Binjiang space vitality measurement and vitality influence factor analysis method and system

Abstract

The application provides a riverside space vitality measurement and vitality influence factor analysis method and system, constructs a macro (city energy level / function positioning), medium (district level) and micro (site activity) three-level vitality measurement system, the macro level is connected with the city development stage such as land utilization and economic data, the medium and micro level is connected with space use dynamics such as heat data and activity annotation, and the problem of insufficient adaptability of traditional research macro region is solved; the application forms a closed-loop technical path of "collection-treatment-analysis-diagnosis-optimization", solves the problem of insufficient adaptability of riverside city space vitality measurement macro region, considers the influence of city development, riverside space flood control property, riverside space design and operation management on riverside space vitality, and provides a theoretical basis for optimization and promotion of riverside space vitality.

Description

Technical Field

[0001] This invention belongs to the field of water conservancy engineering technology, specifically relating to a method and system for measuring the vitality of riverside spaces and analyzing the factors influencing vitality. Background Technology

[0002] Riverside spaces are a crucial component of the comprehensive protection and management of rivers. Evaluating the vitality of riverside spaces and identifying key factors influencing their vitality are fundamental to optimizing them. However, traditional research on identifying factors influencing the vitality of riverside spaces has certain limitations: First, insufficient macro-regional adaptability. Existing studies often focus on micro-level spatial design parameters such as green space ratio and facility density, failing to establish multi-scale evaluation models that link with urban capacity, functional positioning, and development direction. This leads to a disconnect between vitality evaluation indicators and urban development stages, potentially causing small and medium-sized cities to blindly apply the riverside vitality thresholds of megacities, resulting in over-development or resource misallocation. Second, neglecting the flood control characteristics of riverside spaces. Existing vitality influencing factors do not fully consider the flood control attributes of riverside spaces, applying general public space research methods to riverside spaces, making the research results not entirely applicable to improving riverside spaces. Third, falling into a static research paradigm dominated by spatial design. Existing vitality influencing factor systems and improvement strategies overemphasize purely spatial design, neglecting the important role of planning, operation, and management in enhancing the vitality of riverside spaces. Summary of the Invention

[0003] To address the problems mentioned in the background section regarding the insufficient macro-regional adaptability of traditional research on the identification of factors influencing the vitality of riverside spaces, neglect of the flood control characteristics of riverside spaces, and being trapped in a static research paradigm dominated by spatial design, this invention provides a method and system for measuring the vitality of riverside spaces and analyzing the factors influencing their vitality.

[0004] The method of the present invention includes the following steps:

[0005] Collect data including urban riverside spatial patterns, environmental quality, and cultural and economic aspects to construct a macro-level riverside spatial vitality assessment database;

[0006] We will acquire data including Baidu heatmap data, spatial annotations of activity occurrences within the Binjiang space, the number of people participating in activities at different times and locations, and the specific types of activities, and construct a micro-vibration database of the Binjiang space.

[0007] Collect data including point data, land use data, building data, road traffic data and remote sensing data to construct a database of factors influencing the vitality of riverside space at the micro and meso levels;

[0008] The raw data of the macro-level riverside space vitality assessment database are preprocessed by dimensionless and translational methods to obtain standardized index values ​​for evaluating the construction level of urban riverside space.

[0009] Data preprocessing was performed on the micro-vitality characterization database in the riverside space. Through spatial connection, spatial identification and data statistics, the vitality distribution of each research grid with a scale similar to that of the riverside block was calculated at different time nodes and spatial locations on weekdays and weekends.

[0010] The database of factors influencing the vitality of riverside space at the micro and meso levels was preprocessed using ArcGIS nearest neighbor analysis tools to obtain standard values ​​of relevant parameters for each riverside space unit, including the minimum distance from each riverside space unit to the regional core point, the minimum distance from each riverside space unit to the riverside space, the population density within each riverside space unit, and the density of different functional facilities.

[0011] Based on the macro-level riverside space vitality assessment database after data preprocessing, the AHP-entropy weight method is used to determine the combined weights of standardized index values ​​for evaluating the construction level of urban riverside space. The TOPSIS model is used to assess the threshold closeness of urban vitality level, and the macro-level vitality of riverside space is measured based on the threshold closeness of urban vitality level.

[0012] Based on the vitality distribution of various research grids with a similar scale to the riverside block at different time points and spatial locations on weekdays and weekends, the vitality of the riverside space at the meso-micro level is measured from two aspects: vitality density characteristics and vitality stability characteristics.

[0013] Based on the preprocessed database of micro- and meso-level factors influencing the vitality of the riverside space, this study uses spatial autocorrelation analysis, constructs a multiple linear regression model, and removes explanatory variables with collinearity to analyze the factors influencing the vitality of the riverside space at the meso-level.

[0014] Based on the macro-level riverside space vitality assessment database, the micro-level riverside space vitality characterization database, and the meso-micro-level riverside space vitality influencing factor database after data preprocessing, factors significantly related to spatial vitality in various activity types were initially screened out through correlation coefficients. Multiple linear regression analysis was then performed on the factors significantly related to spatial vitality in various activity types and the spatial vitality intensity of that activity type to analyze the vitality influencing factors at the micro level of riverside space.

[0015] Furthermore, the method for measuring the macro-level vitality of the riverside space is as follows:

[0016] First, the combined weights of standardized index values ​​for evaluating the construction level of urban riverside space are determined using the AHP-entropy weight method.

[0017] The calculation method for the index weights in the entropy weight method is as follows:

[0018] If the sample matrix is ​​constructed, A city, The evaluation indicators can be used to construct the original matrix as follows:

[0019] ,

[0020] in, Indicates the first The first city The dimensionless values ​​of the indicators;

[0021] Calculate the weight of each indicator in the evaluation indicators:

[0022] ,

[0023] in, Indicates the first The first city The proportion of each indicator;

[0024] Calculate information entropy:

[0025] ,

[0026] in, , It is the natural logarithm. ;

[0027] Calculate information redundancy:

[0028] ,

[0029] in, Indicates the first Information redundancy of the indicators;

[0030] Finally, calculate the indicator weights:

[0031] ,

[0032] in, Indicates the first The weight of each indicator;

[0033] The calculation method for the weights in the analytic hierarchy process is as follows:

[0034] Construct a consistency matrix to compare each evaluation indicator pairwise;

[0035] Use CR values ​​for consistency testing:

[0036] ,

[0037] ,

[0038] If the CR value is less than 0.1, the consistency test is passed; otherwise, the consistency test is not passed. The consistency matrix is ​​reconstructed and the calculation is performed again.

[0039] Next, the weights obtained from the entropy weight method and the analytic hierarchy process are substituted into the matrix method for calculation, ultimately yielding the combined weights of the comprehensive evaluation index of the vitality level of the riverside space:

[0040] ,

[0041] In the formula, W j For the combined weights; α j β represents the weights calculated by the analytic hierarchy process (AHP); j This represents the weights calculated using the entropy weighting method;

[0042] Finally, the TOPSIS model is used for comprehensive evaluation, and a standardized matrix is ​​constructed:

[0043] ，

[0044] Calculate the positive ideal solution for each index. With negative ideal solution :

[0045] Positive Ideal Solution Evaluation indicators The maximum value among all evaluation objects, i.e.

[0046] ,

[0047] Negative ideal solution Evaluation indicators The minimum value among all evaluation objects, i.e.

[0048] ,

[0049] The Euclidean distance formula is used to calculate the Euclidean distance of the positive ideal solution for each scheme. Euclidean distance to negative ideal solution :

[0050] ,

[0051] ,

[0052] Calculate the degree of closeness between the evaluation object and the ideal solution, i.e., the degree of closeness to the urban vitality level threshold:

[0053] ,

[0054] in, Let Euclidean distance represent the positive ideal solution. Denotes the Euclidean distance of the negative ideal solution; , The larger the value, the higher the macro-level vitality of the riverside space being evaluated; conversely, the smaller the value, the lower the level.

[0055] Furthermore, the vitality density characteristic refers to the quantitative change of population activity in a unit space at a certain moment or over a period of time, and is represented by instantaneous vitality density and cumulative vitality density, respectively.

