Method for intelligently managing and processing administrative division data based on ai technology

Abstract

This application provides a method for intelligent management and processing of administrative division data based on AI technology, belonging to the field of government data governance and spatial information processing. It solves the problem of asynchronous publication of administrative division codes, place names, and administrative division maps. The method includes the following steps: data reading and structure construction; field standardization and data preprocessing; determining whether the division data has been adjusted or changed, and identifying the level, type, and management category of the adjusted data, including data changes caused by level adjustments, type adjustments, management category adjustments, and sorting of divisions within the same level, type, and management category; after change identification, matching the division code data with the division map data using the relationship between different levels of division codes and division map data; this application is applied to administrative division data updates and historical tracing.

Description

Technical Field

[0001] This application relates to the fields of government data governance and spatial information processing technology, and in particular to a method for intelligent management and processing of administrative division data based on AI technology. Background Technology

[0002] Administrative division data is a crucial foundation for national governance, serving as the core shared data for the informatization of all geographic regions, industries, and departments related to geospatial information. It profoundly impacts various statistical work, government administration, and the informatization and digitalization processes of information evolution and adjustments. Furthermore, it is a vital component of data acquisition for surveying and mapping science and technology. This data provides a solid foundation for modern spatial information acquisition methods such as navigation and positioning, remote sensing information extraction, and geographic information management. Its management covers the surveying and mapping field, as well as all regions, industries, and departments involved in spatial planning.

[0003] Administrative division data is a broad concept, with its core being various related data generated around "administrative divisions." It encompasses both narrow and broad definitions. Narrowly defined, administrative division data focuses on core foundational data such as the spatial extent, hierarchical divisions, codes, place names, and historical versions of administrative regions. This is the core object for map database construction and map editing at the technical level. Broadly defined, administrative division data, in addition to this core component, includes all related data tied to administrative divisions. This includes spatially related data based on administrative division statistics, surveying and mapping data conducted in conjunction with administrative divisions, and management data linked to divisions in different systems. It is a collective term for the former and all related derived data.

[0004] In a narrow sense, administrative division data is typically acquired based on current administrative division data, published annually to form a complete data system encompassing the current version and different historical versions. The core difference between administrative division data managed by different systems lies in the mismatch between the spatial scope and hierarchical divisions of administrative divisions and the spatial scope and hierarchical divisions required for management. Specifically, data related to the spatial location, management levels, and division types of high-level administrative divisions, and data related to lower-level spatial area divisions and village management, belong to different management systems, collectively constituting the national administrative division data system.

[0005] When the spatial location, management level, and division type of administrative regions change and are adjusted, the corresponding administrative region maps need to be re-edited, the administrative region codes need to be adjusted synchronously, and the relevant place names also need to be updated accordingly. This leads to differences in the administrative region data of each version released in different years. In terms of magnitude, across the country, the number of annual administrative region adjustments and changes is much less than the number of regions without adjustments and changes. Only for the administrative regions with changes in the current year, their administrative region maps, codes, and place name data will be updated. For those without changes, the relevant data of the previous version will be used.

[0006] Currently, there is an issue of out-of-sync release among administrative region codes, place names, and administrative region maps. The core reason is the lack of annual data supply in the technical support links related to surveying and mapping. In addition, when different users use administrative region data, they often regard it as the basic platform data and tend to ignore the differences in the release years and versions of the data. This results in inconsistent versions of the basic data platforms used in different regions, industries, and departments in the national public data resources, thus affecting the promotion of national big data applications and artificial intelligence construction.

[0007] To sum up, the existing administrative region data has the following characteristics: 1. Released annually, with multiple historical versions; 2. Frequent adjustments to administrative regions; 3. There are multiple sets of rules such as administrative region codes, urban-rural classification codes, and management category codes; 4. The separation of administrative region table data and administrative region map data; 5. Require cross-departmental sharing and cross-year statistical alignment.

[0008] However, the existing statistical or coding technologies have the following deficiencies: (1) Can only process single-version data and cannot identify cross-version changes; (2) When mergers, splits, or cancellations occur, it is unable to establish stable mapping relationships; (3) Unable to identify the rearrangement of the same-level and same-category administrative region sorting; (4) Hierarchical changes and management category changes cannot be structurally recorded; (5) Historical traceability relies on manual comparison, with low efficiency; (6) The administrative region table and the administrative region map cannot be linked.

[0009] Therefore, the existing technologies cannot achieve the multi-version unified management and intelligent sharing of administrative region data. Summary of the Invention

[0010] To solve the above technical problems, this application proposes a method for the intelligent management and processing of administrative region data based on AI technology.

