Network signal quality determination method and device and nonvolatile storage medium

Abstract

The invention discloses a network signal quality determination method and device and a nonvolatile storage medium. The method comprises the following steps: extracting a to-be-filled text from a network signal quality test image; determining a first similarity and a second similarity between the to-be-filled text and a preset field, the first similarity being a similarity between a field name of the to-be-filled text and a field name of the preset field, and the second similarity being a similarity between a field value of the to-be-filled text and a field value of the preset field; under the condition that the first similarity is greater than a first similarity threshold value or the second similarity is greater than a second similarity threshold value, determining that the to-be-filled text is a target text; and determining an evaluation result of the network signal quality according to the preset table filled with the target text. The technical problem that network signal faults cannot be found and processed in time due to the fact that the network signal quality is determined through manual testing in the related technology is solved.

Description

Technical Field

[0001] This application relates to the field of communication testing, and more specifically, to a method, apparatus, and non-volatile storage medium for determining network signal quality. Background Technology

[0002] In related technologies, network signal quality is typically determined by manual testing by testers after customers proactively report faults. The problem with this approach is that it takes time for customers to discover faults, and manually scheduling analysis and testing further delays fault diagnosis and resolution, leading to a failure to promptly detect and address network signal faults.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method, apparatus, and non-volatile storage medium for determining network signal quality, in order to at least solve the technical problem that network signal faults cannot be detected and handled in a timely manner due to the use of manual testing to determine network signal quality in related technologies.

[0005] According to one aspect of the embodiments of this application, a method for determining network signal quality is provided, comprising: extracting text to be filled from a test image of network signal quality, wherein the text to be filled includes field names and field values; determining a first similarity and a second similarity between the text to be filled and preset fields, wherein the first similarity is the similarity between the field names of the text to be filled and the field names of the preset fields, and the second similarity is the similarity between the field values ​​of the text to be filled and the field values ​​of the preset fields; confirming the text to be filled as target text if the first similarity is greater than a first similarity threshold or the second similarity is greater than a second similarity threshold; filling the target text into a preset table, and determining the evaluation result of network signal quality based on the preset table after filling in the target text.

[0006] Optionally, extracting the text to be filled from the test image of network signal quality includes: determining the grayscale image of the test image; extracting the initial text from the grayscale image; and determining the text to be filled from the initial text according to a preset text format.

[0007] Optionally, identifying and determining the text to be filled from the initial text based on the preset text format includes: determining the separator between the field name and the field value based on the preset text format; identifying and determining the text to be filled from the initial text based on the separator; determining the field name and field value of the text to be filled based on the separator between the field name and the field value of the text to be filled, and storing the field name and field value of the text to be filled respectively using a hash mapping method.

[0008] Optionally, determining the first similarity and the second similarity between the text to be filled and the preset field includes: determining the first edit distance and the second edit distance between the text to be filled and the preset field, wherein the first edit distance is the edit distance between the field name of the text to be filled and the field name of the preset field, and the second edit distance is the edit distance between the field value of the text to be filled and the field value of the preset field; determining the first similarity based on the first edit distance, and determining the second similarity based on the second edit distance.

[0009] Optionally, determining the first edit distance and the second edit distance between the text to be filled and the preset field includes: determining the importance information corresponding to the preset field, wherein the importance information includes the importance weight of each part of the characters in the field name of the preset field, and the importance weight of each part of the characters in the field value of the preset field; determining the first edit distance between the text to be filled and the field name of the preset field based on the importance weight of each part in the field name of the preset field; and determining the second edit distance between the text to be filled and the field value of the preset field based on the importance weight of each part in the field value of the preset field.

[0010] Optionally, determining the network signal quality assessment result based on the preset table after the target text is filled in includes: determining the test value of each assessment indicator in the preset table after the target text is filled in; determining the threshold corresponding to each assessment indicator; comparing the test value of the assessment indicator with the threshold corresponding to the assessment indicator, and determining the network signal quality assessment result based on the comparison result.

[0011] Optionally, the method further includes: storing the field name of the preset field and the data table number corresponding to the preset field using a hash mapping method, wherein the data table number is used to determine the preset table corresponding to the preset field.

