Community multi-source data fusion analysis processing method and system

Abstract

The invention provides a community multi-source data fusion analysis processing method and system, and relates to the technical field of data fusion analysis processing, and the method comprises the steps: carrying out the region division and data collection of a community, obtaining region collection data, carrying out the extraction and combination of the region collection data, and obtaining type combination data and a type combination region; variable data analysis is carried out, and updating combination and updating deletion of the type combination area and the data are carried out according to a variable data analysis result; performing segmentation judgment on the type combination region to obtain a combination sub-region; analyzing the same preset analysis category to obtain an abnormal analysis coefficient; according to the method, the community multi-source data is classified, combined and fused, an intersection area is obtained, weight analysis and comparison of the intersection area and a non-intersection area are carried out, preliminary and final abnormal influence judgment is carried out on the intersection area according to an analysis and comparison result, classification, combination and fusion abnormal analysis of the community multi-source data is achieved, and abnormal fusion processing efficiency is improved.

Description

Technical Field

[0001] This invention proposes a method and system for fusion analysis and processing of multi-source data in communities, which relates to the field of data fusion analysis and processing technology, specifically to the field of multi-source data fusion analysis and processing technology in communities. Background Technology

[0002] Traditional community multi-source data fusion typically employs methods such as data transformation, preprocessing, or normalization, which involves a large amount of computation and consumes significant computing resources. Furthermore, it is difficult to perform multi-type regional data analysis and processing, resulting in low intelligence, inflexibility, and a relatively singular processing method, making it difficult to solve the problem of deep regional correlation. Summary of the Invention

[0003] This invention provides a method and system for multi-source data fusion analysis and processing in communities to solve the above-mentioned problems: This invention proposes a method and system for multi-source data fusion analysis and processing in communities, the method comprising: S1. Divide the community into areas and collect data, obtain regional data, extract and combine different types of data and corresponding areas from the regional data, and obtain combined data and their combined areas. S2. Obtain community variable data, perform variable data analysis, and update and delete categories, regions, and data based on the variable data analysis results. S3. Analyze and determine whether the category combination regions are adjacent, and then divide the category combination regions to obtain combination sub-regions; S4. Perform the same preset analysis category analysis on the combination data of different types of regions to obtain the anomaly analysis coefficient; S5. Obtain the intersection region of multiple types of combined regions, perform weight analysis and comparison of the intersection region and the non-intersection region, and make preliminary and final judgments on the abnormal impact of the intersection region based on the analysis and comparison results.

[0004] Furthermore, the system includes: The area combination module is used to divide the community into areas and collect data, obtain area collection data, extract and combine different types of collection data and corresponding areas to obtain type combination data and type combination areas. The combined update module is used to acquire community variable data, perform variable data analysis, and update and delete categories, regions, and data based on the variable data analysis results. The segmentation and determination module is used to analyze and determine whether the category combination regions are adjacent, and then segment the category combination regions to obtain combination sub-regions; The anomaly analysis module is used to perform the same preset analysis category analysis on the combination data of different types of regions to obtain anomaly analysis coefficients; The region comparison module is used to obtain the intersection region of multiple types of combined regions, perform weight analysis and comparison of the intersection region and the non-intersection region, and make preliminary and final judgments on the abnormal impact of the intersection region based on the analysis and comparison results.

[0005] The beneficial effects of this invention are as follows: The technical solution of this invention enables accurate acquisition and independent data analysis of each area within a community; it allows for the combination of data and areas of the same data collection type, further facilitating the fusion analysis of similar data and areas, reducing the complexity and data processing difficulty of fusion analysis of similar data and areas; it enables dynamic monitoring of multi-source data, and then dynamically updates the originally combined areas and data based on variable data, ensuring data up-to-dateness; by determining whether data is adjacent, it enables separate processing of non-adjacent data, ensuring targeted handling of complex situations and avoiding the inability of a single processing method to cope with other complex situations; it enables the fusion analysis of data from multiple different data sources and corresponding areas, reducing fusion complexity and computational load, and improving the efficiency of data fusion analysis processing; through comparative analysis of intersecting and non-intersecting areas, it enables the determination of the influence of intersecting areas on non-intersecting areas, further identifying the important influencing areas of the community. Attached Figure Description

[0006] Figure 1 This is a schematic diagram of a method for fusion analysis and processing of multi-source data in a community. Detailed Implementation

[0007] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0008] In one embodiment of the present invention, a method and system for community multi-source data fusion analysis and processing is proposed, the method comprising: S1. Divide the community into regions and collect data to obtain regional data. Extract and combine different types of regional data and corresponding regions to obtain combined data and their respective regions. Achieve independent analysis of regional data of the same type through regional division, data collection, data extraction and combination.

