Node graph legend identification method and device, equipment, storage medium and program product

Abstract

The present application relates to the technical field of computer, disclose a kind of node legend identification method, device, equipment, storage medium and program product, wherein, method includes: obtaining the candidate graph element to be identified in pipe network drawing drawing;From candidate graph element, obtain the target graph element set corresponding to target legend type;According to the identification rule corresponding to target legend type, identify target node legend in target graph element set;According to the geometric line of target legend type and target node legend, determine the feature information of target node legend.The present application realizes the automatic identification of node legend, improves the identification efficiency of node legend.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and specifically to a method, apparatus, device, storage medium, and program product for node legend recognition. Background Technology

[0002] In pipeline engineering, the process typically begins with drawing pipeline network diagrams. Then, based on these diagrams, relevant information from node symbols is identified and quantities are calculated. Procurement and construction are then carried out based on the calculated quantities. Currently, node symbol information is usually identified manually. However, because pipeline network diagrams often contain a large number of graphic elements with diverse styles, manual identification of node symbols is not only inefficient but also prone to errors. Summary of the Invention

[0003] In view of this, the present invention provides a method, apparatus, device, storage medium and program product for node legend recognition, so as to solve the problems of low recognition efficiency and easy error in node legend.

[0004] In a first aspect, the present invention provides a node legend recognition method, comprising: acquiring candidate elements to be identified in a pipeline drawing; acquiring a set of target elements corresponding to a target legend type from the candidate elements; identifying target node legends in the set of target elements according to the recognition rules corresponding to the target legend type; and determining the feature information of the target node legends according to the target legend type and the geometric lines of the target node legends.

[0005] The node legend recognition method provided by this invention involves acquiring candidate elements to be identified in a pipeline network drawing; obtaining a set of target elements corresponding to the target legend type from the candidate elements; identifying target node legends in the target element set according to the recognition rules corresponding to the target legend type; and determining the feature information of the target node legend based on the target legend type and the geometric lines of the target node legend. Therefore, no manual intervention is required in the recognition process of node legends and their feature information, which not only achieves automated node legend recognition and greatly improves the recognition efficiency, but also avoids recognition errors caused by human factors.

[0006] In one optional implementation, the step of obtaining candidate graphic elements to be identified in the pipeline network drawing includes: obtaining each original graphic element in the pipeline network drawing and the graphic element information of the original graphic elements; for each graphic element information, determining whether the graphic element information includes target information that meets preset conditions; if not, determining the original graphic element corresponding to the graphic element information as a candidate graphic element to be identified.

[0007] The node legend recognition method provided by this invention obtains the graphic information of each original graphic element in the pipeline network drawing and determines whether the graphic information includes target information that meets preset conditions. This can filter out the original graphic elements that do not belong to the node legend, narrow the recognition range, and then perform recognition processing based on the candidate graphic elements after narrowing the recognition range, which can greatly improve the recognition efficiency and recognition accuracy.

[0008] In one optional implementation, the target legend type includes a shuffled type; obtaining the target element set corresponding to the target legend type from the candidate elements includes: obtaining the element number of the candidate elements; dividing each candidate element according to the continuity of the element number to obtain at least one target element set.

[0009] Correspondingly, the step of identifying target node legends in the target element set according to the identification rules corresponding to the target legend type includes: for each target element set, determining the positional relationship between two candidate elements with consecutive element numbers in the target element set; determining whether there exists a target positional relationship in the positional relationship that indicates that the graphic ranges of the two candidate elements do not intersect; if so, dividing the target element set into multiple first subsets according to the target positional relationship, and determining each candidate element in the first subset as a whole as a target node legend; the graphic ranges of two candidate elements with consecutive element numbers in the first subset intersect; if not, determining each candidate element in the target element set as a whole as a target node legend.

[0010] The node legend recognition method provided by this invention achieves automatic and accurate recognition of broken node legends based on the continuity of the primitive number and the intersection between the graphic ranges corresponding to the minimum bounding boxes of candidate primitives.

[0011] In an optional implementation, the method further includes: filtering candidate primitives of the broken type from the candidate primitives to obtain candidate primitives to be processed; determining the primitive type of the candidate primitives to be processed based on the primitive information of the candidate primitives to be processed; if the target legend type includes a block reference type, then assigning the candidate primitives to be processed with the primitive type of block reference type to the target primitive set corresponding to the block reference type; if the target legend type includes a combination type, then assigning the candidate primitives to be processed with the primitive type of combination type to the target primitive set corresponding to the combination type.

[0012] The node legend recognition method provided by this invention, when the target legend type includes a broken type and also includes at least one of a block reference type and a combined type, first identifies the node legend of the target type, then filters the candidate legends of the broken type from the candidate legends to obtain the candidate legends to be processed, and performs recognition of other types of node legends based on the candidate legends to be processed, can avoid the broken type candidate legends being identified multiple times, causing recognition errors.

[0013] In one optional implementation, the target legend type includes a block reference type. Identifying the target node legend in the target element set according to the identification rules corresponding to the target legend type includes: dividing the target element set into at least one second subset based on a preset correspondence between block definition elements and block reference elements; the candidate elements in the second subset correspond to the same block definition element; for each second subset, selecting target candidate elements from the second subset; determining whether the target candidate element is a target node legend; if so, determining each candidate element in the second subset as a target node legend.

[0014] The node legend recognition method provided by this invention divides all candidate nodes (i.e., block reference nodes) corresponding to the same defined primitive into the same second subset. It determines whether each candidate node in the second subset is a target node legend of the fast reference type simply by determining whether it is one of the target node legends of the fast reference type. This eliminates the need to individually determine whether each candidate node in the target primitive set corresponding to the fast reference type is a target node legend of the fast reference type. Therefore, it greatly improves recognition efficiency.