[0012] According to another aspect of the embodiments of this application, a network signal quality determination apparatus is also provided, comprising: a first processing module, configured to extract text to be filled from a test image of network signal quality, wherein the text to be filled includes field names and field values; a second processing module, configured to determine a first similarity and a second similarity between the text to be filled and a preset field, wherein the first similarity is the similarity between the field names of the text to be filled and the field names of the preset field, and the second similarity is the similarity between the field values ​​of the text to be filled and the field values ​​of the preset field; a third processing module, configured to confirm that the text to be filled is target text if the first similarity is greater than a first similarity threshold, or the second similarity is greater than a second similarity threshold; and a fourth processing module, configured to fill the target text into a preset table, and determine the evaluation result of network signal quality based on the preset table after the target text is filled.

[0013] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, wherein a program is stored in the non-volatile storage medium, and the program controls the device where the non-volatile storage medium is located to execute a network signal quality determination method when it runs.

[0014] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program executes a network signal quality determination method when it runs.

[0015] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements a method for determining network signal quality.

[0016] In this embodiment, the method involves extracting text to be filled from a test image of network signal quality, wherein the text to be filled includes field names and field values; determining a first similarity and a second similarity between the text to be filled and preset fields, wherein the first similarity is the similarity between the field names of the text to be filled and the field names of the preset fields, and the second similarity is the similarity between the field values ​​of the text to be filled and the field values ​​of the preset fields; if the first similarity is greater than a first similarity threshold, or the second similarity is greater than a second similarity threshold, the text to be filled is confirmed as target text; the target text is filled into a preset table, and the evaluation result of network signal quality is determined based on the preset table after the target text is filled. By automatically extracting target text from the test image and filling it into a preset table, and determining the evaluation result of network signal quality based on the preset table, the purpose of automatically determining the evaluation result of network signal quality is achieved, thereby improving the technical effect of network signal fault identification efficiency. This solves the technical problem that the method of determining network signal quality by manual testing in related technologies cannot detect and handle network signal faults in a timely manner. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 This is a schematic diagram of the structure of a computer terminal (mobile device) according to an embodiment of this application;

[0019] Figure 2 This is a flowchart illustrating a method for determining network signal quality according to an embodiment of this application;

[0020] Figure 3 This is a flowchart illustrating a text extraction process according to an embodiment of this application;

[0021] Figure 4 This is a flowchart illustrating a text segmentation process according to an embodiment of this application;

[0022] Figure 5 This is a schematic diagram of an editing distance provided according to an embodiment of this application;

[0023] Figure 6 This is a schematic diagram of a target text determination process provided according to an embodiment of this application;

[0024] Figure 7 This is a flowchart illustrating a network signal quality determination process according to an embodiment of this application;

[0025] Figure 8 This is a schematic diagram of a network signal quality determination device provided according to an embodiment of this application. Detailed Implementation

[0026] 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.

[0027] 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.

[0028] To better understand the embodiments of this application, the technical terms involved in the embodiments of this application are explained below:

[0029] OCR (Optical Character Recognition) is a technology that converts printed or handwritten text from paper documents or images into machine-readable text. Through OCR technology, computers can recognize text in images and convert it into digital text that can be edited, stored, or searched. OCR has wide applications in document digitization, automated data entry, and other fields.

[0030] CRNN (Convolutional Recurrent Neural Network): It is a deep learning model that combines the advantages of convolutional neural networks (CNN) and recurrent neural networks (RNN). It is widely used in sequence data processing, especially in image recognition tasks, such as text recognition, handwritten digit recognition, and video analysis.

[0031] Levenshtein (Levenshtein Editing Distance) is an algorithm that measures the difference between two strings. Specifically, it calculates the minimum number of editing operations required to transform one string into another. It can be effectively used to measure the similarity between multiple texts, especially at the character level, providing an intuitive metric for text similarity.

[0032] Field matching technology is primarily used to compare and match information across different data sources, ensuring that data with identical or related fields can be correctly matched or compared. The core purpose of field matching technology is to compare fields in different datasets and determine, through certain rules or algorithms, whether they are identical data or have similar meanings.

[0033] Data filling refers to the process of filling in missing or incomplete data items using certain methods in data processing.

[0034] Multitext similarity refers to calculating the similarity or dissimilarity among a set of multiple texts. Its core purpose is to measure the degree of similarity between a set of texts in terms of semantics, structure, or content using a specific metric.

[0035] In related technologies, assessing the quality of network signals, such as 5G private network signals, primarily relies on private network customers proactively reporting faults and providing test analysis screenshots, followed by manual testing and analysis. This approach has several significant drawbacks:

[0036] Long response time: It takes time for customers to discover and report problems, and manual analysis and testing further delays the diagnosis and handling of faults, resulting in a long problem resolution cycle.

