Antenna quality determination method and apparatus, storage medium, and electronic device

Abstract

This application discloses a method, apparatus, storage medium, and electronic device for determining antenna quality. Relating to the field of artificial intelligence, the method includes: acquiring a target image corresponding to the antenna under test, wherein the target image is an image obtained after preprocessing a screen image of a VSWR (Standing Wave Ratio) tester; using a target localization model to extract and recognize features from the target image to obtain the coordinates of at least one target keyword, and determining the bounding box coordinates of the numerical region corresponding to the target keyword based on the coordinates of the target keyword and a preset spatial topology relationship; analyzing the bounding box coordinates of the numerical region and the target image to obtain the VSWR value of the antenna under test, and determining the quality judgment result of the antenna under test based on the VSWR value and a preset judgment threshold. This solves the problem of low accuracy in antenna quality judgment based on full-screen optical character recognition in related technologies.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and more specifically, to a method and apparatus for determining antenna quality, a storage medium, and an electronic device. Background Technology

[0002] Antenna impedance matching is the core of communication base station construction, and VSWR (Standing Wave Ratio) is a key parameter for measuring this indicator. VSWR testers often display multiple curves, multiple marker points (such as M1, M2, etc.), and a large amount of frequency and amplitude data. Related technologies mainly rely on full-screen optical character recognition to extract text, which often results in garbled characters and numerous interference values, leading to low data extraction accuracy and consequently, low accuracy in determining antenna quality.

[0003] Regarding the issue of low accuracy in determining antenna quality based on full-screen optical character recognition in related technologies, no effective solution has yet been proposed. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, storage medium, and electronic device for determining antenna quality, in order to solve the problem that the accuracy of antenna quality determination based on full-screen optical character recognition in related technologies is low.

[0005] To achieve the above objectives, according to one aspect of this application, a method for determining antenna quality is provided. The method includes: acquiring a target image corresponding to the antenna under test, wherein the target image is an image obtained after preprocessing a screen image of a VSWR (Standing Wave Ratio) tester; using a target localization model to extract and identify features from the target image to obtain the coordinates of at least one target keyword, and determining the bounding box coordinates of the numerical region corresponding to the target keyword based on the coordinates of the target keyword and a preset spatial topology relationship, wherein the target localization model is obtained by training an initial target detection network using a sample image set, the target keyword is used to characterize the identification of test marker points for testing the antenna under test, and the preset spatial topology relationship is used to characterize the relative positional relationship between the target keyword and the numerical region; analyzing the bounding box coordinates of the numerical region and the target image to obtain the VSWR value of the antenna under test, and determining the quality judgment result of the antenna under test based on the VSWR value and a preset judgment threshold.

[0006] Furthermore, the target localization model is used to extract and identify features from the target image to obtain the coordinates of at least one target keyword. This process includes: inputting the target image into the target localization model; extracting multi-scale features from the target image through the first network of the detection network of the target localization model to obtain multiple feature maps; aggregating the multiple feature maps across scales through the second network of the detection network to obtain a fused feature map; and making predictions based on the fused feature map through the third network of the detection network to obtain the coordinates of at least one target keyword.

[0007] Further, based on the coordinates of the target keyword and the preset spatial topology, the bounding box coordinates of the numerical region corresponding to the target keyword are determined as follows: Preset offset parameters associated with the preset spatial topology are obtained through the coordinate calculation module of the target positioning model, where the preset offset parameters include horizontal and vertical offsets; the lower right horizontal coordinate and the horizontal offset contained in the target keyword's coordinates are summed to obtain the upper left horizontal coordinate contained in the bounding box coordinates; the upper left vertical coordinate and the vertical offset contained in the target keyword's coordinates are summed to obtain the upper left vertical coordinate contained in the bounding box coordinates; the upper left horizontal coordinate contained in the bounding box coordinates are summed with the preset numerical box width to obtain the lower right horizontal coordinate contained in the bounding box coordinates; the upper left vertical coordinate contained in the bounding box coordinates are summed with the preset numerical box height to obtain the lower right vertical coordinate contained in the bounding box coordinates; the bounding box coordinates are formed based on the upper left horizontal coordinate, upper left vertical coordinate, lower right horizontal coordinate, and lower right vertical coordinate contained in the bounding box coordinates.

[0008] Furthermore, based on the bounding box coordinates of the numerical region and the target image, the VSWR value of the antenna under test is obtained by analysis including: cropping the target image according to the bounding box coordinates of the numerical region to obtain the target region image, wherein the target region image contains the VSWR value of the antenna under test; performing optical character recognition on the target region image to obtain the text string corresponding to the target region image; and extracting text from the text string to obtain the VSWR value of the antenna under test.

[0009] Furthermore, the text extraction based on the text string to obtain the VSWR value of the antenna under test includes: extracting candidate values ​​that conform to a preset numerical format from the text string according to a preset regular expression to obtain a candidate value sequence, wherein the preset numerical format includes integer format, decimal format or format with leading decimal point; reversing the candidate value sequence to obtain a sorted candidate value sequence, and sequentially traversing each candidate value in the sorted candidate value sequence to determine whether the candidate value is within a preset numerical range, and taking the first candidate value that meets the preset numerical range as the VSWR value of the antenna under test.

