Entity data association method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to an entity data association method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: for each piece of to-be-matched entity data in a to-be-matched entity set, respectively determining a positioning point of each piece of to-be-matched entity data; performing step-by-step mesh generation on the entity data to be matched according to a preset mesh generation rule until a target mesh is included in an ith-level mesh generation result, and taking a mesh code corresponding to the target mesh as a mesh code feature value of the entity data to be matched, the target grid completely falls into the entity data to be matched; and inputting the to-be-matched entity set, the grid coding feature values of the to-be-matched entity data and the target entity set into an entity association model, and outputting to obtain an entity data association result. By adopting the method, the entity association efficiency and precision can be improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for associating entity data. Background Technology

[0002] Spatial data from multiple departments, across different fields, at different times, and at different scales are widely available. Improving data update efficiency, enhancing reusability, and improving the quality of entity data have become core industry needs. Eliminating geometric and semantic differences between multi-source data through entity data association and matching, and constructing high-precision, timely, and attribute-complete spatial datasets, is a key foundation for supporting the efficient application of spatial data.

[0003] Current entity data association methods are mainly divided into three categories: geometric matching, topological matching, and semantic matching. Among them, geometric matching achieves spatial matching of entity data based on area overlap; topological matching achieves association matching between entity data based on topological relationships such as intersection and adjacency between entities; and semantic matching uses attribute information such as the address corresponding to entity data as the core to perform association matching between entity data.

[0004] However, topological matching suffers from poor fault tolerance and complex algorithms, leading to frequent failures and low efficiency; semantic matching relies on data models, attribute types, and completeness, resulting in low accuracy; geometric matching is prone to mismatches and has low accuracy, making it difficult to balance the accuracy and efficiency requirements of association matching. Therefore, there is an urgent need for an entity data association method that can balance efficiency and accuracy. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for entity data association that can balance efficiency and accuracy in addressing the aforementioned technical problems.

[0006] Firstly, this application provides a method for associating entity data, the method comprising:

[0007] For each entity data in the entity set to be matched, determine the location point of each entity data;

[0008] For any of the entity data to be matched, the entity data to be matched is meshed step by step according to the preset meshing rules until the target mesh is included in the i-th level meshing result. The mesh code corresponding to the target mesh is used as the mesh code feature value of the entity data to be matched. The target mesh includes the positioning point and the target mesh is completely inside the entity data to be matched. i is an integer greater than 0.

[0009] The entity association model is input with the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set. The output is the entity data association result. The target entity set includes the target entity data and the grid-coded feature values ​​of each target entity data.

[0010] In one embodiment, determining the location point of each entity data in the entity set to be matched includes:

[0011] For any entity data in the set of entities to be matched, a first value and a second value are determined based on the coordinate values ​​of each node in the entity data on the X-axis of the two-dimensional plane coordinate system. The first value is the maximum coordinate value of each node on the X-axis, and the second value is the minimum coordinate value of each node on the X-axis.

[0012] The target perpendicular line of the entity to be matched is determined based on the first value and the second value, and a target line segment is determined from each intersecting line segment of the target perpendicular line and the data of the entity to be matched, wherein the target line segment has the largest line segment length among all the intersecting line segments.

[0013] The location point of the entity data to be matched is determined based on the target line segment.

[0014] In one embodiment, the coordinate value of the positioning point on the X-axis is the coordinate value of the target perpendicular line on the X-axis, and the coordinate value of the positioning point on the Y-axis of the two-dimensional plane coordinate system is the average of the coordinate values ​​of the two endpoints of the target line segment on the Y-axis.

[0015] In one embodiment, the entity association model includes a first association module, which inputs the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set into the entity association model, and outputs the entity data association result, including:

[0016] For any of the entity data to be matched, each target entity data in the target entity set is traversed sequentially. The first association module calculates the grid code correlation between the grid code feature value of the entity data to be matched and the grid code feature value of the currently traversed target entity data until the calculated grid code correlation is the target correlation value.

[0017] Establish the association between the entity data to be matched and the target entity data currently being traversed, and output the entity data association result based on the association.

[0018] In one embodiment, the entity association model further includes a second association module, wherein the step of inputting the set of entities to be matched, the grid-coded feature values ​​of each of the entity data to be matched, and the target entity set into the entity association model, and outputting the entity data association result, further includes:

[0019] If, after traversing each target entity data in the target entity set, there is no target entity data with a grid coding correlation degree equal to the target correlation degree value, then each target entity data in the target entity set is traversed sequentially, and the spatial correlation degree between the entity data to be matched and the currently traversed target entity data is calculated through the second correlation module until the calculated spatial correlation degree is greater than or equal to the spatial correlation degree threshold.

[0020] Establish the association between the entity data to be matched and the target entity data currently being traversed, and output the entity data association result based on the association.

[0021] In one embodiment, the method further includes:

[0022] The recall rate is determined based on the total number of entity data to be matched in the entity set to be matched and the number of entity data to be matched with accurate association results in the entity data set to be matched.

[0023] The precision rate is determined based on the total number of entity data association results output for the entity set to be matched and the number of entity data in the entity set to be matched that are accurately matched by the entity data association results.

