Data processing methods, apparatus, data processing equipment and storage media

Abstract

This application relates to the field of data processing technology and provides a data processing method, apparatus, device, and storage medium, comprising: acquiring data to be processed, the data to be processed including data for indicating a graphic, and data including data for indicating the weights of the graphic; performing a transformation process on the data to be processed to obtain transformed data, the transformation process being used to convert the data to be processed into machine-recognizable data containing key geometric information and weights of the graphic; performing machine recognition on the transformed data to obtain target data; and performing computational processing based on the target data to obtain a data processing result. This application can improve data processing efficiency.

Description

Technical Field

[0001] This application belongs to the field of data processing technology, and in particular relates to data processing methods, apparatus, equipment and computer-readable storage media. Background Art

[0002] In data processing scenarios such as image feature processing and map analysis, it is often necessary to perform calculations on graphics (i.e., data to be processed) containing different weights. Before processing, the data to be processed usually needs to be converted into machine-readable data so that the machine can identify the correct data and perform subsequent calculations.

[0003] Currently, when converting data to be processed into machine-readable data, the process typically involves dividing the data into squares of the same size, segmenting each graphic within the data, adjusting the square size so that each graphic's corresponding square only contains the weight of that graphic, and then representing the data using a matrix with dimensions equal to the number of squares. When the graphics have uneven boundaries, the data is often converted into a high-dimensional matrix, requiring high-dimensional matrix operations during processing, resulting in low computational efficiency. Summary of the Invention

[0004] This application provides a data processing method, apparatus, equipment, and storage medium, which can improve data processing efficiency.

[0005] In a first aspect, embodiments of this application provide a data processing method, including:

[0006] Acquire data to be processed, the data to be processed including data for indicating a graph, and data for indicating the weights of the graph;

[0007] The data to be processed is transformed to obtain transformed data. The transformation process is used to convert the data to be processed into machine-recognizable data containing key geometric information and weights of the graphic.

[0008] The converted data is subjected to machine recognition to obtain the target data;

[0009] The target data is processed to obtain the data processing result.

[0010] Secondly, embodiments of this application provide a data processing apparatus, including:

[0011] A data acquisition module is used to acquire data to be processed, the data to be processed including data for indicating a graph, and data for indicating the weights of the graph;

[0012] A conversion module is used to convert the data to be processed to obtain converted data. The conversion process is used to convert the data to be processed into machine-recognizable data containing key geometric information and weights of the graphic.

[0013] The identification module is used to perform machine recognition on the converted data to obtain target data;

[0014] The calculation module is used to perform calculations based on the target data to obtain the data processing results.

[0015] Thirdly, embodiments of this application provide a data processing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the data processing method described in the first aspect.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the data processing method described in the first aspect.

[0017] Fifthly, embodiments of this application provide a computer program product that, when run on a data processing device, causes the data processing device to execute the data processing method described in the first aspect.

[0018] The beneficial effects of the embodiments in this application compared with the prior art are:

[0019] In this embodiment, after obtaining the data to be processed, which reflects one or more graphics and their weights, it is transformed to obtain transformed data. The transformation process can convert the data to be processed into machine-recognizable data containing key geometric information and weights of the graphics. This allows the transformed data to be quickly and easily recognized by the machine when computation is required, obtaining target data including key geometric information and weights of each graphic. Then, computation is performed based on the target data. That is, computation is performed directly based on the key geometric information and weights of each graphic. Compared to converting the data to be processed into a high-dimensional matrix for machine recognition and computation, high-dimensional matrix operations are not required, which can significantly improve data processing efficiency and reduce the computational power requirements of the machine. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0021] Figure 1This is a schematic flowchart of a data processing method provided in an embodiment of this application;

[0022] Figure 2 This is a schematic diagram of data to be processed provided in an embodiment of this application;

[0023] Figure 3 This is a schematic diagram of data to be processed provided in an embodiment of this application;

[0024] Figure 4 This is a schematic diagram of data to be processed provided in an embodiment of this application;

[0025] Figure 5 This is a schematic diagram of a graphic division provided in an embodiment of this application;

[0026] Figure 6 This is a schematic diagram of the structure of the data processing apparatus provided in the embodiments of this application;

[0027] Figure 7 This is a schematic diagram of the structure of the data processing device provided in the embodiments of this application. DETAILED DESCRIPTION

[0028] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0029] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0030] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0031] Furthermore, in the description of this application and the appended claims, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized.

[0033] Example 1:

[0034] Figure 1 A flowchart illustrating a data processing method provided by an embodiment of the present invention is shown below, and is described in detail below:

[0035] Step S101: Obtain data to be processed, which includes data for indicating the graph and data for indicating the weights of the graph.

[0036] The data to be processed may be image data containing graphics and their corresponding weights, text data describing graphics and their weights, or combined data describing graphics and their weights through both images and text. This application does not impose specific limitations on these aspects.

[0037] For example, such as Figure 2 As shown, figures 1, 2, and 3 are directly represented in the image, and the weight (denoted as G) corresponding to each figure is described in the image. Figure 2 As shown, assuming the background weight is 1 by default, the weight of graph 1 can be set to 1.5, the weight of graph 2 can be set to 3.6+0.5i, and the weight of graph 3 can be set to -0.8i.

[0038] It is understood that the information reflected by the weights is determined based on the data to be processed. For example, suppose the data to be processed is a map containing various cities in province A, where each graphic corresponds to a region in each city, and the weight of the graphic reflects the population density of the city. In other embodiments, the size of the graphic is related to the weight. For example, suppose the data to be processed is a map containing various cities in province A, where each graphic corresponds to a region in each city, and the weight of the graphic reflects the area of ​​the region corresponding to the city.

[0039] It is important to note that the weights of a graph can be fixed numerical values ​​or analytical expressions containing variables. For example, when the weights of a graph contain analytical expressions of variables, the weights of that graph can be determined based on analytical expressions that include coordinate positions. In this case, the weights corresponding to different positions within the same graph are usually different.