[0010] Furthermore, based on the VSWR value and the preset judgment threshold, the quality judgment result of the antenna under test is determined by: comparing the VSWR value with the preset judgment threshold; if the VSWR value is less than or equal to the preset judgment threshold, the quality judgment result of the antenna under test is determined to be qualified; if the VSWR value is greater than the preset judgment threshold, the quality judgment result of the antenna under test is determined to be unqualified.

[0011] Furthermore, before acquiring the target image corresponding to the antenna under test, the method also includes: acquiring the original screen image generated when the VSWR tester tests the antenna under test, and performing image normalization scaling and Gaussian filtering noise reduction preprocessing on the original screen image to obtain the target image.

[0012] To achieve the above objectives, according to another aspect of this application, an antenna quality determination apparatus is provided. The apparatus includes: an acquisition unit for acquiring a target image corresponding to the antenna under test, wherein the target image is an image obtained after preprocessing a screen image of a VSWR tester; a processing unit for using a target localization model to perform feature extraction and recognition based on the target image to obtain the coordinates of at least one target keyword, and determining the bounding box coordinates of the numerical region corresponding to the target keyword based on the coordinates of the target keyword and a preset spatial topology relationship, wherein the target localization model is obtained by training an initial target detection network using a sample image set, the target keyword is used to characterize the identification of test marker points for testing the antenna under test, and the preset spatial topology relationship is used to characterize the relative positional relationship between the target keyword and the numerical region; and a determination unit for analyzing the bounding box coordinates of the numerical region and the target image to obtain the VSWR value of the antenna under test, and determining the quality determination result of the antenna under test based on the VSWR value and a preset judgment threshold.

[0013] Furthermore, the processing unit includes: a first processing subunit, used to input the target image into the target localization model, and extract multi-scale features from the target image through the first network of the detection network of the target localization model to obtain multiple feature maps; a second processing subunit, used to perform cross-scale feature aggregation on the multiple feature maps through the second network of the detection network to obtain a fused feature map; and a third processing subunit, used to make predictions based on the fused feature map through the third network of the detection network to obtain the coordinates of at least one target keyword.

[0014] Furthermore, the processing unit also includes: a fourth processing subunit, used to obtain preset offset parameters associated with preset spatial topological relationships through the coordinate calculation module of the target localization model, wherein the preset offset parameters include horizontal offset and vertical offset; a first calculation subunit, used to sum the lower right horizontal coordinate and horizontal offset contained in the coordinates of the target keyword to obtain the upper left horizontal coordinate contained in the bounding box coordinates; a second calculation subunit, used to sum the upper left vertical coordinate and vertical offset contained in the coordinates of the target keyword to obtain the upper left vertical coordinate contained in the bounding box coordinates; and a third... The third calculation subunit is used to sum the upper left corner x-coordinate and the preset value box width in the bounding box coordinates to obtain the lower right corner x-coordinate in the bounding box coordinates; the fourth calculation subunit is used to sum the upper left corner y-coordinate and the preset value box height in the bounding box coordinates to obtain the lower right corner y-coordinate in the bounding box coordinates; the fifth processing subunit is used to assemble the bounding box coordinates based on the upper left corner x-coordinate, upper left corner y-coordinate, lower right corner x-coordinate, and lower right corner y-coordinate in the bounding box coordinates.

[0015] Furthermore, the determining unit includes: a sixth processing subunit, used to crop the target image based on the bounding box coordinates of the numerical region to obtain a target region image, wherein the target region image contains the VSWR value of the antenna under test; a seventh processing subunit, used to perform optical character recognition on the target region image to obtain a text string corresponding to the target region image; and an eighth processing subunit, used to extract text based on the text string to obtain the VSWR value of the antenna under test.

[0016] Furthermore, the eighth processing subunit includes: a first processing module, used to extract candidate values ​​that conform to a preset numerical format from a text string according to a preset regular expression, to obtain a candidate value sequence, wherein the preset numerical format includes an integer format, a decimal format, or a format with a leading decimal point; and a second processing module, used to reverse the candidate value sequence to obtain a sorted candidate value sequence, and to sequentially traverse each candidate value in the sorted candidate value sequence, determine whether the candidate value is within a preset numerical range, and take the first candidate value that meets the preset numerical range as the VSWR value of the antenna under test.

[0017] Furthermore, the determining unit also includes: a first determining subunit, used to compare the VSWR value with a preset judgment threshold; a second determining subunit, used to determine that the quality judgment result of the antenna under test is qualified if the VSWR value is less than or equal to the preset judgment threshold; and a third determining subunit, used to determine that the quality judgment result of the antenna under test is unqualified if the VSWR value is greater than the preset judgment threshold.

[0018] Furthermore, the device also includes a preprocessing unit, used to acquire the original screen image generated when the VSWR tester tests the antenna under test before acquiring the target image corresponding to the antenna under test, and to perform image normalization scaling and Gaussian filtering noise reduction preprocessing on the original screen image to obtain the target image.

[0019] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the antenna quality determination method described above during runtime.

[0020] According to another aspect of the present invention, a computer-readable storage medium is also provided, the storage medium storing a program, wherein, when the program is running, the device where the storage medium is located executes the method for determining antenna quality as described above.

