Map green land identification method, device and equipment, and storage medium

Abstract

This disclosure provides a method, apparatus, device, and storage medium for map green space recognition, relating to the field of artificial intelligence technology, specifically computer vision, map navigation, large-scale modeling, autonomous driving, and intelligent transportation. The method includes: detecting the region to be recognized according to preset morphological detection rules to obtain detection results; determining feature values ​​of the region to be recognized in multiple preset dimensions in response to determining that the detection result is passed; generating comprehensive information of the region to be recognized based on the feature values ​​of the multiple preset dimensions; and determining the target recognition result of the region to be recognized based on the comprehensive information and a preset information threshold, wherein the target recognition result is used to characterize whether the region to be recognized is a green space or a non-green space. This method improves the accuracy, stability, and adaptability of green space recognition, achieving efficient and accurate automated recognition of green spaces.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, specifically to the fields of computer vision, map navigation, large models, autonomous driving, and intelligent transportation, and particularly to a method, apparatus, device, and storage medium for map green space recognition. Background Technology

[0002] Accurate identification of urban green spaces, ecological green spaces, and vegetation cover in national land space is a crucial technical support for map navigation, ecological monitoring, urban planning, and environmental assessment. While automatic green space identification technology is gradually being applied in various scenarios, significant limitations remain. For example, green spaces along highways, as important components of transportation infrastructure and ecological corridors, have an increasingly prominent need for accurate identification, rapid statistical analysis, and routine monitoring. However, existing methods largely rely on manual interpretation, on-site surveying, or hard rule filtering based on single features such as area and shape. This is not only inefficient and costly but also poorly adaptable to green space samples with complex shapes and ambiguous boundaries. Summary of the Invention

[0003] This disclosure provides a method, apparatus, device, and storage medium for identifying green areas on a map.

[0004] According to a first aspect of this disclosure, a method for identifying green areas on a map is provided, comprising: detecting an area to be identified according to a preset morphological detection rule to obtain a detection result; in response to determining that the detection result is a pass detection, determining feature values ​​of the area to be identified in multiple preset dimensions; generating comprehensive information of the area to be identified based on the feature values ​​of the multiple preset dimensions; and determining a target identification result of the area to be identified based on the comprehensive information and a preset information threshold, wherein the target identification result is used to characterize whether the area to be identified is a green area or a non-green area.

[0005] According to a second aspect of this disclosure, a map green space identification device is provided, comprising: a morphological detection module configured to detect a region to be identified according to a preset morphological detection rule and obtain a detection result; a feature determination module configured to determine feature values ​​of the region to be identified in multiple preset dimensions in response to determining that the detection result is passed; an information generation module configured to generate comprehensive information of the region to be identified based on the feature values ​​of the multiple preset dimensions; and a target identification module configured to determine a target identification result of the region to be identified based on the comprehensive information and a preset information threshold, wherein the target identification result is used to characterize whether the region to be identified is a green space or a non-green space.

[0006] According to a third aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a method as described in any implementation of the first aspect.

[0007] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform a method as described in any implementation of the first aspect.

[0008] According to a fifth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method as described in any implementation of the first aspect.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 This is an exemplary system architecture diagram to which this disclosure can be applied; Figure 2 This is a flowchart of the first embodiment of the map green space identification method according to the present disclosure; Figure 3 This is a flowchart of a second embodiment of the map green space identification method according to the present disclosure; Figure 4 This is a flowchart of a third embodiment of the map green space identification method according to the present disclosure; Figure 5 This is a flowchart of the fourth embodiment of the map green space identification method according to the present disclosure; Figure 6 This is a flowchart of the fifth embodiment of the map green space identification method according to the present disclosure; Figure 7 This is a flowchart of the sixth embodiment of the map green space identification method according to the present disclosure; Figure 8 This is a schematic diagram of a structure of an embodiment of the map green space identification device according to the present disclosure; Figure 9 This is a block diagram of an electronic device used to implement the map green space recognition method of the present disclosure embodiments. Detailed Implementation

[0011] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0012] It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0013] Figure 1 An exemplary system architecture 100 is shown that can be applied to embodiments of the map green space identification method or map green space identification device disclosed herein.

[0014] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, and 104, network 105, and server 106. Network 105 is used as a medium to provide communication links between terminal devices 101, 102, 103, and 104 and server 106. Network 105 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0015] Users can use terminal devices 101, 102, 103, and 104 to interact with server 106 via network 105 to receive or send information, etc. Various client applications can be installed on terminal devices 101, 102, 103, and 104.

[0016] Terminal devices 101, 102, 103, and 104 can be either hardware or software. When terminal devices 101, 102, 103, and 104 are hardware, they can be various electronic devices, including but not limited to smartphones, tablets, laptops, and desktop computers. When terminal devices 101, 102, 103, and 104 are software, they can be installed in the aforementioned electronic devices. They can be implemented as multiple software programs or software modules, or as a single software program or software module. No specific limitations are made here.

[0017] Server 106 can provide various services. For example, server 106 can analyze and process the regions to be identified obtained from terminal devices 101, 102, 103, and 104, and generate processing results (such as target identification results).

[0018] It should be noted that server 106 can be either hardware or software. When server 106 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When server 106 is software, it can be implemented as multiple software units or software modules (for example, to provide distributed services), or as a single software unit or software module. No specific limitations are made here.

[0019] It should be noted that the map green space recognition method provided in this embodiment is generally executed by server 106, and correspondingly, the map green space recognition device is generally set in server 106.

[0020] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0021] Continue to refer to Figure 2 The diagram illustrates a flow 200 of a first embodiment of a map-based green space identification method according to the present disclosure. This map-based green space identification method includes the following steps: Step 201: Detect the region to be identified according to the preset shape detection rules to obtain the detection result.

[0022] In this embodiment, the executing entity of the map green space identification method (e.g.) Figure 1 The server 106 shown takes the data of the area to be identified as input and performs filtering detection area by area according to the preset morphological detection rules, thereby eliminating abnormal areas that obviously do not conform to the characteristics of green areas and retaining candidate areas that meet the morphological requirements. The area to be identified here is the vector surface of the green area to be identified. It should be noted that a vector surface is a closed polygon formed by an ordered sequence of spatial coordinate points connected end to end. It is the standard data format for representing isal features in the field of GIS (Geographic Information System). It has calculable geometric attributes such as precise boundaries, clear area, perimeter, shape, and topological relationships. In other words, a vector surface is a map surface graphic with closed boundaries, area, and shape.

