A grassroots governance data analysis method and system based on cloud computing

Abstract

The present invention relates to the field of grassroots governance data analysis technology, specifically a grassroots governance data analysis method and system based on cloud computing, comprising the following steps: based on the spatiotemporal distribution characteristics of event reporting data, calculating the number of events, change rate and abnormal value ratio within the grid, performing weight calculation and comparing with dynamic thresholds, marking key grids according to event change fluctuations, and generating adaptive grid structure values. In the present invention, by combining spatial adjacency weight calculation, the potential spatial correlation characteristics between grids are captured, regional collaborative analysis of data is optimized, trend changes and spatial data are coupled, the accuracy of spatiotemporal data prediction is improved, and abnormal change areas are effectively located. In the dynamic monitoring process of governance hotspot areas, abnormal areas of policy implementation are timely marked through data fluctuation and policy progress deviation analysis, governance effect evaluation and precise resource allocation are strengthened, and governance weaknesses are addressed.

Description

Technical Field

[0001] The present invention relates to the technical field of grassroots governance data analysis, and in particular to a grassroots governance data analysis method and system based on cloud computing. Background Art

[0002] The field of grassroots governance data analysis technology refers to the use of modern information technology to collect, store, process, and analyze the large amounts of data generated in grassroots governance to support scientific decision-making and efficient management of grassroots affairs by government departments, social organizations, and communities. This technology field includes big data technologies, cloud computing, artificial intelligence, and visualization tools. By comprehensively mining and analyzing data related to grassroots social governance, it provides data-driven decision-making support, improves the efficiency of resource allocation, and promotes the intelligent, precise, and modern development of grassroots governance. Application scenarios in this technology field cover urban management, community services, public security, people's livelihood services, emergency management, and other aspects, aiming to achieve scientific governance and efficient operation of grassroots affairs.

[0003] The cloud computing-based grassroots governance data analysis method leverages the powerful data processing capabilities of cloud computing platforms to analyze and mine the massive amounts of data collected during grassroots governance, generating actionable governance insights and decision-making basis. This method primarily leverages the real-time analysis and processing capabilities of cloud computing to improve the storage, management, sharing, and application efficiency of grassroots governance data, providing precise decision-making support for grassroots governance, optimizing grassroots social governance models, and enhancing overall governance effectiveness.

[0004] Existing technologies for identifying anomalies often rely on static thresholds, making them difficult to adapt to dynamic data changes and resulting in distorted identification of key areas. The lack of spatial correlation calculations between regions prevents data analysis from fully reflecting regional interactions and ignores potential anomaly propagation paths. In terms of dynamic monitoring of governance hotspots, data trends and regional collaboration are not coupled, resulting in a crude assessment of policy implementation effectiveness, making it impossible to accurately locate areas of governance deviation. Resource allocation is prone to misjudgment, reducing overall governance efficiency. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the existing technology and propose a grassroots governance data analysis method and system based on cloud computing.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a cloud computing-based grassroots governance data analysis method, comprising the following steps:

[0007] S1: Based on the spatiotemporal distribution characteristics of event reporting data, the number of events, change rate, and outlier ratio within the grid are calculated, weighted and compared with dynamic thresholds. Key grids are marked according to event fluctuations, and adaptive grid structure values ​​are generated.

[0008] S2: Based on demographic data and regional resource allocation data, define the spatial adjacency relationship between multiple grids, calculate the spatial association weights between the grid and the adjacent grids, summarize the spatial correlation between differentiated grids, and generate the neighborhood spatial weight matrix value;

[0009] S3: Based on the adaptive grid structure value, extract the community anomaly monitoring data of differentiated time periods within the grid, calculate the trend change of the monitoring data, couple the trend characteristics with the neighborhood spatial weight matrix value, obtain the spatial regression coefficient and the time trend term, and generate the spatiotemporal autoregressive prediction value;

[0010] S4: Based on the spatiotemporal autoregressive prediction value, calculate the change trend of the hotspot area data in each grid, overlay the result with the spatiotemporal regression parameters of the adjacent grids for analysis, identify the area of ​​abnormal governance change, and generate dynamic monitoring values ​​for the hotspot area;

[0011] S5: Based on the dynamic monitoring value of the hotspot area and combined with the threshold parameters in the policy implementation progress, the data fluctuations and policy progress deviations in the hotspot area are analyzed, the policy implementation abnormal areas are marked, and the hotspot area evolution evaluation value is generated.

[0012] The adaptive grid structure values ​​include the number of events, change rate, outlier ratio, dynamic threshold, and key grid mark. The neighborhood space weight matrix values ​​include demographic data association weights, regional resource allocation association weights, spatial adjacency relationship weights, and differentiated grid spatial correlation. The spatiotemporal autoregressive prediction values ​​include spatial regression coefficients, time trend items, and trend changes in community abnormal monitoring data. The hot spot area dynamic monitoring values ​​include governance hot spot area data change trends, neighboring grid spatiotemporal regression parameter analysis results, and governance abnormal change area identification results. The hot spot area evolution assessment values ​​include hot spot area data fluctuations, policy progress deviations, and policy implementation abnormal area marks.