[0015] In one optional implementation, the target legend type includes a combination type, and the step of identifying the target node legend in the target element set according to the identification rule corresponding to the target legend type includes: for each candidate element in the target element set, obtaining a second geometric shape from the geometric lines of the candidate element; determining whether the second geometric shape contains a preset geometric shape; if so, determining that the candidate element is a target node legend.

[0016] The node legend recognition method provided by this invention realizes the automatic recognition of combined node legends based on the geometric shape type of the node legend, which not only improves the recognition efficiency, but also avoids the problems of errors that are easy to occur in human recognition.

[0017] Secondly, the present invention provides a node legend recognition device, comprising: a first acquisition module, configured to acquire candidate elements belonging to node legends in a pipeline network drawing; a second acquisition module, configured to acquire a target element set corresponding to a target legend type from the candidate elements; an identification module, configured to identify node legends in the target element set according to the identification rules corresponding to the target legend type; and a determination module, configured to determine the feature information of the node legends according to the target legend type and the geometric lines of the node legends.

[0018] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the node legend recognition method of the first aspect or any corresponding embodiment described above.

[0019] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the node legend recognition method of the first aspect or any corresponding embodiment thereof.

[0020] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the node legend recognition method of the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is an abstract schematic diagram of a pipeline node;

[0023] Figure 2 This is a schematic diagram of some node legends;

[0024] Figure 3 It is a schematic diagram of part of the pipeline network drawings constructed simultaneously by the water supply and drainage professionals;

[0025] Figure 4 This is a schematic diagram of a node legend that has been broken up;

[0026] Figure 5 This is a flowchart illustrating a node legend recognition method according to an embodiment of the present invention;

[0027] Figure 6 This is a flowchart illustrating another node legend recognition method according to an embodiment of the present invention;

[0028] Figure 7 This is a flowchart illustrating another node legend recognition method according to an embodiment of the present invention;

[0029] Figure 8 This is a schematic diagram of the target primitive set 1 according to an embodiment of the present invention;

[0030] Figure 9 This is a flowchart illustrating a method for identifying a node legend according to an embodiment of the present invention.

[0031] Figure 10 This is a schematic diagram of the geometric shape of a node diagram according to an embodiment of the present invention;

[0032] Figure 11 This is a flowchart illustrating a method for identifying a node legend according to an embodiment of the present invention.

[0033] Figure 12 This is a structural block diagram of a node legend recognition device according to an embodiment of the present invention;

[0034] Figure 13 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] In pipeline network drawings, the intersection of pipes can be called a node, and the graphic describing the node can be called a node legend. Each node legend can include at least one graphic element. An abstract schematic diagram of a pipeline network drawing is shown below. Figure 1 As shown, nodes can be wells, valves, supports, etc.; pipes can be drainage pipes, water supply pipes, gas pipes, heating pipes, etc.; node labels are used to describe the attribute information of the node, such as node number, drawing set number, etc.; pipe labels are used to describe the attribute information of the pipe, such as pipe diameter, pipe length, etc. Manually identifying node symbols from pipeline network drawings often presents the following difficulties: Difficulty 1: A single pipeline network drawing contains a large number of node symbols, generally ranging from dozens to hundreds. Difficulty 2: The types of node symbols are numerous and cannot be exhaustively listed; a single pipeline network drawing may contain a large number of different node symbols. Figure 2 The diagram shows a partial node legend. Figure 2 Each dashed box in the diagram corresponds to a node legend. Challenge 3: Multiple piping specialties can be represented on the same piping drawing, for example... Figure 3 The diagram shows partial pipe network drawings constructed concurrently by the water supply and drainage specialties. However, the shapes and types of node symbols from different pipe network specialties are difficult to distinguish and identify. Challenge 4: When drawing pipe network drawings, drafters may break down block-referenced elements, that is, break down a single element into several individual elements, such as... Figure 4 As shown, the dashed box represents a broken node legend, while the solid box represents a node legend composed of a single element. The broken elements in the dashed box are easily mistaken for similar node legends in the solid box, leading to multiple identifications and errors. Challenge 5: When single and combined legends share some similarities, different identification orders can result in different identification results. Challenge 6: When node legends are missed, pipes may be mistakenly merged. Challenge 7: For multiple combined node legends, due to the overall similarity of the graphics and the difference only in the length of the connecting lines between elements, they are easily misidentified as multiple elements.

[0037] In other words, manually identifying node symbols from pipeline network drawings is not only inefficient but also prone to errors. To address this technical problem, several node symbol identification methods have been proposed in related technologies. One method uses template matching, meaning the node symbol to be identified can only be recognized if it perfectly matches the template; otherwise, it cannot be identified. Furthermore, manual selection of the node symbols is required, and when there are many, multiple manual selections are necessary, leading to omissions or incorrect selections. Therefore, this method still fails to solve difficulties 2 to 7 mentioned above. Another identification method in related technologies uses recognition algorithms. However, this method also requires manual selection of the node symbols to be identified, and when there are many, multiple manual selections are necessary, leading to omissions or incorrect selections. Therefore, this method also fails to solve difficulties 4 to 7 mentioned above. Another identification method in related technologies utilizes machine learning. This method requires a large number of pipeline network drawings as a training set, making it complex to implement. Furthermore, due to the numerous and exhaustive types of node legends, it is difficult to distinguish between combined legends and single legends. Therefore, machine learning-trained identification models often have low accuracy and cannot solve the aforementioned difficulties 3 to 5, as well as difficulty 7. Based on this, the present invention provides a node legend identification method. This method involves acquiring candidate elements to be identified in the pipeline network drawings; obtaining a set of target elements corresponding to the target legend type from the candidate elements; identifying target node legends in the target element set according to the identification rules corresponding to the target legend type; and determining the feature information of the target node legend based on the target legend type and the geometric lines of the target node legend. Thus, the identification process of node legends and their feature information does not require manual intervention, achieving automated identification of node legends, greatly improving the identification efficiency, and avoiding identification errors caused by human factors.

