Visual intelligent big data city planning decision support management method and system

Abstract

The invention provides a visual intelligent big data city planning decision support management method and system, and relates to the technical field of big data management, and the method comprises the steps: obtaining real-time data from a plurality of data sources, and generating an original data flow; performing first preprocessing on the original data stream to generate a standardized data set; acquiring a first timestamp of data in the standardized data set, and performing time alignment and synchronization processing on the first timestamp to generate a synchronous data set; acquiring content features of data in the synchronous data set, and matching the content features to generate a matched data set; performing deep analysis on the data of the matched data set by using a long-short-term memory model to generate a comprehensive analysis data set; generating dynamic visual display content according to the comprehensive analysis data set; generating a customized user interface according to an input operation and a personalized demand of the user; according to the invention, dynamic analysis content can be provided, and decision basis can be provided for conferences.

Description

Technical Field

[0001] The present invention relates to the technical field of big data management, and in particular to a visualized intelligent big data urban planning decision support management method and system. Background Art

[0002] At present, the application of big data technology in urban planning and decision-making management has become more common. Existing technologies usually use data collection, storage, analysis and visualization to comprehensively process information such as urban traffic, environment, population distribution, etc. to support urban managers in formulating reasonable planning schemes. Specifically, common methods include using IoT devices to collect urban dynamic data, storing and processing them through cloud computing or distributed databases, and using geographic information systems (GIS) or three-dimensional visualization technology to present analysis results, making urban planning schemes more intuitive and scientific. For example, in terms of traffic management, existing technologies use historical traffic flow data and real-time monitoring data, combined with machine learning algorithms to predict future road congestion, thereby optimizing traffic signal control strategies. However, although existing technologies have played an important role in improving data processing capabilities and assisting decision-making, they still have certain limitations.

[0003] In the existing big data urban planning decision support technology, there is a problem of insufficient mining of data correlation, resulting in the inadequate reflection of the interaction between different urban elements. For example, in smart community planning, existing systems often analyze factors such as population density, commercial facility distribution and traffic flow separately, but lack in-depth modeling of the interaction between these data. Taking the site selection of a new commercial complex in a certain city as an example, the existing method may make a preliminary screening based on population density and consumption capacity, but fails to fully consider the impact of surrounding traffic flow, parking capacity and public transportation accessibility on the activity of the business district, resulting in lower-than-expected passenger flow and insufficient commercial vitality after site selection. This defect makes it difficult to achieve precise optimization of urban planning decisions, thus affecting the rational allocation of urban resources. Summary of the invention

[0004] The purpose of the present invention is to provide a visualized intelligent big data urban planning decision support management method and system, aiming to solve the problems mentioned in the background technology.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, a visualized smart big data urban planning decision support management method is provided, characterized in that the method comprises:

[0007] Obtain multidimensional data related to urban planning, including population density data, commercial facility distribution data, traffic flow data, parking capacity data, and public transportation accessibility data; preprocess the multidimensional data, including format standardization, missing value filling, and data deduplication, to obtain a structured data set;

[0008] Based on the structured data set, a correlation analysis model between urban elements is established, and the interaction factors between different urban element data are calculated through it to form an urban element correlation matrix;

[0009] Extract features from the urban factor association matrix, screen out urban factor combinations, and use causal inference methods to calculate the weight values ​​of different urban factor combinations to obtain the decision-making influencing factor weight matrix;

[0010] According to the decision-making influencing factor weight matrix, the site selection optimization calculation is performed on the target planning area, and the comprehensive fitness score of each candidate area is calculated;

[0011] According to the comprehensive fitness score, the candidate areas are ranked, and the candidate area with the highest comprehensive fitness score is selected as the target area. A visual urban planning decision report is generated, including the geographical location of the target area, the composition of the comprehensive fitness score, the results of the urban element correlation analysis, and the site selection optimization calculation process.

[0012] Preferably, the method of establishing a correlation analysis model between urban elements based on the structured data set, and calculating the interaction factors between different urban element data through the model to form an urban element correlation matrix includes:

[0013] According to the structured data set, extract the urban element data to obtain the element basic data;

[0014] Analyze the data characteristics of the basic data of the elements, calculate the distribution patterns of each city element in different regions, and obtain the element characteristic data;

[0015] According to the element characteristic data, the correlation relationship between urban elements is calculated to obtain element correlation data;

[0016] According to the factor correlation data, the interaction factors between different factors are calculated to form the factor interaction data; , For urban elements With urban elements The interaction factors between For urban elements in state The weight coefficient at , is the number of samples, is the number of spatial locations, is the time step, For urban elements With urban elements The weighted mutual information entropy between is the spatial correlation coefficient, is the time correlation coefficient, , is the adjustment coefficient, satisfying ;in, , For urban elements With urban elements In Status The joint probability at , Urban elements and urban elements In Status The independent probability of , and Urban elements and urban elements In spatial position The value at and Urban elements and urban elements The mean value at all spatial locations; , and Urban elements and urban elements In time The value at and Urban elements With urban elements Mean across all time points;

[0017] Based on the element interaction data, the urban element association matrix is ​​constructed.

[0018] Preferably, the feature extraction of the city element association matrix is ​​performed to screen out the city element combinations, and the weight values ​​of different city element combinations are calculated using a causal inference method to obtain a decision-making influencing factor weight matrix, including:

[0019] Perform data screening on the urban element correlation matrix, remove low-correlation urban elements, and obtain screening element data;

[0020] Conduct causal inference analysis on the screening factor data, calculate the causal relationship between the city factors, and obtain causal analysis data;

[0021] According to the causal analysis data, the impact weights of different city element combinations are calculated to obtain the impact weight data;

[0022] Based on the impact weight data, a decision-making impact factor weight matrix is ​​constructed.

[0023] Preferably, the calculation formula for the influence weight of the combination of urban elements is: , is the impact weight of the combination of urban elements, For urban elements In Status When The probability of occurrence, satisfying =1, For urban elements In Status When The expected value of Pick or , , For urban elements different states, For urban elements The weight coefficient satisfies 0.

[0024] Preferably, the site selection optimization calculation is performed on the target planning area according to the decision influencing factor weight matrix, and the comprehensive fitness score of each candidate area is calculated, including:

[0025] According to the decision-making influencing factor weight matrix, the data of the target planning area is extracted to obtain the regional element data;

[0026] Evaluate the regional factor data, calculate the basic fitness score of each candidate region, and obtain preliminary score data;

[0027] Based on the preliminary scoring data, analyze the competition relationship between candidate regions, calculate the competition impact factor, and obtain the competition correction data;

[0028] Based on the accessibility of the target planning area to key resources, the resource accessibility correction factor is calculated to obtain resource correction data;

[0029] Based on the environmental constraints of the target planning area, calculate the environmental restriction factors and obtain the environmental correction data:

[0030] Based on the preliminary scoring data, competition correction data, resource correction data and environment correction data, the comprehensive fitness score of the candidate area is calculated to obtain the comprehensive fitness score data.

