Dynamic aggregation and decision support system of urban physical examination spatiotemporal data

Abstract

The present invention relates to the field of smart city management technology, and specifically to a dynamic aggregation and decision support system for urban physical examination spatiotemporal data, including a data acquisition module, a data preprocessing module, a spatiotemporal data aggregation module, an indicator calculation module, a dynamic analysis module, and a decision support module; wherein: the data acquisition module is used to collect multi-source heterogeneous original urban operation data; the spatiotemporal data aggregation module aggregates data according to a specified time window and spatial unit; the indicator calculation module extracts core indicators that reflect the health status of the city; the dynamic analysis module predicts the future change trend of the core indicators; the decision support module generates an optimization plan for urban governance strategies. The present invention accurately predicts the trend of urban operation and generates targeted governance optimization plans through the dynamic integration and spatiotemporal correlation analysis of multi-source heterogeneous data, significantly improving the comprehensiveness of urban physical examinations and the scientific nature of decision support.

Description

Technical Field

[0001] The present invention relates to the field of smart city management technology, and in particular to a dynamic aggregation and decision support system for urban physical examination spatiotemporal data. Background Art

[0002] With the acceleration of urbanization and the continuous expansion of urban scale, data in multiple fields such as traffic circulation and environmental monitoring involved in urban management have shown explosive growth. These data come from diverse sources and are highly real-time. They include both static data (such as urban infrastructure information and historical operation records) and dynamic data (such as traffic flow, environmental quality, crowd behavior, etc.). The effective integration, analysis and utilization of these multi-source heterogeneous data are crucial for a comprehensive understanding of the city's operating status, predicting future trends, optimizing resource allocation, and formulating emergency response strategies. However, existing urban management systems usually focus on the analysis of a single field or static data, and lack the ability to perform dynamic correlation analysis on multi-dimensional spatiotemporal data, making it difficult to achieve comprehensive diagnosis of urban operations and scientific decision-making support.

[0003] The existing technologies have the following main problems in spatiotemporal data analysis and decision support: First, it is difficult to integrate multi-source heterogeneous data. Data from different sources have significant differences in format, scale, and timeliness, resulting in low data processing efficiency and incomplete analysis results; second, there is a lack of dynamic correlation analysis capabilities. Existing methods are mostly based on static analysis and cannot capture the spatiotemporal dynamic change characteristics of multidimensional data in urban operation; third, decision support is not accurate enough. The strategy generation scheme based on traditional analysis lacks accurate prediction and targeted optimization of complex urban operation status. In view of the above problems, there is an urgent need for a dynamic aggregation and decision support system for urban physical examination spatiotemporal data to solve the key problems in the existing technology. Summary of the invention

[0004] Based on the above objectives, the present invention provides a city physical examination spatiotemporal data dynamic aggregation and decision support system.

[0005] The urban physical examination spatiotemporal data dynamic aggregation and decision support system includes a data acquisition module, a data preprocessing module, a spatiotemporal data aggregation module, an indicator calculation module, a dynamic analysis module and a decision support module; among which:

[0006] Data collection module: used to collect multi-source heterogeneous original urban operation data, which includes static data and dynamic data; static data includes urban infrastructure information and historical operation records; dynamic data includes real-time traffic flow, environmental monitoring data and crowd behavior trajectory; the collected data is uploaded to the data preprocessing module through a unified interface;

[0007] Data preprocessing module: used to receive multi-source heterogeneous data transmitted by the data acquisition module, and perform format conversion, missing value filling, outlier removal and data normalization to generate a standardized data set;

[0008] Spatiotemporal data aggregation module: Based on the standardized data set output by the data preprocessing module, the spatiotemporal association mechanism is used to aggregate the data according to the specified time window and spatial unit to generate an aggregated data set with spatiotemporal characteristics;

[0009] Index calculation module: receives the aggregated data set output by the spatiotemporal data aggregation module, and extracts the core indicators reflecting the health status of the city based on the set calculation rules, including the traffic circulation index and the environmental load index;

[0010] Dynamic analysis module: receives the core indicators output by the indicator calculation module and predicts the future trend of the core indicators based on the time series prediction algorithm;

[0011] Decision support module: Generates urban governance strategy optimization plans based on future change trend data output by the dynamic analysis module, including resource allocation optimization and emergency response plans.

[0012] Optionally, the data acquisition module includes a sensor acquisition unit, a data docking unit and a data transmission unit; wherein:

[0013] Sensor collection unit: used to collect dynamic operation data through multiple types of sensors deployed in designated areas of the city, including traffic flow sensors, air quality monitoring sensors and personnel flow monitoring sensors; among which, traffic flow sensors are used to collect real-time traffic flow data; air quality monitoring sensors are used to collect environmental monitoring data; and personnel flow monitoring sensors are used to collect crowd behavior trajectory data;

[0014] Data docking unit: used to connect with external data sources through interface protocols to obtain static data; the static data includes urban infrastructure information and historical operation records; the external data sources include urban management databases and commercial data service platforms, which are specifically transmitted to the data docking unit through API interfaces;

[0015] Data transmission unit: used to receive data acquired by the sensor acquisition unit and the data docking unit, and preliminarily package the data; and upload it to the data preprocessing module through a unified interface.