[0023] Here, the preset morphological detection rules can include, but are not limited to, one or more of the following: area detection rules, shape detection rules, and topological relationship detection rules. The aforementioned execution entity reads vector polygon data of the area to be identified from the GIS vector library. A vector polygon is a closed polygon composed of a sequence of coordinate points, containing geometric information such as boundaries, area, perimeter, and spatial location. Then, the execution entity calculates the actual area based on the vector polygon data and performs area threshold filtering according to the area detection rules, thereby filtering out abnormal areas such as small, fragmented patches or large planar features in non-green areas; and / or calculates shape values ​​(e.g., perimeter, area-to-perimeter ratio) based on the vector polygon data and performs shape rule filtering according to the shape detection rules, thereby filtering out areas with abnormal shapes; and / or constructs topological relationships between all areas to be identified, including adjacency, shared edges, intersection, containment, and proximity, to determine the spatial association between the area to be identified and surrounding typical features, and performs topological relationship filtering according to the topological relationship detection rules, thereby filtering out abnormal areas such as completely isolated patches without any adjacent green areas, without spatial clustering characteristics, or without topological association with vegetation features.

[0024] After area threshold filtering and / or shape regularity filtering and / or topological relationship filtering, the target areas that conform to the preset shape rules are retained as the shape coarse screening results. The detection results include pass or fail. It should be noted that when the preset shape detection rules include multiple specific categories of detection rules, if any one of the detection results is a fail, the final detection result is determined to be a fail; conversely, if all detection results are pass, the final detection result is determined to be a pass. For example, if the preset shape detection rules include area detection rules and shape detection rules, and the area detection result of the area to be identified is pass, but the shape detection result is fail, then the final detection result of the area to be identified is determined to be a fail.

[0025] Step 202: In response to determining that the detection result is passed, determine the feature values ​​of the region to be identified in multiple preset dimensions.

[0026] In this embodiment, if the detection result is determined to be a pass, the aforementioned execution entity will determine the feature values ​​of the region to be identified in multiple preset dimensions. That is, based on the aforementioned morphological detection output results, the vector surface regions to be identified that meet the requirements of area range, regular shape, and valid topology are selected, and then proceed to the feature extraction operation.

[0027] Multiple preset dimensions may include, but are not limited to, at least two of the following: area dimension, aspect ratio dimension, compactness dimension, orientation dimension, distance dimension, and intersection dimension. The aforementioned execution entity will extract features of the region to be identified in the dimensions of area, aspect ratio, compactness, orientation, distance, and / or intersection, and then determine the feature values ​​corresponding to the above dimensions.

[0028] The aforementioned execution entity can directly calculate the actual projected area of ​​the vector surface, thereby obtaining the area dimension feature value. Dividing the length of the longer side of the circumscribed rectangle by the length of the shorter side yields the aspect ratio dimension feature value, used to characterize the degree of regional extension. The compactness dimension feature value can be calculated using a preset formula, area value, and perimeter value; the closer the value is to 1, the more regular and compact the shape. The direction dimension, distance dimension, and intersection dimension are features related to the surrounding environment. Specifically, calculating the angle difference between the main extension direction of the area to be identified and the overall extension direction of the land parcel yields the direction dimension feature value; calculating the Euclidean distance from the center of the target area to the nearest road, waterway, or land parcel boundary yields the distance dimension feature value; assigning values ​​according to topological relationships (e.g., adjacent = 1, disjoint = 0, contained = 2, intersecting = 3) converts these into calculable intersection dimension feature values.

[0029] Step 203: Generate comprehensive information about the region to be identified based on feature values ​​of multiple preset dimensions.

[0030] In this embodiment, the execution entity determines the weight value corresponding to each preset dimension, and then performs a weighted calculation based on the weight value and feature value of each preset dimension to obtain the comprehensive information of the region to be identified. Alternatively, the execution entity can generate a score corresponding to each preset dimension based on the feature values ​​of multiple preset dimensions, and then normalize the scores to map the values ​​to the 0-1 range. Then, a weighted calculation is performed based on the weight value and score of each preset dimension to obtain the comprehensive information (or comprehensive score) of the region to be identified.

[0031] As an example, several preset dimensions include: area, aspect ratio, compactness, orientation, distance, and intersection. The execution entity first generates scores for each dimension based on the feature values ​​of these dimensions: area score, aspect ratio score, compactness score, orientation score, distance score, and intersection score. Then, the execution entity determines the weight value for each dimension. These weights can be set based on practical experience; for example, the weight for area is 0.2, the weight for aspect ratio is 0.15, the weight for compactness is 0.2, the weight for orientation is 0.15, the weight for distance is 0.15, and the weight for intersection is 0.15, with the sum of all dimension weights being 1. Then, the score for each dimension is multiplied by its weight to obtain the numerical value for that dimension. Finally, the values ​​for all dimensions are summed to obtain the comprehensive score for the region to be identified.

[0032] Step 204: Determine the target recognition result of the area to be identified based on the comprehensive information and the preset information threshold.

[0033] In this embodiment, the aforementioned execution entity determines the target identification result of the area to be identified based on comprehensive information and a preset information threshold. The target identification result is used to characterize whether the area to be identified is a green area or a non-green area.

[0034] The aforementioned implementing entity will pre-configure a unified preset information threshold and traverse the comprehensive score data of all areas to be identified, comparing the comprehensive score with the preset threshold for classification. When the comprehensive score of an area to be identified is greater than or equal to the preset information threshold, it is determined that the vegetation features of the area are complete and the morphology conforms to the characteristics of a green area, and its target identification result is directly determined as a green area; when the comprehensive score of an area to be identified is less than the preset information threshold, it indicates that the geometric shape, spatial structure, and vegetation-related features of the area do not conform to the basic attributes of a green area, and its target identification result is determined as a non-green area.