[0031] Preferably, the calculation formula of the comprehensive fitness score is: , For alternative areas The comprehensive fitness score of For alternative areas The basic fitness score of For alternative areas Competitive Area The competitive influence factors between For competitive areas The weight coefficient satisfies , Resource Center The weight coefficient satisfies , Alternative regional center location Go to Resource Center The Euclidean distance of Environmental factors The weight coefficient satisfies , Environmental factors In the data sample Alternative areas The impact value of is the number of competitive impact factors, is the number of resource centers, is the number of environmental factors, is the number of data samples.

[0032] Preferably, the candidate areas are sorted according to the comprehensive fitness scores, the candidate area with the highest comprehensive fitness score is selected as the target area, and a visual urban planning decision report is generated, including:

[0033] According to the comprehensive fitness score data, the candidate area with the highest score is extracted to obtain the target area data;

[0034] Perform feature analysis on the target area data, extract key urban element information, and obtain regional feature data;

[0035] According to the regional characteristic data, analyze the advantages and disadvantages of the target area in different urban element dimensions to obtain regional evaluation data;

[0036] Generate visual planning decision data based on regional assessment data and combined with the urban element association matrix;

[0037] Visualize the planning decision data and output it to the urban planning management system.

[0038] In a second aspect, a visual intelligent big data urban planning decision support management system is provided, the system comprising:

[0039] The data collection and processing module is used to obtain multidimensional data related to urban planning, including population density data, commercial facility distribution data, traffic flow data, parking lot capacity data, and public transportation accessibility data; pre-process the multidimensional data, including format standardization, missing value filling, and data deduplication, to obtain a structured data set;

[0040] The urban element association module is used to establish an association analysis model between urban elements based on the structured data set, and calculate the interaction factors between different urban element data to form an urban element association matrix;

[0041] The urban element analysis module is used to extract features from the urban element association matrix, screen out urban element combinations, and use causal inference methods to calculate the weight values ​​of different urban element combinations to obtain the decision-making influencing factor weight matrix;

[0042] The urban element analysis module is used to optimize the site selection of the target planning area according to the decision-making influencing factor weight matrix and calculate the comprehensive fitness score of each candidate area;

[0043] The decision report generation module is used to sort the candidate areas according to the comprehensive fitness score, select the candidate area with the highest comprehensive fitness score as the target area, and generate a visual urban planning decision report, including the geographical location of the target area, the composition of the comprehensive fitness score, the results of the urban element correlation analysis, and the site selection optimization calculation process.

[0044] The above solution of the present invention includes at least the following beneficial effects:

[0045] In the context of big data technology being widely used in urban planning and decision-making management, although existing technologies can collect, store, analyze and visualize information such as urban transportation, environment, and population distribution, there are still certain limitations in data correlation mining, resulting in the inability to fully reflect the interaction between different urban elements. For example, in the process of smart community planning or commercial complex site selection, existing methods often analyze population density, commercial facility distribution, and traffic flow independently, but fail to fully consider the causal relationship and interaction between these factors, affecting the accuracy of planning decisions. To address this problem, this method proposes a visual smart big data urban planning decision support management method, which establishes a correlation analysis model between urban elements and calculates the interaction factors between different urban element data to form an urban element correlation matrix, thereby making up for the shortcomings of existing technologies in element correlation analysis.

[0046] First, in the data processing stage, this method constructs a multidimensional data input source by obtaining population density data, commercial facility distribution data, traffic flow data, parking capacity data, and public transportation accessibility data to ensure the comprehensiveness and accuracy of the data. Compared with the existing technology that relies on a single or a few key indicators for decision-making, this method uses richer urban element data, so that the planning scheme can fully consider the various influencing factors of urban development. In addition, through data preprocessing operations such as format standardization, missing value filling, and data deduplication, data quality is ensured, the impact of data redundancy on decision-making calculations is reduced, and the reliability of data analysis is improved.

[0047] Secondly, this method breaks through the limitation of existing technologies that only conduct single-factor analysis by establishing a correlation analysis model between urban elements. In existing methods, the site selection of commercial facilities may be mainly based on population density and consumption capacity, while ignoring the impact of key factors such as traffic flow, parking capacity and public transportation accessibility on the activity of the business district, resulting in insufficient commercial vitality after site selection. This method calculates the interaction factors between urban element data and constructs an urban element association matrix, so that the interaction relationship between different urban elements can be quantified and visualized. For example, in a certain planning area, population density may be positively correlated with the distribution of commercial facilities, while traffic flow may have a nonlinear effect on commercial attractiveness. These interactions can be accurately reflected in the urban element association matrix, making urban planning more accurate and efficient.

[0048] In addition, this method further improves the intelligence level of decision-making optimization. By extracting features from the urban element association matrix, screening out highly correlated urban element combinations, and using causal inference methods to calculate the weight values ​​of different urban element combinations, the relative importance of different factors in planning decisions can be accurately identified. In contrast, existing technologies mainly rely on static data analysis and fail to deeply explore the causal relationship between data, resulting in low adaptability of planning schemes. This method calculates the impact weights of urban element combinations through causal inference, and can dynamically adjust the priorities of different elements to ensure that planning schemes are more in line with actual needs. For example, in different types of urban planning, commercial site selection may be more dependent on population density and consumption capacity, while transportation hub planning may be more dependent on traffic flow and public transportation accessibility. This method can automatically adjust the weight parameters of the decision model according to specific planning goals, making the final site selection plan more targeted.

[0049] Finally, the method also uses site optimization calculations to perform comprehensive fitness scores on multiple candidate areas in the target planning area, thereby improving the accuracy of site selection decisions. In the prior art, site optimization is usually ranked only based on certain static indicators, while ignoring the impact of competitive relationships and resource distribution between different regions. This method corrects the basic fitness score by calculating the competitive impact factor, resource accessibility correction factor and environmental restriction factor of the candidate area, so that the final comprehensive fitness score can more accurately reflect the true suitability of the candidate area. For example, in the site selection of a commercial complex, the population density of a certain area may be high, but if there are already multiple competitive commercial projects in the surrounding area, the market competition pressure is high, and the fitness score may be negatively affected. This method can incorporate these competitive factors into the site selection evaluation scope through the calculation of competitive impact factors, making the final decision more scientific and reasonable.

[0050] In summary, this method effectively makes up for the shortcomings of existing technologies in terms of insufficient mining of urban element correlation, weak causal relationship identification, and inaccurate site optimization by establishing an urban element correlation analysis model, calculating interactive influence factors, using causal inference methods to calculate weight matrices, and optimizing site selection schemes based on multi-factor analysis. This method not only improves the scientificity and rationality of urban planning decisions, but also improves the understanding and utilization of planning data by urban managers through visualizing urban planning decision reports, thereby facilitating the efficient development of smart cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a flowchart of a visualized intelligent big data urban planning decision support management method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0053] like Figure 1 As shown, an embodiment of the present invention proposes a visual smart big data urban planning decision support management method, the method comprising:

[0054] Obtain multidimensional data related to urban planning, including population density data, commercial facility distribution data, traffic flow data, parking capacity data, and public transportation accessibility data; preprocess the multidimensional data, including format standardization, missing value filling, and data deduplication, to obtain a structured data set;

[0055] Based on the structured data set, a correlation analysis model between urban elements is established, and the interaction factors between different urban element data are calculated through it to form an urban element correlation matrix;

[0056] Extract features from the urban factor association matrix, screen out urban factor combinations, and use causal inference methods to calculate the weight values ​​of different urban factor combinations to obtain the decision-making influencing factor weight matrix;

[0057] According to the decision-making influencing factor weight matrix, the site selection optimization calculation is performed on the target planning area, and the comprehensive fitness score of each candidate area is calculated;

[0058] According to the comprehensive fitness score, the candidate areas are ranked, and the candidate area with the highest comprehensive fitness score is selected as the target area. A visual urban planning decision report is generated, including the geographical location of the target area, the composition of the comprehensive fitness score, the results of the urban element correlation analysis, and the site selection optimization calculation process.