[0009] S2. Obtain community variable data, perform variable data analysis, and update and delete category combination areas and data based on the variable data analysis results; achieve dynamic updating of category combination areas based on community changes through change data analysis and update combination deletion.

[0010] S3. Analyze and determine whether the category combination regions are adjacent, and then divide the category combination regions to obtain combination sub-regions; achieve independent analysis of multiple regions of the category combination regions through the division of category combination regions.

[0011] S4. Perform the same preset analysis category analysis on the combination data of different type combination areas to obtain the anomaly analysis coefficient; realize the anomaly linkage analysis of multiple type combination areas by analyzing the same preset analysis category of different type combination areas.

[0012] S5. Obtain the intersection region of multiple type combination regions, perform weight analysis and comparison of the intersection and non-intersection regions, and make preliminary and final anomaly judgments on the intersection region based on the analysis and comparison results. Figure 1 As shown, the analysis of intersection and non-intersection was used to achieve the linkage analysis of abnormal impacts in community areas.

[0013] The working principle and technical effect of the above technical solution are as follows: the community is divided into areas and data is collected, and regional data is obtained, which realizes accurate data acquisition and independent data analysis for each area of ​​the community; The system extracts and combines different types of collected data and corresponding regions to obtain combined data and their corresponding regions. It also enables the combination of data and regions of the same type of data collection, further facilitating the fusion analysis of data and regions of the same type and reducing the complexity and data processing difficulty of fusion analysis of data and regions of the same type. The system acquires community variable data, performs variable data analysis, and updates and deletes categories, regions, and data based on the analysis results. It enables dynamic monitoring of multi-source data and dynamically updates the original combinations of regions and data based on variable data, ensuring the up-to-dateness of the data.

[0014] The system analyzes and determines whether the categories of combined regions are adjacent, and then segments the categories of combined regions to obtain combined sub-regions. By determining whether they are adjacent, the system can process non-adjacent data separately, ensuring targeted handling of complex cases and avoiding the inability of a single processing method to cope with other complex situations. The system performs analysis on the same preset analysis category on the combination data of different types of regions to obtain anomaly analysis coefficients; it realizes the fusion analysis of data from multiple different data sources and corresponding regions, reducing the fusion complexity and computational load, and improving the efficiency of data fusion analysis and processing; The system identifies the intersection of multiple types of combined regions, performs weight analysis and comparison of the intersection and non-intersection regions, and makes preliminary and final judgments on the abnormal impact of the intersection regions based on the analysis and comparison results. Through comparative analysis of the intersection and non-intersection regions, the system determines the influence of the intersection regions on the non-intersection regions, further identifying the important influence areas of the community.

[0015] All preset thresholds in this application are set by those in the art based on historical experience data.

[0016] In one embodiment of the present invention, S1 includes: The community is divided into N*N regions, and regional data is collected for each region to obtain regional data; regional independent data analysis and processing are then achieved.

[0017] Data is collected from each region according to the preset data source type, and data is extracted for each preset data source type to obtain the type of collected data for each region; thus enabling independent data analysis for each region.

[0018] Data on all categories and their corresponding regions are collected, extracted, and combined to obtain category combination data and category combination regions. This enables analysis of combinations of regions of the same category.

[0019] The working principle and technical effect of the above technical solution are as follows: the community is divided into N*N areas, and regional data is collected for each area to obtain regional data; N is greater than 1 and is a positive integer; independent and accurate data collection for each area of ​​the community is achieved. Data is collected from each region according to preset data source types, and data is extracted for each preset data source type to obtain the type of collected data for each region. These preset data source types include air quality data, pedestrian flow data, outdoor temperature data, vehicle flow data, and energy consumption data, etc. Based on historical standards, collection thresholds are determined, including air quality thresholds, pedestrian flow thresholds, outdoor temperature thresholds, and vehicle flow data thresholds, etc. When the actual collected data is greater than the corresponding collection threshold, it is considered that type of collected data can be collected; when the actual collected data is less than or equal to the corresponding collection threshold, it is considered that type of collected data cannot be collected. This achieves the collection of multi-source data for each region, thereby enabling the analysis of various types of data for each region. The system extracts and combines data from all regions and their corresponding regions to obtain combined data and their associated regions. For example, when collecting pedestrian traffic data, it retrieves pedestrian traffic data from all regions where such data exists (when the collected data exceeds a threshold) and the regions containing this data. The regions and data are then combined separately.

