A tree skeleton semantic subgraph construction method and system based on growth key point and branch axis simplification, a terminal and a storage medium

Abstract

This invention relates to the field of 3D tree modeling technology, and discloses a method, system, terminal, and storage medium for constructing a semantic subgraph of a tree skeleton based on growth key points and branch axis simplification. The method includes: acquiring tree skeleton data, determining basic topological attributes, identifying growth key points based on the basic topological attributes, and dividing them into root key points, branching key points, terminal growth key points, branch axis turning point key points, and connection transition key points; then, using the key points as constraints, performing topological simplification of the branch axis and deleting redundant sampling nodes along the branch axis direction; finally, constructing a semantic subgraph of the tree skeleton based on the growth key points and simplified branch axis fragments, and outputting standardized subgraph data containing subgraph center, node semantics, edge semantics, branch axis attributes, parent-child relationships, and local topological patterns. This invention can convert dense tree skeletons into semantically clear and scale-uniform local subgraph representations, reducing the data complexity of subsequent learning and analysis.

Description

Technical Field

[0001] This invention relates to the field of tree 3D modeling technology, and in particular to a method, system, terminal, and computer-readable storage medium for constructing a tree skeleton semantic subgraph based on growth key points and simplified branch axes. Background Technology

[0002] Trees possess a complex hierarchical structure composed of a trunk, primary branches, secondary branches, and terminal twigs. This structure is not simply a set of spatial curves, but rather encompasses a variety of semantic information, including root initiation points, branch axis extension directions, bifurcation nodes, terminal growth points, branch hierarchy, parent-child connections, and local neighborhood configurations. In scenarios such as landscape design, ecological digital twins, plant phenotypic analysis, procedural modeling, 3D content production, and tree structure simulation, the tree skeleton is often used as a crucial intermediate representation connecting real-world observational data with editable 3D tree models.

[0003] With the development of laser scanning, image reconstruction, and deep learning technologies, the ability to acquire tree point clouds, tree skeleton curves, and tree diagram data has been continuously improved. However, the original tree skeletons often suffer from problems such as dense nodes, redundant branch polylines, significant local noise, and inconsistent topological scales among different samples. If the complete tree skeleton is directly input into subsequent learning or generative models, the model needs to process a large number of low-level geometric details while simultaneously understanding local growth semantics and global topological relationships, which can easily lead to problems such as high representation dimensionality, unstable training, and difficulty in summarizing structural patterns.

[0004] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0005] The main objective of this invention is to provide a method, system, terminal, and computer-readable storage medium for constructing semantic subgraphs of tree skeletons based on growth key points and simplified branch axes. This aims to solve the problem in the prior art that when modeling tree skeletons with dense nodes, there is a lot of local noise and the model topology is chaotic, resulting in inaccurate tree skeleton models.

[0006] To achieve the above objectives, the present invention provides a method for constructing a semantic subgraph of a tree skeleton based on simplified growth key points and branch axes. The method includes the following steps: Spatial location analysis is performed on the target tree skeleton to obtain the node coordinate set and edge adjacency set. The node coordinate set is identified based on the edge adjacency set to obtain the node degree of each skeleton node. Based on all the node degrees, multiple growth key points are identified from all the skeleton nodes. Based on the tree skeleton connectivity, branch axis tracing is performed on every two adjacent growth key points to obtain the branch axis path corresponding to each growth key point. Then, geometric simplification and attribute calculation are performed on each branch axis path to obtain the branch axis unit at each level. Based on the tree skeleton connectivity, traverse all branch axis units from the root key point to obtain the topological distance of each growth key point relative to the root key point, and establish the inheritance relationship and hierarchy depth between all branch axis units based on the topological distance of each growth key point; Based on the inheritance relationship and the hierarchical depth, all the growth key points are used as graph nodes, and all the branch axis units are used as graph edges to construct the overall semantic subgraph of the target tree skeleton and the local semantic subgraphs of multiple local tree skeletons. The overall semantic subgraph and each of the local semantic subgraphs are subjected to coordinate encoding. The encoding results are then checked for quality. The overall semantic subgraph and all the local semantic subgraphs that pass the quality test are displayed as files in various formats.

[0007] Optionally, in the tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification, the growth key points include: root key points, terminal key points, branch key points and branch axis transition key points. The spatial location analysis of the target tree skeleton yields a set of node coordinates and an edge adjacency set. Based on the edge adjacency set, the node coordinate set is identified to obtain the degree of each skeleton node. Based on all the node degrees, multiple growth keypoints are identified from all the skeleton nodes, specifically including: The three-dimensional spatial positions of all skeleton nodes in the target tree skeleton are analyzed to obtain the three-dimensional coordinates of each skeleton node, and all the three-dimensional coordinates are integrated to obtain the initial node coordinate set; Analyze the topological connectivity between each skeleton node to obtain all skeleton edges, and integrate all skeleton edges to obtain an initial edge adjacency set; After preprocessing the initial node coordinate set and the initial edge adjacency set respectively, the node coordinate set and the edge adjacency set are obtained: ; ; in, Represents the set of node coordinates. Indicates the first One skeleton node This represents the total number of skeleton nodes. express x-coordinate express The ordinate, express The vertical coordinate; ; in, Indicates an edge-adjacent set. Represents a node and nodes The skeleton edges between, Indicates the index of the skeleton edge. This represents the total number of skeleton edges; The preprocessing includes: deleting duplicate skeleton nodes, merging nearest neighbor nodes whose spatial distance is less than a set threshold, and removing skeleton edges whose length is shorter than an edge threshold. Calculate the degree of all skeleton nodes in the node coordinate set: ; in, Indicates the first The degree of each skeleton node Indicates an indicator function; For each of the skeleton nodes, when the node degree is 1 and the skeleton node is located in the lower part of the tree, the skeleton node is defined as a root key point. When the node degree is 1 and the skeleton node is located in the end region of the branch, the skeleton node is defined as the end key point; When the degree of the node is not less than 3, the skeleton node is defined as a branch key point; When the degree of the node is 2, it is determined whether the skeleton node is a key point for branch-axis transition based on the two adjacent nodes of the skeleton node.