[0056] The instantaneous activity density is a measure of the population density in a riverside spatial unit at a certain moment. It is expressed as the ratio of the total population at that moment to the area of ​​the unit space, and the formula is:

[0057] ,

[0058] ,

[0059] in, For the first Heavenly The number of people per hour For the area of ​​the research unit, For the first Heavenly hourly crowd density Instantaneous vitality density;

[0060] The accumulated vitality density is a measure of population density in a riverside spatial unit within a certain time period, and the formula is:

[0061] ,

[0062] ,

[0063] in, For the first Heavenly The number of people per hour The area of ​​the study unit (unit: ), For the first Population density during the statistical period of the day, To accumulate vitality density; m is the total number of hours in the statistical period;

[0064] The vitality stability refers to the dynamic changes of population activity in a unit space over a period of time, and is represented by instantaneous vitality stability and cumulative vitality stability, respectively.

[0065] The instantaneous vitality stability is a measure of the fluctuation in population size within a riverside spatial unit at a given moment. It is represented by an inverse index of the rate of change in vitality density within the riverside spatial unit at a given moment, and the formula is as follows:

[0066] ,

[0067] ,

[0068] in, For the first Heavenly hourly rate of change in vitality density For the first Heavenly Instantaneous vitality stability within hours; the higher the instantaneous vitality stability, the more stable the vitality, and vice versa.

[0069] The accumulated vitality stability is a measure of the fluctuation in population size within a riverside spatial unit over a certain period. It is expressed as an inverse index of the standard deviation of vitality density in the riverside spatial unit over a certain period, and the formula is:

[0070] ,

[0071] ,

[0072] In the formula, For the first Standard deviation of vitality density For the first The accumulated vitality stability is measured over time; the higher the accumulated vitality stability, the more stable the vitality, and vice versa.

[0073] Furthermore, the analysis process of the influencing factors of vitality at the meso-level of the riverside space includes:

[0074] First, spatial autocorrelation analysis is performed. The spatial correlation of the mean vitality density at different times on weekdays and rest days is initially calculated using the global Moran's I index. The formula is as follows:

[0075] ,

[0076] in, Represents the global Moran's I exponent; This refers to the number of research units; and Representing research units and research unit The vitality density value, The mean vitality density of the study unit at each time point; Represents the spatial weight matrix;

[0077] The global Moran's I index ranges from -1 to 1. A positive global Moran's I index indicates that the vitality density values ​​of the research units exhibit a spatial positive correlation, and units with similar vitality density values ​​show a clustering trend. The closer the value is to 1, the stronger the spatial clustering. A negative global Moran's I index indicates that the vitality density values ​​of the research units exhibit a spatial negative correlation, and units with similar vitality density values ​​show a discrete trend. The closer the value is to -1, the stronger the spatial discreteness. A zero global Moran's I index indicates that there is no spatial correlation between the vitality density values ​​of the research units, and they are randomly distributed.

[0078] Then, a multiple linear regression model is constructed, and the collinearity of the index values ​​of potential influencing factors is tested based on the variance inflation factor to eliminate potential influencing factors with strong collinearity.

[0079] A spatiotemporal weighted regression model was used, employing a Gaussian distance function to establish the spatiotemporal weight function. This model explored the correlation between explanatory and explained variables, representing the degree of influence of each explanatory variable on the vitality of the riverside space on weekdays and weekends at the meso-level. The calculation formula for the spatiotemporal weighted regression model is as follows:

[0080] ,

[0081] In the formula, For the first The spatiotemporal three-dimensional coordinates of each sample point The independent variable is the explanatory variable. The dependent variable is the same as the explained variable. The number of independent variables. It is the first The first sample point The regression coefficients of the independent variables, It is the first Random error of each sample point For the intercept term;

[0082] The least squares method is typically used for estimation, and the estimated value is calculated using the following formula:

[0083] ,

[0084] In the formula, For sample points The spatiotemporal weight matrix, whose value is diagonal elements For sample points The weights of the spatiotemporal weight function at the observation point.

[0085] The Gaussian distance function is used to establish the spatiotemporal weighting function, as shown in the following formula:

[0086] ,

[0087] In the formula, For the first The sample point and the first The spatiotemporal distance between sample points; For bandwidth; define samples and Spatial distance between For time distance Spatial distance The combination function of is given by the following formula:

[0088] ,

[0089] In the formula, and It is a ratio factor that balances time and spatial distance; and Representing sample points respectively and Spatial location coordinates; and For sample points and The sum of time observations; weights are calculated using a Gaussian function. for:

[0090]

[0091] In the formula, Indicates spatiotemporal bandwidth; Indicates spatial bandwidth. , Indicates time bandwidth. ;

[0092] The cross-confirmation method is selected as the method for determining bandwidth, and the formula is as follows:

[0093] ,

[0094] In the formula, It is the dependent variable In the Observations at each sample point; This is the fitted value; the optimal bandwidth is The corresponding minimum value.

[0095] Furthermore, the analysis process of the influencing factors of vitality at the micro level of the riverside space includes:

[0096] Pearson correlation coefficients were selected to preliminarily identify factors that significantly influence space activity, and factors significantly correlated with space activity across various activity types were preliminarily screened, providing a basis for further multiple linear regression analysis. The formula is as follows:

[0097] ,

[0098] in, represents the Pearson correlation coefficient; n is the sample size, and x and y are the values ​​of the independent and dependent variables, respectively.

[0099] Factors significantly related to spatial activity were initially screened using the Pearson correlation coefficient. The Pearson correlation coefficient value ranged from -1 to 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no correlation.

[0100] Multiple linear regression models were used to analyze the linear relationship between factors significantly related to spatial vitality and the spatial vitality intensity of various activity types. At the micro level, the quantitative data results of vitality intensity and vitality influencing factors of riverside public spaces of the leisure, cultural tourism, and public activity types were used for pairwise correlation analysis, as shown in the following formula:

[0101] ,

[0102] in, It is the dependent variable. , ... As the independent variable, It is the intercept term. , ... These are the regression coefficients of each independent variable. It is the random error term, representing the portion that cannot be explained by the independent variable.

[0103] Based on the above methods, this invention proposes a riverside space vitality measurement and vitality influencing factor analysis system, including a vitality assessment database construction module, a vitality characterization database construction module, a vitality influencing factor database construction module, a data preprocessing module, a macro-level vitality measurement module, a meso-micro-level vitality measurement module, a meso-level vitality influencing factor analysis module, and a micro-level vitality influencing factor analysis module.

[0104] The vitality assessment database construction module is used to collect data including the urban riverside spatial pattern, environmental quality, and human economy to construct a macro-level riverside spatial vitality assessment database.

[0105] The vitality characterization database construction module is used to acquire data including Baidu heat data, spatial annotations of vitality occurrence in the Binjiang space, the number of people and specific activity types at different times and locations, and to construct a micro-vitality characterization database in the Binjiang space.

[0106] The vitality influencing factors database construction module is used to collect data including point data, land use data, building data, road traffic data and remote sensing data to construct a micro-level database of riverside space vitality influencing factors.

[0107] The data preprocessing module is used to perform dimensionless and translational data preprocessing on the raw data of the macro-level riverside space vitality assessment database to obtain standardized index values ​​for evaluating the construction level of urban riverside space; to perform data preprocessing on the micro-level vitality characterization database of riverside space, and to calculate the vitality distribution of each research grid with a similar scale to the riverside block at different time nodes and spatial locations on weekdays and weekends through spatial connectivity, spatial identification and data statistics; and to perform data preprocessing on the database of riverside space vitality influencing factors at the meso-micro level through ArcGIS nearest neighbor analysis tools to obtain the standard values ​​of parameters related to each riverside space unit, including the minimum distance from each riverside space unit to the regional core point, the minimum distance from each riverside space unit to the riverside space, the population density within each riverside space unit, and the density of different functional facilities.

[0108] The macro-level vitality measurement module is used to determine the combined weights of standardized index values ​​for evaluating the construction level of urban riverside space based on the macro-level riverside space vitality assessment database after data preprocessing, using the AHP-entropy weight method, evaluating the threshold closeness of urban vitality level through the TOPSIS model, and measuring the macro-level vitality of riverside space based on the threshold closeness of urban vitality level.

[0109] The aforementioned micro-level vitality measurement module is used to measure the micro-level vitality of the riverside space from two aspects: vitality density characteristics and vitality stability characteristics, based on the vitality distribution of various research grids similar to the scale of the riverside block at different time nodes and spatial locations on weekdays and weekends.