[0059] In an embodiment of the present invention, this method can effectively improve the scientificity and feasibility of urban planning, and improve the accuracy of site optimization based on multidimensional data analysis. By obtaining multidimensional data related to urban planning, including population density data, commercial facility distribution data, traffic flow data, parking lot capacity data, and public transportation accessibility data, it is possible to fully grasp the distribution of key elements in the urban area and ensure the comprehensiveness and accuracy of the data. These data cover the important factors that affect the layout of urban functional areas and provide reliable data support for subsequent planning decisions. In the process of data acquisition, data can be updated in real time through various channels such as urban management systems, remote sensing data, and traffic monitoring systems to ensure the timeliness and accuracy of the data.

[0060] The process of data preprocessing can further improve data quality and ensure the reliability of model analysis. Standardizing the format of multidimensional data makes data from different sources have a consistent structure to avoid information loss or calculation errors caused by data format mismatch. At the same time, for missing value filling operations, mean filling, interpolation or prediction based on historical data can be used to ensure data integrity and improve the calculation accuracy of the model. In addition, through data deduplication, the interference of duplicate data on the analysis results can be effectively avoided, ensuring the authenticity and reliability of data statistics. After these processes, the structured data set obtained has a high-quality calculation basis, which provides accurate data input for subsequent urban planning analysis.

[0061] Based on structured data sets, a correlation analysis model between urban elements is established, so that urban planning is no longer limited to the independent analysis of a single element, but can consider the interaction and influence between different elements. There may be complex interactions between urban element data, such as the attraction effect of population density on commercial facilities, the impact of traffic flow on parking demand, etc. By constructing an urban element correlation matrix, these interactions can be quantitatively described, so that the degree of correlation between each element can be scientifically evaluated during the planning process. In the process of calculating the interaction influence factors, statistical analysis methods, machine learning models or causal inference methods can be used to reveal the deep correlation between different urban elements, so as to more accurately predict the future change trend of urban elements.

[0062] The construction of the weight matrix of decision-making influencing factors further improves the rationality of site selection optimization. After screening out the combination of urban elements with strong correlation, the weight values ​​of different combinations of urban elements are calculated by causal inference method, which can clarify the influence of each factor on the final site selection decision. For example, in the site selection process of commercial areas, population density and traffic flow may be the main decision factors, while in industrial area planning, land availability and infrastructure construction may have higher weights. By calculating the weight matrix, the importance of each factor can be adjusted according to different planning scenarios, so that the planning scheme can be more in line with actual needs.

[0063] Finally, through this method, the site selection optimization calculation of the target planning area can be carried out, and the optional areas in the city can be comprehensively evaluated based on multi-dimensional data, avoiding the one-sidedness caused by a single indicator decision. The calculation of the comprehensive fitness score takes into account the interaction of multiple urban elements, making the final selected area more reasonable in the overall planning. By sorting the candidate areas, the advantages and disadvantages of different site selection schemes can be objectively evaluated to ensure that the final selected area has the best fitness and reduce the waste of resources caused by unreasonable planning. At the same time, a visual urban planning decision report is generated, so that planners can intuitively understand the advantages and disadvantages of different site selection schemes, thereby improving the transparency and explainability of decision-making. This method not only improves the scientific nature of urban planning, but also enhances its feasibility in practical applications.

[0064] The multidimensional data related to urban planning are obtained, including population density data, commercial facility distribution data, traffic flow data, parking lot capacity data and public transportation accessibility data; the multidimensional data are preprocessed, including format standardization, missing value filling and data deduplication, to obtain a structured data set, specifically including:

[0065] The main data types include:

[0066] Population density is an important parameter in urban planning and is usually used to measure the population distribution in different areas to assist in decisions such as commercial site selection and layout of public service facilities.

[0067] Data source: can be obtained through census data, mobile signaling data, and socio-economic survey data.

[0068] Data characteristics: stored in grid form (such as 100m×100m or 1km×1km), and the unit is usually "person / square kilometer".

[0069] Application scenarios: It can be used to analyze residents’ residential density, commuting needs, commercial needs, etc.

[0070] The spatial distribution of commercial facilities directly affects the economic vitality of urban areas and is crucial to commercial site selection and land use planning.

[0071] Data source: can be obtained through government statistical data, online map APIs such as Amap, Baidu, Google Maps, corporate registration information, etc.

[0072] Data characteristics: usually include the geographic coordinates, category (such as retail, catering, entertainment), scale (such as business area, number of employees), etc. of the commercial facilities.

[0073] Application scenarios: It can be used to analyze the formation mechanism of business districts, the commercial competition landscape, and the development potential of commercial areas.

[0074] Traffic flow data is used to describe traffic flow conditions in different areas, and can assist in optimizing road planning, public transportation layout, and business district vitality analysis.

[0075] Data sources: Sources include traffic monitoring systems (cameras, radars), GPS devices, mobile phone signaling data, etc.

[0076] Data characteristics: can be stored in the form of time series, such as "hourly traffic volume", "peak hour traffic pressure", etc., and can be subdivided according to different modes of transportation, such as walking, bicycle, bus, and private car.

[0077] Application scenarios: It can be used for traffic bottleneck analysis, travel pattern prediction, and evaluation of the accessibility of commercial facilities.

[0078] The capacity and distribution of parking lots affect urban traffic mobility and are also of great significance to the site optimization of commercial and residential areas.

[0079] Data sources: mainly from parking management systems, government planning data, Internet of Things (IoT) sensor monitoring systems, etc.

[0080] Data features: including parking lot location, total number of parking spaces, utilization rate, charging standards, etc.

[0081] Application scenarios: It can be used to evaluate the carrying capacity of commercial areas, optimize parking lot locations, and reduce traffic congestion.

[0082] Public transportation accessibility measures the convenience for residents or visitors in different areas to reach specific locations and is one of the core indicators in urban planning.

[0083] Data sources: Data can be obtained from bus companies, subway operators, urban planning management systems, or through open data such as the GTFS data format.

[0084] Data features: including the location of bus stops and subway stations, line coverage, frequency intervals, transfer times, etc.

[0085] Application scenarios: Used to evaluate the convenience of public transportation, optimize station layout, and enhance the attractiveness of public transportation.

[0086] The data formats of different data sources may be incompatible, such as: Inconsistent coordinate systems: Some data may use the WGS84 coordinate system, while others may use the GCJ-02 coordinate system, which requires unified conversion. Different unit standards: For example, traffic flow may use "vehicles / hour", while some systems use "vehicles / minute", which needs to be converted to a unified unit. Inconsistent data storage structure: For example, some data is stored in CSV format, while some data is stored in JSON or database, which needs to be converted to a standardized database format. In the process of format standardization, the data storage format is usually unified so that all data conforms to a unified structure and ensures that data from different sources can be used compatibly. For example, all geographic data can be converted to GeoJSON or Shapefile format for unified management in a GIS system.

