Method, apparatus and photovoltaic system for determining a target device

Abstract

The application discloses a kind of method for determining target equipment, device and photovoltaic system. Among them, the method comprises: generating a preset template, wherein the preset template has a plurality of preset regions and first positioning marks, and the plurality of preset regions have one-to-one corresponding region numbers;Obtain the image of target page, wherein the image of target page has target graphics and second positioning marks, and the target graphics are used to provide the mark for identifying target equipment;The first distance parameter between target graphics and second positioning marks is obtained;According to the similarity between the first distance parameter and each preset distance parameter in the preset distance parameter set, determine the target region number from the plurality of region numbers;According to target region number, determine target equipment. The above method is convenient for quickly and accurately based on the target equipment identified, to segment the paper image with label for determining target equipment, to finally be merged into a complete target equipment layout panoramic view.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of photovoltaics, in particular, to a method and device for determining a target device and a photovoltaic system. BACKGROUND

[0002] At present, in a photovoltaic system, a device for optimizing the output power of a photovoltaic module, such as a photovoltaic power optimizer, can be provided, which is usually installed on the back of each panel to track and deeply optimize the maximum power output point of the panel, so as to solve the problem of output power reduction of the entire string caused by reasons such as shadow blocking of a single module, module failure, and module aging in a traditional photovoltaic system, so that the installation capacity and power output in a limited space are greatly improved.

[0003] Generally, after the above-mentioned optimization device is installed on the photovoltaic module, the optimization device can be marked, and the labels with the same mark are recorded on the paper, and the above steps are repeated until the photovoltaic modules requiring output power optimization in the power station are installed with the optimization device. Then, the multiple physical layout diagrams of the optimization device corresponding to the positions of the photovoltaic modules in the power station are obtained by taking pictures of the multiple papers, and the multiple physical layout diagrams are merged into a complete optimization device layout panorama, so that the operation and maintenance personnel can monitor and maintain the optimization device and the corresponding photovoltaic module according to the panorama.

[0004] However, due to the influence of external factors such as the resolution of the photographing device, the photographing angle, the environmental light (shadow or overexposure), and the size of the paper, it is difficult to quickly and accurately identify and segment the content in the physical layout diagram to finally merge all the physical layout diagrams into a complete layout panorama.

[0005] Therefore, after the installation of the optimization device in the photovoltaic power station is completed, how to accurately and quickly determine the target device so as to more efficiently identify and segment the content in the physical layout diagram to finally merge multiple physical layout diagrams into a complete optimization device layout panorama, so as to facilitate subsequent monitoring and finding the position of the module or the optimization device when needed and maintaining it as needed, thereby improving the operation and maintenance efficiency and convenience of the photovoltaic power station, is a technical problem to be solved by those skilled in the art. SUMMARY

[0006] The main purpose of the present application is to provide a method and device for determining a target device and a photovoltaic system, so as to solve the problem that in the prior art, due to the influence of external factors, it is difficult to quickly and accurately identify and segment the content in the physical layout diagram, thereby making it difficult to merge all the physical layout diagrams into a complete layout panorama.

[0007] In order to achieve the above object, according to one aspect of the present application, a method for determining a target device is provided, comprising: generating a preset template, wherein the preset template has a plurality of preset areas and a first positioning mark, the plurality of preset areas have one-to-one corresponding area numbers; acquiring an image of a target page, wherein the image of the target page has a target pattern and a second positioning mark, the target pattern is used to provide a mark for identifying the target device; acquiring a first distance parameter between the target pattern and the second positioning mark; determining a target area number from the plurality of area numbers according to a similarity between the first distance parameter and each preset distance parameter in a preset distance parameter set, wherein each preset distance parameter in the preset distance parameter set is used to represent a distance between each preset area in the plurality of preset areas and the first positioning mark; and determining the target device according to the target area number.

[0008] Further, the determining of the target area number from the plurality of area numbers according to the similarity between the first distance parameter and each preset distance parameter in the preset distance parameter set comprises: comparing the first distance parameter with each preset distance parameter; determining a preset distance parameter in the preset distance parameter set having the greatest similarity with the first distance parameter to obtain a target distance parameter; and determining the target area number from the plurality of area numbers according to a preset area corresponding to the target distance parameter.

[0009] Further, the target pattern at least comprises a label pattern, the image of the target page further comprises a physical table having a plurality of label grids, at least part of the plurality of label grids are used to one-to-one display the label pattern, the generating of the preset template comprises: generating a virtual table having a plurality of preset areas and the first positioning mark, wherein the plurality of preset areas comprise a plurality of virtual grids, the plurality of virtual grids are used to at least simulate the plurality of label grids, and the first positioning mark is used to simulate the second positioning mark; and numbering the plurality of virtual grids to obtain the plurality of area numbers corresponding to the plurality of virtual grids.

[0010] Further, the target pattern further comprises a logical number pattern, the image of the target page further comprises a plurality of logical number grids one-to-one corresponding to the plurality of label grids, at least part of the plurality of logical number grids are used to one-to-one display the logical number pattern, and another part of the plurality of virtual grids are used to simulate the plurality of logical number grids.

[0011] Further, the second positioning mark comprises four second sub-positioning marks located at an outer periphery of the physical table, and the acquiring of the first distance parameter between the target pattern and the second positioning mark comprises: calculating distances between a center point of the target pattern and center points of the four second sub-positioning marks and normalizing to obtain the first distance parameter.

[0012] Further, the method for determining the target device further comprises: inputting the image of the target page into a preset model for analysis to obtain a target graph corresponding to the image of the target page, wherein the preset model is obtained by training a plurality of sets of data, and each set of data in the plurality of sets of data comprises: an image of a sample page and a label for identifying a target graph corresponding to the image of the sample page.

[0013] Further, the distance between the center point of the target graph and the center points of the four second sub-positioning marks is calculated and normalized to obtain a first distance parameter, comprising: establishing a two-dimensional coordinate system of the width and length of the physical table; determining a first coordinate value of the center point of the target graph and a second coordinate value of the center positioning point of the four second sub-positioning marks based on the two-dimensional coordinate system of the width and length of the physical table; based on the first coordinate value and the second coordinate value, the distance between the center point of each target graph and the center points of the four second sub-positioning marks is calculated and normalized to generate a first distance vector for representing the first distance parameter.