[0013] As a further solution of the present invention, the step of obtaining the adaptive grid structure value is specifically as follows:

[0014] S111: Based on the spatiotemporal distribution characteristics of the event reporting data, the number of events per unit time in the grid is calculated, and the event change rate of multiple grids is calculated by comparing the difference in the number of events in adjacent time periods, thereby generating event change rate data;

[0015] S112: Statistically analyzing the event change rate data, calculating the average value and standard deviation thereof, and identifying grids whose change rate exceeds twice the standard deviation by setting a threshold value to obtain abnormal grid data;

[0016] S113: Comprehensively use the abnormal grid data and assign differentiated weights according to the number of events and the degree of abnormality in the grid, using the weighted formula:

[0017] ;

[0018] Calculate the tag value of the key grid and generate the key grid tag;

[0019] in, represents the event change rate of grid i, represents the weight of grid i, Indicates the tag value of the key grid;

[0020] S114: comparing the key grid mark with a set dynamic threshold to determine whether to adjust the grid structure and obtain an adaptive grid structure value.

[0021] As a further solution of the present invention, the steps for obtaining the neighborhood space weight matrix value are specifically as follows:

[0022] S211: Based on demographic data and regional resource allocation data, define the spatial adjacency relationship between multiple grids, and generate spatial adjacency data by calculating the geographical distance and population density difference between each grid and its adjacent grids;

[0023] S212: Using the spatial adjacency data, evaluating the spatial correlation between grids, applying a weighted method with reference to the influence of population density and resource allocation, calculating the spatial correlation weight between grids, and obtaining spatial correlation weight data;

[0024] S213: Calculate the differential impact of each grid and its adjacent grids using the entropy method based on the spatial association weight data, using the formula:

[0025] ;

[0026] Generate neighborhood spatial weight matrix values;

[0027] in, represents the resource allocation score of grid i, reflecting the resource allocation level of the grid, represents the resource allocation score of grid j, which also reflects the resource allocation level of the grid. is the geographical distance between grid i and grid j, and the denominator is increased by To reduce the impact of geographical distance on weights and avoid division by zero, Represents the absolute difference in resource allocation scores between grids.

[0028] As a further solution of the present invention, the step of obtaining the spatiotemporal autoregressive prediction value is specifically as follows:

[0029] S311: extracting community anomaly monitoring data of differentiated time periods within the grid based on the adaptive grid structure value, determining the difference in monitoring data within each grid by time period segmentation, and generating a trend of community anomaly monitoring data;

[0030] S312: Calculate the trend change of the monitoring data in the time series by using the trend of the community abnormal monitoring data, analyze the change amplitude between time points, summarize the trend change characteristics, and generate the time trend characteristics of the monitoring data;

[0031] S313: Combine the time trend characteristics of the monitoring data and the neighborhood space weight matrix value to perform a coupling operation, and use the formula:

[0032] ;

[0033] Calculate spatial regression coefficients and time trend terms to generate spatiotemporal autoregressive prediction values;

[0034] in, represents the spatiotemporal autoregressive coefficient, represents the spatial weight from the i-th grid to the j-th grid, represents the time difference weight from the i-th time point to the j-th time point, represents the time trend coefficient at time point t, represents the observation value at time point t, represents the number of samples or the total number of data points, Represents the number of time points in time series data.

[0035] As a further solution of the present invention, the step of obtaining the dynamic monitoring value of the hotspot area is specifically as follows:

[0036] S411: extracting the governance hotspot data within each grid based on the spatiotemporal autoregressive prediction value, calculating the change trend of the hotspot data within the grid by segmenting the time series of the hotspot data, and generating a change trend result of the governance hotspot data;

[0037] S412: Using the change trend results of the hotspot area data, overlay analysis is performed with the spatiotemporal regression parameters of adjacent grids. By dynamically adjusting the spatiotemporal correlation weights between grids, the area of ​​abnormal governance change is identified using the formula:

[0038] ;

[0039] Calculate the degree of abnormal governance change and generate identification results of abnormal governance change areas;

[0040] in, Representative Grid and grid The value of the degree of abnormal change in governance, Represents the change trend value of the governance hotspot area data of grid i, reflecting the dynamic changes of the governance activities of grid i within the target time. Represents the change trend value of the governance hotspot area data of grid j, reflecting the dynamic changes of the governance activities of grid j within the same time range. Indicates the absolute difference in the hotspot area data change trend between the two grids. is the spatiotemporal regression parameter value of grid i and grid j, is the sum of the spatiotemporal regression parameters of grid i and all adjacent grids;

[0041] S413: Combined with the identification results of the abnormal change areas, dynamic monitoring of the hotspot area data and the neighborhood space weight matrix values ​​is performed, and the dynamic monitoring values ​​of the hotspot area are combined with the superimposed spatiotemporal regression parameters to generate dynamic monitoring values ​​of the hotspot area.

[0042] As a further solution of the present invention, the step of obtaining the hotspot area evolution evaluation value is specifically as follows:

[0043] S511: Based on the dynamic monitoring value of the hotspot area and in combination with the threshold parameters in the policy implementation progress, the fluctuation of the data in the hotspot area is analyzed, and the change trend and fluctuation standard within the threshold range are referred to to generate the hotspot area data fluctuation analysis results;

[0044] S512: Calculate the policy progress deviation using the hotspot area data fluctuation analysis results, determine the degree of abnormality in policy implementation by comparing the deviation between the actual data and the expected threshold, and generate a policy progress deviation analysis result;

[0045] S513: Superimpose the policy progress deviation analysis results with the data fluctuations of the adjacent grids for analysis using the formula:

[0046] ;

[0047] Evaluate policy implementation within multiple grid regions, mark areas with policy implementation anomalies, and generate hotspot area evolution assessments;

[0048] in, Indicates the policy implementation abnormality mark value of grid i and grid j, Represents the data fluctuation value of grid i, represents the data fluctuation value of grid j, Indicates the data fluctuation difference between the two grids, represents the policy deviation value of grid i, represents the policy deviation value of grid j, The common threshold parameter representing the policy progress between grids i and j is used to measure the synchronization of policy implementation.