[0011] The technical solution adopted in this application is: a method for intelligent management and processing of administrative division data based on AI technology, comprising the following steps: Step 1: Data reading and structure construction; Step 2: Field standardization and data preprocessing; Step 3: Adjacent Version Matching and Change Identification: Compare each administrative division data in two adjacent versions to determine whether the division data has been adjusted or changed, and the level, division type, and management category of the adjusted or changed data. The types of adjustments or changes to the division data include data changes caused by level adjustments, data changes caused by division type adjustments, data changes caused by management category adjustments, and data changes caused by the same level, same division type, same management category, or division sorting. Step 4: After completing the change and adjustment identification, use the relationship between different levels of administrative division codes and administrative division map data to match the administrative division code data with the administrative division map data, re-edit the administrative division map data, and obtain administrative division maps that match different versions of administrative division data.

[0012] Further, in step 1, administrative division data from multiple years and different versions are read. Each version of the administrative division data includes at least field data and record data. The field data includes an ID number indicating the type of adjustment or change in the administrative division code, and the record data includes the administrative division level, ID number, place name, and administrative division code. After organizing the administrative division data from different versions, the version number and year of publication are added. Based on this, data tables / datasets for different versions of administrative division data are constructed using Excel format, creating a database containing all versions of administrative division data. Using AI technology and an Excel spreadsheet system, a comparison table between the different versions of data tables / datasets is created, and this comparison table... In this process, identification information indicating whether adjustments or changes have occurred is placed at the same record location as the corresponding version of the data table / dataset. By comparing the adjustment and change information recorded in the table, it reveals whether the corresponding version of the administrative division data has undergone adjustments or changes, and provides information on the year, level, type, and management category of the adjustments or changes. It also statistically analyzes the corresponding administrative divisions that have undergone adjustments or changes, their ranking by level, type, and management category, and their ID numbers in different versions of the data. Furthermore, it statistically analyzes the results of adjustments or changes in place names, level, type, and management category across different versions of the data, generating a table of administrative division data adjustments and changes for the corresponding year. This provides detailed parameters for the intelligent generation of the next version of administrative division data.

[0013] Furthermore, the field standardization process in step 2 includes unifying the naming and coding length of the administrative division codes in versions of administrative division data corresponding to different years; At the same time, hierarchical variable mapping was set up: Let the administrative division level variable be j, defined as follows: j=1: Provincial level; j=2: Prefecture-level city; j=3: County level; j=4: Township level; j=5: Village level.

[0014] Furthermore, in step 3, the principles and procedures for determining data changes caused by hierarchical adjustments are as follows: First, determine the administrative division level at which the change occurred. Then, determine the type and category of the administrative division and management category. Based on the confirmed administrative division level, type, and management category at which the change occurred, change the place name according to the place name naming rules.

[0015] Furthermore, when there is an adjustment or change in the administrative division level, the type and category of the adjusted administrative division are determined by the administrative division level variable. Based on the changes in administrative division level, type, and category, the corresponding administrative division code is adjusted or changed, including the level change details and the type of level change. The level change details are determined by a change coefficient i, where i = j new -j old j new For the changed hierarchy, j old If the level before the change is i, the rules for the value of the change coefficient are as follows: if i=0, it indicates a change at the same level; if i>0, it indicates a downgrade change; if i<0, it indicates an upgrade change. The types of changes in administrative division levels include four categories: cancellation, merger, division, and establishment.

[0016] Furthermore, the determination of the type of administrative division level change is based on basic matching rules, which are as follows: 1) Revocation identification: If a certain district code record exists in V_old but not in V_new, it is determined to be revoked, where V_old represents the old version of the data table / dataset set and V_new represents the new version of the data table / dataset set; 2) Establishment identification: If a certain district code record exists in V_new but not in V_old, it is determined to be newly established; 3) Merge Identification: If multiple old records are mapped to the same new district code in the new version, they are determined to be merged; 4) Segmentation identification: If an old record is mapped to multiple new zone codes in the new version, it is determined to be a segmentation.

[0017] Furthermore, the rules for handling data changes caused by adjustments to administrative division types and administrative categories are as follows: Based on the adjustments and changes and the new and old versions of the data tables / data sets compiled due to hierarchical adjustments, determine the administrative division type and administrative category before and after the adjustment and change of administrative division. Change the corresponding administrative division code according to the adjusted administrative division type and administrative category, and adjust the new version of the administrative division data table / data set. The old version of the administrative division data table / data set remains unchanged.