[0021] In this embodiment, the following steps are employed: acquiring a target image corresponding to the antenna under test, wherein the target image is an image obtained after preprocessing the screen image of the VSWR tester; using a target localization model to extract and identify features based on the target image to obtain the coordinates of at least one target keyword, and determining the bounding box coordinates of the numerical region corresponding to the target keyword based on the coordinates of the target keyword and a preset spatial topology relationship, wherein the target localization model is obtained by training an initial target detection network through a sample image set, the target keyword is used to characterize the identification of the test marker point for testing the antenna under test, and the preset spatial topology relationship is used to characterize the relative positional relationship between the target keyword and the numerical region; analyzing the bounding box coordinates of the numerical region and the target image to obtain the VSWR value of the antenna under test, and determining the quality judgment result of the antenna under test based on the VSWR value and a preset judgment threshold. This solves the technical problem of low accuracy in quality judgment when using full-screen optical character recognition to determine antenna quality in related technologies.

[0022] In this solution, the screen image of the VSWR tester is acquired and preprocessed to eliminate deformation and noise interference. The target localization model trained on samples is combined with the preset spatial topology to accurately locate the test marker points and calculate the corresponding numerical region boundary box. This effectively avoids the positioning drift and confusion with other values ​​caused by blind search of the whole screen. Based on the boundary box, region analysis is performed to extract the VSWR value, and the quality judgment result is automatically determined by combining the preset judgment threshold, which improves the accuracy of data extraction and the accuracy of quality judgment. Attached Figure Description

[0023] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0024] Figure 1 A hardware block diagram of a computer terminal for implementing a method for determining antenna quality is shown.

[0025] Figure 2 This is a flowchart of a method for determining antenna quality according to an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of an antenna quality determination device provided according to an embodiment of this application;

[0027] Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, and necessary measures have been taken to ensure compliance with public order and good morals. Corresponding access points are provided for users to choose whether to authorize or refuse. For example, interfaces are established between this system and relevant users or organizations, providing users with corresponding access points to choose whether to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0031] Example 1

[0032] According to an embodiment of this application, a method embodiment for determining antenna quality is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a method for determining antenna quality is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0034] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0035] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the antenna quality determination method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned antenna quality determination method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0036] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0037] The display may be a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0038] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for determining antenna quality is shown. Figure 2 This is a flowchart of a method for determining antenna quality according to Embodiment 1 of this application. The method for determining antenna quality includes:

[0039] Step S201: Obtain the target image corresponding to the antenna under test, wherein the target image is the image obtained after preprocessing the screen image of the VSWR tester;

[0040] Step S202: The target localization model is used to extract and identify features based on the target image to obtain the coordinates of at least one target keyword. Based on the coordinates of the target keyword and the preset spatial topology relationship, the bounding box coordinates of the numerical region corresponding to the target keyword are determined. The target localization model is obtained by training the initial target detection network through the sample image set. The target keyword is used to represent the identification of the test marker point for testing the antenna under test. The preset spatial topology relationship is used to represent the relative positional relationship between the target keyword and the numerical region.

[0041] Step S203: Analyze the bounding box coordinates of the numerical region and the target image to obtain the standing wave ratio (SWR) value of the antenna under test, and determine the quality judgment result of the antenna under test based on the SWR value and the preset judgment threshold.

[0042] Optionally, the antenna quality determination system is used as the execution subject. The system acquires the target image corresponding to the antenna under test. This image is obtained after preprocessing the screen image of the VSWR tester.

[0043] Optionally, in the method for determining antenna quality provided in the embodiments of this application, before acquiring the target image corresponding to the antenna under test, the method further includes: acquiring the original screen image generated when the VSWR tester tests the antenna under test, and performing image normalization scaling and Gaussian filtering noise reduction preprocessing on the original screen image to obtain the target image.

[0044] In an optional embodiment, before acquiring the target image corresponding to the antenna under test, image acquisition and standardization preprocessing are first performed. For example, the system first acquires the original screen image generated when the VSWR tester tests the antenna under test through the image acquisition device. Then, the original screen image is scaled and filled proportionally to make its size meet the model input requirements and eliminate the deformation caused by shooting angle or equipment differences. Then, the image is subjected to Gaussian filtering noise reduction processing to remove high-frequency noise in the image (such as screen pixel noise or ambient light spots), thereby obtaining a clear and standardized target image, ensuring the clarity of the keywords (such as M1) and small values ​​of the marker points on the screen.

[0045] Optionally, the system calls a pre-trained target localization model to extract and recognize features from the target image, obtaining the pixel coordinates of specific test markers (i.e. target keywords, such as M1, M2, etc.) in the image. Then, the system combines the preset spatial topological relationship (i.e. the fixed relative position of the marker and the numerical region on the screen, such as the value being to the right of M1 or below M1) and uses the coordinates of the target keywords to accurately calculate the bounding box coordinates of the corresponding numerical region.

[0046] In an optional embodiment, the preprocessed image is input into a pre-trained target localization model, and cascaded localization logic is executed: First, global localization is performed through a trained target detection network to identify the entire display screen area of ​​the VSWR tester. Then, anchor point localization is performed, that is, within the display screen area, the coordinates of highly recognizable keywords (such as M1, M2, etc.) are oriented and identified as spatial prior anchor points. Then, the target is locked through the coordinate calculation module. For example, using the M1 keyword anchor point as a reference, spatial topological correlation is used to accurately lock and output the bounding box coordinates of the corresponding M1 numerical region. ,in, This represents the x-coordinate of the top-left corner of the bounding box. This represents the y-coordinate of the top-left corner of the bounding box. This represents the x-coordinate of the bottom right corner of the bounding box. This represents the y-coordinate of the bottom right corner of the bounding box.