[0014] Further, the first positioning mark comprises four first sub-positioning marks located on the outer periphery of the virtual table, and the method for determining the target device further comprises: calculating the distance between each virtual grid in the plurality of virtual grids and the center points of the four first sub-positioning marks and normalizing to obtain a preset distance parameter set.

[0015] Further, the distance between each virtual grid in the plurality of virtual grids and the center points of the four first sub-positioning marks is calculated and normalized to obtain a preset distance parameter set, comprising: establishing a two-dimensional coordinate system of the width and length of the virtual table; based on the two-dimensional coordinate system of the width and length of the virtual table, obtaining a third coordinate value of the center point of each virtual grid and a fourth coordinate value of the center positioning point of the four first sub-positioning marks; based on the third coordinate value and the fourth coordinate value, the distance between each virtual grid and the center positioning point of the four first sub-positioning marks is calculated and normalized to generate a second distance vector for representing a preset distance parameter in the preset distance parameter set.

[0016] Further, the target region number is determined from the plurality of region numbers according to the similarity between the target distance parameter and each preset distance parameter in the preset distance parameter set, comprising: calculating the cosine similarity of the first distance vector and the second distance vector to obtain a similarity calculation result; taking the region number corresponding to the maximum similarity in the similarity calculation result as the target region number.

[0017] Further, the method for determining the target device further comprises: assigning a target region number to a target grid for displaying the target pattern, the target grid being a label grid in a physical table or a logically numbered grid; segmenting the target grid corresponding to the target region number from the image of the target page; in a case where a plurality of images of target pages are obtained, merging a plurality of target grids corresponding to the plurality of images of target pages in an order of the target region numbers to obtain a target table, wherein different images of the plurality of images of target pages have different target patterns, and the target patterns are used to provide a mark for identifying different target devices.

[0018] According to another aspect of the present application, there is provided a device for determining a target device, comprising: a generating module configured to generate a preset template, wherein the preset template has a plurality of preset regions and a first positioning mark, the plurality of preset regions have one-to-one corresponding region numbers; a first obtaining module configured to obtain an image of a target page, wherein the image of the target page has a target pattern and a second positioning mark, the target pattern is used to provide a mark for identifying the target device; a second obtaining module configured to obtain a first distance parameter between the target pattern and the second positioning mark; a first determining module configured to determine a target distance parameter and a target region number from the plurality of region numbers according to a similarity between the first distance parameter and each preset distance parameter in a preset distance parameter set, wherein each preset distance parameter in the preset distance parameter set is used to represent a distance between each preset region in the plurality of preset regions and the first positioning mark; and a second determining module configured to determine the target device according to the target region number.

[0019] According to another aspect of the present application, there is also provided a photovoltaic system, comprising: a photovoltaic assembly; a target device for optimizing output power of the photovoltaic assembly; a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method for determining the target device as described above.

[0020] According to another aspect of the present application, there is also provided a computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of a photovoltaic system, the photovoltaic system is enabled to perform the method for determining the target device as described above.

[0021] The technical scheme of the present application provides a method for determining a target device, which generates a preset template having a plurality of preset areas and a first positioning mark, the plurality of preset areas having one-to-one area numbers, then acquires a first distance parameter between a target pattern in an image of a target page and a second positioning mark, and determines a target area number from the plurality of area numbers according to the similarity between the first distance parameter and each preset distance parameter in a preset distance parameter set, so that in the case that the target pattern in the image of the target page is not clear due to external factors, the area number of the preset area in the preset template corresponding to the position of the target pattern can be determined to determine the target device, so that the paper image with the label for determining the target device can be quickly and accurately segmented based on the identified target device to finally be combined into a complete target device layout panoramic view, so as to facilitate subsequent monitoring and finding the component or target device position when needed, and maintaining it as needed, thereby improving the operation and maintenance efficiency and convenience of the photovoltaic power station. BRIEF DESCRIPTION OF DRAWINGS

[0022] The drawings accompanying the specification of the present application form a part thereof and serve to provide further understanding of the present application, the exemplary embodiments of the present application and its description serve to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0023] Figure 1 is a flow chart of a method for determining a target device according to embodiment 1 of the present application;

[0024] Figure 2 is a schematic diagram of a mark in a physical table in the method for determining a target device;

[0025] Figure 3 is a schematic diagram of a virtual table in a preset template in the method for determining a target device;

[0026] Figure 4 is a schematic diagram of the position relationship between the center point of a virtual grid in a virtual table and the center positioning point of a first sub-positioning mark in the method for determining a target device;

[0027] Figure 5 is a schematic diagram of a yolov5 algorithm model used in the method for determining a target device;

[0028] Figure 6 is a schematic diagram of the training process of a yolov5 algorithm model used in the method for determining a target device;

[0029] Figure 7is a schematic view of a position relationship between a center point of a target pattern in a physical table and a center positioning point of a second sub-positioning mark in the method for determining a target device;

[0030] Figure 8 is a device block diagram for determining a target device according to Embodiment 2 of the present application. DETAILED DESCRIPTION

[0031] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0032] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0033] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0034] Embodiment 1

[0035] Taking a power optimization device installed on a photovoltaic module as a photovoltaic power optimizer as an example, the generation steps of the physical layout of the power optimizer in the entire power station can include the following:

[0036] 1. Install the power optimizer on the back of the photovoltaic module. Each power optimizer is equipped with two unique two-dimensional code markers during production. After installation, one of the same two two-dimensional codes is attached to the surface of the power optimizer, and the other is attached to the corresponding position in a power optimizer physical layout table paper to indicate that the photovoltaic module at the position is installed with the power optimizer, wherein the content of the identification two-dimensional code can obtain the unique number of the power optimizer.

[0037] 2、Repeat the above steps, install a power optimizer on each photovoltaic module in the power station that needs to be installed with a power optimizer, and finally obtain a plurality of physical layout table papers for displaying the distribution of the power optimizers.

[0038] 3、Take photos of all the physical layout table papers to upload a plurality of physical layout diagrams to a server, and perform physical layout layout segmentation and intelligent recognition of the layout content, including recognition of various mark symbols and characters in the layout.

[0039] 4、Merge the content recognized from each of the above physical layout diagrams according to certain rules, and finally generate a physical layout panoramic diagram of the power optimizers of the power station corresponding to the positions of each photovoltaic module in the power station. The identifier in the diagram can indicate the power optimizer with a unique number installed on each photovoltaic module.