[0016] Optionally, the data preprocessing module includes a format conversion unit, a missing value processing unit, an outlier elimination unit and a data normalization unit; wherein:

[0017] Format conversion unit: used to receive multi-source heterogeneous data transmitted by the data acquisition module, and convert the data into a unified structured format according to the source type and format characteristics of the data; the data collected by the sensor is arranged into a table structure according to the timestamp, and the static data obtained by the external interface is parsed into JSON format according to the preset template;

[0018] Missing value processing unit: used to identify missing values ​​in the output data of the format conversion unit, and fill them with interpolation or default values ​​according to the data type; for time series data, linear interpolation method is used to fill missing values; for categorical data, historical mean or preset constant is used to fill missing values;

[0019] Outlier elimination unit: used to detect and eliminate outliers in the original data through a set threshold range; the threshold range is set based on historical statistical data, and data exceeding the threshold range is marked as abnormal and eliminated;

[0020] Data normalization unit: used to normalize the data output by the missing value processing unit and the outlier removal unit to eliminate the dimensional differences of different data sources; specifically, the Min-Max normalization method is adopted, and the normalized values ​​are standardized to the range of [0, 1].

[0021] Optionally, the spatiotemporal data aggregation module includes a time window processing unit, a space unit division unit, a spatiotemporal correlation calculation unit and an aggregation result generation unit; wherein:

[0022] Time window processing unit: used to aggregate the standardized data set output by the data preprocessing module in segments according to the time dimension according to the preset time window parameters; and calculate the statistical characteristic values ​​of each time window, including the average value, maximum value, minimum value and change trend, to generate a time window labeled data set;

[0023] Spatial unit division unit: used to allocate the time window marked data set to the corresponding spatial unit according to the geographic spatial position according to the preset spatial division rule;

[0024] A spatiotemporal correlation calculation unit is used to combine the output data of the time window processing unit and the space unit division unit, and perform calculations based on a spatiotemporal correlation model; the spatiotemporal correlation model includes a time series analysis algorithm and a geographic space clustering algorithm, and is used to calculate the similarity between spatial units in different time windows, and identify the association relationship between multiple spatial units in the same time window, as well as the dynamic changes of the same spatial unit in different time windows, and generate a spatiotemporal correlation matrix;

[0025] Aggregation result generation unit: used to integrate the output results of the spatiotemporal correlation calculation unit to generate an aggregated data set with spatiotemporal characteristics, including time window number, spatial unit identifier, statistical eigenvalue and spatiotemporal correlation matrix, for use by the indicator calculation module.

[0026] Optionally, the time window processing unit specifically includes:

[0027] Time window division: First receive the standardized data set output by the data preprocessing module, and divide it into and preset time window parameters The data is segmented by time dimension; the time window division rule formula is: window number ,in, Indicates the timestamp of the data record; is the earliest timestamp in the data set; is the time window length; is the window number. After segmentation, each data point belongs to a unique window. ;

[0028] Data grouping: by window number Group the standardized data set, each group of data corresponds to a time window , the timestamp of this group of data meets the following conditions: ;

[0029] Statistical eigenvalue calculation: For each time window Calculate the statistical characteristics of the data, including the mean value , maximum value , minimum and changing trends ;

[0030] Generate a time window labeled dataset: Each time window The statistical feature values ​​of are integrated into a time window marked data set; the time window marked data set includes the following fields: ,in and Represents the time window The start and end time.

[0031] Optionally, the space unit division unit specifically includes:

[0032] Preset spatial division rules: According to the coverage of the urban geographical area, the urban area is divided into several spatial units using a regular grid division method; the boundary of each spatial unit is determined by the longitude range. and latitude range OK; set the spatial unit number to , and are allocated according to the following rules: ,in, Represents the index of the spatial unit in the longitude direction; Represents the index of the spatial unit in the latitude direction; and is the longitude boundary of the spatial unit; and is the latitude boundary of the spatial unit;

[0033] Spatial unit division calculation: total longitude range of urban area and latitude range The boundary length of each space unit is determined according to the grid division rules. The formula is:

[0034] and ,in, and is the number of grid divisions in longitude and latitude; and are the longitude and latitude lengths of each spatial unit respectively; the longitude and latitude boundaries of each spatial unit are calculated as: and ; and ;

[0035] Data is assigned to spatial units: Each data record in the dataset is labeled in the time window according to its geographic location coordinates Determine the spatial unit to which it belongs , the judgment conditions are: Condition 1, ; Condition 2, ; If both of the above conditions are met, the record is assigned to the spatial unit , and add the corresponding unit number.

[0036] Optionally, the spatiotemporal correlation calculation unit includes:

[0037] Similarity calculation between spatial units in different time windows: First, extract the characteristic value set of each spatial unit in each time window from the output data of the time window processing unit and the spatial unit division unit, including the average value, maximum value, minimum value and change trend; then use the difference in the characteristic values ​​between spatial units to calculate the similarity between spatial units; and normalize the similarity values ​​to generate a similarity matrix reflecting the similarity between spatial units;

[0038] Calculation of association relationships of spatial units in the same time window: Based on the similarity matrix generated in the time window and the geographical location of the spatial units, the association relationships between spatial units are identified through the geospatial clustering algorithm to generate an association relationship matrix;

[0039] Dynamic change analysis of the same spatial unit in different time windows: Perform time series analysis on the changes of the characteristic values ​​of each spatial unit in multiple time windows, calculate the change rate between each time window, so as to capture the dynamic change characteristics of a single spatial unit in different time periods; and organize the analysis results into a dynamic change matrix;

[0040] Output spatiotemporal correlation matrix: Integrate the correlation relationship matrix and dynamic change matrix in different time windows into a unified spatiotemporal correlation matrix.