[0049] A cloud computing-based grassroots governance data analysis system, which is used to execute the above-mentioned cloud computing-based grassroots governance data analysis method, includes:

[0050] The event grid marking module obtains the number of events and the rate of change in each grid based on the temporal and spatial distribution of event reporting data. It compares them item by item through weight calculation and dynamic threshold, marks key grids and generates adaptive grid structure values.

[0051] The spatial association weight calculation module defines the spatial adjacency relationship of multiple grids based on demographic data and regional resource allocation data, marks the area in combination with the adaptive grid structure value, summarizes the grid spatial association and generates the neighborhood spatial weight matrix value through the adjacency relationship and event distribution weight calculation.

[0052] The spatiotemporal autoregressive prediction module extracts the monitoring data of differentiated time periods within the grid based on the adaptive grid structure value, calculates the data trend and couples it with the neighborhood space weight matrix value, superimposes the data results of multiple time periods and generates spatiotemporal autoregressive prediction values.

[0053] The policy implementation dynamic assessment module calculates the changing trend of the governance hotspot area data based on the spatiotemporal autoregressive prediction value, superimposes the trend result with the spatial regression parameter of the adjacent grid, determines the deviation of policy implementation and generates the hotspot area evolution assessment value.

[0054] Compared with the prior art, the advantages and positive effects of the present invention are:

[0055] In this invention, by calculating the spatiotemporal distribution of event data and identifying outliers, key grids are accurately marked, enhancing the adaptive recognition capability of changes in event distribution. Combined with the calculation of spatial adjacency weights, the potential spatial correlation characteristics between grids are captured, optimizing regional collaborative analysis of data. Trend changes are coupled with spatial data to improve the accuracy of spatiotemporal data predictions and effectively locate areas of abnormal changes. During the dynamic monitoring of governance hotspots, through analysis of data fluctuations and policy progress deviations, abnormal areas of policy implementation are promptly marked, governance effect evaluation and precise resource allocation are strengthened, addressing governance weaknesses. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0057] Figure 2 Flowchart of the steps for obtaining the adaptive grid structure value of the present invention;

[0058] Figure 3 Flowchart of the steps for obtaining the neighborhood space weight matrix value of the present invention;

[0059] Figure 4 This is a flow chart of the steps for obtaining spatiotemporal autoregressive prediction values ​​of the present invention;

[0060] Figure 5 This is a flow chart of the steps for obtaining the dynamic monitoring value of the hotspot area of ​​the present invention;

[0061] Figure 6 Flowchart of the steps for obtaining the hotspot area evolution evaluation value of the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0063] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined. Example

[0064] See also Figure 1 The present invention provides a technical solution: a grassroots governance data analysis method based on cloud computing, comprising the following steps:

[0065] S1: Based on the spatiotemporal distribution characteristics of event reporting data, the number of events, change rate, and outlier ratio within the grid are calculated, weighted and compared with dynamic thresholds. Key grids are marked according to event fluctuations, and adaptive grid structure values ​​are generated.

[0066] S2: Based on demographic data and regional resource allocation data, define the spatial adjacency relationship between multiple grids, calculate the spatial association weights between the grid and the adjacent grids, summarize the spatial correlation between differentiated grids, and generate the neighborhood spatial weight matrix value;

[0067] S3: Based on the adaptive grid structure value, extract the community anomaly monitoring data of different time periods within the grid, calculate the trend change of the monitoring data, couple the trend characteristics with the neighborhood spatial weight matrix value, obtain the spatial regression coefficient and time trend term, and generate the spatiotemporal autoregressive prediction value;

[0068] S4: Based on the spatiotemporal autoregressive prediction value, calculate the change trend of the governance hotspot area data in each grid, overlay the results with the spatiotemporal regression parameters of the adjacent grids for analysis, identify the areas of abnormal governance changes, and generate dynamic monitoring values ​​for the hotspot areas;

[0069] S5: Based on the dynamic monitoring values ​​of hotspot areas and combined with the threshold parameters in the policy implementation progress, analyze the data fluctuations and policy progress deviations in hotspot areas, mark abnormal policy implementation areas, and generate hotspot area evolution assessment values.

[0070] The adaptive grid structure values ​​include the number of events, change rate, proportion of outliers, dynamic thresholds, and key grid markers. The neighborhood space weight matrix values ​​include the demographic data association weights, regional resource allocation association weights, spatial adjacency relationship weights, and differentiated grid spatial correlations. The spatiotemporal autoregressive prediction values ​​include the spatial regression coefficients, time trend items, and trend changes in community abnormal monitoring data. The dynamic monitoring values ​​of hotspot areas include the data change trends of governance hotspot areas, the analysis results of the spatiotemporal regression parameters of neighboring grids, and the identification results of governance abnormal change areas. The hotspot area evolution assessment values ​​include the data fluctuations in hotspot areas, the deviations in policy progress, and the marking of abnormal policy implementation areas.

