Infrastructure area balance evaluation method and system based on multi-dimensional data

Abstract

The invention discloses an infrastructure area balance evaluation method and system based on multi-dimensional data, and belongs to the technical field of data processing, and the method comprises the steps: carrying out the multi-dimensional data integration and space environment modeling, calculating the area supply capability and the area demand condition through the multi-dimensional data, carrying out the evaluation and scoring of the supply and demand balance of an area, and carrying out the evaluation of the balance of an infrastructure area. And outputting a corresponding strategy based on the score and the regional population condition. According to the infrastructure area balance evaluation method and system based on the multi-dimensional data, an infrastructure dynamic space service area modeling mechanism is introduced, the effective radiation capacity of infrastructures inside and outside the area to crowds is truly reflected, a crowd microscopic behavior modeling mechanism is combined, the supply and demand relation is accurately described, and the balance evaluation accuracy is improved. And a regional balance dynamic evaluation and feedback mechanism is established, and balance evaluation results and strategy suggestions are updated in real time.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and particularly relates to a method and system for evaluating the regional balance of infrastructure based on multi-dimensional data. Background Art

[0002] In the process of modern urban and regional development, infrastructure (such as medical care, education, transportation, energy, etc.), as a key factor supporting the operation of regional social economy, its layout and distribution directly affect the fairness, coordination and sustainable development among regions. The evaluation of the regional balance of infrastructure has become an important tool for governments at all levels and planning agencies in formulating regional development policies, optimizing the allocation of public resources, and improving the quality of people's livelihood services. Most of the existing balance evaluation methods are based on traditional spatial statistics, weighted scoring, analytic hierarchy process (AHP) or evaluation mechanisms based on per capita indicators. Such methods usually use evaluation units divided by administrative boundaries, and calculate the per capita infrastructure resource indicators among regions based on data such as the quantity of infrastructure, service capacity and population size within the region, and use this as a standard to measure the balance. However, in reality, the use and distribution of regional infrastructure show highly spatial heterogeneity and characteristics of population dynamic behavior. On the one hand, the actual service capacity of infrastructure is restricted by various factors, such as terrain obstacles, traffic accessibility, service level, etc. The "service radius" of the same facility in different geographical environments varies greatly, and it is difficult to truly reflect the service spillover effect of infrastructure on the surrounding areas by simply dividing by administrative boundaries. On the other hand, existing evaluation methods generally ignore the cross-regional mobility, service preferences and selection behaviors of people when actually using infrastructure. Under the influence of factors such as travel distance, service quality, and economic cost, there is an obvious "unbalanced use" phenomenon among different groups, that is, even if the infrastructure resources are evenly distributed in space, the actual use behaviors of people may still cause some areas of facilities to be overloaded, while other areas are underutilized. In addition, some existing methods only conduct static evaluations at the current time point, and cannot dynamically reflect the balance evolution process of the region under the action of multiple factors such as infrastructure supply and demand, population flow changes, and policy interventions, lacking forward-looking and strategic guidance capabilities.

[0003] Therefore, when the existing technology is applied to the evaluation of regional infrastructure balance, the following main defects exist: (1) The division of evaluation units is too rigid, making it difficult to truly reflect the spatial service capacity of facilities; (2) There is a lack of dynamic modeling of people's actual use behaviors, and it is impossible to reveal the complex interaction relationship between infrastructure supply and actual demand; (3) There is a lack of dynamic prediction of future balance trends and no effective decision-making support can be provided. These problems seriously restrict the scientific nature and operability of the evaluation results, leading to the risk of decision-making lag or resource misallocation in infrastructure planning and adjustment.