[0038] According to an embodiment of the present invention, a node legend recognition method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0039] This embodiment provides a node legend recognition method, which can be used in computer devices such as mobile phones, tablets, desktop computers, laptops, and servers. Figure 5 This is a flowchart of a node legend recognition method according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps:

[0040] Step S101: Obtain the candidate graphic elements to be identified in the pipeline network drawing.

[0041] Considering that pipeline network drawings often include various types of graphic elements, such as topographic line elements, elevation elements, block reference elements, combined elements, and fragmented elements, and that topographic line elements and elevation elements are not part of the node legend, this invention first filters out elements in the pipeline network drawing that do not belong to the node legend in order to improve the recognition efficiency of the node legend, thereby obtaining candidate graphic elements to be identified in the pipeline network drawing.

[0042] Step S102: Obtain the set of target primitives corresponding to the target legend type from the candidate primitives.

[0043] The target legend type includes at least one of the following: a shattered type, a block reference type, and a combined type. To improve the recognition efficiency of node legends of the target legend type, instead of determining whether each candidate element is a node legend of the target legend type, in one or more embodiments of the present invention, after obtaining candidate elements, the target element set corresponding to the target legend type is first obtained from the candidate elements.

[0044] Step S103: Identify the target node legend in the target primitive set according to the recognition rules corresponding to the target legend type.

[0045] Considering that different types of node legends are presented differently in pipeline drawings, in order to improve the recognition efficiency of target node legends of target legend types, in one or more embodiments of the present invention, different recognition rules are set in advance for different legend types, and the target node legends in the corresponding target element set are identified according to the recognition rules corresponding to the target legend type.

[0046] Step S104: Determine the feature information of the target node legend based on the target legend type and the geometric lines of the target node legend.

[0047] The feature information may include legend type, geometric features, style information, etc. For the specific methods of determining the feature information, please refer to the relevant description below.

[0048] The node legend recognition method provided in this embodiment obtains candidate elements to be identified in the pipeline network drawing; from the candidate elements, it obtains a set of target elements corresponding to the target legend type; and according to the recognition rules corresponding to the target legend type, it identifies the target node legend in the target element set; and based on the target legend type and the geometric lines of the target node legend, it determines the feature information of the target node legend. Therefore, in the process of identifying node legends and their feature information, no manual intervention is required, which not only achieves automated identification of node legends, greatly improving the identification efficiency, but also avoids identification errors caused by human factors.

[0049] Considering that pipeline network drawings often include elements that do not belong to the node legend, in order to improve the efficiency of node legend recognition, some embodiments can preprocess the pipeline network drawing to be recognized after acquisition to filter out elements that do not belong to the node legend. Specifically, this embodiment provides a node legend recognition method that can be used on computer devices such as mobile phones, tablets, desktop computers, laptops, servers, etc. Figure 6 This is a flowchart of a node legend recognition method according to an embodiment of the present invention, such as... Figure 6 As shown, the process includes the following steps:

[0050] Step S201: Obtain the candidate graphic elements to be identified in the pipeline network drawing.

[0051] In some implementations, step S201 may include steps S2011 to S2013:

[0052] Step S2011: Obtain the original graphic elements and graphic element information of each original graphic element in the pipeline network drawing.

[0053] In some implementations, the pipeline network drawing can be created by a drafter using drawing tools, and the element information of each original element in the drawing can be edited during the drawing process. When node legend recognition is required, the pipeline network drawing to be recognized can be loaded using a drawing tool, and the original elements and their element information can be obtained from the drawing tool. In some implementations, the drawing tool can be AutoCAD software, and the element information can include element name, element type, element number, layer name of the layer containing the element, color, text, a first attribute indicating whether the element is visible, and the first size of the element's minimum bounding box. The minimum bounding box of the element can be an axis-aligned rectangular bounding box (AABB), and the first size can include length and width.

[0054] Step S2012: For each graphic element information, determine whether the graphic element information includes target information that meets preset conditions.

[0055] In some implementations, at least one of the following operations may be performed for each element information:

[0056] Determine whether the first attribute in the primitive information indicates that the corresponding original primitive is not visible; if so, determine that the primitive information includes target information that meets the preset conditions.

[0057] Determine whether the length included in the first dimension of the primitive information is greater than the length threshold. If so, determine that the primitive information includes target information that meets the preset conditions.

[0058] Determine whether the width included in the first dimension of the graphic element information is greater than the length and width threshold. If so, determine that the graphic element information includes target information that meets the preset conditions.

[0059] Determine whether the layer name in the element information is in the first blacklist. If so, determine that the element information includes target information that meets the preset conditions. The first blacklist includes layer names that do not belong to the node legend.

[0060] Determine whether the graphic element type in the graphic element information is text. If so, determine whether the graphic element information includes target information that meets the preset conditions.

[0061] If it is determined that the element type in the element information is a block reference type and the block name is in the second blacklist, then it is determined that the element information includes target information that meets the preset conditions. The second blacklist includes block names that do not belong to the node legend.

[0062] If it is determined that the primitive type in the primitive information is a block reference type, and the number of sub-primaries in the original primitive corresponding to the primitive information is greater than the first quantity threshold, then it is determined that the primitive information includes target information that meets the preset conditions.