[0087] The following methods are usually used to fill missing values: Interpolation: For time series data such as traffic flow, linear interpolation or moving average can be used to fill missing values. Neighboring area inference: For spatial data such as population density, inference can be made based on the data of adjacent areas. Machine learning prediction: Based on historical data and related variables, the model can be trained to predict missing values, such as using a regression model to predict the density of commercial facilities in a certain area.

[0088] Deduplication methods include:

[0089] Deduplication based on geographic location: If the coordinates of two data points are very close, such as the error is less than 10 meters, and their attributes are basically the same, they can be merged into one data point. Deduplication based on unique identifier: If the data contains a unique ID, such as a business registration number or a camera number, deduplication can be performed based on the ID. Deduplication based on similarity matching: Use fuzzy matching technology to determine whether records with similar names are the same entity. After format standardization, missing value filling and deduplication processing, a high-quality structured data set is finally obtained. This data set is usually stored in the form of a table or database with unified data fields.

[0090] The candidate area refers to a candidate area within the target planning area or near its boundary that meets specific site selection conditions and has potential development value. The candidate area is used for site selection optimization calculation to screen out the best target area.

[0091] The target planning area refers to the overall planning scope set by the urban planning management department or decision makers. The target planning area is used to define the geographical boundary of the site selection optimization and ensure that the site selection calculation is only performed within this scope. The scope of the target planning area can be set according to administrative divisions, functional zoning, economic development needs or urban expansion plans;

[0092] The target planning area is divided into different geographical units and segmented using a gridding method or a method based on existing administrative divisions to form multiple alternative areas. The gridding method is used to divide the target planning area into regular geographical units, for example, into grid units of 100m×100m or 1km×1km, while the method based on administrative divisions can directly use existing streets, communities or functional areas as alternative areas to reduce repeated calculations and geographical errors.

[0093] In a preferred embodiment of the present invention, the correlation analysis model between urban elements is established based on the structured data set, and the interaction factors between different urban element data are calculated through the model to form an urban element correlation matrix, including:

[0094] According to the structured data set, extract the urban element data to obtain the element basic data;

[0095] Analyze the data characteristics of the basic data of the elements, calculate the distribution patterns of each city element in different regions, and obtain the element characteristic data;

[0096] According to the element characteristic data, the correlation relationship between urban elements is calculated to obtain element correlation data;

[0097] According to the factor correlation data, the interaction factors between different factors are calculated to form the factor interaction data; , For urban elements With urban elements The interaction factors between For urban elements in state The weight coefficient at , is the number of samples, is the number of spatial locations, is the time step, For urban elements With urban elements The weighted mutual information entropy between is the spatial correlation coefficient, is the time correlation coefficient, , is the adjustment coefficient, satisfying ;in, , For urban elements With urban elements In Status The joint probability at , Urban elements and urban elements In Status The independent probability of , and Urban elements and urban elements In spatial position The value at and Urban elements and urban elements The mean value at all spatial locations; , and Urban elements and urban elements In time The value at and Urban elements With urban elements Mean across all time points;

[0098] Based on the element interaction data, the urban element association matrix is ​​constructed.

[0099] In an embodiment of the present invention, in the process of urban planning, the interaction between urban elements plays a key role in planning decisions. There are complex interactions between different elements. For example, the distribution of commercial facilities is closely related to population density, public transportation accessibility affects travel patterns, and parking capacity affects traffic flow. In order to more scientifically analyze the relationship between these elements, a correlation analysis model between urban elements is constructed. This model can reveal the statistical relationship and causal influence between urban elements based on structured data sets, so that the planning scheme is more in line with actual needs.

[0100] First, before constructing the urban element association matrix, it is necessary to extract urban element data from the structured data set to form element basic data. These data contain information such as population density, commercial facility distribution, and traffic flow in different areas of the city to ensure the integrity and accuracy of the input data. After extracting the data, it is necessary to analyze the data characteristics to calculate the distribution patterns of various urban elements in different areas. There may be significant differences in the element characteristics of different areas. For example, the traffic flow in the commercial center area is much higher than that in the residential area, and areas with higher population density are usually accompanied by more commercial facilities. Through data feature analysis, these distribution patterns can be more clearly identified, providing data support for subsequent correlation analysis.

[0101] Based on the characteristic data of each urban element, the correlation between urban elements can be calculated to obtain element correlation data. The correlation between different elements can be calculated by statistical methods (such as Pearson correlation coefficient, Spearman correlation coefficient), or modeled and analyzed by machine learning methods. For example, in some cases, the distribution of commercial facilities may be highly positively correlated with population density, while parking lot capacity may be negatively correlated with public transportation accessibility. By analyzing these correlations, the interactions between urban elements can be quantified and it can be clarified which elements have a strong correlation in the urban planning process.

[0102] In order to further refine the interactions between urban elements, it is necessary to calculate the interaction factors between different elements. These factors can reflect how changes in a certain element affect other elements. For example, an increase in traffic flow may lead to an increase in commercial facilities, which in turn may further affect population mobility. When calculating the interaction factors, a more accurate impact model can be constructed based on causal inference methods or regression analysis methods based on historical data. Ultimately, through the calculation of these interaction factors, element interaction data is formed, allowing urban planning to consider the complex interactions between different elements.

[0103] After completing the calculation of the element interaction data, an urban element association matrix is ​​constructed to systematically present the degree of association between the elements. This matrix can not only be used for urban planning analysis, but also as basic data for subsequent decision optimization. In the planning process, decision makers can adjust the weights of different urban elements according to the matrix to ensure that the planning scheme can more accurately meet the needs of urban development. Through the establishment of the urban element association matrix, the scientificity and rationality of urban planning are further improved, making the planning scheme more forward-looking and adaptable.

[0104] The step of calculating the association relationship between city elements based on element feature data to obtain element correlation data specifically includes:

[0105] Acquire element characteristic data, wherein the element characteristic data includes spatial distribution data of various urban elements in different areas, and the urban elements include at least population density, commercial facility distribution, traffic flow, parking lot capacity and public transportation accessibility;

[0106] Based on the element characteristic data, characteristic values ​​of urban elements in each region are extracted, wherein the characteristic values ​​include distribution density, spatial distribution uniformity, change trend and impact range of the elements, so as to form a regional element characteristic matrix;

[0107] Based on the regional element characteristic matrix, the spatial similarity between different urban elements is calculated to obtain spatial correlation data, and the spatial correlation data is used to reflect the degree of overlap of different urban elements in spatial distribution, wherein if the spatial correlation of two elements is high, it indicates that their distribution trends in the urban area are relatively consistent;

[0108] Based on the regional element characteristic matrix, the change trend of different urban elements in the time dimension is analyzed to obtain time correlation data, which is used to describe the degree of synchronization of the changes of different urban elements over time. If the time correlation of two elements is high, it indicates that their temporal change patterns are similar. For example, the peak period of traffic flow and the change of activity of commercial facilities may have a strong time correlation.