[0047] Optionally, the target localization model is obtained by training an initial target detection network (such as a single-stage regression detection network or a two-stage detection network based on region proposal) using a sample image set. For example, during the training phase, screen images with different types of VSWR testers, different shooting angles, different lighting conditions, and different VSWR values ​​are collected. Each image is labeled using a labeling tool, for example, drawing the bounding box of the entire display screen area and assigning a label (e.g., zbb_xsp), and drawing the bounding box containing the keyword M1 and assigning a label (e.g., zbb_m1_key). This labeled data is input into the initial target detection network as a sample image set. The loss function between the predicted box and the ground truth labeled box is calculated through forward propagation, and the network weights are updated using the backpropagation algorithm, enabling the model to learn to extract key features from complex screen backgrounds and waveform curve interference, such as the character shape features of the keyword M1 and the geometric contour features of the display screen.

[0048] Optionally, the system performs region analysis on the target image based on the bounding box coordinates of the numerical region to extract the VSWR value, and compares the value with a preset judgment threshold (such as 1.3) to determine the quality judgment result (qualified or unqualified) of the antenna under test.

[0049] In summary, by acquiring and preprocessing the screen image of the VSWR tester to eliminate deformation and noise interference, and using a target localization model trained on samples combined with preset spatial topological relationships, the test marker points are accurately located and the corresponding numerical region boundary boxes are calculated. This effectively avoids the positioning drift and confusion with other values ​​caused by blind search across the entire screen. Based on this boundary box, region analysis is performed to extract the VSWR value, and the quality judgment result is automatically determined by combining it with a preset judgment threshold, thus improving the accuracy of data extraction and the accuracy of quality judgment.

[0050] Optionally, in the antenna quality determination method provided in this application embodiment, the method of using a target localization model to extract and identify features based on a target image to obtain the coordinates of at least one target keyword includes: inputting the target image into the target localization model; extracting multi-scale features from the target image through a first network of the detection network of the target localization model to obtain multiple feature maps; aggregating cross-scale features from the multiple feature maps through a second network of the detection network to obtain a fused feature map; and predicting based on the fused feature map through a third network of the detection network to obtain the coordinates of at least one target keyword.

[0051] In an optional embodiment, the target localization model includes a trained target detection network. During the inference phase, the target image is input into the detection network, and the backbone network (i.e., the first network) of the detection network performs multi-scale feature extraction on the target image, capturing abstract feature representations from low-level pixel edges to high-level semantics (such as screen borders and character structures), resulting in multiple feature maps. Then, the extracted feature maps are fed into the neck network (i.e., the second network), where cross-scale feature aggregation is performed through a bidirectional feature pyramid structure to obtain a fused feature map. Finally, the fused feature map is fed into the head network (i.e., the third network) for prediction to obtain the bounding box coordinates of target keywords such as M1.

[0052] Through the above process, the model can accurately locate target keywords, thereby improving the accuracy of data extraction and, consequently, the accuracy of quality assessment.

[0053] Optionally, in the antenna quality determination method provided in this application embodiment, determining the bounding box coordinates of the numerical region corresponding to the target keyword based on the coordinates of the target keyword and the preset spatial topology relationship includes: obtaining preset offset parameters associated with the preset spatial topology relationship through the coordinate calculation module of the target positioning model, wherein the preset offset parameters include horizontal offset and vertical offset; summing the lower right horizontal coordinate and the horizontal offset contained in the coordinates of the target keyword to obtain the upper left horizontal coordinate contained in the bounding box coordinates; and summing the upper left vertical coordinate and the vertical offset contained in the coordinates of the target keyword. The displacement is summed to obtain the top-left ordinate of the bounding box coordinates; the top-left abscissa of the bounding box coordinates is summed with the width of the preset value box to obtain the bottom-right abscissa of the bounding box coordinates; the top-left ordinate of the bounding box coordinates is summed with the height of the preset value box to obtain the bottom-right ordinate of the bounding box coordinates; the bounding box coordinates are then constructed based on the top-left abscissa, top-left ordinate, bottom-right abscissa, and bottom-right ordinate of the bounding box coordinates.

[0054] In an optional embodiment, the preset spatial topological relationship is achieved through preset offset parameters. For example, fixed offsets are set between the target keyword bounding box and the numerical region bounding box in the horizontal and vertical directions, i.e., horizontal offsets and vertical offsets, thereby deriving the coordinates of the numerical region using the coordinates of the target keyword. Optionally, the target localization model further includes a coordinate calculation module, through which the horizontal offset ( ) and vertical offset ( For example, the coordinates of the keyword M1 are... First, the coordinates of the target keyword include the lower right x-coordinate (e.g., ...). ) and horizontal offset ( Add them together to obtain the x-coordinate of the top left corner of the numerical region bounding box (e.g., ...). Secondly, the top-left ordinate of the target keyword's coordinates (e.g., ...) ) and vertical offset ( Add them together to obtain the ordinate of the top left corner of the numerical region bounding box (e.g., ...). Next, Add the coordinates of the lower right corner of the bounding box to the preset width of the numerical region (e.g., ...). Finally, Add the height of the preset numerical bounding box to obtain the y-coordinate of the lower right corner of the numerical region's bounding box (e.g., ...). Then, these four coordinate values ​​are combined to form the complete numerical region bounding box coordinates, such as... .