[0110] The meso-level vitality influencing factor analysis module is used to analyze the vitality influencing factors of the riverside space at the meso- and micro-level based on the pre-processed database of meso- and micro-level riverside space vitality influencing factors, using methods including spatial autocorrelation analysis, constructing a multiple linear regression model and removing explanatory variables with collinearity.

[0111] The micro-level vitality influencing factor analysis module is used to pre-screen factors that are significantly related to spatial vitality in various activity types based on the macro-level riverside space vitality assessment database, the micro-level vitality characterization database in riverside space, and the meso-micro-level riverside space vitality influencing factor database after data preprocessing. Then, it performs multiple linear regression analysis on the factors that are significantly related to spatial vitality in various activity types and the spatial vitality intensity of that activity type to analyze the vitality influencing factors at the micro level of riverside space.

[0112] The present invention also proposes an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to realize the above-described method for measuring the vitality of riverside space and analyzing the factors influencing vitality.

[0113] The present invention also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method for measuring the vitality of riverside spaces and analyzing the factors influencing vitality.

[0114] Compared with the prior art, the present invention has the following advantages:

[0115] (1) Multi-scale dynamic analysis: By constructing a three-level vitality measurement system of macro (city level / functional positioning), meso (regional level), and micro (site activities), the macro level is connected to the stage of urban development such as land use and economic data, and the meso and micro levels are connected to the dynamics of space use such as thermal data and activity annotations, which solves the problem of insufficient adaptability of traditional macro-regional research.

[0116] (2) Strong adaptability: The AHP-entropy weight method and TOPSIS model are used to quantify the macro-level vitality of the riverside space. The micro-level vitality of the riverside space is quantified from the two aspects of vitality density characteristics and vitality stability characteristics. Differentiated evaluation standards are provided for cities of different levels, avoiding the blind application of a single evaluation standard by cities of different sizes, and avoiding the resource mismatch caused by small and medium-sized cities blindly applying the threshold of megacities. The evaluation indicators are accurately matched with urban functions.

[0117] (3) Deep integration of flood control characteristics and vitality analysis: Integrate the flood control characteristic parameters of the riverside space, such as the minimum distance from each riverside space unit to the core point of the region and the minimum distance from each riverside space unit to the riverside space, into the database of micro and meso-level influencing factors. This breaks through the limitations of traditional public space research methods and makes the results of vitality measurement and vitality influencing factor analysis more in line with the actual functional needs of the riverside space.

[0118] (4) The analysis process combines static and dynamic data: By using multi-source dynamic data such as Baidu heat data and spatiotemporal activity annotations, combined with spatial autocorrelation and multiple linear regression analysis, the dynamic measurement of the riverside space can be realized. At the same time, operation and management factors such as facility density and population density are included, which makes up for the shortcomings of traditional static analysis.

[0119] (5) High practicality: Based on data-driven approach, it adopts ArcGIS nearest neighbor analysis tool, AHP-entropy weight method, operations research method TOPSIS model, spatial autocorrelation analysis, correlation screening and multiple linear regression analysis to systematically identify key vitality influencing factors at the macro, meso and micro levels, such as the accessibility of regional core points and the density of functional facilities. It establishes a standardized analysis process and forms a closed-loop technical path of "collection-processing-analysis-diagnosis-optimization". It provides reusable analysis tools for measuring the vitality of riverside space and analyzing the influencing factors of vitality, as well as for riverside space planning. It provides quantitative basis for strategies to enhance the vitality of riverside space and is highly practical.

[0120] In summary, this invention addresses the problem of insufficient macro-regional adaptability in measuring the vitality of riverside urban spaces. It comprehensively considers the impact of urban development, the flood control attributes of riverside spaces, riverside space design, and operation and management on the vitality of riverside spaces, providing a theoretical basis for optimizing and enhancing the vitality of riverside spaces. Attached Figure Description

[0121] Figure 1 This is a flowchart of the method of the present invention.

[0122] Figure 2 This is a system architecture diagram of the present invention.

[0123] Figure 3 This is an assessment of the vitality level of the riverside space in a city in the middle reaches of a river at the macro level.

[0124] Figure 4 This is a spatial distribution map of instantaneous vitality density on a weekday.

[0125] Figure 5 This is a spatial distribution map of instantaneous vitality density on a rest day.

[0126] Figure 6 Accumulate a spatial distribution map of vitality density for weekdays / rest days.

[0127] Figure 7 This is a spatial distribution map of instantaneous vitality stability on weekdays.

[0128] Figure 8 This is a spatial distribution map of instantaneous vitality stability on rest days. Detailed Implementation

[0129] To make the technical problems, technical solutions, and beneficial effects to be solved by this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and are not intended to limit the scope of this application.

[0130] Example 1

[0131] Methods for measuring the vitality of riverside spaces and analyzing factors influencing vitality, flowchart as follows: Figure 1 As shown, the specific steps are as follows.

[0132] Collect data including urban riverside spatial patterns, environmental quality, and cultural and economic aspects to construct a macro-level riverside spatial vitality assessment database.

[0133] We will acquire data including Baidu heatmap data, spatial annotations of activity occurrences within the Binjiang space, the number of people participating in activities at different times and locations, and the specific types of activities, and construct a micro-level vitality characterization database for the Binjiang space.

[0134] We will collect data including point data, land use data, building data, road traffic data, and remote sensing data to construct a database of factors influencing the vitality of riverside space at the micro and meso levels.

[0135] The raw data from the macro-level riverside space vitality assessment database undergoes dimensionless and translational data preprocessing to obtain standardized index values ​​for evaluating the urban riverside space construction level. In this data preprocessing, to meet computational requirements, the dimensionless data needs to be shifted backward by a minimum unit to obtain the standardized index values.

[0136] Data preprocessing was performed on the micro-vitality characterization database of the riverside space. Through spatial connection, spatial identification and data statistics, the vitality distribution of each research grid with a scale similar to that of the riverside block was calculated at different time nodes and spatial locations on weekdays and weekends.

[0137] The database of factors influencing the vitality of riverside spaces at the micro and meso levels was preprocessed using ArcGIS nearest neighbor analysis to obtain standard values ​​for relevant parameters of each riverside spatial unit, including the minimum distance from each riverside spatial unit to the regional core point, the minimum distance from each riverside spatial unit to the riverside space, population density within each riverside spatial unit, and density of different functional facilities. Unit conversion may be performed if necessary during this data preprocessing.

[0138] Based on the macro-level riverside space vitality assessment database after data preprocessing, the AHP-entropy weight method was used to determine the combined weights of standardized indicator values ​​for evaluating the construction level of urban riverside spaces. The TOPSIS model was used to assess the threshold proximity of urban vitality levels, and the macro-level vitality of riverside spaces was measured based on this threshold proximity. This aims to clarify the influence of various indicators on the vitality of riverside spaces in the measurement and analysis of influencing factors.

[0139] Specifically, the method for measuring the macro-level vitality of the riverside space is as follows:

[0140] First, the combined weights of standardized index values ​​for evaluating the construction level of urban riverside space are determined using the AHP-entropy weight method.

[0141] The calculation method for the index weights in the entropy weight method is as follows:

[0142] If the sample matrix is ​​constructed, A city, The evaluation indicators can be used to construct the original matrix as follows:

[0143] ,

[0144] in, Indicates the first The first city The dimensionless values ​​of the indicators;

[0145] Calculate the weight of each indicator in the evaluation indicators:

[0146] ,

[0147] in, Indicates the first The first city The proportion of each indicator;

[0148] Calculate information entropy:

[0149] ,

[0150] in, , It is the natural logarithm. ;

[0151] Calculate information redundancy:

[0152] ,

[0153] in, Indicates the first Information redundancy of the indicators;

[0154] Finally, calculate the indicator weights:

[0155] ,

[0156] in, Indicates the first The weight of each indicator;

[0157] The calculation method for the weights in the analytic hierarchy process is as follows:

[0158] Construct a consistency matrix to compare each evaluation indicator pairwise;

[0159] Use CR values ​​for consistency testing:

[0160] ,

[0161] ,

[0162] If the CR value is less than 0.1, the consistency test is passed; otherwise, the consistency test is not passed. The consistency matrix is ​​reconstructed and the calculation is performed again.