[0020] By combining data, it is possible to perform combined analysis on similar regions of the same type, thereby obtaining the overall area where the accident occurred.

[0021] The above solution addresses the technical problem that existing technologies often rely on fixed data collection and regional analysis methods, making flexible data collection and analysis difficult. It enables the comprehensive collection and classification of various regional data, improving the efficiency and accuracy of individual data collection and analysis, and achieving precise identification and analysis of areas with high pedestrian and vehicle traffic and / or high outdoor temperatures.

[0022] In one embodiment of the present invention, S2 includes: Real-time data collection of community area variables is performed to obtain community variable data; this enables the monitoring of changes in the area.

[0023] The community variable data is compared with the preset community variable threshold to obtain the community variable comparison results; Trigger a regional variable analysis command based on the community variable comparison results; When the regional variable analysis command is triggered, the variables of each type of data collected in each area of ​​the community are compared with the variable thresholds to obtain regional variable comparison data; thus realizing the monitoring of regional changes. The category combination update labeling of the region is performed based on the comparison data of the regional category variables. The category combination update labeling includes category combination labeling and category deletion labeling; thereby realizing the category combination change analysis of the region. Based on category combination annotations and category deletion annotations, the system performs category combination region and data update and deletion. By using different category annotations to update the category combination regions, the system completes the update of the category combination regions.

[0024] The working principle and technical effect of the above technical solution are as follows: real-time variable collection of regional data in the community to obtain community variable data; the community variable data includes variables of each type of data collected in each area of ​​the community; and dynamic monitoring of community data collection is realized. The community variable data is compared with the preset community variable threshold to obtain the community variable comparison results; When the community variable data is greater than the preset device variable threshold, the regional variable analysis command is triggered; otherwise, it is not triggered.

[0025] The regional variable analysis command is triggered based on the comparison results of community variables; the community variable analysis can be triggered based on the comparison of community variables. When the regional variable analysis command is triggered, the variables of each type of data collected in each region of the community are compared with the variable thresholds to obtain regional variable comparison data. Based on the regional variable comparison, the regions and data can be updated according to the established rules, avoiding the waste of data processing resources caused by updating as soon as there is data, and at the same time avoiding the accumulation of variable data caused by not updating for too long, which affects the timeliness of data.

[0026] The region is updated and labeled with category combinations based on the comparison data of the region category variables. The category combination update label includes category combination label and category deletion label; the variable is the data upward variable.

[0027] When the number of regional categories exceeds the variable threshold, the region is labeled with a combination of categories. When the region category variable is less than or equal to the variable threshold, the region is marked for category deletion.

[0028] Based on category combination and category deletion annotations, the region is used for category combination, data update, and deletion. When the category variable of a region is large, it indicates that the region has changed from not needing combination to needing combination. In this case, combination analysis should be performed on the region and its corresponding data. When the category variable of a region is small, it indicates that the region has changed from needing combination to not needing combination. In this case, deletion analysis should be performed on the region and its corresponding data. If the data variable is small, it indicates that the event has not progressed further, so deletion can be performed without analysis. If analysis is required, you can choose not to delete and continue the analysis.

[0029] In one embodiment of the present invention, the step of updating and deleting category combination regions and data based on category combination labels and category deletion labels includes: When the category combination of a region is updated and labeled as a category combination label, the region and the category combination region corresponding to the category collection data are updated and combined to obtain the latest category combination region. The variables of the type data collected in the region are updated and combined with the type combination data corresponding to the type data collected to obtain the latest type combination data of the type combination region; thus realizing the addition and updating of the type combination region. When the category combination update label of a region is a category deletion label, the category combination region corresponding to the region and the category collection data is updated and deleted to obtain the latest category combination region. The variables of the type data collected in the region and the type combination data corresponding to the type data are updated and deleted to obtain the latest type combination data of the type combination region, which is used for the reduction and update of the type combination region.