[0040] 5、Monitor the real-time power of the photovoltaic module using the power optimizer. When a power optimizer detects a power-decreased photovoltaic module, the maintenance personnel can find the corresponding two-dimensional code in the above physical layout panoramic diagram according to the logical number of the photovoltaic module, identify the two-dimensional code to view the power optimizer number corresponding to the module, record the number, and then navigate to find the position of the module in the power station. Then, the remaining two-dimensional code on the back of the module is scanned and identified by the mobile phone. The identification content is compared with the recorded number to confirm whether it is the module. If the results are consistent, the module can be maintained.

[0041] However, when taking photos of the power optimizer physical layout table paper, due to the influence of factors such as the resolution of the photo-taking mobile phone, the photo-taking angle, the environmental light (shadow or overexposure), and the size of the paper, there may be difficulties in recognizing and segmenting the physical layout diagram, which leads to the inability to accurately merge a plurality of physical layout diagrams into a complete power optimizer physical layout panoramic diagram, and further leads to the difficulty in quickly and accurately determining the photovoltaic module and the power optimizer that need to be maintained.

[0042] To solve the above technical problems, the embodiments of the present application provide a method for determining a target device. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in a different order.

[0043] Figure 1 is a flowchart of an optional method for determining a target device according to an embodiment of the present application, as shown in Figure 1 , comprising:

[0044] In step S102, a preset template is generated, wherein the preset template has a plurality of preset areas and a first positioning mark, and the plurality of preset areas have one-to-one area numbers.

[0045] In step S104, an image of a target page is acquired, wherein the image of the target page has a target pattern and a second positioning mark, and the target pattern is used to provide a mark for identifying the target device.

[0046] In step S106, a first distance parameter between the target pattern and the second positioning mark is acquired.

[0047] In step S108, a target area number is determined from the plurality of area numbers according to a similarity between the first distance parameter and each preset distance parameter in a preset distance parameter set, wherein each preset distance parameter in the preset distance parameter set is used to represent a distance between each preset area in the plurality of preset areas and the first positioning mark.

[0048] In step S110, the target device is determined according to the target area number.

[0049] By using the method provided in the above embodiment, in the case that the target pattern in the image of the target page is not clear due to external factors, the area number of the preset area in the preset template corresponding to the position of the target pattern can be determined, and the target device can be determined, so that the paper image with the label for determining the target device can be quickly and accurately segmented based on the identified target device, and finally, the paper image can be merged into a complete target device layout panoramic image, thereby facilitating subsequent monitoring and finding the position of the component or the target device when needed, and maintaining the component or the target device as needed, and improving the operation and maintenance efficiency and convenience of the photovoltaic power station.

[0050] In addition, in the case that the target page is a physical grid, the above method can also assign the target area number to the grid where the target pattern is located, so as to quickly and accurately segment the physical grid, and then by merging the grids with the area numbers, a target table showing a plurality of target device layout panoramas can be quickly generated, thereby facilitating the positioning and maintenance of the photovoltaic components and the target devices.

[0051] As an optional implementation, acquiring the image of the target page includes: after the target device is installed on the photovoltaic component, providing a physical grid with the target pattern, and collecting an image of the physical table, wherein the target pattern is used to provide a mark for identifying the target device.

[0052] The photovoltaic modules in the power station are arranged according to the distribution positions and matched with corresponding logical numbers. The logical numbers corresponding to the photovoltaic modules can be filled in the grids of the physical table. At this time, the target pattern in the collected image of the physical table includes a label pattern used to provide identification of the target device and a logical number pattern. The logical number pattern can be understood as a pattern formed by the logical number and the surrounding area. The grid with the label pattern in the physical table is a label grid, and the grid with the logical number pattern in the physical table is a logical number grid.

[0053] As shown in the left part of FIG. 6, for example, the physical grid can include three kinds of marks. If a power optimizer is installed behind a photovoltaic module, a two-dimensional code is pasted on the surface of the power optimizer, another two-dimensional code is pasted in the label grid at the corresponding position, and the logical number of the photovoltaic module is filled in the logical number grid. Figure 2 As shown in the middle part of FIG. 6, if the photovoltaic module is not installed behind the power optimizer, a black solid square is marked in the label grid at the corresponding position, and the logical number of the photovoltaic module is filled in the logical number grid. As shown in the right part of FIG. 6, if the photovoltaic module is not installed, a dashed line hollow square is marked in the label grid at the corresponding position. The two-dimensional code and the black solid square mark described above are all label patterns used to identify the corresponding target device.

[0054] In the step S102, the corresponding preset template can be generated based on the image of the target page. For example, the image of the target page is the image of the physical table, and the preset template with the corresponding virtual table is generated.

[0055] As an optional implementation, the target pattern at least includes a label pattern, the image of the target page further includes a physical table with a plurality of label grids, at least part of the plurality of label grids are used to correspondingly display the label pattern, and the preset template is generated by generating a virtual table with a plurality of preset areas and a first positioning mark, wherein the plurality of preset areas include a plurality of virtual grids, the plurality of virtual grids are used to simulate the plurality of label grids, and the first positioning mark is used to simulate the second positioning mark; and the plurality of virtual grids are numbered to obtain a plurality of area numbers corresponding to the plurality of virtual grids.

[0056] In the above implementation, the target pattern can further include a logical number pattern. At this time, the image of the target page further includes a plurality of logical number grids corresponding to the plurality of label grids, at least part of the plurality of logical number grids are used to correspondingly display the logical number pattern, and another part of the plurality of virtual grids are used to simulate the plurality of logical number grids.

[0057] As an example, the virtual table in the preset template can be as shown in FIG. 7. Figure 3As shown, the grid sequence for simulating the label grid and the logical numbering grid is numbered, and (1.1.0), (1.1.1), (6.10.0) and (6.10.1) in the figure represent the grid numbers numbered according to the grid sequence.

[0058] The first positioning mark in the preset template can include four first sub-positioning marks located at the periphery of the virtual table, and the method for determining the target device can further include: calculating distances between each virtual grid in the plurality of virtual grids and center points of the four first sub-positioning marks and normalizing to obtain a preset distance parameter set.

