CN-121997286-A - Entity data association method, entity data association apparatus, entity data association computer device, entity data association readable storage medium, and entity data association program product

CN121997286ACN 121997286 ACN121997286 ACN 121997286ACN-121997286-A

Abstract

The present application relates to an entity data association method, apparatus, computer device, computer readable storage medium and computer program product. The method comprises the steps of determining locating points of all entity data to be matched according to all entity data to be matched in an entity set to be matched, conducting mesh subdivision on the entity data to be matched step by step according to preset mesh subdivision rules until a target mesh is included in an ith mesh subdivision result, enabling a mesh code corresponding to the target mesh to serve as a mesh code characteristic value of the entity data to be matched, enabling the target mesh to include locating points and enable the target mesh to fall in the entity data to be matched completely, inputting the mesh code characteristic value of the entity set to be matched, all the entity data to be matched and the target entity set into an entity association model, and outputting an entity data association result. By adopting the method, the entity association efficiency and accuracy can be improved.

Inventors

ZENG YANYAN
CHEN QI
ZHANG KUI
Tao Yingchun
HOU MENGYING
Liang Hanmei
ZHOU YANDI
XU ZONGXIA
ZHANG XUPING
TIAN HUIMIN

Assignees

北京市测绘设计研究院

Dates

Publication Date: 20260508
Application Date: 20260127

Claims (10)

1. A method of associating entity data, the method comprising: Determining locating points of the entity data to be matched respectively aiming at the entity data to be matched in the entity set to be matched; performing mesh subdivision on the entity data to be matched according to a preset mesh subdivision rule for any entity data to be matched step by step until a target mesh is included in an ith mesh subdivision result, and taking a mesh code corresponding to the target mesh as a mesh code characteristic value of the entity data to be matched, wherein the target mesh comprises the positioning points, and the target mesh is completely located in the entity data to be matched, and i is an integer greater than 0; And inputting the entity set to be matched, the grid coding characteristic values of the entity data to be matched and the target entity set into an entity association model, and outputting to obtain an entity data association result, wherein the target entity set comprises target entity data and the grid coding characteristic values of the target entity data.
2. The method according to claim 1, wherein the determining, for each entity data to be matched in the entity set to be matched, a locating point of each entity data to be matched, respectively, includes: Determining a first value and a second value based on coordinate values of all nodes in the entity data to be matched on an X-axis of a two-dimensional plane coordinate system, wherein the first value is a maximum coordinate value of all the nodes on the X-axis, and the second value is a minimum coordinate value of all the nodes on the X-axis; Determining a target perpendicular line of the entity to be matched based on the first numerical value and the second numerical value, and determining a target line segment from all intersecting line segments of the target perpendicular line and the entity data to be matched, wherein the length of the target line segment in all the intersecting line segments is the largest; and determining the locating point of the entity data to be matched based on the target line segment.
3. The method of claim 2, wherein the coordinate value of the locating point on the X-axis is the coordinate value of the vertical line of the object on the X-axis, and the coordinate value of the locating point on the Y-axis of the two-dimensional planar coordinate system is the average value of the coordinate values of the two end points of the target line segment on the Y-axis.
4. The method of claim 1, wherein the entity association model includes a first association module, the inputting the grid-encoded feature values of the entity set to be matched and each of the entity data to be matched and the target entity set into the entity association model, and outputting to obtain an entity data association result, including: for any entity data to be matched, traversing each target entity data in a target entity set in sequence, and calculating the grid coding association degree of the grid coding feature value of the entity data to be matched and the grid coding feature value of the target entity data traversed currently through the first association module until the calculated grid coding association degree is a target association degree value; And establishing an association relation between the entity data to be matched and the currently traversed target entity data, and outputting an entity data association result based on the association relation.
5. The method of claim 4, wherein the entity association model further comprises a second association module, the inputting the grid-encoded feature values of the entity set to be matched and each of the entity data to be matched and the target entity set into the entity association model, and outputting to obtain an entity data association result, and further comprising: If the target entity data with the grid coding association degree as the target association degree value does not exist after each target entity data in the target entity set is traversed, sequentially traversing each target entity data in the target entity set, and calculating the spatial association degree of the entity data to be matched and the currently traversed target entity data through the second association module until the calculated spatial association degree is greater than or equal to a spatial association degree threshold value; And establishing an association relation between the entity data to be matched and the currently traversed target entity data, and outputting an entity data association result based on the association relation.
6. The method of claim 5, wherein the method further comprises: Determining a recall ratio according to 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, the entity data association result of which is accurate in the entity set to be matched; determining the precision according to 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, the entity data association results of which are accurate in the entity set to be matched; Determining association speed according to the total number of entity data to be matched in the entity set to be matched and the time for the entity set to be matched to complete entity data association; and iteratively updating the entity association model based on the recall ratio, the precision ratio and the association speed.
7. An entity data association apparatus, the apparatus comprising: The first determining module is used for determining locating points of the entity data to be matched respectively aiming at the entity data to be matched in the entity set to be matched; The grid subdivision module is used for carrying out grid subdivision on the entity data to be matched according to a preset grid subdivision rule aiming at any entity data to be matched until a target grid is included in an ith grid subdivision result, and a grid code corresponding to the target grid is used as a grid code characteristic value of the entity data to be matched, wherein the target grid comprises the positioning points and is completely located in the entity data to be matched, and i is an integer greater than 0; And the association module is used for inputting the entity set to be matched, the grid coding characteristic values of the entity data to be matched and the target entity set into an entity association model, and outputting to obtain an entity data association result, wherein the target entity set comprises target entity data and the grid coding characteristic values of the target entity data.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