[0055] By utilizing deep learning networks to first identify fixed keywords on the screen (such as M1) as spatial anchors, the model can be guided and locked onto the true numerical region based on topological relationships. This reduces the difficulty of model recognition in complex backgrounds and improves the accuracy and robustness of data extraction.

[0056] Optionally, in the antenna quality determination method provided in this application embodiment, the analysis based on the bounding box coordinates of the numerical region and the target image to obtain the VSWR value of the antenna under test includes: cropping the target image based on the bounding box coordinates of the numerical region to obtain a target region image, wherein the target region image contains the VSWR value of the antenna under test; performing optical character recognition on the target region image to obtain a text string corresponding to the target region image; and extracting text based on the text string to obtain the VSWR value of the antenna under test.

[0057] In an optional embodiment, the system crops the target image based on the bounding box coordinates of the numerical region to obtain the region of interest (i.e., the target region image), removes strong interference backgrounds such as frequency axes and waveform curves on the screen image, and then the system traverses the region through a high-precision optical character recognition engine, splices the extracted discrete text block sequence to obtain the text string corresponding to the region, and then performs text extraction based on the text string to obtain the VSWR value of the antenna under test.

[0058] By obtaining a clean target area image based on bounding box coordinates and performing optical character recognition and extraction, screen background interference is effectively eliminated, improving the accuracy of VSWR numerical recognition.

[0059] Optionally, in the method for determining antenna quality provided in this application embodiment, extracting text from a text string to obtain the VSWR value of the antenna under test includes: extracting candidate values ​​that conform to a preset numerical format from the text string according to a preset regular expression to obtain a candidate value sequence, wherein the preset numerical format includes an integer format, a decimal format, or a format with a leading decimal point; reversing the candidate value sequence to obtain a sorted candidate value sequence, and sequentially traversing each candidate value in the sorted candidate value sequence to determine whether the candidate value is within a preset numerical range, and taking the first candidate value that meets the preset numerical range as the VSWR value of the antenna under test.

[0060] In an optional embodiment, the system utilizes a regular expression extracted from the VSWR value. (i.e., using a predefined regular expression) Extract candidate values ​​from a text string that conform to a predefined numerical format, resulting in a candidate value sequence. For example, iterate through the string, extract all values ​​that satisfy the integer format, decimal format, or format with a leading decimal point, and generate a candidate value sequence according to the order in which the text is read. Optionally, an example of a regular expression is shown below:

[0061]

[0062] in, Represents a string.

[0063] In an optional embodiment, the system reverses the order of the candidate numerical sequences to obtain a sorted candidate numerical sequence. Then, based on the preset physical reasonable range thresholds of the standing wave ratio (VSWR) (lower limit), upper limit ), traverse from the beginning For each candidate value in the dataset, determine whether the candidate value falls within a preset value range (e.g., ...). Within the preset range, the first candidate value that meets the preset value range is taken as the VSWR value of the antenna under test. Optionally, if no value meets the condition after traversing the entire array, an exception capture mechanism is triggered, and a null value is returned.

[0064] By reverse traversal and combining physical boundary constraints to filter candidate values, the interference of pre-processing random characters in optical character recognition is effectively avoided, thus improving the accuracy of VSWR value recognition.

[0065] Optionally, in the method for determining antenna quality provided in this application embodiment, determining the quality judgment result of the antenna under test based on the standing wave ratio (SWR) value and a preset judgment threshold includes: comparing the SWR value with the preset judgment threshold; if the SWR value is less than or equal to the preset judgment threshold, the quality judgment result of the antenna under test is determined to be qualified; if the SWR value is greater than the preset judgment threshold, the quality judgment result of the antenna under test is determined to be unqualified.

[0066] In an optional embodiment, the system compares the standing wave ratio (SWR) value with a preset judgment threshold (e.g., 1.3). If the SWR value is less than or equal to the preset judgment threshold, the antenna impedance matching is considered good, and the system determines that the quality judgment result of the antenna under test is qualified. If the SWR value is greater than the preset judgment threshold, the antenna impedance matching is considered poor, and the system determines that the quality judgment result of the antenna under test is unqualified.

[0067] In an optional embodiment, the system transmits the extracted VSWR value to a cloud server, which then dynamically issues different pass / fail standards based on the specific device model or the current test frequency band to determine whether the value meets the standard.

[0068] In an optional embodiment, the system encapsulates the VSWR value and the determination result into structured data and outputs it externally.

[0069] The antenna quality determination method provided in this application includes the following steps: acquiring a target image corresponding to the antenna under test, wherein the target image is an image obtained after preprocessing the screen image of the VSWR tester; using a target localization model to extract and identify features based on the target image to obtain the coordinates of at least one target keyword, and determining the bounding box coordinates of the numerical region corresponding to the target keyword based on the coordinates of the target keyword and a preset spatial topology relationship, wherein the target localization model is obtained by training an initial target detection network through a sample image set, the target keyword is used to characterize the identification of the test marker point for testing the antenna under test, and the preset spatial topology relationship is used to characterize the relative positional relationship between the target keyword and the numerical region; analyzing the bounding box coordinates of the numerical region and the target image to obtain the VSWR value of the antenna under test, and determining the quality judgment result of the antenna under test based on the VSWR value and a preset judgment threshold. This solves the technical problem of low accuracy in quality judgment when using full-screen optical character recognition to determine antenna quality in related technologies.