[0004] To this end, we propose a method and system for evaluating the regional balance of infrastructure based on multi-dimensional data to solve the above problems. Summary of the Invention

[0005] The object of the present invention is to solve the problem of lack of dynamic modeling evaluation in the prior art, and to propose a method and system for evaluating the regional balance of infrastructure based on multi-dimensional data.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] A method for evaluating the regional balance of infrastructure based on multi-dimensional data, including:

[0008] S1: Collect multi-dimensional raw data, preprocess the multi-dimensional raw data and integrate it into a data set, and establish a data graph model with each region and facility as nodes and the traffic connection and influence relationship between regions as edges;

[0009] S2: Calculate the influence of each facility on any region based on the data graph model, delimit the dynamic service area of each facility based on the influence, and generate a corresponding spatial supply matrix to represent the comprehensive service volume obtained by the region from each facility;

[0010] S3: Use the spatial supply matrix and the population attributes and facility service areas of each region as inputs to calculate the demand of the region for the facility, screen the facilities actually reachable by the region, and output the dynamic actual demand matrix of each region;

[0011] S4: Use the spatial supply matrix and the dynamic actual demand matrix as inputs to complete the supply-demand matching analysis of the infrastructure services in the region, and output the regional balance index sequence after quantifying it;

[0012] S5: Divide the different regional balance index sequences into different intervals corresponding to different strategy levels, and combine the basic population scale of the region to output the corresponding response strategy.

[0013] Preferably, the multi-dimensional raw data in step S1 includes infrastructure data, traffic network data, terrain data and population data.

[0014] Preferably, the calculation of the influence in step S2 is obtained by weighted calculation of the traffic time or distance from the region to the facility, the traffic cost ratio at the location of the facility, and the service supply-demand pressure ratio.

[0015] Preferably, the demand for the facility in step S3 is calculated by balancing the weights of the population base, travel activity, spatial supply, traffic accessibility, subjective preference and service scope.

[0016] Preferably, in step S4, the supply-demand matching analysis evaluates the basic deviation between supply and demand by calculating the normalized cumulative degree of the supply and demand of all facilities in the region, and after multi-dimensional adjustment and correction of the basic deviation, the balance score of the region is obtained through calculation.

[0017] Preferably, the balance score of the region magnifies the imbalance by weighted summation of negative factors and is converted into a standardized score through reciprocal transformation, i.e., the regional balance index sequence. The negative factors include the basic deviation between supply and demand, the degree of dependence of the region on external services, and the overloading situation of facilities.

[0018] Preferably, in step S5, by respectively setting a first balance threshold, a second balance threshold, and a population critical threshold, the corresponding situation of the strategy level is as follows:

[0019] When the balance score sequence is lower than the first balance threshold and the population is lower than the population critical threshold, the strategy level is expansion priority, and infrastructure is added or expanded.

[0020] When the balance score sequence is higher than or equal to the first balance threshold and lower than the second balance threshold and / or the population is lower than the population critical threshold, the strategy level is structural adjustment, and the layout of existing facilities is optimized.

[0021] When the balance score sequence is higher than the second balance threshold, the strategy level is flexible redundancy, and no new facilities are added.

[0022] An infrastructure regional balance evaluation system based on multi-dimensional data includes:

[0023] A data collection module, which is configured to collect multi-dimensional raw data, integrate the multi-dimensional raw data into a data set after preprocessing, and establish a data graph model with each region and facility as nodes and the traffic connection and influence relationship between regions as edges.

[0024] A supply-demand calculation module, which is configured to calculate the influence of each facility on any region based on the data graph model, delimit the dynamic service area of each facility based on the influence, and generate a corresponding spatial supply matrix for representing the comprehensive service volume obtained by the region from each facility; use the spatial supply matrix, the population attribute of each region, and the facility service area as inputs to calculate the demand of the region for the facility, and screen the facilities actually reachable by the region, and output the dynamic actual demand matrix of each region.

[0025] A supply-demand balance evaluation module, which is configured to use the spatial supply matrix and the dynamic actual demand matrix as inputs, complete the supply-demand matching analysis of the infrastructure services in the region, and output the regional balance index sequence after quantification.

[0026] The strategy generation module is configured to divide the sequence of regional balance indicators into different intervals corresponding to different strategy levels, and combine with the basic population scale of the region to output corresponding response strategies.