[0071] See also Figure 2 , the specific steps for obtaining the adaptive grid structure value are:

[0072] S111: Based on the spatiotemporal distribution characteristics of the event reporting data, the number of events per unit time in the grid is calculated, and the event change rate of multiple grids is calculated by comparing the difference in the number of events in adjacent time periods, thereby generating event change rate data;

[0073] This process involves the collection and preliminary processing of raw event data. First, the integrity and accuracy of the data must be ensured. Then, events are sorted according to timestamps to calculate the changes between adjacent time periods. For each grid, its event change rate needs to be calculated independently. This ratio reflects the increase or decrease in event activity within the time period and is the basis for subsequent steps to determine abnormal grids. The data obtained is the event change rate data, which provides the basis for the next step of analysis.

[0074] S112: Statistically analyze the event change rate data, calculate its average value and standard deviation, and identify grids whose change rate exceeds twice the standard deviation by setting a threshold to obtain abnormal grid data;

[0075] In-depth statistical analysis of the event change rate data, including the calculation of the mean and standard deviation, requires not only a comprehensive understanding of the distribution of the event change rate, but also a normality test of the data to ensure the effectiveness of the subsequent application of the standard deviation for anomaly detection. By setting a threshold, grids with a change rate exceeding twice the standard deviation can be identified. This process requires high requirements for data sensitivity and the ability to identify outliers to ensure accurate calibration of abnormal grids. The result is abnormal grid data, which lays the foundation for further analysis.

[0076] S113: Comprehensively use abnormal grid data and assign differentiated weights based on the number of events and the degree of abnormality within the grid, using the weighted formula:

[0077] ;

[0078] Calculate the tag value of the key grid and generate the key grid tag;

[0079] in, represents the event change rate of grid i, represents the weight of grid i, Indicates the tag value of the key grid;

[0080] formula:

[0081] ;

[0082] The benefits of the formula lie in that it reflects the cumulative impact of abnormal events in each grid through weight adjustment, emphasizes the importance of outliers to the overall grid structure score, effectively integrates the event change rate and the influence of the grid, and improves the accuracy and practicality of key grid markings.

[0083] Detailed explanation of the formula and the process of formula calculation and derivation:

[0084] Set the event change rate of grid i to , indicating a 5% growth rate, the weight of the grid , reflecting its importance in the overall network. If there are five grids, the and The values ​​are given as above and calculated:

[0085] ;

[0086] ;

[0087] ;

[0088] The results show that the calculated key grid marker value is 0.053, which represents the average event change rate of the entire grid system after weighted averaging. This result can be used to compare with the preset threshold to determine whether the grid structure needs to be adjusted.

[0089] S114: Compare the key grid mark with the set dynamic threshold to determine whether to adjust the grid structure and obtain an adaptive grid structure value.

[0090] Based on key grid markers, a comparison is made with a dynamic threshold. This threshold is set based on previous data and expected safety standards. The comparison process involves not only a simple comparison of values, but also needs to consider the volatility of grid marker values ​​and the possible error range. This requires a high degree of flexibility and adaptability in threshold setting to ensure that it can truly reflect changes in grid status and generate an adaptive grid structure value. This value will guide subsequent grid adjustment and optimization strategies to adapt to the actual event distribution and dynamic changes.

[0091] See also Figure 3 , the steps for obtaining the neighborhood space weight matrix value are as follows:

[0092] S211: Based on demographic data and regional resource allocation data, define the spatial adjacency relationship between multiple grids, and generate spatial adjacency data by calculating the geographical distance and population density difference between each grid and its adjacent grids;

[0093] This process requires detailed geographic information system data processing and demographic data analysis. First, the geographic information of the area, including topography, land use, and existing infrastructure layout, is imported through GIS software. Then, combined with census data, these data include but are not limited to the age distribution of residents, economic income level, housing conditions, etc. These data are aggregated and analyzed through advanced data processing tools to ensure that the population density and resource allocation of each grid can be accurately mapped. Spatial analysis tools are used to calculate the geographic distance between grids. Taking into account the accessibility and connectivity between different grids, these distance data are based not only on actual geographic paths, but also on the development of transportation networks. The spatial adjacency relationship data of the grids is generated. This data is generated based on the straight-line distance measurement from each grid center point to the center points of other grids, and the grid boundaries are adjusted to ensure that the data of each grid reflects its spatial location and the actual status of population resources.

[0094] S212: Using spatial adjacency data, evaluate the spatial correlation between grids, apply a weighted approach and refer to the impact of population density and resource allocation to calculate the spatial correlation weight between grids and obtain spatial correlation weight data;

[0095] It is necessary to combine spatial adjacency data with resource allocation data in the grid, which includes public facilities, educational resources, medical resources, etc. Each resource is weighted according to its direct impact on the quality of life of residents. Resource data comes from government departments and public records. The resource index is calculated using advanced statistical software. The resource index of each grid reflects the richness of the resources in the grid. Considering the impact of population density on resource demand, grids with higher population density may require more resources to maintain quality of life. Spatial statistical methods are used to calculate the spatial association weights between grids. This calculation not only reflects the geographical proximity between grids, but also comprehensively considers the distribution of population and resources. The weight calculation formula includes considerations of distance and population resource differences. Through this method, the interaction and dependence between grids can be more accurately understood and evaluated. The obtained spatial association weight data can be directly applied to urban planning and resource allocation decision-making processes to ensure the rational allocation of resources among different grids.

[0096] S213: Based on the spatial association weight data, the entropy method is used to calculate the differential impact of each grid and its adjacent grids using the formula:

[0097] ;

[0098] Generate neighborhood spatial weight matrix values;

[0099] in, represents the resource allocation score of grid i, reflecting the resource allocation level of the grid, represents the resource allocation score of grid j, which also reflects the resource allocation level of the grid. is the geographical distance between grid i and grid j, and the denominator is increased by To reduce the impact of geographical distance on weights and avoid division by zero, Represents the absolute difference in resource allocation scores between grids.