[0008] Optionally, the method for constructing a semantic subgraph of a tree skeleton based on growth key points and branch axis simplification, wherein the step of performing spatial location analysis on the target tree skeleton to obtain a set of node coordinates and an edge adjacency set, identifying the node coordinate set based on the edge adjacency set to obtain the node degree of each skeleton node, and identifying multiple growth key points from all the skeleton nodes based on all the node degrees, further includes: Add corresponding semantic tags to each of the aforementioned growth key points: ; in, Represents a set of semantic tags. Semantic tags representing root key points. Semantic tags representing key branch points. Semantic tags representing terminal key points, Semantic tags representing key points in the transition of branches; For each branch key point, construct a set of neighboring nodes for the branch key point, and calculate the number of branches for the branch key point based on the set of neighboring nodes: ; ; in, Indicates the first Key points of branching The set of adjacent nodes, express The adjacent nodes, express and The skeleton edges between, express The number of branches; Construct the branch direction for each of the adjacent nodes: ; in, express and The direction of branching.

[0009] Optionally, the tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification, wherein the step of tracing the branch axis of every two adjacent growth key points according to the tree skeleton connectivity to obtain the branch axis path corresponding to each growth key point, and performing geometric simplification and attribute calculation on each branch axis path to obtain the branch axis unit at each level, specifically includes: Based on the tree skeleton connectivity of the target tree skeleton, starting from any of the growth key points, a search is performed using the adjacent edges of the growth key points as paths until a growth key point adjacent to the growth key point is found. Then, the two growth key points and all the skeleton nodes on the path are combined into a branch-axis path between the two growth key points. ; in, Indicates the first Branch axis path, Indicates the initial critical point of growth. express The first ordinary skeleton node in the process. express The second ordinary skeleton node in the process. express The first in A typical skeleton node The critical point indicating the termination of growth. Indicates the total number of branch paths; Add retrieved tags to all the growth key points for which the branch axis path has been generated, and perform branch axis tracking on all the growth key points for which the retrieved tags have not been added, so as to finally obtain the branch axis path corresponding to each growth key point. Define the main direction and path length for each of the branch paths: ; in, express The main direction; ; in, express Path length, express The number of skeleton edges in the middle, and express Two adjacent skeleton nodes in the middle; Calculate the Euclidean distance between the two critical growth points, and based on the Euclidean distance and the path length, calculate the curvature of the branch path: ; in, Indicates the first The degree of curvature of the branch axis path; For branch paths with a curvature that meets preset requirements, construct branch axis units for the branch path: ; in, Indicates the first Branch axis unit of branch axis path, Indicates the first The hierarchical attributes of branch axis paths.

[0010] Optionally, the method for constructing a semantic subgraph of a tree skeleton based on growth keypoints and simplified branch axes, wherein the step of traversing all branch axis units from the root keypoint according to the tree skeleton connectivity to obtain the topological distance of each growth keypoint relative to the root keypoint, and establishing the inheritance relationship and hierarchical depth among all branch axis units based on the topological distance of each growth keypoint, specifically includes: Starting from the root key point, all growth key points are traversed according to the tree skeleton connectivity to obtain the topological distance between the root key point and all growth key points, and the main direction of the branch axis path between the root key point and all growth key points is determined according to the topological distance. If the termination growth key point of the first branch axis path is the starting growth key point of the second branch axis path, then the first branch axis path is defined as the upstream relationship of the second branch axis path. Based on the sequence of each growth key point, define the upstream and downstream relationships between each branch path, and determine the inheritance relationship and hierarchical depth between all branch units based on all upstream and downstream relationships.

[0011] Optionally, the method for constructing a semantic subgraph of a tree skeleton based on growth key points and simplified branch axes, wherein the step of constructing an overall semantic subgraph of the target tree skeleton and multiple local semantic subgraphs of local tree skeletons based on the inheritance relationship and the hierarchy depth, using all growth key points as graph nodes and all branch axis units as graph edges, specifically includes: Based on the inheritance relationship and the hierarchy depth of each branch unit, all growth key points are defined as graph nodes, all branch units are defined as graph edges, and the overall semantic subgraph of the target tree skeleton is constructed based on all graph nodes and all graph edges. Add the semantic label of each growth key point, the geometric attributes and hierarchical attributes of each branch axis unit to the overall semantic subgraph: ; in, Represents the overall semantic subgraph. Represents the set of critical growth points. Represents the set of branch axis units. Represents a collection of node attributes. Represents the set of edge attributes; For all branch key points that meet the modeling requirements, utilize the branch key points in Construct a local semantic subgraph by considering all growth keypoints and corresponding branch axis units within the order neighborhood: ; in, Represents a local semantic subgraph. This indicates that the distance from the branch key point does not exceed The set of key growth points for the order. This represents the set of branch axis units corresponding to all growth key points.

[0012] Optionally, the method for constructing a tree skeleton semantic subgraph based on growth key points and branch axis simplification includes, in which, coordinate encoding is performed on the overall semantic subgraph and each local semantic subgraph, the encoding results are quality checked, and the qualified overall semantic subgraph and all local semantic subgraphs are displayed as files in various formats, specifically including: For the overall semantic subgraph and each of the local semantic subgraphs, taking any node in any graph as the local coordinate origin, all nodes are converted to relative coordinates based on the local coordinate origin: ; in, Indicates the first The relative coordinates of each node Indicates the first The coordinates of each node in the graph. Indicates the local coordinate origin; Based on the scale of the graph, the relative coordinates of all the nodes in the graph are normalized to obtain the normalized coordinates of each node: ; in, express Normalized coordinates, Indicates the maximum spatial extent of the graph; The semantic label, geometric attributes, hierarchical attributes, branch axis direction, and length attributes of each node are uniformly encoded to obtain the encoding result of the graph: ; in, This indicates the encoding result. Represents the node feature matrix, Represents the adjacency matrix of a subgraph. Represents the edge feature matrix, Indicates the overall properties of the subgraph; All the encoding results are subjected to quality checks to correct encoding results with abnormal node counts, abnormal branches and axes, incomplete connection relationships, and isolated nodes, and finally all semantic subgraphs are obtained. All node information, branch information, and subgraph information of all the semantic subgraphs are constructed into node files, branch files, and subgraph files, respectively, and all the semantic subgraphs are visualized.