[0018] Furthermore, the rules for handling data changes caused by the sorting of administrative divisions at the same level, of the same type, or of the same management category are as follows: After the processing of changes in administrative division data caused by adjustments to administrative division level, type, or management category is completed, the sorting of existing administrative divisions that have not undergone adjustments remains unchanged. The administrative divisions newly added to the data table / dataset are ranked after the original administrative divisions of the same type or management category at the same level, and are assigned sequential codes. The administrative division data that has been deleted in the old version of the data table / dataset remains unchanged, and the historical information of the administrative divisions is recorded. The administrative division data added in the new version is assigned sequential codes following the original data of the current year.

[0019] Furthermore, step 4, updating the zoning map, is based on the premise that the settlement point map remains unchanged. First, the zoning map is assigned settlement point codes as map data attribute values. Then, according to the hierarchical compilation rules of the zoning code segments, the province, city, county, and township locations of the settlement points are determined. Under the premise that the corresponding codes of the same level and number of segments containing settlement points are completely consistent, settlement point patches with consistent codes are merged to generate a township-level map. Following this method, lower-level maps are merged to generate upper-level maps, processing layer by layer. Utilizing the logical and geometric topological relationships of the hierarchical inclusion, all levels of township, county, city, and province maps are generated based on the settlement point map patches. The process involves creating a high-level administrative division map. Conversely, based on high-level map features, using hierarchical segmentation logic and geometric topological relationships, and ensuring that the corresponding number of regional division codes are completely consistent across all regions within the higher-level map, lower-level map features are segmented to generate the required administrative division map. After generating all administrative division maps, GIS technology is used to add time attribute information indicating adjustments or changes to each feature, generating administrative division maps for different years. Based on the year, administrative division map data is linked with place name and administrative division code data for the same year, achieving interconnectivity between place names, administrative division codes, and administrative division map data.

[0020] A computer device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0021] A computer device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0022] The advantages of this application over the prior art are as follows: ① By using a version difference comparison method, changes can be automatically identified, reducing the workload of manual comparison; ②Because a mapping relationship structure was established, stable cross-version data association and historical traceability were achieved; ③ Because a unified identifier was generated, continuous management of entities within the same administrative region was achieved. Attached Figure Description

[0023] The following description, in conjunction with the accompanying drawings, further illustrates this application: Figure 1 A structural diagram of the basic functional layer provided in the embodiments of this application; Figure 2 A flowchart of administrative division data analysis and processing provided for embodiments of this application; Figure 3 This application provides a flowchart for changing administrative division data. Detailed Implementation

[0024] like Figures 1 to 3 As shown, this application provides a method for intelligent management and processing of administrative division data based on AI technology. It aims to integrate different versions of administrative division data to achieve intelligent management and intelligent adjustment of shared basic data in the construction of the national artificial intelligence system, providing a method for the expansion of artificial intelligence technology. Simultaneously, a cross-version automatic identification mechanism is constructed, which can solve the problem of low efficiency caused by existing technologies that mostly rely on manual comparison or single-version management. Furthermore, for cases of administrative division mergers or divisions, a stable mapping relationship is established; or for cases of administrative division adjustments, changes in management levels, or changes in classification types, the rules of GB / T 2260 and GB / T 10114-2003 are followed to solve the sorting problem of administrative divisions at the same level, management level, and classification type after the adjustment or change, accurately tracing historical data and realizing the historical tracing of administrative division data adjustments and changes in different years; it can also solve the problem of intelligent combination changes in administrative division maps, intelligently generating administrative division codes and matching place names for the corresponding year. This truly builds administrative division data into a nationally shared basic data platform that can be intelligently applied.

[0025] Based on this, the principle of the method for intelligent management and processing of administrative division data based on AI technology in this application is as follows: First, we traced and associated multiple versions of administrative division codes: Considering that place names and administrative division codes are currently republished annually, while most regional data remains unchanged, this embodiment uses a specific version of data as the base data and other versions as the changed data. An Excel spreadsheet system is used to create a data table for each version of administrative division data, creating a unified dataset for all versions. Different data tables are compared based on the ID field, generating a standard table. Matching fields and records is performed; if they match, a value of 1 is assigned; otherwise, a value of 0 is assigned. Different tables are named after the year the data version was generated. The comparison between the base table and the corresponding year's version table determines the time and frequency of administrative division adjustments. A unified dataset is created for all versions of place names and administrative division data. AI functions can be used to freely compare different versions of the data tables. Based on this concept, a traceability and correlation relationship for all versions of data can be established.

[0026] Each version of the administrative division data includes three types of data: a division code table, a place name table, and a division map data. The division code table and place name table are represented in Excel spreadsheets as attribute data, while the division map data are represented in GIS software as spatial data.

[0027] Meanwhile, when other industries, departments, and regions need to use different versions of administrative division data, the above concept can also be used to establish corresponding traceability and correlation relationships.