[0024] The association speed is determined based on the total number of entity data to be matched in the entity set to be matched and the time taken for the entity set to complete the association of entity data.

[0025] The entity association model is iteratively updated based on the recall rate, the precision rate, and the association speed.

[0026] Secondly, this application also provides an entity data association device, the device comprising:

[0027] The first determining module is used to determine the location point of each entity data to be matched in the entity set to be matched.

[0028] The mesh partitioning module is used to perform mesh partitioning on any entity data to be matched according to a preset mesh partitioning rule, until the target mesh is included in the i-th level mesh partitioning result. The mesh code corresponding to the target mesh is used as the mesh code feature value of the entity data to be matched. The target mesh includes the positioning point and the target mesh is completely inside the entity data to be matched. i is an integer greater than 0.

[0029] The association module is used to input the set of entities to be matched, the grid-coded feature values ​​of each of the entity data to be matched, and the target entity set into the entity association model, and output the entity data association result. The target entity set includes target entity data and the grid-coded feature values ​​of each of the target entity data.

[0030] In one embodiment, determining the location point of each entity data in the entity set to be matched includes:

[0031] For any entity data in the set of entities to be matched, a first value and a second value are determined based on the coordinate values ​​of each node in the entity data on the X-axis of the two-dimensional plane coordinate system. The first value is the maximum coordinate value of each node on the X-axis, and the second value is the minimum coordinate value of each node on the X-axis.

[0032] The target perpendicular line of the entity to be matched is determined based on the first value and the second value, and a target line segment is determined from each intersecting line segment of the target perpendicular line and the data of the entity to be matched, wherein the target line segment has the largest line segment length among all the intersecting line segments.

[0033] The location point of the entity data to be matched is determined based on the target line segment.

[0034] In one embodiment, the coordinate value of the positioning point on the X-axis is the coordinate value of the target perpendicular line on the X-axis, and the coordinate value of the positioning point on the Y-axis of the two-dimensional plane coordinate system is the average of the coordinate values ​​of the two endpoints of the target line segment on the Y-axis.

[0035] In one embodiment, the entity association model includes a first association module, which inputs the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set into the entity association model, and outputs the entity data association result, including:

[0036] For any of the entity data to be matched, each target entity data in the target entity set is traversed sequentially. The first association module calculates the grid code correlation between the grid code feature value of the entity data to be matched and the grid code feature value of the currently traversed target entity data until the calculated grid code correlation is the target correlation value.

[0037] Establish the association between the data to be matched and the target entity data currently being traversed, and output the entity data association result based on the association.

[0038] In one embodiment, the entity association model further includes a second association module, wherein the step of inputting the set of entities to be matched, the grid-coded feature values ​​of each of the entity data to be matched, and the target entity set into the entity association model, and outputting the entity data association result, further includes:

[0039] If, after traversing each target entity data in the target entity set, there is no target entity data with a grid coding correlation degree equal to the target correlation degree value, then each target entity data in the target entity set is traversed sequentially, and the spatial correlation degree between the entity data to be matched and the currently traversed target entity data is calculated through the second correlation module until the calculated spatial correlation degree is greater than or equal to the spatial correlation degree threshold.

[0040] Establish the association between the data to be matched and the target entity data currently being traversed, and output the entity data association result based on the association.

[0041] In one embodiment, the device further includes:

[0042] The second determining module is used to determine the recall rate based on the total number of entity data to be matched in the entity set to be matched and the number of entity data to be matched with accurate association results in the entity data set to be matched.

[0043] The third determining module is used to determine the precision rate based on the total number of entity data association results output for the entity set to be matched and the number of entity data to be matched that are accurately associated with the entity data in the entity set to be matched.

[0044] The fourth determining module is used to determine the association speed based on the total number of entity data to be matched in the entity set to be matched and the time taken for the entity set to be matched to complete the association of entity data.

[0045] The iterative update module is used to iteratively update the entity association model based on the recall rate, the precision rate, and the association speed.

[0046] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the entity data association method described above.

[0047] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the entity data association method of any of the above.

[0048] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the entity data association method described above.

[0049] The aforementioned entity data association method, apparatus, computer equipment, computer-readable storage medium, and computer program product determine the location points of each entity data to be matched in the entity set to be matched, and then perform grid partitioning on any entity data to be matched according to a preset grid partitioning rule until the target grid is included in the i-th level grid partitioning result. The grid code corresponding to the target grid is used as the grid code feature value of the entity data to be matched, wherein the target grid includes the location points and the target grid completely falls inside the entity data to be matched, and i is an integer greater than 0. Finally, the entity set to be matched, the grid code feature values ​​of each entity data to be matched, and the target entity set are input into the entity association model, and the entity data association result is output. The target entity set includes the target entity data and the grid code feature values ​​of each target entity data. The entity data association method, apparatus, computer equipment, computer-readable storage medium, and computer program product provided in the embodiments of this application associate entity data through grid coding, realizing comprehensive consideration of geometric and shape features of entity data. In this way, the association between multi-source entity data can be achieved efficiently and accurately without complex calculations, which improves both the efficiency and accuracy of entity data association. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating an entity data association method in one embodiment;

[0052] Figure 2 This is a flowchart illustrating step 102 in one embodiment;

[0053] Figure 3 This is a flowchart illustrating step 106 in one embodiment;

[0054] Figure 4 This is a flowchart illustrating step 106 in another embodiment;

[0055] Figure 5 This is a flowchart illustrating the iterative optimization process of an entity association model in one embodiment;

[0056] Figure 6 This is a schematic diagram of an entity data association method in one embodiment;

[0057] Figure 7 This is a structural block diagram of an entity data association device in one embodiment;

[0058] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0061] In one exemplary embodiment, such as Figure 1 As shown, an entity data association method is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The method includes the following steps 102 to 106, wherein:

[0062] Step 102: For each entity data in the entity set to be matched, determine the location point of each entity data to be matched.