[0013] Furthermore, to achieve the above objectives, the present invention also provides a tree skeleton semantic subgraph construction system based on simplified growth key points and branch axes, wherein the tree skeleton semantic subgraph construction system based on simplified growth key points and branch axes includes: The key point identification module is used to perform spatial location analysis on the target tree skeleton to obtain a set of node coordinates and an edge adjacency set. Based on the edge adjacency set, the node coordinate set is identified to obtain the node degree of each skeleton node. Based on all the node degrees, multiple growth key points are identified from all the skeleton nodes. The attribute acquisition module is used to trace the branch axis of every two adjacent growth key points according to the tree skeleton connectivity, obtain the branch axis path corresponding to each growth key point, and perform geometric simplification and attribute calculation on each branch axis path to obtain the branch axis unit at each level. The hierarchy determination module is used to traverse all the branch axis units from the root key point according to the tree skeleton connectivity relationship, obtain the topological distance of each growth key point relative to the root key point, and establish the inheritance relationship and hierarchy depth between all the branch axis units according to the topological distance of each growth key point; The subgraph construction module is used to construct the overall semantic subgraph of the target tree skeleton and multiple local semantic subgraphs of the local tree skeleton based on the inheritance relationship and the hierarchical depth, taking all the growth key points as graph nodes and all the branch axis units as graph edges. The visualization module is used to perform coordinate encoding processing on the overall semantic subgraph and each of the local semantic subgraphs, perform quality checks on the encoding results, and display the overall semantic subgraph and all the local semantic subgraphs that pass the quality test as files in various formats.

[0014] Furthermore, to achieve the above objectives, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a tree skeleton semantic subgraph construction program based on growth key points and branch axis simplification stored in the memory and executable on the processor, wherein when the tree skeleton semantic subgraph construction program based on growth key points and branch axis simplification is executed by the processor, it implements the steps of the tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification as described above.

[0015] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a tree skeleton semantic subgraph construction program based on growth key points and branch axis simplification, and the tree skeleton semantic subgraph construction program based on growth key points and branch axis simplification, when executed by a processor, implements the steps of the tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification as described above.

[0016] In this invention, spatial location analysis is performed on the target tree skeleton to obtain a set of node coordinates and an edge adjacency set. The node coordinates are then identified based on the edge adjacency set to obtain the degree of each skeleton node. Based on all the node degrees, multiple growth key points are identified from all the skeleton nodes. Branch-axis tracing is performed on every two adjacent growth key points according to the tree skeleton connectivity to obtain the branch-axis path corresponding to each growth key point. Geometric simplification and attribute calculation are then performed on each branch-axis path to obtain branch-axis units at each level. Finally, based on the tree skeleton connectivity, all branch-axis units are traversed from the root key point to obtain each... The topological distance between each growth keypoint and the root keypoint is used to establish the inheritance relationship and hierarchical depth among all branch units. Based on the inheritance relationship and hierarchical depth, all growth keypoints are treated as graph nodes, and all branch units are treated as graph edges to construct the overall semantic subgraph of the target tree skeleton and multiple local semantic subgraphs of local tree skeletons. Coordinate encoding is performed on the overall semantic subgraph and each local semantic subgraph, and the encoding results are quality checked. The qualified overall semantic subgraph and all local semantic subgraphs are displayed as files in various formats. This invention can convert dense tree skeletons into semantically clear and scale-uniform local subgraph representations, reducing the data complexity of subsequent learning and analysis. Attached Figure Description

[0017] Figure 1 This is a flowchart of a preferred embodiment of the tree skeleton semantic subgraph construction method based on growth key points and simplified branch axes of the present invention; Figure 2 This is a flowchart of a preferred embodiment of the tree skeleton semantic subgraph construction method based on growth key points and simplified branch axes of the present invention. Figure 3 This is a schematic diagram of branch axis division and hierarchy determination in a preferred embodiment of the tree skeleton semantic subgraph construction method based on growth key points and simplified branch axes of the present invention. Figure 4 This is a flowchart of semantic subgraph encoding and standardized output of a preferred embodiment of the semantic subgraph construction method for tree skeleton based on growth key points and simplified branch axes of the present invention. Figure 5 This is a structural diagram of a preferred embodiment of the tree skeleton semantic subgraph construction system based on the simplification of growth key points and branch axes of the present invention; Figure 6 This is a structural diagram of a preferred embodiment of the terminal of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] Existing tree skeleton data is typically represented by dense nodes and edge connections, which suffers from redundancy in branches and axes, local noise, unclear key growth locations, and difficulty in standardizing and encoding local structures. Therefore, this invention proposes a tree skeleton semantic subgraph construction method based on growth key points and simplified branches and axes. Without destroying the parent-child topological relationships and branch semantics of the tree skeleton, it automatically extracts growth key points, performs topological simplification of branches and axes, and constructs a tree skeleton semantic subgraph with unified semantic fields and reusable structural expressions.

[0020] The preferred embodiment of the present invention describes a method for constructing a semantic subgraph of a tree skeleton based on growth key points and simplified branch axes, such as... Figure 1 As shown, the method for constructing a semantic subgraph of a tree skeleton based on growth key points and simplified branch axes includes the following steps: Step S10: Perform spatial location analysis on the target tree skeleton to obtain the node coordinate set and edge adjacency set. Identify the node coordinate set based on the edge adjacency set to obtain the node degree of each skeleton node. Based on all the node degrees, identify multiple growth key points from all the skeleton nodes.

[0021] Among them, such as Figure 2 As shown, this method uses an existing tree skeleton as input and focuses on solving the problem of transforming the tree skeleton from an original dense graph to a local semantic subgraph. After normalizing the tree skeleton data, the obtained 3D tree skeleton data is used to identify growth key points, so that the subsequent branch axis construction no longer depends on a large number of fragmented points, but revolves around nodes with structural significance. Among them, growth key points include: root key points, terminal key points, branch key points, and branch axis transition key points.

[0022] Specifically, the three-dimensional spatial positions of all skeleton nodes in the target tree skeleton are analyzed to obtain the three-dimensional coordinates of each skeleton node, and all the three-dimensional coordinates are integrated to obtain an initial node coordinate set; Analyze the topological connectivity between each skeleton node to obtain all skeleton edges, and integrate all skeleton edges to obtain an initial edge adjacency set; After preprocessing the initial node coordinate set and the initial edge adjacency set respectively, the node coordinate set and the edge adjacency set are obtained: ; ; in, Represents the set of node coordinates. Indicates the first One skeleton node This represents the total number of skeleton nodes. express x-coordinate express The ordinate, express The vertical coordinate; ; in, Indicates an edge-adjacent set. Represents a node and nodes The skeleton edges between, Indicates the index of the skeleton edge. This represents the total number of skeleton edges; The preprocessing includes: deleting duplicate skeleton nodes, merging nearest neighbor nodes whose spatial distance is less than a set threshold, and removing skeleton edges whose length is shorter than an edge threshold. Calculate the degree of all skeleton nodes in the node coordinate set: ; in, Indicates the first The degree of each skeleton node This indicates an indicator function, meaning that when the node... Belongs to the edge The value is 1 if the condition is met, and 0 otherwise. For each of the skeleton nodes, when the node degree is 1 and the skeleton node is located in the lower part of the tree, the skeleton node is defined as a root key point. When the node degree is 1 and the skeleton node is located in the end region of the branch, the skeleton node is defined as the end key point; When the degree of the node is not less than 3, the skeleton node is defined as a branch key point; When the degree of the node is 2, it is determined whether the skeleton node is a key point for branch-axis transition based on the two adjacent nodes of the skeleton node.