[0028] Then, using the aforementioned tracing and correlation relationships, the current (latest) version of the place name and administrative division code data file is edited. The principle is as follows: Using intelligent methods, edit and fill in the current version of the place name and administrative division code data file; Using the current version of the place name and administrative division code data file, the administrative divisions (including settlements) of the adjusted and changed areas are displayed, along with the corresponding level, division type, and management category. Then, combined with the division adjustment and change information reported at each level or the latest adjustment and change information, the administrative division code segment corresponding to the part of the administrative division code that has changed in the area after the adjustment and change in the previous year is determined. Then, the division level, division type, and management category of the administrative division (including settlements) that has undergone adjustment and change are confirmed. If the adjustment or change is an addition, the original version data remains completely unchanged. In the new version data, first, add one ID number to the ID field of the corresponding level segment according to the sorting order of the newly added area. The ID number will continue from the original ID number. If there is no adjustment or change, the ID number will remain unchanged. If the new area sorting is inserted into the same level, the same area type, and the same management category, adjust the ID field according to the existing sorting. For areas sorted after the new area, the original ID field number will remain unchanged, and the position will be extended accordingly. By utilizing information on the administrative division level, type, and management category of the area to be adjusted or changed, the system identifies the order of areas within the same level, type, and management category, locates the code data of the last area in the order, and increments the corresponding digits of the code segment used to send the adjustment or change, thus intelligently generating the administrative division code for the corresponding area. For place name data, the system confirms the administrative division type and management category of the area being adjusted by referring to the administrative division adjustment documents submitted at each level, identifies the corresponding place name, and adds management place names such as province (autonomous region, special administrative region), city (region), county (district, city), and (street office, town, township) based on the level, type, and management category. Similarly, if manual adjustments result in reductions, mergers, or splits, in addition to retaining the current version data, the original data must be added or deleted from the ID field of the new version data table to ensure that the relationship between the number of records in the original version and the number of records after the adjustment is such that the original number of records = the number of records after the adjustment + / - the actual number of adjustments.

[0029] For spatial area adjustments and changes such as merging, dividing, and excavating, they can all be treated as either reducing first and then increasing, or increasing first and then reducing.

[0030] Finally, an administrative division map for the corresponding year is intelligently generated based on the administrative division data. The specific principle is as follows: 1) Administrative division maps are currently the most scarce data problem. This embodiment uses GIS topological operations, based on the hierarchy, division type, and management category of administrative division codes. It adopts the principle that spatial areas at the same level are formed by merging data from the next lower level, and data at the next higher level can be divided from data from the previous level. Using village-level settlement data as a foundation, and utilizing village-level and community regional maps, village-level areas with consistent street, town, and township level codes are merged to generate street, town, and township level administrative division maps. Street, town, and township level administrative division maps with consistent street, town, and township level codes are merged to generate district, county, and managed city administrative division maps. This process is repeated upwards, merging them into city and prefecture administrative division maps. Similarly, they are merged into municipality, province, and autonomous region administrative division maps.

[0031] 2) After some areas are re-divided and adjusted into new zoning, the zoning code blocks of the corresponding spatial location are used on the existing corresponding level zoning map. The topological segmentation method is used to cut or merge the adjusted and changed areas into the changed areas, and a new zoning map of the corresponding year (version) is generated.

[0032] 3) This method can be extended to various applications that manage spatial areas by division or merger, such as land management, watershed management, river section management, road management, and cadastral management.

[0033] The method in this application can integrate currently independently managed and used place names, administrative division codes, and administrative divisions. Figure 3 All data is unified in a public shared dataset, enabling consistent service regardless of whether place names, administrative division codes, or administrative maps are used, thus establishing a foundational platform for national data resource sharing. This lays the foundation for services across various industries and regions, as well as for aggregated analysis across different years.

[0034] Based on the above principles, the method of this application can be implemented through the following means: ① Standardize the fields and unify the coding rules for administrative division data from different years; ② Compare the differences between adjacent versions based on the time dimension and hierarchical relationship; ③ Identify types such as cancellation, establishment, merger, division, change of affiliation, renaming of place names, changes in hierarchy, and changes in order; ④ Establish a mapping relationship between the old version and the new version; ⑤ Generate a unified identifier for the same administrative division entity across different versions and record its change history.

[0035] Based on the above principles and methods, the specific implementation steps of the method in this application include: Step 1: Data reading and structure construction; Read administrative division data records from multiple years and different versions. Each record must include at least: ID number, place name, division code, and the place name, division level, ID number, place name, and division code of the division where each record is located, as well as the ID number, place name, and level division code of the superior division level of each record. The data mentioned above can come from database tables, Excel files, or spatial feature classes.