[0063] In this embodiment of the application, the entity set to be matched is a dataset constructed from multiple entity data to be matched, and the entity data to be matched can be newly added entity data to be associated. During the construction of the entity set to be matched,

[0064] In one example, the entity data to be matched can be a polygon entity. For instance, the location points of each entity data point can be calculated based on its geometric features; these location points are coordinate points used to anchor the spatial position of the entity data. The determination of location points requires calculation based on the geometric features of the entity data, and is particularly suitable for polygon entities such as land parcels, lakes, and administrative regions.

[0065] In one exemplary embodiment, such as Figure 2 As shown, in step 102, for each entity data in the entity set to be matched, the location point of each entity data to be matched is determined, which may include the following steps 202 to 206, wherein:

[0066] Step 202: For any entity data to be matched in the entity set to be matched, based on the coordinate values ​​of each node in the entity data to be matched on the X-axis of the two-dimensional plane coordinate system, determine the first value and the second value. The first value is the maximum coordinate value of each node on the X-axis, and the second value is the minimum coordinate value of each node on the X-axis.

[0067] Step 204: Determine the target vertical line of the entity to be matched based on the first and second values, and determine the target line segment from each intersecting line segment of the target vertical line and the entity data to be matched, wherein the target line segment has the longest line segment among all intersecting line segments.

[0068] Step 206: Determine the location points of the entity data to be matched based on the target line segment.

[0069] In this embodiment of the application, the entity data to be matched in a planar shape (which can be represented as...) That is, the entity data to be matched is the first one in the set of entities to be matched. Taking one entity data to be matched as an example, first iterate through... Given the coordinates of all nodes, find the maximum value of the X-coordinate. (That is, the first value) and the minimum value (That is, the second value), and based on the first and second values, determine the perpendicular line L to the X-axis, and take the X coordinate of the perpendicular line L as... That is, the centerline of the entity in the X direction, the perpendicular line L can be represented as:

[0070] ;X=x.

[0071] After determining the perpendicular line L, we can statistically analyze the perpendicular line L and its parallels. Intersecting line segments, only those falling inside the solid are counted, and the length of each segment is calculated. The mathematical expression for a line segment is: ,in and These are the minimum and maximum Y-coordinates of the intersection point of the j-th line segment and the graphical boundary of the entity data to be matched (i.e., the Y-coordinates of the two endpoints of the line segment). The expression for calculating the length of the line segment is: Take the length of it. ( The longest line segment Lmax is taken as the target line segment, and the midpoint of Lmax is taken as the final line segment. The location point O (x 中心 y 中心 ).

[0072] In an exemplary embodiment, the coordinates of the positioning point on the X-axis are the coordinates of the target perpendicular line on the X-axis, and the coordinates of the positioning point on the Y-axis of the two-dimensional plane coordinate system are the average of the coordinates of the two endpoints of the target line segment on the Y-axis. Wherein, the coordinates of the positioning point on the X-axis are x... 中心 x 中心 Let L be the fixed X-axis coordinate value, and the coordinate value of the positioning point on the X-axis be y. 中心 y 中心 The calculation formula is ,in and These are the minimum and maximum Y-coordinates of the intersection point of the target line segment Lmax and the boundary of the entity data graphic to be matched, respectively. The positioning points determined in this way can accurately fall within the core region of the entity data to be matched, thus providing a reliable benchmark for subsequent mesh generation.

[0073] Step 104: For any entity data to be matched, perform grid subdivision of the entity data to be matched level by level according to the preset grid subdivision rules until the target grid is included in the i-th level grid subdivision result. Use the grid code corresponding to the target grid as the grid code feature value of the entity data to be matched. The target grid includes positioning points and the target grid is completely inside the entity data to be matched. i is an integer greater than 0.

[0074] In this embodiment, for any entity data in the entity set to be matched, it is meshed level by level according to a preset grid rule, such as the GeoSOT (Geographic Spatial One-dimensional Tiling system) rule, until the i-th level grid subdivision result includes the target grid. The grid code corresponding to the target grid is then used as the grid code feature value of the entity data to be matched. The target grid includes location points and falls entirely within the entity data to be matched. The GeoSOT system is a globally unified spatial grid standard with a hierarchical structure from coarse to fine. Each grid level has a unique code; the finer the level, the higher the coding and positioning accuracy.