[0027] In summary, the technical effects and advantages of the present invention are as follows: The infrastructure regional balance evaluation method and system based on multi-dimensional data, based on multi-source heterogeneous data, innovatively introduce the infrastructure dynamic spatial service area modeling mechanism, which can fully consider various spatial factors such as terrain, traffic accessibility, and facility supply capacity, dynamically construct the real service scope of each facility, and truly reflect the effective radiation ability of the infrastructure inside and outside the region to the population. At the same time, the system combines the crowd micro-behavior modeling mechanism to simulate the cross-regional flow, preference selection, and usage behavior of different groups for infrastructure inside and outside the service area, accurately depict the dynamic supply-demand relationship of "people-facility-space", and significantly improve the authenticity and accuracy of the evaluation results. In addition, the present invention further establishes a regional balance dynamic evaluation and feedback mechanism to support real-time updating of the balance evaluation results and strategy recommendations under the action of dynamic factors such as supply-demand relationship, population change, and resource adjustment. Brief Description of the Drawings

[0028] Figure 1 is the flowchart of the method in the present invention;

[0029] Figure 2 is the schematic structural diagram of the system in the present invention. Detailed Embodiments

[0030] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0031] As Figure 1 shown, an infrastructure regional balance evaluation method based on multi-dimensional data includes:

[0032] S1: Collect multi-dimensional raw data, preprocess the multi-dimensional raw data and integrate it into a data set, and establish a data graph model with each region and facility as nodes and the traffic connection and influence relationship between regions as edges;

[0033] S2: Calculate the influence of each facility on any region based on the data graph model, delimit the dynamic service area of each facility based on the influence, and generate a corresponding spatial supply matrix to represent the comprehensive service volume obtained by the region from each facility;

[0034] S3: Use the spatial supply matrix and the population attributes and facility service areas of each region as inputs to calculate the demand of the region for the facility, screen the facilities actually reachable by the region, and output the dynamic actual demand matrix of each region.

[0035] S4: Take the spatial supply matrix and the dynamic actual demand matrix as inputs, complete the supply-demand matching analysis of infrastructure services within the region, and output a sequence of regional equilibrium indicators after quantifying it;

[0036] S5: Divide the sequences of different regional equilibrium indicators into different intervals corresponding to different strategy levels, and combine with the basic population scale of the region to output the corresponding response strategies.

[0037] Specifically as follows:

[0038] Step 1: Multi-dimensional data integration and spatial environment modeling

[0039] In this step, integrate multi-dimensional data such as region, infrastructure, transportation network, terrain, and population, and establish a comprehensive data graph model of "space-facility-population" , providing data support for subsequent steps such as spatial service area modeling, population behavior simulation, and equilibrium evaluation.

[0040] Data integration and graph model construction:

[0041] Goal: Construct a multi-dimensional data graph , which includes a comprehensive representation of factors such as facilities, transportation, population, and terrain.

[0042] Data collection:

[0043] Infrastructure data: Include the location, capacity, service type, etc. of facilities such as hospitals, schools, and transportation hubs (for example, Hospital A has 200 beds, School B has 500 student places, etc.);

[0044] Transportation network data: Include the spatial location and accessibility of road networks, bus lines, subway lines, etc. (for example, the walking time from Region 1 to Region 2 is 15 minutes, and the public transportation time from Region 1 to Region 3 is 30 minutes);

[0045] Terrain data: For example, slope, geographical obstacles, population density, etc. (for example, there is a large hill from Region A to Region B, and it takes 40 minutes to walk);

[0046] Population data: Socio-economic information such as the total population, age structure, and income level of each region (for example, the population of Region 1 is 5000 people, and 80% are young people).

[0047] Integrate data: These data will be preprocessed (such as standardized, normalized) and then integrated into a unified data set for subsequent steps. Each region and facility will be used as a node in the graph ( ), and the transportation connections and influence relationships between regions will be used as edges ( Add it to the figure.

[0048] Example: Suppose there are three regions A, B, and C, each with different facilities and transportation connections:

[0049] Region A has a hospital and a school, Region B has a school, and Region C has multiple transportation hubs.