[0023] To ensure consistency in subsequent keypoint identification and branch simplification results, the tree skeleton data is first preprocessed. This includes deleting duplicate nodes, merging nearest neighbor nodes with a spatial distance less than a set threshold, removing abnormally short noise edges that do not affect overall connectivity, checking the connectivity of the skeleton graph, and determining root candidate regions based on the tree height direction. Within these candidate regions, the root node is determined. This yields the node set and edge adjacency set of the target tree skeleton. The node set represents the three-dimensional spatial position of each skeleton node, and the edge adjacency set represents the topological connectivity between nodes. Then, the connectivity of the skeleton graph is checked, and root candidate regions are determined based on the tree height direction. Within these candidate regions, the root node is determined, and the degree of each skeleton node is calculated. In this process, the invention effectively reduces the impact of acquisition noise, reconstruction errors, and locally redundant nodes on the keypoint identification results, ensuring the input skeleton has a clear connectivity structure and a stable spatial scale foundation.

[0024] Furthermore, after preprocessing, growth key points are identified in the nodes of the tree skeleton; among them, growth key points can reflect the tree's growth organization relationship, branching behavior and structural boundaries, including at least root key points, branch key points, terminal key points and branch axis transition key points.

[0025] When a key point has 2 nodes, the angle between two adjacent sides can be used to determine whether the key point is a branch axis transition key point. Branch axis transition key points retain positions in the skeleton with significant bends or changes in growth direction, avoiding excessive smoothing of tree branch morphology in the subsequent simplification process.

[0026] Node Two adjacent nodes are defined as and Then the directions of adjacent edges can be represented as: ; ; in, Represents a node With neighboring nodes The direction of the adjacent side, Represents a node With neighboring nodes The directions of adjacent sides; based on this, the included angle between two adjacent sides can be determined: ; in, express neighboring nodes and The included angle between adjacent sides.

[0027] when When the angle exceeds a preset threshold, it indicates a significant directional change near the node, which can be identified as a key transition point for the branch axis. Extracting key nodes with growth semantics from the original skeleton nodes allows subsequent branch axis construction to focus on nodes with structural significance rather than relying on numerous fragmented points, thus improving the efficiency of tree skeleton modeling.

[0028] Furthermore, a corresponding semantic tag is added to each of the aforementioned growth key points: ; in, Represents a set of semantic tags. Semantic tags representing root key points. Semantic tags representing key branch points. Semantic tags representing terminal key points, Semantic tags representing key points in the transition of branches; For each branch key point, construct a set of neighboring nodes for the branch key point, and calculate the number of branches for the branch key point based on the set of neighboring nodes: ; ; in, Indicates the first Key points of branching The set of adjacent nodes, express The adjacent nodes, express and The skeleton edges between, express The number of branches; Construct the branch direction for each of the adjacent nodes: ; in, express and The direction of branching.

[0029] After identifying key growth points, this invention assigns semantic type labels to each key point, including root nodes, branch nodes, terminal nodes, and transition nodes. For branch key points, the number of branches, branch angles, and branch directions are further calculated to obtain a local set of branch directions at that key point. This set can be used to describe the branching morphology of the tree at a local location, providing node-level structural attributes for subsequent construction of semantic subgraphs. This invention adds corresponding semantic meanings to each key growth point, enabling the tree skeleton to evolve from simple geometric connections to a structural expression that includes growth organization relationships.

[0030] Step S20: Based on the tree skeleton connectivity, perform branch axis tracing on every two adjacent growth key points to obtain the branch axis path corresponding to each growth key point, and perform geometric simplification and attribute calculation on each branch axis path to obtain the branch axis unit at each level.

[0031] After obtaining the set of key growth points, the present invention continues to trace branches along the tree skeleton connectivity and performs geometric simplification and attribute calculation for each branch.

[0032] Specifically, based on the tree skeleton connectivity of the target tree skeleton, a search is performed starting from any of the growth key points and using the adjacent edges of the growth key points as paths, until a growth key point adjacent to the growth key point is found. Then, the two growth key points and all the skeleton nodes on the path are combined into a branch-axis path between the two growth key points. ; in, Indicates the first Branch axis path, Indicates the initial critical point of growth. express The first ordinary skeleton node in the process. express The second ordinary skeleton node in the process. express The first in A typical skeleton node The critical point indicating the termination of growth. Indicates the total number of branch paths; Add retrieved tags to all the growth key points for which the branch axis path has been generated, and perform branch axis tracking on all the growth key points for which the retrieved tags have not been added, so as to finally obtain the branch axis path corresponding to each growth key point.

[0033] In this context, a branch axis refers to a continuous skeletal path connecting two adjacent keypoints. This path typically consists of several ordinary nodes with a degree of 2, and as a whole, it represents a continuously growing branch axis. Starting from each keypoint, a path search is performed along its adjacent edges. When another keypoint is encountered during the search, the current path tracing stops, and the sequence of the starting keypoint, the ending keypoint, and the intermediate nodes between them are combined to form a branch axis path.

[0034] To avoid redundant tracing, visited edges are marked during path search. Once an edge has been assigned to a branch path, it will not be used again to construct other branch paths, unless the edge is a shared connection edge at a branch key point. By organizing the numerous continuous fragmented edges in the original skeleton into branch paths with clearly defined start and end key points, the tree skeleton is elevated from a "node-edge" level to a "key point-branch" level expression.

[0035] Define the main direction and path length for each of the branch paths: ; in, express The main direction; ; in, express Path length, express The number of skeleton edges in the middle, and express Two adjacent skeleton nodes in the middle; Calculate the Euclidean distance between the two critical growth points, and based on the Euclidean distance and the path length, calculate the curvature of the branch path: ; in, Indicates the first The degree of curvature of the branch axis path; For branch paths with a curvature that meets preset requirements, construct branch axis units for the branch path: ; in, Indicates the first Branch axis unit of branch axis path, Indicates the first The hierarchical attributes of branch axis paths.