[0100] formula:

[0101] ;

[0102] The benefit of the formula is that by introducing a comprehensive consideration of geographical distance and resource score differences, the spatial weights between grids can be measured more accurately, which helps urban planners make more reasonable decisions when considering resource allocation and development strategies.

[0103] Detailed explanation of the formula and the process of formula calculation and derivation:

[0104] Assume that the resource allocation score of grid i is =200, the resource allocation score of grid j is 150, the distance between grids i and j is 10 kilometers. Substituting these values ​​into the formula, the calculation process is as follows:

[0105] ;

[0106] ;

[0107] ;

[0108] The results show that when considering distance and resource differences, the spatial weight between grid i and grid j is 2.14, which means that the resource allocation differences between the two grids have a great impact on their spatial correlation. This weight value can be used to adjust the resource allocation and planning strategies between the two grids to ensure the rational flow and allocation of resources within the region.

[0109] See also Figure 4 , the steps for obtaining spatiotemporal autoregressive prediction values ​​are as follows:

[0110] S311: extracting community anomaly monitoring data for differentiated time periods within the grid based on the adaptive grid structure value, determining the differences in monitoring data within each grid by time period segmentation, and generating community anomaly monitoring data trends;

[0111] This process requires analyzing and comparing previous data to determine which data represents abnormal behavior. This usually involves statistical analysis, pattern recognition, and trend analysis techniques. In order to more accurately identify anomalies, judgments will be made based on the fluctuations in data within each time period and preset anomaly indicators. For example, if the data of a specific grid exceeds twice the standard deviation of the normal range in three consecutive time periods, it is considered that there is an anomaly in this time period. Through this method, anomalies that require attention can be effectively screened out from a large amount of data, thereby better monitoring and preventing community safety.

[0112] S312: Calculate the trend change of the monitoring data in the time series by using the trend of the community abnormal monitoring data, summarize the trend change characteristics by analyzing the change amplitude between time points, and generate the time trend characteristics of the monitoring data;

[0113] This involves quantitative analysis of the correlation between data points. By calculating the autoregressive coefficient and moving average coefficient of each data point, a mathematical model of the time trend can be obtained. This process requires detailed mathematical calculations and model evaluation. Time series data are fitted through statistical methods such as the least squares method to determine the main trend of the data. This analysis helps understand the dynamic changes of the data and predict future trends. This method not only improves the accuracy of the prediction, but also enhances the understanding of the possible reasons behind abnormal data.

[0114] S313: Combine the time trend characteristics of the monitoring data with the neighborhood space weight matrix value, and perform coupling operation. By comprehensively referring to the proportion of the influence of the neighborhood space weight and the time trend characteristics on the grid, the formula is used:

[0115] ;

[0116] Calculate spatial regression coefficients and time trend terms to generate spatiotemporal autoregressive prediction values;

[0117] in, represents the spatiotemporal autoregressive coefficient, represents the spatial weight from the i-th grid to the j-th grid, represents the time difference weight from the i-th time point to the j-th time point, represents the time trend coefficient at time point t, represents the observation value at time point t, represents the number of samples or the total number of data points, Represents the number of time points in time series data.

[0118] formula:

[0119] ;

[0120] The benefit of the formula is that by comprehensively considering the combined effects of spatial weights and temporal trends, it can more accurately predict and analyze the dynamic relationship between temporal and spatial changes.

[0121] Detailed explanation of the formula and the process of formula calculation and derivation:

[0122] Assume there are three spatial locations (n=3), and the data observed at three time points (T=3) are as follows:

[0123] Spatial weight : 1.0, 0.8, 0.5 (representing the spatial connection strength between adjacent grids, respectively).

[0124] Time difference weight : 0.9, 0.7, 0.3 (taking into account the approximation in time).

[0125] Time trend coefficient : 0.4, 0.6, 0.8 (reflecting the importance of each time point).

[0126] Observations : 100, 150, 200 (observation data at each time point).

[0127] The calculation process is as follows:

[0128] 1. Calculate the numerator: ;

[0129] 2. Calculate the denominator: ;

[0130] 3. Calculation : ;

[0131] The results show that the obtained spatiotemporal autoregressive coefficient is very small, which indicates that the spatiotemporal dependence between grids is low or the influence of the observations is greater than the influence of the spatiotemporal position relationship. Therefore, when making predictions, we need to pay more attention to the changing trend of the data itself rather than relying solely on the spatial or temporal weights.

[0132] See also Figure 5 ,The specific steps for obtaining the dynamic monitoring value of the hotspot area are:

[0133] S411: Extracting governance hotspot data within each grid based on spatiotemporal autoregressive prediction values, calculating the change trend of the hotspot data within the grid by segmenting the time series of the hotspot data, and generating a change trend result for the governance hotspot data;

[0134] Based on the spatiotemporal autoregressive prediction value, the data of the hotspot areas in the grid are evaluated in detail to find the trend of change. By collecting data in each time period, the changes before and after are compared one by one, and abnormal fluctuations or trends are identified, the continuity and sporadic changes of the data are analyzed. Data collection is combined with the real-time monitoring system based on the trend to ensure the accuracy and real-time nature of the data obtained. By regularly updating the data set, the accuracy and response speed of data processing are improved. After continuous monitoring, the trend of change of the data in the hotspot areas is obtained.

