Automatic identification and intelligent processing method and device for sharp angle pattern spots

Abstract

The invention discloses an automatic identification and intelligent processing method and device for a sharp-angle pattern spot, and relates to the technical field of geographic information investigation, and the method comprises the steps: S1, calculating a pattern spot angular point included angle through setting a threshold value, and identifying and outputting the position and attribute of a sharp angle; s2, pattern spot positions and angular point features are extracted, and sharp-angle pattern spots are classified; s3, for different types of sharp angle pattern spots, respectively adopting a cutting and merging strategy, a corner cut back-filling strategy, an area fusion strategy or a boundary adjustment strategy, and ensuring the correctness of processed data through topology verification; s4, realizing non-destructive processing through data backup, marking and process recording; and S5, constructing an error processing and feedback mechanism to guarantee the process stability. According to the automatic identification and intelligent processing method and device for the sharp angle pattern spots, human errors can be reduced, data accuracy can be improved, repeated labor can be reduced, labor input can be reduced, the production cycle can be shortened, and the production process can be smoother and more efficient through intelligent process processing.

Description

Technical Field

[0001] The present invention relates to the field of geographic information survey technology, and in particular to a method and device for automatic recognition and intelligent processing of sharp-angle spots. Background Art

[0002] With the rapid development of "3S" technology, my country has gradually built a complete land survey and monitoring technology system, and established a database management and service technology system from the second national land survey to the third national land survey, and then to the annual land change survey. However, the automation level of some links in the production process is still not high, and a lot of manpower and material resources need to be invested. For example, in the land change survey project, it is necessary to build a database and pass the quality inspection. The handling of sharp corners in quality inspection errors is a major problem.

[0003] The annual land change survey project has a short cycle and heavy tasks. At the same time, the survey and monitoring data itself has two significant characteristics: one is the large amount of data, and the other is the complex data relationship. During the operation, a large number of sharp-angle spots will be generated for various reasons. These spots may be narrow and long sharp corners caused by improper operation of the internal mapping process, or they may be generated because the boundaries of various related layers are not overlapped during the superposition analysis (for example, the map spots of the change survey update library not only need to overlap with the boundaries of the basic library issued by the state, but also need to be consistent with the boundaries of the town and village map layers and ownership layers issued by the state. Therefore, when cutting the land class spots for spatial assignment, a large number of sharp-angle spots will also be generated). According to the current technical specifications for land space surveys, sharp-angle spots in the database are judged as quality inspection errors. The number of such quality inspection errors ranges from hundreds to thousands. Manual analysis and processing of such large data with complex data relationships is not only time-consuming and labor-intensive, difficult and cumbersome, but also easy to miss important information and cause errors.

[0004] The types of sharp-angle spots that need to be processed are mainly divided into the following types:

[0005] Convex polygonal sharp-angled spots refer to spots with multiple other spots around them and protruding sharp corners.

[0006] Concave polygonal sharp-angled spots refer to spots with multiple other spots around them and concave corners.

[0007] Fragmented polygons with sharp corners refer to patches whose area is less than 30 square meters after cutting of the graphic patches of the update layer elements;

[0008] Small cracks between patches refer to patches where there are no gaps between different elements in the same surface layer, and the surface crack tolerance is 0.0001 meters;

[0009] Independent sharp-corner patches belong to patches that exist independently, that is, patches with no other patches around them. Such patches are relatively special and require manual analysis of the main reasons and manual processing.

[0010] Currently, there are mainly two processing schemes for sharp-corner patches by each operating unit:

[0011] One is manual elimination: Through the inspection results of the national quality inspection software, determine whether the patches in the layer meet the national inspection requirements, find the error location according to the error prompt and modify it. Manually crop, split, and merge sharp-corner patches one by one. For example, for the manual editing of sharp-corner patches, the sharp corner part needs to be cropped out to form independent fragmented polygons, and then analyze the attribute relationships between layers and merge them with adjacent large patches one by one to eliminate the sharp corners. The manual elimination processing scheme is mainly applicable when the number of sharp-corner patch errors is small. Although this method can ensure the accuracy of processing, the processing speed is slow, the efficiency is low, it is time-consuming and laborious, and due to the complexity of the change survey data, it is difficult to achieve consistent standards manually. It may generate other error types while modifying this error, such as gaps, small fragmented surfaces, and blank patches caused by operation errors. Therefore, manual elimination of sharp corners also requires a process of topological inspection to modify topological errors, increasing the workload, so it has relatively high requirements for the experience of data processing personnel.