[0030] The working principle and technical effect of the above technical solution are as follows: when the category combination update label of the region is the category combination label, the region and the category combination region corresponding to the category collection data are updated and combined to obtain the latest category combination region; it can realize dynamic variable combination update of the combination region; The variable data of the type collection data of the region is updated and combined with the type combination data corresponding to the type collection data to obtain the latest type combination data of the type combination region; this can realize dynamic variable combination update of the combination data. When the category combination update label of a region is a category deletion label, the category combination region corresponding to the region and the category collection data is updated and deleted to obtain the latest category combination region; update deletion refers to deleting the region and data with the category deletion label in the category combination region; it can realize dynamic variable deletion and update of the combination region; The variable data of the type collection data for a region is updated and deleted along with the corresponding type combination data to obtain the latest type combination data for that region. This allows for dynamic variable deletion and updating of the combination data. The above method solves the problems of existing technologies, such as the difficulty in combining multiple data types and regions based on variables in certain areas, and the difficulty in dynamically analyzing certain areas based on variables. It enables flexible updating and efficient processing of certain areas, closely follows data changes, and greatly enhances the accuracy and efficiency of data fusion processing.

[0031] In one embodiment of the present invention, S3 includes: Obtain the regional location relationship information for each type combination region; this information is used to perform independent regional analysis and determination of type combination regions based on their regional location relationships.

[0032] Based on the location relationship information of the regions, the adjacency of the combination regions is determined to obtain adjacency determination information; Based on the adjacency judgment information, the classification combination region is divided to determine whether it is divided, and the division judgment information of the classification combination region is obtained for the division analysis of non-adjacent regions. The category combination region is segmented according to the segmentation determination information to obtain multiple combination sub-regions of the category combination region, which are used to obtain some adjacent regions and perform independent analysis of some adjacent regions.

[0033] The working principle and technical effect of the above technical solution are as follows: analyze and determine whether the combination regions of different types are adjacent, and then divide the combination regions of different types to obtain combination sub-regions; Obtain the regional location relationship information for each type of combination area; Based on the location relationship information of the regions, the adjacency of the combination regions is determined to obtain adjacency determination information; When there are two non-adjacent regions in a category combination region, the category combination region is determined to be non-adjacent. When there are no two non-adjacent regions in a category combination region, the category combination region is determined to be adjacent. It takes into account whether regions and data of the same type are adjacent, avoiding the combination and analysis of non-adjacent regions of the same type, which would make it difficult to process and monitor scattered data of the same type. Based on the adjacency judgment information, determine whether the category combination region should be segmented, and obtain the segmentation judgment information of the category combination region; When the category combination region is determined to be non-adjacent, the category combination region is divided into non-adjacent regions. When the category combination region is determined to be adjacent, the category combination region is not divided.

[0034] It enables consideration of similar regions and adjacent data, and achieves overall data analysis and processing; The category combination region is segmented based on the segmentation determination information to obtain multiple combination sub-regions of the category combination region.

[0035] When the category combination region is used for region segmentation, the non-adjacent regions of the category combination region are segmented. When the category combination region is determined by region segmentation, the category combination region is not segmented.

[0036] It takes into account the non-adjacent nature of regions and data of the same type, avoiding the combination and analysis of non-adjacent regions of the same type, which would make it difficult to process and monitor scattered data of the same type.

[0037] In one embodiment of the present invention, S4 includes: Obtain preset analysis categories, perform category anomaly analysis on category combination data of multiple different type combination regions for each preset analysis index category, and obtain category anomaly analysis coefficients for multiple different type combination regions for each preset data source category; use this to perform anomaly analysis on regions of the same type and obtain anomaly conditions of regions of the same type.

[0038] The process of obtaining the category anomaly analysis coefficients for multiple different combinations of regions for each preset data source type includes: Calculate the category anomaly analysis coefficient for each region based on the ratio of the actual collected data to the category standard data for each region. Calculate the average of the category anomaly analysis coefficients for all regions in the category combination region to obtain the category anomaly analysis coefficients for the category combination region; Calculate the average of the category anomaly analysis coefficients for all types of combined regions to obtain the community anomaly values.