[0075] For example, meshing is performed with location point O as the center. It begins with the highest-level (coarsest-grained) mesh, identifying the initial mesh containing O. Then, it is meshed downwards level by level based on this initial mesh. After each level of meshing is completed, the current level's mesh is checked using the DE-9IM (Dimensionally Extended 9-Intersection Model) to determine if it simultaneously meets two conditions: first, the mesh completely falls within the entity data to be matched; second, the mesh contains location point O. When meshing reaches the i-th level, the first target mesh that satisfies both conditions is found, and meshing immediately stops. This target mesh is then uniquely encoded. As entity data to be matched The grid-coded feature value. This feature value can accurately characterize the spatial location of the entity data to be matched. The judgment formula using the DE-9IM model is as follows:

[0076]

[0077] in, , In DE-9IM, 'a' identifies the mesh, and 'b' represents the entity data to be matched. Geometric objects in DE-9IM are divided into three parts: interior I, boundary B, and exterior E. That is, mesh 'a' in DE-9IM is divided into interior I (a), boundary B (a), and exterior E (a), and entity data to be matched 'b' in DE-9IM is divided into interior I (b), boundary B (b), and exterior E (b). This represents the dimension of the intersecting part. A non-intersecting dimension is denoted as False, and an intersecting dimension as True. For True, False If the value is False, meaning the inside of the grid intersects with the inside of the entity data to be matched, the inside of the grid does not intersect with the outside of the entity data to be matched, and the boundary of the grid does not intersect with the outside of the entity data to be matched, then the grid is determined to be completely inside the entity data to be matched.

[0078] It should be noted that the embodiments of this application do not limit the upper limit of the specific level of GeoSOT subdivision, and can be dynamically adjusted according to the size of the entity data and the data accuracy requirements, as long as a target mesh that meets the conditions can be found.

[0079] Step 106: Input the entity set to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set into the entity association model, and output the entity data association result. The target entity set includes the target entity data and the grid-coded feature values ​​of each target entity data.

[0080] In this embodiment of the application, the target entity data of each target entity in the target entity set is entity data that is pre-associated using a method that is completely consistent with steps 102 and 104. The target entity set includes the grid-coded feature values ​​of each target entity data.

[0081] The entity association model inputs the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set. The entity association model can determine the target entity data associated with each entity data to be matched based on the degree of spatial association between entities and the degree of association between the grid-coded feature values ​​of entities, and establish the association relationship between the two, and output the corresponding entity data association result.

[0082] The aforementioned entity data association method determines the location points of each entity data in the entity set to be matched, and then performs a step-by-step meshing of any entity data according to a preset meshing rule until the target mesh is included in the i-th level meshing result. The mesh code corresponding to the target mesh is used as the mesh code feature value of the entity data to be matched. The target mesh includes the location points and falls completely within the entity data to be matched, where i is a positive integer. Finally, the entity set to be matched, the mesh code feature values ​​of each entity data to be matched, and the target entity set are input into the entity association model, and the entity data association result is output. The target entity set includes the target entity data and the mesh code feature values ​​of each target entity data. Using the entity data association method provided in this application, which associates entity data through mesh coding, the geometric and shape features of the entity data are comprehensively considered. This allows for efficient and accurate association between multi-source entity data without complex calculations, improving both the efficiency and accuracy of entity data association.

[0083] In one exemplary embodiment, such as Figure 3 As shown, the entity association model includes a first association module. In step 106, the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set are input into the entity association model, and the entity data association result is output. This may include the following steps 302 to 304, wherein:

[0084] Step 302: For any entity data to be matched, traverse each target entity data in the target entity set in turn, and calculate the grid coding correlation degree between the grid coding feature value of the entity data to be matched and the grid coding feature value of the currently traversed target entity data through the first association module until the calculated grid coding correlation degree is the target correlation degree value.

[0085] Step 304: Establish the association between the entity data to be matched and the target entity data currently being traversed, and output the entity data association result based on the association relationship.

[0086] In this embodiment of the application, for any entity data to be matched It can iterate through each target entity data in the target entity set sequentially, and then process the target entity data iterates through. (That is, the s-th target entity data in the target entity set), first verified by the first association module. and The correlation between two grid codes is determined by the consistency of their feature values. If their feature values ​​are identical, they are considered strongly correlated. If the grid coding feature values ​​are inconsistent (e.g., 1 for the target correlation value), they are considered unrelated. If the value is 0, the calculation formula is as follows:

[0087]

[0088] When the grid coding correlation degree is 1, it can be determined that the two are strongly correlated, and a correlation relationship can be established between them. The correlation relationship value is recorded in the entity data correlation result. And switch to the next entity data to be matched. If the grid encoding correlation is 0, it can be determined that the two are not related, and the process continues to the next one. until a matching entity data is found. The process continues until all associated target entity data or target entity sets have been traversed.

[0089] In one exemplary embodiment, such as Figure 4As shown, the entity association model also includes a second association module. In step 106, the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set are input into the entity association model, and the entity data association result is output. It may also include the following steps 402 to 404, wherein:

[0090] Step 402: If, after traversing each target entity data in the target entity set, there is no target entity data whose grid coding correlation degree is equal to the target correlation degree value, then traverse each target entity data in the target entity set in turn, and calculate the spatial correlation degree between the entity data to be matched and the target entity data currently being traversed through the second correlation module, until the calculated spatial correlation degree is greater than or equal to the spatial correlation degree threshold.