[0037] Limited accuracy: Manual testing may be affected by factors such as the experience of the tester and the testing environment, making it difficult to guarantee the accuracy of the judgment on signal problems.

[0038] Inefficient: It requires a large investment of manpower for testing and analysis, and it cannot monitor large-scale private network terminals in real time.

[0039] Furthermore, the application of 5G private networks requires stable network operation. Therefore, to ensure that faults are identified and responded to promptly, it is necessary to analyze and judge a large number of test screenshots from private network terminals. However, related technologies mainly rely on manual analysis of individual test screenshots, which is inefficient and prone to human error.

[0040] To address this issue, this application provides a solution that effectively extracts key text information from a large number of uploaded complex images to populate form data. Combined with the judgment of form data information, it can effectively determine whether a signal fault exists in the terminal area and monitor the real-time signal fault status of the 5G private network. This method has the advantages of automation, high accuracy, and real-time performance. Platforms using the method provided in this application automatically upload real-time signal screenshots from private network terminals, enabling them to identify signal problems quickly and improve the speed of fault diagnosis. This significantly improves fault perception and early warning capabilities, substantially reduces labor costs, decreases reliance on manual testing, and increases the automation level of signal fault diagnosis. The following is a detailed description.

[0041] According to an embodiment of this application, a method embodiment for determining network signal quality is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0042] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, or similar computing devices. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a method for determining network signal quality is shown. Figure 1As shown, the computer terminal 10 (or mobile device 10) 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.

[0043] 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).

[0044] 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 network signal 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 network signal 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 the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0045] 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.

[0046] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0047] Under the above operating environment, embodiments of this application provide a method for determining network signal quality, such as... Figure 2 As shown, the method includes the following steps:

[0048] Step S202: Extract the text to be filled from the test image of network signal quality, wherein the text to be filled includes field names and field values;

[0049] In some embodiments of this application, network signal quality test images can be collected and uploaded by a dedicated network terminal. For example, the dedicated network terminal can be configured to perform a signal test every certain period of time (e.g., 5 minutes) while in a spatial state to obtain network signal quality test images. The test image data is then uploaded to the acquisition server via a UPF platform through a data transmission module. This acquisition server can be located on an edge MEC. Idle state refers to the state when the load rate of the terminal device is lower than a preset load rate. The aforementioned test images may include screenshots of the test report.

[0050] As an optional implementation, the el-upload component from the Element library can be used in the private network terminal device to implement the image file upload function. The el-upload component converts the image into binary data and sends it to the backend via the Axios plugin. When the image is sent to the backend Spring Boot server via a POST request, the backend parses the binary data in the request body and converts it into a usable byte array according to the HTTP protocol. At this point, the image has been successfully uploaded to the specified server for subsequent recognition processing.

[0051] Alternatively, the acquisition server can preprocess the uploaded test image data, using CRNN to extract image features and classify characters, outputting text data, and finally performing post-processing operations on the text data. Post-processing operations include filtering the desired target text. Preprocessing steps include determining the grayscale image, etc.

[0052] In some embodiments of this application, extracting text to be filled from a test image of network signal quality includes: determining a grayscale image of the test image; extracting initial text from the grayscale image; and determining the text to be filled from the initial text according to a preset text format.

[0053] Optionally, determining the grayscale value of the test image can improve the accuracy of subsequent recognition. Image grayscale conversion refers to converting the original image from three channels to a single channel, transforming the original color information into individual brightness information to reduce the influence of irrelevant information in pixels. The weighted average method is the most commonly used grayscale method. The following is the formula for the weighted average method:

[0054]

[0055] Here, R, G, and B represent the values ​​of the three channels. After converting the image to a grayscale image, a threshold segmentation method is used for binarization, converting the grayscale image into a binary image with only black and white values. This is done to further highlight the character's outline and edges, facilitating subsequent character recognition.

[0056] In some embodiments of this application, a CRNN model can be used to extract text features from a grayscale image. The process of extracting text features using a CRNN model is as follows: Figure 3 As shown, the CRNN model consists of three parts: convolutional layers, recurrent layers, and transcription layers. The convolutional layers extract features from the input image, and the extracted feature sequences are fed into the recurrent layers. The recurrent layers predict the labels of the feature sequences, and finally, the transcription layers integrate the predicted feature sequence labels. By predicting the label of the sequence with the highest probability at each time step, it is converted into the final recognition result.