[0059] As an optional implementation, the calculating distances between each virtual grid in the plurality of virtual grids and center points of the four first sub-positioning marks and normalizing to obtain a preset distance parameter set includes: establishing a two-dimensional coordinate system of the width and length of the virtual table; obtaining third coordinate values of the center points of each virtual grid and fourth coordinate values of the center positioning points of the four first sub-positioning marks based on the two-dimensional coordinate system of the width and length of the virtual table; and calculating distances between each virtual grid and the center positioning points of the four first sub-positioning marks based on the third coordinate values and the fourth coordinate values and normalizing to generate a second distance vector for representing a preset distance parameter in the preset distance parameter set.

[0060] Specifically, a two-dimensional coordinate system can be established with the width direction of the virtual table as the x-axis and the length direction of the virtual table as the y-axis. Figure 4 As shown, the coordinate values of the center points of each virtual grid and the coordinate values of the center positioning points of the four first sub-positioning marks are obtained, wherein the coordinate value of the center point of each virtual grid is O', the center positioning points of the four first sub-positioning marks are the fifth positioning point, the sixth positioning point, the seventh positioning point and the eighth positioning point respectively, and the corresponding coordinate values are A, B, C and D respectively. The distances between each virtual grid and the center positioning points of the four first sub-positioning marks are calculated and normalized to generate a distance vector b i =(y i1 ,y i2 ,y i3 ,y i4 ), wherein y i1 =|O′A| / |AD|, y i2 =|O′B| / |BC|, y i3 =|O′D| / |AD|, and y i4= |O'C| / |BC|, i is the area number corresponding to each virtual grid, |O'A|, |O'B|, |O'C| and |O'D| are the relative distances between the fifth positioning point, the sixth positioning point, the seventh positioning point and the eighth positioning point and the center point of each virtual grid, |AD| is the relative distance between the fifth positioning point and the eighth positioning point, and |BC| is the relative distance between the sixth positioning point and the seventh positioning point.

[0061] For example, a virtual grid as shown in Figure 3 is generated, where (1.1.0) and (1.1.1) represent grid numbers, the distances between the center points of each grid and the four positioning points are calculated and normalized, as shown in Figure 4 , and recorded as a grid normalization distance table of the preset template. Assuming that the coordinates of the center points of the grids and the four positioning points O'1, O'2, A, B, C and D are known, the distances between the center points of the labeled grids and the four positioning points are calculated and normalized, and the calculation method of the logical number grid center point is the same, as shown in Table 1.

[0062] Table 1

[0063]

[0064]

[0065] In step S104, all labels in the image of the target page can be obtained through the neural network model, including the target figure and the second positioning label. The target figure is located in the grid in the physical table, and the second positioning label includes four second sub-positioning labels located outside the periphery of the physical table.

[0066] As an optional implementation, the method for determining the target device further includes: inputting the image of the target page into a preset model for analysis to obtain a target figure corresponding to the image of the target page, wherein the preset model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data includes: an image of a sample page and a label for identifying a target figure corresponding to the image of the sample page.

[0067] For example, all labels in the image of the target page uploaded to the server are detected and recognized through a yolov5 neural network model, including four second sub-positioning labels, all label figures and logical numbers. The all-label detection and recognition algorithm uses a yolov5 algorithm model, and the overall network structure of the algorithm is as shown in Figure 5 As can be seen from the figure, the entire structure is mainly divided into four parts: input data, Backbone network structure, Neck network structure and Prediction structure, wherein:

[0068] Input data: Primarily composed of mosaic data augmentation and adaptive anchor box calculation. Mosaic data augmentation involves splicing data using random scaling, random cropping, and random arrangement. During each training session, the optimal anchor box values ​​from different training sets are adaptively calculated.

[0069] Backbone network architecture: Consists of a Focus architecture and a CSP architecture. The Focus architecture uses a slicing operation to convert the original 608*608*3 image into a 304*304*12 feature map. This is then convolved with 32 convolution kernels, ultimately resulting in a 304*304*32 feature map. The CSP architecture draws on the CSPNet network architecture and consists of a convolutional layer and X Res unint modules (concatenated).

[0070] Neck network structure: It consists of FPN and PAN structures. FPN and PAN are based on PANet, which is mainly used in the field of image segmentation to further improve feature extraction capabilities.

[0071] Prediction structure: GIOU_Loss is used as the loss function of the Bounding box. The goal of GIoU is equivalent to adding a penalty for the closure formed by the ground truth and the predicted box to the loss function. Its penalty term is the area of ​​the closure minus the union of the two boxes. The smaller the ratio in the closure, the better.

[0072] The training process of the above yolov5 target detection and recognition algorithm model can be as follows Figure 6 As shown, the process includes: collecting images of the target layout uploaded to the server, annotating the markers in the images, creating a marker dataset, and dividing the marker recognition dataset into a training set and a test set according to a certain ratio. A YOLOv5 network model is constructed, the algorithm model parameters are adjusted, and the marker recognition algorithm model is trained using the marker recognition training set to obtain a marker recognition algorithm model. The trained network model is then used for marker recognition. The YOLOv5 neural network model is used to detect and identify all markers in the images of the target layout uploaded to the server.

[0073] In the above-mentioned step S106, the second positioning mark includes four second sub-positioning marks located on the periphery of the physical table. Obtaining the first distance parameter between the target graphic and the second positioning mark can include: calculating the distance between the center point of the target graphic and the center points of the four second sub-positioning marks and normalizing it to obtain the first distance parameter.

[0074] As an optional implementation, the distance between the center point of the target pattern and the center points of the four second sub-positioning marks is calculated and normalized to obtain the first distance parameter, including: establishing a two-dimensional coordinate system of the width and length of the physical table; determining the first coordinate value of the center point of the target pattern and the second coordinate value of the center positioning points of the four second sub-positioning marks based on the two-dimensional coordinate system of the width and length of the physical table; calculating the distance between the center point of each target pattern and the center points of the four second sub-positioning marks based on the first coordinate value and the second coordinate value and normalizing to generate a first distance vector for representing the first distance parameter.