[0070] In this solution, the screen image of the VSWR tester is acquired and preprocessed to eliminate deformation and noise interference. The target localization model trained on samples is combined with the preset spatial topology to accurately locate the test marker points and calculate the corresponding numerical region boundary box. This effectively avoids the positioning drift and confusion with other values ​​caused by blind search of the whole screen. Based on the boundary box, region analysis is performed to extract the VSWR value, and the quality judgment result is automatically determined by combining the preset judgment threshold, which improves the accuracy of data extraction and the accuracy of quality judgment.

[0071] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0072] Example 2

[0073] This application also provides an antenna quality determination apparatus. It should be noted that the antenna quality determination apparatus of this application can be used to execute the antenna quality determination method provided in this application. The antenna quality determination apparatus provided in this application will be described below.

[0074] According to an embodiment of this application, an antenna quality determination apparatus for implementing the above-described antenna quality determination method is also provided, such as... Figure 3 As shown, the device includes: an acquisition unit 301, a processing unit 302, and a determination unit 303.

[0075] The acquisition unit 301 is used to acquire the target image corresponding to the antenna under test, wherein the target image is the image obtained after preprocessing the screen image of the VSWR tester;

[0076] The processing unit 302 is used to perform feature extraction and recognition based on the target image using a target localization model to obtain the coordinates of at least one target keyword, and to determine the bounding box coordinates of the numerical region corresponding to the target keyword based on the coordinates of the target keyword and a preset spatial topology relationship. The target localization model is obtained by training an initial target detection network through a sample image set. The target keyword is used to characterize the identification of the test marker point for testing the antenna under test, and the preset spatial topology relationship is used to characterize the relative positional relationship between the target keyword and the numerical region.

[0077] The determination unit 303 is used to analyze the bounding box coordinates of the numerical region and the target image to obtain the standing wave ratio (SWR) value of the antenna under test, and to determine the quality judgment result of the antenna under test based on the SWR value and a preset judgment threshold.

[0078] Optionally, in the antenna quality determination apparatus provided in this application embodiment, the processing unit includes: a first processing subunit, used to input the target image into the target localization model, and extract multiple feature maps by multi-scale feature extraction of the target image through the first network of the detection network of the target localization model; a second processing subunit, used to perform cross-scale feature aggregation of the multiple feature maps through the second network of the detection network, and obtain a fused feature map; and a third processing subunit, used to make predictions based on the fused feature map through the third network of the detection network, and obtain the coordinates of at least one target keyword.

[0079] Optionally, in the antenna quality determination device provided in this application embodiment, the processing unit further includes: a fourth processing subunit, used to obtain preset offset parameters associated with preset spatial topology through the coordinate calculation module of the target positioning model, wherein the preset offset parameters include horizontal offset and vertical offset; a first calculation subunit, used to sum the lower right horizontal coordinate and horizontal offset contained in the coordinates of the target keyword to obtain the upper left horizontal coordinate contained in the bounding box coordinates; and a second calculation subunit, used to sum the upper left vertical coordinate and vertical offset contained in the coordinates of the target keyword to obtain the upper left vertical coordinate contained in the bounding box coordinates. The first subunit contains the top-left ordinate; the second subunit calculates the sum of the top-left x-coordinate and the preset value box width to obtain the bottom-right x-coordinate; the third subunit calculates the sum of the top-left ordinate and the preset value box height to obtain the bottom-right ordinate; the fourth subunit calculates the sum of the top-left ordinate and the preset value box height to obtain the bottom-right ordinate; and the fifth subunit processes the bounding box coordinates based on the top-left x-coordinate, top-left ordinate, bottom-right x-coordinate, and bottom-right ordinate.

[0080] Optionally, in the antenna quality determination apparatus provided in this application embodiment, the determination unit includes: a sixth processing subunit, used to crop the target image according to the bounding box coordinates of the numerical region to obtain a target region image, wherein the target region image contains the VSWR value of the antenna under test; a seventh processing subunit, used to perform optical character recognition on the target region image to obtain a text string corresponding to the target region image; and an eighth processing subunit, used to extract text based on the text string to obtain the VSWR value of the antenna under test.

[0081] Optionally, in the antenna quality determination device provided in this application embodiment, the eighth processing subunit includes: a first processing module, used to extract candidate values ​​that conform to a preset numerical format from a text string according to a preset regular expression to obtain a candidate value sequence, wherein the preset numerical format includes an integer format, a decimal format, or a format with a leading decimal point; and a second processing module, used to reverse the candidate value sequence to obtain an arranged candidate value sequence, and sequentially traverse each candidate value in the arranged candidate value sequence to determine whether the candidate value is within a preset numerical range, and take the first candidate value that meets the preset numerical range as the VSWR value of the antenna under test.