[0091] Step 404: Establish the association between the entity data to be matched and the target entity data currently being traversed, and output the entity data association result based on the association relationship.

[0092] In this embodiment, if after traversing all target entity data there is no matching code (i.e., there is no target entity data whose calculated grid code correlation degree is the target correlation degree value), then all target entity data are traversed again, and the spatial correlation degree between the two entity data is calculated by the area ratio between the two entity data through the second correlation module. The formula is as follows:

[0093]

[0094] in, This represents the intersection area between the entity to be matched and the target entity. The area of ​​the entity data to be matched. The area of ​​the target entity data. The spatial correlation is compared with a preset spatial correlation threshold. If the spatial correlation is greater than or equal to the threshold, a strong correlation can be established, and the correlation value is recorded in the entity data correlation results. And switch to the next entity data to be matched. If the spatial correlation is less than the spatial correlation threshold, it can be determined that the two are not related, and the process continues to the next one. until a matching entity data is found. The process continues until all associated target entity data or target entity sets have been traversed.

[0095] After all entity data to be matched has been traversed, the complete entity data association result is output. This result can be directly used for the integration, updating and reuse of multi-source spatial data, effectively eliminating matching errors caused by data heterogeneity.

[0096] The entity data association method provided in this application adopts a combination of grid coding association and spatial association in the entity association model. The entity set to be matched, the grid coding feature values ​​of each entity data to be matched, and the target entity set are input into the entity association model. The matching between entity data is achieved through two-level association verification of grid coding association and spatial association, and the entity data association result is finally obtained. It can balance matching efficiency and accuracy, and improve association efficiency while improving association accuracy.

[0097] In one exemplary embodiment, such as Figure 5 As shown, the method may further include steps 502 to 508, wherein:

[0098] Step 502: Determine the recall rate based on the total number of entity data to be matched in the entity set to be matched and the number of entity data to be matched that are accurately associated with the entity data in the entity set to be matched.

[0099] Step 504: Determine the precision based on the total number of entity data association results output for the entity set to be matched and the number of entity data in the entity set to be matched that are accurately associated with the entity data.

[0100] Step 506: Determine the association speed based on the total number of entity data to be matched in the entity set to be matched and the time taken for the entity set to complete the association of entity data;

[0101] Step 508: Iteratively update the entity association model based on recall, precision, and association speed.

[0102] In this embodiment, recall is an indicator used to measure the degree of missed matching in the entity association model. It reflects the ability of the entity association model to cover real relationships and avoids the problem of missing entity associations due to missed judgments, which affects the integrity of spatial data integration. Recall is positively correlated with the number of entities that are accurately matched in the association results. For example, recall can be calculated as: Recall = Number of entities that are accurately matched in the association results / Total number of entity data to be matched.

[0103] Assuming the set of entities to be matched contains 100 land parcel entities (i.e., the total number of entity data to be matched is 100), and after manual verification or comparison with authoritative data, it is determined that the association results of 85 of these entity data are accurate (i.e., there is a real association and the match is correct), then the recall rate of this model is 85%. The higher the recall rate, the more comprehensive the real association relationships that the entity association model can capture, and the fewer the missed matches.

[0104] Precision is a metric used to measure the degree of mismatch in entity association models. It reflects the reliability of the association results output by the model, preventing erroneous associations due to misjudgments and thus affecting the quality of spatial datasets. Precision is positively correlated with the number of accurately matched entities in the association results, and negatively correlated with the total number of entity data association results output for the set of entities to be matched. For example, precision can be calculated as: Precision = Number of accurately matched entities in the association results / Total number of entity data association results.

[0105] Using the example above, if the entity association model outputs 90 association results for 100 entities to be matched (including some false matches, i.e., the total number of output association results is 90), and 85 of these are accurate association results, then the precision is approximately 94.4%. A higher precision indicates stronger reliability of the association results output by the entity association model, fewer false matches (such as classifying different land parcels as entities with the same name), and effectively avoids decision-making biases caused by data errors.

[0106] Association speed is a metric used to measure the operational efficiency of an entity association model. It reflects the model's ability to process massive amounts of spatial data, adapts to the timeliness requirements of large-scale data integration across multiple departments, and addresses the low efficiency of existing methods such as topology matching. For example, association speed can be calculated as: Association speed = Total number of entity data to be matched / Time taken for the set of entities to be matched to complete the association of entity data.

[0107] Assuming there are 1000 entities to be matched, and the entity association model takes 200 seconds to complete the association of all entity data, the association speed is 5 entities / second. A higher association speed indicates higher processing efficiency of the entity association model, enabling it to quickly complete the association and matching of multi-source, massive spatial data, reducing the time cost of cross-departmental data integration.

[0108] In an exemplary embodiment, the iterative update process may include: setting preset thresholds for three key metrics (recall, precision, and association speed), such as setting recall ≥90%, precision ≥95%, and association speed ≥8 items / second. By comparing the differences between the current output metrics of the entity association model and the preset thresholds, if the recall and / or precision do not reach the preset thresholds, the calculation logic of spatial association degree and / or the spatial association degree threshold can be adjusted to reduce missed matches and false matches; if the association speed does not reach the preset thresholds, the calculation logic of spatial association degree and / or grid-coded association degree can be adjusted.