[0075] Specifically, a two-dimensional coordinate system can be established with the width direction of the physical table as the x-axis and the length direction of the physical table as the y-axis; the coordinate values of the center point of the target pattern and the center positioning points of the four second sub-positioning marks are obtained, wherein the coordinate value of the center point of the target pattern is O, the center points of the four second sub-positioning marks are the first positioning point, the second positioning point, the third positioning point and the fourth positioning point, and the corresponding coordinate values are A, B, C and D respectively; the distance between the center point of each target pattern and the center points of the four second sub-positioning marks is calculated and normalized to generate a distance vector a=(x1, x2, x3, x4), wherein x1=|OA| / |AD|, x2=|OB| / |BC|, x3=|OD| / |AD|, x4=|OC| / |BC|, |OA|, |OB|, |OC| and |OD| are the relative distances between the first positioning point, the second positioning point, the third positioning point and the fourth positioning point and the center point of each target pattern, |AD| is the relative distance between the first positioning point and the fourth positioning point, and |BC| is the relative distance between the second positioning point and the third positioning point.

[0076] For example, the image of the target layout as shown in FIG. 2 is obtained, and the coordinate values of the label pattern center point, the logical number pattern center point and the four second sub-positioning marks are obtained. Assuming that the coordinate values of the center point of the label pattern and the center points of the four second sub-positioning marks are O, A, B, C and D, the distance between the center point of the label pattern and the center points of the four second sub-positioning marks is calculated and normalized, and the calculation method of the logical number pattern center point is the same, as shown in Table 2. Figure 7

[0077] Table 2

[0078] Positioning point A Positioning point B Positioning point C Positioning point D x1 = |OA| / |AD| x2 = |OB| / |BC| x3 = |OD| / |AD| x4 = |OC| / |BC|

[0079] ​In the above-mentioned step S108, determining the target area number from the multiple area numbers based on the similarity between the first distance parameter and each preset distance parameter in the preset distance parameter set may include: comparing the first distance parameter with each preset distance parameter; determining the preset distance parameter in the preset distance parameter set that has the greatest similarity with the first distance parameter to obtain the target distance parameter; and determining the target area number from the multiple area numbers based on the preset area corresponding to the target distance parameter.

[0080] As an optional implementation method, based on the similarity between the target distance parameter and each preset distance parameter in the preset distance parameter set, the target area number is determined from multiple area numbers, including: calculating the cosine similarity between the above-mentioned first distance vector and the above-mentioned second distance vector to obtain a similarity calculation result; taking the area number corresponding to the maximum similarity in the similarity calculation result as the target area number.

[0081] For example, the normalized distances between the center point of the label grid and the four positioning points are combined into a vector a = (x1, x2, x3, x4). According to the grid number, the normalized distance table of the template A grid is searched in sequence to obtain the combined vector b corresponding to each grid number. i =(y ia ,y ib ,y ic ,y id ), calculate a and b i Cosine similarity calculation formula: Calculate the corresponding grid numbers Similarity value: grid number The grid number corresponding to the maximum similarity is taken out and assigned to the grid where the mark is located.

[0082] As an optional implementation, the method for determining the target device also includes: assigning a target area number to a target grid for displaying a target graphic, the target grid being a label grid or a logical number grid in a physical table; segmenting a target grid corresponding to the target area number from an image of a target layout; in the case of obtaining images of multiple target layouts, merging multiple target grids corresponding to the images of the multiple target layouts in the order of the target area numbers to obtain a target table, wherein different target layouts in the images of the multiple target layouts have different target graphics for providing marks for identifying different target devices.

[0083] Specifically, the target area number is assigned to the target grid used to display the target graphics, thereby completing the segmentation of the target grid in the target layout. After completing the assignment of target area numbers for all target graphics, all the segmented target grids are merged in the order of the target area numbers to obtain a target table for displaying the panoramic view of the layout of all target devices.

[0084] Embodiment 2

[0085] According to the embodiment of the present application, the device for determining the target equipment is also provided, Figure 8 is a device structure block diagram for determining the target equipment according to the embodiment of the present application, as shown in the figure, the device comprises: a generating module 202, a first obtaining module 204, a second obtaining module 206, a first determining module 208, and a second determining module 210, which will be described below. Figure 8 The generating module 202 is configured to generate a preset template, wherein the preset template has a plurality of preset areas and a first positioning mark which do not overlap, and the plurality of preset areas have one-to-one area numbers.

[0086] The first obtaining module 204 is configured to obtain an image of a target page, wherein the image of the target page has a target pattern and a second positioning mark, and the target pattern is used to provide a mark for identifying the target equipment.

[0087] The second obtaining module 206 is configured to obtain a first distance parameter between the target pattern and the second positioning mark.

[0088] The first determining module 208 is configured to determine a target distance parameter and a target area number from the plurality of area numbers according to the similarity between the first distance parameter and each preset distance parameter in a preset distance parameter set, wherein each preset distance parameter in the preset distance parameter set is used to represent the distance between each preset area in the plurality of preset areas and the first positioning mark.

[0089] The second determining module 210 is configured to determine the target equipment according to the target area number.

[0090] The device provided by the above embodiment can determine the area number of the preset area corresponding to the position of the target pattern in the preset template through the first determining module 208 in the case that the target pattern in the image of the target page is not clear due to external factors, and determine the target equipment through the second determining module 210, so as to quickly and accurately segment all paper images with labels for determining the target equipment based on the identified target equipment, and finally merge them into a complete target equipment layout panoramic view, so as to facilitate subsequent monitoring and finding the position of the component or the target equipment when needed, and maintaining it as needed, thereby improving the operation and maintenance efficiency and convenience of the photovoltaic power station.

[0091]

[0092] ​It should be noted that the above generation module 202, the first acquisition module 204, the second acquisition module 206, the first determination module 208 and the second determination module 210 correspond to steps S102 to S110 in Embodiment 1, and the three modules have the same instances and application scenarios as the corresponding steps, but are not limited to the above disclosed content in Embodiment 1.

[0093] Embodiment 3

[0094] Embodiments of the present application can provide a photovoltaic system, which can include: a photovoltaic assembly; a target device for optimizing the output power of the photovoltaic assembly; a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method of determining the target device as described above.

[0095] With the photovoltaic system provided by the above embodiments, in the case that the target image in the target page is not clear due to external factors, the processor can execute the instructions stored in the memory to determine the region number of the preset region in the preset template corresponding to the position of the target image, so as to determine the target device, so that the operation and maintenance personnel can quickly and accurately segment all paper images with labels for determining the target device based on the identified target device, so as to finally combine them into a complete target device layout panoramic view, and then facilitate subsequent monitoring and finding the component or target device position when needed, and maintaining it as needed, thereby improving the operation and maintenance efficiency and convenience of the photovoltaic power station.