[0036] The goal of branch simplification is not to remove its structural meaning, but to abstract a continuous path composed of multiple fragmented edges into a branch unit. For a given branch, if the branch is straight, all ordinary nodes in the middle of the branch can be omitted, and only the two endpoints of the branch can be retained, which can significantly reduce the complexity of the original skeleton.

[0037] Furthermore, if the degree of bending of the branch axis is large (i.e. If the tree is relatively large, then its local curvature needs to be preserved. In this case, multiple sampling points can be used to represent its centerline. Finally, while maintaining the main growth form and branching relationship of the tree, it is simplified to obtain a branch axis level expression that is more suitable for semantic modeling, local pattern statistics and subsequent structure learning.

[0038] Step S30: Traverse all branch axis units from the root key point according to the tree skeleton connectivity relationship, obtain the topological distance of each growth key point relative to the root key point, and establish the inheritance relationship and hierarchy depth between all branch axis units according to the topological distance of each growth key point.

[0039] Specifically, starting from the root key point, all the growth key points are traversed according to the tree skeleton connectivity to obtain the topological distance between the root key point and all the growth key points, and the main direction of the branch axis path between the root key point and all the growth key points is determined according to the topological distance. If the termination growth key point of the first branch axis path is the starting growth key point of the second branch axis path, then the first branch axis path is defined as the upstream relationship of the second branch axis path. Based on the sequence of each growth key point, define the upstream and downstream relationships between each branch path, and determine the inheritance relationship and hierarchical depth between all branch units based on all upstream and downstream relationships.

[0040] Among them, such as Figure 3 As shown, after simplifying the branch axes, the hierarchical relationship between branches is determined based on the connectivity direction of the tree skeleton from the root to the end. First, starting from the root key point, a breadth-first or depth-first traversal is performed along the skeleton connectivity to determine the topological distance of each key point relative to the root node. Then, the branch axis direction is determined based on the topological distance between the start and end points of the branch axis.

[0041] Among them, based on the embodiments disclosed in this invention, for branch axes (its two endpoints are) and ),like The topological distance relative to the root node is less than Then it is assumed that the direction of the branch axis is from point to Conversely, the starting and ending points are interchanged. This yields a set of directed branches that expand outwards from the root.

[0042] Furthermore, if the termination key point of one branch axis is the same as the starting key point of another branch axis, then the former branch axis is the upstream branch axis of the latter branch axis, and the latter branch axis is the downstream branch axis of the former branch axis. Based on this relationship, the inheritance relationship and hierarchical depth between branches axis can be established (where... Indicates the grade of the main shaft. Indicates the first-order branch axis. Indicates secondary branch axis, (Representing terminal branches); by assigning hierarchical relationships to branch units that conform to the tree's growth direction, the constructed semantic subgraph can express the organizational structure from the trunk to the lateral branches, and from the primary branches to the terminal branches.

[0043] Step S40: Based on the inheritance relationship and the hierarchical depth, all the growth key points are used as graph nodes, and all the branch axis units are used as graph edges to construct the overall semantic subgraph of the target tree skeleton and the local semantic subgraphs of multiple local tree skeletons.

[0044] Specifically, based on the inheritance relationship and the hierarchical depth of each branch axis unit, all growth key points are defined as graph nodes, all branch axis units are defined as graph edges, and an overall semantic subgraph of the target tree skeleton is constructed based on all graph nodes and all graph edges; Add the semantic label of each growth key point, the geometric attributes and hierarchical attributes of each branch axis unit to the overall semantic subgraph: ; in, Represents the overall semantic subgraph. Represents the set of critical growth points. Represents the set of branch axis units. Represents a collection of node attributes. Represents the set of edge attributes; For all branch key points that meet the modeling requirements, utilize the branch key points in Construct a local semantic subgraph by considering all growth keypoints and corresponding branch axis units within the order neighborhood: ; in, Represents a local semantic subgraph. This indicates that the distance from the branch key point does not exceed The set of key growth points for the order. This represents the set of branch axis units corresponding to all growth key points.

[0045] In the embodiments disclosed in this invention, the semantic subgraph uses growth keypoints as graph nodes and branch axis units as graph edges, and incorporates the semantics of keypoints, the geometric attributes of branches and axes, and hierarchical attributes into the graph structure. For complex tree structures, a local semantic subgraph can be further constructed around a specific branch keypoint. This local semantic subgraph can be used to describe local tree structure patterns, such as trunk-side branch connection patterns, multi-branching patterns, and terminal branch cluster patterns. By transforming the tree skeleton into a graph structure representation containing semantic nodes and semantic edges, it can be used for local structure analysis, tree pattern retrieval, structural prototype learning, and conditional encoding of subsequent generative models.

[0046] Step S50: Perform coordinate encoding processing on the overall semantic subgraph and each of the local semantic subgraphs, perform quality checks on the encoding results, and display the qualified overall semantic subgraphs and all the local semantic subgraphs as files in various formats.

[0047] In order to facilitate comparison and learning between different tree samples, the semantic subgraph is standardized and encoded. After obtaining the semantic subgraph, subgraph filtering and structural quality checks can be performed to finally output the tree skeleton semantic subgraph result.

[0048] Specifically, for the overall semantic subgraph and each of the local semantic subgraphs, taking any node in any graph as the local coordinate origin, all nodes are converted to relative coordinates based on the local coordinate origin: ; in, Indicates the first The relative coordinates of each node Indicates the first The coordinates of each node in the graph. Indicates the local coordinate origin; Based on the scale of the graph, the relative coordinates of all the nodes in the graph are normalized to obtain the normalized coordinates of each node: ; in, express Normalized coordinates, Indicates the maximum spatial extent of the graph; The semantic label, geometric attributes, hierarchical attributes, branch axis direction, and length attributes of each node are uniformly encoded to obtain the encoding result of the graph: ; in, This indicates the encoding result. Represents the node feature matrix, Represents the adjacency matrix of a subgraph. Represents the edge feature matrix, Indicates the overall properties of the subgraph; All the encoding results are subjected to quality checks to correct encoding results with abnormal node counts, abnormal branches and axes, incomplete connection relationships, and isolated nodes, and finally all semantic subgraphs are obtained. All node information, branch information, and subgraph information of all the semantic subgraphs are constructed into node files, branch files, and subgraph files, respectively, and all the semantic subgraphs are visualized.