[0035] The map green space recognition method provided in this embodiment first detects the area to be recognized according to preset morphological detection rules to obtain detection results; then, in response to determining that the detection result is passed, it determines the feature values ​​of the area to be recognized in multiple preset dimensions; subsequently, it generates comprehensive information of the area to be recognized based on the feature values ​​of multiple preset dimensions; finally, it determines the target recognition result of the area to be recognized based on the comprehensive information and preset information thresholds. The map green space recognition method in this embodiment, through hierarchical filtering and multi-dimensional feature analysis, eliminates irregular areas layer by layer, and combines quantitative comprehensive information with threshold judgment, reducing recognition errors in complex environments, weakening the limitations of single features, and improving the accuracy, stability, and adaptability of green space recognition, thus achieving efficient and accurate automated recognition of green space areas.

[0036] Furthermore, the collection, storage, use, processing, transmission, provision, and disclosure of any type of information, such as user personal information, involved in the technical solutions disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0037] Continue to refer to Figure 3 , Figure 3 A flowchart 300 of a second embodiment of the map green space identification method according to this disclosure is shown. The map green space identification method includes the following steps: Step 301: Calculate the actual area of ​​the region to be identified based on the vector surface data of the region to be identified.

[0038] In this embodiment, the executing entity of the map green space identification method (e.g.) Figure 1The server 106 shown will use the spatial coordinates of the closed polygon of the vector surface as a basis, and use the planar geometric area algorithm to calculate the actual planar coverage area of ​​the vector surface. It will perform numerical calculations based on the coordinates of the polygon vertices, and combine the spatial distance correction with the projection coordinate system to solve the actual area of ​​the vector surface, thereby eliminating the interference of terrain undulations and obtaining the actual area of ​​the region that conforms to the geographic spatial scale.

[0039] Step 302: Generate the area detection result of the region to be identified based on the area detection rules and the actual area.

[0040] In this embodiment, the preset morphological detection rules include: area detection rules. The area detection rules are as follows: if the actual area is greater than a first area threshold, the area to be identified is determined to be a large, non-green area with a large planar feature, and it is directly removed, meaning the area detection result is "failed detection"; if the actual area is less than a second area threshold, the area to be identified is determined to be a small, fragmented patch with an excessively small area, and it is directly removed, meaning the area detection result is "failed detection"; if the area is within the range of the second area threshold and the first area threshold (the second area threshold is less than the first area threshold), it is retained and proceeds to the next stage, meaning the area detection result is "passed detection". This filters out abnormal areas such as small, fragmented patches with an excessively small area and large, non-green areas with large planar features.

[0041] Step 303: In response to determining that the area detection result is passed, determine the feature values ​​of the region to be identified in multiple preset dimensions.

[0042] Step 304: Generate comprehensive information about the region to be identified based on feature values ​​of multiple preset dimensions.

[0043] Step 305: Determine the target recognition result of the area to be identified based on the comprehensive information and the preset information threshold.

[0044] Steps 303-305 are basically the same as steps 202-204 in the aforementioned embodiments. For specific implementation methods, please refer to the aforementioned description of steps 202-204, which will not be repeated here.

[0045] from Figure 3 It can be seen from this that, with Figure 2 Compared with the corresponding embodiments, the map green space recognition method in this embodiment emphasizes the step of detecting the area to be identified. By calculating the actual area of ​​the vector surface of the area to be identified and combining it with preset area detection rules for quantitative judgment, it can accurately identify fragments that are too small or abnormal areas that are too large, eliminate interference areas that do not conform to the size characteristics of green space areas, simplify the subsequent recognition process, and thus improve the screening efficiency and overall recognition accuracy of green space recognition.

[0046] Continue to refer to Figure 4 , Figure 4A flowchart 400 is shown according to a third embodiment of the map green space identification method according to this disclosure. The map green space identification method includes the following steps: Step 401: Calculate the shape value of the region to be identified based on the vector surface data of the region to be identified.

[0047] In this embodiment, the executing entity of the map green space identification method (e.g.) Figure 1 The server 106 shown will calculate the shape value of the region to be identified based on the vector surface data of the region to be identified. The shape value includes at least one of the following: perimeter, aspect ratio, and area-to-perimeter ratio.

[0048] Specifically, the aforementioned execution entity extracts the coordinates of all vertices of the closed polygon of the vector surface and arranges them in order of boundary direction. It then sequentially selects two adjacent vertices, calculates the length of each boundary segment using the coordinate distance formula, and sums the lengths of all boundary segments to obtain the total length of the polygon boundary. Finally, it performs corrections using coordinate projection parameters, standardizes unit conversions, and ultimately calculates the actual planar perimeter of the vector surface.

[0049] The aforementioned execution entity will extract the contour boundary of the vector surface to be identified, calculate the minimum bounding rectangle of the vector surface, determine the length of the long side and the length of the short side of the bounding rectangle, and then calculate the aspect ratio by dividing the length of the long side by the length of the short side.

[0050] The aforementioned implementing entity will calculate the ratio of area to perimeter, thereby obtaining the area-perimeter ratio.

[0051] Step 402: Generate the shape detection result of the region to be identified based on the shape detection rules and shape values.

[0052] In this embodiment, the preset shape detection rules include: shape detection rules. The aforementioned execution entity will pre-set corresponding shape detection rules and judgment thresholds, covering judgment conditions such as contour regularity, shape extension, and boundary complexity. The aforementioned execution entity will sequentially compare and analyze the shape values ​​such as the aspect ratio, perimeter, and area-to-perimeter ratio of each region to be identified with the preset thresholds, and remove regions with narrow and elongated shapes, complex boundaries, fragmented structures, and irregular contours, thereby selecting target regions with complete morphological structures, regular contours, and conforming to the morphological characteristics of green areas.

[0053] Specifically, if the perimeter of a region is less than the minimum threshold, it is judged as a small, fragmented region with short boundaries; if the perimeter exceeds the maximum threshold, it is judged as a narrow, elongated region with abnormal contour extension. Both types are judged as failing shape detection and are removed.

[0054] If the aspect ratio exceeds the preset upper limit, it indicates that the area is too long and narrow and the shape is distorted; if the aspect ratio is lower than the preset lower limit, it indicates that the area is too compact and does not conform to the normal shape of green space, and is judged as unqualified in shape detection.