[0012] The other is to modify based on the toolbox of GIS software: The elimination tool in GIS software, such as the Eliminate tool in ArcGlS, selects the elements to be eliminated in the relevant layer, specifies the paths and names of the input and output elements, and sets the merging parameters, that is, specifies the conditions (such as area size, shared boundary length, etc.) to merge the fragmented polygons with sharp corners with adjacent large patches. The operation based on the GIS toolbox can automatically merge sharp-corner patches, reduce the workload of manual operations, and improve work efficiency. However, the parameter settings of the toolbox are relatively limited, and the adaptability to complex data structures is insufficient, especially when dealing with patches with complex boundaries or irregular shapes, it is not flexible enough.

[0013] Regardless of which scheme of the existing technologies, it can only be implemented based on determining the error location through the quality inspection software. However, in actual operations, sharp-corner patches cannot be identified solely by the human eye. Therefore, it is urgent to study the automated processing of sharp-corner patches to overcome the current time-consuming and laborious problems. Summary of the Invention

[0014] The purpose of the present invention is to provide a method and device for automatic recognition and intelligent processing of sharp-corner patches, which can improve the automation level of sharp-corner patch recognition. At the same time, through intelligent process processing, it can reduce human errors, improve data accuracy, reduce repetitive labor, reduce manual input, shorten the production cycle, and make the production process smoother and more efficient.

[0015] To achieve the above object, the present invention provides a method for automatically identifying and intelligently processing sharp patches, and the steps are as follows:

[0016] S1. Corner identification and extraction, including:

[0017] S1.1. Set the determination threshold for sharp corner patches;

[0018] S1.2. Traverse all corner points of the patch and calculate the degree of the included angle between adjacent sides of the corner points;

[0019] S1.3. Output the coordinates and coordinate values of the sharp corner positions, display them through a graphical interface, and generate a vector table containing attribute information;

[0020] S2. Feature analysis and classification, including:

[0021] S2.1. Extract the position features and corner point features of the patch, and select the features that are most meaningful for classification from the extracted features;

[0022] S2.2. Classify the sharp corners into convex polygon sharp corners, concave polygon sharp corners, fragmented polygon patches, thin slits that require intelligent processing, and independent sharp corners that require manual processing according to the extracted features;

[0023] S3. Process the sharp corner patches through an intelligent processing mechanism, including:

[0024] S3.1. For convex polygon sharp corner patches, cut the protruding sharp corner patches according to the spatial relationship with adjacent patches and merge them into adjacent patches according to the rules;

[0025] S3.2. For concave polygon sharp corner patches, fill in the cut corners by adjacent figures;

[0026] S3.3. For fragmented polygon patches with sharp corners, when the area of the patch is less than the preset threshold, directly merge them into adjacent patches;

[0027] S3.4. For thin slits between patches, eliminate the slits by filling the empty slits, deleting the overlaps or adjusting the boundary lines;

[0028] S3.5. After processing all sharp corners, re-identify the sharp corners and use a topology checking tool to verify. For those with topology errors, return to S3 for reprocessing;

[0029] S4. Non-destructive processing and result output, including:

[0030] S4.1. Automatically copy the original data set to generate a processing copy to avoid losing or overwriting the original data during the modification process;

[0031] S4.2. Add a marker field or an explanatory field to the processed data to distinguish between the original data and the modified data;

[0032] S4.3. Record the processing flow information, including the algorithm type, parameter settings, and operation sequence;

[0033] S5. Error handling and feedback mechanism

[0034] S5.1. Detect anomalies in the processing process in real time, and record the error code and detailed log;

[0035] S5.2. Provide a human-computer interaction feedback interface to support operators in modifying parameters or intervening in the processing flow.

[0036] Preferably, in S1.2, the method for calculating the included angle degree between adjacent sides of a corner point is as follows: Represent the two adjacent sides of the corner point by vector A and vector B respectively, and the cosine of the included angle θ between vector A and vector B is calculated by the following formula:

[0037]

[0038] Then, the angle value of θ is obtained through the arccos function of the tangent function.

[0039] Preferably, in S1.3, the attribute information of the vector table includes sharp corner coordinates, angle values, and patch ID information.

[0040] Preferably, in S2.1, the position features of the patch include patch coordinates and the spatial relationship with adjacent patches, and the corner point features of the patch include the number of corner points, the distribution of corner points, and the sharpness of corner points.