[0096] In the above photovoltaic system, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the method and device for determining the target device in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implements the method of determining the target device as described above. The memory can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some examples, the memory can further include remotely located memories relative to the processor, which can be connected to the computer terminal through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0097] The processor can call information and application programs stored in the memory through the transmission device to execute the following steps: generating a preset template, wherein the preset template has a plurality of preset areas and a first positioning mark, the plurality of preset areas have one-to-one area numbers; obtaining an image of a target page, wherein the image of the target page has a target pattern and a second positioning mark, the target pattern is used to provide a mark for identifying a target device; obtaining a first distance parameter between the target pattern and the second positioning mark; determining a target area number from the plurality of area numbers according to the similarity between the first distance parameter and each preset distance parameter in a preset distance parameter set, wherein each preset distance parameter in the preset distance parameter set is used to represent the distance between each preset area in the plurality of preset areas and the first positioning mark; and determining the target device according to the target area number.

[0098] Optionally, the processor can further execute program codes of the following steps: determining the target area number from the plurality of area numbers according to the similarity between the first distance parameter and each preset distance parameter in the preset distance parameter set, comprising: comparing the first distance parameter with each preset distance parameter; determining a preset distance parameter in the preset distance parameter set having the maximum similarity with the first distance parameter to obtain a target distance parameter; and determining the target area number from the plurality of area numbers according to the preset area corresponding to the target distance parameter.

[0099] Optionally, the processor can further execute program codes of the following steps: the target pattern at least includes a label pattern, the image of the target page further includes a physical table having a plurality of label grids, at least part of the plurality of label grids are used to one-to-one display the label pattern, generating the preset template, comprising: generating a virtual table having a plurality of preset areas and a first positioning mark, wherein the plurality of preset areas include a plurality of virtual grids, the plurality of virtual grids are used to at least simulate the plurality of label grids, and the first positioning mark is used to simulate the second positioning mark; and numbering the plurality of virtual grids to obtain a plurality of area numbers corresponding to the plurality of virtual grids.

[0100] Optionally, the processor can further execute program codes of the following steps: the target pattern further includes a logical number pattern, the image of the target page further includes a plurality of logical number grids one-to-one corresponding to the plurality of label grids, at least part of the plurality of logical number grids are used to one-to-one display the logical number pattern, and another part of the plurality of virtual grids are used to simulate the plurality of logical number grids.

[0101] Optionally, the processor can further execute program codes of the following steps: the second positioning mark comprises four second sub-positioning marks located at the periphery of the physical table, and the first distance parameter between the target graph and the second positioning mark is obtained by calculating and normalizing the distances between the center point of the target graph and the center points of the four second sub-positioning marks.

[0102] Optionally, the processor can further execute program codes of the following steps: the image of the target page is input into a preset model for analysis to obtain a target graph corresponding to the image of the target page, wherein the preset model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data comprises an image of a sample page and a label for identifying a target graph corresponding to the image of the sample page.

[0103] Optionally, the processor can further execute program codes of the following steps: the first distance parameter is obtained by calculating and normalizing the distances between the center point of the target graph and the center points of the four second sub-positioning marks, comprising: establishing a two-dimensional coordinate system of the width and length of the physical table; determining the first coordinate value of the center point of the target graph and the second coordinate value of the center positioning point of the four second sub-positioning marks based on the two-dimensional coordinate system of the width and length of the physical table; and calculating and normalizing the distance between the center point of each target graph and the center points of the four second sub-positioning marks based on the first coordinate value and the second coordinate value to generate a first distance vector for representing the first distance parameter.

[0104] Optionally, the processor can further execute program codes of the following steps: the first positioning mark comprises four first sub-positioning marks located at the periphery of the virtual table, and the method for determining the target device further comprises: calculating and normalizing the distances between each virtual grid in the plurality of virtual grids and the center points of the four first sub-positioning marks to obtain a preset distance parameter set.

[0105] Optionally, the processor can further execute program codes of the following steps: the first distance parameter is obtained by calculating and normalizing the distances between the center point of the target graph and the center points of the four second sub-positioning marks, comprising: establishing a two-dimensional coordinate system of the width and length of the physical table; determining the first coordinate value of the center point of the target graph and the second coordinate value of the center positioning point of the four second sub-positioning marks based on the two-dimensional coordinate system of the width and length of the physical table; and calculating and normalizing the distance between the center point of each target graph and the center points of the four second sub-positioning marks based on the first coordinate value and the second coordinate value to generate a first distance vector for representing the first distance parameter.

[0106] Optionally, the processor can further execute program codes of the following steps: determining the target region number from the plurality of region numbers according to a similarity between the target distance parameter and each preset distance parameter in the set of preset distance parameters, including: calculating a cosine similarity between the first distance vector and the second distance vector to obtain a similarity calculation result; and taking a region number corresponding to a maximum similarity in the similarity calculation result as the target region number.

[0107] Optionally, the processor can further execute program codes of the following steps: assigning the target region number to a target grid for displaying the target graphic, the target grid being a label grid in a physical table or a logical number grid; segmenting the target grid corresponding to the target region number from the image of the target page; and in a case where a plurality of images of target pages are acquired, merging a plurality of target grids corresponding to the plurality of images of target pages in an order of the target region numbers to obtain a target table, wherein different images of the plurality of images of target pages have different target graphics, and the target graphics are used to provide marks for identifying different target devices.

[0108] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiments can be completed by instructing the hardware related to the terminal device by a program, and the program can be stored in a computer readable storage medium, which can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0109] Embodiment 4

[0110] In the exemplary embodiments, a computer readable storage medium including instructions is also provided, when the instructions in the computer readable storage medium are executed by a processor of a photovoltaic system, the photovoltaic system is enabled to perform the above-mentioned method for determining a target device. Optionally, the computer readable storage medium can be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0111] Optionally, in the present embodiment, the above-mentioned computer readable storage medium can be used to save the program codes executed by the method for determining a target device provided in the above-mentioned embodiment 1.

[0112] Optionally, in the present embodiment, the above-mentioned computer readable storage medium can be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the mobile terminals in a mobile terminal group.