[0040] Step S102: The data to be processed is transformed to obtain transformed data. The transformation process is used to convert the data to be processed into machine-recognizable data containing key geometric information and weights of the above-mentioned graphics.

[0041] To avoid the need for high-dimensional matrix calculations in subsequent processing, in this embodiment, when converting the data to be processed into machine-recognizable data, the key geometric information of each graphic in the data to be processed can be determined first. Then, the data to be processed is converted into machine-recognizable data containing the key geometric information and weights of the graphics, resulting in the converted data. Since the geometric information of the graphics can reflect information such as the shape and size of the graphics, the converted data can indicate the graphics through the key geometric information of the graphics, without needing to indicate the graphics through a matrix, thereby reducing the size of the converted data, i.e., reducing the amount of data that the machine needs to recognize in subsequent processing.

[0042] In some embodiments, the transformed data can represent the key geometric information and weights of each graphic through a preset structure (such as an array). For example, assuming that the key geometric information of graphic A includes coordinates 1, 2, and 3, and the weight is -8, then the key geometric information and weights of graphic A can be represented as: {(coordinates 1, 2, 3), (-8)}.

[0043] In this embodiment, the data to be processed is converted into transformed data containing key geometric information and weights of the graphics, without having to represent the data to be processed through a high-dimensional matrix. This reduces the size of the resulting transformed data, thereby reducing the amount of data that the subsequent machine needs to recognize, and also avoids high-dimensional matrix operations during subsequent processing.

[0044] Step S103: Perform machine recognition on the above-mentioned converted data to obtain the target data.

[0045] Specifically, to facilitate machine computation based on user data processing needs, the obtained conversion data can be pre-identified by the machine, and the identified data can be used as the target data, or the identified data can be processed accordingly to obtain the target data.

[0046] Optionally, the target data may include key geometric information of each graphic and its corresponding weights.

[0047] It is understood that the aforementioned machine can be a smart device such as a smartphone, tablet, or computer, or it can be a machine learning model. This application does not impose specific limitations on this.

[0048] Step S104: Perform calculations based on the target data to obtain the data processing results.

[0049] Specifically, after the target data is identified, corresponding calculations can be performed based on the target data according to the user's data processing needs to obtain the data processing results required by the user.

[0050] For example, suppose a user's data processing needs include: calculating the transportation convenience of transportation hub B in province A based on the population density of each city in province A. Then, according to the user's data processing needs, the data to be processed can include the population density of each city in province A. After the machine identifies the transformed data corresponding to the data to be processed and obtains the target data, it can perform corresponding calculations based on the target data to obtain the data processing result required by the user: the transportation convenience of transportation hub B in province A.

[0051] In this embodiment, after acquiring the data to be processed, a transformation process is performed to convert the data into machine-recognizable transformed data containing key geometric information and weights of the graphics. That is, the obtained transformed data indicates the graphics through their key geometric information, without needing to represent the graphics and their weights using matrices or similar forms. This reduces the size of the transformed data, thus reducing the amount of data the machine needs to recognize. Furthermore, when the machine performs calculations on the identified target data, it no longer needs to perform matrix-based operations, avoiding high-dimensional matrix operations. This significantly improves data processing efficiency while reducing the computational demands on the machine.

[0052] In some embodiments, step S103 includes:

[0053] A1. For each of the above-mentioned graphics in the data to be processed, determine the graphics type to which the graphics belong, and obtain the target graphics type.

[0054] A2. Based on each of the above target graphic types, determine the corresponding key geometric information of the above graphics.

[0055] A3. Determine the transformation data based on the key geometric information and weights of each of the above-mentioned figures.

[0056] Specifically, since different types of graphics have different geometric features, the key geometric information used to indicate the graphics is usually different as well. Therefore, in order to better indicate each graphic in the data to be processed, when converting the data to be processed, we can first determine the graphic type to which each graphic in the data to be processed belongs, and obtain the target graphic type corresponding to each image.

[0057] After determining the target graphic type corresponding to each graphic, the key geometric information corresponding to each graphic can be determined by combining the geometric features corresponding to the graphic type and the target graphic type corresponding to the graphic.

[0058] After determining the key geometric information corresponding to each graphic, the transformed data is obtained based on the key geometric information and weights corresponding to each graphic.

[0059] For example, suppose the data to be processed includes the following three figures: figure 1, figure 2 and figure 3, and suppose that the figure type of figure 1 (target figure type 1) is triangle, the figure type of figure 2 (target figure type 2) is trapezoid, and the figure type of figure 3 (target figure type 3) is circle.

[0060] When determining the key geometric information corresponding to these three figures, figures 1 and 2 are both figures that can be formed by connecting vertices. Therefore, for figure 1, based on target figure type 1 (triangle), the position information of the three vertices of figure 1 can be determined as its corresponding key geometric information; for figure 2, based on target figure type 2 (trapezoidal shape), the position information of the four vertices of figure 2 can be determined as its corresponding key geometric information; and for figure 3, based on target figure type 3 (circle), the center point and radius of figure 3 can be determined as the key geometric information corresponding to figure 3.

[0061] In this embodiment of the application, when determining the key geometric information of a graphic, the different geometric features of different types of graphics are fully considered. The key geometric information of the graphic is determined according to the type of graphic to which the graphic belongs, so that the obtained key geometric information can better indicate the graphic and ensure the accuracy of the obtained conversion data.

[0062] In some embodiments, the data to be processed includes image data and / or text data, and prior to step A1, the process further includes:

[0063] When the data to be processed includes the image data, each of the aforementioned graphics in the image data is determined based on an image recognition algorithm.

[0064] When the data to be processed includes the text data, semantic analysis is performed on the text data to determine each of the aforementioned graphics in the text data.