[0041] Preferably, in S3.1, the path algorithm for cutting sharp-corner patches of convex polygons adopts the Dijkstra algorithm or the cutting algorithm of the minimum circumscribed circle.

[0042] Preferably, in S3.2, the backfilling operation for sharp corners of concave polygons is based on Delaunay triangulation, Voronoi diagrams, and the minimum circumscribed circle algorithm.

[0043] Preferably, in S3.4, the preprocessing common point recognition algorithm for slit processing accurately locates the common endpoints of different line segments or polygons in the vector graph through the common point recognition algorithm.

[0044] Preferably, in S3.4, the slit elimination is based on the adjustment of geometric figures or algorithms such as Delaunay triangulation, and the graphic topology structure is reconstructed to fill the slit area.

[0045] An automatic recognition and intelligent processing device for sharp-corner patches, comprising:

[0046] A sharp corner detection module for calculating the patch included angle and generating a position vector table;

[0047] A feature classification module for extracting the position features and corner features of patches and classifying sharp corners.

[0048] An intelligent processing module integrating processing algorithms and topology checking tools for different types of sharp-corner patches.

[0049] A data management module for implementing data backup, marking, and process recording.

[0050] A human-computer interaction module providing a visual interface and an error feedback interface.

[0051] According to the specific embodiments provided by the present invention, the following technical effects are disclosed:

[0052] 1. Avoid sharp-corner patch errors in advance: Automatically process before the quality inspection software detects errors, avoiding multiple repeated reworks, multiple rounds of processing, exporting, and passing the national inspection, which makes the in-house database construction work time-consuming and inefficient.

[0053] 2. Improve the recognition accuracy of sharp-corner patches: Automatically extract and recognize the features of sharp-corner patches to improve the recognition accuracy of sharp-corner patches and reduce human errors.

[0054] 3. Achieve intelligent processing of sharp-corner patches: Utilize the automated processing mode to achieve fast and accurate processing of sharp-corner patches and improve work efficiency.

[0055] 4. Maintain the integrity and accuracy of data: Ensure the integrity and accuracy of the original data during the process of processing sharp-corner patches, and avoid data loss or errors caused by improper processing.

[0056] 5. Promote the development of technologies in related fields: Not only solve the problem of processing sharp-corner patches in the land use change investigation project, but also promote the application and development of automated processing in investigation and monitoring projects, providing new ideas and methods for the technological progress of related fields.

[0057] The technical solutions of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0059] Figure 1Schematic flowchart of an embodiment of an automatic recognition and intelligent processing method for sharp patches in the present invention;

[0060] Figure 2 Example of a convex polygon sharp corner patch in an embodiment of the present invention;

[0061] Figure 3 Example of a concave polygon sharp corner patch in an embodiment of the present invention;

[0062] Figure 4 Example of a fragmented polygon patch with sharp corners in an embodiment of the present invention;

[0063] Figure 5 Example of a small gap between patches in an embodiment of the present invention;

[0064] Figure 6 Output display diagram of the sharp corner position in an embodiment of the present invention;

[0065] Figure 7 Output vector attribute table of the sharp corner position in an embodiment of the present invention;

[0066] Figure 8 Comparison diagram before and after processing of the convex polygon sharp corner patch in an embodiment of the present invention;

[0067] Figure 9 Comparison diagram before and after processing of the concave polygon sharp corner patch in an embodiment of the present invention;

[0068] Figure 10 Comparison diagram before and after processing when the gap is a void in an embodiment of the present invention;

[0069] Figure 11 Comparison diagram before and after processing when the gaps overlap in an embodiment of the present invention;

[0070] Figure 12 Comparison diagram before and after processing when the boundary line of the gap is inaccurate in an embodiment of the present invention;

[0071] Figure 13 Comparison diagram before and after processing of the fragmented polygon sharp corner patch in an embodiment of the present invention;

[0072] Figure 14 Data marking schematic diagram in an embodiment of the present invention. Detailed implementation manner

[0073] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0074] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0075] Embodiment

[0076] As Figure 1 shown, an automatic recognition and intelligent processing method for sharp patches is as follows:

[0077] S1. Corner recognition and extraction, including:

[0078] S1.1. Set the determination threshold for sharp corner patches.