[0049] This process involves local coordinate normalization of node coordinates in the subgraph. First, a key node is used as the center. Then, within this semantic subgraph (or local semantic subgraph), other nodes can be converted to relative coordinates based on this key node. Finally, the coordinates are normalized according to the subgraph scale. Simultaneously, node semantic type, branch type, hierarchy attribute, direction attribute, and length attribute are encoded into a unified format. For node semantic type, integer labels or one-hot encoding can be used; for branch direction, length, and curvature, continuous numerical encoding can be used; and for branch hierarchy, discrete hierarchy encoding can be used. By converting local tree skeleton structures of different scales, locations, and topological complexities into a unified data representation, subsequent machine learning modeling, structural clustering, template matching, or local structure generation are facilitated.

[0050] Furthermore, subgraphs with too few nodes, abnormal branch lengths, incomplete connections, or isolated nodes can be removed or corrected. For local subgraphs near key branch points, the number of branches can be checked to ensure it meets the node semantic label requirements, avoiding inconsistencies between semantic labels and actual connectivity. For example, first check if the subgraph is connected, and determine if the semantic type of the key point matches the node degree. Second, check if the branch direction conforms to the direction of expansion from the root to the end. Then, check if the branch length, curvature, and level attributes are within a reasonable range. Finally, check if the local subgraph contains duplicate edges, isolated points, or invalid cycles.

[0051] For subgraphs that do not meet quality requirements, corrections can be made as needed. For example, duplicate nodes can be merged; extremely short branches can be deleted or merged into adjacent branches; branches with incorrect orientations can be readjusted based on root topological distance; and locally broken structures can be repaired by connecting them based on spatial proximity and topological continuity. This process can effectively improve the standardization and reliability of semantic subgraph data and reduce the impact of abnormal skeleton data on subsequent analysis and learning processes.

[0052] Among them, such as Figure 4As shown in the embodiments disclosed in this invention, after the semantic subgraph is constructed, its results can be output, specifically including a set of growth keypoints, keypoint semantic labels, a simplified branch axis set, branch axis geometric attributes, branch axis hierarchical attributes, a set of local semantic subgraphs, and standardized coding results; and the output format can generate different files according to different content, such as: node files ( Figure 4 The node feature matrix in step 5 can store keypoint numbers, keypoint coordinates, keypoint semantic types, and node degrees; branch axis text ( Figure 4 The adjacency matrix in step 5 can record the branch axis start point, branch axis end point, branch axis length, branch axis direction, branch axis curvature, and branch axis level; subgraph file ( Figure 4 The edge feature matrix in step 5 is used to record the node set, edge set, adjacency relationship, and attribute features of each local semantic subgraph; the visualization file ( Figure 4 The overall attributes in step 5 can display the spatial distribution results of key points, branches, and semantic subgraphs. Compared with methods that directly use the original skeleton nodes and edges for analysis, this invention can highlight the key structures of tree growth, reduce skeleton redundancy and complexity, enhance the expressive power of local structures, and provide standardized input for semantic analysis and structure learning of tree skeletons.

[0053] This invention can convert dense tree skeletons into semantically clear and scale-uniform local subgraph representations, reducing the data complexity of subsequent learning and analysis.

[0054] Furthermore, such as Figure 5 As shown, based on the above-described method for constructing a tree skeleton semantic subgraph based on simplified growth key points and branch axes, this invention also provides a system for constructing a tree skeleton semantic subgraph based on simplified growth key points and branch axes, wherein the system for constructing a tree skeleton semantic subgraph based on simplified growth key points and branch axes includes: The key point identification module 51 is used to perform spatial position analysis on the target tree skeleton to obtain a set of node coordinates and an edge adjacency set. Based on the edge adjacency set, the node coordinate set is identified to obtain the node degree of each skeleton node. Based on all the node degrees, multiple growth key points are identified from all the skeleton nodes. The attribute acquisition module 52 is used to perform branch axis tracing on every two adjacent growth key points according to the tree skeleton connectivity, to obtain the branch axis path corresponding to each growth key point, and to perform geometric simplification and attribute calculation on each branch axis path to obtain the branch axis unit at each level. The hierarchy determination module 53 is used to traverse all the branch axis units from the root key point according to the tree skeleton connectivity relationship, obtain the topological distance of each growth key point relative to the root key point, and establish the inheritance relationship and hierarchy depth between all the branch axis units according to the topological distance of each growth key point. The subgraph construction module 54 is used to construct the overall semantic subgraph of the target tree skeleton and multiple local semantic subgraphs of the local tree skeleton based on the inheritance relationship and the hierarchical depth, taking all the growth key points as graph nodes and all the branch axis units as graph edges. The visualization module 55 is used to perform coordinate encoding processing on the overall semantic subgraph and each of the local semantic subgraphs, perform quality checks on the encoding results, and display the overall semantic subgraph and all the local semantic subgraphs that have passed the quality test as files in various formats.

[0055] Furthermore, such as Figure 6 As shown, based on the above-mentioned method and system for constructing a semantic subgraph of a tree skeleton based on growth key points and branch axis simplification, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 6 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0056] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a tree skeleton semantic subgraph construction program 40 based on simplified growth key points and branch axes. This tree skeleton semantic subgraph construction program 40 can be executed by the processor 10, thereby implementing the tree skeleton semantic subgraph construction method based on simplified growth key points and branch axes in this application.

[0057] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification.

[0058] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0059] In one embodiment, when the processor 10 executes the tree skeleton semantic subgraph construction program 40 based on growth key points and branch axes simplified in the memory 20, it implements the steps of the tree skeleton semantic subgraph construction method based on growth key points and branch axes simplified as described above.

[0060] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a tree skeleton semantic subgraph construction program based on growth key points and branch axis simplification, and the tree skeleton semantic subgraph construction program based on growth key points and branch axis simplification, when executed by a processor, implements the steps of the tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification as described above.