[0109] Based on the spatial correlation data and the temporal correlation data, the comprehensive correlation between different urban elements is calculated to form element correlation data. The element correlation data is used to quantify the degree of association between different urban elements, so that subsequent urban planning can evaluate the interaction between different elements based on these data to optimize the layout of urban functional areas and resource allocation.

[0110] in, Comprehensively evaluate urban factors through weighted summation and The first term is the weighted mutual information entropy , reflects the correlation between the two factors in the state distribution, weight Indicates the importance of different states. The second and third terms introduce spatial correlation coefficients respectively. and time correlation coefficient , the dependence of quantitative elements on spatial distribution and time series, the adjustment coefficient and ,satisfy It is used to balance the contribution of space and time dimensions. This model can more comprehensively describe the dynamic interaction mechanism between urban elements through multi-dimensional integration, and is suitable for multi-factor collaborative analysis in urban planning.

[0111] in, Based on the concept of mutual information in information theory, the two city factors are measured and The statistical independence of . Joint probability With independent probability The larger the ratio is, the more the two factors are in state The stronger the correlation is. Through the negative logarithmic weighted summation, the larger the final value is, the higher the dependence of the two elements is. This method can effectively identify the nonlinear relationship between elements and provide a quantitative basis for the analysis of element coordination or conflict in urban systems.

[0112] in, The linear correlation between two factors in spatial position is calculated by referring to the form of Pearson correlation coefficient. The numerator is the covariance, the denominator is the product of the standard deviation, and the result range is [−1,1]. Positive values ​​indicate that the spatial distribution changes in the same direction, and negative values ​​indicate that the spatial distribution changes in the opposite direction. By introducing the spatial mean , and the global mean , , the formula distinguishes between local and overall spatial characteristics and is suitable for analyzing the spatial agglomeration effect or diffusion pattern of urban elements.

[0113] in, Similar to the spatial correlation coefficient structure, but focuses on the time dimension. By comparing the fluctuation trends of two factors in the time series, the dynamic correlation is quantified. and It represents the benchmark value within the time window, and the denominator is standardized to ensure the comparability of the results. This method can identify the lag effect or periodic co-change between factors, providing support for urban dynamic monitoring and prediction.

[0114] In a preferred embodiment of the present invention, the feature extraction of the city element association matrix is ​​performed to screen out the city element combinations, and the weight values ​​of different city element combinations are calculated by using a causal inference method to obtain a decision-making influencing factor weight matrix, including:

[0115] Perform data screening on the urban element correlation matrix, remove low-correlation urban elements, and obtain screening element data;

[0116] Conduct causal inference analysis on the screening factor data, calculate the causal relationship between the city factors, and obtain causal analysis data;

[0117] According to the causal analysis data, the impact weights of different city element combinations are calculated to obtain the impact weight data;

[0118] Based on the impact weight data, a decision-making impact factor weight matrix is ​​constructed.

[0119] In an embodiment of the present invention, in urban planning decisions, the interaction between urban elements has a key impact on site optimization. However, there is more than a simple correlation relationship between urban elements, but a complex causal relationship. For example, the increase in commercial facilities may be due to the growth of population density, and in turn, the density of commercial facilities will also affect the population flow pattern. Therefore, in order to more accurately evaluate the actual impact of urban elements, it is necessary to extract features from the urban element association matrix, screen out the element combinations that truly have a decisive impact, and use causal inference methods to calculate the weight values ​​of different urban element combinations to form a decision-making influencing factor weight matrix. This process can effectively improve the scientific nature of urban planning, so that site optimization is no longer a simple analysis based on static data, but can fully consider the interaction between different elements, so as to make more accurate planning decisions.

[0120] First, the urban element correlation matrix is ​​screened to remove low-correlation urban elements, which can avoid the interference of irrelevant or weakly correlated factors on the final decision. In urban planning data, not all elements are equally important for site optimization. For example, in the planning of commercial areas, commercial facility density, population density, and traffic flow may be key factors, while the impact of park green space area may be relatively small. Therefore, by screening low-correlation elements, it can be ensured that only urban elements that have an important impact on decision-making are retained, thereby improving the calculation efficiency and accuracy of the model.

[0121] Next, the selected urban element data are subjected to causal inference analysis to clarify the causal relationship between different elements. Traditional statistical correlation analysis can only indicate whether two variables have a certain linear or nonlinear relationship, but cannot distinguish causal relationships. For example, population density and commercial facility density may be highly correlated, but this does not mean that there is a direct causal relationship between the two. Therefore, the introduction of causal inference methods can infer which elements are the key factors that really affect other elements based on historical data, experimental data or structured causal models. For example, in the causal inference process, it can be found that public transportation accessibility is a direct factor affecting the distribution of commercial facilities, and the density of commercial facilities further affects the surrounding housing prices and population mobility. This in-depth causal analysis enables site optimization to be more in line with the actual situation of urban development, rather than simply relying on statistical covariation relationships.

[0122] Based on the results of causal inference analysis, the impact weights of different combinations of urban elements can be calculated to determine the contribution of each element in site optimization. The impact weights of different elements vary depending on specific planning needs. For example, in residential area planning, green space ratio may have a higher weight, while in commercial area site selection, traffic flow and population density have higher weights. By calculating the impact weights, it can be ensured that in different site selection scenarios, the optimal area selected meets specific types of planning needs, rather than using the same decision-making criteria across the board.

[0123] Finally, based on the calculated influence weight data, a decision-making influence factor weight matrix is ​​constructed, making the site selection optimization model more adaptable and intelligent. This matrix can be used as the core data for subsequent optimization calculations, allowing the model to dynamically adjust the factor weights when facing different types of urban planning needs, ensuring that the final selected area can meet the actual planning needs. In addition, the construction of this matrix can also improve the transparency of the planning scheme, allowing urban planners to clearly understand the impact of different factors on decision-making, so as to make decisions that are more in line with the direction of urban development in actual operations.

[0124] In summary, through the feature extraction and causal inference analysis of urban elements, we can not only screen out the most influential urban elements, but also quantify the influence of different elements on site optimization, so as to build a more accurate and intelligent urban planning decision-making model. This method can effectively improve the scientific nature of planning, expand the analysis of urban elements from simple correlation research to causal inference, provide more accurate data support for urban development, and improve the rationality and feasibility of site optimization.

[0125] In a preferred embodiment of the present invention, the calculation formula of the influence weight of the city element combination is: , is the impact weight of the combination of urban elements, For urban elements In Status When The probability of occurrence, satisfying =1, For urban elements In Status When The expected value of Pick or , , For urban elements different states, For urban elements The weight coefficient satisfies 0; , is the total number of data samples, For the target variable in the data sample The value at For urban elements In the data sample The value at , For urban elements The value is Time target variable Value probability.

[0126] In an embodiment of the present invention, Calculate the effect of factor combinations on the target variable through a causal inference framework The core is the intervention effect , indicating the city element State change pair The marginal impact of . Combined with the conditional probability and weight coefficient , the formula combines statistical association with causal contribution to avoid confounding bias.

[0127] in, Calculate urban elements through data-driven approach In Status When The conditional probability of occurrence. The numerator is the and The sum of the products of The sum of is actually a deformation of weighted average. Its core logic is to The presence or intensity of contribution, thus reflecting right Statistical relevance.