[0079] S1.2. Traverse all corner points of the patch, and calculate the degree of the included angle between the adjacent sides of the corner point; the method for calculating the degree of the included angle between the adjacent sides of the corner point is: represent the two adjacent sides of the corner point by vector A and vector B respectively, and the cosine of the included angle θ between vector A and vector B is calculated by the following formula:

[0080]

[0081] Then obtain the angle value of θ through the arccos function.

[0082] S1.3. Output the position coordinates and coordinate values of the sharp corners. As Figure 6 shown, display through the graphical interface and generate a vector table containing attribute information; the attribute information of the vector table includes sharp corner coordinates, angle values, and patch ID information, as Figure 7 shown.

[0083] S2. Feature analysis and classification, including:

[0084] S2.1. Extract the position features and corner features of the patch, and select the most significant features for classification from the extracted features; the position features of the patch include patch coordinates, adjacent patch spatial relationships, etc., and the corner features of the patch include the number of corner points, the distribution of corner points, the sharpness of corner points, etc.

[0085] S2.2. Classify the sharp corners into convex polygon sharp corners (such as Figure 2 shown), concave polygon sharp corners (such as Figure 3 shown), and fragmented polygon patches (such as Figure 4as shown), small narrow slits (such as Figure 5 as shown), and independent sharp corners that require manual processing;

[0086] S3. Process the sharp corner patches through an intelligent processing mechanism, including:

[0087] S3.1. For convex polygon sharp corner patches, according to the spatial relationship of adjacent patches, cut the protruding sharp corner patches and merge them into adjacent patches according to the rules of attribute consistency, spatial adjacency, distance, and area ratio. The cutting path algorithm is based on the shortest path cutting (using the Dijkstra algorithm) or the minimum circumscribed circle cutting algorithm. As shown in Figure 8 (a) in represents the image before the sharp corner is processed, Figure 8 (b) in represents the image after the sharp corner is processed.

[0088] S3.2. For concave polygon sharp corner patches, fill in the cut corners by adjacent figures. As shown in Figure 9 (a) represents the image before the sharp corner is processed, (b) represents the image after the sharp corner is processed, (c) represents the image before the internal sharp corner of the layer is processed, and (d) represents the image after the internal sharp corner of the layer is processed.

[0089] S3.3. For fragmented polygon patches with sharp corners, when the area of the patch is less than the preset threshold, directly merge it into the adjacent patch. A fragmented polygon refers to a patch smaller than the relevant threshold. For example, the minimum mapping area for land use change surveys is 30 square meters. If the normal sharp corner processing method for convex and concave polygons is used, the processed patches may be too narrow, so the method of directly merging into the surrounding patches is adopted. Figure 13 (a) in represents the image before the fusion processing of the fragmented polygon patch with sharp corners, and (b) represents the image after the fusion processing of the fragmented polygon patch with sharp corners.

[0090] S3.4. For small narrow slits between patches. Slits usually refer to the tiny gaps or overlaps between the patch boundary lines, which may be caused by errors in data collection or processing. In the present invention, a pre - processing common point recognition algorithm link is added for slit elimination, which accurately locates the common endpoints of different line segments or polygons in the vector graph, quickly locks the potential common point positions that may cause slit problems, and then based on the adjustment of geometric figures, makes the originally separated common points coincide, thereby eliminating the slits; or based on the Delaunay triangulation algorithm, reconstructs the graph topology structure to fill the slit area.

[0091] If the slit is a gap, a filling algorithm can be used to fill these gaps. As shown in Figure 10 (a) in represents the image before the slit gap is processed, and (b) represents the image after the slit gap is processed.

[0092] If the slit is caused by overlap, a deletion algorithm can be used to remove the extra boundary lines. As Figure 11 shown in (a) of

[0093] is the image before overlap processing, and (b) is the image after overlap processing. If the boundary line of the patch feature is inaccurate, an adjustment algorithm can be used to adjust the position of the boundary line to eliminate the slit. As Figure 12 shown in (a) of

[0094] is the image before slit gap processing, and (b) is the image after slit gap processing.

[0095] S3.5. After processing all sharp corners, re-identify the sharp corners and use the topology check tool to verify whether the topology of the patch is correct. For those with topology errors, return to S3 for processing. This helps ensure that all sharp corners are correctly repaired and avoid the occurrence of other errors.

[0095] S4. Non-destructive processing and result output, including:

[0096] S4.1. Automatically copy the original dataset to generate a processed copy to avoid losing or overwriting the original data during the modification process;

[0097] S4.2. Add marker fields or explanatory fields to the processed data to distinguish between the original data and the modified data; the content of the marker field should be readable and the expression should be intuitive and easy to understand, all using easy-to-understand terms, as Figure 14 shown.