[0065] In order to better transform the data to be processed, after obtaining the data, we first determine all the graphics that describe the data so that we can directly transform each graphic during the subsequent transformation process, thereby improving the data processing efficiency.

[0066] Since different data to be processed may be described by different descriptive methods for their graphs and weights, and the same data to be processed may be described by multiple descriptive methods for their graphs and weights, in order to accurately determine all the graphs described by the data to be processed, the corresponding method can be used to determine the graphs described by the descriptive methods used by the data to be processed.

[0067] When the data to be processed includes image data, an image recognition algorithm can be used to identify and process the image data in the data to determine all the graphics described by the image data, so that each graphic in the image data can be converted and processed in the subsequent process.

[0068] When the data to be processed includes text data, semantic analysis can be performed on the text data to identify all the graphics described by the text data based on the semantic information of the text. Since semantic analysis can combine contextual information to analyze the meaning of text data, it can reduce interference caused by the diversity of text data due to factors such as different users and different expression methods. Therefore, it can better identify the entities (i.e., graphics) in the text data and the weights associated with the graphics.

[0069] For example, suppose there is a text data in the data to be processed: a circle with a center at (0,0) and a radius of 5 and a weight of 2. If semantic recognition is performed on this text data, then based on the semantic analysis of this text data, it can be determined that the graphic in the text data includes a circle. The key geometric information of the circle may include: the center coordinates (0,0), the radius 5, and the weight of the circle 2.

[0070] It is worth noting that when determining the graphic described by the text data through semantic analysis, the positional information of each graphic can also be determined. This allows for direct calculation based on the positional information of each graphic when needed, without the need for further semantic analysis and transformation, thus improving data processing efficiency.

[0071] It is understandable that when both image data and text data are used to describe the graphics and their corresponding weights in the data to be processed, that is, when the data to be processed includes both image data and text data, the graphics described by the image data can be determined based on image recognition algorithms, and the graphics described by the text data can be determined based on semantic analysis. Then, all the graphics described by the data to be processed can be determined based on the graphics described by the image data and the graphics described by the text data.

[0072] It should be noted that in some embodiments, there may be data to be processed that describes graphics through image data and the weights of graphics through text data. In this case, the graphics in the image data can be determined first through image recognition algorithms, and the features of the graphics corresponding to each weight in the text data (such as shape, position, and size) can be determined based on semantic analysis. Then, by combining the features of the graphics corresponding to the weights described in the text data, each weight can be matched with each graphic in the determined image data to obtain all the graphics described in the data to be processed and the weights corresponding to the graphics.

[0073] In this embodiment of the application, for image data in the data to be processed, the graphics in the image data are identified based on the image recognition algorithm. For text data in the data to be processed, the graphics in the text data are determined through semantic analysis. This ensures that when different description methods are used to describe the graphics and the corresponding weights of the graphics, all the graphics described by the data to be processed can be determined well, thus ensuring the accuracy of the converted data and the accuracy of the data processing results.

[0074] In some embodiments, step A1 above, when determining the graphic type to which the graphic belongs and obtaining the target graphic type, includes:

[0075] Determine whether the above graphic matches any one of the multiple preset graphic types.

[0076] If the above-mentioned graphic does not match any of the above-mentioned preset graphic types, the above-mentioned graphic is divided into multiple sub-graphics based on each of the above-mentioned preset graphic types.

[0077] The target graphic type corresponding to each of the above-mentioned sub-graphics is determined based on the preset graphic type corresponding to each of the above-mentioned sub-graphics.

[0078] Specifically, in order to improve the efficiency of the conversion process while reducing its complexity, multiple graphic types (i.e., preset graphic types) can be pre-set. When determining the graphic type to which each graphic belongs, the graphic type to which the graphic belongs is determined based on the preset graphic types.

[0079] When determining the graphic type of a graphic, first check if the graphic matches any of the preset graphic types. If the graphic matches any preset graphic type, it indicates that the graphic type to which the graphic belongs is the matched preset graphic type, and the target graphic type corresponding to the graphic can be determined based on the matched preset graphic type.

[0080] If a graphic does not match any of the preset graphic types, it indicates that the graphic may be a complex graphic. In this case, the graphic can be divided based on the preset graphic types to obtain multiple sub-graphics corresponding to the graphic.

[0081] Correspondingly, when determining the target graphic type corresponding to the graphic, the target graphic type corresponding to the graphic is determined according to the preset graphic type matched by each sub-graphic.

[0082] Through the above processing, complex graphics are transformed into graphics composed of multiple simple sub-graphics. This allows for the simple and quick determination of the graphic type of the graphic based on the graphic type of each sub-graphic, reducing the complexity of the conversion process.

[0083] It is understandable that in the final result, each sub-graphic is matched with one of the multiple preset graphic types, and multiple sub-graphics may be matched with the same preset graphic type.

[0084] For example, such as Figure 3 As shown, suppose there is a graphic A in the data to be processed, and suppose there are the following 5 preset image types: triangle, quadrilateral, polygon, circle and parabola; if it is determined that graphic A does not match any of the preset graphic types, then graphic A can be divided based on triangle and parabola among the 5 preset graphic types to obtain sub-graphic 1, sub-graphic 2 and sub-graphic 3.

[0085] If sub-figure 1 and sub-figure 2 match triangles and sub-figure 3 matches a parabola, then based on the preset figure types matched by sub-figure 1, sub-figure 2 and sub-figure 3, the target figure type corresponding to the figure is determined to include triangles and parabolas.

[0086] In this embodiment, multiple preset graphic types are pre-defined. When determining the target graphic type corresponding to a graphic, the graphic is matched with each preset graphic type to determine the target graphic type. Simultaneously, when the graphic does not match any of the preset graphic types, the graphic is divided into multiple sub-graphics based on each preset graphic type. That is, the graphic is converted into a combination of multiple sub-graphics that match the preset graphic types, achieving a simplified representation of complex graphics and reducing the complexity of subsequent conversion processing.