[0082] Optionally, in the antenna quality determination device provided in the embodiments of this application, the determination unit further includes: a first determination subunit, used to compare the standing wave ratio (SWR) value with a preset judgment threshold; a second determination subunit, used to determine that the quality judgment result of the antenna under test is qualified if the SWR value is less than or equal to the preset judgment threshold; and a third determination subunit, used to determine that the quality judgment result of the antenna under test is unqualified if the SWR value is greater than the preset judgment threshold.

[0083] Optionally, in the antenna quality determination device provided in the embodiments of this application, the device further includes: a preprocessing unit, used to acquire the original screen image generated when the VSWR tester tests the antenna under test before acquiring the target image corresponding to the antenna under test, and to perform image normalization scaling and Gaussian filtering noise reduction preprocessing on the original screen image to obtain the target image.

[0084] It should be noted that the acquisition unit 301, processing unit 302, and determination unit 303 mentioned above correspond to steps S201 to S203 in Embodiment 1. The three units and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0085] Example 3

[0086] Embodiments of this application may provide an electronic device. Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (Only one is shown) Processor 402, memory 404, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0087] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0088] The processor can access the information and application programs stored in the memory via a transmission device to execute the following steps: acquiring the target image corresponding to the antenna under test, wherein the target image is an image obtained after preprocessing the screen image of the VSWR tester; using a target localization model to extract and identify features based on the target image to obtain the coordinates of at least one target keyword, and determining the bounding box coordinates of the numerical region corresponding to the target keyword based on the coordinates of the target keyword and a preset spatial topology relationship, wherein the target localization model is obtained by training an initial target detection network through a sample image set, the target keyword is used to characterize the identification of the test marker point for testing the antenna under test, and the preset spatial topology relationship is used to characterize the relative positional relationship between the target keyword and the numerical region; analyzing the bounding box coordinates of the numerical region and the target image to obtain the VSWR value of the antenna under test, and determining the quality judgment result of the antenna under test based on the VSWR value and a preset judgment threshold.

[0089] The processor can access the information and application programs stored in the memory via the transmission device to perform the following steps: inputting the target image into the target localization model; extracting multiple features from the target image using the first network of the detection network of the target localization model to obtain multiple feature maps; aggregating the multiple feature maps across scales using the second network of the detection network to obtain a fused feature map; and making predictions based on the fused feature map using the third network of the detection network to obtain the coordinates of at least one target keyword.

[0090] The processor can access information and applications stored in the memory via a transmission device to execute the following steps: Obtain preset offset parameters associated with a preset spatial topology through the coordinate calculation module of the target localization model. These preset offset parameters include horizontal and vertical offsets. Summate the lower right x-coordinate and horizontal offset within the target keyword's coordinates to obtain the upper left x-coordinate within the bounding box coordinates. Summate the upper left y-coordinate and vertical offset within the target keyword's coordinates to obtain the upper left y-coordinate within the bounding box coordinates. Summate the upper left x-coordinate within the bounding box coordinates with the preset value box width to obtain the lower right x-coordinate within the bounding box coordinates. Summate the upper left y-coordinate within the bounding box coordinates with the preset value box height to obtain the lower right y-coordinate within the bounding box coordinates. Construct the bounding box coordinates based on the upper left x-coordinate, upper left y-coordinate, lower right x-coordinate, and lower right y-coordinate within the bounding box coordinates.

[0091] The processor can access the information and application program stored in the memory via the transmission device to perform the following steps: cropping the target image based on the bounding box coordinates of the numerical region to obtain a target region image, wherein the target region image contains the VSWR value of the antenna under test; performing optical character recognition on the target region image to obtain the text string corresponding to the target region image; and extracting text from the text string to obtain the VSWR value of the antenna under test.

[0092] The processor can access the information and application programs stored in the memory via the transmission device to perform the following steps: extracting candidate values ​​that conform to a preset numerical format from the text string according to a preset regular expression to obtain a candidate value sequence, wherein the preset numerical format includes integer format, decimal format, or format with leading decimal point; reversing the candidate value sequence to obtain a sorted candidate value sequence, and sequentially traversing each candidate value in the sorted candidate value sequence to determine whether the candidate value is within a preset numerical range, and taking the first candidate value that meets the preset numerical range as the VSWR value of the antenna under test.

[0093] The processor can call the information and application program stored in the memory through the transmission device to perform the following steps: compare the standing wave ratio (SWR) value with the preset judgment threshold; if the SWR value is less than or equal to the preset judgment threshold, the quality judgment result of the antenna under test is determined to be qualified; if the SWR value is greater than the preset judgment threshold, the quality judgment result of the antenna under test is determined to be unqualified.

[0094] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: before acquiring the target image corresponding to the antenna under test, acquire the original screen image generated when the VSWR tester tests the antenna under test, and perform image normalization scaling and Gaussian filtering noise reduction preprocessing on the original screen image to obtain the target image.

[0095] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 4 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.

[0096] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0097] Example 4

[0098] Embodiments of this application also provide a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the antenna quality determination method provided in Embodiment 1.

[0099] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0100] This application also provides a computer program product, which, when executed on a data processing device, is adapted to perform the steps of a method for determining antenna quality.

[0101] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0102] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of 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 displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0104] The units described as separate components may or may not be physically separate. 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 the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0105] Furthermore, the functional units in the various embodiments of this application 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.