[0098] S4.3. Record the processing flow information, including the algorithm type, parameter settings, and operation sequence, which helps to reproduce the processing process when needed or understand the impact of the modification on the result.

[0099] S5. Error handling and feedback mechanism

[0100] S5.1. Detect process anomalies in real time and record the error code and detailed log. During the entire automated sharp corner processing flow, due to the complexity of the data, errors and anomalies are inevitable. To ensure the stability and continuity of the processing flow, a sound error handling mechanism should be built. This mechanism should include error detection, recording, reporting, and repair. When the system encounters an anomaly, it can automatically trigger corresponding processing measures and provide as detailed error information as possible for manual troubleshooting and correction.

[0101] S5.2. Provide a human-computer interaction feedback interface to support operators in modifying parameters or intervening in the processing flow. To continuously improve data processing efficiency and accuracy, set up feedback interfaces at key processing nodes so that operators can timely obtain the working status and results at the current stage; and regularly collect and analyze bottleneck problems and common error patterns in the processing process to guide process improvement and innovation. Through the organic combination of this error handling and feedback mechanism, not only can the existing problems be effectively solved, but also the data processing flow can be continuously optimized and improved, thereby enhancing the overall work efficiency and the quality of the results.

[0102] A method for automatically identifying and intelligently processing sharp patches of the present invention realizes the function of efficiently automating the processing of sharp angles. In the process of land change survey data processing, it can improve work efficiency, reduce labor costs, and improve data accuracy. After multiple rounds of experiments by multiple people, it is found that when manually eliminating sharp angles, it takes an average of 10 seconds for each sharp angle, and a large amount of manual time is required for topological inspection after elimination. However, this technology can not only automatically locate the position of sharp angles, but also automatically eliminate sharp angles of a specified angle, taking very little time and increasing the efficiency by dozens of times. The automated processing of sharp-angle patches shows significant advantages both at the technical level and the application level. It not only brings convenience to natural resource monitoring projects such as land change surveys, but also provides strong support for the processing and application of geographic information data.

[0103] An automatic identification and intelligent processing device for sharp-angle patches, comprising:

[0104] A sharp-corner detection module for calculating the included angle of the patch and generating a position vector table;

[0105] A feature classification module for extracting the position features and corner features of the patch and classifying the sharp corners;

[0106] An intelligent processing module integrating processing algorithms and topological inspection tools for different types of sharp-angle patches;

[0107] A data management module for realizing data backup, marking and process recording;

[0108] A human-computer interaction module for providing a visual interface and an error feedback interface.

[0109] In addition to the corresponding system device, combined with relevant tools of GIS or FME software, it is also possible to sort out the data processing logic of existing project experience and create a geoprocessing model for processing sharp-angle patches using a model builder.

[0110] At the application level, through an automatic identification and intelligent processing device for sharp-angle patches, the following beneficial effects are obtained:

[0111] 1. Improve data processing efficiency

[0112] Automated processing can quickly handle a large amount of sharp-corner patch data, reducing the time and labor costs of manual processing and improving the overall work efficiency.

[0113] 2. Optimize resource allocation

[0114] Automated processing helps to avoid waste and duplicate investment of resources and improve resource utilization efficiency.

[0115] 3. Promote intelligent development

[0116] The automated processing of sharp-corner patches is an important part of the intelligent development of geographic information systems (GIS), remote sensing technology, etc. With the continuous progress of technology and the expansion of application scenarios, automated processing will play an important role in more fields and promote the process of intelligent development.

[0117] For the rest of the technical features in the above embodiments, those skilled in the art can flexibly select them according to the actual situation to meet different specific actual needs. However, it is obvious to those of ordinary skill in the art that these specific details do not have to be adopted to implement the present invention. In other instances, well-known components, structures, or parts are not specifically described in order to avoid obscuring the present invention, and all are within the scope of the technical solutions claimed in the claims of the present invention.

[0118] Modifications and changes made by those skilled in the art without departing from the spirit and scope of the present invention shall fall within the protection scope of the appended claims of the present invention. In the above description, in order to provide a thorough understanding of the present invention, a large number of specific details are set forth. However, it is obvious to those of ordinary skill in the art that these specific details do not have to be adopted to implement the present invention. In other instances, well-known technologies, such as specific construction details, operating conditions, and other technical conditions, are not specifically described in order to avoid obscuring the present invention.