Description

Entity data association method, entity data association apparatus, entity data association computer device, entity data association readable storage medium, and entity data association program product Technical Field The present application relates to the field of data processing technology, and in particular, to a method, an apparatus, a computer device, a computer readable storage medium, and a computer program product for associating entity data. Background Spatial data of multiple departments across fields, different periods and scales widely exist, and the improvement of data updating efficiency, the enhancement of multiplexing degree and the improvement of entity data quality become industry core demands. The geometrical and semantic differences of the multi-source data are eliminated through entity data association matching, and a space data set with high precision, good behavior and complete attribute is constructed, so that the method is a key basis for supporting efficient application of space data. The current entity data association method is mainly divided into three categories, namely geometric matching, topological matching and semantic matching. The geometrical matching realizes space matching of entity data based on area overlapping degree, the topological matching realizes association matching among the entity data according to topological relations such as intersection, adjacency and the like among the entities, and the semantic matching carries out association matching among the entity data by taking attribute information such as addresses and the like corresponding to the entity data as a core. However, topology matching has poor fault tolerance, complex algorithm, easy failure and low efficiency of matching, semantic matching depends on a data model, attribute type and integrity, accuracy is low, geometrical matching is easy to have mismatching, accuracy is low, and both accuracy and efficiency requirements of association matching are difficult to be met. Therefore, there is a need for a physical data association method that can achieve both efficiency and accuracy. Disclosure of Invention In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, a computer-readable storage medium, and a computer program product for correlating physical data that can achieve both efficiency and accuracy. In a first aspect, the present application provides a method for associating entity data, the method comprising: Determining locating points of the entity data to be matched respectively aiming at the entity data to be matched in the entity set to be matched; performing mesh subdivision on the entity data to be matched according to a preset mesh subdivision rule for any entity data to be matched step by step until a target mesh is included in an ith mesh subdivision result, and taking a mesh code corresponding to the target mesh as a mesh code characteristic value of the entity data to be matched, wherein the target mesh comprises the positioning points, and the target mesh is completely located in the entity data to be matched, and i is an integer greater than 0; And inputting the entity set to be matched, the grid coding characteristic values of the entity data to be matched and the target entity set into an entity association model, and outputting to obtain an entity data association result, wherein the target entity set comprises target entity data and the grid coding characteristic values of the target entity data. In one embodiment, the determining, for each entity data to be matched in the entity set to be matched, a locating point of each entity data to be matched includes: Determining a first value and a second value based on coordinate values of all nodes in the entity data to be matched on an X-axis of a two-dimensional plane coordinate system, wherein the first value is a maximum coordinate value of all the nodes on the X-axis, and the second value is a minimum coordinate value of all the nodes on the X-axis; Determining a target perpendicular line of the entity to be matched based on the first numerical value and the second numerical value, and determining a target line segment from all intersecting line segments of the target perpendicular line and the entity data to be matched, wherein the length of the target line segment in all the intersecting line segments is the largest; and determining the locating point of the entity data to be matched based on the target line segment. In one embodiment, the coordinate value of the positioning point on the X axis is the coordinate value of the target vertical 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 value of the coordinate values of the two end points of the target line segment on the Y axis. In one embodiment, the entity association model includes a first association module, and the inputting the to-be-mat