[0135] S412: Using the trend of the governance hotspot data, we overlay the spatial-temporal regression parameters of the adjacent grids for analysis. By dynamically adjusting the spatial-temporal correlation weights between grids, we identify areas with abnormal governance changes. The formula is:

[0136] ;

[0137] Calculate the degree of abnormal governance change and generate identification results of abnormal governance change areas;

[0138] in, Representative Grid and grid The value of the degree of abnormal change in governance, Represents the change trend value of the governance hotspot area data of grid i, reflecting the dynamic changes of the governance activities of grid i within the target time. Represents the change trend value of the governance hotspot area data of grid j, reflecting the dynamic changes of the governance activities of grid j within the same time range. Indicates the absolute difference in the hotspot area data change trend between the two grids. is the spatiotemporal regression parameter value of grid i and grid j, is the sum of the spatiotemporal regression parameters of grid i and all adjacent grids;

[0139] formula:

[0140] ;

[0141] The benefit of the formula is that it evaluates the abnormal changes between grids by integrating the differences in temporal trends and spatial regression parameters, which enhances the sensitivity and response speed to regional dynamic changes.

[0142] Detailed explanation of the formula and the process of formula calculation and derivation:

[0143] Set the hotspot area data change trend values ​​of grid i and grid j in a specific time as and , spatiotemporal regression parameters , the number of adjacent grids is , the spatiotemporal regression parameters of each adjacent grid They are , first calculate the absolute value of the difference , then calculate the sum of the parameters ;

[0144] Substitute into the formula to calculate:

[0145] ;

[0146] The results show that the degree of governance anomaly change between grid i and grid j is 8, which indicates that there are obvious dynamic changes in governance hotspot areas, which require further monitoring and intervention measures.

[0147] S413: Combined with the identification results of the abnormal change areas, dynamic monitoring of hotspot area data and neighborhood spatial weight matrix values ​​is performed, and the dynamic monitoring values ​​of the hotspot areas are combined with the superimposed spatiotemporal regression parameters to generate dynamic monitoring values ​​of the hotspot areas.

[0148] By analyzing the differences between data points and surrounding points, the identification method can be based on statistical methods or machine learning algorithms. For example, the local anomaly factor algorithm is used to detect local deviations in density. This method can effectively identify data points that are significantly different from most data. The hotspot area data and the neighborhood spatial weight matrix values ​​are dynamically monitored. Dynamic monitoring involves continuous observation and analysis of data to promptly detect any important changes in the data. Through real-time data analysis tools, patterns and trends in data streams can be monitored. The weight matrix is ​​an important tool for adjusting the mutual influence between neighbors in this process. For example, weights can be set according to the proximity of time or events, which helps to improve the accuracy of predictions and the timeliness of responses. Combining the dynamic monitoring values ​​of hotspot areas with the superimposed spatiotemporal regression parameters to generate dynamic monitoring values ​​of hotspot areas can be used to predict future trends or discover potential risk areas, which is extremely important for optimal resource allocation and risk management.

[0149] See also Figure 6 ,The steps for obtaining the hotspot area evolution evaluation value are as follows:

[0150] S511: Based on the dynamic monitoring values ​​of the hotspot area and in combination with the threshold parameters in the policy implementation progress, the fluctuation of the data in the hotspot area is analyzed. Referring to the change trend and fluctuation standard within the threshold range, the hotspot area data fluctuation analysis results are generated;

[0151] By investigating and analyzing data fluctuations within the region and evaluating changing trends within the threshold range, this includes monitoring the effectiveness of the implementation of specific policies or measures, as well as the implementation of these measures in different regions. This method can identify hot spots that require special attention. These areas may, for some reason, lead to substandard policy implementation or less-than-expected results. This analysis is of great significance for adjusting policy measures and ensuring maximum policy effectiveness.

[0152] S512: Calculate the policy progress deviation using the hotspot area data fluctuation analysis results. By comparing the deviation between the actual data and the expected threshold, determine the degree of abnormality in policy implementation and generate the policy progress deviation analysis results.

[0153] This involves comparing actual data with expected thresholds and calculating differences in policy implementation across grids or regions. This variance analysis helps identify weaknesses or problem areas in policy implementation. By measuring the size of the deviation, the specific degree of abnormality in policy implementation can be clarified, which is crucial for subsequent policy adjustments and resource reallocation, ensuring that resources can be more effectively invested in areas that need improvement or strengthening, thereby improving the overall efficiency and effectiveness of policy implementation.

[0154] S513: Superimpose the policy progress deviation analysis results with the data fluctuations of the adjacent grids and use the formula:

[0155] ;

[0156] Evaluate policy implementation within multiple grid regions, mark areas with policy implementation anomalies, and generate hotspot area evolution assessments;

[0157] in, Indicates the policy implementation abnormality mark value of grid i and grid j, Represents the data fluctuation value of grid i, represents the data fluctuation value of grid j, Indicates the data fluctuation difference between the two grids, represents the policy deviation value of grid i, represents the policy deviation value of grid j, The common threshold parameter representing the policy progress between grids i and j is used to measure the synchronization of policy implementation.

[0158] formula:;

[0159] The formula is beneficial in that it effectively identifies key anomalies in policy implementation by calculating the interplay between policy execution differences and policy progress thresholds across grids. This approach allows policymakers and implementers to understand which areas may require additional attention or policy adjustments, thereby more precisely guiding resource allocation and management decisions.