[0055] If the area-to-perimeter ratio is lower than the preset threshold, it indicates that the region boundary is tortuous, the outline is broken, the edges are complex, and the geometric shape is irregular, and the shape detection is deemed unqualified.

[0056] The aforementioned executing entity will comprehensively judge the three shape indicators of perimeter, aspect ratio, and area-perimeter ratio simultaneously. If any one of them fails to meet the corresponding preset rules and threshold requirements, the overall shape detection result of the area to be identified will be unsuccessful; if all of them meet the preset specifications, the shape detection will be deemed successful.

[0057] Step 403: In response to determining that the shape detection result is passed, determine the feature values ​​of the region to be identified in multiple preset dimensions.

[0058] Step 404: Generate comprehensive information about the region to be identified based on feature values ​​of multiple preset dimensions.

[0059] Step 405: Determine the target recognition result of the area to be identified based on the comprehensive information and the preset information threshold.

[0060] Steps 403-405 are basically the same as steps 202-204 in the aforementioned embodiments. For specific implementation methods, please refer to the aforementioned description of steps 202-204, which will not be repeated here.

[0061] from Figure 4 It can be seen from this that, with Figure 2 Compared to the corresponding embodiments, the map green space recognition method in this embodiment emphasizes the step of detecting the area to be identified. By calculating the shape parameters of the area to be identified, such as the perimeter, aspect ratio, and area-to-perimeter ratio, and combining them with preset shape detection rules, the method can effectively identify irregular areas with narrow shapes, complex boundaries, and fragmented structures, eliminate interference targets with abnormal shapes, optimize the quality of candidate areas, and improve the accuracy and stability of subsequent green space recognition.

[0062] Continue to refer to Figure 5 , Figure 5 A flowchart 500 is shown according to a fourth embodiment of the map green space identification method of this disclosure. The map green space identification method includes the following steps: Step 501: Construct the spatial adjacency relationship between the region to be identified and other candidate regions.

[0063] In this embodiment, the executing entity of the map green space identification method (e.g.) Figure 1The server 106 shown traverses the boundary contour and spatial coordinates of a single region to be identified. Based on a vector topology analysis algorithm, it searches all surrounding candidate regions one by one, and sequentially determines the spatial topological relationships between each region, including spatial adjacency, shared boundaries, region intersection, and spatial isolation. It also records the positional association information, boundary contact range, spatial distance, and other parameters between the region to be identified and each surrounding candidate region, quantitatively distinguishing between neighboring regions and isolated regions, thereby constructing the spatial adjacency association relationship between each region to be identified and the other candidate regions, forming structured spatial association data.

[0064] Step 502: Generate the topological relationship detection results of the region to be identified based on the topological relationship detection rules and spatial adjacency relationships.

[0065] In this embodiment, the preset morphological detection rules include: topological relationship detection rules. These rules are used to determine the integrity of regional contiguous areas and spatial clustering attributes, filtering out isolated, discrete patches without vegetation clustering characteristics. Specifically, the execution entity traverses each region to be identified, determining whether there are adjacent or shared-edge candidate regions. If the region to be identified shares an edge or is adjacent to at least one other candidate region, it is determined that the region possesses the characteristics of contiguous green space distribution and passes the topological detection. If the region to be identified is completely separated from all surrounding candidate regions and has no spatial adjacency, it is determined to be an isolated, fragmented patch that does not conform to the spatial characteristics of clustered growth in green spaces, fails the topological detection, and is removed. By performing topological verification on all candidate regions, regions with strong spatial connectivity and distribution characteristics conforming to the laws of natural green spaces are selected, and the topological relationship detection results for all regions to be identified are finally output.

[0066] Step 503: In response to determining that the topological relationship detection result is passed, determine the feature values ​​of the region to be identified in multiple preset dimensions.

[0067] Step 504: Generate comprehensive information about the region to be identified based on feature values ​​of multiple preset dimensions.

[0068] Step 505: Determine the target recognition result of the area to be identified based on the comprehensive information and the preset information threshold.

[0069] Steps 503-505 are basically the same as steps 202-204 in the aforementioned embodiments. For specific implementation methods, please refer to the aforementioned description of steps 202-204, which will not be repeated here.

[0070] from Figure 5 It can be seen from this that, with Figure 2Compared with the corresponding embodiments, the map green space identification method in this embodiment emphasizes the step of detecting the area to be identified. By constructing the spatial adjacency relationship between the area to be identified and the surrounding candidate areas, and combining it with topological detection rules for discrimination, it can effectively identify isolated and scattered patch areas, screen targets with contiguous distribution characteristics, eliminate interference areas with weak spatial correlation, strengthen the constraint of the spatial distribution pattern of green space areas, and further improve the rationality and reliability of green space identification.

[0071] Continue to refer to Figure 6 , Figure 6 A flowchart 600 of a fifth embodiment of the map green space identification method according to the present disclosure is shown. The map green space identification method includes the following steps: Step 601: Detect the region to be identified according to the preset morphological detection rules to obtain the detection result.

[0072] Step 601 is basically the same as step 201 in the aforementioned embodiment. For the specific implementation method, please refer to the aforementioned description of step 201, which will not be repeated here.

[0073] Step 602: In response to determining that the detection result is passed, perform spatial analysis on the vector surface of the region to be identified, and extract features of multiple preset dimensions based on the analysis results.

[0074] In this embodiment, if the detection result is determined to be a pass, the execution entity of the map green space recognition method (e.g., Figure 1 The server 106 shown will perform spatial analysis on the vector surface of the region to be identified, and extract features of multiple preset dimensions based on the analysis results. Among them, the multiple preset dimensions include at least two of the following: area dimension, aspect ratio dimension, compactness dimension, orientation dimension, distance dimension, and spatial connectivity dimension.

[0075] The aforementioned implementing entity will use geospatial analysis technology to comprehensively analyze the geometric contour, spatial location, and adjacency relationships of the vector surface, sequentially extracting features from dimensions such as area, aspect ratio, compactness, direction, distance, and spatial connectivity. This will standardize the calculation methods and data formats for each dimension, completing the standardized extraction and quantification of multi-dimensional features, comprehensively covering geometric shape, spatial location, and adjacency attributes.