[0087] In some embodiments, when the data to be processed includes image data, step A2 above includes:

[0088] For each of the above-mentioned graphics in the above image data, determine whether the target graphic type corresponding to the above-mentioned graphic conforms to the fitting type, which includes circular and curved types.

[0089] When the target graphic type corresponding to the above graphic conforms to the above fitting type, key point extraction and fitting processing are performed on the above graphic to obtain the analytical expression corresponding to the above graphic, and the key geometric information of the above graphic is determined according to the parameters of the above analytical expression.

[0090] When the target graphic type corresponding to the above graphic does not conform to the above fitting type, the above graphic is subjected to key point extraction processing to obtain the position information of at least one key point, and the above key geometric information of the above graphic is determined based on the position information of the above key point.

[0091] Since the geometric features of different graphic types usually differ, meaning that the key geometric information that needs to be determined for different graphic types is usually different, different methods are used to determine the key geometric information of each graphic in the image data in order to better determine the key geometric information of each graphic type.

[0092] Since the graphs corresponding to circular and curved shapes are usually quite complex, in order to better describe these graphs, we first determine whether the target graph type matches the fitting type. This fitting type includes both circular and curved shapes.

[0093] It is important to note that "circular" and "curved" can be generalizations of various graphic types. For example, graphic types that conform to the "circular" category can include circles and ellipses, while "curved" can include parabolic and hyperbolic shapes.

[0094] It can be understood that when the target graphic type corresponding to the graphic matches any graphic type contained in the circle-like type, or when the target graphic type corresponding to the graphic matches any graphic type contained in the curve type, the target graphic type is determined to conform to the fitting type.

[0095] When the target graphic type matches the fitting type, it indicates that the graphic is complex. In this case, key point extraction and fitting processes can be performed. Key point extraction first identifies the key points of the graphic, and then, combined with these key points, the analytical expression corresponding to the graphic is obtained through fitting. This analytical expression indicates information such as the size and position of the graphic.

[0096] When the target graphic type corresponding to the graphic does not match the fitting type, it indicates that the graphic is not a complex graphic and does not need to be fitted. In this case, the key point extraction process can be performed directly on the graphic to determine the key points of the graphic. Then, the key geometric information of the graphic can be determined based on the position information of the determined key points.

[0097] In some embodiments, when performing key point extraction processing on a shape that conforms to the fitting type, points on the boundary line of the shape can be extracted as key points corresponding to the shape. Then, based on the extracted key points located on the boundary line of the shape, an analytical expression of the boundary line of the shape is obtained by fitting using methods such as spline interpolation. At the same time, the center point of the shape is extracted as another key point of the shape, so as to determine the position information of the shape based on the center point. After obtaining the analytical expression of the boundary line of the shape and the position information of the center point, the key geometric information of the shape can be determined based on the analytical expression and the position information of the center point.

[0098] In this embodiment, the graphic is judged to be a complex graphic based on whether the target graphic type matches the fitting type, so that the graphic can be processed in a corresponding way to obtain the key geometric information corresponding to the graphic, thereby improving data processing efficiency. At the same time, the key geometric information of complex graphics can be extracted well, ensuring the accuracy of the obtained conversion data.

[0099] In some embodiments, step S104 includes:

[0100] B1. Determine the operation type corresponding to the data processing requirements to obtain the target operation type. The above data processing requirements are used to indicate the data processing results required by the user. The above operation types include independent operations and related operations.

[0101] B21. When the target operation type is the independent operation, based on the data processing requirements, independent operation processing is performed according to the key geometric information and weights of each of the above-mentioned graphics to obtain the first operation result corresponding to each of the above-mentioned graphics, and the data processing result is determined according to each of the above-mentioned first operation results.

[0102] The aforementioned data processing requirements are used to indicate the data processing results required by the user, that is, the data processing results to be obtained after performing corresponding calculations on the data to be processed. It can be understood that after determining the data processing requirements and the data to be processed, the required calculations can be determined based on the data processing requirements.

[0103] Specifically, since the data to be processed, i.e., the target data, may include multiple graphics, and some calculations need to consider the positional relationships between the graphics, in order to ensure the accuracy of the data processing results, before performing calculations based on the transformed target data, the required calculation type is determined according to the user's data processing needs, thus obtaining the target calculation type. The calculations include independent calculations and associative calculations.

[0104] If the determined target operation type is independent operation, it means that when performing operation on the target data based on the user's data processing needs, there is no need to consider the relative positional relationship between the graphics. In this case, based on the user's data processing needs, independent operation can be performed directly according to the key geometric information of the graphics in the target data and the corresponding weights. That is, for each graphic, operation is performed based on the key geometric information of the graphic and the corresponding weights to obtain the first operation result corresponding to the graphic.

[0105] After obtaining the first calculation results for each graphic, the final data processing result can be determined based on each first calculation result.

[0106] For example, suppose a user's data processing needs include calculating the transportation convenience of transportation hub B built in province A. Then, maps of all cities in province A can be obtained as the data to be processed, with the weights corresponding to each city's map including its population density. Assume province A has N (greater than 1) cities, meaning the data to be processed contains N maps.

[0107] After determining the key geometric information of each graphic based on its target graphic type in the data to be processed, and determining the transformation data based on the key geometric information and weights of each graphic, the machine identifies the transformation data to obtain target data containing the key geometric information and weights of each graphic. In this embodiment, the key geometric information of each graphic includes the parameters of the graphic's analytical expression.

[0108] Since the level of transportation convenience (the data processing result required by the user) is determined based on the location of transportation hub B and is independent of the relative positional relationship between various cities, when performing corresponding calculations on the target data, the results are processed independently based on the key geometric information and weights of each graphic.

