Search

CN-122022057-A - Urban public facility layout optimization method and system based on multi-source space-time big data

CN122022057ACN 122022057 ACN122022057 ACN 122022057ACN-122022057-A

Abstract

The invention discloses a city public facility layout optimization method and system based on multi-source space-time big data, and relates to the technical field of city planning; the method comprises the steps of firstly obtaining and fusing multi-source space-time big data such as mobile equipment signaling data and interest point data, identifying and defining a three-level center system of urban public service through a spatial clustering and network analysis algorithm based on the fused data, determining each center level and the space influence range, constructing a differentiated service demand quantization model aiming at each level of service center, constructing a multi-level collaborative layout optimization model, completing distribution and site selection optimization of facility levels, evaluating a layout scheme in a simulation environment and outputting a hierarchical evaluation report.

Inventors

  • LI FANG
  • YANG WENSHENG
  • YANG YIQING
  • LI BEI

Assignees

  • 武汉金超盛光电有限公司

Dates

Publication Date
20260512
Application Date
20260209

Claims (10)

  1. 1. The urban public facility layout optimization method based on the multi-source space-time big data is characterized by comprising the following steps of: s1, acquiring and fusing multi-source space-time big data in a target area, wherein the multi-source space-time big data comprise mobile equipment signaling data, interest point data, public transportation network data and land utilization grid data; s2, automatically identifying and defining a three-level center system of the urban public service based on the fused data through a spatial clustering and network analysis algorithm, and determining the level of each center and the spatial influence range of each center; S3, constructing a differentiated service demand quantization model aiming at each identified service center; S4, constructing a multi-level collaborative layout optimization model, wherein the model assigns a target level for public facilities to be configured, and optimizes corresponding specific addresses in the target level to generate a layout scheme with the service capacity of each level of center matched with the requirements; And S5, deploying the layout scheme in a simulation environment, calculating the service coverage rate, service bearing saturation and connection convenience of cross-level service of each level of service center, and outputting a hierarchical evaluation report.
  2. 2. The urban public facility layout optimization method based on multi-source space-time big data according to claim 1, wherein in the step S2, a three-level central system of urban public service is automatically identified and defined through a spatial clustering and network analysis algorithm, and the method comprises the following steps: Based on the public facility distribution density and the grade in the interest point data and population activity intensity reflected by the mobile signaling data, calculating a composite service attraction value of each geographic unit, wherein the composite service attraction value specifically comprises: ; Wherein G i is a composite service gravity value of the ith geographic unit, S i 、D i and I i are respectively a standardized facility supply index, a standardized dynamic demand intensity index and a standardized interaction potential index of the ith geographic unit, and α S 、α D and α I are corresponding weight coefficients; Three-dimensional curved surface modeling is carried out on the composite service gravitation value G i space field, and a watershed algorithm in topography is used for identifying local peak points of the gravitational field as a candidate center point set ; Defining clustering constraint conditions including space proximity constraint and gravity similarity constraint by taking the candidate center point as an initial clustering center; And performing iterative clustering by using a hierarchical clustering algorithm meeting the clustering constraint conditions to form a preliminary service center influence area.
  3. 3. The method for optimizing urban public facility layout based on multi-source spatio-temporal big data according to claim 1, characterized in that in said step S2, the hierarchy of each center is determined, comprising the steps of: For each cluster k, a hierarchical decision score is calculated, specifically: ; LS k is a hierarchical judgment score of a cluster k, area k is a space Area of the cluster k, gag k is an average composite service gravitation value of all units in the cluster k, iavg k is an average interaction potential index of all units in the cluster k, con k is a traffic network connectivity index of the cluster k, area max 、G max and I max are maximum values in all clusters, and beta 1 、β 2 、β 3 and beta 4 are weight coefficients; Setting a hierarchy judgment rule according to the hierarchy judgment score and the traffic network connectivity index, wherein the hierarchy judgment rule specifically comprises the following steps: if LS k ≥θ 1 , an Judging the service center as a first-level service center; if theta 2 ≤LS k ＜θ 1 , and Judging the service center as a secondary service center; If LS k ＜θ 2 is executed, determining that the service center is a three-level service center; Wherein, theta 1 、θ 2 , And (3) with Is obtained through historical data training for the threshold value.
  4. 4. The method for optimizing urban public facility layout based on multi-source spatio-temporal big data according to claim 1, wherein in step S2, the spatial influence range of each center comprises the following steps: aiming at the service center of each determined level, constructing a competition membership model based on a dominant traffic mode corresponding to the level and a preset maximum acceptable travel cost threshold; according to the competition membership model, carrying out competitive space allocation; The method comprises the steps of carrying out space continuity optimization and hierarchical service network consistency check on preliminary space influence ranges of each service center formed by distribution, wherein the space continuity optimization is used for eliminating holes and unreasonable enclaves in the ranges; And generating and outputting a comprehensive city public service network map, wherein the map comprises a spatial influence range of service centers at all levels, spatial distribution of service blind areas and fuzzy areas and a hierarchical network topological structure formed by coverage relations among the service centers.
  5. 5. The method for optimizing urban public facility layout based on multi-source spatio-temporal big data according to claim 4, characterized in that said competitive space allocation is performed according to said competitive membership model, comprising the steps of: The competition membership model specifically comprises the following steps: ; Wherein A (i, c) is the membership of the ith geographic unit to the c-th service center, G c is the composite service attraction value of the c-th service center, For the attraction reference associated with the ith geographic unit, C min (i, C) is the minimum generalized travel cost from the ith geographic unit to the C-th service center, T max (L c ) is the maximum acceptable travel cost threshold corresponding to level L c of the C-th service center, Is a monotonically decreasing function; The competitive space distribution is carried out according to the competitive membership model, specifically, for each geographic unit, according to whether the generalized travel cost from the geographic unit to each service center exceeds the maximum acceptable threshold of a corresponding level, screening out all reachable service centers to form an effective candidate service center set of the geographic unit, calculating the quantitative membership of the unit to each service center in the effective candidate set by utilizing the competitive membership model, and finally classifying the unit to the service center with the highest membership, and identifying the unit without the effective candidate service center as a service blind area, and identifying the unit with the highest membership value lower than a preset confidence threshold as a service fuzzy area.