[0050] The transportation network connects Region A and Region B (10-minute walk), and Region B and Region C (15-minute walk).

[0051] Weighted influence factor and data graph construction:

[0052] To realistically depict the relationships between regions and the influence of facilities, we introduce a weighted influence factor , and calculate the influence between each pair of adjacent regions through the following formula:

[0053] ;

[0054] Where:

[0055] : Represents the influence of region on region ;

[0056] : The transportation distance or time between region and region , representing "transportation accessibility";

[0057] , : Respectively represent the population numbers of regions and (which can be population density, reflecting the intensity of demand);

[0058] : The service capacity of the infrastructure within region , such as the number of hospital beds and school places, reflecting the service capacity;

[0059] , , : Weighting factors used to adjust the weights of different factors.

[0060] Example:

[0061] Assume that the distance between area A and area B is a 15 - minute walk. The population of area A is 5000 people, and the population of area B is 3000 people. Area A has a hospital and a school with a total service capacity of 200 beds and 500 school places. Area B has only a school with a total service capacity of 300 school places. Assume we are given weights , , , then:

[0062] minutes (walking time);

[0063] , ;

[0064] (total service capacity of facilities), .

[0065] Substitute into the formula for calculation :

[0066] ;

[0067] ;

[0068] ;

[0069] This weighting method can dynamically adjust the influence between regions according to traffic accessibility, population distribution, and infrastructure service capacity.

[0070] Construction of node attribute vectors:

[0071] The attribute vectors of each region and facility will comprehensively consider factors such as facilities, population, traffic, and terrain. The specific formula is:

[0072] ;

[0073] Example:

[0074] For area A:

[0075] = [hospital bed capacity = 200, school places = 500];

[0076] = 5000 people;

[0077] = 15 - minute walk to area B;

[0078] = 200 (facility service capacity).

[0079] So the attribute vector of area A is as follows:

[0080] ;

[0081] Step 2: Modeling of the infrastructure dynamic service area

[0082] In this step, our goal is to dynamically calculate the service area for each infrastructure based on the multi-dimensional data graph model provided in Step 1 , and generate the corresponding spatial supply matrix . The core innovation of this step lies in the design of the dynamic influence factor. Combining with the scenario of "infrastructure area balance assessment" faced by the solution, the supply capacity of each area is dynamically adjusted through the weighted influence model, so as to provide a more realistic supply environment for subsequent population behavior modeling and balance assessment .

[0083] The input of this step is the multi-dimensional spatial graph output in Step 1 , which includes the node sets of areas and facilities, the connecting edges, and the attribute vectors of each node .

[0084] Based on , calculate the influence of each facility on any area , which is defined as follows:

[0085] ;

[0086] Where:

[0087] : The service influence of facility on area ;

[0088] : The travel time or distance from area to facility , representing accessibility (unit: minutes or kilometers);

[0089] : The traffic network accessibility index of the location where facility is located, usually represented by the connectivity or average adjacent accessibility time (such as the number of buses / subways, road density);

[0090] : The unit service cost of facility , such as maintenance cost or construction budget (unit: 10,000 yuan);

[0091] : Facilities Service capacity, such as the number of beds or degrees (unit: person);

[0092] : Region Population quantity (unit: person);

[0093] : Smoothing constant, to prevent division by zero, generally take ;

[0094] : Weighting coefficient set by experience (such as ), used to adjust the contribution degree of each item to the influence.

[0095] This formula innovatively introduces item, reflecting the supply - demand pressure ratio, while traditional models mostly ignore this dynamic item; and add , to measure the traffic service benefit under unit input.

[0096] Based on all , delimit the dynamic service area of each facility :

[0097] ;

[0098] Among them:

[0099] : Facilities 's service area, representing the set of all areas that it can effectively radiate;

[0100] : Service influence threshold (can be set by facility level or experience, representing the minimum effective service standard, such as ).