[0063] If it is determined that the type of the graphic element in the graphic element information is a block reference type, and the original graphic element corresponding to the graphic element information includes text graphic elements, then it is determined that the graphic element information includes target information that meets the preset conditions.

[0064] If it is determined that the type of the graphic element in the graphic element information is a combination type, and the number of sub-graphic elements in the original graphic element corresponding to the graphic element information is greater than the second quantity threshold, then it is determined that the graphic element information includes target information that meets the preset conditions.

[0065] If it is determined that the graphic element type in the graphic element information is a combination type, and the original graphic element corresponding to the graphic element information includes text graphic elements, then it is determined that the graphic element information includes target information that meets the preset conditions.

[0066] Step S2013: If not, then the original graphic element corresponding to the graphic element information is determined as the candidate graphic element to be identified.

[0067] Step S202: Obtain the set of target primitives corresponding to the target legend type from the candidate primitives.

[0068] Step S203: Identify the target node legend in the target primitive set according to the recognition rules corresponding to the target legend type.

[0069] Step S204: Determine the feature information of the target node legend based on the target legend type and the geometric lines of the target node legend.

[0070] For details of steps S202 to S204, please refer to [link / reference]. Figure 5 Steps S102 to S104 of the illustrated embodiment will not be described again here.

[0071] Therefore, by acquiring the graphic information of each original graphic element in the pipeline network drawing and determining whether the graphic information includes target information that meets preset conditions, original graphic elements that do not belong to the node legend can be filtered out, narrowing the recognition range. Then, based on the candidate graphic elements after narrowing the recognition range, recognition processing can be performed, which can greatly improve the recognition efficiency and recognition accuracy.

[0072] In some implementations, the target legend type includes a shattered type. Correspondingly, this embodiment provides a node legend recognition method that can be used in computer devices such as mobile phones, tablets, desktop computers, laptops, and servers. Figure 7 This is a flowchart of a node legend recognition method according to an embodiment of the present invention, such as... Figure 7 As shown, the process includes the following steps:

[0073] Step S301: Obtain the candidate graphic elements to be identified in the pipeline network drawing.

[0074] For details on the implementation of step S301, please refer to [link / reference]. Figure 6 Step S201 of the illustrated embodiment will not be described again here.

[0075] Step S302: Obtain the set of target primitives corresponding to the type of being broken up from the candidate primitives.

[0076] In some implementations, step S302 may include steps S3021 and S3022:

[0077] Step S3021: Obtain the element number of each candidate element.

[0078] During the process of drawing pipeline network diagrams using drawing tools, the drawing tools automatically generate element numbers for each original graphic element. These element numbers are sequential, for example, element numbers are 1, 2, 3…N, etc. After obtaining candidate graphic elements, the element number of the corresponding candidate graphic element can be retrieved from the element information of each candidate graphic element.

[0079] Step S3022: Based on the continuity of the graphic element number, divide each candidate graphic element into at least one set of target graphic elements corresponding to the broken type.

[0080] Specifically, based on the continuity of the primitive numbers, the candidate primitives corresponding to consecutive primitive numbers are divided into a target primitive set, resulting in at least one target primitive set.

[0081] As an example, if the candidate graphic elements are numbered 1, 2, 3, 4, 6, 7, 10, 11, and 12, then the candidate graphic elements with graphic element numbers 1, 2, 3, and 4 are assigned to target graphic element set 1, the candidate graphic elements with graphic element numbers 6 and 7 are assigned to target graphic element set 2, and the candidate graphic elements with graphic element numbers 10, 11, and 12 are assigned to target graphic element set 3.

[0082] Step S303: Identify the target node legend in the target primitive set according to the identification rules corresponding to the scattered type.

[0083] In some implementations, step S303 may include steps S3031 to S3034:

[0084] Step S3031: For each target set of graphic elements, determine the positional relationship between two candidate graphic elements with consecutive graphic element numbers in the target set of graphic elements;

[0085] Specifically, for each target set of graphic elements, determine whether the minimum bounding boxes of two candidate graphic elements with consecutive graphic element numbers in the target set intersect; if yes, determine that the positional relationship between the two candidate graphic elements is that the graphic ranges intersect; if no, determine that the positional relationship between the two candidate graphic elements is that the graphic ranges do not intersect.

[0086] Step S3032: Determine whether there is a target positional relationship among the positional relationships that represents the non-intersecting graphic ranges of two candidate primitives;

[0087] Step S3033: If yes, then divide the target primitive set into multiple first subsets according to the target position relationship, and determine each candidate primitive in the first subset as a whole as the target node legend, and execute step S304.

[0088] Specifically, when there is a target positional relationship in the target set of graphic elements, the two candidate graphic elements corresponding to the target positional relationship are divided into different first subsets so that the graphic ranges of two candidate graphic elements with consecutive graphic element numbers in each first subset intersect, thereby obtaining multiple first subsets.

[0089] Continuing with the example above, the schematic diagrams of each candidate primitive in the target primitive set 1 are as follows: Figure 8As shown, the positional relationship between candidate elements corresponding to element number 1 and element number 2 is determined to be that their graphic ranges intersect; the positional relationship between candidate elements corresponding to element number 2 and element number 3 is that their graphic ranges do not intersect; and the positional relationship between candidate elements corresponding to element number 3 and element number 4 is that their graphic ranges intersect. The target positional relationship is the positional relationship between candidate elements corresponding to element number 2 and element number 3. Therefore, candidate elements corresponding to element number 1 and element number 2 are divided into a first subset 1, and candidate elements corresponding to element number 3 and element number 4 are divided into a first subset 2. The candidate elements corresponding to element number 1 and element number 2 in the first subset 1 are treated as a whole and determined as node legend 1; the candidate elements corresponding to element number 3 and element number 4 in the first subset 2 are treated as a whole and determined as node legend 2.