[0160] Detailed explanation of the formula and the process of formula calculation and derivation:

[0161] Assume that the data fluctuation value of grid i is and the data fluctuation value of grid j is , then the difference is Assume that the policy deviation values ​​of grids i and j are and Calculate the mean deviation and square it to get Assuming a common threshold parameter for policy progress , substituting into the formula, we get:

[0162] ;

[0163] This result indicates that there is a slight difference in policy implementation between grids i and j. Since the difference is small, it indicates that policy implementation in these two regions is relatively consistent, suggesting that the policy is implemented evenly across these regions.

[0164] A cloud computing-based grassroots governance data analysis system, which is used to execute the above-mentioned cloud computing-based grassroots governance data analysis method, includes:

[0165] The event grid marking module obtains the number of events and the rate of change in each grid based on the temporal and spatial distribution of event reporting data. It compares them item by item through weight calculation and dynamic threshold, marks key grids and generates adaptive grid structure values.

[0166] The spatial association weight calculation module defines the spatial adjacency relationship of multiple grids based on demographic data and regional resource allocation data, marks the area in combination with the adaptive grid structure value, summarizes the grid spatial association and generates the neighborhood spatial weight matrix value through the adjacency relationship and event distribution weight calculation.

[0167] The spatiotemporal autoregressive prediction module extracts monitoring data of differentiated time periods within the grid based on the adaptive grid structure value, calculates the data trend and couples it with the neighborhood spatial weight matrix value, superimposes the data results of multiple time periods and generates spatiotemporal autoregressive prediction values.

[0168] The policy implementation dynamic assessment module calculates the changing trend of governance hotspot area data based on spatiotemporal autoregressive prediction values, superimposes the trend results with the spatial regression parameters of adjacent grids, determines the deviation of policy implementation and generates hotspot area evolution assessment values.

[0169] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A cloud computing-based grassroots governance data analysis method, characterized in that: The following steps are involved: Based on the spatiotemporal distribution characteristics of event reporting data, the number of events, change rate, and outlier ratio within the grid are calculated, weighted and compared with dynamic thresholds. Key grids are marked according to event fluctuations to generate adaptive grid structure values. Based on demographic data and regional resource allocation data, the spatial adjacency relationship between multiple grids is defined, the spatial association weights between the grid and the adjacent grids are calculated, the spatial correlation between the differentiated grids is summarized, and the neighborhood spatial weight matrix value is generated; Based on the adaptive grid structure value, extract the community anomaly monitoring data of differentiated time periods within the grid, calculate the trend change of the monitoring data, couple the trend characteristics with the neighborhood spatial weight matrix value, obtain the spatial regression coefficient and the time trend term, and generate the spatiotemporal autoregressive prediction value; Based on the spatiotemporal autoregressive prediction value, the change trend of the hotspot area data in each grid is calculated, and the result is superimposed and analyzed with the spatiotemporal regression parameters of the adjacent grids to identify the area of ​​abnormal governance change and generate dynamic monitoring values ​​for the hotspot area; Based on the dynamic monitoring values ​​of the hotspot areas, combined with the threshold parameters in the policy implementation progress, the data fluctuations and policy progress deviations of the hotspot areas are analyzed, the policy implementation abnormal areas are marked, and the hotspot area evolution assessment value is generated; The steps for obtaining the hotspot area evolution evaluation value are specifically as follows: Based on the dynamic monitoring values ​​of the hotspot areas, combined with the threshold parameters in the policy implementation progress, the fluctuation of the data in the hotspot areas is analyzed, and the change trend and fluctuation standard within the threshold range are referred to to generate the hotspot area data fluctuation analysis results; Utilizing the hotspot area data fluctuation analysis results, the policy progress deviation is calculated, and by comparing the deviation between the actual data and the expected threshold, the degree of abnormality in policy implementation is determined, thereby generating a policy progress deviation analysis result; The policy progress deviation analysis results are superimposed on the data fluctuations of the adjacent grids and the formula is used: ； Evaluate policy implementation within multiple grid regions, mark areas with policy implementation anomalies, and generate hotspot area evolution assessments; in, Indicates the policy implementation abnormality mark value of grid i and grid j, Represents the data fluctuation value of grid i, represents the data fluctuation value of grid j, Indicates the data fluctuation difference between the two grids, represents the policy deviation value of grid i, represents the policy deviation value of grid j, The common threshold parameter representing the policy progress between grids i and j is used to measure the synchronization of policy implementation.

2. The cloud computing-based grassroots governance data analysis method according to claim 1 is characterized in that: The adaptive grid structure values ​​include the number of events, change rate, outlier ratio, dynamic threshold, and key grid mark. The neighborhood space weight matrix values ​​include demographic data association weights, regional resource allocation association weights, spatial adjacency relationship weights, and differentiated grid spatial correlation. The spatiotemporal autoregressive prediction values ​​include spatial regression coefficients, time trend items, and trend changes in community abnormal monitoring data. The hot spot area dynamic monitoring values ​​include governance hot spot area data change trends, neighboring grid spatiotemporal regression parameter analysis results, and governance abnormal change area identification results. The hot spot area evolution assessment values ​​include hot spot area data fluctuations, policy progress deviations, and policy implementation abnormal area marks.

3. The cloud computing-based grassroots governance data analysis method according to claim 2 is characterized in that: The steps for obtaining the adaptive grid structure value are specifically as follows: Based on the spatiotemporal distribution characteristics of event reporting data, the number of events per unit time in the grid is calculated. By comparing the difference in the number of events in adjacent time periods, the event change rate of multiple grids is calculated to generate event change rate data; Performing statistical analysis on the event change rate data, calculating its average value and standard deviation, and identifying grids whose change rate exceeds two times the standard deviation by setting a threshold, thereby obtaining abnormal grid data; The abnormal grid data is comprehensively used, and differentiated weights are assigned according to the number of events and the degree of abnormality in the grid, using the weighted formula: ； Calculate the tag value of the key grid and generate the key grid tag; in, represents the event change rate of grid i, represents the weight of grid i, Indicates the tag value of the key grid; The key grid mark is compared with a set dynamic threshold to determine whether to adjust the grid structure and obtain an adaptive grid structure value.