[0036] Build separate datasets for different versions of the data: V_old: Collection of old version data tables / datasets; V_new: New version of the data table / dataset collection; An index structure is created for each version of administrative division data to improve subsequent matching efficiency.

[0037] Step 2: Field standardization and data preprocessing; To ensure comparability between data from different years, the fields are first standardized, including: 1) Standardization of field place names: To unify the differences in field naming across different years, such as unifying "code", "administrative code", and "xzqdm" into "district code".

[0038] 2) Uniform encoding length: In accordance with the national administrative division coding rules, the coding length is standardized (e.g., 6 or 12 digits), and any insufficient parts are padded with zeros.

[0039] Then, data preprocessing is performed, including: Outlier cleaning includes: null value handling, duplicate record detection, illegal character filtering, and logical conflict verification; Hierarchical variable mapping: Let the administrative division level variable be j, defined as follows: j=1: Provincial level; j=2: Prefecture-level city; j=3: County level; j=4: Township level; j=5: Village level; After preprocessing, a unified and comparable set of version data is formed.

[0040] Step 3: Adjacent Version Matching and Change Identification: Compare each administrative division data in two adjacent versions to determine whether the division data has been adjusted or changed, and the level, division type, and management category of the adjusted or changed data. The types of adjustments or changes to the division data include data changes caused by level adjustments, data changes caused by division type adjustments, data changes caused by management category adjustments, and data changes caused by sorting divisions at the same level, with the same division type, and with the same management category.

[0041] When a district's administrative division level is adjusted, first determine the level at which the changed division falls, then determine if the change is an upgrade, downgrade, or parallel change, and finally determine if it is a cancellation, merger, division, or new establishment. Based on the confirmed level and type of change, and following place name naming rules, if the change involves an upgrade, merger, division, or new establishment, add records for the upgraded, merged, or divided divisions, as well as the newly established division, to the new version of the data table / data set. If the change involves cancellation, merger, or division, delete all changed data, add the changed data, and add the year information of the change to the new version of the data table / data set. In the old version of the data table / data set, retain the original data unchanged, and also add the year information of the old version's data. The place names of the changed administrative divisions are named according to the place names in the change metadata released by the Ministry of Civil Affairs.

[0042] There are three common types of changes in administrative division levels: parallel level, upgrade, and downgrade. This application introduces a change coefficient i=j. new -j old , where j new For the changed hierarchy, j old If the level before the change is defined, the rules for determining the value of the change coefficient are as follows: if i=0, it indicates a change at the same level; if i>0, it indicates a downgrade change; if i<0, it indicates an upgrade change.

[0043] For example: a county-level city is upgraded to a prefecture-level city → i=-1; a township-level city is upgraded to a county-level city → i=-1, both of which are upgrade changes.

[0044] This coefficient of variation can be used to quantify changes in administrative rank.

[0045] The determination of the type of administrative division level change is based on identification using basic matching rules, which are as follows: 1) Cancellation identification: If a certain district code record exists in V_old but not in V_new, it is determined to be cancelled; 2) Establishment identification: If a certain district code record exists in V_new but not in V_old, it is determined to be newly established; 3) Merge Identification: If multiple old records are mapped to the same new district code in the new version, they are determined to be merged; 4) Segmentation identification: If an old record is mapped to multiple new zone codes in the new version, it is determined to be a segmentation.

[0046] The above matching is based on administrative division codes, spatial topological relationships, and place names as auxiliary criteria.

[0047] After basic matching is completed, place name and sorting change identification can be performed for further analysis: 1) Name change identification: If the administrative division code is the same but the place name field is different, it is recorded as "name change".

[0048] 2) Order change: If the set of administrative divisions at the same level is the same, but their arrangement in the order of administrative divisions changes, it is recorded as an order change.

[0049] The rules for handling data changes caused by adjustments to administrative division types and administrative categories are as follows: Based on the adjustments and changes and the new and old versions of the data tables / data sets compiled due to hierarchical adjustments, determine the administrative division type and administrative category before and after the adjustment. Change the corresponding administrative division code according to the adjusted administrative division type and administrative category, and adjust the new version of the administrative division data table / data set. The old version of the administrative division data table / data set remains unchanged.

[0050] The rules for handling data changes caused by the sorting of administrative divisions within the same level and category are as follows: After processing the changes in administrative division data due to changes in level or management category, the sorting of administrative divisions within the same level and management category must also be addressed. In principle, existing administrative divisions that have not changed should retain their sorting to ensure the continued use of the original codes. Newly added administrative divisions in data tables / datasets should be placed after existing administrative divisions of the same type or management category within the same level, and assigned sequential codes. For older versions of data tables / datasets, deleted administrative division data should be retained, recording the historical information of the administrative divisions. Newly added administrative division data should not reuse data that has already been used and deleted from the older data; it must continue the order of the existing data for the current year and be assigned codes accordingly.