[0090] Step S3034: If not, then each candidate element in the target element set is determined as a whole as the target node legend.

[0091] When there is no target relationship in the positional relationship corresponding to the target primitive set, if the graphic ranges of two candidate primitives with consecutive primitive numbers in the target primitive set intersect, then each candidate primitive in the target primitive set is determined as a whole as a node legend.

[0092] Step S304: Determine the feature information of the target node legend based on the type of scattering and the geometric lines of the target node legend.

[0093] Therefore, based on the continuity of primitive numbering and the intersection between the graphic ranges corresponding to the minimum bounding boxes of candidate primitives, the automatic and accurate identification of scattered type node legends is realized.

[0094] Considering that in practical applications, pipeline network drawings may include not only the aforementioned fragmented node legends, but also block reference type node legends and combined type node legends, in some embodiments, the target legend type may also include at least one of reference type and combined type. Correspondingly, this embodiment provides a node legend recognition method that can be used on the aforementioned mobile terminals, such as mobile phones, tablets, desktop computers, laptops, servers, etc. Figure 9 This is a flowchart of a node legend recognition method according to an embodiment of the present invention, such as... Figure 9 As shown, the process includes the following steps:

[0095] Step S401: Obtain the candidate graphic elements to be identified in the pipeline network drawing;

[0096] For details on the implementation of step S401, please refer to the relevant description above. Repeated details will not be repeated here.

[0097] Step S402: Filter the candidate primitives of the broken type from the candidate primitives to obtain the candidate primitives to be processed;

[0098] When the target legend type includes a broken type and at least one of a block reference type and a combined type, in order to avoid multiple identifications of candidate primitives of the broken type, which would cause identification errors, in some embodiments of the present invention, after obtaining the candidate primitives, the node legends of the target type are first identified, and then the candidate primitives of the broken type are filtered from the candidate primitives to obtain the candidate primitives to be processed. Other types of node legends are then identified based on the candidate primitives to be processed. The identification process of the node legends of the target type can be found in the relevant description above, and will not be repeated here.

[0099] Step S403: Determine the element type of the candidate element to be processed based on its element information.

[0100] As mentioned earlier, after the drawing tool loads the pipeline network drawing, the element information of each element can be obtained from the drawing tool, and candidate elements can be obtained based on the element information. Accordingly, in step S403, for each candidate element to be processed, the element type of the candidate element to be processed is obtained from the element information of the candidate element to be processed.

[0101] Step S404: If the target legend type includes a block reference type, then the candidate graphics elements whose type is block reference type are assigned to the target graphics element set corresponding to the block reference type.

[0102] Candidate primitives whose primitive type is block reference type can also be called block reference primitives.

[0103] Step S405: Identify the target node legend in the target primitive set corresponding to the block reference type according to the identification rules corresponding to the block reference type.

[0104] In some implementations, step S405 may include steps S4051 to S4054:

[0105] Step S4051: Based on the preset correspondence between block definition primitives and block reference primitives, divide the target primitive set corresponding to the block reference type into at least one second subset.

[0106] In this model, there is a one-to-many correspondence between block definition primitives and block reference primitives. Block definition primitives are composed of basic entity types and can be considered as templates. Block reference primitives are obtained by transforming block definition primitives and can be considered as instances of the templates. For example, a block definition primitive is an arrow pointing in a first direction, and its corresponding block reference primitives can include arrows specifying a second direction, arrows pointing in a third direction, etc. The second direction can be a direction rotated 45 degrees clockwise from the reference of the first direction, and the third direction can be a direction rotated 90 degrees clockwise from the reference of the first direction. In step S4051, each candidate primitive to be processed in the target primitive set corresponding to the block reference type can be determined as a block reference primitive. Based on the correspondence between block definition primitives and block reference primitives, for each block reference primitive in the target primitive set corresponding to the block reference type, the target block definition primitive corresponding to that block reference primitive is determined, and that block reference primitive is assigned to the second subset corresponding to the target block definition primitive. That is, each candidate primitive to be processed in each second subset corresponds to the same block definition primitive.

[0107] Step S4052: For each second subset, select target candidate primitives from the second subset.

[0108] In some implementations, a candidate primitive to be processed (i.e., a block reference primitive) can be randomly selected from the second subset and determined as the target candidate primitive. Alternatively, the first candidate primitive to be processed assigned to the second subset can be determined as the target candidate primitive according to the order in which they were assigned.

[0109] Step S4053: Determine whether the target candidate primitive is the target node legend.

[0110] Although the style of node legends is complex, it usually conforms to... Figure 10 The diagram shows geometric shapes such as circles, rectangles, X-shapes, and irregular shapes. Based on this, in order to quickly identify target node legends of block reference types, in some embodiments, a preset geometric shape can be used. Accordingly, step S4053 may include: obtaining a first geometric shape from the geometric lines of the target candidate element; determining whether the first geometric shape contains a preset geometric shape; if so, determining that the target candidate element is a target node legend.

[0111] Determining whether the first geometric figure contains a preset geometric figure may include: determining whether the first geometric figure includes a figure with a closed region; if it includes a figure with a closed region, then the first geometric figure is determined to contain a preset geometric figure; if it does not include a figure with a closed region, then the first geometric figure includes an X-shape; if it includes an X-shape, then the first geometric figure is determined to contain a preset geometric figure; if it does not include an X-shape, then the first geometric figure does not contain a preset geometric figure.

[0112] Step S4054: If so, then each candidate primitive to be processed in the second subset is determined as the target node legend.