[0041] Optionally, the index calculation module includes a data parsing unit, a traffic circulation index calculation unit and an environmental load index calculation unit; wherein:

[0042] Data parsing unit: receives the aggregated data set output by the spatiotemporal data aggregation module, and parses the grouping structure of the time window and spatial unit, and extracts the statistical feature value set of each spatial unit in each time window, including the average value, maximum value, minimum value and change trend;

[0043] Traffic circulation index calculation unit: According to the parsed data, each space unit The traffic circulation index is calculated using the formula: ,in, is the average vehicle speed of the spatial unit in the corresponding time window; is the maximum value of vehicle speed in all spatial units; is the average vehicle flow of the spatial unit in the corresponding time window; is the maximum value of vehicle flow in all spatial units; is the traffic circulation index, with a value range of ,The larger the value, the better the traffic flow;

[0044] Environmental load index calculation unit: According to the analyzed data, The environmental load is calculated and the environmental load index is set , the formula is: ,in, For space unit In the time window The average concentration of each pollutant; is the total number of pollutant types; is the pollutant exceeding standard rate, calculated as: ,in, For space unit In this time window The number of data points where the pollutant exceeds the standard; is the total number of data points; environmental load index The value range is , the higher the value, the heavier the environmental load.

[0045] Optionally, the dynamic analysis module includes a data preparation unit, a feature extraction unit, a time series modeling unit and a result generation unit; wherein:

[0046] Data preparation unit: receives the core indicator data output by the indicator calculation module, including the traffic circulation index and environmental load index of each time window and space unit, sorts the data according to the time window, and organizes the core indicator data of each space unit into time series data;

[0047] Feature extraction unit: used to extract trend features from time series data to characterize the changing rules of core indicators in the time dimension; the extracted trend features include mean change rate, fluctuation amplitude and periodicity characteristics;

[0048] Time series modeling unit: Based on the extracted trend features, the time series prediction algorithm is used to model the future change trend of the core indicators, and the predicted values ​​of the core indicators in the future time window are output;

[0049] Result generation unit: associates the prediction result of the time series modeling unit with the spatial unit number and the time window number, and generates a future change trend data set containing the predicted values ​​of the traffic circulation index and the environmental load index in the future time window; the future change trend data set includes the spatial unit number, the time window number, the predicted value of the traffic circulation index in the future time window, and the predicted value of the environmental load index in the future time window.

[0050] Optionally, the decision support module includes:

[0051] Data analysis unit: receives the future change trend data set output by the dynamic analysis module, and analyzes the predicted values ​​of the traffic circulation index and environmental load index of each spatial unit in the future time window;

[0052] Strategy analysis unit: Analyze the traffic flow and environmental conditions in designated areas and time periods of the city based on the predicted values ​​of the traffic flow index and environmental load index, and identify the areas and times where problems occur;

[0053] Strategy Generation Unit: Based on the strategy analysis unit, the unit identifies the areas and times where problems occur, and develops an optimization plan for urban governance strategies, including resource allocation adjustment suggestions and emergency response plans;

[0054] The resource allocation adjustment suggestions include adjusting traffic signal control, increasing public transportation resources, planning temporary traffic control measures, and reallocating environmental monitoring resources;

[0055] The emergency response plan includes temporary road closures, emergency evacuation route settings, air quality warnings, and health protection recommendations;

[0056] Program output unit: Organize the generated urban governance strategy optimization plan into a structured report format, including resource allocation diagrams and emergency response flowcharts, to provide operational guidance and decision-making support for urban managers.

[0057] Beneficial effects of the present invention:

[0058] The present invention realizes the comprehensive integration and analysis of multi-dimensional spatio-temporal data by setting up a data acquisition module, a data preprocessing module, a spatio-temporal data aggregation module, an indicator calculation module, a dynamic analysis module and a decision support module; in particular, through the spatio-temporal correlation calculation model and the time series prediction algorithm, it can capture the spatio-temporal dynamic change characteristics in the city's operating status, and generate data results with accurate trend prediction and multi-dimensional correlation characteristics, thereby comprehensively and dynamically reflecting the health status of the city.

[0059] The present invention outputs targeted urban governance strategy optimization plans through a decision support module, including resource allocation adjustment suggestions and emergency response plans; based on scientific predictions of future change trends and precise analysis of key areas, it has significant advantages in improving the pertinence, timeliness and operability of urban governance strategies; it not only improves urban management efficiency, but also provides a data-driven intelligent solution for addressing complex urban operation problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 A schematic diagram of a dynamic aggregation and decision support system according to an embodiment of the present invention;

[0062] Figure 2 Schematic diagram of a spatiotemporal data aggregation module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0064] like Figure 1-Figure 2 As shown, the urban physical examination spatiotemporal data dynamic aggregation and decision support system includes a data acquisition module, a data preprocessing module, a spatiotemporal data aggregation module, an indicator calculation module, a dynamic analysis module and a decision support module; among which:

[0065] Data collection module: used to collect multi-source heterogeneous original urban operation data, which includes static data and dynamic data; static data includes urban infrastructure information and historical operation records; dynamic data includes real-time traffic flow, environmental monitoring data and crowd behavior trajectory; the collected data is uploaded to the data preprocessing module through a unified interface;

[0066] Data preprocessing module: used to receive multi-source heterogeneous data transmitted by the data acquisition module, and perform format conversion, missing value filling, outlier removal and data normalization to generate a standardized data set;

[0067] Spatiotemporal data aggregation module: Based on the standardized data set output by the data preprocessing module, the spatiotemporal association mechanism is used to aggregate the data according to the specified time window and spatial unit to generate an aggregated data set with spatiotemporal characteristics;

[0068] Index calculation module: receives the aggregated data set output by the spatiotemporal data aggregation module, and extracts the core indicators reflecting the health status of the city based on the set calculation rules, including the traffic circulation index and the environmental load index;

[0069] Dynamic analysis module: receives the core indicators output by the indicator calculation module and predicts the future trend of the core indicators based on the time series prediction algorithm;

[0070] Decision support module: Generates urban governance strategy optimization plans based on future change trend data output by the dynamic analysis module, including resource allocation optimization and emergency response plans.