[0061] In summary, this invention provides a method and related equipment for constructing a semantic subgraph of a tree skeleton based on growth key points and branch axis simplification. The method includes: performing spatial location analysis on the target tree skeleton to obtain a set of node coordinates and an edge adjacency set; identifying the node coordinate set based on the edge adjacency set to obtain the node degree of each skeleton node; identifying multiple growth key points from all the skeleton nodes based on all the node degrees; tracing the branch axis of every two adjacent growth key points according to the tree skeleton connectivity to obtain the branch axis path corresponding to each growth key point; and performing geometric simplification and attribute calculation on each branch axis path to obtain branch axis units at each level; and constructing a semantic subgraph of a tree skeleton based on the tree skeleton connectivity. The root keypoint traverses all branch axis units to obtain the topological distance of each growth keypoint relative to the root keypoint. Based on the topological distance of each growth keypoint, the inheritance relationship and hierarchical depth among all branch axis units are established. Based on the inheritance relationship and hierarchical depth, all growth keypoints are used as graph nodes, and all branch axis units are used as graph edges to construct the overall semantic subgraph of the target tree skeleton and multiple local semantic subgraphs of local tree skeletons. The overall semantic subgraph and each local semantic subgraph are subjected to coordinate encoding processing, the encoding results are quality checked, and the qualified overall semantic subgraph and all local semantic subgraphs are displayed as files in various formats. This invention can convert dense tree skeletons into semantically clear and scale-uniform local subgraph representations, reducing the data complexity of subsequent learning and analysis.

[0062] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.

[0063] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The computer-readable storage medium can be a memory, magnetic disk, optical disk, etc.

[0064] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for constructing a semantic subgraph of a tree skeleton based on growth key points and simplified branch axes, characterized in that, The tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification includes: Spatial location analysis is performed on the target tree skeleton to obtain the node coordinate set and edge adjacency set. The node coordinate set is identified based on the edge adjacency set to obtain the node degree of each skeleton node. Based on all the node degrees, multiple growth key points are identified from all the skeleton nodes. Based on the tree skeleton connectivity, branch axis tracing is performed on every two adjacent growth key points to obtain the branch axis path corresponding to each growth key point. Then, geometric simplification and attribute calculation are performed on each branch axis path to obtain the branch axis unit at each level. Based on the tree skeleton connectivity, traverse all branch axis units from the root key point to obtain the topological distance of each growth key point relative to the root key point, and establish the inheritance relationship and hierarchy depth between all branch axis units based on the topological distance of each growth key point; Based on the inheritance relationship and the hierarchical depth, all the growth key points are used as graph nodes, and all the branch axis units are used as graph edges to construct the overall semantic subgraph of the target tree skeleton and the local semantic subgraphs of multiple local tree skeletons. The overall semantic subgraph and each of the local semantic subgraphs are subjected to coordinate encoding. The encoding results are then checked for quality. The overall semantic subgraph and all the local semantic subgraphs that pass the quality test are displayed as files in various formats.

2. The tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification according to claim 1, characterized in that, The key growth points include: root key points, terminal key points, branching key points, and branch axis transition key points; The spatial location analysis of the target tree skeleton yields a set of node coordinates and an edge adjacency set. Based on the edge adjacency set, the node coordinate set is identified to obtain the degree of each skeleton node. Based on all the node degrees, multiple growth keypoints are identified from all the skeleton nodes, specifically including: The three-dimensional spatial positions of all skeleton nodes in the target tree skeleton are analyzed to obtain the three-dimensional coordinates of each skeleton node, and all the three-dimensional coordinates are integrated to obtain the initial node coordinate set; Analyze the topological connectivity between each skeleton node to obtain all skeleton edges, and integrate all skeleton edges to obtain an initial edge adjacency set; After preprocessing the initial node coordinate set and the initial edge adjacency set respectively, the node coordinate set and the edge adjacency set are obtained: ； ； in, Represents the set of node coordinates. Indicates the first One skeleton node This represents the total number of skeleton nodes. express x-coordinate express The ordinate, express The vertical coordinate; ； in, Indicates an edge-adjacent set. Represents a node and nodes The skeleton edges between, Indicates the index of the skeleton edge. This represents the total number of skeleton edges; The preprocessing includes: deleting duplicate skeleton nodes, merging nearest neighbor nodes whose spatial distance is less than a set threshold, and removing skeleton edges whose length is shorter than an edge threshold. Calculate the degree of all skeleton nodes in the node coordinate set: ； in, Indicates the first The degree of each skeleton node Indicates an indicator function; For each of the skeleton nodes, when the node degree is 1 and the skeleton node is located in the lower part of the tree, the skeleton node is defined as a root key point. When the node degree is 1 and the skeleton node is located in the end region of the branch, the skeleton node is defined as the end key point; When the degree of the node is not less than 3, the skeleton node is defined as a branch key point; When the degree of the node is 2, it is determined whether the skeleton node is a key point for branch-axis transition based on the two adjacent nodes of the skeleton node.

3. The tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification according to claim 1, characterized in that, The process involves performing spatial location analysis on the target tree skeleton to obtain a set of node coordinates and an edge adjacency set. Based on the edge adjacency set, the node coordinate set is identified to obtain the degree of each skeleton node. Based on all the node degrees, multiple growth keypoints are identified from all the skeleton nodes. The process then further includes: Add corresponding semantic tags to each of the aforementioned growth key points: ； in, Represents a set of semantic tags. Semantic tags representing root key points. Semantic tags representing key branch points. Semantic tags representing terminal key points, Semantic tags representing key points in the transition of branches; For each branch key point, construct a set of neighboring nodes for the branch key point, and calculate the number of branches for the branch key point based on the set of neighboring nodes: ； ； in, Indicates the first Key points of branching The set of adjacent nodes, express The adjacent nodes, express and The skeleton edges between, express The number of branches, Represents an edge-adjacent set; Construct the branch direction for each of the adjacent nodes: ； in, express and The direction of branching.

4. The tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification according to claim 1, characterized in that, The process involves tracing the branch axis of every two adjacent growth key points based on the tree skeleton connectivity to obtain the branch axis path corresponding to each growth key point. Then, geometric simplification and attribute calculation are performed on each branch axis path to obtain the branch axis unit at each level. Specifically, this includes: Based on the tree skeleton connectivity of the target tree skeleton, starting from any of the growth key points, a search is performed using the adjacent edges of the growth key points as paths until a growth key point adjacent to the growth key point is found. Then, the two growth key points and all the skeleton nodes on the path are combined into a branch-axis path between the two growth key points. ； in, Indicates the first Branch axis path, Indicates the initial critical point of growth. express The first ordinary skeleton node in the process. express The second ordinary skeleton node in the process. express The first in A typical skeleton node The critical point indicating the termination of growth. Indicates the total number of branch paths; Add retrieved tags to all the growth key points for which the branch axis path has been generated, and perform branch axis tracking on all the growth key points for which the retrieved tags have not been added, so as to finally obtain the branch axis path corresponding to each growth key point. Define the main direction and path length for each of the branch paths: ； in, express The main direction; ； in, express Path length, express The number of skeleton edges in the middle, and express Two adjacent skeleton nodes in the middle; Calculate the Euclidean distance between the two critical growth points, and based on the Euclidean distance and the path length, calculate the curvature of the branch path: ； in, Indicates the first The degree of curvature of the branch axis path; For branch paths with a curvature that meets preset requirements, construct branch axis units for the branch path: ； in, Indicates the first Branch axis unit of branch axis path, Indicates the first The hierarchical attributes of branch axis paths.

