Mobile phone data line detection and analysis system

Abstract

The invention discloses a mobile phone data line detection and analysis system, which relates to the technical field of data line detection and is characterized in that a suitable high-speed transmission test environment is created for a data line through a test environment construction module, and signal quality is monitored by equipment such as an oscilloscope and a signal analyzer; the data monitoring module detects a signal transmission bit error rate amplification index and a delay fluctuation index in real time in an environment with or without electromagnetic interference; the data analysis module converts the detection data into a comprehensive feature vector and inputs the comprehensive feature vector into a machine learning model to generate a signal quality index; the comparative analysis module compares the signal quality index with a set threshold value and divides the quality of the data line; and the optimization module predicts the abnormal degree of the low-quality data line, and if the abnormal degree is serious, optimization measures are taken, so that the anti-interference performance of the data line is effectively improved, the error rate and delay fluctuation in the data transmission process are remarkably reduced, and reliable communication and data integrity between equipment are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of data line detection, and in particular to a mobile phone data line detection and analysis system. Background Art

[0002] Mobile phone data cable detection and analysis refers to the process of testing and evaluating the function, performance and quality of mobile phone data cables. Through this detection and analysis, it is possible to determine whether the data cable can transmit data normally, whether the charging is stable, whether the connection is reliable, and whether the durability and anti-interference ability of the data cable can be evaluated. These tests usually cover electrical performance tests, signal quality tests, mechanical strength tests, etc., to ensure that the data cable can provide a good user experience in daily use. In addition, mobile phone data cable detection and analysis may also involve the evaluation of its design, materials and manufacturing processes. For example, check whether the cable insulation layer of the data cable is durable enough and whether the connector meets the standards to avoid damage caused by frequent plugging and unplugging or external force. Through this comprehensive detection, manufacturers can optimize their designs, improve product quality, and help consumers choose more reliable mobile phone data cables.

[0003] The prior art has the following deficiencies:

[0004] Some substandard connector designs may not have effective electromagnetic interference (EMI) shielding, especially during high-speed data transmission. In this case, when the data line is transmitting data, the magnetic field of the external environment or the interference generated by the device may affect the signal quality, resulting in data loss, transmission errors, or even device system crashes. At the same time, this signal interference may cause data transmission failures, file corruption, or serious communication errors between electronic devices, affecting the normal operation of the device, and in severe cases, may cause system crashes or equipment repairs. Summary of the invention

[0005] The purpose of the present invention is to provide a mobile phone data line detection and analysis system to solve the shortcomings of the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solutions: a mobile phone data line detection and analysis system, including a test environment construction module, a data monitoring module, a data analysis module, a comparison and analysis module and an optimization module;

[0007] The test environment construction module is used to build a test environment for data transmission over a mobile phone data line and select test equipment that can perform high-speed data transmission and is equipped with corresponding interference detection functions. The test equipment includes an oscilloscope, a signal analyzer, and a data transmission test platform.

[0008] The data monitoring module is used to conduct tests under external electromagnetic interference sources and non-interference environments respectively, connect the data line to the computer and perform high-speed data transmission, and use an oscilloscope and a signal analyzer to monitor the signal quality data in real time. The signal quality data includes the signal transmission bit error rate increase index and the signal transmission delay fluctuation index;

[0009] A data analysis module is used to convert the signal transmission bit error rate increase index and the signal transmission delay fluctuation index into a comprehensive feature vector as an input item of the machine learning model, and obtain the signal quality index of the data line during high-speed data transmission after training the model;

[0010] A comparison and analysis module, used to compare and analyze the signal quality index of the data line obtained during the high-speed data transmission process with a preset quality threshold, and divide the data line into a high-quality signal data line and a low-quality signal data line according to the analysis result;

[0011] The optimization module recommends that high-quality signal data lines continue to be used; for low-quality signal data lines, the abnormality of their signal quality during high-speed data transmission is further predicted. If the abnormality is high, corresponding optimization measures are taken immediately.