[0057] In some embodiments of this application, identifying and determining the text to be filled from the initial text based on the preset text format includes: determining the separator between the field name and the field value based on the preset text format; identifying and determining the text to be filled from the initial text based on the separator; determining the field name and field value of the text to be filled based on the separator between the field name and the field value of the text to be filled, and storing the field name and field value of the text to be filled respectively using a hash mapping method.

[0058] The process of identifying delimiters in each word of a text and storing the field names and values ​​separately is as follows: Figure 4 As shown. Among them. Figure 4 The i-th word in the text refers to the i-th character in the text word. Figure 4 The word length in the code refers to the total number of characters in the word. When the separator ":" is detected, the relative positions of the characters within the word and the separator determine whether they belong to the field name or the field value. For example, characters before the separator are field names, and characters after the separator are field values. Figure 4 In this context, segmentation refers to dividing the data into segments upon recognizing a colon (":") and storing the key and value separately. Key-value storage involves determining whether a segment belongs to a field name or a field value and storing them separately using a hash mapping. For image data containing objects in the format of "name:content", segmentation can be performed upon recognizing the first colon (":"), which serves as the delimiter.

[0059] Step S204: Determine the first similarity and the second similarity between the text to be filled and the preset field, wherein the first similarity is the similarity between the field name of the text to be filled and the field name of the preset field, and the second similarity is the similarity between the field value of the text to be filled and the field value of the preset field.

[0060] In some embodiments of this application, before determining the text to be filled from the test image, a hash mapping method can be used to store the field name of the preset field and the data table number corresponding to the preset field, wherein the data table number is used to determine the preset table corresponding to the preset field.

[0061] Optionally, it's necessary to establish the data information for the form fields before performing a formal text similarity comparison. This can be done using a hash map, storing the "key" as the field name and the "value" as the corresponding table number. Form fields are pre-determined fields that may need to be filled into the form.

[0062] This table stores predefined field structure information, which is a predefined key information used by the system for recognition. It provides mapping rules to translate the various "raw field names" (such as "my location") recognized by OCR into "standard field names" (such as "location") within the system.

[0063] In some embodiments of this application, determining the first similarity and the second similarity between the text to be filled and the preset field includes: determining the first edit distance and the second edit distance between the text to be filled and the preset field, wherein the first edit distance is the edit distance between the field name of the text to be filled and the field name of the preset field, and the second edit distance is the edit distance between the field value of the text to be filled and the field value of the preset field; determining the first similarity based on the first edit distance, and determining the second similarity based on the second edit distance.

[0064] As an optional implementation, determining the first edit distance and the second edit distance between the text to be filled and the preset field includes: determining the importance information corresponding to the preset field, wherein the importance information includes the importance weight of each part of the characters in the field name of the preset field, and the importance weight of each part of the characters in the field value of the preset field; determining the first edit distance between the text to be filled and the field name of the preset field based on the importance weight of each part in the field name of the preset field; and determining the second edit distance between the text to be filled and the field value of the preset field based on the importance weight of each part in the field value of the preset field.

[0065] It's important to note that because both the extracted text and the original text in the table contain many similar fields, directly calculating edit distance and then similarity may not effectively distinguish between some very similar fields. To improve the efficiency of identification and filtering, such as... Figure 5 As shown, the embodiments of this application employ a weighted method for calculating edit distance. Optionally, from Figure 5 As can be seen, if the edit distance is calculated using the standard formula "Ss-RSRP", the distance between the "Ss" and "RSRP" fields is equal, which is not the expected result. However, if the importance of "RSRP" is set to 0.7 and the importance of "Ss" is set to 0.3, the recalculated edit distance will differ due to the influence of the weights. Figure 5 For example, since "RSRP" has a higher weight, it is more important. This means that the edit distance will be greater when deleting or adding variables with higher importance. Furthermore, to store the importance of different parts of the string in different fields, some embodiments of this application also use a nested HashMap structure, where the keys store the corresponding fields and the values ​​store the importance-related content of the fields. This means that the edit distance will also be greater when adding or deleting variables with higher importance. If the similarity is greater than a certain value, it is retained, that is, the matching item (including its standardized field name and value) is added to the feature text and subsequently filled into the table.