5. The method for constructing a semantic subgraph of a tree skeleton based on growth key points and simplified branch axes according to claim 1, characterized in that, The step of traversing all branch axis units from the root keypoint according to the tree skeleton connectivity to obtain the topological distance of each growth keypoint relative to the root keypoint, and establishing the inheritance relationship and hierarchy depth among all branch axis units based on the topological distance of each growth keypoint, specifically includes: Starting from the root key point, all growth key points are traversed according to the tree skeleton connectivity to obtain the topological distance between the root key point and all growth key points, and the main direction of the branch axis path between the root key point and all growth key points is determined according to the topological distance. If the termination point of the first branch axis path is the starting point of the second branch axis path, then the first branch axis path is defined as the upstream path of the second branch axis path. Based on the sequence of each growth key point, define the upstream and downstream relationships between each branch path, and determine the inheritance relationship and hierarchical depth between all branch units based on all upstream and downstream relationships.

6. The method for constructing a semantic subgraph of a tree skeleton based on growth key points and branch axis simplification according to claim 1, characterized in that, Based on the inheritance relationship and the hierarchical depth, all the growth key points are treated as graph nodes, and all the branch axis units are treated as graph edges. This process constructs an overall semantic subgraph of the target tree skeleton and multiple local semantic subgraphs of local tree skeletons, specifically including: Based on the inheritance relationship and the hierarchy depth of each branch unit, all growth key points are defined as graph nodes, all branch units are defined as graph edges, and the overall semantic subgraph of the target tree skeleton is constructed based on all graph nodes and all graph edges. Add the semantic label of each growth key point, the geometric attributes and hierarchical attributes of each branch axis unit to the overall semantic subgraph: ； in, Represents the overall semantic subgraph. Represents the set of critical growth points. Represents the set of branch axis units. Represents a collection of node attributes. Represents the set of edge attributes; For all branch key points that meet the modeling requirements, utilize the branch key points in Construct a local semantic subgraph by considering all growth keypoints and corresponding branch axis units within the order neighborhood: ； in, Represents a local semantic subgraph. This indicates that the distance from the branch key point does not exceed The set of key growth points for the order. This represents the set of branch axis units corresponding to all growth key points.

7. The method for constructing a semantic subgraph of a tree skeleton based on simplified growth key points and branch axes according to claim 1, characterized in that, The process of performing coordinate encoding on the overall semantic subgraph and each of the local semantic subgraphs, performing quality checks on the encoding results, and displaying the qualified overall semantic subgraph and all of the local semantic subgraphs as files in various formats specifically includes: For the overall semantic subgraph and each of the local semantic subgraphs, taking any node in any graph as the local coordinate origin, all nodes are converted to relative coordinates based on the local coordinate origin: ； in, Indicates the first The relative coordinates of each node Indicates the first The coordinates of each node in the graph. Indicates the local coordinate origin; Based on the scale of the graph, the relative coordinates of all the nodes in the graph are normalized to obtain the normalized coordinates of each node: ； in, express Normalized coordinates, Indicates the maximum spatial extent of the graph; The semantic label, geometric attributes, hierarchical attributes, branch axis direction, and length attributes of each node are uniformly encoded to obtain the encoding result of the graph: ； in, This indicates the encoding result. Represents the node feature matrix, Represents the adjacency matrix of the subgraph. Represents the edge feature matrix, Indicates the overall properties of the subgraph; All the encoding results are subjected to quality checks to correct encoding results with abnormal node counts, abnormal branches and axes, incomplete connection relationships, and isolated nodes, and finally all semantic subgraphs are obtained. All node information, branch information, and subgraph information of all the semantic subgraphs are constructed into node files, branch files, and subgraph files, respectively, and all the semantic subgraphs are visualized.

8. A tree skeleton semantic subgraph construction system based on simplified growth key points and branch axes, characterized in that, The tree skeleton semantic subgraph construction system based on simplified growth key points and branch axes is used to implement the tree skeleton semantic subgraph construction method based on simplified growth key points and branch axes as described in any one of claims 1-7. The tree skeleton semantic subgraph construction system based on simplified growth key points and branch axes includes: The key point identification module is used to perform spatial location analysis on the target tree skeleton to obtain a set of node coordinates and an edge adjacency set. Based on the edge adjacency set, the node coordinate set is identified to obtain the node degree of each skeleton node. Based on all the node degrees, multiple growth key points are identified from all the skeleton nodes. The attribute acquisition module is used to trace the branch axis of every two adjacent growth key points according to the tree skeleton connectivity, obtain the branch axis path corresponding to each growth key point, and perform geometric simplification and attribute calculation on each branch axis path to obtain the branch axis unit at each level. The hierarchy determination module is used to traverse all the branch axis units from the root key point according to the tree skeleton connectivity relationship, obtain the topological distance of each growth key point relative to the root key point, and establish the inheritance relationship and hierarchy depth between all the branch axis units according to the topological distance of each growth key point; The subgraph construction module is used to construct the overall semantic subgraph of the target tree skeleton and multiple local semantic subgraphs of the local tree skeleton based on the inheritance relationship and the hierarchical depth, taking all the growth key points as graph nodes and all the branch axis units as graph edges. The visualization module is used to perform coordinate encoding processing on the overall semantic subgraph and each of the local semantic subgraphs, perform quality checks on the encoding results, and display the overall semantic subgraph and all the local semantic subgraphs that pass the quality test as files in various formats.

9. A terminal, characterized in that, The terminal includes: a memory, a processor, and a tree skeleton semantic subgraph construction program based on growth key points and branch axis simplification stored in the memory and executable on the processor. When the tree skeleton semantic subgraph construction program based on growth key points and branch axis simplification is executed by the processor, it implements the steps of the tree skeleton semantic subgraph construction method based on growth key points and branch axis simplification as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a tree skeleton semantic subgraph construction program based on simplified growth key points and branch axes. When the tree skeleton semantic subgraph construction program based on simplified growth key points and branch axes is executed by a processor, it implements the steps of the tree skeleton semantic subgraph construction method based on simplified growth key points and branch axes as described in any one of claims 1-7.

Images