[0012] Preferably, in the data monitoring module, the signal quality data includes a signal transmission bit error rate increase index, and the method for obtaining the signal transmission bit error rate increase index is:

[0013] In signal transmission, the relationship between the bit error rate BER and the signal-to-noise ratio SNR is: Among them, B is the function term, M is the order of the modulation method, and a bit error rate sequence is constructed. The bit error rate sequence is expressed as {BER i}; where i represents the bit error rate value measured for the i-th time. For the calculation of the bit error rate increase index, the likelihood function is expressed as: Among them, P(BER i |θ) represents the bit error rate BER obtained in the i-th experiment under the given parameter θ i The probability of , in order to simplify the calculation, use the log-likelihood function lnL(θ), the expression:

[0014] The core task of maximum likelihood estimation is to find the optimal parameter θ* to maximize the log-likelihood function: After obtaining the optimal parameters, the bit error rate BER0 under interference-free conditions is calculated, and the bit error rate BER1 under interference conditions is calculated, that is, the bit error rate measured in an environment containing factors such as electromagnetic interference, and the signal transmission bit error rate increase index is calculated. The expression is: Where MK is the signal transmission bit error rate increase index.

[0015] Preferably, the signal quality data includes a signal transmission delay fluctuation index, and the method for obtaining the signal transmission delay fluctuation index is:

[0016] Collect delay data during signal transmission. Delay data refers to the transmission delay L(t) of the signal at each time point t. The collected delay data is {(t1,L1),(t2,L2),...,(t n ,L n )}, where t n It's time, L n is the signal delay at the corresponding time point; in Gaussian process regression, the kernel function determines the similarity between input data points. The kernel function is used to measure the similarity between different time points t i and t j Based on the selected kernel function, the covariance matrix K between the delayed data points is calculated: Among them, k(t n ,t n ) is the covariance value calculated by the kernel function. If the signal delay data is affected by noise, the noise term needs to be added The expression is: Where I is the unit matrix. Through Gaussian process regression, the predicted value of the delay data is obtained. The new time point is predicted to obtain its corresponding delay value. Input X = {t1, t2, ..., t n}, output y = {L1, L2, ..., L n}; Prediction data: prediction point t * ; Calculate the covariance matrix: K(X,X) is the covariance matrix between the training data, K(X,t * ) is the covariance matrix between the training data and the prediction points, K(t * ,t * ) is the covariance matrix between the prediction points, and the prediction mean μ * is: μ * =K(t * ,X)K(X,X) -1 y; prediction variance for: The standard deviation of the signal is extracted from the prediction variance, and the standard deviation of the delay fluctuation calculated at several time points is weighted averaged to obtain the signal transmission delay fluctuation index.

[0017] Preferably, in the data analysis module, the signal transmission error rate increase index and the signal transmission delay fluctuation index are converted into a comprehensive feature vector, and the comprehensive feature vector is used as the input of the machine learning model. The machine learning model takes predicting the signal quality index label of the data line during high-speed data transmission for each group of comprehensive feature vectors as the prediction target, and minimizing the sum of the prediction errors of the signal quality index labels of all data lines during high-speed data transmission as the training target. The machine learning model is trained until the sum of the prediction errors converges and then the model training is stopped. The signal quality index of the data line during high-speed data transmission is determined according to the model output result, where the machine learning model is a polynomial regression model.

[0018] Preferably, in the comparative analysis module, the signal quality index of the data line obtained during high-speed data transmission is compared with a pre-set quality threshold. If the signal quality index of the data line during high-speed data transmission is greater than or equal to the pre-set quality threshold, it indicates that the signal quality of the data line during high-speed data transmission is high and the data transmission is stable. At this time, no warning signal is generated, and the corresponding data line is classified as a high-quality signal data line. If the signal quality index of the data line during high-speed data transmission is less than the pre-set quality threshold, it indicates that the signal quality of the data line during high-speed data transmission is low and the data transmission is unstable. At this time, a warning signal is generated, and the corresponding data line is classified as a low-quality signal data line.

[0019] Preferably, in the optimization module, the signal quality abnormality degree is marked as E, and the calculation expression is: When Q < T, E is a positive value, and the larger the value, the higher the signal quality abnormality degree. Set a high abnormality threshold Ecritical and a low abnormality threshold Elow. Predict and classify the signal quality abnormality degree E. If E < Elow, the abnormality degree is low, and no immediate optimization is required, but close monitoring is needed. If Elow ≤ E < Ecritical, the abnormality degree is medium, and optimization or replacement is carried out. If E ≥ Ecritical, the abnormality degree is high, and immediate optimization measures should be taken.