[0163] Next, the weights obtained from the entropy weight method and the analytic hierarchy process are substituted into the matrix method for calculation, ultimately yielding the combined weights of the comprehensive evaluation index of the vitality level of the riverside space:

[0164] ,

[0165] In the formula, W j For the combined weights; α j β represents the weights calculated by the analytic hierarchy process (AHP); j This represents the weights calculated using the entropy weighting method;

[0166] Finally, the TOPSIS model is used for comprehensive evaluation, and a standardized matrix is ​​constructed:

[0167] ，

[0168] Calculate the positive ideal solution for each index. With negative ideal solution :

[0169] Positive Ideal Solution Evaluation indicators The maximum value among all evaluation objects, i.e.

[0170] ,

[0171] Negative ideal solution Evaluation indicators The minimum value among all evaluation objects, i.e.

[0172] ,

[0173] The Euclidean distance formula is used to calculate the Euclidean distance of the positive ideal solution for each scheme. Euclidean distance to negative ideal solution :

[0174] ,

[0175] ,

[0176] Calculate the degree of closeness between the evaluation object and the ideal solution, i.e., the degree of closeness to the urban vitality level threshold:

[0177] ,

[0178] in, Let Euclidean distance represent the positive ideal solution. Denotes the Euclidean distance of the negative ideal solution; , The larger the value, the higher the macro-level vitality of the riverside space being evaluated; conversely, the smaller the value, the lower the level.

[0179] Based on the vitality distribution of various research grids similar in scale to the riverside block at different time points and spatial locations on weekdays and weekends, the vitality of the riverside space at the meso-micro level is measured from two aspects: vitality density characteristics and vitality stability characteristics.

[0180] Specifically, vitality density characteristics refer to the quantitative changes in population activity within a unit space at a certain moment or over a period of time, and are represented by instantaneous vitality density and cumulative vitality density, respectively.

[0181] Instantaneous activity density is a measure of the population density in a riverside spatial unit at a certain moment. It is expressed as the ratio of the total population at that moment to the area of ​​the unit space, and the formula is:

[0182] ,

[0183] ,

[0184] in, For the first Heavenly The number of people per hour For the area of ​​the research unit, For the first Heavenly hourly crowd density Instantaneous vitality density;

[0185] The accumulated vitality density is a measure of population density in a riverside spatial unit within a certain time period, and the formula is:

[0186] ,

[0187] ,

[0188] in, For the first Heavenly The number of people per hour The area of ​​the study unit (unit: ), For the first Population density during the statistical period of the day, To accumulate vitality density; m is the total number of hours in the statistical period.

[0189] Vitality stability refers to the dynamic changes in population activity within a unit space over a period of time, and is represented by instantaneous vitality stability and cumulative vitality stability.

[0190] Instantaneous vitality stability is a measure of the fluctuation in population size within a riverside spatial unit at a given moment. It is expressed as an inverse index of the rate of change in vitality density within the riverside spatial unit at that moment, and the formula is:

[0191] ,

[0192] ,

[0193] in, For the first Heavenly hourly rate of change in vitality density For the first Heavenly Instantaneous vitality stability within hours; the higher the instantaneous vitality stability, the more stable the vitality, and vice versa.

[0194] Accumulated vitality stability is a measure of the fluctuation in population size within a riverside spatial unit over a certain period. It is expressed as an inverse indicator of the standard deviation of vitality density in the riverside spatial unit over a certain period, and the formula is:

[0195] ,

[0196] ,

[0197] In the formula, For the first Standard deviation of vitality density For the first The accumulated vitality stability is measured over time; the higher the accumulated vitality stability, the more stable the vitality, and vice versa.

[0198] Based on the preprocessed database of micro- and meso-level factors influencing the vitality of the riverside space, this study analyzes the factors influencing the vitality of the riverside space at the meso-level using spatial autocorrelation analysis, constructing a multiple linear regression model, and removing explanatory variables with collinearity.

[0199] Specifically, the analysis process of the factors influencing the vitality of the riverside space at the meso-level includes:

[0200] First, spatial autocorrelation analysis is performed. The spatial correlation of the mean vitality density at different times on weekdays and rest days is initially calculated using the global Moran's I index. The formula is as follows:

[0201] ,

[0202] in, Represents the global Moran's I exponent; This refers to the number of research units; and Representing research units and research unit The vitality density value, The mean vitality density of the study unit at each time point; Represents the spatial weight matrix;

[0203] The global Moran's I index ranges from -1 to 1. A positive global Moran's I index indicates that the vitality density values ​​of the research units exhibit a spatial positive correlation, and units with similar vitality density values ​​show a clustering trend. The closer the value is to 1, the stronger the spatial clustering. A negative global Moran's I index indicates that the vitality density values ​​of the research units exhibit a spatial negative correlation, and units with similar vitality density values ​​show a discrete trend. The closer the value is to -1, the stronger the spatial discreteness. A zero global Moran's I index indicates that there is no spatial correlation between the vitality density values ​​of the research units, and they are randomly distributed.

[0204] Then, a multiple linear regression model is constructed, and the collinearity of the index values ​​of potential influencing factors is tested based on the variance inflation factor. Potential influencing factors with strong collinearity are eliminated to improve the reliability of the regression coefficients and the explanatory power of the regression model.

[0205] A spatiotemporal weighted regression model was used, employing a Gaussian distance function to establish the spatiotemporal weight function. This model explored the correlation between explanatory and explained variables, representing the degree of influence of each explanatory variable on the vitality of the riverside space on weekdays and weekends at the meso-level. The calculation formula for the spatiotemporal weighted regression model is as follows:

[0206] ,

[0207] In the formula, For the first The spatiotemporal three-dimensional coordinates of each sample point The independent variable is the explanatory variable. The dependent variable is the same as the explained variable. The number of independent variables. It is the first The first sample point The regression coefficients of the independent variables, It is the first Random error of each sample point This is the intercept term.

[0208] The least squares method is typically used for estimation, and the estimated value is calculated using the following formula:

[0209] ,

[0210] In the formula, For sample points The spatiotemporal weight matrix, whose value is diagonal elements For sample points The weights of the spatiotemporal weight function at the observation point.

[0211] The Gaussian distance function is used to establish the spatiotemporal weighting function, as shown in the following formula:

[0212] ,

[0213] In the formula, For the first The sample point and the first The spatiotemporal distance between sample points; For bandwidth; define samples and Spatial distance between For time distance Spatial distance The combination function of is given by the following formula:

[0214] ,

[0215] In the formula, and It is a ratio factor that balances time and spatial distance; and Representing sample points respectively and Spatial location coordinates; and For sample points and The sum of time observations; weights are calculated using a Gaussian function. for:

[0216]

[0217] In the formula, Indicates spatiotemporal bandwidth; Indicates spatial bandwidth. , Indicates time bandwidth. .

[0218] The cross-confirmation method is selected as the method for determining bandwidth, and the formula is as follows:

[0219] ,

[0220] In the formula, It is the dependent variable In the Observations at each sample point; This is the fitted value; the optimal bandwidth is The corresponding minimum value.

[0221] Based on the macro-level riverside space vitality assessment database, the micro-level riverside space vitality characterization database, and the meso-micro-level riverside space vitality influencing factor database after data preprocessing, factors significantly related to spatial vitality in various activity types were initially screened out through correlation coefficients. Multiple linear regression analysis was then performed on the factors significantly related to spatial vitality in various activity types and the spatial vitality intensity of that activity type to analyze the vitality influencing factors at the micro level of riverside space.

[0222] Specifically, the analysis process of the factors influencing the vitality of the riverside space at the micro level includes:

[0223] Pearson correlation coefficients were selected to preliminarily identify factors that significantly influence space activity, and factors significantly correlated with space activity across various activity types were preliminarily screened, providing a basis for further multiple linear regression analysis. The formula is as follows:

[0224] ,

[0225] in, represents the Pearson correlation coefficient; n is the sample size, and x and y are the values ​​of the independent and dependent variables, respectively.

[0226] Factors significantly related to spatial activity were initially screened using the Pearson correlation coefficient. The Pearson correlation coefficient value ranged from -1 to 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no correlation.

[0227] Multiple linear regression models were used to analyze the linear relationship between factors significantly related to spatial vitality and the spatial vitality intensity of various activity types. At the micro level, the quantitative data results of vitality intensity and vitality influencing factors of riverside public spaces of the leisure, cultural tourism, and public activity types were used for pairwise correlation analysis, as shown in the following formula:

[0228] ,

[0229] in, It is the dependent variable. , ... As the independent variable, It is the intercept term. , ... These are the regression coefficients of each independent variable. It is the random error term, representing the portion that cannot be explained by the independent variable.