[0071] The data acquisition module includes a sensor acquisition unit, a data docking unit and a data transmission unit; wherein:

[0072] Sensor collection unit: used to collect dynamic operation data through multiple types of sensors deployed in designated areas of the city. The multiple types of sensors include traffic flow sensors, air quality monitoring sensors and personnel flow monitoring sensors. Among them, traffic flow sensors are used to collect real-time traffic flow data, including road traffic volume and vehicle speed data; air quality monitoring sensors are used to collect environmental monitoring data, including PM2.5 concentration and carbon dioxide content in the environment; personnel flow monitoring sensors are used to collect crowd behavior trajectory data;

[0073] Data docking unit: used to connect with external data sources through interface protocols to obtain static data; static data includes urban infrastructure information and historical operation records; external data sources include urban management databases and commercial data service platforms, which are specifically transmitted to the data docking unit through API interfaces;

[0074] Data transmission unit: used to receive data acquired by the sensor acquisition unit and the data docking unit, and perform preliminary packaging of the data; and upload the data to the data preprocessing module through a unified interface to ensure the integrity and consistency of the original data during transmission; the above units work together, the sensor acquisition unit and the data docking unit respectively acquire multi-source heterogeneous original urban operation data, the data transmission unit packages the acquired data and uploads it to the data preprocessing module through a unified interface to provide input data for subsequent standardized processing.

[0075] The data preprocessing module includes a format conversion unit, a missing value processing unit, an outlier removal unit, and a data normalization unit; among which:

[0076] Format conversion unit: used to receive multi-source heterogeneous data transmitted by the data acquisition module, and convert the data into a unified structured format according to the source type and format characteristics of the data; the data collected by the sensor is arranged into a table structure according to the timestamp, and the static data obtained by the external interface is parsed into JSON format according to the preset template;

[0077] Missing value processing unit: used to identify missing values ​​in the output data of the format conversion unit, and fill them with interpolation or default values ​​according to the data type; for time series data, linear interpolation method is used to fill missing values; for categorical data, historical mean or preset constant is used to fill missing values;

[0078] Outlier elimination unit: used to detect and eliminate outliers in the original data through the set threshold range; the threshold range is set based on historical statistical data, and data exceeding the threshold range is marked as abnormal and eliminated;

[0079] Data normalization unit: used to normalize the data output by the missing value processing unit and the outlier removal unit to eliminate the dimensional differences of different data sources; specifically, the Min-Max normalization method is adopted, and the normalized values ​​are standardized to the range of [0, 1]; the above units work together, the format conversion unit first unifies the original data into a standard structure, the missing value processing unit and the outlier removal unit process the problem items in the data in turn, and the data normalization unit unifies the scale of the processed data, and finally generates a standardized data set that can be used by the spatiotemporal data aggregation module.

[0080] The spatiotemporal data aggregation module includes a time window processing unit, a space unit division unit, a spatiotemporal correlation calculation unit, and an aggregation result generation unit; wherein:

[0081] Time window processing unit: used to aggregate the standardized data set output by the data preprocessing module in segments according to the time dimension according to the preset time window parameters; and calculate the statistical characteristic values ​​of each time window, including the average value, maximum value, minimum value and change trend, to generate a time window labeled data set;

[0082] Spatial unit division unit: used to allocate the time window marker data set to the corresponding spatial unit according to the geographic spatial position according to the preset spatial division rules; the spatial unit is defined in a grid division manner, the division accuracy is determined by the grid size, and the spatial unit identifier is represented by the grid number or geographic coordinate range;

[0083] Spatiotemporal correlation calculation unit: used to combine the output data of the time window processing unit and the space unit division unit, and perform calculations based on the spatiotemporal correlation model; the spatiotemporal correlation model includes a time series analysis algorithm and a geographic space clustering algorithm, which are used to calculate the similarity between spatial units in different time windows, and identify the correlation relationship between multiple spatial units in the same time window, as well as the dynamic changes of the same spatial unit in different time windows, and generate a spatiotemporal correlation matrix;

[0084] Aggregation result generation unit: used to integrate the output results of the spatiotemporal correlation calculation unit to generate an aggregated data set with spatiotemporal characteristics, including time window number, spatial unit identifier, statistical characteristic value and spatiotemporal correlation matrix, for use by the indicator calculation module; the above units work together, the time window processing unit divides the data into time dimensions, the spatial unit division unit completes the spatial area division, the spatiotemporal correlation calculation unit extracts correlation features in combination with the time and space dimensions, the aggregation result generation unit summarizes the processing results, and finally outputs an aggregated data set with spatiotemporal characteristics for use by the indicator calculation module.