[0020] Preferably, in the case of a high abnormality degree, optimization measures are taken to improve the signal quality index Q by improving the signal transmission error rate increase index MK and the signal transmission delay fluctuation index LH. A new signal quality index Q′ is obtained through adjustment, and the expression is: Q′ = f(MK′, LH′); where MK′ = MK - ΔMK; MK′ is the optimized error rate increase index, and ΔMK represents the improvement amplitude; LH′ = LH - ΔLH; LH′ is the optimized delay fluctuation index, and ΔLH represents the improvement amplitude; f is the output function of the polynomial regression model. After optimization, calculate the new abnormality degree E′, and the expression is: If E′ < Elow, the optimization measure is effective and the data cable can continue to be used; if E ≥ Ecritical, further optimization or replacement of the data cable is required.

[0021] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0022] 1. Through the collaborative work of the test environment construction, data monitoring, data analysis, comparative analysis, and optimization modules, the present invention uses precise test equipment (such as oscilloscopes and signal analyzers) to monitor signal quality, generates the increase index of signal transmission bit error rate and the delay fluctuation index, and analyzes and predicts the signal quality index through a machine learning model, providing a scientific and reliable evaluation of the quality of the data cable.

[0023] 2. The present invention can not only automatically distinguish high-quality and low-quality data cables, classify and judge the signal abnormality degree of low-quality data cables, but also take optimization measures in a timely manner when the abnormality degree is high, and improve the signal quality index by improving the increase index of bit error rate and the delay fluctuation index. After the system is optimized, the optimization effect is re-evaluated to ensure the stability and anti-interference ability of the data cable in actual applications. Through these precise analysis and optimization processes, the present invention significantly improves the signal stability and data integrity of the data cable in high-speed transmission, reduces the risk of equipment failure, and provides a more reliable transmission solution for users. Brief Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0025] Figure 1 It is the system module diagram of the present invention. Detailed Embodiments

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0027] Embodiment, please refer to Figure 1 As shown, the mobile phone data cable detection and analysis system described in this embodiment includes a test environment construction module, a data monitoring module, a data analysis module, a comparative analysis module, and an optimization module;

[0028] The test environment construction module is used to build a test environment for data transmission over a mobile phone data line and select test equipment that can perform high-speed data transmission and is equipped with corresponding interference detection functions. The test equipment includes an oscilloscope, a signal analyzer, and a data transmission test platform.

[0029] The data monitoring module is used to conduct tests under external electromagnetic interference sources and non-interference environments respectively, connect the data line to the computer and perform high-speed data transmission, and use an oscilloscope and a signal analyzer to monitor the signal quality data in real time. The signal quality data includes the signal transmission bit error rate increase index and the signal transmission delay fluctuation index;

[0030] A data analysis module is used to convert the signal transmission bit error rate increase index and the signal transmission delay fluctuation index into a comprehensive feature vector as an input item of the machine learning model, and obtain the signal quality index of the data line during high-speed data transmission after training the model;

[0031] A comparison and analysis module, used to compare and analyze the signal quality index of the data line obtained during the high-speed data transmission process with a preset quality threshold, and divide the data line into a high-quality signal data line and a low-quality signal data line according to the analysis result;

[0032] The optimization module recommends that high-quality signal data lines continue to be used; for low-quality signal data lines, the abnormality of their signal quality during high-speed data transmission is further predicted. If the abnormality is high, corresponding optimization measures are taken immediately.

[0033] In the test environment construction module, the main goal of the test environment construction is to provide a test environment that can simulate real usage scenarios for mobile phone data lines during high-speed data transmission, and to be equipped with appropriate test equipment. These test equipment will be used to detect signal quality problems that may occur during data transmission, including the impact of external electromagnetic interference (EMI) and other environmental factors on the signal.

[0034] Choose a laboratory environment with good electromagnetic compatibility (EMC) control to reduce unnecessary external electromagnetic interference and ensure the normal operation of the equipment. For the comprehensiveness of the test, ensure that the test environment can simulate electromagnetic interference with different strengths and directions. This means that in the test, not only the ideal situation without interference should be considered, but also the interference factors that may be encountered in the actual use environment (for example: home appliances, wireless devices, mobile phones, etc.) should be introduced.