[0113] As an example, if the second subset includes candidate primitives to be processed with primitive number 20 and candidate primitives to be processed with primitive number 24, then candidate primitives to be processed with primitive number 20 will be identified as target node legends of the quick reference type, and candidate primitives to be processed with primitive number 24 will be identified as another target node legend of the quick reference type.

[0114] Therefore, by grouping all candidate primitives (i.e., block reference primitives) corresponding to the same defined primitive into the same second subset, and only determining whether the target candidate primitives in the second subset are target node legends of the fast reference type, it is possible to determine whether each candidate primitive in the second subset is a target node legend of the fast reference type. This eliminates the need to individually determine whether each candidate primitive in the target primitive set corresponding to the fast reference type is a target node legend of the fast reference type. Thus, the recognition efficiency is greatly improved.

[0115] Step S406: If the target legend type includes a combination type, then the candidate graphics elements whose type is a combination type are assigned to the target graphics element set corresponding to the combination type.

[0116] Step S407: Identify the target node legend in the target primitive set corresponding to the combination type according to the identification rules corresponding to the combination type.

[0117] In some implementations, step S407 may include steps S4071 to S4073:

[0118] Step S4071: For each candidate graphic element to be processed in the target graphic element set corresponding to the combination type, obtain the second geometric shape from the geometric lines of the candidate graphic element to be processed;

[0119] Step S4072: Determine whether the second geometric figure contains a preset geometric figure;

[0120] Specifically, it is determined whether the second geometric figure includes a figure with a closed region. If it includes a figure with a closed region, it is determined that the second geometric figure contains a preset geometric figure. If it does not include a figure with a closed region, it is determined whether the second geometric figure includes an X-shape. If it includes an X-shape, it is determined that the second geometric figure contains a preset geometric figure. If it does not include an X-shape, it is determined that the second geometric figure does not contain a preset geometric figure.

[0121] Step S4073: If yes, then determine that the candidate primitive is the target node legend.

[0122] Therefore, based on the geometric type of the node legend, the automatic recognition of combined node legends is realized, which not only improves the recognition efficiency, but also avoids the problems that are prone to errors in human recognition.

[0123] Step S408: Determine the feature information of the target node legend based on the target legend type and the geometric lines of the target node legend.

[0124] The method for determining feature information can be found in the relevant description below.

[0125] This embodiment provides a node legend recognition method, which can be used in the aforementioned mobile terminals, such as mobile phones, tablets, desktop computers, laptops, servers, etc. Figure 11 This is a flowchart of a node legend recognition method according to an embodiment of the present invention, such as... Figure 11 As shown, the process includes the following steps:

[0126] Step S501: Obtain the candidate graphic elements to be identified in the pipeline network drawing.

[0127] Step S502: Obtain the set of target primitives corresponding to the target legend type from the candidate primitives.

[0128] Step S503: Identify the target node legend in the target primitive set according to the recognition rules corresponding to the target legend type.

[0129] The specific implementation methods of steps S501 to S503 can be found in the relevant descriptions above, and the repeated parts will not be repeated here.

[0130] Step S504: Determine the feature information of the target node legend based on the target legend type and the geometric lines of the target node legend.

[0131] In some implementations, step S504 includes steps S5041 to S5043:

[0132] Step S5041: For each target node legend, determine the geometric features of the target node legend based on the geometric lines of the target node legend.

[0133] In some implementations, step S5041 may include: for each target node legend, determining the geometric shape of the outer contour of the target node legend based on the geometric lines of the target node legend; determining the geometric type of the node legend based on the geometric shape; determining the ring type of the target node legend based on the number of rings included in the geometric shape; and determining the geometric type and ring type as the geometric features of the target node legend.

[0134] Specifically, for each target node legend, based on the geometric lines of the target node legend, determine whether its outer contour is a closed region. If it is a closed region and its geometric shape is circular, then the geometric type of the target node legend is circular; if it is a closed region and its geometric shape is rectangular, then the geometric type of the target node legend is rectangular; if it is a closed region and its geometric shape is neither circular nor rectangular, then the geometric type of the target node legend is irregular; if there is no closed region and it is X-shaped, then the geometric type of the target node legend is X-shaped. Furthermore, when the outer contour of the target node legend is a closed region, determine the number of rings included in the geometric shape of the closed region; if the number of rings is 1, then the ring type of the target node legend is single-ring; if the number of rings is greater than 1, then the ring type of the target node legend is multi-ring. When the outer contour of the target node legend is not a closed region, determine that the number of rings included in the geometric shape of the target node legend is zero, and the ring type of the target node legend is acyclic.

[0135] Step S5042: Obtain style information from the element information of the candidate elements corresponding to the target node legend.

[0136] Specifically, the layer name and color information are obtained from the element information of the candidate elements corresponding to the target node legend, and the layer name and color information are determined as the style information of the target node legend.

[0137] Step S5043: Determine the geometric features, style information, and target legend type corresponding to the target node legend as the feature information of the target node legend.

[0138] The node legend recognition method provided in this embodiment achieves accurate and automated recognition of the feature information of the target node legend based on the geometric shape of the outer contour of the target node legend and the primitive information of the candidate primitives corresponding to the target node legend, without human intervention.

[0139] This embodiment also provides a node legend recognition device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0140] This embodiment provides a node legend recognition device, such as Figure 12 As shown, it includes:

[0141] The first acquisition module 601 is used to acquire candidate elements belonging to the node legend in the pipeline network drawing.

[0142] The second acquisition module 602 is used to acquire the target primitive set corresponding to the target legend type from the candidate primitives.

[0143] The identification module 603 is used to identify the node legends in the target primitive set according to the identification rules corresponding to the target legend type.

[0144] The determination module 604 is used to determine the feature information of the node legend based on the target legend type and the geometric lines of the node legend.