[0076] Step 603: Perform geometric calculations based on features of multiple preset dimensions to obtain feature values ​​of multiple preset dimensions.

[0077] In this embodiment, the aforementioned execution entity can directly calculate the actual projected area of ​​the vector surface, thereby obtaining the area dimension feature value. The aspect ratio dimension feature value is obtained by dividing the length of the longer side of the circumscribed rectangle by the length of the shorter side, which characterizes the degree of regional extension. The compactness dimension feature value can be calculated according to a preset formula, area value, and perimeter value; the closer the value is to 1, the more regular and compact the shape. The direction dimension, distance dimension, and intersection dimension are features related to the surrounding environment. Specifically, the direction dimension feature value is obtained by calculating the angle difference between the main extension direction of the area to be identified and the overall extension direction of the land parcel; the distance dimension feature value is obtained by calculating the Euclidean distance from the center of the target area to the nearest road, water system, or land parcel boundary; and the intersection dimension (spatial connectivity dimension) feature value is obtained by assigning values ​​according to topological relationships (e.g., adjacent = 1, disjoint = 0, contained = 2, intersecting = 3).

[0078] By conducting spatial analysis on the regional vector surface, geometric morphology, spatial location, and connectivity-related features are extracted from multiple angles. Based on standardized geometric calculations, feature values ​​of each dimension are quantified, comprehensively characterizing the structure and spatial attributes of the region to be identified. This provides objective and accurate quantitative data for subsequent comprehensive analysis and threshold determination, improving the scientific rigor and reliability of the identification process.

[0079] Step 604: Determine the weight value corresponding to each preset dimension.

[0080] In this embodiment, the aforementioned execution entity will determine the weight value corresponding to each preset dimension. This weight value can be set based on actual experience. For example, the weight of the area dimension is 0.2, the weight of the aspect ratio dimension is 0.15, the weight of the compactness dimension is 0.2, the weight of the direction dimension is 0.15, the weight of the distance dimension is 0.15, the weight of the intersection dimension is 0.15, and the sum of all dimension weights is 1.

[0081] Step 605: Perform weighted calculations based on the feature values ​​of each preset dimension and the corresponding weight values ​​of each preset dimension to obtain comprehensive information about the region to be identified.

[0082] In this embodiment, the execution entity will determine the weight value corresponding to each preset dimension, and then perform weighted calculation based on the weight value of each preset dimension and the feature value of each preset dimension to obtain comprehensive information of the region to be identified.

[0083] Alternatively, the aforementioned execution entity can generate a score corresponding to each preset dimension based on the feature values ​​of multiple preset dimensions, and then normalize the scores to map the values ​​uniformly to the 0-1 interval, thereby obtaining the area score (area_score), aspect ratio score (aspect_ratio_score), compactness score (compactness_score), orientation score (orientation_score), distance score (distance_score), and intersection score (intersection_score). A weighted calculation is then performed based on the weight value of each preset dimension and the score of each preset dimension to obtain the comprehensive information (also known as the comprehensive score) of the region to be identified. Specifically, the weighted calculation can be performed according to the following formula to obtain the comprehensive information of the region to be identified. : ; Where i is the number of dimensions. It is the weight of each rating dimension, satisfying ; These are scores based on different dimensions, including: area score, aspect ratio score, compactness score, orientation score, distance score, and cross score.

[0084] By matching differentiated weight values ​​to each preset dimension and performing weighted calculations based on the feature values ​​of each dimension, it is possible to reasonably distinguish the importance of different geometric and spatial features, weaken the influence of interfering indicators, comprehensively integrate multi-dimensional quantitative information, objectively reflect the overall attributes of the area to be identified, and improve the comprehensiveness of the comprehensive evaluation and the accuracy of the judgment results.

[0085] Step 606: In response to determining that the comprehensive information is greater than or equal to the preset information threshold, the target identification result is determined to be a green area.

[0086] In this embodiment, if the comprehensive information is greater than or equal to a preset information threshold, the execution entity will determine that the vegetation features of the area are complete and the morphology conforms to the characteristics of a green area, and directly determine its target identification result as a green area. The preset information threshold can be set based on practical experience; for example, it can be set to 0.5, i.e., if... If the value is ≥0.5, then the area to be identified is determined to be a green area.

[0087] Step 607: In response to determining that the comprehensive information is less than the preset information threshold, the target identification result is determined to be a non-green area.

[0088] In this embodiment, if the comprehensive information is less than a preset information threshold, it indicates that the geometric shape, spatial structure, and vegetation-related features of the area do not conform to the basic attributes of a green area, and the target identification result is determined to be a non-green area. That is, if If the value is less than 0.5, the area to be identified is determined to be a non-green area.

[0089] This method establishes a unified discrimination standard based on preset information thresholds, and compares and judges the comprehensive quantitative information of the area to be identified to clearly distinguish between green areas and non-green areas. This method is logically rigorous and follows consistent rules, stably quantifying the comprehensive characteristics of the area, avoiding subjective judgment bias, effectively improving the consistency and accuracy of target identification, and achieving automated and accurate identification of area types.

[0090] from Figure 6 It can be seen from this that, with Figure 2 Compared to the corresponding embodiments, the map-based green space identification method in this embodiment extracts regional geometric and spatial features through multi-dimensional spatial analysis, quantifies various indicators through geometric calculations, matches corresponding weights for weighted fusion, and forms comprehensive evaluation information. It relies on a unified threshold for quantitative discrimination, comprehensively integrates diverse features, reduces the limitations of single indicators, improves the objectivity, accuracy, and stability of green space identification, and achieves automated and accurate determination of regional categories.

[0091] Continue to refer to Figure 7 , Figure 7 A flowchart 700 of a sixth embodiment of the map green space identification method according to the present disclosure is shown. The map green space identification method includes the following steps: Step 701: Detect the region to be identified according to the preset shape detection rules to obtain the detection result.

[0092] Step 702: In response to determining that the detection result is passed, determine the feature values ​​of the region to be identified in multiple preset dimensions.