[0230] Example 2

[0231] The system architecture diagram for measuring the vitality of riverside spaces and analyzing factors influencing vitality is as follows: Figure 6 As shown, it consists of a vitality assessment database construction module, a vitality characterization database construction module, a vitality influencing factor database construction module, a data preprocessing module, a macro-level vitality measurement module, a meso- and micro-level vitality measurement module, a meso-level vitality influencing factor analysis module, and a micro-level vitality influencing factor analysis module.

[0232] The Vitality Assessment Database Construction Module is used to collect data including the urban riverside spatial pattern, environmental quality, and human economy to construct a macro-level riverside spatial vitality assessment database.

[0233] The Vitality Characterization Database Construction Module is used to acquire data including Baidu heat map data, spatial annotations of vitality occurrences within the Binjiang Space, the number of people participating in activities at different times and locations, and the specific types of activities, to construct a micro-vitality characterization database in the Binjiang Space.

[0234] The Vitality Influencing Factors Database Construction Module is used to collect data including point data, land use data, building data, road traffic data, and remote sensing data to construct a micro-level database of riverside spatial vitality influencing factors.

[0235] The data preprocessing module is used to perform dimensionless and translational data preprocessing on the raw data of the macro-level riverside space vitality assessment database to obtain standardized index values ​​for evaluating the construction level of urban riverside space; it preprocesses the micro-level vitality characterization database of riverside space, and calculates the vitality distribution of each research grid at different time nodes and spatial locations on weekdays and weekends through spatial connectivity, spatial identification and data statistics; it preprocesses the database of riverside space vitality influencing factors at the meso-micro level using ArcGIS nearest neighbor analysis tools to obtain the standard values ​​of relevant parameters for each riverside space unit, including the minimum distance from each riverside space unit to the regional core point, the minimum distance from each riverside space unit to the riverside space, the population density within each riverside space unit, and the density of different functional facilities.

[0236] The macro-level vitality measurement module is used to determine the combined weights of standardized indicator values ​​for evaluating the construction level of urban riverside spaces based on the macro-level riverside space vitality assessment database after data preprocessing, using the AHP-entropy weight method. It then assesses the proximity of the city's vitality level threshold using the TOPSIS model and measures the macro-level vitality of the riverside space based on the proximity of the city's vitality level threshold.

[0237] The meso-micro level vitality measurement module is used to measure the meso-micro level vitality of the riverside space from two aspects: vitality density characteristics and vitality stability characteristics, based on the vitality distribution of various research grids similar to the scale of the riverside block at different time nodes and spatial locations on weekdays and weekends.

[0238] The module for analyzing the influencing factors of vitality at the meso-level is used to analyze the influencing factors of vitality at the meso- and micro-level of the riverside space based on the preprocessed database of factors influencing vitality at the meso- and micro-level. It employs methods including spatial autocorrelation analysis, construction of a multiple linear regression model, and elimination of explanatory variables with collinearity to analyze the influencing factors of vitality at the meso-level of the riverside space.

[0239] The micro-level vitality influencing factor analysis module is used to pre-screen factors that are significantly related to spatial vitality in various activity types based on the macro-level riverside space vitality assessment database, the micro-level vitality characterization database in riverside space, and the meso-micro-level riverside space vitality influencing factor database after data preprocessing. Then, it performs multiple linear regression analysis on the factors that are significantly related to spatial vitality in various activity types and the spatial vitality intensity of that activity type to analyze the vitality influencing factors at the micro level of riverside space.

[0240] The specific implementation methods of each module in this system are the same as those described in Example 1, and will not be repeated here.

[0241] Example 3

[0242] An electronic device is characterized in that it comprises: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to realize the riverside space vitality measurement and vitality influencing factor analysis method as described in Embodiment 1 above, and the riverside space vitality measurement and vitality influencing factor analysis system as described in Embodiment 2.

[0243] Example 4

[0244] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for measuring the vitality of riverside space and analyzing its influencing factors as described in Embodiment 1 above, and the system for measuring the vitality of riverside space and analyzing its influencing factors as described in Embodiment 2.

[0245] Example 5

[0246] In this embodiment, A, B, C, D, E, F, G, and H are city codes for the middle reaches of a certain river, while HK, WC, HY, QS, SJJ, BS, and ZJ are codes for areas within city D. POIs refer to point-of-interest (POI) data.

[0247] The constructed database comprises three categories: a macro-level database for assessing the vitality of riverside spaces, a micro-level database for characterizing the vitality of riverside spaces, and a database of factors influencing the vitality of riverside spaces at the micro and meso-level.

[0248] Using eight cities (A, B, C, D, E, F, G, and H) in the middle reaches of a certain river as the data collection targets, nine indicators were obtained through statistical yearbook reviews and relevant planning materials. These indicators included the proportion of residential shoreline in the central urban area, the average depth of residential shoreline in the central urban area, the per capita construction land area in the central urban area, the average distance from the core node of the central urban area to the shoreline, the proportion of days with good air quality, the population density of the central city, the GDP per capita in the central urban area, the proportion of the tertiary industry in the central urban area, and the number of cultural relics protection units in the central urban area. This data was used to construct a macro-level assessment database of the vitality of the riverside space.

[0249] Taking the riverside space of City D as an example, we obtained Baidu heat map data (which records the total number of mobile phone users using Baidu Maps location service every hour, and can accurately reflect the distribution of people's activities), on-site collection of spatial annotations of vitality in the riverside space, the number of people and specific types of activities at different times and locations, and constructed a micro-vitality characterization database in the riverside space.

[0250] We will collect data including point data, land use data, building data, road traffic data, and remote sensing data to construct a database of factors influencing the vitality of riverside space at the micro and meso levels.

[0251] At the meso-level: 16 indicators were quantitatively collected, including location centrality, road network density, public transportation station density, distance to public transportation station, street density, building density, development intensity, functional density, functional mix, waterfront distance, green coverage rate, residential population density, average residential housing price, media check-in index, public service facility density, and commercial service facility density, to construct a meso-level vitality influencing factors database.

[0252] At the micro level, a database of factors influencing the vitality of riverside spaces at the micro level was constructed by quantifying 21 indicators, including diversity of types, shoreline curvature, area, spatial elevation difference, pedestrian accessibility, visual accessibility, transportation convenience, transportation accessibility, functional mixing, facility richness, waterfront accessibility, activity type richness, landscape greening richness, revetment morphology richness, green view rate, flood control facility completeness, warning and guidance signage completeness, hard ground ratio, completeness of rest facility configuration, completeness of public service facility configuration, and richness of historical and cultural elements.

[0253] Based on the method in Example 1, data preprocessing was performed on the macro-level riverside space vitality assessment database, the micro-level riverside space vitality characterization database, and the micro-level riverside space vitality influencing factor database.

[0254] Based on the method in Example 1, the vitality measurement and influencing factors of the riverside space were analyzed, and the specific results are as follows.

[0255] I. Assessment results of the vitality level of riverside spaces in eight cities in the middle reaches of a certain river at the macro level, as follows: Figure 3 As shown, the results indicate that City D is at a Level 1 vitality level, with a proximity ratio of [missing information]. T i Values ​​between 0.7 and 1.0 indicate the highest overall vitality level of the riverside space; A represents a secondary vitality level, indicating a high degree of proximity. T i Values ​​between 0.5 and 0.7 indicate a relatively high overall level of vitality in the riverside space; H, B, G, and C represent three levels of vitality, indicating a high degree of proximity. T i The values ​​are all between 0.3 and 0.5, indicating a generally average overall level of vitality in the riverside space; E and F represent level four vitality, indicating a low degree of proximity. T i The values ​​are all between 0 and 0.3, indicating a low overall level of vitality in the riverside space.