[0101] Finally, calculate the supply matrix for each region , representing the comprehensive service volume obtained by this region from each facility:

[0102] ;

[0103] Among them:

[0104] : Spatial supply intensity of region (unit: influence score);

[0105] : Indicator function, if , then it is 1, otherwise it is 0, only counting the contribution of facilities actually belonging to the service area.

[0106] Through this mechanism, the service capabilities of all facilities for the region are comprehensively formed .

[0107] Step 3: Dynamic demand modeling based on microscopic population behavior

[0108] The goal of this step is to, based on the spatial supply matrix generated in Step 2 , combine the population attributes of each region and the facility service area , and construct a spatial behavior response model to output the dynamic actual demand matrix for each region , which is used to characterize the true usage tendency of the population for infrastructure services under multi-dimensional influencing factors.

[0109] To model the true demand quantity of the region for the facility , we design a behavior-aware demand generation function:

[0110] ;

[0111] Where:

[0112] : The actual usage demand (number of people) of region for the facility ;

[0113] : The total population of region ;

[0114] : The behavioral travel activity of the regional population (e.g., indicates a high mobility of the regional population);

[0115] : The total spatial supply intensity of region ;

[0116] : The traffic access time from region to the facility ;

[0117] : The preference coefficient of the population for the type of facility ;

[0118] : A small constant to prevent division by zero (e.g., );

[0119] : The service area indicator function. If Within the service area of the facility, it is 1; otherwise, it is 0. ;

[0120] : The behavior response weight coefficient, which balances the influences of accessibility orientation and subjective preference orientation (such as ).

[0121] What this formula expresses is:

[0122] The basic demand of the population is determined by ;

[0123] Supply - distance ratio represents "distance perception on the premise of supply availability";

[0124] Subjective preference and whether it is within the service area jointly determine whether the population will actively choose this type of facility;

[0125] Combining these two determines the facility response intensity of the population.

[0126] Finally, a dynamic demand matrix is output, and each element represents the "true number of people with the tendency to use the facility" in this area:

[0127] ;

[0128] Among them is the set of facilities actually accessible in area .

[0129] Through the above design, we have constructed a real, dynamic, and spatially perceptive population demand modeling mechanism, providing indispensable "demand - side modeling support" for the evaluation of regional infrastructure balance.

[0130] Step 4: Dynamic evaluation of the balance of supply - demand integration

[0131] The core objective of this step is to establish a fusion relationship between the regional supply matrix output in Step 2 and the dynamic demand matrix output in Step 3, complete the supply - demand matching analysis of infrastructure services within the region, and thereby quantify the "dynamic balance level" of the region in terms of infrastructure use 。Different from the traditional supply-demand difference analysis, this step combines factors such as cross-regional service flow, population behavior activity, and facility carrying pressure, and proposes a "Supply-Demand Structural Deviation Index" (SDSDI) with a fusion structure and dynamic correction to finely depict the imbalance degree between infrastructure supply and usage behavior in different regions.

[0132] The input variables include:

[0133] Regional supply matrix , representing the service intensity of facilities for region .

[0134] Regional demand matrix , representing the actual usage demand of region for facilities .

[0135] Regional population travel activity coefficient (from step 3);

[0136] Regional facility load risk coefficient , reflecting the long-term tension degree of infrastructure carrying within the region (such as the normalized value of the annual average load ratio of facilities);

[0137] Cross-regional service outflow ratio , defined as the proportion of the demand generated by the population in region for "non-local facilities", reflecting the degree of dependence of the region on external facilities. The calculation formula is as follows:

[0138] ;

[0139] Where:

[0140] represents the set of facilities within region ;

[0141] represents the actual demand of region for facilities ;

[0142] is a small constant to prevent the denominator from being 0.

[0143] This item reflects the "external overflow dependence" of regional services and is an important dimension for evaluating regional structural imbalance.