[0085] The time window processing unit specifically includes:

[0086] Time window division: First receive the standardized data set output by the data preprocessing module, and divide it into and preset time window parameters (Units are minutes, hours or days) The data is segmented by time dimension; the time window division rule formula is: window number ,in, Indicates the timestamp of the data record; is the earliest timestamp in the data set; is the time window length; is the window number. After segmentation, each data point belongs to a unique window. ;

[0087] Data grouping: by window number Group the standardized data set, each group of data corresponds to a time window , the timestamp of this group of data meets the following conditions: ;

[0088] Statistical eigenvalue calculation: For each time window Calculate the statistical characteristics of the data, including the mean value , maximum value , minimum and changing trends ;

[0089] The average value is The calculation formula is: ,in For time window The first Items of data, is the total number of data in the time window;

[0090] The maximum value is The formula is: ;

[0091] The minimum value is The formula is: ;

[0092] The changing trend is , calculate the data value by linear regression With time The changing trend of is: ,in is the average value of timestamps in the time window, is the average value of the corresponding data value;

[0093] Generate a time window labeled dataset: Each time window The statistical feature values ​​of are integrated into a time window labeling dataset; the time window labeling dataset contains the following fields: ,in and Represents the time window The above steps realize the functions of the time window processing unit to divide the data from the time dimension, calculate the statistical characteristic values, and generate a structured time window labeled data set, providing clear time series data input for subsequent modules.

[0094] The spatial unit division units specifically include:

[0095] Preset spatial division rules: According to the coverage of the urban geographical area, the urban area is divided into several spatial units using a regular grid division method; the boundary of each spatial unit is determined by the longitude range. and latitude range OK; set the spatial unit number to , and are allocated according to the following rules: ,in, Represents the index of the spatial unit in the longitude direction; Represents the index of the spatial unit in the latitude direction; and is the longitude boundary of the spatial unit; and is the latitude boundary of the spatial unit;

[0096] Spatial unit division calculation: total longitude range of urban area and latitude range The boundary length of each space unit is determined according to the grid division rules. The formula is:

[0097] and ,in, and is the number of grid divisions in longitude and latitude; and are the longitude and latitude lengths of each spatial unit respectively; the longitude and latitude boundaries of each spatial unit are calculated as: and ; and ;

[0098] Data is assigned to spatial units: Each data record in the dataset is labeled in the time window according to its geographic location coordinates Determine the spatial unit to which it belongs , the judgment conditions are: Condition 1, ; Condition 2, ; If both of the above conditions are met, the record is assigned to the spatial unit , and add the corresponding unit number; the above steps realize the geographical location allocation of the time window marked data set by the spatial unit division unit and the generation of the spatial unit marked data set, providing accurate spatial feature data input for the spatiotemporal correlation calculation unit.

[0099] The spatiotemporal correlation calculation unit includes:

[0100] Similarity calculation between spatial units in different time windows: First, extract the characteristic value set of each spatial unit in each time window from the output data of the time window processing unit and the spatial unit division unit, including the average value, maximum value, minimum value and change trend; then use the difference in the characteristic values ​​between spatial units to calculate the similarity between spatial units; and normalize the similarity values ​​to generate a similarity matrix reflecting the similarity between spatial units;

[0101] Calculation of association relationships of spatial units in the same time window: Based on the similarity matrix generated in the time window and the geographical location of the spatial units, the association relationships between spatial units are identified through the geospatial clustering algorithm; in the clustering process, the similarity threshold and geographical distance limit are considered at the same time to ensure that only spatial units with high similarity and close geographical distance are divided into the same association group, and an association relationship matrix is ​​generated to represent the association between the spatial units in the time window;

[0102] Dynamic change analysis of the same spatial unit in different time windows: Perform time series analysis on the changes of the characteristic values ​​of each spatial unit in multiple time windows, calculate the change rate between each time window, so as to capture the dynamic change characteristics of a single spatial unit in different time periods; and organize the analysis results into a dynamic change matrix to reflect the trend change of the spatial unit in different time periods;

[0103] Output spatiotemporal association matrix: Integrate the association relationship matrix and dynamic change matrix in different time windows into a unified spatiotemporal association matrix; the spatiotemporal association matrix includes the spatial unit association information in each time window and its dynamic changes in different time periods, providing comprehensive spatiotemporal feature data input for subsequent modules.

[0104] The steps for generating the spatiotemporal correlation matrix are as follows:

[0105] Feature extraction: Receive the output data of the time window processing unit and the spatial unit division unit, and extract the feature value from each spatial unit. Extract feature values ​​from the time window labeled dataset ,include: ,in, Indicates the time window number; Indicates the spatial unit number; They are the average value, maximum value, minimum value and change trend in the time window respectively;

[0106] Similarity measurement: Use Euclidean distance to calculate the similarity between two spatial units in different time windows and The similarity of eigenvalues , the formula is: ,in, Represents a time window Inner space unit and The similarity of eigenvalues; is the first eigenvalue vector item;

[0107] Normalization: Normalize all calculated similarity values ​​to obtain a similarity matrix , the expression is: ;

[0108] Cluster analysis: using geospatial clustering algorithms, based on the geographic coordinates of spatial units and similarity matrices , identify the association between multiple spatial units in the same time window; the clustering conditions are: ,in, is the similarity threshold; is the geographic distance threshold; Represents spatial unit and The geographical distance is calculated as:

[0109] ;

[0110] Generate association matrix: Generate an association matrix based on clustering results , where the matrix elements Represents spatial unit and In the time window The internal correlation generates The expression is:

[0111] ;

[0112] Time series analysis: For each spatial unit , extract its feature value sequence in multiple time windows , conduct time series trend analysis; rate of change The calculation formula is: ;

[0113] Dynamic change matrix generation: Generate a dynamic change matrix based on time series analysis results , where the matrix elements Represents spatial unit In the time window The rate of change within: ;

[0114] Output association matrix: Finally, the association matrix of the spatial unit and the dynamically changing matrix Integration into a spatiotemporal correlation matrix , the matrix contains the following elements: , the spatiotemporal correlation matrix Output to the aggregation result generation unit for further processing of subsequent spatiotemporal data.