[0109] After adjusting the entity association model, the entity association process is re-executed, and the indicator evaluation and optimization process is repeated until all three indicators meet the preset requirements, forming a stable entity association model. Through continuous iteration, the model is adapted to the spatial data association needs in different scenarios, achieving a dynamic balance between model accuracy and efficiency, and further improving data update efficiency and reusability.

[0110] To enable those skilled in the art to better understand the embodiments of this application, the embodiments of this application are described below through specific examples.

[0111] Reference Figure 6 As shown, the entity data association method provided in this application mainly includes five important steps: entity data preprocessing, entity data feature extraction, entity association model calculation, entity feature similarity comparison, and entity association model evaluation. The specific processing flow of each module is as follows:

[0112] Step (1), Entity Data Preprocessing: Data processing is performed on the entities, including entity standardization, multi-component splitting, etc., to construct the entity set to be matched. Entity standardization includes data formatting, coordinate transformation, etc. Specifically, data formatting involves modifying the target entity set TargetEntity={TE1,TE2,TE3,....,TE...}. s ...} and the set of entities to be matched, MatchEntity={ME1,ME2,ME3,....,ME...} k Both types of data are stored in a commonly used vector data format. Coordinate transformation unifies the target entity set and the entity set to be matched under the same spatial reference, reducing projection bias between the data. Through standardization, a data foundation is laid for the overlay analysis between the target entity set and the entity set to be matched.

[0113] Step (2), Entity data feature extraction: Randomly extract one entity data ME to be matched from the entity set to be matched. k Calculate the location point O(x) of the entity data to be matched. 中心 y 中心 Taking a face solid as an example, the specific calculation method is as follows:

[0114] To find the maximum and minimum X-coordinates of the entity data to be matched: Assuming the graph has multiple nodes such as 1, 2, 3, 4, 5, ..., first traverse the coordinates of each node in the entity data to be matched, and then find the maximum X-coordinate Xmax and the minimum Xmin.

[0115] Xmax=max{x1,x2,x3,x4,x5,....};

[0116] Xmin = min{x1,x2,x3,x4,x5,....};

[0117] Next, the perpendicular line L is calculated based on the maximum value Xmax and the minimum value Xmin. The equation of the perpendicular line L is:

[0118] ;

[0119] ;

[0120] The line segments (L1, L2, L3, ...) that define the area where the perpendicular line L intersects with the entity data to be matched are mathematically expressed as:

[0121] X j =x(ymin j ≤y j ≤ymax j (j=1,2,3,…);

[0122] Where ymax j ymin j Line segment L j The maximum and minimum Y values ​​at the intersection with the boundary of the figure.

[0123] Find the lengths d1, d2, d3... of the line segments in the intersecting regions L1, L2, L3... The calculation expression is:

[0124] d1=ymax1–ymin1

[0125] d2=ymax2–ymin2

[0126] ...

[0127] Let the line segment Lmax corresponding to the maximum value dmax be the target line segment, where dmax = Max(d1, d2, d3, ...). The midpoint of the target line segment Lmax is taken as the positioning point. Let the mathematical expression of Lmax be:

[0128] X = x (ymin ≤ y ≤ ymax)

[0129] The coordinates of the graphic positioning point are O(x) 中心 y 中心 ),in , .

[0130] According to the GeoSOT partitioning rules, the entity data MEi to be matched is partitioned into a grid, and the grid code is calculated. The location point O(x) obtained by the aforementioned process is... 中心 y 中心Using the first-level grid as the meshing center, the entity data to be matched is meshed level by level down. After each level of meshing is completed, it is determined whether each mesh falls completely inside the entity. The DE-9IM model is used to determine whether the entity contains the interior, and the formula is as follows:

[0131]

[0132] Dangdang For True, False When the value is False, it is determined that the grid is completely inside the entity data to be matched.

[0133] When a mesh is found that falls entirely within the entity data to be matched and contains the entity location point O(x) 中心 y 中心 ), encode the grid code k This is denoted as the grid-coded feature value of the entity data.

[0134] Step (3), Entity Association Model Calculation: The entity association model consists of two parts: grid-coded association and spatial association. The specific steps are as follows:

[0135] Mesh-coded association is the process of calculating the consistency of mesh-coded feature values. If the mesh-coded... , If they are consistent, it proves that the two entities are related; otherwise, it is a weak association. Grid coding association degree The calculation formula is as follows:

[0136] When entity When the value is 1, the two entities are associated, and the association result R={...,[ME] is recorded. k ,TE s ],...}, and select the next ME from the entity data to be matched. k+1 Perform association calculations. Otherwise, perform spatial association between the two entities.

[0137] Spatial association is calculated by measuring the ratio of the areas of two entities. If spatial correlation If the spatial correlation score is greater than the threshold, it indicates a correlation between the two entities; otherwise, it indicates a weak correlation. Spatial correlation. The calculation formula is as follows:

[0138]

[0139] in, This represents the area of ​​intersection between the entity data to be matched and the target entity data. The area of ​​the entity data to be matched. The area of ​​the target entity data.