[0256] Second, spatial visualization was performed on the mean activity density at different times on weekdays and rest days, and spatial distribution maps of activity density at different times on weekdays and rest days were drawn respectively. Figure 4 This is a spatial distribution map of instantaneous vitality density on weekdays. Figure 5 This is a spatial distribution map of instantaneous activity density on rest days. Within the measurement time interval, weekdays and rest days exhibited similar spatial distribution characteristics of "dispersion-aggregation-redispersion". At 6:00 AM, the activity density along the river was scattered, without forming obvious activity aggregation points, with areas of higher activity density mainly concentrated in residential clusters. At 8:00 AM, the impact of commuting to work caused the activity density value along the river to exhibit a spatial variation of "large dispersion and small concentration". At 10:00 AM, this characteristic became more significant as the activity of the population increased. By noon, within the study area of ​​the riverside space, the activity of the population formed obvious aggregation centers around the main historical commercial areas, public service centers, and riverside business districts. At 2:00 PM, the aggregation characteristic weakened slightly, then became more significant again between 4:00 PM and 8:00 PM, and the spatial activity aggregation point showed a characteristic of shifting towards the riverside shoreline. After 8:00 PM, as the activity density value decreased, the aggregation characteristic weakened and shifted again towards the riverside blocks, gradually showing a dispersion characteristic after 10:00 PM. Comparing weekdays and weekends, the distribution of activity density in the riverside area is more characterized by "large dispersion and small concentration" on weekends, and there is a spatial lag and stability.

[0257] Third, the sum of vitality density values ​​throughout the entire weekday and rest day period was spatially visualized, and spatial distribution maps of accumulated vitality density on weekdays and rest days were drawn respectively. Figure 6 A spatial distribution map of vitality density was created for weekdays and rest days. Within the measured spatial range, the vitality density of weekdays and rest days exhibits a distribution characteristic of "central clustering and ring-shaped decrease." The core of vitality in the riverside space is concentrated within the area between a certain bridge and a certain second bridge, including the core sections of the HK historical commercial district, WC ancient city area, HY ancient city area, and WC riverside business district on both banks. This section concentrates the city's main historical and cultural facilities, commercial and entertainment facilities, and living service facilities, resulting in a high vitality density value. Downstream on the south bank of this section, areas with high vitality density values ​​include the QS riverside area and the industrial and cultural area transformed from former factory sites. On the north bank, the SJJ riverside area is mostly traditional industrial areas and suburban green spaces, with a lower vitality density value due to sparse population and lagging development. Upstream on the HY and BS riverside areas of this section, the areas with high vitality density values ​​are some distance from the riverside shoreline and are mostly urban residential clusters, with a lower vitality density value in the riverside area. In addition, the vitality density values ​​in the study area also show significant clustering characteristics in areas such as large green parks, cultural relics, bridgeheads across rivers, and large convention and exhibition centers.

[0258] IV. Spatial visualization of the mean vitality stability at different times on weekdays and rest days was performed, and spatial distribution maps of vitality stability at different times on weekdays and rest days were drawn respectively. Figure 7 This is a spatial distribution map of instantaneous activity stability on weekdays. Within the measurement time interval, both weekdays and rest days exhibit a scattered spatial distribution. At 6:00 AM, the riverside area shows areas with significantly higher activity stability values. From 6:00 AM to 8:00 AM, during the commuting period, activity density values ​​fluctuate considerably, with lower activity stability values, particularly noticeable in residential areas. After 8:00 AM, areas of stable activity begin to appear along the riverside, continuing until 4:00 PM, as areas with consistently high activity stability values ​​in people's activity areas expand. After 6:00 PM, with the arrival of the evening rush hour, population activity declines, activity density values ​​fluctuate more, and areas with high activity stability values ​​gradually decrease. Similar to the activity density characteristics, the spatial distribution of activity stability on rest days also exhibits a lag and stability compared to weekdays.

[0259] V. Spatial visualization of vitality stability values ​​throughout the weekday and rest day periods was performed, and spatial distribution maps of accumulated vitality stability were drawn for weekdays and rest days, respectively. Figure 8 This is a spatial distribution map of instantaneous activity stability on rest days. Within the measured spatial range, overall, the activity stability on weekdays and rest days exhibits a distribution characteristic of "low stability in riverside blocks and high stability along the riverbank." In specific areas, the cultural and commercial districts exhibit lower activity stability compared to riverside residential areas. This is because the historical, cultural, and commercial districts of HK, WC, and HY have diverse populations and activities, resulting in greater fluctuations in activity density. In contrast, the riverside residential areas upstream and downstream of the city's core area have a more homogeneous population and fewer activities, leading to less fluctuation in activity density. Downstream of the city's core area, ecological riverside areas, such as HK Phase IV, HK Phase V, and QS Phase II riverside areas on both sides of the ZJ River estuary, show higher activity stability compared to the residential riverside areas of the core area, such as WC riverside and HK Phase I and II riverside areas. This is because ecological riverside areas have fewer people and less fluctuation in activity density compared to riverside areas in the core area. Furthermore, a certain riverside park on the south bank within the core area, primarily serving a flood control function, has a narrow embankment, a steep slope, and sparse green space and facilities within the embankment, resulting in a lower activity density, less fluctuation, and higher stability.

[0260] VI. Spatial autocorrelation analysis was conducted using urban planning vector files, Open Street Map, map.baidu.com, wuhan.anjuke.com, etc., to obtain the following data: the reciprocal of the shortest distance from the riverside spatial unit to the urban core and nodes; the ratio of road area to riverside spatial unit area; the number of bus stops and subway stations in the riverside spatial unit; the shortest distance from the riverside spatial unit to public transportation stations; the number of road intersections in the riverside spatial unit; the ratio of building footprint area to unit area in the riverside spatial unit; the ratio of total building area to unit area in the riverside spatial unit; and the number of points of interest (POIs) in the riverside spatial unit. Sixteen data points were used to construct a system of influencing factors on the vitality of the riverside space at the meso-level, including the number of points of interest (POIs), the degree of mixing of POIs in the riverside space unit, the distance from the riverside space unit to the nearest riverside shoreline, the coverage area of ​​green vegetation in the riverside space unit, the number of residents in the riverside space unit, the average housing price in the riverside space unit, the number of media check-ins in the riverside space unit, the number of public service facilities in the riverside space unit, and the number of commercial service facilities in the riverside space unit.

[0261] Based on the method in Example 1, the results show that the global Moran's I index of the average vitality density of 1028 grid units in the riverside space of the central urban area of ​​D city at all times from 6:00 to 23:00 on weekdays and weekends is much greater than 0, and the standardized values ​​are all greater than the critical value of the significance level test, thus passing the significance level test. This indicates that the average vitality density at each time point exhibits significant spatial autocorrelation and shows a significant clustering distribution pattern. That is, the average vitality density of the grid unit with a high average vitality density is also high in the surrounding area, and vice versa.

[0262] The collinearity test results showed that the variance inflation factor (VIF) of functional density (FD) was 11.318 (greater than the critical value of 10), indicating high collinearity; the variance inflation factor (VIF) of commercial service facility density (CD) was 8.261 (close to the critical value of 10), indicating moderate collinearity. Further correlation analysis of the explanatory variables revealed that the correlation coefficient between functional density (FD) and commercial service facility density (CD) was 0.933, which may be due to variable redundancy caused by spatial autocorrelation. Therefore, to ensure the stability of the analytical model, the explanatory variable of functional density (FD) was removed, and 15 explanatory variables were retained for further analysis.

[0263] After removing explanatory variables with collinearity, this paper uses 15 explanatory variables: location centrality (LC), road network density (RD), public transport station density (PD), distance to transport stations (DPTS), street density (BD), building density (AD), development intensity (FAR), functional mixing (MU), distance to waterfront (DS), green coverage rate (NDVI), population density (RPD), average house price in the area (HP), media check-in index (WI), public service facility density (SD), and commercial service facility density (CD). The mean activity density on weekdays and weekends is the dependent variable.

[0264] Based on the method of Example 1, the results show:

[0265] In riverside public spaces designed for leisure and recreation, the indicators that show a significant correlation with vitality intensity include eight indicators across three dimensions and five levels. In descending order of correlation strength, they are: completeness of public service facilities > completeness of rest facilities > richness of historical and cultural elements >= richness of activity types > hard ground ratio = green view ratio > transportation accessibility > type diversity, among which green view ratio shows a negative correlation.

[0266] In cultural tourism-oriented riverside public spaces, the indicators that show a significant correlation with vitality intensity include 11 indicators across three dimensions and six levels. In descending order of correlation intensity, they are: functional mixing degree > activity type richness > water accessibility > revetment form richness > type diversity > historical and cultural element richness > facility richness > landscape greening richness > rest facility configuration completeness > visual accessibility > transportation accessibility.

[0267] In public riverside spaces for public activities, 12 indicators showed a significant correlation with vitality intensity. In descending order of correlation intensity, they were: activity type richness > type diversity > completeness of warning and guidance signage > water accessibility > functional mixing > visual accessibility > area > green view rate > transportation accessibility > shoreline curvature > transportation convenience. Among them, green view rate showed a negative correlation.