[0051] Step 4: After completing the change identification, use the relationship between different levels of administrative division codes and administrative division map data to match the administrative division code data with the administrative division map data, re-edit the administrative division map data, and obtain administrative division maps that match different versions of administrative division data.

[0052] This step assumes the settlement map remains unchanged. First, settlement codes are assigned to the zoning map as map data attribute values. Then, following the hierarchical compilation rules of the 12-digit zoning code segments, the first four 9-digit segments determine the province, city, county, and township location of the settlement. Under the premise that the corresponding codes of the same level and number of segments containing settlements are completely consistent, settlement patches with the same codes are merged to generate a township-level map. Following this method, lower-level maps are merged to generate higher-level maps, processing layer by layer. Utilizing hierarchical inclusion logic and geometric topological relationships, zoning maps at all levels (township, county, city, province) are generated based on settlement map patches. Conversely, based on higher-level map patches, using hierarchical segmentation logic and geometric topological relationships, and assuming that the corresponding zoning codes of the areas contained in the higher-level area are completely consistent, lower-level patches are segmented from higher-level map patches to generate the required zoning map. This innovative algorithm intelligently manages map data for each region at all levels. After generating all the administrative division maps, GIS technology is used to add time attribute information of adjustments and changes to each map patch, generating administrative division maps for different years. Based on the year, the administrative division map data is linked with the place name and administrative division code data of the same year version, realizing the interconnection of place names, division codes, and map data. It also displays the level, administrative category, and corresponding division sort information of each region, realizing unified management in time and space, recording changes, regional jurisdiction, and place name changes.

[0053] This technology changes the current problem of inconsistent versions of administrative division data, and the lack of integration of place names, division codes, and map data, which prevents dynamic management.

[0054] If there is an adjustment to the spatial range of settlement points, the data before and after the adjustment are saved simultaneously, and the data are interchanged according to the time difference. Then, the above process is followed to obtain the correlation relationship corresponding to all administrative division data versions, laying the foundation for dynamic management of administrative division data.

[0055] When merging and segmenting spatial data in a map, a topological analysis method can be used. This method includes analyzing the intersection, containment, and overlap ratios of polygon features. It employs a double for loop for spatial feature comparison, resulting in a time complexity of O(n^2). 2 The first for loop iterates through all elements in featureclass1, requiring a time complexity of O(n). The inner loop also iterates through all elements in featureclass1, also requiring a time complexity of O(n). Because the inner and outer loops are nested, the overall time complexity of the algorithm is O(n^2). 2In each iteration, it is necessary to compare the relationships between the current element and all other elements in terms of place name, ID, and shape, and determine the administrative division change type to which the current element belongs based on these relationships. The time complexity of comparing place names and IDs is O(1); however, the time complexity of comparing shapes requires the use of virtual methods, which may be higher, otherwise the code will lose its practical meaning.

[0056] The outer loop iterates through the V_old elements, and the inner loop iterates through the V_new elements.

[0057] To improve efficiency, an R-tree spatial index structure can be used in the optimized implementation to reduce the number of spatial range detections and improve the efficiency of boundary overlap judgment.

[0058] After identifying the change relationship, a unified identifier ID (Global_ID) is generated for the same administrative division entity.

[0059] This unified identifier is used for: Link administrative division records from different years; Store change history; Supports time-based queries; Supports cross-version statistical analysis; A one-to-many relationship is formed between the unified identifier and the regional codes of each version.

[0060] In addition, a change history table was created, which records: Original administrative division code; New administrative division code; Change type; Year of change; Changes in hierarchy; Changes in place names.

[0061] This historical table allows us to: Inquire about the administrative division status for any given year; Tracing the evolution of administrative divisions; Cross-year data alignment analysis.

[0062] This application can ultimately output a mapping relationship table, a change type statistics table, hierarchical change analysis results, and a visual change coating, which can be called by the front-end module. Its front-end functional modules are as follows: Figure 1 As shown.

[0063] This application is applicable to administrative division data management systems, government data governance platforms, historical division evolution analysis, and cross-year statistical data alignment.