[0106] 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, the technical solution of this application, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0107] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for determining antenna quality, characterized in that, include: Acquire the target image corresponding to the antenna under test, wherein the target image is the image obtained after preprocessing the screen image of the VSWR tester; A target localization model is used to extract and identify features from the target image to obtain the coordinates of at least one target keyword. Based on the coordinates of the target keyword and a preset spatial topology relationship, the bounding box coordinates of the numerical region corresponding to the target keyword are determined. The target localization model is obtained by training an initial target detection network through a sample image set. The target keyword is used to identify the test marker point for testing the antenna under test. The preset spatial topology relationship is used to represent the relative positional relationship between the target keyword and the numerical region. The standing wave ratio (SWR) of the antenna under test is obtained by analyzing the bounding box coordinates of the numerical region and the target image. Based on the SWR and a preset judgment threshold, the quality judgment result of the antenna under test is determined.

2. The method according to claim 1, characterized in that, The target localization model is used to extract and identify features from the target image, obtaining the coordinates of at least one target keyword, including: The target image is input into the target localization model, and the first network of the detection network of the target localization model performs multi-scale feature extraction on the target image to obtain multiple feature maps; The second network of the detection network performs cross-scale feature aggregation on the multiple feature maps to obtain a fused feature map. The coordinates of the at least one target keyword are obtained by the third network of the detection network based on the fused feature map.

3. The method according to claim 1, characterized in that, Based on the coordinates of the target keyword and a preset spatial topology, determining the bounding box coordinates of the numerical region corresponding to the target keyword includes: The preset offset parameters associated with the preset spatial topology are obtained through the coordinate calculation module of the target positioning model, wherein the preset offset parameters include horizontal offset and vertical offset. The lower right horizontal coordinate and the horizontal offset contained in the coordinates of the target keyword are summed to obtain the upper left horizontal coordinate contained in the bounding box coordinates. The top-left ordinate of the target keyword's coordinates and the vertical offset are summed to obtain the top-left ordinate of the bounding box coordinates. The upper left horizontal coordinate and the width of the preset value box contained in the bounding box coordinates are summed to obtain the lower right horizontal coordinate contained in the bounding box coordinates. The upper left corner ordinate and the preset value box height contained in the bounding box coordinates are summed to obtain the lower right corner ordinate contained in the bounding box coordinates. The bounding box coordinates are formed based on the top-left horizontal coordinate, the top-left vertical coordinate, the bottom-right horizontal coordinate, and the bottom-right vertical coordinate contained in the bounding box coordinates.

4. The method according to claim 1, characterized in that, Based on the bounding box coordinates of the numerical region and the target image, the VSWR value of the antenna under test is obtained, including: The target image is cropped based on the bounding box coordinates of the numerical region to obtain a target region image, wherein the target region image contains the VSWR value of the antenna under test; Optical character recognition is performed on the target region image to obtain the text string corresponding to the target region image; Text extraction is performed based on the text string to obtain the VSWR value of the antenna under test.

5. The method according to claim 4, characterized in that, Based on the text string, text extraction is performed to obtain the VSWR value of the antenna under test, including: Candidate values ​​that conform to a preset numerical format are extracted from the text string according to a preset regular expression to obtain a candidate numerical sequence, wherein the preset numerical format includes integer format, decimal format or format with leading decimal point; The candidate value sequence is reversed to obtain the sorted candidate value sequence. Each candidate value in the sorted candidate value sequence is traversed sequentially to determine whether the candidate value is within a preset value range. The first candidate value that meets the preset value range is taken as the VSWR value of the antenna under test.

6. The method according to claim 1, characterized in that, Based on the VSWR value and the preset judgment threshold, the quality judgment result of the antenna under test is determined as follows: The standing wave ratio (SWR) value is compared with the preset threshold value; If the standing wave ratio is less than or equal to the preset judgment threshold, the quality judgment result of the antenna under test is determined to be qualified. If the standing wave ratio (SWR) value is greater than the preset threshold, the quality judgment result of the antenna under test is determined to be unqualified.

7. The method according to claim 1, characterized in that, Before acquiring the target image corresponding to the antenna under test, the method further includes: The original screen image generated when the VSWR tester tests the antenna under test is acquired, and the original screen image is preprocessed by image normalization scaling and Gaussian filtering noise reduction to obtain the target image.

8. A device for determining antenna quality, characterized in that, include: The acquisition unit is used to acquire the target image corresponding to the antenna under test, wherein the target image is an image obtained after preprocessing the screen image of the VSWR tester; The processing unit is configured to use a target localization model to perform feature extraction and recognition based on the target image to obtain the coordinates of at least one target keyword, and determine the bounding box coordinates of the numerical region corresponding to the target keyword based on the coordinates of the target keyword and a preset spatial topology relationship. The target localization model is obtained by training an initial target detection network through a sample image set. The target keyword is used to characterize the identification of the test marker point for testing the antenna under test, and the preset spatial topology relationship is used to characterize the relative positional relationship between the target keyword and the numerical region. The determining unit is used to analyze the bounding box coordinates of the numerical region and the target image to obtain the standing wave ratio (SWR) value of the antenna under test, and to determine the quality judgment result of the antenna under test based on the SWR value and a preset judgment threshold.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the antenna quality determination method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, executes the method for determining antenna quality according to any one of claims 1 to 7.

Images