[0144] To evaluate the "basic deviation" between supply and demand, we define the regional-level supply-demand structural deviation value , representing the normalized cumulative degree of the supply and demand offset of all relevant facilities in the area :

[0145] ;

[0146] Among them:

[0147] : The unit supply-demand deviation index of the area , usually ranging between ;

[0148] : The set of all facilities that generate services for the area ;

[0149] : The supply intensity of the facility for the area ;

[0150] : The actual demand intensity of the area for the facility ;

[0151] : The smoothing factor to prevent division by zero (recommended );

[0152] : The facility response importance factor, defined as:

[0153] ;

[0154] represents the service weight of the facility in all facilities that affect the area ;

[0155] This formula not only considers the proportional offset of supply and demand differences, but also introduces the influence weight of the service "main facility" through , giving higher evaluation sensitivity to the imbalance of the main service sources. This structural design can reflect the real scenario of "the imbalance of key facilities is more important".

[0156] After calculating , we further define the "behavior-structure fusion dynamic equilibrium score" , and construct the following index model by performing multi-dimensional adjustment and correction on the basic deviation:

[0157] ;

[0158] Among them:

[0159] : The balance score of the area, with a value range , where a larger value indicates a higher degree of balance;

[0160] : The deviation of the basic supply-demand structure;

[0161] : The population travel activity coefficient (from step 3);

[0162] : The service spillover coefficient, indicating the degree of dependence of the area on external services;

[0163] : The area facility load pressure coefficient (such as the annual average utilization rate), and its square term strengthens the non-linear increase of high-pressure risk;

[0164] : The weighted adjustment factor (for example, it can be set , , ) to adapt to the urban policy orientation.

[0165] For example: Suppose the parameters of a certain area are as follows:

[0166] (slight deviation of the supply-demand structure);

[0167] (high travel activity area);

[0168] (40% of the population uses external services);

[0169] (the facilities have entered the high-load risk);

[0170] Set the adjustment coefficient , , , then:

[0171] ;

[0172] This balance score indicates that the overall supply-demand imbalance in the area is relatively serious, and there are co-existing problems on both the behavioral side and the facility side.

[0173] The output result is the area balance index sequence , which will serve as the basic support for generating sorting, grading, and control suggestions in the subsequent optimization feedback.

[0174] In summary, in this step, through the integration of multi-dimensional regulation and structural indices, a quantification scheme highly adaptable to the scenario of infrastructure space imbalance assessment is constructed, which is the technical core node supporting systematic evaluation in this scheme.

[0175] Step 5: Dynamic Feedback and Generation of Policy Recommendations

[0176] This step aims to conduct a regularized interpretation of the regional balance score output in the previous step, and combine it with the basic attributes of the region to form structured and classified policy recommendations, which are used as the response output of the entire patent system to achieve a closed-loop of "modeling - evaluation - optimization". We propose a "rule set for policy generation driven by evaluation" to achieve differentiated regulation recommendations for the balance results, avoid continued modeling or numerical optimization, and ensure the clarity, reproducibility, and operability of policy generation.

[0177] The only input for this step is the balance score sequence output in the previous step , where:

[0178] ∈ (0, 1], representing the dynamic supply-demand balance score of region ; the lower the

[0179] , the higher the degree of supply-demand imbalance in this region.

[0180] Design a rule set based on the score interval to directly divide different value segments into several policy levels, and combine the basic population size of region (determined in Step 1) to output the response policy recommendation category :

[0181] ;

[0182] where:

[0183] : the policy category recommendation corresponding to region ;

[0184] : the balance threshold (such as , );

[0185] : the population critical scale used to distinguish high-population and low-population areas (such as );

[0186] The specific recommendations for each policy category are as follows:

[0187] Expansion Priority ( very low + high population):

[0188] Strategic suggestions: Build or expand infrastructure, give priority to introducing supply points within the region, and shorten the service distance;

[0189] Supporting measures: Set up new stations, increase the capacity of existing facilities, and encourage local and nearby use.

[0190] Structural adjustment (medium score or small population area):

[0191] Strategic suggestions: Optimize the layout of existing facilities and improve the resource utilization efficiency;

[0192] Supporting measures: Through facility integration and cross-regional cooperation, divert redundant / insufficient resources.