[0145] In some optional implementations, the first acquisition module 601 includes:

[0146] The first acquisition unit is used to acquire each original graphic element in the pipeline network drawing and the graphic element information of the original graphic elements;

[0147] The first determining unit is used to determine, for each of the graphic element information, whether the graphic element information includes target information that meets preset conditions; if not, the original graphic element corresponding to the graphic element information is determined as a candidate graphic element to be identified.

[0148] In some optional implementations, the target legend type includes a shattered type, and the second acquisition module 602 includes:

[0149] The second acquisition unit is used to acquire the element number of the candidate element;

[0150] A partitioning unit is used to partition each of the candidate graphic elements according to the continuity of the graphic element numbers to obtain at least one set of the target graphic elements.

[0151] Accordingly, the identification module 603 includes:

[0152] The first identification unit is configured to, for each target set of graphic elements, determine the positional relationship between two candidate graphic elements with consecutive graphic element numbers in the target set of graphic elements; and,

[0153] Determine whether, among the positional relationships, there exists a target positional relationship that indicates that the graphic ranges of the two candidate primitives do not intersect;

[0154] If so, the target primitive set is divided into multiple first subsets according to the target positional relationship, and each candidate primitive in the first subset is determined as a whole as the target node legend; the graphic ranges of two candidate primitives with consecutive primitive numbers in the first subset intersect.

[0155] If not, then all candidate primitives in the target primitive set will be determined as a whole as the target node legend.

[0156] In some optional implementations, the second acquisition module 602 further includes:

[0157] A filtering unit is used to filter the candidate primitives of the shattered type from the candidate primitives to obtain candidate primitives to be processed;

[0158] The second determining unit is used to determine the element type of the candidate element to be processed based on the element information of the candidate element to be processed.

[0159] The attribution unit is used to, if the target legend type includes a block reference type, assign the candidate graphic element of the block reference type to the target graphic element set corresponding to the block reference type; if the target legend type includes a combination type, assign the candidate graphic element of the combination type to the target graphic element set corresponding to the combination type.

[0160] Correspondingly, the recognition module 603 also includes:

[0161] The second identification unit is configured to, when the target legend type includes a block reference type, divide the target legend set into at least one second subset according to a preset correspondence between block definition legends and block reference legends; the candidate legends in the second subset correspond to the same block definition legends; and, for each second subset, select target candidate legends from the second subset; determine whether the target candidate legend is a target node legend; if so, determine each candidate legend in the second subset as a target node legend.

[0162] The third identification unit is used to, when the target legend type includes a combination type, for each candidate legend in the target legend set, obtain a second geometric shape from the geometric lines of the candidate legend; determine whether the second geometric shape contains a preset geometric shape; if so, determine that the candidate legend is a target node legend.

[0163] In some optional implementations, the second identification unit includes:

[0164] A sub-unit is used to obtain a first geometric shape from the geometric lines of the target candidate primitive;

[0165] The first determining subunit is used to determine whether the first geometric figure contains a preset geometric figure; if so, the target candidate graphic element is determined to be a target node legend.

[0166] In some alternative implementations, the determining module 604 includes:

[0167] The third determining unit is used to determine the geometric features of each target node legend based on the geometric lines of the target node legend;

[0168] The third acquisition unit is used to acquire style information from the element information of the candidate elements corresponding to the target node legend;

[0169] The feature information includes the geometric features, the style information, and the target legend type corresponding to the target node legend.

[0170] In some optional implementations, the third determining unit includes:

[0171] The second determining subunit is used to determine the geometric shape of the outer contour of the target node legend based on the geometric lines of the target node legend;

[0172] The third determining subunit is used to determine the geometric type of the target node legend based on the geometric shape;

[0173] The fourth determining subunit is used to determine the ring type of the target node legend based on the number of ring targets included in the geometry.

[0174] The geometric features of the target node legend include the geometric type and the ring type.

[0175] In some optional implementations, the third acquisition unit is specifically used for:

[0176] Obtain the layer name and color information from the element information of the candidate elements corresponding to the node legend;

[0177] The style information includes the layer name and the color information.

[0178] The node legend recognition device in this embodiment acquires candidate elements to be recognized in the pipeline network drawing; obtains a set of target elements corresponding to the target legend type from the candidate elements; and identifies the target node legend in the target element set according to the recognition rules corresponding to the target legend type. Based on the target legend type and the geometric lines of the target node legend, it determines the feature information of the target node legend. Therefore, no manual intervention is required in the recognition process of node legends and their feature information, which not only achieves automated recognition of node legends and greatly improves the recognition efficiency, but also avoids recognition errors caused by human factors.

[0179] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0180] In this embodiment, the node legend recognition device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0181] This invention also provides a computer device having the above-described features. Figure 12 The node legend recognition device shown.

[0182] Please see Figure 13 , Figure 13 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 13 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 13 Take a processor 10 as an example.

[0183] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0184] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0185] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0186] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0187] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 13 Taking the example of a connection between China and Israel via a bus.

[0188] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0189] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0190] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0191] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for node legend recognition, characterized in that, The method includes: Obtain candidate graphic elements to be identified in the pipeline network drawing; Obtaining a target element set corresponding to a target legend type from the candidate elements includes: the target legend type includes a broken type; obtaining the element number of the candidate elements; and dividing each candidate element according to the continuity of the element number to obtain at least one target element set corresponding to a broken type. Based on the recognition rules corresponding to the target legend type, identify the target node legend in the target primitive set, including: Based on the recognition rules corresponding to the scattered type, identify the target node legend in the target primitive set; Filter the candidate primitives of the scattered type from the candidate primitives to obtain the candidate primitives to be processed; determine the primitive type of the candidate primitives to be processed based on the primitive information of the candidate primitives to be processed. If the target legend type includes a block reference type, then the candidate graph elements whose graph element type is a block reference type are assigned to the target graph element set corresponding to the block reference type; according to the identification rules corresponding to the block reference type, the target node legend in the target graph element set corresponding to the block reference type is identified; If the target legend type includes a combination type, then the candidate legends to be processed with the legend type being a combination type are assigned to the target legend set corresponding to the combination type; and the target node legends in the target legend set corresponding to the combination type are identified according to the identification rules corresponding to the combination type. Based on the target legend type and the geometric lines of the target node legend, the feature information of the target node legend is determined.