[0109] Since a city typically occupies a large area, the level of transportation convenience varies across different locations. Therefore, when performing independent calculations based on the key geometric information and weights corresponding to each graphic, the analytical expression corresponding to the boundary of the graphic can be determined based on the key geometric information of each graphic. Then, integration is performed based on the analytical expression and weights corresponding to the graphic to obtain the first calculation result corresponding to each graphic. The first calculation result corresponding to the graphic is the level of transportation convenience of the city.

[0110] It is understandable that when performing integration operations based on the analytical expression and weights corresponding to the graph, the integration operations are usually performed differently for different graph types.

[0111] For example, for a polygonal shape, the integral operation can be performed on each side separately, and then the first operation result corresponding to the shape can be obtained based on the integral operation results of each side.

[0112] For example, for a circular figure, its analytical expression can be expressed as x = Rcosθ + x0, y = Rsinθ + y0, where R is the radius of the circle, (x0, y0) are the center coordinates of the circle, and θ varies with different boundary points, ranging from 0 to 2π. Substituting this analytical expression into the calculation formula corresponding to the traffic convenience level and performing integration, we obtain the first calculation result corresponding to the circle.

[0113] After determining the traffic convenience level of each city (i.e., the first calculation result), the traffic convenience level of the entire province A can be determined based on the traffic convenience level of each city (i.e., the data processing result).

[0114] B22. When the target operation type is the above-mentioned correlation operation, based on the above-mentioned data processing requirements and the relative positional relationship between each of the above-mentioned graphics, correlation operation processing is performed according to the above-mentioned key geometric information and weights of each of the above-mentioned graphics to obtain one or more second operation results, and the above-mentioned data processing result is determined according to each of the above-mentioned second operation results.

[0115] If the determined target operation type is an association operation, it means that when processing the target data based on the user's data processing needs, the relative positional relationship between the graphics needs to be considered. In this case, the association operation can be performed based on the user's data processing needs and the relative positional relationship between each graphic, according to the key geometric information of each graphic and the corresponding weight. That is, the operation is performed based on the relationship between the positions of each graphic, the key geometric information of each graphic and the weight corresponding to the graphic, to obtain the data processing result corresponding to the target data (i.e. the data to be processed).

[0116] It should be noted that when the target operation type is determined to be an association operation, the positions of some graphics may not be related to the positions of other graphics. In this case, graphics whose positions are not related to other graphics can be processed independently to obtain their corresponding first operation results. For graphics whose positions are related to the positions of other graphics, association operation is performed according to the relationship between the graphics to obtain one or more second operation results. Finally, the final data processing result is determined based on each first operation result and second operation result.

[0117] For example, suppose a user's data processing needs include: analyzing the relationship between the average tree height and latitude of forests in area A; and assuming that based on the distribution of four forests (Forest 1 to Forest 4) in area A and the average tree height of each forest, the user wants to obtain data such as... Figure 4 The data to be processed is shown below; the data to be processed includes graph 1, graph 2, graph 3 and graph 4 (corresponding to forest 1 to forest 4 respectively), wherein the weight of each graph is the average height of the trees in its corresponding forest.

[0118] Based on the user's data processing needs, it is necessary to calculate the relationship between the average height of trees in a forest and latitude. Different forests may be distributed at the same latitude, which means that it may be necessary to analyze the relationship between the average height of trees and a certain latitude based on the average height of trees in multiple forests. Therefore, when performing calculations based on the target data corresponding to the data to be processed, the relative positional relationship between the graphics must be considered, and correlation calculations must be performed.

[0119] Based on the target data corresponding to the data to be processed, namely the key geometric information and weights of the graphics, it can be seen that graphics 1 and 4 are independently distributed, and their positions are not related to the positions of other graphics (in this example, the relationship includes having the same position information, that is, having the same latitude). That is, graphics 1 and other graphics are distributed at different latitudes, and graphics 4 and other graphics are also distributed at different latitudes; while some graphics of graphics 2 and some graphics of graphics 3 are distributed at the same latitude (20° to 30°), that is, the positions of graphics 2 and graphics 3 are related.

[0120] Therefore, when processing the target data, the relationship between the average height of trees in forest 1 and latitude can be calculated based on the key geometric information and weights of graph 1; the relationship between the average height of trees in forest 4 and latitude can be calculated based on the key geometric information and weights of graph 4; and for graphs 2 and 3, the corresponding parts of the same latitude (target latitude) and their weights can be determined based on the key geometric information and weights of graphs 2 and 3, thereby calculating the relationship between the target latitude and the average height of trees. That is, based on the average height of trees in the parts of forest 2 and forest 3 that have a positional relationship, the relationship between the average height of trees in that part and the corresponding latitude can be calculated.

[0121] In this embodiment, the relative positional relationship between graphics needs to be considered when performing calculations based on the user's data processing requirements, and the target calculation type is determined. Then, based on the obtained target calculation type, independent calculation processing or associated calculation processing is selected to ensure the accuracy of the obtained data processing results.

[0122] In some embodiments, step B22 above, when performing correlation calculations based on the data processing requirements and the relative positional relationships between the graphics, according to the key geometric information and weights of each graphic, to obtain one or more second calculation results, includes:

[0123] The first target graphic and the second target graphic are determined based on the relative positional relationship of the aforementioned graphics. The first target graphic includes the aforementioned graphics that are related in position, and the second target graphic includes the aforementioned graphics that are not related in position.

[0124] For each of the aforementioned first target graphics, the first target graphics are divided into multiple rectangles.

[0125] The calculations are performed on each of the aforementioned rectangles and their corresponding weights to obtain the second calculation result corresponding to the aforementioned rectangles. Similarly, the calculations are performed on each of the aforementioned second target graphics and their corresponding weights to obtain the second calculation result corresponding to the aforementioned second target graphics.