[0066] Optionally, when calculating the similarity between two strings (e.g., comparing the OCR-recognized field "Ss-RSRP" with the preset field "RSRP"), the classic edit distance measures the difference by calculating how many "editing operations" (such as adding a character, deleting a character, or replacing a character) are required to transform one string into another. For example, the similarity between "Ss-RSRP" and "RSRP" is much higher than its similarity with "Ss".

[0067] Additionally, the comparison process can determine the table number associated with the preset fields corresponding to the target text, thus determining which table the target text should be entered into. The preset fields corresponding to the target text refer to those fields where the first similarity to the target text is greater than a first preset threshold, or the second similarity is greater than a second preset threshold.

[0068] Step S206: If the first similarity is greater than the first similarity threshold, or the second similarity is greater than the second similarity threshold, confirm that the text to be filled is the target text.

[0069] In the solution provided in step S206, such as Figure 6 As shown, the first and second similarity scores can be considered together to determine whether the text to be filled is the target text. Once identified as the target text, it will be added to the main text.

[0070] Figure 6 The i-th character in the input field represents the i-th OCR recognition result, corresponding to the i-th field in the text to be filled. The similarity of the OCR-recognized field name (i-th character) is compared with the system-preset field name (j-th character). The j-th character corresponds to the field name of the j-th preset field. Key-value comparison refers to comparing the name of the i-th text field to be filled with with the field name of the j-th preset field, using a weighted edit distance algorithm to calculate the similarity between them, which is the first similarity. When the similarity between field names is lower than a set threshold, the process continues to load the data table information corresponding to that preset field, and then compares the field value of the i-th text field to be filled with with the field value of the j-th preset field to calculate the second similarity. It should be noted that... Figure 6 The thresholds of 0.5 and 0.8 shown are only illustrative values. In actual applications, these similarity thresholds can be adjusted according to the specific scenario, and it is not necessary to use 0.5 or 0.8.

[0071] Figure 6 The feature mapping table in the context refers to the field mapping table, which is a pre-defined lookup table containing standard field names and values. Figure 6 In the process, the j-th character read is the field name of the preset field. When comparing field values ​​later, it is necessary to first load the feature mapping table and then determine the field value from the feature mapping table.

[0072] Step S208: Fill the target text into the preset table, and determine the evaluation result of the network signal quality based on the preset table after filling in the target text.

[0073] In the technical solution provided in step S208, the step of determining the evaluation result of network signal quality based on the preset table after the target text is filled in includes: determining the test value of each evaluation indicator in the preset table after the target text is filled in; determining the threshold corresponding to each evaluation indicator; comparing the test value of the evaluation indicator with the threshold corresponding to the evaluation indicator, and determining the evaluation result of network signal quality based on the comparison result.

[0074] In some embodiments of this application, when determining the evaluation result based on a preset table, if the value of the evaluation item "Network" in the table is "NR" and the value of the evaluation item "Ss-RSRP" is greater than -105, then the 5G private network signal in the terminal area is determined to be normal, and the form data is marked as a normal signal. If the value of "Network" is "LTE" or the value of "Ss-RSRP" is less than -105, then the 5G signal fault in the terminal area is determined, the form data is marked as a signal abnormality, and specific signal value data and terminal information are output to dispatch a work order to maintenance personnel for further processing.

[0075] According to embodiments of this application, a method is also provided. Figure 7 The network signal quality determination process shown includes the following steps:

[0076] S702: Signal test data upload. The private network terminal performs signal tests at regular intervals during idle time, and uploads the signal test image data to the designated acquisition server (located on the edge MEC) via the data transmission module through the UPF platform.

[0077] S704: Optical Character Recognition. The acquired signal image data is first preprocessed, then a trained model is used with CRNN to extract image features and classify characters, outputting text data. Finally, post-processing is performed on the text data.

[0078] S706: Filtering Information. After acquiring the text information from the image, it needs to be filtered because not all information needs to be entered into the form. This type of data exists in the form of "name: content". The name is the field name in this embodiment, and the content is the field value.

[0079] S708: Extracting information from multiple similar texts. Since the segmented data is not all that is desired, a method based on edit distance and common strings to determine similarity can be used to extract key text information.

[0080] S710: Information integration and population. The final result is obtained by double-comparing the "key" and "value". After some packaging and integration operations, this key information is sent to the front end for population.