2. The method according to claim 1, characterized in that, The process of acquiring candidate graphic elements to be identified in the pipeline network drawing includes: Obtain each original graphic element and its graphic element information from the pipeline network drawing; For each of the graphic element information, determine whether the graphic element information includes target information that meets preset conditions; If not, the original graphic element corresponding to the graphic element information is determined as the candidate graphic element to be identified.

3. The method according to claim 1, characterized in that, The step of identifying target node legends in the target primitive set according to the recognition rules corresponding to the target legend type includes: For each target set of graphic elements, determine the positional relationship between two candidate graphic elements with consecutive graphic element numbers in the target set; Determine whether, among the positional relationships, there exists a target positional relationship that indicates that the graphic ranges of the two candidate primitives do not intersect; If so, the target primitive set is divided into multiple first subsets according to the target positional relationship, and each candidate primitive in the first subset is determined as a whole as the target node legend; the graphic ranges of two candidate primitives with consecutive primitive numbers in the first subset intersect. If not, then all candidate primitives in the target primitive set will be determined as a whole as the target node legend.

4. The method according to claim 1, characterized in that, The step of identifying target node legends in the target primitive set corresponding to the block reference type according to the identification rules includes: Based on the preset correspondence between block-defined primitives and block-reference primitives, the target primitive set is divided into at least one second subset; the candidate primitives in the second subset correspond to the same block-defined primitive. For each of the second subsets, select target candidate primitives from the second subset; Determine whether the target candidate primitive is a target node legend; If so, then each of the candidate primitives in the second subset will be determined as the target node legend.

5. The method according to claim 4, characterized in that, Determining whether the target candidate primitive is a target node legend includes: Obtain the first geometric shape from the geometric lines of the target candidate primitive; Determine whether the first geometric figure contains a preset geometric figure; If so, then the target candidate primitive is determined to be a target node legend.

6. The method according to claim 1, characterized in that, The step of identifying the target node legend in the target primitive set corresponding to the combination type according to the identification rule corresponding to the combination type includes: For each candidate graphic element in the target graphic element set, a second geometric shape is obtained from the geometric lines of the candidate graphic element; Determine whether the second geometric figure contains a preset geometric figure; If so, then the candidate primitive is determined to be the target node legend.

7. The method according to claim 1, characterized in that, The step of determining the feature information of the target node legend based on the target legend type and the geometric lines of the target node legend includes: For each target node legend, the geometric features of the target node legend are determined based on the geometric lines of the target node legend; Style information is obtained from the element information of the candidate elements corresponding to the target node legend; The feature information includes the geometric features, the style information, and the target legend type corresponding to the target node legend.

8. The method according to claim 7, characterized in that, Determining the geometric features of the target node legend based on its geometric lines includes: Based on the geometric lines of the target node legend, determine the geometric shape of the outer contour of the target node legend; Based on the geometric shape, determine the geometric type of the target node legend; The ring type of the target node legend is determined based on the number of rings included in the geometry; The geometric features of the target node legend include the geometric type and the ring type.

9. The method according to claim 7, characterized in that, The step of obtaining style information from the element information of the candidate elements corresponding to the target node legend includes: Obtain the layer name and color information from the element information of the candidate elements corresponding to the target node legend; The style information includes the layer name and the color information.

10. A node legend recognition device, characterized in that, The device includes: The first acquisition module is used to acquire candidate graphic elements to be identified in the pipeline network drawings; The second acquisition module is used to acquire a set of target elements corresponding to the target legend type from the candidate elements, including: the target legend type includes a broken type; the second acquisition unit is used to acquire the element number of the candidate elements; the division unit is used to divide each candidate element according to the continuity of the element number to obtain at least one set of target elements corresponding to the broken type. The identification module is used to identify node legends in the target primitive set according to the identification rules corresponding to the target legend type, including: Based on the recognition rules corresponding to the scattered type, identify the target node legend in the target primitive set; A filtering unit is used to filter the candidate primitives of the scattered type from the candidate primitives to obtain the candidate primitives to be processed; a second determining unit is used to determine the primitive type of the candidate primitives to be processed based on the primitive information of the candidate primitives to be processed. The attribution unit is used to, if the target legend type includes a block reference type, assign the candidate grapheme whose grapheme type is a block reference type to the target grapheme set corresponding to the block reference type; the identification module is also used to identify the target node legend in the target grapheme set corresponding to the block reference type according to the identification rules corresponding to the block reference type. The attribution unit is further configured to, if the target legend type includes a combination type, assign the candidate grapheme whose grapheme type is a combination type to the target grapheme set corresponding to the combination type; the identification module is further configured to, according to the identification rules corresponding to the combination type, identify the target node legend in the target grapheme set corresponding to the combination type. The determination module is used to determine the feature information of the target node legend based on the target legend type and the geometric lines of the target node legend.

11. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the node legend recognition method according to any one of claims 1 to 9 by executing the computer instructions.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the node legend recognition method according to any one of claims 1 to 9.

13. A computer program product, characterized in that, It includes computer instructions for causing a computer to perform the node legend recognition method according to any one of claims 1 to 9.

Images