[0115] The index calculation module includes a data analysis unit, a traffic circulation index calculation unit and an environmental load index calculation unit; wherein:

[0116] Data parsing unit: receives the aggregated data set output by the spatiotemporal data aggregation module, and parses the grouping structure of the time window and spatial unit, and extracts the statistical feature value set of each spatial unit in each time window, including the average value, maximum value, minimum value and change trend;

[0117] Traffic circulation index calculation unit: According to the parsed data, each space unit The traffic circulation index is calculated using the formula: ,in, is the average vehicle speed of the spatial unit in the corresponding time window; is the maximum value of vehicle speed in all spatial units, used for normalization; is the average vehicle flow of the spatial unit in the corresponding time window; is the maximum value of vehicle flow in all spatial units; is the traffic circulation index, with a value range of ,The larger the value, the better the traffic flow;

[0118] Environmental load index calculation unit: According to the analyzed data, The environmental load is calculated and the environmental load index is set , the formula is: ,in, For space unit In the time window The average concentration of a pollutant (such as PM2.5 or CO2); is the total number of pollutant types; is the pollutant exceeding standard rate, calculated as: ,in, For space unit In this time window The number of data points where the pollutant exceeds the standard; is the total number of data points; environmental load index The value range is The higher the value, the heavier the environmental load; the above units work together to extract core indicators from spatiotemporal data, fully reflect the city’s traffic circulation status and environmental load conditions, and provide structured indicator data input for subsequent modules.

[0119] The dynamic analysis module includes a data preparation unit, a feature extraction unit, a time series modeling unit, and a result generation unit; wherein:

[0120] Data preparation unit: receives the core indicator data output by the indicator calculation module, including the traffic circulation index and environmental load index of each time window and space unit, sorts the data according to the time window, and organizes the core indicator data of each space unit into time series data;

[0121] Feature extraction unit: used to extract trend features from time series data to characterize the changing rules of core indicators in the time dimension; the extracted trend features include mean change rate, fluctuation range and periodicity features; the mean change rate is used to measure the overall change trend of core indicators; the fluctuation range is used to describe the fluctuation range of core indicators; the periodicity features are used to identify possible periodic change patterns; feature extraction is based on the sliding window method: select a fixed-length historical time window, perform feature calculations on the indicator data in the window, and slide the window to cover the entire time series to form a feature sequence;

[0122] Time series modeling unit: Based on the extracted trend features, a time series prediction algorithm (such as long short-term memory network LSTM or ARIMA model) is used to model the future trend of core indicators and output the predicted value of the core indicators in the future time window;

[0123] Predictive modeling involves the following steps:

[0124] Training phase: Use the core indicator feature data in the historical time window as input and the core indicator values ​​in one or more future time windows as output to train the time series prediction model; and minimize the error between the predicted value and the true value by optimizing the model parameters;

[0125] Prediction stage: Input the feature sequence in the current time window, and output the predicted value of the core indicator in the future time window through the trained time series prediction model.

[0126] Result generation unit: associates the prediction results of the time series modeling unit with the spatial unit number and the time window number to generate a future change trend data set containing the predicted values ​​of the traffic circulation index and the environmental load index in the future time window; the future change trend data set includes the spatial unit number, the time window number, the predicted value of the traffic circulation index in the future time window, and the predicted value of the environmental load index in the future time window.

[0127] The decision support modules include:

[0128] Data analysis unit: receives the future change trend data set output by the dynamic analysis module, and analyzes the predicted values ​​of the traffic circulation index and environmental load index of each spatial unit in the future time window;

[0129] Strategy Analysis Unit: Analyze the traffic flow and environmental conditions in designated areas and time periods of the city based on the predicted values ​​of the traffic flow index and environmental load index, and identify the areas and times where problems occur; this analysis determines the priority and urgency of resource allocation based on the predicted traffic congestion and environmental pollution level;

[0130] Strategy Generation Unit: Based on the strategy analysis unit, the unit identifies the areas and times where problems occur, and develops an optimization plan for urban governance strategies, including resource allocation adjustment suggestions and emergency response plans;

[0131] Recommendations for resource allocation adjustments include adjusting traffic signal controls, increasing public transportation resources, planning temporary traffic control measures, and reallocating environmental monitoring resources to ensure that expected pressures can be effectively addressed during predicted high-risk periods and areas;

[0132] Emergency response plans include temporary road closures, emergency evacuation route establishment, air quality warning issuance and health protection recommendations;

[0133] Solution output unit: The generated urban governance strategy optimization plan is organized into a structured report format, including resource allocation diagrams and emergency response flowcharts, to provide operational guidance and decision-making support for urban managers; in addition, the solution report also includes a visual representation of the forecast data to assist in explaining the data-driven factors behind the solution decision.