[0081] S712: Signal Fault Judgment. Based on the obtained filled-in form text information, a multi-factor judgment is performed. If the signal exceeds a certain threshold range, the terminal area is considered to have an abnormal signal; if it is within the normal threshold, the terminal area is considered to have a normal signal.

[0082] By extracting text to be filled from test images of network signal quality, where the text includes field names and field values; determining a first similarity and a second similarity between the text to be filled and preset fields, where the first similarity is the similarity between the field names of the text to be filled and the field names of the preset fields, and the second similarity is the similarity between the field values ​​of the text to be filled and the field values ​​of the preset fields; confirming the text to be filled as target text if the first similarity is greater than a first similarity threshold or the second similarity is greater than a second similarity threshold; filling the target text into a preset table, and determining the network signal quality assessment result based on the preset table after filling in the target text, this method automatically extracts target text from test images, fills it into a preset table, and determines the network signal quality assessment result based on the preset table. This achieves the goal of automatically determining the network signal quality assessment result, thereby improving the technical effect of network signal fault identification efficiency and solving the technical problem of not being able to detect and handle network signal faults in a timely manner due to the use of manual testing to determine network signal quality in related technologies.

[0083] Furthermore, the network signal quality determination method provided in this application embodiment can automatically identify a large amount of terminal image test data and extract text information in a short time without manual intervention, reducing labor costs. In addition, this application embodiment uses a weighted qualitative assessment of field importance, classifying fields into importance levels during field judgment, extraction, and storage to ensure calculation accuracy and thus improve the accuracy of signal test information extraction. A multi-similarity algorithm is also introduced, performing a dual comparison from the perspectives of key (field name) and value (field), further improving the accuracy of filling signal test form field data. Moreover, the method provided in this application embodiment utilizes the high bandwidth, low latency, and massive connectivity characteristics of 5G private networks, combined with the capabilities of UPF local edge data offloading and MEC edge computing, to improve data transmission efficiency.

[0084] Compared with testing methods in related technologies, the method provided in this application has a high degree of automation and real-time performance. Especially in scenarios where a large number of 5G private network terminals are used, it can automatically extract text information from image data uploaded by a large number of terminals without manual intervention, achieving rapid early warning response. Furthermore, the accuracy of extracted text information is high, improving the efficiency of signal fault diagnosis. This enhances the reliability and stability of the 5G private network, providing better service quality for private network customers.

[0085] Regarding fault handling timeliness, the testing method relying on manual reporting + initial background identification + on-site testing in related technologies takes an average of 1-3 hours. The fully automatic real-time monitoring (polling at 5-minute intervals) + real-time analysis by machine learning model provided in this application embodiment takes an average of less than 30 seconds.

[0086] Regarding fault location efficiency, related technologies require at least three people for location communication and fault diagnosis (one for the private network customer and two engineers from the operator's front-end and back-end network optimization teams), taking an average of 2-3 hours, or even longer. Furthermore, the fault diagnosis accuracy is only around 72%. The method provided in this application, however, achieves a fault diagnosis accuracy of approximately 96.5% with an average time of less than 30 seconds.

[0087] In terms of cost, the method provided in this application can reduce the number of on-site maintenance personnel by 75%. Furthermore, in practical application, it reduces the hardware failure rate by 68%, decreases the mean time to repair (MTTR) from 4.5 hours to 18 minutes, and increases network availability from 99.5% to 99.99%.

[0088] This application provides a network signal quality determination device. Figure 8 This is a schematic diagram of the device. From Figure 8 As can be seen from the diagram, the device includes: a first processing module 80, used to extract text to be filled from a test image of network signal quality, wherein the text to be filled includes field names and field values; a second processing module 82, used to determine a first similarity and a second similarity between the text to be filled and a preset field, wherein the first similarity is the similarity between the field names of the text to be filled and the field names of the preset field, and the second similarity is the similarity between the field values ​​of the text to be filled and the field values ​​of the preset field; a third processing module 84, used to confirm that the text to be filled is the target text if the first similarity is greater than the first similarity threshold, or the second similarity is greater than the second similarity threshold; and a fourth processing module 86, used to fill the target text into a preset table, and determine the evaluation result of network signal quality based on the preset table after the target text is filled.

[0089] In some embodiments of this application, the step of the first processing module 80 extracting the text to be filled from the test image of network signal quality includes: determining the grayscale image of the test image; extracting the initial text from the grayscale image; and determining the text to be filled from the initial text according to the preset text format of the text to be filled.