[0126] When the calculations required by the user's data processing needs need to be combined with the position, the graphs whose positions are not related to the positions of other graphs usually do not affect the calculations of other graphs. Therefore, in order to improve the efficiency of data processing while ensuring the accuracy of the data processing results, before the calculation, the graphs whose positions are related are determined according to the relative positional relationship between the graphs to obtain the first target graph, and the second target graph is determined according to the graphs whose positions are not related.

[0127] In some embodiments, a first target graphic can be determined based on graphics that have the same location information, and a second target graphic can be determined based on graphics that do not have the same location information.

[0128] After determining each first target graphic and the second target graphic, the first target graphic can be divided into multiple rectangles based on the relative positional relationship between them, thus obtaining each rectangle corresponding to the first target graphic.

[0129] Optionally, when performing rectangular division on each first target graphic, the rectangles to be divided can be determined based on the key geometric information and geometric features of the first target graphic. That is, the position and size of the rectangles are not limited, but the division is based on the geometric features of the first target graphic to facilitate subsequent calculations.

[0130] It is important to note that when dividing each first target graphic, the division should also take into account the relationship between the positions of each first target graphic, so that subsequent calculations can be performed in a better manner based on their positional relationships.

[0131] During the calculation, for the first target graphic, the calculation can be performed based on its corresponding rectangles and weights to obtain the corresponding second calculation result; for the second target graphic, the calculation can be performed directly based on the key geometric information and weights of the second target graphic to obtain the corresponding second calculation result.

[0132] After obtaining the results of each second operation, the final data processing result can be determined based on the results of each second operation.

[0133] In some embodiments, before performing the transformation process, each first target graphic can be determined, divided into multiple rectangles, and additional transformation data for each first target graphic can be determined based on the key geometric information of each rectangle and the weight corresponding to the first target graphic. Subsequently, during computational processing, if correlation operations are required, the target data corresponding to each additional transformation data can be directly obtained for computation, eliminating the need for rectangular partitioning every time a correlation operation is required, thus improving data processing efficiency.

[0134] For example, such as Figure 5 As shown, assuming the data to be processed is image data, this image data includes the following three graphics: A, B, and C. Graphic A and Graphic B share the same height (y4-y6), and Graphic C and Graphic B share the same height (y2-y3). That is, the positions of Graphic A and Graphic B are related, and the positions of Graphic C and Graphic B are also related. Correspondingly, the first target graphics include Graphic A, Graphic B, and Graphic C.

[0135] When performing rectangular division, based on the positional relationship between graphic C and graphic B, graphic A is divided into multiple rectangles based on its geometric characteristics, specifically the portion of graphic A with a height between y6 and y7.

[0136] Based on the geometric features of figures A and B, and the height y4-y6, the portion of the figure with height y5-y6 is divided into two rectangles, and the portion of the figure with height y4-y5 is divided into two rectangles.

[0137] The portion of figure B with a height of y3-y4 is divided into two rectangles based on its geometric characteristics.

[0138] Based on the geometric features of figures B and C, as well as the height y2-y3, the portion of the figure with height y2-y3 is divided into a rectangle;

[0139] For the portion of figure C with height y0-y2, based on the geometric characteristics of figure C, it is divided into seven rectangles; after the above division process, the following is obtained: Figure 5 The diagram shown.

[0140] In this embodiment, when correlation operations are required, the graphics with positional relationships are determined based on their relative positions. These correlated graphics are then divided into multiple rectangles. This allows for better computation by combining the positional relationships using rectangles of a uniform type, improving computational efficiency and reducing computational complexity. For graphics without positional relationships, the corresponding operations are performed directly without the need for rectangular division, thus reducing unnecessary processing steps.

[0141] It should be noted that currently, the data to be processed is usually converted into matrix form, meaning that the target data recognized by the machine is usually a matrix. When integration is required, the implementation of matrix integration is relatively cumbersome and requires high computing power. However, in this embodiment, the data to be processed is converted into transformed data containing key geometric information and weights of the graphic through the above-mentioned conversion process. This ensures that the target data recognized by the machine contains key geometric information and weights of the graphic. When integration is required, the analytical expression of the graphic boundary can be determined based on the key geometric information of the graphic. This allows the integration operation of the graphic to be converted into the line integral operation of the graphic boundary. This reduces computational complexity, avoids high-dimensional matrix operations, improves data processing efficiency, and reduces the computing power requirements of the machine.

[0142] Furthermore, during the conversion process, when determining the key geometric information of a graphic, the target graphic type corresponding to the graphic can be determined based on a preset graphic type. For complex graphics that cannot be directly determined based on a preset graphic type, they can be divided into multiple sub-graphics through a partitioning process. The target graphic type corresponding to the graphic can then be determined based on the graphic type of the sub-graphics, thus simplifying complex graphics. At the same time, the complex operations on complex graphics in subsequent processing can be converted into simple operations based on sub-graphics, thereby reducing computational complexity.

[0143] In some embodiments, the weights of a graphic can be represented as a location-dependent distribution function. When integration is required based on the identified target data, the integration result corresponding to the graphic can be represented in the following form:

[0144]

[0145] Where G() is the weight fraction function of the graph, G(x,y) represents the weight of the position with coordinates (x,y) in the graph; H(x,y) is the analytical function determined according to the user's data processing requirements; S represents the region to be integrated, that is, the region corresponding to the graph; Indicates the boundary of the figure. This represents the vector differential operator.

[0146] Correspondingly, the integral result of the target data can be expressed in the following form:

[0147]

[0148] Where Q(x,y) represents an analytic function constructed based on the integral result of the graph. represents the curl of G(x,y)H(x,y); q represents the number of graphs contained in the target data. This represents the boundary of the i-th figure.