[0039] The working principle and technical effect of the above technical solution are as follows: A preset analysis category is obtained; for multiple different types of combined data regions, category anomaly analysis is performed on each preset analysis indicator category to obtain the category anomaly analysis coefficient for multiple different types of combined data regions for each preset data source type; the preset analysis category includes data anomaly category and data volume category, etc.; when updated category combination data and regions exist, the latest ones are analyzed; otherwise, the originally obtained category combination data and regions are analyzed. The data anomaly category is the ratio of actual data to standard data, and the data volume category is the ratio of actual data volume to standard data volume. The process of obtaining the category anomaly analysis coefficients for multiple different combinations of regions for each preset data source type includes: The anomaly analysis coefficient for each category is calculated based on the ratio of the actual collected data to the standard data for each category. For example, the ratio of the actual pedestrian flow to the standard pedestrian flow data for a certain area is the pedestrian flow anomaly analysis coefficient for that area. Calculate the average of the category anomaly analysis coefficients of all regions in the category combination region to obtain the category anomaly analysis coefficient of the category combination region; for example, the average of the pedestrian flow anomaly analysis coefficients of all regions in the pedestrian flow combination region is the pedestrian flow anomaly analysis coefficient of the pedestrian flow combination region. Calculate the average of the category anomaly analysis coefficients for all types of combined regions to obtain the community anomaly values.

[0040] The above method solves the problem that existing technologies cannot directly perform anomaly analysis on different types of data. It enables the fusion anomaly analysis of different types of data, improves the efficiency of fusion anomaly analysis of multiple data sources, reduces the computational load and steps of traditional data fusion analysis, and enhances the flexibility of regional anomaly analysis.

[0041] In one embodiment of the present invention, S5 includes: Obtain the common area of ​​multiple type combination regions, and define the common area as the intersection region. The multiple type combination regions are called the linkage region. The linkage region is used to perform linkage analysis on multiple type regions. Get the number of combination regions of different types in the linked region, and let it be M; When the number of category combination regions is M, the intersection region is set as an M-level region; the M-level region is used to determine the information corresponding to the intersection region.

[0042] Calculate the combined region weight value of the M-level region in each type of combined region in the linkage region, and obtain the M-level region weight value of each type of combined region in the linkage region. Obtain the non-intersecting regions from each type of combination region within the linked region, excluding the M-level region. Calculate the weight value of the non-intersecting region in the category combination region to obtain the weight value of the non-intersecting region; compare the weight value of the intersecting region with the weight value of the non-intersecting region in each category combination region to obtain the weight comparison result of the category combination region. Based on the weight comparison results, anomaly impact determination is performed on the M-level region to obtain the M-level impact determination result; Based on the segmentation determination information, an impact determination analysis is performed on the obtained independent category combination regions.

[0043] The working principle and technical effects of the above technical solution are as follows: Linkage area analysis is a key technology in fields such as data processing, image recognition, and urban planning. It can accurately locate key areas and anomalies, linkage areas and intersection areas. Linkage areas are composed of multiple types of combined areas. Through linkage analysis, the inherent relationship is discovered. Intersection areas are the common parts of these combined areas. M-level areas, where M represents the number of types of combined areas in the linkage areas, and the corresponding intersection areas are M-level areas, which are the core objects of analysis. The weight value of the M-level region in each category combination region is calculated to reflect its importance. Then, non-overlapping regions other than the M-level regions are extracted from each combination region, and their weight values ​​are calculated similarly for comparison. The two weight values ​​are then compared, and based on preset rules, it is determined whether the M-level region has any abnormal influence, thus obtaining the M-level influence determination result. Furthermore, by obtaining segmentation determination information, influence determination analysis can be carried out on independent category combination regions, improving the overall analysis system. In terms of data accuracy, it can accurately capture regional correlations and differences, reducing analysis errors. In multi-scenario applications, in addition to helping communities locate overlapping and different areas and optimize resource allocation, it can also be used in traffic control (such as identifying common areas of traffic congestion) and environmental monitoring (such as locating areas affected by overlapping multiple pollution sources). In terms of decision-making efficiency, it significantly shortens the analysis cycle, helps users quickly develop targeted solutions, and reduces decision-making costs.