[0268] Based on the method in Example 1, multiple linear regression analysis was conducted on the factors that were significantly correlated with the vitality intensity of riverside public spaces, as determined by correlation analysis, and the vitality intensity of this type of space. The results show that, to enhance the vitality of riverside public spaces for leisure and recreation, it is necessary to focus on improving functionality, strengthening the configuration of rest facilities and public service facilities, and appropriately enhancing accessibility and the diversity of internal space types. To enhance the vitality of riverside public spaces for cultural tourism, it is necessary to comprehensively consider the functional diversity of the space and strengthen the utilization of historical and cultural elements. To enhance the vitality of riverside public spaces for public activities, it is necessary to focus on spatial design that meets the needs of various activities and setting up appropriate and abundant warning and guidance signs.

[0269] Finally, based on the above analysis, the optimization and improvement path for the riverside space is as follows:

[0270] I. Macro-level Optimization and Improvement Path: Based on the quantitative data of various indicators in the macro-level riverside space vitality assessment database, the weights of each indicator are reasonably determined, and optimization and improvement paths are proposed based on the connotation of the quantitative indicators.

[0271] Taking eight major cities (A, B, C, D, E, F, G, and H) in the middle reaches of a river as an example, the path to optimize and enhance the vitality of the riverside area at the macro level includes building a planning response mechanism that coordinates time and space, using a spatial design method that integrates functions, and improving a digital and intelligent operation and maintenance model with the participation of multiple parties.

[0272] II. Optimization and Improvement Paths at the Meso- and Micro-Levels: Based on the results of correlation analysis of the vitality representation and the quantitative data of vitality influencing factors, the mechanism of influence of each influencing factor on the vitality representation of the riverside space at the meso- and micro-levels is clarified. Among them, the influencing factor indicators with obvious positive and negative correlations are selected, and targeted optimization and improvement paths are proposed.

[0273] Taking the quantitative analysis model of the vitality of public activity-oriented riverside public spaces in City D at the micro level as an example, 12 indicators show a significant correlation with vitality intensity. Ranked from strongest to weakest in terms of correlation strength, they are: activity type richness > type diversity > completeness of warning and guidance signage > waterfront accessibility > functional mixing > visual accessibility > area > green view rate > transportation accessibility > shoreline curvature > transportation convenience. Among these, green view rate shows a negative correlation. Therefore, to enhance the vitality of public activity-oriented riverside public spaces, it is crucial to consider spatial design that meets the needs of diverse activities and to provide appropriate and abundant warning and guidance signage.

[0274] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as object-oriented programming languages ​​like Java, C++, Python, and interpreted scripting languages ​​like JavaScript.

[0275] This application is described with reference to flowchart illustrations and / or block diagrams of methods, electronic devices (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing electronic device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing electronic device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0276] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing electronic device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0277] These computer program instructions can also be loaded onto a computer or other programmable data processing electronic device to cause a series of operational steps to be performed on the computer or other programmable electronic device to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable electronic device for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0278] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0279] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for measuring the vitality of a riverside space and analyzing factors affecting the vitality, characterized in that, The method comprises the following steps: collecting data including urban riverside space pattern, environmental quality, and human economy, and constructing a macro-level riverside space vitality evaluation database; obtaining data including Baidu heat data, riverside space site vitality note, number of people and specific activity types at different time and place, and constructing a micro-level riverside space vitality characterization database; collecting data including point data, land use data, building data, road traffic data and remote sensing data, and constructing a micro-level riverside space vitality influencing factor database; performing data preprocessing on the original data of the macro-level riverside space vitality evaluation database, and obtaining standardized index values of the urban riverside space construction level evaluation; performing data preprocessing on the micro-level riverside space vitality characterization database, and calculating the vitality distribution of each research grid similar to the riverside block scale at different time nodes and spatial positions on weekdays and rest days through spatial connection, spatial identification and data statistics; performing data preprocessing on the micro-level riverside space vitality influencing factor database through the ArcGIS near neighbor analysis tool, and obtaining parameter standard values related to each riverside space unit, including the minimum distance of each riverside space unit to the regional core point, the minimum distance of each riverside space unit to the riverside space, the population density in each riverside space unit, and the density of different functional facilities; determining the combination weight of the standardized index values of the urban riverside space construction level evaluation according to the macro-level riverside space vitality evaluation database after data preprocessing, evaluating the closeness of the urban vitality level threshold value through the TOPSIS model, and measuring the macro-level vitality of the riverside space according to the closeness of the urban vitality level threshold value; measuring the micro-level vitality of the riverside space from the aspects of vitality density characteristics and vitality stability characteristics according to the vitality distribution of each research grid similar to the riverside block scale at different time nodes and spatial positions on weekdays and rest days; analyzing the micro-level vitality influencing factors of the riverside space by means of spatial autocorrelation analysis, constructing a multiple linear regression model and excluding explanatory variables with collinearity according to the micro-level riverside space vitality influencing factor database after data preprocessing; preliminarily screening out factors significantly related to space vitality in various activity types according to the correlation coefficient, performing multiple linear regression analysis on the factors significantly related to space vitality in various activity types and the space vitality intensity of the activity type, and analyzing the micro-level vitality influencing factors of the riverside space.

2. The waterfront space vitality measure and vitality influencing factor analysis method according to claim 1, characterized in that: The method for measuring the macro-level vitality of the riverside space comprises the following steps: firstly, determining the combination weight of the standardized index values of the urban riverside space construction level evaluation by means of AHP-entropy weight method; the calculation method of the index weight of the entropy weight method is as follows: Constructing sample matrix if there are cities, evaluation indexes, the original matrix is constructed as follows: ， wherein, represents the number of the city the number of the index dimensionless value after the number of the city calculating the proportion of each index in the evaluation index: ， wherein, represents the proportion of the first index of the first city; calculating information entropy: ， wherein , is the natural logarithm, ; calculating information redundancy: ， wherein, represents the first item indicates the information redundancy; Finally, the index weight is calculated: ， wherein, represents the first weight of the item indicator; The weight of AHP is calculated as follows: Construct a consistency matrix, compare the evaluation indexes with each other; Use CR value to analyze the consistency test: ， , If CR value is less than 0.1, it means that the consistency test is passed, otherwise, the consistency test is not passed, and the consistency matrix is reconstructed and calculated again; Then, the weight obtained by the entropy weight method and the weight obtained by the AHP are substituted into the matrix operation, and the combined weight of the comprehensive evaluation index of the Binjiang space vitality level is finally obtained: , In the formula, W j is a combination weight; α j represents a weight obtained by analytic hierarchy process calculation; β j represents a weight obtained by entropy weight method calculation; Finally, the TOPSIS model is used for comprehensive evaluation, and a standardized matrix is constructed: ， Positive ideal solution for each index Negative ideal solution : positive ideal solution evaluation index the maximum value among all evaluation objects, i.e. ， negative ideal solution evaluation index the minimum value among all evaluation objects, i.e. ， Euclidean distance formula is used to calculate the Euclidean distance of the positive ideal solution and the negative ideal solution of each scheme and the Euclidean distance of the negative ideal solution : ， ， The closeness degree of the evaluation object and the ideal solution is calculated, that is, the threshold closeness degree of urban vitality level: ， wherein, denotes the Euclidean distance of the positive ideal solution, denotes the Euclidean distance of the negative ideal solution; , The greater the value of the index, the higher the macro-level vitality of the waterfront space of the evaluation object, and vice versa.