[0128] in, Based on the concept of "intervention" in causal inference, the calculation of the mandatory setting of urban elements For a specific state When Unlike ordinary conditional expectations, intervention expectations are achieved by splitting Confounding paths with other variables directly reflect right The causal effect of Indicates that under intervention The value is This method can effectively eliminate confounding bias and provide theoretical support for policy intervention or factor regulation.

[0129] Among them, in the formula, , The specific meaning is:

[0130] Indicates that a city element is in a changed state, such as new additions, upgrades, optimizations, etc.

[0131] It indicates that a certain urban element is in a baseline state, such as no change, original state, policy not implemented, etc.

[0132] The purpose of calculating the impact weight is to evaluate the impact of a certain factor change on the urban system, so it is necessary to construct two states of "change" and "no change" for comparison. (the state in which the element changes) and The difference in the impact of a factor (the state in which the factor has not changed) on a specific urban area can quantify the contribution of a factor to urban planning. For example, when evaluating the impact of a subway station construction on commercial vitality, It stands for "subway station has been built". It stands for “the subway station has not been built yet”, and the difference between the two can measure the impact of the subway station on the distribution of commercial facilities.

[0133] In a preferred embodiment of the present invention, the site selection optimization calculation is performed on the target planning area according to the decision influencing factor weight matrix, and the comprehensive fitness score of each candidate area is calculated, including:

[0134] According to the decision-making influencing factor weight matrix, the data of the target planning area is extracted to obtain the regional element data;

[0135] Evaluate the regional factor data, calculate the basic fitness score of each candidate region, and obtain preliminary score data;

[0136] Based on the preliminary scoring data, analyze the competition relationship between candidate regions, calculate the competition impact factor, and obtain the competition correction data;

[0137] Based on the accessibility of the target planning area to key resources, the resource accessibility correction factor is calculated to obtain resource correction data;

[0138] Based on the environmental constraints of the target planning area, calculate the environmental restriction factors and obtain the environmental correction data:

[0139] Based on the preliminary scoring data, competition correction data, resource correction data and environment correction data, the comprehensive fitness score of the candidate area is calculated to obtain the comprehensive fitness score data.

[0140] In an embodiment of the present invention, in urban planning, reasonable site optimization is an important link to improve the scientific layout of urban functional areas. Site optimization based on multidimensional data can not only improve land use efficiency, but also promote the rational distribution of various urban resources, so that the development of each region is more in line with the overall urban planning needs. Through a detailed analysis of the target planning area and calculating the comprehensive fitness score of each candidate area based on the decision-making influencing factor weight matrix, it can provide urban decision makers with an intuitive and scientific site selection basis to ensure that the final selected area has the best adaptability.

[0141] First, based on the decision-making influencing factor weight matrix, the data of the target planning area is extracted to construct a comprehensive regional element data set. This data set contains various urban element information in the target planning area, such as population density, traffic flow, commercial facility distribution, public resource accessibility, etc. The extraction of these data enables the site optimization analysis to be based on a complete data foundation, ensuring the accuracy of subsequent calculations.

[0142] Evaluating regional element data and calculating the basic fitness score of each candidate area is an important step in site optimization. In this process, the basic adaptability of each candidate area can be calculated based on the weight of each urban element. For example, an area with high population density and high commercial facility density is usually more suitable for commercial use, while an area with low population density and high green space coverage may be more suitable as an ecological protection area. By calculating the basic fitness score, candidate areas that meet planning needs can be preliminarily screened out, thus providing a basis for subsequent optimization calculations.

[0143] In order to further improve the accuracy of site selection optimization, it is necessary to analyze the competitive relationship between candidate areas and calculate the competitive impact factor. There may be a competitive relationship between different areas of a city. For example, two adjacent commercial areas may compete for the same flow of people and market share. If there are already multiple similar facilities around an area, the competitive pressure in the area is greater, and its fitness score may be reduced. By calculating the competitive impact factor, it is possible to identify areas that have advantages or disadvantages in market competition, thereby avoiding planning and construction in over-competitive areas.

[0144] In addition to competitive relationships, resource accessibility is also an important factor affecting site optimization. Urban planning needs to ensure the rational distribution of key resources to improve the overall accessibility of the region. Therefore, it is necessary to calculate the accessibility of key resources in the alternative areas and obtain resource correction data. For example, in the process of shopping mall site selection, the accessibility of subway stations, bus hubs, and main roads is an important consideration. If a candidate area is far away from a major transportation hub, its resource accessibility may be low, which will affect its comprehensive fitness score. By calculating resource accessibility, it can be ensured that site optimization fully considers transportation and infrastructure factors and improves the rationality of site selection.

[0145] In addition, urban planning also needs to fully consider the constraints of environmental factors on the suitability of candidate areas. Different urban areas may be subject to different types of environmental constraints, such as noise pollution, air quality, flood risk, etc. If a candidate area is located in an area with severe air pollution or in an area susceptible to natural disasters, its fitness score may be reduced. By analyzing the environmental impacts of each candidate area, it can be ensured that the site selection plan meets the requirements of sustainable development, thereby avoiding adverse effects caused by environmental problems.

[0146] Finally, by comprehensively calculating the basic fitness score, competition correction data, resource correction data, and environmental correction data, the comprehensive fitness score of the candidate areas can be obtained, and the candidate areas can be ranked based on the scoring results. The area with the highest score will be used as the most optimal site selection area to provide the final decision basis for urban planning. This method can ensure the scientificity and rationality of site selection optimization, make urban planning decisions more intelligent and data-based, and improve the utilization efficiency of land resources in practical applications, while optimizing the urban functional layout and improving the overall urban operation efficiency.

[0147] In a preferred embodiment of the present invention, the calculation formula of the comprehensive fitness score is: , For alternative areas The comprehensive fitness score of For alternative areas The basic fitness score of For alternative areas Competitive Area The competitive influence factors between For competitive areas The weight coefficient satisfies , Resource Center The weight coefficient satisfies , Alternative regional center location Go to Resource Center The Euclidean distance of Environmental factors The weight coefficient satisfies , Environmental factors In the data sample Alternative areas The impact values ​​of, such as PM2.5 concentration, noise level, etc. is the number of competitive impact factors, is the number of resource centers, is the number of environmental factors, is the number of data samples; , For urban elements The weight coefficient of For alternative areas Inner city elements The value of is the number of urban elements; , For competitive areas In the data sample Location and alternative areas The intensity of competition can be expressed as merchant density, market share, etc. For competitive areas In the alternative area The average competition intensity of all data samples in .

[0148] In the embodiment of the present invention, the scoring formula evaluates the candidate regions from four dimensions: foundation, competition, resources, and environment. The fitness of . Basic score is the linear weighted sum of urban elements; the competition term The variance is used to measure the intensity of inter-regional competition; the resource term reflects the accessibility of resources by the inverse of the distance; the environmental term quantifies negative factors such as pollution by the mean. The weight coefficient satisfies normalization to ensure the flexibility of the model. This formula can support decision-making scenarios such as urban site selection and functional zoning, and balance the interests of multiple parties.

[0149] in, It is the basis of comprehensive scoring and directly evaluates the city elements. Perform weighted summation. Weight It reflects the importance of various factors, such as transportation convenience, population density, etc. Its logic is simple and intuitive, which facilitates quick calculation.