[0134] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0135] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. The city physical examination spatiotemporal data dynamic aggregation and decision support system is characterized by: It includes data collection module, data preprocessing module, spatiotemporal data aggregation module, indicator calculation module, dynamic analysis module and decision support module; among which: Data collection module: used to collect multi-source heterogeneous original urban operation data, which includes static data and dynamic data; static data includes urban infrastructure information and historical operation records; dynamic data includes real-time traffic flow, environmental monitoring data and crowd behavior trajectory; the collected data is uploaded to the data preprocessing module through a unified interface; Data preprocessing module: used to receive multi-source heterogeneous data transmitted by the data acquisition module, and perform format conversion, missing value filling, outlier removal and data normalization to generate a standardized data set; Spatiotemporal data aggregation module: Based on the standardized data set output by the data preprocessing module, the spatiotemporal association mechanism is used to aggregate the data according to the specified time window and spatial unit to generate an aggregated data set with spatiotemporal characteristics; The spatiotemporal data aggregation module includes a time window processing unit, a space unit division unit, a spatiotemporal correlation calculation unit and an aggregation result generation unit; wherein: Time window processing unit: used to aggregate the standardized data set output by the data preprocessing module in segments according to the time dimension according to the preset time window parameters; and calculate the statistical characteristic values ​​of each time window, including the average value, maximum value, minimum value and change trend, to generate a time window labeled data set; Spatial unit division unit: used to allocate the time window marked data set to the corresponding spatial unit according to the geographic spatial position according to the preset spatial division rule; A spatiotemporal correlation calculation unit is used to combine the output data of the time window processing unit and the space unit division unit, and perform calculations based on a spatiotemporal correlation model; the spatiotemporal correlation model includes a time series analysis algorithm and a geographic space clustering algorithm, and is used to calculate the similarity between spatial units in different time windows, and identify the association relationship between multiple spatial units in the same time window, as well as the dynamic changes of the same spatial unit in different time windows, and generate a spatiotemporal correlation matrix; Aggregation result generation unit: used to integrate the output results of the spatiotemporal correlation calculation unit to generate an aggregated data set with spatiotemporal characteristics, including time window number, spatial unit identifier, statistical characteristic value and spatiotemporal correlation matrix, for use by the indicator calculation module; Index calculation module: receives the aggregated data set output by the spatiotemporal data aggregation module, and extracts the core indicators reflecting the health status of the city based on the set calculation rules, including the traffic circulation index and the environmental load index; The index calculation module includes a data analysis unit, a traffic circulation index calculation unit and an environmental load index calculation unit; wherein: Data parsing unit: receives the aggregated data set output by the spatiotemporal data aggregation module, and parses the grouping structure of the time window and spatial unit, and extracts the statistical feature value set of each spatial unit in each time window, including the average value, maximum value, minimum value and change trend; Traffic circulation index calculation unit: According to the parsed data, each space unit The traffic circulation index is calculated using the formula: ,in, is the average vehicle speed of the spatial unit in the corresponding time window; is the maximum value of vehicle speed in all spatial units; is the average vehicle flow of the spatial unit in the corresponding time window; is the maximum value of vehicle flow in all spatial units; is the traffic circulation index, with a value range of ,The larger the value, the better the traffic flow; Environmental load index calculation unit: According to the analyzed data, The environmental load is calculated and the environmental load index is set , the formula is: ,in, For space unit In the time window The average concentration of each pollutant; is the total number of pollutant types; is the pollutant exceeding standard rate, calculated as: ,in, For space unit In this time window The number of data points where the pollutant exceeds the standard; is the total number of data points; environmental load index The value range is ,The higher the value, the heavier the environmental load; Dynamic analysis module: receives the core indicators output by the indicator calculation module and predicts the future trend of the core indicators based on the time series prediction algorithm; Decision support module: Generates urban governance strategy optimization plans based on future change trend data output by the dynamic analysis module, including resource allocation optimization and emergency response plans; The decision support module includes: Data analysis unit: receives the future change trend data set output by the dynamic analysis module, and analyzes the predicted values ​​of the traffic circulation index and environmental load index of each spatial unit in the future time window; Strategy analysis unit: Analyze the traffic flow and environmental conditions in designated areas and time periods of the city based on the predicted values ​​of the traffic flow index and environmental load index, and identify the areas and times where problems occur; Strategy Generation Unit: Based on the strategy analysis unit, the unit identifies the areas and times where problems occur, and develops an optimization plan for urban governance strategies, including resource allocation adjustment suggestions and emergency response plans; The resource allocation adjustment suggestions include adjusting traffic signal control, increasing public transportation resources, planning temporary traffic control measures, and reallocating environmental monitoring resources; The emergency response plan includes temporary road closures, emergency evacuation route settings, air quality warnings, and health protection recommendations; Program output unit: Organize the generated urban governance strategy optimization plan into a structured report format, including resource allocation diagrams and emergency response flowcharts, to provide operational guidance and decision-making support for urban managers.

2. The city physical examination spatiotemporal data dynamic aggregation and decision support system according to claim 1 is characterized in that: The data acquisition module includes a sensor acquisition unit, a data docking unit and a data transmission unit; wherein: Sensor collection unit: used to collect dynamic operation data through multiple types of sensors deployed in designated areas of the city, including traffic flow sensors, air quality monitoring sensors and personnel flow monitoring sensors; among which, traffic flow sensors are used to collect real-time traffic flow data; air quality monitoring sensors are used to collect environmental monitoring data; and personnel flow monitoring sensors are used to collect crowd behavior trajectory data; Data docking unit: used to connect with external data sources through interface protocols to obtain static data; the static data includes urban infrastructure information and historical operation records; the external data sources include urban management databases and commercial data service platforms, which are specifically transmitted to the data docking unit through API interfaces; Data transmission unit: used to receive data acquired by the sensor acquisition unit and the data docking unit, and preliminarily package the data; and upload it to the data preprocessing module through a unified interface.