3. The waterfront space vitality measure and vitality influencing factor analysis method according to claim 1, characterized in that: The activity density characteristic refers to the number change of crowd activities in a unit space at a moment or in a period of time, which is represented by instantaneous activity density and accumulated activity density respectively; The instantaneous activity density is a measure of the crowd density in a Binjiang space unit at a moment, which is represented by the ratio of the total number of crowds at a moment to the unit space area, and the formula is: ， ， wherein, is the number of people in the study unit, is the number of people in the study unit, is the number of people in the study unit, is the area of the study unit, is the number of people in the study unit, is the number of people in the study unit, is the number of people in the study unit, is the instantaneous density of activity. The accumulated activity density is a measure of the crowd density in a Binjiang space unit in a period of time, and the formula is: ， ， wherein, is the number of people on the day, hour, is the area of the study unit, is the crowd density on the day in the statistical period, is the accumulated vitality density; m is the total number of hours in the statistical period. The activity stability refers to the dynamic change of crowd activities in a unit space in a period of time, which is represented by instantaneous activity stability and accumulated activity stability respectively; The instantaneous activity stability is a measure of the fluctuation of the number of crowds in a Binjiang space unit at a moment, which is represented by the inverse index of the activity density change rate of the Binjiang space unit at a moment, and the formula is: ， ， wherein, is the first day of the first hour of the first day of the first is the first day of the first hour of the first day of the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is the first is The accumulated activity stability is a measure of the fluctuation of the number of crowds in a Binjiang space unit in a period of time, which is represented by the inverse index of the activity density standard deviation of the Binjiang space unit in a period of time, and the formula is: ， ， In the formula, is the first day standard deviation of the viability density, is the first day accumulated viability stability; the greater the accumulated viability stability, the more stable the viability, and vice versa.

4. The waterfront space vitality measure and vitality influencing factor analysis method according to claim 1, characterized in that: The analysis process of the activity influencing factors at the observation level in the Binjiang space includes: Firstly, spatial autocorrelation analysis is carried out, and the global Moran's I index is used to preliminarily calculate the spatial correlation of the activity density mean value at each moment on weekdays and rest days, and the formula is as follows: ， wherein, represents the global Moran's I index; denotes the number of study units; and represent the value of the vigor density of the study unit and the study unit respectively, is the mean value of the vigor density of the study unit at each time; denotes the spatial weight matrix; The global Moran's I index is between [-1, 1], if the global Moran's I index is positive, it means that the activity density value of the research unit presents spatial positive correlation characteristics, the units with similar activity density values tend to be aggregated, and the closer the value is to 1, the stronger the spatial aggregation is; if the global Moran's I index is negative, it means that the activity density value of the research unit presents spatial negative correlation characteristics, the units with similar activity density values tend to be discrete, and the closer the value is to-1, the stronger the spatial discreteness is; if the global Moran's I index is 0, it means that the activity density value of the research unit does not have spatial correlation, and presents random distribution; Then, a multiple linear regression model is constructed, and the collinearity of the potential influencing factor index value is tested based on the variance inflation factor, and the potential influencing factors with strong collinearity are removed; The spatiotemporal geographically weighted regression model selects a Gaussian distance function to establish a spatiotemporal weight function, and explores the correlation between the explanatory variables and the explained variables, and represents the influence degree of each explanatory variable on the riverside space vitality on weekdays and weekends at the meso level. The calculation formula of the spatiotemporal geographically weighted regression model is: ， In the formula, is the time-space three-dimensional coordinate of the th sample point, is the independent variable, i.e., the explanatory variable, is the dependent variable, i.e., the explained variable, is the number of independent variables, is the regression coefficient of the th independent variable of the th sample point, is the random error of the th sample point, is the intercept term; The least square method is usually used for estimation, and the estimation value is calculated according to the following formula: ， wherein is the spatial weight matrix of the sample points with values ; the diagonal elements are the weights of the spatio-temporal weight function of the sample points at the observation point The Gaussian distance function is selected to establish a spatiotemporal weight function, and the formula is as follows: ， wherein is the spatial distance between the first sample point and the second sample point; is the temporal distance between the first sample point and the second sample point; is the spatio-temporal distance between the first sample point and the second sample point; is the bandwidth; defining the sample and is the spatio-temporal distance between the first sample point and the second sample point is the temporal distance and the spatial distance is the combination function of the temporal distance and the spatial distance, formulated as follows: ， where and are the ratio factors balancing the time and spatial distances; and denote the spatial position coordinates of the sample points and respectively; and are the time observations of the sum of the sample points and The weights are calculated using a Gaussian function: In the formula, denotes the space-time bandwidth; denotes the space bandwidth, , denotes the time bandwidth, ; The cross-validation method is selected as the determination method of the bandwidth, and the formula is as follows: ， where is the dependent variable is the observed value at the th sample point; is the fitted value; the optimal bandwidth is the value of that achieves the minimum.

5. The waterfront space vitality measure and vitality influencing factor analysis method according to claim 1, characterized in that: The analysis process of the influence factors of the riverside space at the micro level includes: Pearson correlation coefficient is selected to preliminarily determine the influence factors that have a significant influence on the space vitality, and the factors that are significantly related to the space vitality in various activity types are preliminarily screened out to provide a basis for further multiple linear regression analysis, and the formula is as follows: ， wherein, represents the Pearson correlation coefficient; n is the number of samples, and x and y are the values of the independent and dependent variables, respectively. Pearson correlation coefficient is selected to preliminarily screen out the factors that are significantly related to the space vitality, and the Pearson correlation coefficient value ranges from-1 to 1, 1 represents complete positive correlation, -1 represents complete negative correlation, and 0 represents no linear correlation; The multiple linear regression model is used to analyze the linear relationship between the factors that are significantly related to the space vitality in various activity types and the space vitality intensity of the activity type, and the vitality intensity and the vitality influence factor quantitative data results of the riverside public space of the life leisure type, the cultural tourism type and the public activity type are analyzed in pairs at the micro level, and the formula is as follows: , wherein, is the dependent variable, , ⋯ are the independent variables, is the intercept term, , ⋯ are the regression coefficients for each independent variable, is the random error term, representing the portion that cannot be explained by the independent variables.

6. A system for measuring waterfront space vitality and analyzing vitality influencing factors, which implements the method according to any one of claims 1-5, characterized in that: The system includes a vitality evaluation database construction module, a vitality representation database construction module, a vitality influence factor database construction module, a data preprocessing module, a macro level vitality measurement module, a meso and micro level vitality measurement module, a meso level vitality influence factor analysis module and a micro level vitality influence factor analysis module; The vitality evaluation database construction module is used to collect data including urban riverside space pattern, environmental quality, human economy and the like, and construct a macro level riverside space vitality evaluation database; The vitality representation database construction module is used to obtain data including Baidu heat data, riverside space site vitality occurrence spatial annotation, number of people and specific activity types at different time and place, and construct a riverside space micro vitality representation database; The vitality influence factor database construction module is used to collect data including point data, land use data, building data, road traffic data and remote sensing data, and construct a meso and micro level riverside space vitality influence factor database; The data preprocessing module is used to perform data preprocessing such as non-dimensionalization and translation on the original data of the macro level riverside space vitality evaluation database, and obtain standardized index values of urban riverside space construction level evaluation; The micro vitality representation database of the riverside space is subjected to data preprocessing, and through spatial connection, spatial identification and data statistics, the vitality distribution of each research grid at a riverside block scale at different time nodes and spatial positions on weekdays and weekends is calculated. The macro-level activity measure module is configured to determine the combination weight of the standardized index value of the urban waterfront space construction level evaluation according to the data preprocessed macro-level waterfront space activity evaluation database by using the AHP-entropy weight method, to evaluate the threshold closeness of the urban activity level by using a TOPSIS model, and to measure the macro-level activity of the waterfront space according to the threshold closeness of the urban activity level. The meso-level activity measure module is configured to measure the meso-level activity of the waterfront space from the activity density characteristics and the activity stability characteristics according to the activity distribution of each research grid similar to the waterfront block scale at different time nodes and spatial positions on weekdays and rest days. The meso-level activity influence factor analysis module is configured to analyze the activity influence factors of the waterfront space at the meso level according to the data preprocessed meso-level waterfront space activity influence factor database by using the method of spatial autocorrelation analysis, constructing a multiple linear regression model, and eliminating the explanatory variables with multicollinearity. The micro-level activity influence factor analysis module is configured to analyze the activity influence factors of the waterfront space at the micro level by preliminarily screening the factors significantly related to the spatial activity of various activity types according to the data preprocessed macro-level waterfront space activity evaluation database, the waterfront space meso-level activity representation database, and the meso-level waterfront space activity influence factor database, and performing multiple linear regression analysis on the factors significantly related to the spatial activity of various activity types and the spatial activity intensity of the activity type. The computer program is executed by the processor to implement the waterfront space activity measure and activity influence factor analysis method according to any one of claims 1-5.

7. An electronic device, comprising: The computer program is executed by the processor to implement the waterfront space activity measure and activity influence factor analysis method according to any one of claims 1-5. ​ 8. A computer-readable storage medium, the computer-readable storage medium storing a computer program, characterized in that: ​

Images