[0150] in, Computing competitive regions by variance For alternative areas The larger the variance, the more intense the fluctuation of competition intensity and the higher the uncertainty between regions. ,The model can dynamically adjust the impact of competition on the ,comprehensive score, and is suitable for risk assessment in business site ,selection or market analysis.

[0151] The competitive area refers to an area with similar functions or market competition to the candidate area. They may be inside or outside the target planning area, but they will affect the market performance of the candidate area. For example, the competitive area can be an existing shopping mall, office building, commercial street, office area, etc., which may compete with the candidate area for the same target customers.

[0152] In a preferred embodiment of the present invention, the candidate areas are sorted according to the comprehensive fitness scores, the candidate area with the highest comprehensive fitness score is selected as the target area, and a visual urban planning decision report is generated, including:

[0153] According to the comprehensive fitness score data, the candidate area with the highest score is extracted to obtain the target area data;

[0154] Perform feature analysis on the target area data, extract key urban element information, and obtain regional feature data;

[0155] According to the regional characteristic data, analyze the advantages and disadvantages of the target area in different urban element dimensions to obtain regional evaluation data;

[0156] Generate visual planning decision data based on regional assessment data and combined with the urban element association matrix;

[0157] Visualize the planning decision data and output it to the urban planning management system.

[0158] In an embodiment of the present invention, in the process of urban planning decision-making, the calculation of the comprehensive fitness score provides a scientific quantitative basis for site optimization. However, simply calculating the fitness score is not enough to be used directly for decision-making, and the scoring results need to be further analyzed to clarify the specific advantages and disadvantages of the candidate areas, so as to make a reasonable final site selection decision. By sorting the comprehensive fitness scores of each candidate area, the suitability of different areas can be intuitively compared to ensure that the best area is finally selected as the target area. In addition, in order to improve the transparency and interpretability of planning decisions, it is necessary to generate a visual urban planning decision report so that planners can more intuitively understand the basis and results of site optimization.

[0159] Based on the comprehensive fitness score data, extracting the candidate areas with the highest scores can ensure that the final site selection plan meets the optimal result of the comprehensive evaluation of multi-dimensional data. In the calculation process of the comprehensive fitness score, multiple urban elements and their interactions have been considered, such as population density, distribution of commercial facilities, traffic flow, resource accessibility, environmental impact, etc. Therefore, the candidate area with the highest score usually means that it has relative advantages in the evaluation dimensions of multiple key elements. This process effectively avoids the uncertainty of subjective decision-making and makes site optimization more scientific and data-driven. In the specific operation process, all candidate areas can be sorted according to the fitness score, and the area with the highest fitness score can be selected as the final target area. This method can ensure the rationality of site optimization and improve the accuracy of urban planning.

[0160] By analyzing the characteristics of the target area data and extracting key urban element information, the accuracy of site selection optimization can be further improved. In the selected target area, each urban element may have different distribution characteristics. For example, a certain area may have a high population density but a low density of commercial facilities, while another area may have the opposite characteristics. Therefore, after the target area is finally determined, it is necessary to further analyze the distribution of urban elements in the area to evaluate its future development potential. Through data analysis, the key factors that affect the comprehensive fitness score of the target area can be identified, and reasonable planning schemes can be formulated based on these factors. For example, in the process of commercial site selection, if the traffic flow in the target area is high but the parking lot capacity is small, you can consider adding parking facilities to optimize the commercial layout.

[0161] According to the regional characteristic data, analyzing the advantages and disadvantages of the target area in different dimensions of urban elements can make the planning scheme more targeted. Different regions may show different characteristics in different dimensions of urban elements. For example, a certain area may have high commercial value, but may have deficiencies in infrastructure construction. By quantitatively analyzing the advantages and disadvantages of the target area, more accurate information can be provided to urban planners so that corresponding optimization measures can be taken. For example, if the fitness score of the target area is mainly affected by resource accessibility, then the planning scheme can focus on improving the transportation infrastructure of the area to enhance its overall adaptability. On the contrary, if the comprehensive fitness score of the target area is high, but there are certain risks in environmental factors, corresponding ecological optimization strategies can be adopted, such as increasing green space coverage or reducing the entry of high-polluting industries, thereby enhancing the sustainable development capacity of the region.

[0162] Combined with the urban element association matrix, visual planning decision data is generated to make the planning results more intuitive and operational. The urban element association matrix provides the interactive influence relationship between different urban elements, allowing planners to have a deeper understanding of the comprehensive impact of each element on the target area. For example, if the population density of the target area is high and the commercial facilities are sparsely distributed, the urban element association matrix may show that the commercial development potential of the area is high. Through this analysis, planners can give priority to increasing the layout of commercial facilities in the area in future urban development strategies to meet the needs of population growth. In addition, the visualized planning decision data can intuitively display the comprehensive fitness score composition of the target area, the results of the urban element correlation analysis, and the site selection optimization calculation process, so that planners can more clearly understand the impact of different factors on the final decision.

[0163] Visualize the planning decision data and output it to the urban planning management system so that the decision results can be efficiently applied in the urban management and planning system. In the modern urban planning process, data visualization is one of the key technologies to improve planning efficiency and accuracy. By converting urban planning decision data into intuitive visual reports, planners can understand complex data structures more quickly and make more accurate decisions. Visualization can be done in a variety of ways, such as map heat maps, trend analysis charts, 3D city modeling, etc., to show the different characteristics of the target area. For example, the spatial distribution of population density can be shown through heat maps, or the possible impact of future planning schemes can be shown through 3D modeling. In addition, these data can be integrated into the urban planning management system as an important reference for future urban development planning, thereby supporting longer-term urban planning decisions.

[0164] In summary, by sorting the comprehensive fitness scores and extracting the target areas, we can ensure that the final site selection decision conforms to the optimal solution of the comprehensive evaluation of multidimensional data. Combining the analysis of urban element characteristics and the visualization of decision data, we can improve the transparency and accuracy of site selection optimization and make the planning scheme more targeted. At the same time, through the integration of urban planning management systems, we can improve the long-term availability of data, make the decision-making system of urban planning more intelligent and data-based, and thus promote the sustainable development of cities.

[0165] An embodiment of the present invention further provides a visual intelligent big data urban planning decision support management system, the system comprising:

[0166] The data collection and processing module is used to obtain multidimensional data related to urban planning, including population density data, commercial facility distribution data, traffic flow data, parking lot capacity data, and public transportation accessibility data; pre-process the multidimensional data, including format standardization, missing value filling, and data deduplication, to obtain a structured data set;

[0167] The urban element association module is used to establish an association analysis model between urban elements based on the structured data set, and calculate the interaction factors between different urban element data to form an urban element association matrix;

[0168] The urban element analysis module is used to extract features from the urban element association matrix, screen out urban element combinations, and use causal inference methods to calculate the weight values ​​of different urban element combinations to obtain the decision-making influencing factor weight matrix;

[0169] The urban element analysis module is used to optimize the site selection of the target planning area according to the decision-making influencing factor weight matrix and calculate the comprehensive fitness score of each candidate area;

[0170] The decision report generation module is used to sort the candidate areas according to the comprehensive fitness score, select the candidate area with the highest comprehensive fitness score as the target area, and generate a visual urban planning decision report, including the geographical location of the target area, the composition of the comprehensive fitness score, the results of the urban element correlation analysis, and the site selection optimization calculation process.