[0119] Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, there will be changes in the specific implementation methods and application scopes according to the idea of the present invention. In summary, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An automatic recognition and intelligent processing method for sharp patches, characterized in that, The steps are as follows: S1. Sharp corner recognition and extraction, including: S1.

1. Set the determination threshold for sharp corner patches; S1.

2. Traverse all corner points of the patch and calculate the degree of the included angle between the adjacent sides of the corner points; S1.

3. Output the position coordinates and coordinate values of the sharp corners, display them through the graphical interface, and generate a vector table containing attribute information; S2. Feature analysis and classification, including: S2.

1. Extract the position features and corner point features of the patch, and select the most meaningful features for classification from the extracted features; S2.

2. Classify the sharp corners into convex polygon sharp corners, concave polygon sharp corners, fragmented polygon patches, thin slits that require intelligent processing, and independent sharp corners that require manual processing according to the extracted features; S3. Process the sharp corner patches through the intelligent processing mechanism, including: S3.

1. For convex polygon sharp corner patches, cut the protruding sharp corner patches according to the spatial relationship of adjacent patches and merge them into adjacent patches according to the rules; S3.

2. For concave polygon sharp corner patches, fill in the cut corners by adjacent graphics; S3.

3. For fragmented polygon patches containing sharp corners, when the area of the patch is less than the preset threshold, directly merge it into the adjacent patch; S3.

4. For thin slits between patches, eliminate the slits by filling the empty slits, deleting the overlaps, or adjusting the boundary lines; S3.

5. After processing all sharp corners, re-recognize the sharp corners and use the topology check tool to verify. For those with topology errors, return to S3 for processing again; S4. Non-destructive processing and result output, including: S4.

1. Automatically copy the original data set to generate a processing copy to avoid losing or overwriting the original data during the modification process; S4.

2. Add a marker field or an explanatory field to the processed data to distinguish the original data from the modified data; S4.

3. Record the processing flow information, including the algorithm type, parameter settings, and operation sequence; S5. Error handling and feedback mechanism S5.

1. Detect process exceptions in real time, record the error code and detailed log; S5.

2. Provide a human-computer interaction feedback interface to support operators to correct parameters or intervene in the processing flow.

2. The automatic recognition and intelligent processing method for sharp patches according to claim 1, wherein: In S1.2, the method for calculating the included angle degree between adjacent sides of a corner point is: represent the two adjacent sides of the corner point by vector A and vector B respectively, and the cosine of the included angle θ between vector A and vector B is calculated by the following formula: Then obtain the angle value of θ through the arccos function of the inverse tangent function.

3. The automatic recognition and intelligent processing method for sharp patches according to claim 1, characterized in that: In S1.3, the attribute information of the vector table includes sharp corner coordinates, angle values, and patch ID information.

4. The automatic recognition and intelligent processing method for sharp patches according to claim 1, characterized in that: In S2.1, the position features of the patch include patch coordinates and the spatial relationship of adjacent patches, and the corner point features of the patch include the number of corner points, the distribution of corner points, and the sharpness of corner points.

5. The automatic recognition and intelligent processing method for sharp patches according to claim 1, wherein: In S3.1, the path algorithm for cutting convex polygon sharp corner patches adopts the Dijkstra algorithm or the cutting algorithm of the minimum circumscribed circle.

6. The automatic recognition and intelligent processing method for sharp patches according to claim 1, characterized in that: In S3.2, the backfilling operation of concave polygon sharp corners is based on the Delaunay triangulation, Voronoi diagram, and minimum circumscribed circle algorithm.

7. A method for automatic recognition and intelligent processing of sharp patches according to claim 1, characterized in that: In S3.3, the preprocessing common point recognition algorithm for slit processing accurately locates the common endpoints of different line segments or polygons in the vector graph through the common point recognition algorithm.

8. An automatic recognition and intelligent processing device for sharp-corner patches applying the method according to any one of claims 1-7, characterized in that, Including: The sharp corner detection module is used to calculate the included angle of the patches and generate a position vector table; The feature classification module is used to extract the position features and corner features of the patches and classify the sharp corners; The intelligent processing module integrates processing algorithms and topology checking tools for different types of sharp-corner patches; The data management module realizes data backup, marking and process recording; The human-computer interaction module provides a visual interface and an error feedback interface.

Images