  6. 6. The urban public facility layout optimization method based on multi-source spatio-temporal big data according to claim 1, wherein in the step S3, a differentiated service demand quantization model is constructed, comprising the following steps: Based on the fused multi-source space-time big data, extracting a demand characteristic index system which is matched with the space influence range of each level of service center and the service radiation energy level; carrying out normalization processing on the demand characteristic indexes by adopting a normalization method to obtain normalized demand characteristic vectors; the method comprises the steps of constructing a demand quantification modeling framework of layer level differentiation based on function positioning differences of service centers of all levels, adopting a multi-index weighted aggregation model for comprehensive service attributes of a primary service center, determining weights through a system evaluation method, and outputting comprehensive service demand intensity; And combining space-time dynamic perception of signaling data of the mobile equipment with space influence range boundaries of centers of all levels, carrying out space-time dimension correction on a demand quantization result, and generating time-division and regional dynamic service demand distribution which is precisely matched with the radiation ranges of the service centers of all levels.
  7. 7. The urban public facility layout optimization method based on multi-source space-time big data according to claim 1, wherein in the step S4, a multi-level collaborative layout optimization model is constructed, comprising the following steps: Setting a layout optimization objective function, specifically: ; wherein, min F is a layout optimization objective function, C is the total service cost, C MAX is the upper limit of the cost of public facility construction and operation in the target area, M is the service demand matching degree, E is the cross-level service engagement efficiency, and w 1 、w 2 and w 3 are weight coefficients; Meanwhile, setting a layout optimization constraint system, and constructing a multi-dimensional constraint rule around a multi-stage collaborative layout target, wherein the multi-dimensional constraint rule comprises space adaptation constraint, resource controllable constraint and hierarchical collaborative constraint; constructing a hierarchy adaptation dispatching mechanism, and determining a target service hierarchy corresponding to a public facility to be configured by adopting a multi-attribute comprehensive decision method based on the dynamic demand quantification result of each level of service center and the service capacity baseline of the existing facility, wherein the core dimension of the multi-attribute decision comprises demand conformity, resource input rationality and traffic accessibility; Constructing a solving model based on an intelligent optimization algorithm, taking the optimal demand matching degree as a core target, combining public transportation network and land utilization characteristics to screen candidate site selection sets conforming to constraint conditions, and obtaining an optimal facility site selection scheme in a target level through algorithm iteration fast optimization; And (3) carrying out multi-level scheme integration, and summarizing facility dispatching results and the optimal site scheme of each level to form a multi-level collaborative public facility layout scheme.
  8. 8. The urban public facility layout optimization method based on multi-source spatio-temporal big data according to claim 7, characterized in that said intelligent optimization algorithm is an improved genetic algorithm, by introducing a spatial constraint fitness penalty function, specifically: in the fitness calculation stage of the genetic algorithm, if the candidate site selection is located in the construction forbidden area, a punishment coefficient is applied to the fitness value, and the punished fitness function is as follows: If the candidate address violates the space constraint, then If the candidate address accords with the space constraint, then Wherein, gamma is a punishment coefficient, For the corrected Fitness function value, fitness is the original Fitness function value; and meanwhile, adding a neighborhood space limit in the crossing and mutation operation, wherein the child site selection and the parent site selection after crossing are in the influence range of the same-level service center, and the site selection change amplitude of the mutation operation does not exceed a preset space distance threshold.
  9. 9. The method for optimizing urban public facility layout based on multi-source spatio-temporal big data according to claim 1, characterized in that said step S5 comprises the following steps: Establishing a level adaptation evaluation index system, namely establishing a first-level evaluation dimension covering service efficiency, running efficiency and level cooperativity based on a core target of a multi-level cooperative layout scheme, and decomposing downwards to form a corresponding second-level evaluation index and a corresponding third-level characterization index; Determining the weight of each level evaluation index by adopting a comprehensive weighting method combining objective data driving and subjective experience judgment; Combining the space influence range of each level of service center with the multi-source space-time big data characteristic, and quantitatively measuring and calculating the evaluation index corresponding to each level of service center; performing aggregation analysis on the evaluation results of the service centers of all levels by adopting a multi-index comprehensive evaluation method, and dividing the evaluation levels; Integrating the evaluation results of each level, the index performance analysis and the layout scheme optimization proposal, and attaching each level of service center space evaluation atlas to generate a hierarchical evaluation report.
  10. 10. Urban public facility layout optimization system based on multi-source space-time big data, for implementing the urban public facility layout optimization method based on multi-source space-time big data according to any one of claims 1-9, characterized by comprising the following modules: The multi-source space-time big data acquisition and fusion module acquires and fuses multi-source space-time big data in a target area, wherein the multi-source space-time big data comprises mobile equipment signaling data, interest point data, public transportation network data and land utilization grid data; the three-level service center system identification and range definition module is used for automatically identifying and defining a three-level center system of urban public service through a spatial clustering and network analysis algorithm based on the fused data, and determining the level of each center and the spatial influence range of each center; the layer-level differentiated service demand quantitative modeling module is used for constructing a differentiated service demand quantitative model aiming at each identified level of service center; The multi-level collaborative public facility layout optimization module is used for constructing a multi-level collaborative layout optimization model, assigning a target level for public facilities to be configured, and optimizing corresponding specific addresses in the target level to generate a layout scheme with the service capacity of each level of center matched with requirements; And the layout scheme simulation evaluation and grading report output module is used for deploying the layout scheme in a simulation environment, calculating the service coverage rate, service bearing saturation and connection convenience of cross-level service of each level of service center and outputting grading evaluation report.