3. The city physical examination spatiotemporal data dynamic aggregation and decision support system according to claim 2 is characterized in that: The data preprocessing module includes a format conversion unit, a missing value processing unit, an outlier elimination unit and a data normalization unit; wherein: Format conversion unit: used to receive multi-source heterogeneous data transmitted by the data acquisition module, and convert the data into a unified structured format according to the source type and format characteristics of the data; the data collected by the sensor is arranged into a table structure according to the timestamp, and the static data obtained by the external interface is parsed into JSON format according to the preset template; Missing value processing unit: used to identify missing values ​​in the output data of the format conversion unit, and fill them with interpolation or default values ​​according to the data type; for time series data, linear interpolation method is used to fill missing values; for categorical data, historical mean or preset constant is used to fill missing values; Outlier elimination unit: used to detect and eliminate outliers in the original data through a set threshold range; the threshold range is set based on historical statistical data, and data exceeding the threshold range is marked as abnormal and eliminated; Data normalization unit: used to normalize the data output by the missing value processing unit and the outlier removal unit to eliminate the dimensional differences of different data sources; specifically, the Min-Max normalization method is adopted, and the normalized values ​​are standardized to the range of [0, 1].

4. The city physical examination spatiotemporal data dynamic aggregation and decision support system according to claim 1 is characterized in that: The time window processing unit specifically includes: Time window division: First receive the standardized data set output by the data preprocessing module, and divide it into and preset time window parameters The data is segmented by time dimension; the time window division rule formula is: window number ,in, Indicates the timestamp of the data record; is the earliest timestamp in the data set; is the time window length; is the window number. After segmentation, each data point belongs to a unique window. ; Data grouping: by window number Group the standardized data set, each group of data corresponds to a time window , the timestamp of this group of data meets the following conditions: ; Statistical eigenvalue calculation: For each time window Calculate the statistical characteristics of the data, including the mean value , maximum value , minimum and changing trends ; Generate a time window labeled dataset: Each time window The statistical feature values ​​of are integrated into a time window marked data set; the time window marked data set includes the following fields: ,in and Represents the time window The start and end time.

5. The city physical examination spatiotemporal data dynamic aggregation and decision support system according to claim 4 is characterized in that: The space unit division unit specifically includes: Preset spatial division rules: According to the coverage of the urban geographical area, the urban area is divided into several spatial units using a regular grid division method; the boundary of each spatial unit is determined by the longitude range. and latitude range OK; set the spatial unit number to , and are allocated according to the following rules: ,in, Represents the index of the spatial unit in the longitude direction; Represents the index of the spatial unit in the latitude direction; and is the longitude boundary of the spatial unit; and is the latitude boundary of the spatial unit; Spatial unit division calculation: total longitude range of urban area and latitude range The boundary length of each space unit is determined according to the grid division rules. The formula is: and ,in, and is the number of grid divisions in longitude and latitude; and are the longitude and latitude lengths of each spatial unit respectively; the longitude and latitude boundaries of each spatial unit are calculated as: and ; and ; Data is assigned to spatial units: Each data record in the dataset is labeled in the time window according to its geographic location coordinates Determine the spatial unit to which it belongs , the judgment conditions are: Condition 1, ; Condition 2, ; If both of the above conditions are met, the record is assigned to the spatial unit , and add the corresponding unit number.

6. The city physical examination spatiotemporal data dynamic aggregation and decision support system according to claim 5 is characterized in that: The spatiotemporal correlation calculation unit comprises: Similarity calculation between spatial units in different time windows: First, extract the characteristic value set of each spatial unit in each time window from the output data of the time window processing unit and the spatial unit division unit, including the average value, maximum value, minimum value and change trend; then use the difference in the characteristic values ​​between spatial units to calculate the similarity between spatial units; and normalize the similarity values ​​to generate a similarity matrix reflecting the similarity between spatial units; Calculation of association relationships of spatial units in the same time window: Based on the similarity matrix generated in the time window and the geographical location of the spatial units, the association relationships between spatial units are identified through the geospatial clustering algorithm to generate an association relationship matrix; Dynamic change analysis of the same spatial unit in different time windows: Perform time series analysis on the changes of the characteristic values ​​of each spatial unit in multiple time windows, calculate the change rate between each time window, so as to capture the dynamic change characteristics of a single spatial unit in different time periods; and organize the analysis results into a dynamic change matrix; Output spatiotemporal correlation matrix: Integrate the correlation relationship matrix and dynamic change matrix in different time windows into a unified spatiotemporal correlation matrix.

7. The city physical examination spatiotemporal data dynamic aggregation and decision support system according to claim 1 is characterized in that: The dynamic analysis module includes a data preparation unit, a feature extraction unit, a time series modeling unit and a result generation unit; wherein: Data preparation unit: receives the core indicator data output by the indicator calculation module, including the traffic circulation index and environmental load index of each time window and space unit, sorts the data according to the time window, and organizes the core indicator data of each space unit into time series data; Feature extraction unit: used to extract trend features from time series data to characterize the changing rules of core indicators in the time dimension; the extracted trend features include mean change rate, fluctuation amplitude and periodicity characteristics; Time series modeling unit: Based on the extracted trend features, the time series prediction algorithm is used to model the future change trend of the core indicators, and the predicted values ​​of the core indicators in the future time window are output; Result generation unit: associates the prediction result of the time series modeling unit with the spatial unit number and the time window number, and generates a future change trend data set containing the predicted values ​​of the traffic circulation index and the environmental load index in the future time window; the future change trend data set includes the spatial unit number, the time window number, the predicted value of the traffic circulation index in the future time window, and the predicted value of the environmental load index in the future time window.

Images