[0193] Flexible redundancy (high-score area):

[0194] Strategic suggestions: Do not add new facilities and retain flexible space;

[0195] Supporting measures: Strengthen behavior monitoring, set up a warning mechanism, and maintain flexible scheduling.

[0196] The technical solutions in the embodiments of the present application at least have the following technical effects or advantages: Based on multi-source heterogeneous data, an innovative infrastructure dynamic spatial service area modeling mechanism is introduced, which can fully consider various spatial factors such as terrain, traffic accessibility, and facility supply capacity, dynamically construct the real service scope of each facility, and truly reflect the effective radiation capacity of infrastructure inside and outside the region to the population; at the same time, the system combines the crowd micro-behavior modeling mechanism to simulate the cross-regional flow, preference selection, and usage behavior of different groups for infrastructure inside and outside the service area, accurately depict the dynamic supply-demand relationship of "people-facility-space", and significantly improve the authenticity and accuracy of the evaluation results. In addition, the present invention further establishes a regional balance dynamic evaluation and feedback mechanism to support real-time updating of the balance evaluation results and strategic suggestions under the action of dynamic factors such as supply-demand relationship, population change, and resource adjustment.

[0197] The embodiments of the present application also provide an infrastructure regional balance evaluation system based on multi-dimensional data, as Figure 2 shown, including:

[0198] A data collection module, configured to collect multi-dimensional raw data, integrate the multi-dimensional raw data into a data set after preprocessing, and establish a data graph model with each region and facility as nodes and the traffic connection and influence relationship between regions as edges;

[0199] Supply and demand calculation module, which is configured to calculate the influence of each facility on any area based on the data graph model, delimit the dynamic service area of each facility based on the influence, and generate a corresponding spatial supply matrix for representing the comprehensive service volume obtained by the area from each facility; use the spatial supply matrix, the population attributes of each area, and the facility service area as inputs to calculate the demand of the area for the facilities, screen the facilities actually reachable by the area, and output the dynamic actual demand matrix of each area;

[0200] Supply and demand equilibrium evaluation module, which is configured to use the spatial supply matrix and the dynamic actual demand matrix as inputs to complete the supply-demand matching analysis of the infrastructure services in the area, and output a sequence of regional equilibrium indicators after quantifying it;

[0201] Strategy generation module, which is configured to divide different sequences of regional equilibrium indicators into different intervals corresponding to different strategy levels, and combine with the basic population scale of the area to output corresponding response strategies.

[0202] The technical solutions in the embodiments of the present application at least have the following technical effects or advantages: Based on multi-source heterogeneous data, an innovative infrastructure dynamic spatial service area modeling mechanism is introduced, which can fully consider various spatial factors such as terrain, traffic accessibility, and facility supply capacity, dynamically construct the real service scope of each facility, and truly reflect the effective radiation ability of the infrastructure inside and outside the area to the population; at the same time, the system combines the crowd micro-behavior modeling mechanism to simulate the cross-regional flow, preference selection, and usage behavior of different groups for the infrastructure inside and outside the service area, accurately depicts the dynamic supply-demand relationship of "people-facility-space", and significantly improves the authenticity and accuracy of the evaluation results. In addition, the present invention further establishes a regional equilibrium dynamic evaluation and feedback mechanism, which supports real-time updating of the equilibrium evaluation results and strategy suggestions under the action of dynamic factors such as supply-demand relationship, population change, and resource adjustment.

[0203] The working principle is as follows: By introducing an infrastructure dynamic spatial service area modeling mechanism, the real service scope of the facility is dynamically constructed based on multi-dimensional data, and the dynamic supply-demand relationship is constructed by combining the crowd behavior for dynamic evaluation.