[0064] To address the need for intelligent querying of data from different versions released in different years, this application utilizes large-scale modeling technology to achieve intelligent management of various adjustments and changes within the same spatial area across different time periods. A spatial topology algorithm and program were designed to solve problems related to topological changes caused by administrative division cancellation, establishment, merger, division, and tunneling, as well as changes in management levels and categories. This enables the intelligent generation of Excel spreadsheets and .shp map files based on the adjustment status. Utilizing Excel's functions, the application addresses the issue of inconsistent record and field counts in Excel tables before and after changes to administrative division code data from different time periods, which prevents direct calculations between different versions of data tables / datasets. A single process table with a sufficiently large number of records and fields is created as a standard table to import all versions of administrative division data, forming a comprehensive administrative division data table categorized by year. The first column of each table is set as a standard ID field, and the second column is set as the sequence number of the old version. The old version is then imported. The version data table uses serial number data. Fields four and five import place names, current place names, and administrative division codes from the old version. This data, after processing, retains the original data for the year in which the imported data was generated (including any changed original data). Fields seven and eight import place names and administrative division codes from the new version. Using existing Excel functions, this table compares the same row of place names and administrative division codes between the old and new versions. The comparison result is entered in column nine, with 1 indicating similarities and 2 indicating changes. By comparing the old and new code values ​​and the differences in different number segments and code positions, the table identifies the levels, management categories, and regional sorting differences in the changes. Corresponding feature values ​​are then designed, more fields are added, and the content of each record is increased to determine the changes to place names and codes in the same record between the old and new versions. A zoning map field is added to record the storage path of the map file for that region in each record, allowing the map file to be read using a record pointer.

[0065] This program compares all data tables / data sets pairwise, achieving interconnectivity of all versions of administrative division data from 1980 to the present, and completely solving the intelligent correlation from the dimensions of time, space, and changes in administrative divisions.

[0066] This application also proposes a computer device including a memory and a processor, wherein the memory stores instructions executable on the processor. When the processor executes the instructions, it implements the methods described in the above embodiments. The number of memories and processors can be one or more. This computer device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The computer device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0067] The computer device may also include a communication interface for communicating with external devices and exchanging data. The devices are interconnected using different buses and can be mounted on a common motherboard or otherwise installed as needed. The processor can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as a display device coupled to the interface). In other embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple electronic devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). The bus can be divided into address buses, data buses, control buses, etc.

[0068] Optionally, in a specific implementation, if the memory, processor, and communication interface are integrated on a single chip, then the memory, processor, and communication interface can communicate with each other through an internal interface.

[0069] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting advanced RISC machines (ARM) architecture.

[0070] This application provides a computer-readable storage medium (such as the memory described above) storing computer instructions that, when executed by a processor, implement the method provided in this application.

[0071] Optionally, the memory may include a stored program area and a stored data area, wherein the stored program area may store the operating system and application programs required for at least one function; the stored data area may store data created based on the use of the computer device for mapping. Furthermore, the memory may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, which can be connected to the computer device for mapping via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for intelligent management and processing of administrative division data based on AI technology, characterized in that: Includes the following steps: Step 1: Data reading and structure construction; Step 2: Field standardization and data preprocessing; Step 3: Adjacent Version Matching and Change Identification: Compare each administrative division data in two adjacent versions to determine whether the division data has been adjusted or changed, and the level, division type, and management category of the adjusted or changed data. The types of adjustments or changes to the division data include data changes caused by level adjustments, data changes caused by division type adjustments, data changes caused by management category adjustments, and data changes caused by the same level, same division type, same management category, or division sorting. Step 4: After completing the change and adjustment identification, use the relationship between different levels of administrative division codes and administrative division map data to match the administrative division code data with the administrative division map data, re-edit the administrative division map data, and obtain administrative division maps that match different versions of administrative division data.

2. The method for intelligent management and processing of administrative division data based on AI technology according to claim 1, characterized in that: Step 1 involves reading administrative division data from multiple years and different versions. Each version of the administrative division data includes at least field data and record data. The field data includes an ID number indicating the type of adjustment or change in the administrative division code, and the record data includes the administrative division level, ID number, place name, and administrative division code. After organizing the administrative division data from different versions, the version number and year of publication are added. Based on this, data tables / datasets for different versions of administrative division data are constructed using Excel format, creating a database containing all versions of administrative division data. Using AI technology and an Excel spreadsheet system, a comparison table is created between the different versions of the data tables / datasets. The system identifies whether adjustments or changes have occurred at the same record location as the corresponding version of the data table / dataset. By comparing the adjustment and change information recorded in the table, it reveals whether the corresponding version of the administrative division data has undergone adjustments or changes, including the year in which adjustments or changes occurred, the administrative division level, administrative division type, and management category information. It also statistically analyzes the corresponding administrative divisions that have undergone adjustments or changes, their ranking by administrative division level, administrative division type, and management category, and their ID numbers in different versions of the data. Furthermore, it statistically analyzes the results of adjustments or changes in place names, administrative division levels, administrative division types, and management categories across different versions of the data, generating a table of administrative division data adjustments and changes for the corresponding year. This provides detailed parameters for the intelligent generation of the next version of administrative division data.