[0140] Comparison of spatial correlation The spatial correlation threshold is used to determine if there is a correlation between the two entities. If the spatial correlation is greater than or equal to the threshold, then the correlation result R={...,[ME] k ,TE s If the spatial correlation is less than the spatial correlation threshold, then the two entities are defined as unrelated. Then, the next ME is selected from the entity data to be matched. k+1 Perform association calculations until the calculations for each entity in the set of entities to be matched are completed.

[0141] Step (4), Entity Association Model Evaluation: Finally, the model is iteratively optimized based on association accuracy and association speed until a relatively satisfactory matching effect is achieved. Association accuracy includes two parts: association recall and precision. Recall... Precision is calculated by comparing the ratio of the number of correctly associated entities N to the total number of entities M. It is the ratio of the number of correctly associated entities N to the total number of associated entities T returned, as shown in the following formula:

[0142] ; .

[0143] Association speed The formula is as follows: N is the number of entities to be associated, and P is the time P used to collect all the data for each entity. .

[0144] Step (5), Outputting the associated entity results: After the association calculation for each entity data in the entity set to be matched has been completed, output the association result R={...,[ME k ,TE s The output of ],...} is the final entity association result.

[0145] The entity data association method provided in this application comprehensively considers the geometric and shape characteristics of entity data and proposes a multi-source entity data association algorithm, which not only improves the efficiency of entity element association but also takes into account the accuracy of entity association. Its results have wide application value in the fields of entity data updating and entity data governance.

[0146] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0147] Based on the same inventive concept, this application also provides an entity data association apparatus for implementing the entity data association method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more entity data association apparatus embodiments provided below can be found in the limitations of the entity data association method described above, and will not be repeated here.

[0148] In one exemplary embodiment, such as Figure 7 As shown, an entity data association device 700 is provided. The device includes: a first determination module 702, a mesh partitioning module 704, and an association module 706, wherein:

[0149] The first determining module 702 is used to determine the location point of each entity data to be matched in the entity set to be matched.

[0150] The mesh partitioning module 704 is used to perform mesh partitioning on any entity data to be matched according to a preset mesh partitioning rule, until the target mesh is included in the i-th level mesh partitioning result. The mesh code corresponding to the target mesh is used as the mesh code feature value of the entity data to be matched. The target mesh includes positioning points and the target mesh is completely inside the entity data to be matched. i is an integer greater than 0.

[0151] The association module 706 is used to input the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set into the entity association model, and output the entity data association result. The target entity set includes the target entity data and the grid-coded feature values ​​of each target entity data.

[0152] The aforementioned entity data association device determines the location points of each entity data in the entity set to be matched, and then performs grid subdivision on each entity data according to a preset grid subdivision rule until the target grid is included in the i-th level grid subdivision result. The grid code corresponding to the target grid is used as the grid code feature value of the entity data to be matched. The target grid includes the location points and falls completely inside the entity data to be matched, where i is an integer greater than 0. Finally, the entity set to be matched, the grid code feature values ​​of each entity data to be matched, and the target entity set are input into the entity association model, and the entity data association result is output. The target entity set includes the target entity data and the grid code feature values ​​of each target entity data. By using the entity data association device provided in this application embodiment to associate entity data through grid coding, the device comprehensively considers the geometric and shape features of entity data. In this way, it can efficiently and accurately associate multi-source entity data without complex calculations, improving both the efficiency and accuracy of entity data association.

[0153] In an exemplary embodiment, determining the location point of each entity data to be matched in the entity set to be matched includes:

[0154] For any entity data in the set of entities to be matched, a first value and a second value are determined based on the coordinate values ​​of each node in the entity data on the X-axis of the two-dimensional plane coordinate system. The first value is the maximum coordinate value of each node on the X-axis, and the second value is the minimum coordinate value of each node on the X-axis.

[0155] The target perpendicular line of the entity to be matched is determined based on the first value and the second value, and a target line segment is determined from each intersecting line segment of the target perpendicular line and the data of the entity to be matched, wherein the target line segment has the largest line segment length among all the intersecting line segments.

[0156] The location point of the entity data to be matched is determined based on the target line segment.

[0157] In an exemplary embodiment, the coordinate value of the positioning point on the X-axis is the coordinate value of the target perpendicular line on the X-axis, and the coordinate value of the positioning point on the Y-axis of the two-dimensional plane coordinate system is the average of the coordinate values ​​of the two endpoints of the target line segment on the Y-axis.

[0158] In an exemplary embodiment, the entity association model includes a first association module, wherein the step of inputting the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set into the entity association model, and outputting the entity data association result, includes:

[0159] For any of the entity data to be matched, each target entity data in the target entity set is traversed sequentially. The first association module calculates the grid code correlation between the grid code feature value of the entity data to be matched and the grid code feature value of the currently traversed target entity data until the calculated grid code correlation is the target correlation value.

[0160] Establish the association between the entity data to be matched and the target entity data currently being traversed, and output the entity data association result based on the association.

[0161] In an exemplary embodiment, the entity association model further includes a second association module, wherein the step of inputting the set of entities to be matched, the grid-coded feature values ​​of each of the entity data to be matched, and the target entity set into the entity association model, and outputting the entity data association result, further includes:

[0162] If, after traversing each target entity data in the target entity set, there is no target entity data with a grid coding correlation degree equal to the target correlation degree value, then each target entity data in the target entity set is traversed sequentially, and the spatial correlation degree between the entity data to be matched and the currently traversed target entity data is calculated through the second correlation module until the calculated spatial correlation degree is greater than or equal to the spatial correlation degree threshold.