[0035] In order to test the transmission quality of data lines in different interference environments, the test environment needs to include equipment or systems that can cause electromagnetic interference. For example: High-frequency signal generator: used to simulate interference signal sources, such as simulating the signal frequency of Wi-Fi routers or mobile phones. Electromagnetic field generator: simulates the impact of external strong magnetic fields on signal transmission, helping to evaluate the performance of data lines in real life. Controllable noise sources: such as wireless devices, LED lighting, etc., can generate electromagnetic noise of specific frequencies, affecting the data transmission process.

[0036] High-speed data transmission platform: In order to test the performance of the data line during high-speed data transmission, it is necessary to select a suitable data transmission protocol and platform. For example: USB 3.0 / 3.1: supports high-speed data transmission and is widely used for data transmission between smartphones and other devices. Thunderbolt 3 or 4: used for higher-speed data transmission, especially when large bandwidth is required (such as video streaming, large file transfer). PCIe (high-speed bus): For special application scenarios, PCIe can be used as a high-speed data transmission standard. Selecting a data transmission platform that meets the test requirements can ensure the authenticity and comprehensiveness of the test and simulate different transmission rates and workloads.

[0037] The equipment in the test environment needs to be able to detect the performance of the data line during high-speed transmission, including key parameters such as electromagnetic interference, bit error rate, signal attenuation, and delay. The oscilloscope is used to monitor and analyze the voltage waveform during data line transmission and check the integrity of the signal. Signal quality monitoring: Use the oscilloscope to observe the voltage waveform during data transmission in real time to check whether the signal is distorted or attenuated. Waveform analysis: Monitor the changes in the signal under external electromagnetic interference and analyze the distortion caused by interference. Bit error rate analysis: By capturing the waveform during data transmission and combining it with error bit rate analysis, it helps identify bit errors or data loss in data transmission.

[0038] Signal analyzers can analyze the spectrum of signals and are particularly suitable for detecting noise or interference in high-frequency signals. Spectrum analysis: monitors possible frequency interference in the signal and identifies the impact of external noise sources on the signal. Signal integrity analysis: analyzes the time domain and frequency domain characteristics of the signal to ensure that the signal transmission is not subject to unnecessary interference. EMI (electromagnetic interference) test: detects electromagnetic emissions from data lines during transmission and determines whether they meet standards to avoid electromagnetic pollution or distortion.

[0039] The data transmission test platform is used to simulate high-speed data transmission, providing the same data volume and transmission speed as the actual use environment, so as to analyze the performance of the data line under actual working conditions. High-speed data transmission simulation: By simulating large file transfer, video streaming or other high-bandwidth transmission tasks, test whether the data line is stable during high-speed transmission. Load test: Test the performance of the data line under different loads (such as different file sizes, different data rates, etc.) to check whether it can continuously and stably transmit data. Environmental simulation: The test platform can be adjusted as needed to simulate different environmental conditions, such as different signal frequencies, transmission rates, etc.

[0040] The data monitoring module is used to perform tests under external electromagnetic interference sources and non-interference environments respectively, connect the data line to the computer and perform high-speed data transmission, and use an oscilloscope and signal analyzer to monitor the signal quality data in real time. The signal quality data includes the signal transmission bit error rate increase index and the signal transmission delay fluctuation index.

[0041] Perform a benchmark test without external electromagnetic interference. Use an oscilloscope to monitor the waveform of data transmission in real time to ensure that the signal is clear and undistorted. Use a signal analyzer to check the spectrum of the signal to ensure that the signal frequency is stable and free of additional noise.

[0042] Add interference sources such as high-frequency signal generators and electromagnetic field generators to the test environment. Measure data such as bit error rate increase and delay fluctuation during data transmission to evaluate the impact of interference on signal quality. Use a signal analyzer to perform interference analysis on the signal spectrum to identify interference sources generated by external devices or environments.

[0043] Expose the data line to electromagnetic interference sources in different directions to evaluate the impact of interference in different directions on signal transmission. Use an oscilloscope and signal analyzer to analyze indicators such as signal attenuation and delay fluctuation to simulate different interference situations that the device may encounter in actual use.

