehensive evaluation as described in claim 1, characterized in that, Calculate the spatial inefficiency index of all land use, mark land use with a spatial inefficiency index not lower than the permissible land use index as inefficient land use, and include inefficient land use in the digital planning and design land use database.

4. The digital planning method for inefficient land use in national land space based on improved comprehensive evaluation as described in claim 3, characterized in that, Inefficient land use is extracted sequentially from the digital planning and design land use database, basic control parameters of inefficient land use are collected, and adjustable design parameters of inefficient land use are set, including: The basic control parameters for inefficient land use include the area, length and width, lower limit of plot ratio, upper limit of plot ratio, maximum building height and maximum building density of inefficient land use, where the building density is the building land area / the land area of ​​inefficient land use. The adjustable design parameters for the inefficient use of land include building function type, plot ratio, building density, number of buildings, building height, green space ratio, and building spacing. The building function type includes residential, office, commercial, and green space. The building function type is discretely coded to obtain a discrete code set for the building function type. The basic control parameters of inefficient land use are used as constraints to filter design schemes that do not conform to the basic control parameters. Initially, H groups of different adjustable design parameters are generated as H group design schemes, and H is set to 20.

5. The digital planning method for inefficient land use in national land space based on improved comprehensive evaluation as described in claim 4, characterized in that, A fitness function is constructed with the goal of improving the utilization rate of inefficient land use, including: The fitness function takes the design scheme as input, and the fitness function value corresponding to the design scheme is the utilization rate of inefficient land use under the design scheme. The constructed fitness function is expressed as follows: ； ； ； ； ； in, Indicate the design scheme, For design scheme Discrete coding form of building function type in China The design schemes are represented in sequence. Medium plot ratio, building density, number of buildings, building height, green space ratio, and building spacing; This represents the maximum building density among the basic control parameters; Indicate design scheme Increase in land space utilization This represents the preset maximum gain in land space utilization. Indicate design scheme Green space friendly benefits, Indicates the green space control weight, and sets... It is 0.

6. Indicates ventilation control weight, setting It is 0.

4. Indicates the preset maximum building spacing; Indicate design scheme Building functional gains Indicates building function type Functional score, This represents the maximum score for the function. Indicate design scheme Development costs, This represents the cost coefficient for building quantity. This represents the cost coefficient for building height. This indicates the preset maximum development cost.

6. The digital planning method for inefficient land use in national land space based on improved comprehensive evaluation as described in claim 5, characterized in that, An improved particle swarm optimization algorithm is used to optimize the design scheme by maximizing the fitness function value corresponding to the design scheme, including: The design scheme is used as the particle position, and the update speed of the design scheme is generated as the particle speed. The particle position and the corresponding speed are used as particles to obtain H groups of particles. The positions of the H groups of particles are sequentially input into the fitness function to obtain the fitness function value of each group of particle positions. The particle swarm algorithm is used to iterate each group of particles until the preset maximum number of iterations Max is reached. Max is set to 50. The design scheme with the largest fitness function value after reaching the maximum number of iterations and meeting the basic control parameters is selected as the optimal design scheme for inefficient land use. The planning and design of inefficient land use is carried out. In each iteration, the inertial weight of the particle velocity and the learning factor are optimized using an iterative strategy. The optimization formula for the inertial weight is as follows: ； in, This represents the inertial weight of the particle's velocity during the t-th iteration. This represents the upper limit of the inertia weight. This represents the lower bound of the inertia weight. This represents the mean fitness function value of the particle positions in group H after the (t-1)th iteration. Let represent the maximum fitness function value of the particle position in group H after the (t-1)th iteration, where t represents the number of iterations for the particle. ; Represents the nonlinear control factor, set It is 2; The iterative strategy optimization formula for the learning factor is: ； ； in, The individual learning factor represents the particle velocity at the t-th iteration. The group learning factor represents the particle velocity when the particle undergoes the t-th iteration; These represent the preset maximum and minimum individual learning factors, respectively. These represent the preset maximum group learning factor and minimum group learning factor, respectively.

Images