[0149] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0150] Example 2:

[0151] Corresponding to the data processing method described in the above embodiments, Figure 6 A structural block diagram of a data processing apparatus provided in an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0152] Reference Figure 6 The device includes: a data acquisition module 61, a conversion module 62, a recognition module 63, and a processing module 64. Among them,

[0153] The data acquisition module 61 is used to acquire data to be processed, which includes data for indicating a graph, and data for indicating the weights of the graph.

[0154] The conversion module 62 is used to convert the above-mentioned data to be processed to obtain converted data. The conversion process is used to convert the above-mentioned data to be processed into machine-recognizable data containing the key geometric information and weights of the above-mentioned graphics.

[0155] The recognition module 63 is used to perform machine recognition on the above-mentioned converted data to obtain the target data.

[0156] The calculation module 64 is used to perform calculations based on the above target data to obtain the data processing results.

[0157] In this embodiment, after acquiring the data to be processed, a transformation process is performed to convert the data into machine-recognizable transformed data containing key geometric information and weights of the graphics. That is, the obtained transformed data indicates the graphics through their key geometric information, without needing to represent the graphics and their weights using matrices or similar forms. This reduces the size of the transformed data, thus reducing the amount of data the machine needs to recognize. Furthermore, when the machine performs calculations on the identified target data, it no longer needs to perform matrix-based operations, avoiding high-dimensional matrix operations. This significantly improves data processing efficiency while reducing the computational demands on the machine.

[0158] In some embodiments, the conversion module 62 includes:

[0159] The target graphic type determination unit is used to determine the graphic type of each graphic in the above-mentioned data to be processed, and to obtain the target graphic type.

[0160] The key geometric information determination unit is used to determine the key geometric information of the corresponding graphic based on each of the above target graphic types.

[0161] The transformation data determination unit is used to determine the transformation data based on the key geometric information and weights of each of the above-mentioned graphics.

[0162] In some embodiments, the conversion module 62 further includes:

[0163] The matching unit is used to determine whether the above graphic matches any one of the multiple preset graphic types.

[0164] A division unit is used to divide the above-mentioned graphic into multiple sub-graphics based on each of the above-mentioned preset graphic types when the above-mentioned graphic does not match any of the above-mentioned preset graphic types.

[0165] The target graphic type determination unit is used to determine the target graphic type corresponding to the above graphic based on the preset graphic type corresponding to each of the above sub-graphics.

[0166] In some embodiments, the data processing apparatus further includes:

[0167] An image recognition module is used to determine each of the aforementioned graphics in the image data based on an image recognition algorithm when the data to be processed includes the aforementioned image data.

[0168] The text recognition module is used to perform semantic analysis on the text data when the data to be processed includes the text data, and to determine each of the graphics in the text data.

[0169] In some embodiments, the data processing apparatus further includes:

[0170] The judgment module is used to determine whether the target graphic type corresponding to each graphic in the above image data conforms to the fitting type, which includes circular and curved types.

[0171] The fitting module is used to perform key point extraction and fitting processing on the above-mentioned graphic when the target graphic type corresponding to the above-mentioned graphic meets the above-mentioned fitting type, to obtain the analytical expression corresponding to the above-mentioned graphic, and to determine the above-mentioned key geometric information of the above-mentioned graphic based on the parameters of the above-mentioned analytical expression.

[0172] The key point extraction module is used to perform key point extraction processing on the above-mentioned graphic when the target graphic type corresponding to the above-mentioned graphic does not conform to the above-mentioned fitting type, to obtain the position information of at least one key point, and to determine the above-mentioned key geometric information of the above-mentioned graphic based on the position information of the above-mentioned key point.

[0173] In some embodiments, the above-mentioned calculation module 64 includes:

[0174] The target operation type determination unit is used to determine the operation type corresponding to the data processing requirements and obtain the target operation type. The aforementioned data processing requirements are used to indicate the data processing results required by the user. The aforementioned operation type includes independent operations and related operations.

[0175] An independent computation unit is used to perform independent computation processing based on the key geometric information and weights of each of the above-mentioned graphics when the target computation type is the above-mentioned independent computation, based on the above-mentioned data processing requirements, to obtain the first computation result corresponding to each of the above-mentioned graphics, and to determine the above-mentioned data processing result based on each of the above-mentioned first computation results.

[0176] The association operation unit is used to perform association operation processing based on the data processing requirements and the relative positional relationship between the graphics, according to the key geometric information and weights of the graphics, to obtain one or more second operation results when the target operation type is the association operation, and to determine the data processing result based on the second operation results.

[0177] In some embodiments, the above-described arithmetic module 64 further includes:

[0178] The graphic classification unit is used to determine a first target graphic and a second target graphic based on the relative positional relationship of the aforementioned graphics. The first target graphic includes the aforementioned graphics that are related in position, and the second target graphic includes the aforementioned graphics that are not related in position.

[0179] The first target graphic division unit is used to divide each of the aforementioned first target graphics into multiple rectangles.

[0180] The calculation unit is used to perform calculations based on each of the rectangles and their corresponding weights to obtain a second calculation result corresponding to the rectangles, and to perform calculations based on each of the second target graphics and their corresponding weights to obtain a second calculation result corresponding to the second target graphics.

[0181] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0182] Example 3:

[0183] Figure 7 This is a schematic diagram of the structure of a data processing device provided in one embodiment of this application. Figure 7 As shown, the data processing device 7 of this embodiment includes: at least one processor 70 ( Figure 7 The diagram shows only one processor, a memory 71, and a computer program 72 stored in the memory 71 and executable on the at least one processor 70, which, when executed, performs the steps of any of the above-described method embodiments.

[0184] The data processing device 7 can be a desktop computer, laptop, handheld computer, or cloud server, etc. This data processing device may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will understand that... Figure 7 This is merely an example of the data processing device 7 and does not constitute a limitation on the data processing device 7. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0185] The processor 70 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0186] In some embodiments, the memory 71 may be an internal storage unit of the data processing device 7, such as a hard disk or memory of the data processing device 7. In other embodiments, the memory 71 may be an external storage device of the data processing device 7, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the data processing device 7. Furthermore, the memory 71 may include both internal and external storage units of the data processing device 7. The memory 71 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 71 can also be used to temporarily store data that has been output or will be output.