[0171] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0172] The embodiment of the present invention further provides a computing device, including: a processor, a memory storing a computer program, and when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0173] The embodiment of the present invention further provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the above method. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0174] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A visual intelligent big data urban planning decision support management method, characterized in that: The method comprises: Obtain multidimensional data related to urban planning, including population density data, commercial facility distribution data, traffic flow data, parking capacity data, and public transportation accessibility data; preprocess the multidimensional data, including format standardization, missing value filling, and data deduplication, to obtain a structured data set; Based on the structured data set, a correlation analysis model between urban elements is established, and the interaction factors between different urban element data are calculated through it to form an urban element correlation matrix; Extract features from the urban factor association matrix, screen out urban factor combinations, and use causal inference methods to calculate the weight values ​​of different urban factor combinations to obtain the decision-making influencing factor weight matrix; According to the decision-making influencing factor weight matrix, the site selection optimization calculation is performed on the target planning area, and the comprehensive fitness score of each candidate area is calculated; According to the comprehensive fitness score, the candidate areas are ranked, and the candidate area with the highest comprehensive fitness score is selected as the target area. A visual urban planning decision report is generated, including the geographical location of the target area, the composition of the comprehensive fitness score, the results of the urban element correlation analysis, and the site selection optimization calculation process.

2. According to claim 1, a visualized intelligent big data urban planning decision support management method is characterized in that: According to the structured data set, a correlation analysis model between urban elements is established, and the interaction factors between different urban element data are calculated through the model to form an urban element correlation matrix, including: According to the structured data set, extract the urban element data to obtain the element basic data; Analyze the data characteristics of the basic data of the elements, calculate the distribution patterns of each city element in different regions, and obtain the element characteristic data; According to the element characteristic data, the correlation relationship between urban elements is calculated to obtain element correlation data; According to the factor correlation data, the interaction factors between different factors are calculated to form the factor interaction data; ， For urban elements With urban elements The interaction factors between For urban elements in state The weight coefficient at , is the number of samples, is the number of spatial locations, is the time step, For urban elements With urban elements The weighted mutual information entropy between is the spatial correlation coefficient, is the time correlation coefficient, , is the adjustment coefficient, satisfying ;in, , For urban elements With urban elements In Status The joint probability at , Urban elements and urban elements In Status The independent probability of , and Urban elements and urban elements In spatial position The value at and Urban elements and urban elements The mean value at all spatial locations; , and Urban elements and urban elements In time The value at and Urban elements With urban elements Mean across all time points; Based on the element interaction data, the urban element association matrix is ​​constructed.

3. According to claim 2, a visual intelligent big data urban planning decision support management method is characterized in that: The feature extraction of the city element association matrix is ​​performed to screen out the city element combinations, and the causal inference method is used to calculate the weight values ​​of different city element combinations to obtain the decision-making influencing factor weight matrix, including: Perform data screening on the urban element correlation matrix, remove low-correlation urban elements, and obtain screening element data; Conduct causal inference analysis on the screening factor data, calculate the causal relationship between the city factors, and obtain causal analysis data; According to the causal analysis data, the impact weights of different city element combinations are calculated to obtain the impact weight data; Based on the impact weight data, a decision-making impact factor weight matrix is ​​constructed.

4. According to claim 3, a visual intelligent big data urban planning decision support management method is characterized in that: The calculation formula for the impact weight of the urban element combination is: ， is the impact weight of the combination of urban elements, For urban elements In Status When The probability of occurrence, satisfying =1, For urban elements In Status When The expected value of Pick or , , For urban elements different states, For urban elements The weight coefficient satisfies 0.

5. According to claim 4, a visualized intelligent big data urban planning decision support management method is characterized in that: The method of performing site selection optimization calculation on the target planning area according to the decision influencing factor weight matrix and calculating the comprehensive fitness score of each candidate area includes: According to the decision-making influencing factor weight matrix, the data of the target planning area is extracted to obtain the regional element data; Evaluate the regional factor data, calculate the basic fitness score of each candidate region, and obtain preliminary scoring data; Based on the preliminary scoring data, analyze the competition relationship between candidate regions, calculate the competition impact factor, and obtain the competition correction data; Based on the accessibility of key resources in the target planning area, the resource accessibility of each candidate area is calculated to obtain resource correction data; Based on the environmental impacts on the candidate areas within the target planning area, the degree of restriction of environmental factors on the suitability of the candidate areas is analyzed to obtain environmental correction data: Based on the preliminary scoring data, competition correction data, resource correction data and environment correction data, the comprehensive fitness score of the candidate area is calculated to obtain the comprehensive fitness score data.

6. According to claim 5, a visualized intelligent big data urban planning decision support management method is characterized in that: The calculation formula of the comprehensive fitness score is: ， For alternative areas The comprehensive fitness score of For alternative areas The basic fitness score of For alternative areas Competitive Area The competitive influence factors between For competitive areas The weight coefficient satisfies , Resource Center The weight coefficient satisfies , Alternative regional center location Go to Resource Center The Euclidean distance of Environmental factors The weight coefficient satisfies , Environmental factors In the data sample Alternative areas The impact value of is the number of competitive impact factors, is the number of resource centers, is the number of environmental factors, is the number of data samples.

7. The method for visual intelligent big data urban planning decision support management according to claim 6 is characterized in that: The candidate areas are sorted according to the comprehensive fitness scores, the candidate area with the highest comprehensive fitness score is selected as the target area, and a visual urban planning decision report is generated, including: According to the comprehensive fitness score data, the candidate area with the highest score is extracted to obtain the target area data; Perform feature analysis on the target area data, extract key urban element information, and obtain regional feature data; According to the regional characteristic data, analyze the advantages and disadvantages of the target area in different urban element dimensions to obtain regional evaluation data; Generate visual planning decision data based on regional assessment data and combined with the urban element association matrix; Visualize the planning decision data and output it to the urban planning management system.

8. A visual intelligent big data urban planning decision support management system, characterized in that: Applied to the method according to any one of claims 1 to 7, the system comprises: The data collection and processing module is used to obtain multidimensional data related to urban planning, including population density data, commercial facility distribution data, traffic flow data, parking lot capacity data, and public transportation accessibility data; pre-process the multidimensional data, including format standardization, missing value filling, and data deduplication, to obtain a structured data set; The urban element association module is used to establish an association analysis model between urban elements based on the structured data set, and calculate the interaction factors between different urban element data to form an urban element association matrix; The urban element analysis module is used to extract features from the urban element association matrix, screen out urban element combinations, and use causal inference methods to calculate the weight values ​​of different urban element combinations to obtain the decision-making influencing factor weight matrix; The urban element analysis module is used to optimize the site selection of the target planning area according to the decision-making influencing factor weight matrix and calculate the comprehensive fitness score of each candidate area; The decision report generation module is used to sort the candidate areas according to the comprehensive fitness score, select the candidate area with the highest comprehensive fitness score as the target area, and generate a visual urban planning decision report, including the geographical location of the target area, the composition of the comprehensive fitness score, the results of the urban element correlation analysis, and the site selection optimization calculation process.

9. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images