4. The cloud computing-based grassroots governance data analysis method according to claim 3 is characterized in that: The steps for obtaining the neighborhood space weight matrix value are specifically as follows: Based on demographic data and regional resource allocation data, the spatial adjacency relationship between multiple grids is defined. The spatial adjacency data is generated by calculating the geographical distance and population density difference between each grid and its adjacent grids. Using the spatial adjacency data, the spatial correlation between grids is evaluated, and a weighted method is applied to calculate the spatial correlation weights between grids with reference to the influence of population density and resource allocation, thereby obtaining spatial correlation weight data; According to the spatial association weight data, the differential impact of each grid and its adjacent grids is calculated using the entropy method using the formula: ； Generate neighborhood spatial weight matrix values; in, represents the resource allocation score of grid i, reflecting the resource allocation level of the grid, represents the resource allocation score of grid j, which also reflects the resource allocation level of the grid. is the geographical distance between grid i and grid j, and the denominator is increased by To reduce the impact of geographical distance on weights and avoid division by zero, Represents the absolute difference in resource allocation scores between grids.

5. The cloud computing-based grassroots governance data analysis method according to claim 4 is characterized in that: The steps for obtaining the spatiotemporal autoregressive prediction value are specifically as follows: Based on the adaptive grid structure value, extract the community abnormal monitoring data of differentiated time periods within the grid, determine the difference of monitoring data within each grid by time period segmentation, and generate the community abnormal monitoring data trend; Utilizing the trend of the community abnormal monitoring data, calculating the trend change of the monitoring data in the time series, summarizing the trend change characteristics by analyzing the change amplitude between time points, and generating the time trend characteristics of the monitoring data; Combined with the time trend characteristics of the monitoring data and the neighborhood space weight matrix value, a coupling operation is performed. By comprehensively referring to the proportion of the influence of the neighborhood space weight and the time trend characteristics on the grid, the formula is adopted: ； Calculate spatial regression coefficients and time trend terms to generate spatiotemporal autoregressive prediction values; in, represents the spatiotemporal autoregressive coefficient, represents the spatial weight from the i-th grid to the j-th grid, represents the time difference weight from the i-th time point to the j-th time point, represents the time trend coefficient at time point t, represents the observation value at time point t, The total number of data points, Represents the number of time points in time series data.

6. The cloud computing-based grassroots governance data analysis method according to claim 5 is characterized in that: The steps for obtaining the dynamic monitoring value of the hotspot area are specifically as follows: Based on the spatiotemporal autoregressive prediction value, the governance hotspot area data in each grid is extracted, and by segmenting the time series of the hotspot area data, the change trend of the hotspot area data in the grid is calculated to generate the change trend result of the governance hotspot area data; The change trend results of the governance hotspot area data are used to perform superposition analysis with the spatiotemporal regression parameters of the adjacent grids. By dynamically adjusting the spatiotemporal correlation weights between grids, the areas of abnormal governance changes are identified using the formula: ； Calculate the degree of abnormal governance change and generate identification results of abnormal governance change areas; in, Representative Grid and grid The value of the degree of abnormal change in governance, Represents the change trend value of the governance hotspot area data of grid i, reflecting the dynamic changes of the governance activities of grid i within the target time. Represents the change trend value of the governance hotspot area data of grid j, reflecting the dynamic changes of the governance activities of grid j within the same time range. Indicates the absolute difference in the hotspot area data change trend between the two grids. is the spatiotemporal regression parameter value of grid i and grid j, is the sum of the spatiotemporal regression parameters of grid i and all adjacent grids; Combined with the identification results of the abnormal change areas, the hotspot area data and the neighborhood space weight matrix values ​​are dynamically monitored, and the dynamic monitoring values ​​of the hotspot area are combined with the superimposed spatiotemporal regression parameters to generate dynamic monitoring values ​​of the hotspot area.

7. A cloud computing-based grassroots governance data analysis system, characterized by: The cloud computing-based grassroots governance data analysis method according to any one of claims 1 to 6, wherein the system comprises: The event grid marking module obtains the number of events and the rate of change in each grid based on the temporal and spatial distribution of event reporting data. It then compares each item with the dynamic threshold through weight calculation, marks key grids, and generates adaptive grid structure values. The spatial association weight calculation module defines the spatial adjacency of multiple grids based on demographic data and regional resource allocation data, marks regions with adaptive grid structure values, and summarizes the spatial association of grids and generates neighborhood spatial weight matrix values ​​through adjacency and event distribution weight calculations. The spatiotemporal autoregressive prediction module extracts monitoring data of differentiated time periods within the grid based on the adaptive grid structure value, calculates data trends and couples them with the neighborhood spatial weight matrix value, superimposes data results of multiple time periods and generates spatiotemporal autoregressive prediction values; The policy implementation dynamic assessment module calculates the changing trend of the governance hotspot area data based on the spatiotemporal autoregressive prediction value, superimposes the trend result with the spatial regression parameter of the adjacent grid, determines the deviation of policy implementation and generates the hotspot area evolution assessment value.

Images