[0113] In the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: generating a preset template, wherein the preset template has a plurality of preset areas and a first positioning mark, the plurality of preset areas have one-to-one corresponding area numbers; obtaining an image of a target page, wherein the image of the target page has a target pattern and a second positioning mark, the target pattern is used to provide a mark for identifying a target device; obtaining a first distance parameter between the target pattern and the second positioning mark; determining a target area number from the plurality of area numbers according to a similarity between the first distance parameter and each preset distance parameter in a preset distance parameter set, wherein each preset distance parameter in the preset distance parameter set is used to represent a distance between each preset area in the plurality of preset areas and the first positioning mark; and determining the target device according to the target area number.

[0114] By using the above computer readable storage medium provided in the embodiment, in the case that the target pattern in the image of the target page is not clear due to external factors, the area number of the preset area in the preset template corresponding to the position of the target pattern can be determined, and the target device can be determined, so that the operation and maintenance personnel can quickly and accurately segment all paper images with labels used to determine the target device based on the identified target device, so as to finally combine them into a complete target device layout panoramic view, thereby facilitating subsequent monitoring and finding components or target device positions when needed and maintaining them as needed, and improving the operation and maintenance efficiency and convenience of the photovoltaic power station.

[0115] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: determining the target area number from the plurality of area numbers according to the similarity between the first distance parameter and each preset distance parameter in the preset distance parameter set, comprising: comparing the first distance parameter with each preset distance parameter; determining a preset distance parameter in the preset distance parameter set having the maximum similarity with the first distance parameter to obtain a target distance parameter; and determining the target area number from the plurality of area numbers according to the preset area corresponding to the target distance parameter.

[0116] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: the target pattern at least includes a label pattern, the image of the target page further includes a physical table having a plurality of label grids, at least part of the plurality of label grids are used to one-to-one display the label pattern; the preset template is generated, comprising: generating a virtual table having a plurality of preset areas and a first positioning mark, wherein the plurality of preset areas include a plurality of virtual grids, the plurality of virtual grids are used to simulate at least the plurality of label grids, and the first positioning mark is used to simulate the second positioning mark; and the plurality of virtual grids are numbered to obtain a plurality of area numbers corresponding to the plurality of virtual grids.

[0117] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: the target graph further comprises a logical number graph, the image of the target layout further comprises a plurality of logical number grids corresponding to the plurality of label grids one-to-one, at least part of the plurality of logical number grids are used to display the logical number graph one-to-one, and another part of the plurality of virtual grids are used to simulate the plurality of logical number grids.

[0118] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: the second positioning mark comprises four second sub-positioning marks located at the outer periphery of the physical table, and the first distance parameter between the target graph and the second positioning mark is obtained by: calculating the distance between the center point of the target graph and the center point of the four second sub-positioning marks and normalizing to obtain the first distance parameter.

[0119] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: the image of the target layout is input into a preset model for analysis to obtain the target graph corresponding to the image of the target layout, wherein the preset model is obtained by training a plurality of groups of data, and each group of data in the plurality of groups of data comprises: an image of a sample layout and a label for identifying a target graph corresponding to the image of the sample layout.

[0120] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: the distance between the center point of the target graph and the center point of the four second sub-positioning marks is calculated and normalized to obtain the first distance parameter, comprising: establishing a two-dimensional coordinate system of the width and length of the physical table; determining the first coordinate value of the center point of the target graph and the second coordinate value of the center positioning point of the four second sub-positioning marks based on the two-dimensional coordinate system of the width and length of the physical table; based on the first coordinate value and the second coordinate value, the distance between the center point of each target graph and the center point of the four second sub-positioning marks is calculated and normalized to generate a first distance vector for representing the first distance parameter.

[0121] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: the first positioning mark comprises four first sub-positioning marks located at the outer periphery of the virtual table, and the method for determining the target device further comprises: calculating the distance between each virtual grid in the plurality of virtual grids and the center point of the four first sub-positioning marks and normalizing to obtain a preset distance parameter set.

[0122] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: calculating distances between each of the plurality of virtual grids and the center points of the four first sub-positioning marks and normalizing to obtain a preset distance parameter set, including: establishing a two-dimensional coordinate system of the width and length of the virtual table; obtaining third coordinate values of the center points of each virtual grid and fourth coordinate values of the center positioning points of the four first sub-positioning marks based on the two-dimensional coordinate system of the width and length of the virtual table; calculating distances between each of the plurality of virtual grids and the center positioning points of the four first sub-positioning marks based on the third coordinate values and the fourth coordinate values and normalizing to generate a second distance vector for representing a preset distance parameter in the preset distance parameter set.

[0123] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: determining the target area number from the plurality of area numbers according to the similarity between the target distance parameter and each preset distance parameter in the preset distance parameter set, including: calculating the cosine similarity between the first distance vector and the second distance vector to obtain a similarity calculation result; taking the area number corresponding to the maximum similarity in the similarity calculation result as the target area number.

[0124] Optionally, in the embodiment, the computer readable storage medium is configured to store program code for performing the following steps: assigning the target area number to a target grid for displaying a target graphic, the target grid being a label grid or a logical number grid in the physical table; segmenting the target grid corresponding to the target area number from the image of the target layout; in the case of obtaining a plurality of images of target layouts, merging a plurality of target grids corresponding to the plurality of images of target layouts in the order of the target area numbers to obtain a target table, wherein different target graphics are present in different images of the plurality of images of target layouts, and the target graphics are used to provide marks for identifying different target devices.

[0125] In an example embodiment, a computer program product is also provided, when a computer program in the computer program product is executed by a processor of an electronic device, the electronic device is enabled to perform the above-described method for determining a target device.

[0126] The above-mentioned serial numbers of the embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0127] In the above-mentioned embodiments of the application, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0129] Units described as separate components may or may not be physically separate, and 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.