Description

Urban public facility layout optimization method and system based on multi-source space-time big data Technical Field The invention belongs to the field, and particularly relates to an urban public facility layout optimization method and system based on multi-source space-time big data. Background With the rapid development of big data technology, multi-source space-time big data such as mobile equipment signaling, interest points, public transportation network and the like provides dynamic and accurate data sources for urban planning, and urban public facilities are used as core carriers for guaranteeing the living quality of residents and improving the urban operation efficiency, and the layout rationality directly influences the equalization level and the resource allocation efficiency of urban public services. The current urban public facility layout planning is based on traditional static statistical data (such as census data and administrative division data) and subjective experience judgment of planners, and has the outstanding problems that the traditional method is difficult to capture space-time dynamic characteristics of population activities, so that a layout scheme cannot adapt to real-time change of resident demands, supply and demand unbalance problems such as surplus supply of partial regional facilities and partial regional service dead zones easily occur, a scientific and quantitative center level and influence range defining method is lacked, the actual service radiation law cannot be accurately reflected due to multi-administrative level or experience division, function positioning of each level of service center is fuzzy, the cooperative efficiency is low, a differential demand model is not built for different levels of service centers, multi-focus single facility or single level is optimized in layout, cooperative linkage of a multi-level service network is ignored, overall service efficiency maximization is difficult to achieve, traditional evaluation is based on basic indexes such as service coverage rate and the like, system evaluation on key dimensions such as service bearing saturation, cross-level connection convenience and the like is lacked, and feasibility and rationality of the layout scheme cannot be comprehensively verified. Therefore, urban public facility layout optimization methods and systems based on multi-source space-time big data are generated. Disclosure of Invention The invention aims to at least solve one of the technical problems in the prior art, and therefore, the invention provides a city public facility layout optimization method and system based on multi-source space-time big data, which are used for solving the technical problems of static hysteresis of data, rough identification of a service center, requirement quantification, dislocation of layout optimization and incomplete scheme evaluation in the existing city public facility layout method. To solve the above problems, a first aspect of the present invention provides a method for optimizing urban public facility layout based on multi-source spatio-temporal big data, comprising the steps of: s1, acquiring and fusing multi-source space-time big data in a target area, wherein the multi-source space-time big data comprise mobile equipment signaling data, interest point data, public transportation network data and land utilization grid data; s2, automatically identifying and defining a three-level center system of the urban public service based on the fused data through a spatial clustering and network analysis algorithm, and determining the level of each center and the spatial influence range of each center; S3, constructing a differentiated service demand quantization model aiming at each identified service center; S4, constructing a multi-level collaborative layout optimization model, wherein the model assigns a target level for public facilities to be configured, and optimizes corresponding specific addresses in the target level to generate a layout scheme with the service capacity of each level of center matched with the requirements; And S5, deploying the layout scheme in a simulation environment, calculating the service coverage rate, service bearing saturation and connection convenience of cross-level service of each level of service center, and outputting a hierarchical evaluation report. Preferably, in the step S2, a three-level center system of the urban public service is automatically identified and defined through spatial clustering and a network analysis algorithm, and the method comprises the following steps: Based on the public facility distribution density and the grade in the interest point data and population activity intensity reflected by the mobile signaling data, calculating a composite service attraction value of each geographic unit, wherein the composite service attraction value specifically comprises: ; Wherein G i is a composite service gravity value of the ith geographic unit,