[0093] Step 703: Generate comprehensive information of the region to be identified based on feature values ​​of multiple preset dimensions.

[0094] Step 704: Determine the target recognition result of the area to be identified based on the comprehensive information and the preset information threshold.

[0095] Steps 701-704 are basically the same as steps 201-204 in the aforementioned embodiments. For specific implementation methods, please refer to the aforementioned description of steps 201-204, which will not be repeated here.

[0096] Step 705: In response to determining that the area to be identified is a green area and the comprehensive information is within the preset edge information range, determine the similarity between the area to be identified and the sample data in the pre-built database.

[0097] In this embodiment, if the area to be identified is determined to be a green area ( ≥0.5) and the comprehensive information is within the preset edge information range, then the execution subject of the map green space recognition method (e.g. Figure 1 The server 106 shown will determine the similarity between the region to be identified and sample data in a pre-built database. The preset edge information interval can be set based on practical experience, for example, [0.5, 0.65]. Assuming the region to be identified... If the similarity is 0.6, then it can be determined that the comprehensive information of the region to be identified lies within the preset edge information range, meaning the region to be identified is a blurry sample at the threshold edge. At this point, the execution entity will calculate the vector similarity (cosine similarity) between the region to be identified and each sample data in the pre-built database. Specifically, the similarity can be calculated based on the following formula: ; Among them, the molecular part 12 represents the dot product (inner product) of 12-dimensional vectors. It is the feature value of the i-th dimension of the region to be identified. The dot product represents the feature value of the i-th dimension of the sample data in the database, reflecting the directional consistency of the two vectors. The denominator represents the product of the magnitudes (lengths) of the two vectors, ensuring that the similarity calculation is not affected by the vector lengths, focusing only on the direction.

[0098] It should be noted that the 12 dimensions of the vector include: area (original area), log_area (logarithmic area), sqrt_area (square root area), aspect_ratio (aspect ratio), sqrt_aspect_ratio (square root aspect ratio), compactness, area_perimeter_ratio (area-perimeter ratio), perimeter (original perimeter), log_perimeter (logarithmic perimeter), orientation_diff (orientation difference), distance_to_highway (distance to the highway), and intersection_type (intersection type).

[0099] It should be noted that the database, or historical case library, is a pre-built and continuously updated standardized database that stores massive amounts of regional sample data that have undergone manual verification, labeling, and classification. It covers the geometric features, spatial topological parameters, multi-dimensional indicator values, and final classification results of the samples, providing a reference benchmark, feature comparison, and threshold optimization basis.

[0100] Step 706: Determine the target sample data from the database based on similarity.

[0101] In this embodiment, the top K sample data are determined from the database based on the calculated similarity to obtain the target sample data, where K is an integer greater than or equal to 1, that is, the number of target sample data can be one or more.

[0102] Step 707: Determine the final recognition result of the region to be identified based on the label of the target sample data and the target similarity between the region to be identified and the target sample data.

[0103] In this embodiment, the execution entity determines the final identification result of the region to be identified based on the labels of the target sample data and the target similarity between the region to be identified and the target sample data. The labels include green area labels and non-green area labels. Since the sample data in the database are all labeled, indicating whether they are green or non-green areas, the execution entity determines the final identification result of the region to be identified based on the labels of the target sample data and the target similarity between the region to be identified and the target sample data.

[0104] Therefore, for candidate green space areas whose comprehensive indicators are in the critical range, a sample database is introduced for similarity comparison, and the target sample with the highest matching degree is selected to assist in the judgment. The final result is determined by combining the sample label and the similarity value, which effectively solves the problem of ambiguity in the identification of critical areas, makes up for the limitations of single threshold judgment, and improves the accuracy and rationality of edge area identification.

[0105] In some optional implementations of this embodiment, step 707 includes: in response to determining that the target similarity is greater than or equal to a preset similarity threshold, determining the label of the target sample data as the final recognition result of the region to be recognized; in response to determining that the target similarity is less than the preset similarity threshold, determining the final recognition result of the region to be recognized as the target recognition result.

[0106] In this implementation, there is only one target sample data. After the target similarity between the region to be identified and the target sample data in the database is calculated, the execution entity retrieves a preset similarity threshold for comparison. The preset similarity threshold can be set to 0.8 or other values; this embodiment does not specifically limit this. If the target similarity is greater than or equal to the preset threshold, the label of the target sample data is determined to have reference value, and the corresponding green area label or non-green area label is directly determined as the final identification result of the region to be identified. If the target similarity is less than the preset similarity threshold, it indicates that the target sample and the region to be identified have significant differences in features, and the sample is not sufficiently referenceable. The sample comparison result is discarded, and the target identification result obtained from the previous multi-dimensional weighted calculation is used as the final identification result of the region to be identified. Thus, by setting a similarity threshold for differentiated judgment, the database label information is fully utilized to assist in the judgment of high-similarity samples, effectively solving the critical region identification error; the original identification result is retained for low-similarity samples, avoiding misjudgment caused by sample bias. This approach balances the reference value of samples and the stability of judgment, improves the critical region identification mechanism, and enhances the accuracy and reliability of the overall identification results.

[0107] In some optional implementations of this embodiment, the number of target sample data is multiple; and step 707 includes: determining the maximum similarity value based on the target similarity between the region to be identified and the multiple target sample data; in response to determining that the maximum similarity value is greater than or equal to a preset similarity threshold, determining the number of green area labels and the number of non-green area labels in the labels of the multiple target sample data; in response to determining that the number of green area labels is greater than or equal to the number of non-green area labels, determining that the final identification result is that the region to be identified is a green area; in response to determining that the number of green area labels is less than the number of non-green area labels, determining that the final identification result is that the region to be identified is a non-green area.

[0108] In this implementation, there are multiple target sample data sets. The execution entity obtains the similarity scores between the region to be identified and multiple target sample data sets in the database, calculates and filters out the maximum similarity score. It then determines whether this maximum score meets a preset similarity threshold. If it does, it counts the number of green area labels and non-green area labels in all target sample data sets. The number of the two types of labels is compared. If the number of green area labels is greater than or equal to the number of non-green area labels, the region to be identified is determined to be a green area; otherwise, it is determined to be a non-green area. This completes the final identification of the critical region. By comparing the similarity scores of multiple target samples and filtering out the maximum score, combined with the number of sample labels, a comprehensive judgment is made, improving the discrimination logic of the critical region, enhancing the objectivity and rationality of the classification results, effectively reducing the probability of misjudgment, and strengthening the stability and applicability of the green area identification model.