[0044] In one embodiment of the present invention, the step of determining the abnormal impact of the M-level region based on the weight comparison result to obtain the M-level impact determination result includes: When the weight value of the M-level region in the category combination area is greater than the weight value of the non-intersecting region, the M-level region is determined to be a preliminary abnormal influence region. When the weight value of the M-level region in the category combination area is less than or equal to the weight value of the non-intersecting region, the M-level region is determined to be a preliminary normal influence region. Obtain the number of preliminary abnormal influence areas and the number of preliminary normal influence areas in the M-level region among the multiple types of combined regions; Compare the number of areas initially identified as having abnormal impact with the number of areas initially identified as having normal impact; When the number of preliminary abnormal impact areas is greater than the number of preliminary normal impact areas, the M-level area is determined to be the final abnormal impact area. When the number of preliminary abnormal impact areas is less than or equal to the number of preliminary normal impact areas, the M-level area is determined to be the final normal impact area.

[0045] The working principle and technical effect of the above technical solution are as follows: when the weight value of the M-level region in the category combination area is greater than the weight value of the non-intersecting region, the M-level region is determined to be the initial abnormal influence region; When the weight value of the M-level region in the category combination area is less than or equal to the weight value of the non-intersecting region, the M-level region is determined to be a preliminary normal influence region. Obtain the number of preliminary abnormal influence areas and the number of preliminary normal influence areas in the M-level region among the multiple types of combined regions; Compare the number of areas initially identified as having abnormal impact with the number of areas initially identified as having normal impact; When the number of preliminary abnormal impact areas is greater than the number of preliminary normal impact areas, the M-level area is determined to be the final abnormal impact area. When the number of preliminary abnormal impact areas is less than or equal to the number of preliminary normal impact areas, the M-level area is determined to be the final normal impact area.

[0046] The above method solves the problem that existing technologies are difficult to analyze and determine the abnormal impact of some areas on other areas of the same type, and even more difficult to analyze and determine the abnormal impact of other areas of different types. It realizes the separate analysis and determination of the same and different types of abnormal impact in some areas, takes into account the analysis of the same type of abnormal impact and the analysis of different types of abnormal impact, improves the efficiency of abnormal data fusion analysis, and simplifies the computational workload of the data analysis process.

[0047] In one embodiment of the present invention, the step of performing influence determination analysis on the obtained independent category combination regions based on segmentation determination information includes: After dividing the category combination region into regions, each combination sub-region of the category combination region is analyzed according to the same preset analysis category to obtain the sub-region anomaly analysis coefficient. Each combination group region is treated as an independent type combination region, and preliminary and final anomaly impact determinations are made for the intersection regions of the independent type combination regions. If the category combination region is not segmented, the independent category combination region is not obtained.

[0048] The working principle and technical effect of the above technical solution are as follows: After the category combination region is divided into regions, the same preset analysis category is analyzed for each combination sub-region of the category combination region to obtain the sub-region anomaly analysis coefficient; it realizes the anomaly analysis of different emission regions of the same type, and avoids the problem that it is difficult to process different emission regions separately when performing comprehensive anomaly analysis on the same type of data. Each combination group region is treated as an independent type combination region, and preliminary and final anomaly impact determinations are made for the intersection regions of the independent type combination regions. When no category combination region is segmented, independent category combination regions are not obtained. This enables anomaly analysis of the entire region of the same category, ensuring the ability to analyze large areas as a whole.

[0049] According to one embodiment of the present invention, the system includes: The area combination module is used to divide the community into areas and collect data, obtain area collection data, extract and combine different types of collection data and corresponding areas to obtain type combination data and type combination areas. The combined update module is used to acquire community variable data, perform variable data analysis, and update and delete categories, regions, and data based on the variable data analysis results. The segmentation and determination module is used to analyze and determine whether the category combination regions are adjacent, and then segment the category combination regions to obtain combination sub-regions; The anomaly analysis module is used to perform the same preset analysis category analysis on the combination data of different types of regions to obtain anomaly analysis coefficients; The region comparison module is used to obtain the intersection region of multiple types of combined regions, perform weight analysis and comparison of the intersection region and the non-intersection region, and make preliminary and final judgments on the abnormal impact of the intersection region based on the analysis and comparison results.