[0187] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0188] This application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above method embodiments.

[0189] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0190] This application provides a computer program product that, when run on a data processing device, enables the data processing device to implement the steps described in the various method embodiments above.

[0191] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographic device / data processing device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0192] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0193] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0194] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0195] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0196] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A data processing method, characterized in that, include: Acquire data to be processed, the data to be processed including data for indicating a graph, and data for indicating the weights of the graph; The data to be processed is transformed to obtain transformed data. The transformation process is used to convert the data to be processed into machine-recognizable data containing key geometric information and weights of the graphic. The key geometric information is used to indicate the graphic. The transformed data represents the key geometric information and weights of the graphic through a preset structure. The transformed data is subjected to machine recognition to obtain target data, which includes the key geometric information and weights of the graphic; The required computational processing is determined based on the user's data processing needs. The corresponding computational processing is performed based on the target data to obtain the data processing result. The data processing needs are used to indicate the data processing result required by the user. The step of transforming the data to be processed to obtain transformed data includes: For each graphic in the data to be processed, determine the graphic type to which the graphic belongs to obtain the target graphic type; The key geometric information of the corresponding graphic is determined based on each of the target graphic types; The transformation data is determined based on the key geometric information and weights of each of the aforementioned graphics; Determining the graphic type to which the graphic belongs, and obtaining the target graphic type, includes: Determine whether the graphic matches any one of the multiple preset graphic types; If the graphic does not match any of the preset graphic types, the graphic is divided into multiple sub-graphics based on each of the preset graphic types. The target graphic type corresponding to each graphic is determined based on the preset graphic type corresponding to each of the sub-graphics.

2. The data processing method as described in claim 1, characterized in that, The data to be processed includes image data and / or text data, and before determining the key geometric information of the corresponding graphics based on each of the target graphics types, the process further includes: When the data to be processed includes the image data, each of the graphics in the image data is determined based on an image recognition algorithm; When the data to be processed includes the text data, semantic analysis is performed on the text data to determine each of the graphics in the text data.

3. The data processing method as described in claim 2, characterized in that, When the data to be processed includes the image data, determining the key geometric information of the corresponding graphic based on each of the target graphic types includes: For each graphic in the image data, determine whether the target graphic type corresponding to the graphic conforms to the fitting type, wherein the fitting type includes circular and curved shapes; When the target graphic type corresponding to the graphic matches the fitting type, key point extraction and fitting processing are performed on the graphic to obtain the analytical expression corresponding to the graphic, and the key geometric information of the graphic is determined according to the parameters of the analytical expression. When the target graphic type corresponding to the graphic does not conform to the fitting type, key point extraction processing is performed on the graphic to obtain the position information of at least one key point, and the key geometric information of the graphic is determined based on the position information of the key point.

4. The data processing method according to any one of claims 1 to 3, characterized in that, The process of performing calculations based on the target data to obtain data processing results includes: Determine the operation type corresponding to the data processing requirements to obtain the target operation type, which includes independent operations and related operations; When the target operation type is the independent operation, based on the data processing requirements, independent operation processing is performed according to the key geometric information and weights of each of the graphics to obtain the first operation result corresponding to each of the graphics, and the data processing result is determined according to each of the first operation results; When the target operation type is the association operation, based on the data processing requirements and the relative positional relationship between the graphics, the association operation is performed according to the key geometric information and weight of each graphics to obtain one or more second operation results, and the data processing result is determined according to each second operation result.

5. The data processing method as described in claim 4, characterized in that, Based on the data processing requirements and the relative positional relationships between the various graphics, the association operation is performed according to the key geometric information and weights of each graphics to obtain one or more second operation results, including: A first target graphic and a second target graphic are determined based on the relative positional relationship of the various graphics. The first target graphic includes graphics that are related in position, and the second target graphic includes graphics that are not related in position. For each of the first target graphics, the first target graphics are divided into multiple rectangles; The second calculation result corresponding to each rectangle is obtained by performing calculations based on each rectangle and its corresponding weight. The second calculation result corresponding to each second target graphic is obtained by performing calculations based on each second target graphic and its corresponding weight.

6. A data processing apparatus, characterized in that, include: A data acquisition module is used to acquire data to be processed, the data to be processed including data for indicating a graph, and data for indicating the weights of the graph; A conversion module is used to convert the data to be processed to obtain converted data. The conversion process is used to convert the data to be processed into machine-recognizable data containing key geometric information and weights of the graphic. The key geometric information is used to indicate the graphic. The converted data represents the key geometric information and weights of the graphic through a preset structure. The recognition module is used to perform machine recognition on the transformed data to obtain target data, wherein the target data includes the key geometric information and weights of the graphic; The calculation module is used to determine the required calculations based on the user's data processing needs, perform corresponding calculations based on the target data, and obtain data processing results. The data processing needs are used to indicate the data processing results required by the user. The conversion module includes: The target graphic type determination unit is used to determine the graphic type of each graphic in the data to be processed, and obtain the target graphic type; A key geometric information determination unit is used to determine the key geometric information of the corresponding graphic based on each of the target graphic types; A conversion data determination unit is used to determine the conversion data based on the key geometric information and weights of each of the graphics. The conversion module also includes: A matching unit is used to determine whether the graphic matches any one of the multiple preset graphic types; A partitioning unit is used to divide the graphic into multiple sub-graphics based on each preset graphic type when the graphic does not match any of the preset graphic types. The target image type determination unit is used to determine the target image type corresponding to the image based on the preset image type corresponding to each of the sub-images.

7. A data processing apparatus, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

Images