[0130] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0131] If the integrated unit is implemented in the form of 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, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0132] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for determining a target device, characterized in that: include: Generate a preset template, wherein the preset template has a plurality of preset areas and a first positioning mark, and the plurality of preset areas have one-to-one corresponding area numbers; Acquire an image of a target layout, wherein the image of the target layout has a target graphic and a second positioning mark, and the target graphic is used to provide a mark for identifying the target device; Acquire a first distance parameter between the target graphic and the second positioning mark; Determining a target area number from the plurality of area numbers based on a similarity between the first distance parameter and each preset distance parameter in a preset distance parameter set includes: comparing the first distance parameter with each preset distance parameter; determining a preset distance parameter in the preset distance parameter set that has the greatest similarity to the first distance parameter to obtain a target distance parameter; and determining the target area number from the plurality of area numbers based on a preset area corresponding to the target distance parameter; wherein each preset distance parameter in the preset distance parameter set is used to represent a distance between each preset area in the plurality of preset areas and the first positioning marker, and the first positioning marker is used to simulate the second positioning marker; The target device is determined according to the target area number.

2. The method for determining a target device according to claim 1, wherein: The target graphic includes at least a label graphic, and the image of the target layout also includes a physical table having a plurality of label grids, at least some of the plurality of label grids being used to display the label graphic in a one-to-one correspondence. Generating a preset template includes: generating a virtual table having the plurality of preset areas and the first positioning mark, wherein the plurality of preset areas include a plurality of virtual grids, and the plurality of virtual grids are at least used to simulate the plurality of label grids; The plurality of virtual grids are numbered to obtain a plurality of region numbers corresponding to the plurality of virtual grids.

3. The method for determining a target device according to claim 2, wherein: The target graphic also includes a logical numbering graphic, and the image of the target layout also includes a plurality of logical numbering grids corresponding one-to-one to the plurality of label grids. At least some of the plurality of logical numbering grids are used to display the logical numbering graphic one-to-one, and another portion of the plurality of virtual grids are used to simulate the plurality of logical numbering grids.

4. The method for determining a target device according to claim 2, wherein: The second positioning mark includes four second sub-positioning marks located on the periphery of the physical table, and obtaining the first distance parameter between the target graphic and the second positioning mark includes: The distance between the center point of the target graphic and the center points of the four second sub-positioning marks is calculated and normalized to obtain the first distance parameter.

5. The method for determining a target device according to claim 1, wherein: Also includes: The image of the target layout is input into a preset model for analysis to obtain a target graphic corresponding to the image of the target layout, wherein the preset model is obtained by training multiple sets of data, and each set of data in the multiple sets of data includes: an image of a sample layout and a label for identifying the target graphic corresponding to the image of the sample layout.

6. The method for determining a target device according to claim 4, wherein: The calculating and normalizing the distance between the center point of the target graphic and the center points of the four second sub-positioning marks to obtain the first distance parameter includes: Establishing a two-dimensional coordinate system of the width and length of the physical table; Determine, based on a two-dimensional coordinate system of the width and length of the physical table, a first coordinate value of a center point of the target graphic and a second coordinate value of a center positioning point of the four second sub-positioning marks; Based on the first coordinate value and the second coordinate value, the distance between the center point of each target graphic and the center point of the four second sub-positioning marks is calculated and normalized to generate a first distance vector for representing the first distance parameter.

7. The method for determining a target device according to claim 6, wherein: The first positioning mark includes four first sub-positioning marks located on the periphery of the virtual table, and the method for determining the target device further includes: The distance between each virtual grid in the plurality of virtual grids and the center point of the four first sub-positioning marks is calculated and normalized to obtain the preset distance parameter set.

8. The method for determining a target device according to claim 7, wherein: The calculating and normalizing the distance between each virtual grid in the plurality of virtual grids and the center point of the four first sub-positioning marks to obtain the preset distance parameter set includes: Establishing a two-dimensional coordinate system of the width and length of the virtual table; Based on the two-dimensional coordinate system of the width and length of the virtual table, obtaining the third coordinate value of the center point of each virtual grid and the fourth coordinate value of the center positioning point of the four first sub-positioning marks; Based on the third coordinate value and the fourth coordinate value, the distance between each virtual grid and the central positioning point of the four first sub-positioning marks is calculated and normalized to generate a second distance vector for representing the preset distance parameter in the preset distance parameter set.

9. The method for determining a target device according to claim 8, wherein: Determining a target area number from the plurality of area numbers based on similarities between the target distance parameter and each preset distance parameter in the preset distance parameter set includes: Calculating the cosine similarity between the first distance vector and the second distance vector to obtain a similarity calculation result; The region number corresponding to the maximum similarity in the similarity calculation result is taken as the target region number.

10. The method for determining a target device according to claim 3, wherein: Also includes: Assigning the target area number to a target grid for displaying the target graphic, wherein the target grid is a label grid or a logical number grid in the physical table; Segmenting a target grid corresponding to the target area number from the image of the target layout; When acquiring images of multiple target layouts, multiple target grids corresponding to the images of the multiple target layouts are merged in the order of the target area numbers to obtain a target table, wherein different target layouts in the images of the multiple target layouts have different target graphics for providing marks for identifying different target devices.

11. A device for determining a target device, characterized in that: include: A generating module, configured to generate a preset template, wherein the preset template comprises a plurality of non-overlapping preset areas and a first positioning mark, and the plurality of preset areas have one-to-one corresponding area numbers; A first acquisition module is configured to acquire an image of a target layout, wherein the image of the target layout includes a target graphic and a second positioning mark, and the target graphic is used to provide a mark for identifying a target device; A second acquisition module, configured to acquire a first distance parameter between the target graphic and the second positioning mark; a first determining module, configured to determine a target area number from the plurality of area numbers based on a similarity between the first distance parameter and each preset distance parameter in a preset distance parameter set, wherein each preset distance parameter in the preset distance parameter set is used to represent a distance between each preset area in the plurality of preset areas and the first positioning mark; A second determining module, configured to determine the target device according to the target area number; The device is further configured to perform the following steps: comparing the first distance parameter with each of the preset distance parameters; determining a preset distance parameter in the preset distance parameter set that has the greatest similarity with the first distance parameter to obtain a target distance parameter; determining the target area number from a plurality of area numbers based on a preset area corresponding to the target distance parameter; and the first positioning mark is used to simulate the second positioning mark.

12. A photovoltaic system, characterized in that: include: Photovoltaic panels; a target device for optimizing the output power of the photovoltaic module; processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for determining a target device according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that When the instructions in the computer-readable storage medium are executed by a processor of a photovoltaic system, the photovoltaic system is enabled to perform the method for determining a target device according to any one of claims 1 to 10.

Images