[0109] Step 708: Associate and bind the features of multiple preset dimensions of the region to be identified with the final identification result of the region to be identified, and add the bound features to the database.

[0110] In this embodiment, after completing the final identification of the region to be identified, the execution entity integrates the preset dimensional feature data (12-dimensional feature vector) of the region and the corresponding final identification result to establish data association binding, so that the feature parameters correspond one-to-one with the classification results. It also supports multiple feature transformations (original value, logarithm, square root) to enhance the robustness of similarity calculation. The execution entity will standardize the bound complete data information, verify the data integrity and standardization, and then batch input and update it to the preset database, continuously expanding the sample data volume and enriching the database feature samples, providing comprehensive data support for subsequent identification optimization and sample comparison.

[0111] from Figure 7 It can be seen from this that, with Figure 2 Compared to the corresponding embodiments, the map green space recognition method in this embodiment, for candidate areas whose comprehensive indicators are in the critical range, introduces a sample database for similarity comparison and selects the target sample with the highest matching degree to assist in the judgment. By combining sample labels and similarity values ​​to comprehensively determine the final result, this method effectively solves the problem of ambiguity in critical area recognition, overcomes the limitations of single threshold judgment, and improves the accuracy and rationality of edge area recognition.

[0112] Further reference Figure 8 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of a map green space recognition device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0113] like Figure 8 As shown, the map green space recognition device 800 of this embodiment includes: a shape detection module 801, a feature determination module 802, an information generation module 803, and a target recognition module 804. The shape detection module 801 is configured to detect the area to be recognized according to preset shape detection rules and obtain a detection result; the feature determination module 802 is configured to determine the feature values ​​of the area to be recognized in multiple preset dimensions in response to determining that the detection result is passed; the information generation module 803 is configured to generate comprehensive information of the area to be recognized based on the feature values ​​of the multiple preset dimensions; and the target recognition module 804 is configured to determine the target recognition result of the area to be recognized based on the comprehensive information and a preset information threshold, wherein the target recognition result is used to characterize whether the area to be recognized is a green space or a non-green space.

[0114] In this embodiment, the specific processing of the shape detection module 801, feature determination module 802, information generation module 803, and target recognition module 804 in the map green space recognition device 800, and the resulting technical effects, can be found in the following references: Figure 2 The relevant descriptions of steps 201-204 in the corresponding embodiments will not be repeated here.

[0115] In some optional implementations of this embodiment, the preset shape detection rules include: area detection rules; and the shape detection module 801 is further configured to: calculate the actual area of ​​the region to be identified based on the vector surface data of the region to be identified; and generate the area detection result of the region to be identified based on the area detection rules and the actual area.

[0116] In some optional implementations of this embodiment, the preset shape detection rules include: area detection rules; and the shape detection module 801 is further configured to: calculate the shape value of the region to be identified based on the vector surface data of the region to be identified, wherein the shape value includes at least one of the following: perimeter, aspect ratio, area-to-perimeter ratio; and generate the shape detection result of the region to be identified based on the shape detection rules and the shape value.

[0117] In some optional implementations of this embodiment, the preset shape detection rules include: topology relationship detection rules; and the shape detection module 801 is further configured to: construct the spatial adjacency relationship between the region to be identified and other candidate regions; and generate the topology relationship detection result of the region to be identified based on the topology relationship detection rules and the spatial adjacency relationship.

[0118] In some optional implementations of this embodiment, the feature determination module 802 is further configured to: perform spatial analysis on the vector surface of the region to be identified, extract features of multiple preset dimensions based on the analysis results, wherein the multiple preset dimensions include at least two of the following: area dimension, aspect ratio dimension, compactness dimension, orientation dimension, distance dimension, and spatial connectivity dimension; and perform geometric calculations based on the features of the multiple preset dimensions to obtain feature values ​​of the multiple preset dimensions.

[0119] In some optional implementations of this embodiment, the information generation module 803 is further configured to: determine the weight value corresponding to each preset dimension; perform weighted calculation based on the feature value of each preset dimension and the weight value corresponding to each preset dimension to obtain comprehensive information of the region to be identified.

[0120] In some optional implementations of this embodiment, the target recognition module 804 is further configured to: determine that the target recognition result is a green area in response to determining that the comprehensive information is greater than or equal to a preset information threshold; and determine that the target recognition result is a non-green area in response to determining that the comprehensive information is less than the preset information threshold.

[0121] In some optional implementations of this embodiment, the map green space recognition device 800 further includes: a similarity calculation module, configured to determine the similarity between the area to be recognized and sample data in a pre-built database in response to determining that the area to be recognized is a green space and that the comprehensive information is within a preset edge information range; a sample determination module, configured to determine target sample data from the database based on the similarity; and a final recognition module, configured to determine the final recognition result of the area to be recognized based on the label of the target sample data and the target similarity between the area to be recognized and the target sample data, wherein the label includes a green space label and a non-green space label.

[0122] In some optional implementations of this embodiment, the final identification module is further configured to: determine the label of the target sample data as the final identification result of the region to be identified in response to determining that the target similarity is greater than or equal to a preset similarity threshold; and determine the final identification result of the region to be identified as the target identification result in response to determining that the target similarity is less than a preset similarity threshold.

[0123] In some optional implementations of this embodiment, the number of target sample data is multiple; and the final identification module is further configured to: determine the maximum similarity value based on the target similarity between the region to be identified and the multiple target sample data; in response to determining that the maximum similarity value is greater than or equal to a preset similarity threshold, determine the number of green area labels and the number of non-green area labels among the labels of the multiple target sample data; in response to determining that the number of green area labels is greater than or equal to the number of non-green area labels, determine that the final identification result is that the region to be identified is a green area; in response to determining that the number of green area labels is less than the number of non-green area labels, determine that the final identification result is that the region to be identified is a non-green area.