[0050] The working principle and technical effect of the above technical solution are as follows: the community is divided into areas and data is collected, and regional data is obtained, which realizes accurate data acquisition and independent data analysis for each area of ​​the community; The system extracts and combines different types of collected data and corresponding regions to obtain combined data and their corresponding regions. It also enables the combination of data and regions of the same type of data collection, further facilitating the fusion analysis of data and regions of the same type and reducing the complexity and data processing difficulty of fusion analysis of data and regions of the same type. The system acquires community variable data, performs variable data analysis, and updates and deletes categories, regions, and data based on the analysis results. It enables dynamic monitoring of multi-source data and dynamically updates the original combinations of regions and data based on variable data, ensuring the up-to-dateness of the data.

[0051] The system analyzes and determines whether the categories of combined regions are adjacent, and then segments the categories of combined regions to obtain combined sub-regions. By determining whether they are adjacent, the system can process non-adjacent data separately, ensuring targeted handling of complex cases and avoiding the inability of a single processing method to cope with other complex situations. The system performs analysis on the same preset analysis category on the combination data of different types of regions to obtain anomaly analysis coefficients; it realizes the fusion analysis of data from multiple different data sources and corresponding regions, reducing the fusion complexity and computational load, and improving the efficiency of data fusion analysis and processing; The system identifies the intersection of multiple types of combined regions, performs weight analysis and comparison of the intersection and non-intersection regions, and makes preliminary and final judgments on the abnormal impact of the intersection regions based on the analysis and comparison results. Through comparative analysis of the intersection and non-intersection regions, the system determines the influence of the intersection regions on the non-intersection regions, further identifying the important influence areas of the community.

[0052] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for fusion analysis and processing of multi-source community data, characterized in that, The method includes: S1. Divide the community into areas and collect data, obtain regional data, extract and combine different types of data and corresponding areas from the regional data, and obtain combined data and their combined areas. S2. Obtain community variable data, perform variable data analysis, and update and delete categories, regions, and data based on the variable data analysis results. S3. Analyze and determine whether the category combination regions are adjacent, and then divide the category combination regions to obtain combination sub-regions; S4. Perform the same preset analysis category analysis on the combination data of different types of regions to obtain the anomaly analysis coefficient; S5. Obtain the intersection region of multiple types of combined regions, perform weight analysis and comparison of the intersection region and the non-intersection region, and make preliminary and final judgments on the abnormal impact of the intersection region based on the analysis and comparison results.

2. The community multi-source data fusion analysis and processing method according to claim 1, characterized in that, S1 includes: The community is divided into N*N regions, and regional data is collected for each region to obtain regional data. Data is collected from each region according to the preset data source type, and data is extracted for each preset data source type to obtain the type of collected data for each region for each preset data source type. Collect data on all regions and their corresponding regions, extract and combine them to obtain combined data on the types and their combined regions.

3. The community multi-source data fusion analysis and processing method according to claim 1, characterized in that, S2 includes: Real-time variable collection of regional data in the community to obtain community variable data; The community variable data is compared with the preset community variable threshold to obtain the community variable comparison results; Trigger a regional variable analysis command based on the community variable comparison results; When the regional variable analysis command is triggered, the variables of each type of data collected in each region of the community are compared with the variable thresholds to obtain regional variable comparison data. The region is updated with category combination labels based on the comparison data of regional category variables. The category combination update labels include category combination labels and category deletion labels. Based on the category combination annotation and category deletion annotation, the region is used to perform category combination, data update and deletion.

4. The community multi-source data fusion analysis and processing method according to claim 3, characterized in that, The process of updating and deleting category combination regions and data based on category combination labels and category deletion labels includes: When the category combination of a region is updated and labeled as a category combination label, the region and the category combination region corresponding to the category collection data are updated and combined to obtain the latest category combination region. The variables of the type data collected in the region are updated and combined with the type combination data corresponding to the type data collected in the region to obtain the latest type combination data of the type combination region. When the category combination update label of a region is a category deletion label, the category combination region corresponding to the region and the category collection data is updated and deleted to obtain the latest category combination region. The variables in the regional category data collection data and the corresponding category combination data are updated and deleted to obtain the latest category combination data for the regional category combination.

5. The community multi-source data fusion analysis and processing method according to claim 3, characterized in that, S3 includes: Obtain the regional location relationship information for each type of combination area; Based on the location relationship information of the regions, the adjacency of the combination regions is determined to obtain adjacency determination information; Based on the adjacency judgment information, determine whether the category combination region should be segmented, and obtain the segmentation judgment information of the category combination region; The category combination region is segmented based on the segmentation determination information to obtain multiple combination sub-regions of the category combination region.