[0090] In some embodiments of this application, the first processing module 80 identifies and determines the text to be filled from the initial text based on the preset text format of the text to be filled, including: determining the separator between the field name and the field value based on the preset text format; identifying and determining the text to be filled from the initial text based on the separator; determining the field name and field value of the text to be filled based on the separator between the field name and the field value of the text to be filled, and storing the field name and field value of the text to be filled respectively using a hash mapping method.

[0091] In some embodiments of this application, the network signal quality determination device is further configured to: store the field name of a preset field and the data table number corresponding to the preset field using a hash mapping method, wherein the data table number is used to determine the preset table corresponding to the preset field.

[0092] In some embodiments of this application, the step of the second processing module 82 in determining the first similarity and the second similarity between the text to be filled and the preset field includes: determining the first edit distance and the second edit distance between the text to be filled and the preset field, wherein the first edit distance is the edit distance between the field name of the text to be filled and the field name of the preset field, and the second edit distance is the edit distance between the field value of the text to be filled and the field value of the preset field; determining the first similarity based on the first edit distance, and determining the second similarity based on the second edit distance.

[0093] In some embodiments of this application, the steps of the second processing module 82 in determining the first edit distance and the second edit distance between the text to be filled and the preset field include: determining the importance information corresponding to the preset field, wherein the importance information includes the importance weight of each part of the characters in the field name of the preset field and the importance weight of each part of the characters in the field value of the preset field; determining the first edit distance between the text to be filled and the field name of the preset field based on the importance weight of each part in the field name of the preset field; and determining the second edit distance between the text to be filled and the field value of the preset field based on the importance weight of each part in the field value of the preset field.

[0094] In some embodiments of this application, the step of the fourth processing module 86 determining the evaluation result of network signal quality based on the preset table after the target text is filled in includes: determining the test value of each evaluation indicator in the preset table after the target text is filled in; determining the threshold corresponding to each evaluation indicator; comparing the test value of the evaluation indicator with the threshold corresponding to the evaluation indicator, and determining the evaluation result of network signal quality based on the comparison result.

[0095] It should be noted that each module in the above-mentioned network signal quality determination device can be a program module (for example, a set of program instructions to implement a certain function) or a hardware module. For the latter, it can be manifested in the following forms, but is not limited to them: each of the above modules is manifested as a processor, or the functions of each of the above modules are implemented by a processor.

[0096] According to an embodiment of this application, a non-volatile storage medium is also provided, which stores a program. When the program runs, it controls the device containing the non-volatile storage medium to execute the following network signal quality determination method: extracting text to be filled from a network signal quality test image, wherein the text to be filled includes field names and field values; determining a first similarity and a second similarity between the text to be filled and preset fields, wherein the first similarity is the similarity between the field names of the text to be filled and the field names of the preset fields, and the second similarity is the similarity between the field values ​​of the text to be filled and the field values ​​of the preset fields; confirming the text to be filled as target text if the first similarity is greater than a first similarity threshold or the second similarity is greater than a second similarity threshold; filling the target text into a preset table, and determining the network signal quality evaluation result based on the preset table after filling in the target text.

[0097] According to an embodiment of this application, an electronic device is also provided, including a memory and a processor. The processor is used to run a program stored in the memory, wherein the program executes the following network signal quality determination method: extracting text to be filled from a test image of network signal quality, wherein the text to be filled includes field names and field values; determining a first similarity and a second similarity between the text to be filled and preset fields, wherein the first similarity is the similarity between the field names of the text to be filled and the field names of the preset fields, and the second similarity is the similarity between the field values ​​of the text to be filled and the field values ​​of the preset fields; confirming the text to be filled as target text if the first similarity is greater than a first similarity threshold or the second similarity is greater than a second similarity threshold; filling the target text into a preset table, and determining the evaluation result of network signal quality based on the preset table after filling in the target text.

[0098] According to an embodiment of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the following method for determining network signal quality: extracting text to be filled from a test image of network signal quality, wherein the text to be filled includes field names and field values; determining a first similarity and a second similarity between the text to be filled and preset fields, wherein the first similarity is the similarity between the field names of the text to be filled and the field names of the preset fields, and the second similarity is the similarity between the field values ​​of the text to be filled and the field values ​​of the preset fields; confirming the text to be filled as target text if the first similarity is greater than a first similarity threshold or the second similarity is greater than a second similarity threshold; filling the target text into a preset table, and determining the evaluation result of network signal quality based on the preset table after filling in the target text.