[0124] In some optional implementations of this embodiment, the map green space recognition device 800 further includes an adding module, configured to associate and bind features of multiple preset dimensions of the area to be recognized with the final recognition result of the area to be recognized, and add the bound features to the database.

[0125] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0126] Figure 9A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0127] like Figure 9 As shown, device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 902 or a computer program loaded from storage unit 908 into random access memory (RAM) 903. RAM 903 may also store various programs and data required for the operation of device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via bus 904. Input / output (I / O) interface 905 is also connected to bus 904.

[0128] Multiple components in device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of monitors, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0129] The computing unit 901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the map green space recognition method. For example, in some embodiments, the map green space recognition method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed on device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by computing unit 901, one or more steps of the map green space recognition method described above can be performed. Alternatively, in other embodiments, the computing unit 901 can be configured to perform the map green space recognition method by any other suitable means (e.g., by means of firmware).

[0130] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0131] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0132] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0133] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0134] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0135] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0136] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0137] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for identifying green areas on a map, comprising: The region to be identified is detected according to a preset shape detection rule to obtain the detection result; In response to determining that the detection result is a pass, the feature values ​​of the region to be identified in multiple preset dimensions are determined; Generate comprehensive information about the region to be identified based on the feature values ​​of the multiple preset dimensions; Based on the comprehensive information and the preset information threshold, the target identification result of the area to be identified is determined, wherein the target identification result is used to characterize whether the area to be identified is a green area or a non-green area.

2. The method according to claim 1, wherein, The preset shape detection rules include: area detection rules; and The step of detecting the region to be identified according to a preset shape detection rule to obtain the detection result includes: Calculate the actual area of ​​the region to be identified based on the vector surface data of the region to be identified; Based on the area detection rules and the actual area, the area detection result of the region to be identified is generated.

3. The method according to claim 1, wherein, The preset shape detection rules include: shape detection rules; and The step of detecting the region to be identified according to a preset shape detection rule to obtain the detection result includes: The shape value of the region to be identified is calculated based on the vector surface data of the region to be identified, wherein the shape value includes at least one of the following: perimeter, aspect ratio, and area-to-perimeter ratio; Based on the shape detection rules and the shape values, the shape detection result of the region to be identified is generated.

4. The method according to claim 1, wherein, The preset morphology detection rules include: topological relationship detection rules; and The step of detecting the region to be identified according to a preset shape detection rule to obtain the detection result includes: Construct the spatial adjacency relationship between the region to be identified and other candidate regions; Based on the topology relationship detection rules and the spatial adjacency relationships, the topology relationship detection results of the region to be identified are generated.

5. The method according to claim 1, wherein, Determining the feature values ​​of the region to be identified in multiple preset dimensions includes: Spatial analysis is performed on the vector surface of the region to be identified, and features of multiple preset dimensions are extracted based on the analysis results. The multiple preset dimensions include at least two of the following: area dimension, aspect ratio dimension, compactness dimension, orientation dimension, distance dimension, and spatial connectivity dimension. Geometric calculations are performed based on the features of the multiple preset dimensions to obtain the feature values ​​of the multiple preset dimensions.

6. The method according to claim 5, wherein, The step of generating comprehensive information about the region to be identified based on the feature values ​​of the multiple preset dimensions includes: Determine the weight value corresponding to each preset dimension; The comprehensive information of the region to be identified is obtained by weighting the feature values ​​of each preset dimension and the corresponding weight values ​​of each preset dimension.

7. The method according to claim 1, wherein, The step of determining the target recognition result of the region to be identified based on the comprehensive information and the preset information threshold includes: In response to determining that the comprehensive information is greater than or equal to the preset information threshold, the target identification result is determined to be the green area; In response to determining that the comprehensive information is less than the preset information threshold, the target identification result is determined to be that the area to be identified is the non-green area.

8. The method according to any one of claims 1-7, further comprising: In response to determining that the area to be identified is the green area and that the comprehensive information is located within a preset edge information range, the similarity between the area to be identified and the sample data in the pre-built database is determined; Target sample data is determined from the database based on the similarity. Based on the labels of the target sample data and the target similarity between the region to be identified and the target sample data, the final identification result of the region to be identified is determined, wherein the labels include green area labels and non-green area labels.

9. The method according to claim 8, wherein, The step of determining the final recognition result of the region to be recognized based on the label of the target sample data and the target similarity between the region to be recognized and the target sample data includes: In response to determining that the target similarity is greater than or equal to a preset similarity threshold, the label of the target sample data is determined as the final recognition result of the region to be identified; In response to determining that the target similarity is less than the preset similarity threshold, the final recognition result of the region to be identified is determined as the target recognition result.

10. The method according to claim 8, wherein, The number of target sample data is multiple; and The step of determining the final recognition result of the region to be recognized based on the label of the target sample data and the target similarity between the region to be recognized and the target sample data includes: The maximum similarity value is determined based on the target similarity between the region to be identified and multiple target sample data. In response to determining that the maximum similarity value is greater than or equal to a preset similarity threshold, the number of green area labels and the number of non-green area labels in the labels of the multiple target sample data are determined; In response to determining that the number of green area tags is greater than or equal to the number of non-green area tags, the final identification result is determined to be that the area to be identified is the green area; In response to determining that the number of green area tags is less than the number of non-green area tags, the final identification result is determined to be that the area to be identified is the non-green area.

11. The method of claim 8, further comprising: The features of multiple preset dimensions of the region to be identified are associated and bound with the final identification result of the region to be identified, and the bound features are added to the database.

12. A map-based green space identification device, comprising: The shape detection module is configured to detect the region to be identified according to preset shape detection rules and obtain the detection result. The feature determination module is configured to determine the feature values ​​of the region to be identified in multiple preset dimensions in response to determining that the detection result is a pass detection. The information generation module is configured to generate comprehensive information about the region to be identified based on the feature values ​​of the multiple preset dimensions. The target recognition module is configured to determine the target recognition result of the area to be identified based on the comprehensive information and a preset information threshold, wherein the target recognition result is used to characterize whether the area to be identified is a green area or a non-green area.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.

14. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-11.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-11.

Images