6. The method for community multi-source data fusion analysis and processing according to claim 1, characterized in that, S4 includes: Obtain the preset analysis categories, perform category anomaly analysis on the category combination data of multiple different category combination areas for each preset analysis index category, and obtain the category anomaly analysis coefficients of multiple different category combination areas for each preset data source category; The process of obtaining the category anomaly analysis coefficients for multiple different combinations of regions for each preset data source type includes: Calculate the category anomaly analysis coefficient for each region based on the ratio of the actual collected data to the category standard data for each region. Calculate the average of the category anomaly analysis coefficients for all regions in the category combination region to obtain the category anomaly analysis coefficients for the category combination region; Calculate the average of the category anomaly analysis coefficients for all types of combined regions to obtain the community anomaly values.

7. The method for community multi-source data fusion analysis and processing according to claim 1, characterized in that, S5 includes: Obtain the common area of ​​multiple type combination regions, and define the common area as the intersection region, and the multiple type combination regions as the linked region; Get the number of combination regions of different types in the linked region, and let it be M; When the number of combination regions is M, the intersection region is defined as an M-level region; Calculate the combined region weight value of the M-level region in each type of combined region in the linkage region, and obtain the M-level region weight value of each type of combined region in the linkage region. Obtain the non-intersecting regions from each type of combination region within the linked region, excluding the M-level region. Calculate the weight value of the non-intersecting region in the category combination region to obtain the weight value of the non-intersecting region; The weight values ​​of the intersection regions and the weight values ​​of the non-intersection regions in each category combination region are compared to obtain the weight comparison results of the category combination regions. Based on the weight comparison results, anomaly impact determination is performed on the M-level region to obtain the M-level impact determination result; Based on the segmentation determination information, an impact determination analysis is performed on the obtained independent category combination regions.

8. The community multi-source data fusion analysis and processing method according to claim 7, characterized in that, The step of determining the abnormal impact of the M-level region based on the weight comparison result to obtain the M-level impact determination result includes: When the weight value of the M-level region in the category combination area is greater than the weight value of the non-intersecting region, the M-level region is determined to be a preliminary abnormal influence region. When the weight value of the M-level region in the category combination area is less than or equal to the weight value of the non-intersecting region, the M-level region is determined to be a preliminary normal influence region. Obtain the number of preliminary abnormal influence areas and the number of preliminary normal influence areas in the M-level region among the multiple types of combined regions; Compare the number of areas initially identified as having abnormal impact with the number of areas initially identified as having normal impact; When the number of preliminary abnormal impact areas is greater than the number of preliminary normal impact areas, the M-level area is determined to be the final abnormal impact area. When the number of preliminary abnormal impact areas is less than or equal to the number of preliminary normal impact areas, the M-level area is determined to be the final normal impact area.

9. The method for community multi-source data fusion analysis and processing according to claim 7, characterized in that, The step of performing an influence determination analysis on the obtained independent category combination regions based on the segmentation determination information includes: After dividing the category combination region into regions, each combination sub-region of the category combination region is analyzed according to the same preset analysis category to obtain the sub-region anomaly analysis coefficient. Each combination group region is treated as an independent type combination region, and preliminary and final anomaly impact determinations are made for the intersection regions of the independent type combination regions. If the category combination region is not segmented, the independent category combination region is not obtained.

10. A community multi-source data fusion analysis and processing system, characterized in that, The system includes: The area combination module is used to divide the community into areas and collect data, obtain area collection data, extract and combine different types of collection data and corresponding areas to obtain type combination data and type combination areas. The combined update module is used to acquire community variable data, perform variable data analysis, and update and delete categories, regions, and data based on the results of the variable data analysis. The segmentation and determination module is used to analyze and determine whether the category combination regions are adjacent, and then segment the category combination regions to obtain combination sub-regions; The anomaly analysis module is used to perform the same preset analysis category analysis on the combination data of different types of regions to obtain anomaly analysis coefficients; The region comparison module is used to obtain the intersection region of multiple types of combined regions, perform weight analysis and comparison of the intersection region and the non-intersection region, and make preliminary and final judgments on the abnormal impact of the intersection region based on the analysis and comparison results.

Images