[0099] 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.

[0100] 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 can be a logical functional division, and in actual implementation, there may be other division methods. For instance, 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.

[0101] 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0102] 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.

[0103] 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 related technologies, 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 USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0104] 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 network signal quality, characterized in that, include: Extract the text to be filled from the test image of network signal quality, wherein the text to be filled includes field names and field values; Determine a first similarity and a second similarity between the text to be filled and a preset field, wherein the first similarity is the similarity between the field name of the text to be filled and the field name of the preset field, and the second similarity is the similarity between the field value of the text to be filled and the field value of the preset field; If the first similarity is greater than the first similarity threshold, or the second similarity is greater than the second similarity threshold, then the text to be filled in is confirmed as the target text. The target text is filled into a preset table, and the evaluation result of the network signal quality is determined based on the preset table after the target text is filled in.

2. The method for determining network signal quality according to claim 1, characterized in that, The text to be filled in is extracted from the test image of network signal quality, including: Determine the grayscale image of the test image; Extract the initial text from the grayscale image; The text to be filled is determined from the initial text according to the preset text format of the text to be filled.

3. The method for determining network signal quality according to claim 2, characterized in that, Identifying and determining the text to be filled from the initial text according to the preset text format includes: The separator between the field name and the field value is determined according to the preset text format; The text to be filled is identified and determined from the initial text based on the delimiter; Based on the separator between the field name and the field value of the text to be filled, the field name and field value of the text to be filled are determined, and the field name and field value of the text to be filled are stored respectively using a hash mapping method.

4. The method for determining network signal quality according to claim 1, characterized in that, Determining the first similarity and second similarity between the text to be filled and the preset field includes: Determine a first edit distance and a second edit distance between the text to be filled and the preset field, wherein the first edit distance is the edit distance between the field name of the text to be filled and the field name of the preset field, and the second edit distance is the edit distance between the field value of the text to be filled and the field value of the preset field; The first similarity is determined based on the first edit distance, and the second similarity is determined based on the second edit distance.

5. The method for determining network signal quality according to claim 4, characterized in that, Determining the first edit distance and the second edit distance between the text to be filled and the preset field includes: Determine the importance information corresponding to the preset field, wherein the importance information includes the importance weight of each part of the characters in the field name of the preset field, and the importance weight of each part of the characters in the field value of the preset field; Based on the importance weight of each part in the field name of the preset field, a first edit distance is determined between the text to be filled and the field name of the preset field; Based on the importance weights of each part of the field value of the preset field, a second edit distance is determined between the text to be filled and the field value of the preset field.

6. The method for determining network signal quality according to claim 1, characterized in that, The evaluation results of network signal quality, determined based on the preset table after the target text is entered, include: Determine the test values ​​of each evaluation indicator in the preset table after the target text is filled in; Determine the threshold values ​​corresponding to each of the aforementioned evaluation indicators; The test values ​​of the evaluation indicators and the thresholds corresponding to the evaluation indicators are compared respectively, and the evaluation result of the network signal quality is determined based on the comparison results.

7. The method for determining network signal quality according to claim 1, characterized in that, The method further includes: The field name of the preset field and the data table number corresponding to the preset field are stored using a hash mapping method, wherein the data table number is used to determine the preset table corresponding to the preset field.

8. A network signal quality determination device, characterized in that, include: The first processing module is used to extract text to be filled from a test image of network signal quality, wherein the text to be filled includes field names and field values; The second processing module is used to determine a first similarity and a second similarity between the text to be filled and a preset field, wherein the first similarity is the similarity between the field name of the text to be filled and the field name of the preset field, and the second similarity is the similarity between the field value of the text to be filled and the field value of the preset field. The third processing module is used to confirm that the text to be filled is the target text when the first similarity is greater than the first similarity threshold or the second similarity is greater than the second similarity threshold. The fourth processing module is used to fill the target text into a preset table and determine the evaluation result of the network signal quality based on the preset table after the target text is filled in.

9. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores a program, wherein when the program is executed, it controls the device containing the non-volatile storage medium to execute the network signal quality determination method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, include: A memory and a processor, the processor being configured to run a program stored in the memory, wherein the program, when running, executes the network signal quality determination method according to any one of claims 1 to 7.

11. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the network signal quality determination method according to any one of claims 1 to 7.

Images