[0163] Establish the association between the entity data to be matched and the target entity data currently being traversed, and output the entity data association result based on the association.

[0164] In one exemplary embodiment, the apparatus further includes:

[0165] The second determining module is used to determine the recall rate based on the total number of entity data to be matched in the entity set to be matched and the number of entity data to be matched with accurate association results in the entity data set to be matched.

[0166] The third determining module is used to determine the precision rate based on the total number of entity data association results output for the entity set to be matched and the number of entity data to be matched that are accurately associated with the entity data in the entity set to be matched.

[0167] The fourth determining module is used to determine the association speed based on the total number of entity data to be matched in the entity set to be matched and the time taken for the entity set to be matched to complete the association of entity data.

[0168] The iterative update module is used to iteratively update the entity association model based on the recall rate, the precision rate, and the association speed.

[0169] Each module in the aforementioned entity data association device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0170] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for associating entity data. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0171] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0172] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0173] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0174] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0175] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0176] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0177] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0178] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for associating entity data, characterized in that, The method includes: For each entity data in the entity set to be matched, determine the location point of each entity data; For any of the entity data to be matched, the entity data to be matched is meshed step by step according to the preset meshing rules until the target mesh is included in the i-th level meshing result. The mesh code corresponding to the target mesh is used as the mesh code feature value of the entity data to be matched. The target mesh includes the positioning point and the target mesh is completely inside the entity data to be matched. i is an integer greater than 0. The entity association model is input with the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set. The output is the entity data association result. The target entity set includes the target entity data and the grid-coded feature values ​​of each target entity data.

2. The method according to claim 1, characterized in that, The step of determining the location point of each entity data in the entity set to be matched includes: For any entity data in the set of entities to be matched, a first value and a second value are determined based on the coordinate values ​​of each node in the entity data on the X-axis of the two-dimensional plane coordinate system. The first value is the maximum coordinate value of each node on the X-axis, and the second value is the minimum coordinate value of each node on the X-axis. The target perpendicular line of the entity to be matched is determined based on the first value and the second value, and a target line segment is determined from each intersecting line segment of the target perpendicular line and the data of the entity to be matched, wherein the target line segment has the largest line segment length among all the intersecting line segments. The location point of the entity data to be matched is determined based on the target line segment.

3. The method according to claim 2, characterized in that, The coordinates of the positioning point on the X-axis are the coordinates of the target perpendicular line on the X-axis, and the coordinates of the positioning point on the Y-axis in the two-dimensional plane coordinate system are the average of the coordinates of the two endpoints of the target line segment on the Y-axis.

4. The method according to claim 1, characterized in that, The entity association model includes a first association module, which inputs the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set into the entity association model, and outputs the entity data association result, including: For any of the entity data to be matched, each target entity data in the target entity set is traversed sequentially. The first association module calculates the grid code correlation between the grid code feature value of the entity data to be matched and the grid code feature value of the currently traversed target entity data until the calculated grid code correlation is the target correlation value. Establish the association between the entity data to be matched and the target entity data currently being traversed, and output the entity data association result based on the association.

5. The method according to claim 4, characterized in that, The entity association model also includes a second association module, which inputs the set of entities to be matched, the grid-coded feature values ​​of each entity data to be matched, and the target entity set into the entity association model, and outputs the entity data association result, further including: If, after traversing each target entity data in the target entity set, there is no target entity data with a grid coding correlation degree equal to the target correlation degree value, then each target entity data in the target entity set is traversed sequentially, and the spatial correlation degree between the entity data to be matched and the currently traversed target entity data is calculated through the second correlation module until the calculated spatial correlation degree is greater than or equal to the spatial correlation degree threshold. Establish the association between the entity data to be matched and the target entity data currently being traversed, and output the entity data association result based on the association.

6. The method according to claim 5, characterized in that, The method further includes: The recall rate is determined based on the total number of entity data to be matched in the entity set to be matched and the number of entity data to be matched with accurate association results in the entity data set to be matched. The precision rate is determined based on the total number of entity data association results output for the entity set to be matched and the number of entity data in the entity set to be matched that are accurately matched by the entity data association results. The association speed is determined based on the total number of entity data to be matched in the entity set to be matched and the time taken for the entity set to complete the association of entity data. The entity association model is iteratively updated based on the recall rate, the precision rate, and the association speed.

7. An entity data association device, characterized in that, The device includes: The first determining module is used to determine the location point of each entity data to be matched in the entity set to be matched. The mesh partitioning module is used to perform mesh partitioning on any entity data to be matched according to a preset mesh partitioning rule, until the target mesh is included in the i-th level mesh partitioning result. The mesh code corresponding to the target mesh is used as the mesh code feature value of the entity data to be matched. The target mesh includes the positioning point and the target mesh is completely inside the entity data to be matched. i is an integer greater than 0. The association module is used to input the set of entities to be matched, the grid-coded feature values ​​of each of the entity data to be matched, and the target entity set into the entity association model, and output the entity data association result. The target entity set includes target entity data and the grid-coded feature values ​​of each of the target entity data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images