[0204] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A method for evaluating the regional balance of infrastructure based on multi-dimensional data, characterized in that It includes the following steps: S1: Collect multi-dimensional raw data, preprocess the multi-dimensional raw data and integrate it into a data set, and establish a data graph model with each region and facility as nodes and the traffic connections and influence relationships between regions as edges; S2: Calculate the influence of each facility on any region based on the data graph model, delimit the dynamic service area of each facility based on the influence, and generate a corresponding spatial supply matrix to represent the comprehensive service volume obtained by the region from each facility; S3: Take the spatial supply matrix, the population attributes of each region, and the facility service area as inputs to calculate the demand of the region for the facility, screen the facilities actually reachable by the region, and output the dynamic actual demand matrix of each region; S4: Take the spatial supply matrix and the dynamic actual demand matrix as inputs, complete the supply-demand matching analysis of the infrastructure services within the region, and output a sequence of regional balance indicators after quantifying it; S5: Divide the sequence of regional balance indicators in different regions into different intervals corresponding to different strategy levels, and combine with the basic population scale of the region to output corresponding response strategies.

2. The infrastructure area balance evaluation method based on multi-dimensional data according to claim 1, wherein The multi-dimensional raw data in step S1 includes infrastructure data, traffic network data, terrain data, and population data.

3. The infrastructure area balance evaluation method based on multi-dimensional data according to claim 1, characterized in that The calculation of the influence in step S2 is obtained by weighted calculation of the traffic time or distance from the region to the facility, the traffic cost ratio at the location of the facility, and the service supply-demand pressure ratio.

4. The infrastructure area balance evaluation method based on multi-dimensional data according to claim 1, characterized in that The demand for the facility in step S3 is calculated by balancing the weights of the population base, travel activity, spatial supply, traffic accessibility, subjective preference, and service scope.

5. The infrastructure area balance evaluation method based on multi-dimensional data according to claim 1, characterized in that The supply-demand matching analysis in step S4 evaluates the basic deviation between supply and demand by calculating the normalized cumulative degree of the supply and demand of all facilities within the region, and calculates the balance score of the region after multi-dimensional adjustment and correction of the basic deviation.

6. The infrastructure area balance evaluation method based on multi-dimensional data according to claim 5, characterized in that The balance score of the region is converted into a standardized score, that is, a sequence of regional balance indicators, by weighted summation of negative factors to amplify the imbalance, and the negative factors include the basic deviation between supply and demand, the degree of dependence of the region on external services, and the overloading situation of the facilities.

7. The infrastructure area balance evaluation method based on multi-dimensional data according to claim 1, characterized in that In step S5, by setting a first balance threshold, a second balance threshold, and a population critical threshold respectively, the corresponding situation of the strategy level is as follows: When the balance score sequence is lower than the first balance threshold and the population is lower than the population critical threshold, the strategy level is expansion priority, adding or expanding infrastructure; When the balance score sequence is higher than or equal to the first balance threshold and lower than the second balance threshold and / or the population is lower than the population critical threshold, the strategy level is structural adjustment, optimizing the layout of existing facilities; When the balance score sequence is higher than the second balance threshold, the strategy level is flexible redundancy, and no new facilities are added.

8. An infrastructure area balance evaluation system based on multi-dimensional data, characterized in that, It includes: A data collection module, which is configured to collect multi-dimensional raw data, preprocess the multi-dimensional raw data and integrate it into a data set, and establish a data graph model with each region and facility as nodes and the traffic connections and influence relationships between regions as edges; Supply and demand calculation module, which is configured to calculate the influence of each facility on any area based on the data graph model, delimit the dynamic service area of each facility based on the influence, and generate a corresponding spatial supply matrix to represent the comprehensive service volume obtained by the area from each facility; use the spatial supply matrix, the population attributes of each area, and the facility service area as inputs to calculate the demand of the area for the facilities, screen the facilities actually reachable by the area, and output the dynamic actual demand matrix of each area; Supply and demand equilibrium evaluation module, which is configured to take the spatial supply matrix and the dynamic actual demand matrix as inputs, complete the supply-demand matching analysis of the infrastructure services in the area, and output the regional equilibrium index sequence after quantification; Strategy generation module, which is configured to divide different regional equilibrium index sequences into different intervals corresponding to different strategy levels, and combine with the basic population scale of the area to output the corresponding response strategies.

Images