3. The method for intelligent management and processing of administrative division data based on AI technology according to claim 2, characterized in that: The field standardization process in step 2 includes unifying the naming and coding length of the administrative division codes in versions of administrative division data for different years; At the same time, hierarchical variable mapping was set up: Let the administrative division level variable be j, defined as follows: j=1: Provincial level; j=2: Prefecture-level city; j=3: County level; j=4: Township level; j=5: Village level.

4. The method for intelligent management and processing of administrative division data based on AI technology according to claim 3, characterized in that: In step 3, the principles and procedures for determining data changes caused by hierarchical adjustments are as follows: First, determine the administrative division level at which the change occurred. Then, determine the type and category of the administrative division and management category. Based on the confirmed administrative division level, type, and management category at which the change occurred, change the place name according to the place name naming rules.

5. The method for intelligent management and processing of administrative division data based on AI technology according to claim 4, characterized in that: When there is an adjustment or change in the administrative division level, the type and management category of the adjusted or changed administrative division are determined by the administrative division level variable. Based on the changes in administrative division level, type, and management category, the corresponding administrative division code is adjusted or changed, including the level change details and the type of level change. The level change details are determined by a change coefficient i, where i = j new -j old j new For the changed hierarchy, j old If the level before the change is i, the rules for the value of the change coefficient are as follows: if i=0, it indicates a change at the same level; if i>0, it indicates a downgrade change; if i<0, it indicates an upgrade change. The types of changes in administrative division levels include four categories: cancellation, merger, division, and establishment.

6. The method for intelligent management and processing of administrative division data based on AI technology according to claim 5, characterized in that: The determination of the type of administrative division level change is based on basic matching rules, which are as follows: 1) Revocation identification: If a certain district code record exists in V_old but not in V_new, it is determined to be revoked, where V_old represents the old version of the data table / dataset set and V_new represents the new version of the data table / dataset set; 2) Establishment identification: If a certain district code record exists in V_new but not in V_old, it is determined to be newly established; 3) Merge Identification: If multiple old records are mapped to the same new district code in the new version, they are determined to be merged; 4) Segmentation identification: If an old record is mapped to multiple new zone codes in the new version, it is determined to be a segmentation.

7. The method for intelligent management and processing of administrative division data based on AI technology according to claim 6, characterized in that: The rules for handling data changes caused by adjustments to administrative division types and administrative categories are as follows: Based on the adjustments and changes and the new and old versions of the data tables / data sets compiled due to hierarchical adjustments, determine the administrative division type and administrative category before and after the adjustment. Change the corresponding administrative division code according to the adjusted administrative division type and administrative category, and adjust the new version of the administrative division data table / data set. The old version of the administrative division data table / data set remains unchanged.

8. The method for intelligent management and processing of administrative division data based on AI technology according to claim 7, characterized in that: The rules for handling data changes caused by the sorting of administrative divisions at the same level, with the same type, or under the same management category are as follows: After the processing of changes in administrative division data caused by adjustments to administrative division level, type, or management category is completed, the sorting of existing administrative divisions that have not been adjusted remains unchanged. The administrative divisions newly added to the data table / dataset are placed after the original administrative divisions of the same type or management category at the same level, and are assigned sequential codes. The administrative division data that has been deleted in the old version of the data table / dataset remains unchanged, and the historical information of the administrative divisions is recorded. The administrative division data added in the new version are assigned sequential codes following the original data of the current year.

9. The method for intelligent management and processing of administrative division data based on AI technology according to claim 8, characterized in that: Step 4, updating the zoning map, assumes the settlement map remains unchanged. First, settlement codes are assigned to the zoning map as map data attribute values. Then, according to the hierarchical compilation rules of the zoning code segments, the province, city, county, and township locations of the settlements are determined. Under the premise that the corresponding codes of the same level and number of segments containing settlements are completely consistent, settlement patches with consistent codes are merged to generate a township-level map. Following this method, lower-level maps are merged to generate higher-level maps, processing layer by layer. Utilizing the hierarchical inclusion logic and geometric topological relationships, and based on the settlement map patches, zoning maps at all levels—township, county, city, and province—are generated. First, draw maps. Second, based on high-level map features, utilize hierarchical segmentation logic and geometric topological relationships, ensuring that the area code of the same segment is completely consistent within the higher-level map features, to segment lower-level map features and generate the required zoning maps. After generating all zoning maps, use GIS technology to add time attribute information of adjustments and changes to each feature, generating zoning maps for different years. Then, based on the year, establish a connection between the administrative zoning map data and the place name and administrative zoning code data of the same year version, realizing the interconnection and interoperability of place name, zoning code, and zoning map data.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1-9.

Images