[0044] All test data is recorded in real time through oscilloscopes, signal analyzers and other equipment. In all test environments, the signal quality, bit error rate, delay and other indicators of the data line are sorted and summarized for subsequent analysis. The test results are evaluated according to the preset quality threshold to determine the signal quality of the data line in different environments and whether it meets the standards.

[0045] Connect the data cable to the computer and start the high-speed data transfer task. Ensure that the test environment can simulate the actual usage scenario and the transferred data can represent the normal workload, such as large file transfer, high-speed data flow, etc. Connect one end of the data cable of the mobile phone to be tested to the USB port or other applicable high-speed data port (such as Thunderbolt port) of the computer, and the other end to the device (such as smartphone, external hard disk, etc.) for data transfer. Ensure that the computer has an interface that supports high-speed data transfer (such as USB 3.0 / 3.1, Thunderbolt, etc.). If you need to transfer specific types of data (such as high-definition video, compressed files, operating system images, etc.), prepare the relevant test files in advance. If you use a dedicated test platform (for example, USB data transfer test platform), ensure that the device is properly configured and can handle the requirements of high-bandwidth data transfer.

[0046] Start file transfer. The data can be high-load, large file data (such as high-definition video files, program packages, etc.) to simulate real transmission scenarios. At this time, the data line will bear a large amount of data exchange tasks between devices. Confirm the relevant parameters of data transmission, such as transmission rate, file size, transmission time, etc., so as to evaluate the signal quality later.

[0047] During data transmission, an oscilloscope and signal analyzer are used to monitor the signal quality in real time to detect problems such as signal attenuation, noise interference, bit error rate, etc., in order to evaluate the performance of the data line in high-speed transmission.

[0048] The main function of the oscilloscope is to monitor the voltage waveform in real time during the transmission process, capture the changes in the signal, and identify problems such as signal distortion and noise. The steps of the oscilloscope are as follows:

[0049] Set the oscilloscope parameters: Time base: Set an appropriate time base (for example, in ns or μs) to ensure that the detailed changes in the data transmission process can be captured. Trigger setting: Ensure that the waveform is displayed stably at the beginning of data transmission through trigger setting to avoid missing signal fluctuations at critical moments. Voltage range: Set an appropriate voltage range to ensure that the signal waveform does not exceed the measurement range of the oscilloscope.

[0050] Capture signal waveform: Observe the signal waveform during data transmission to ensure that the signal waveform is clear and without serious distortion. Compare the waveform during data transmission with the expected ideal waveform to detect whether there is significant noise, waveform distortion or attenuation.

[0051] Signal distortion analysis: Use an oscilloscope to detect the degree of signal distortion and observe whether the waveform has excessive offset or noise. For example, if the shielding in the data line is poor, it may cause signal interference and waveform distortion.

[0052] Bit error rate detection: Use an oscilloscope to observe the voltage waveform during the transmission process, and find the wrong transmission moment on the waveform (for example, the data packet does not reach the destination correctly). By comparing it with the data transmission results on the computer side, the bit error rate is calculated.

[0053] Signal analyzers are mainly used to analyze the frequency characteristics of signals and identify noise, interference and other problems in the signals. The steps are as follows:

[0054] Use a signal analyzer to perform spectrum analysis on the transmitted signal to view the frequency distribution of the signal. Monitor whether the signal is affected by external electromagnetic interference (EMI) and detect possible spurious frequencies in the spectrum. By observing the noise in different frequency bands, you can find out the impact of electromagnetic interference on signal quality.

[0055] If external electromagnetic interference sources (such as wireless devices, home appliances, etc.) may affect signal transmission, a signal analyzer can help identify the location and frequency of the signal interference source. During the test, additional interference frequencies may appear, causing the signal spectrum to be deformed or the signal quality to degrade.

[0056] Signal analyzers can help assess the integrity of a signal and determine if the signal has been severely affected by attenuation or noise during transmission. In an environment with interference, a signal analyzer can show the data line's ability to resist interference, such as excessive signal loss or frequency distortion.

[0057] Use an oscilloscope and signal analyzer to capture signal quality data and record key indicators such as bit error rate, signal distortion, and interference frequency. Collect performance indicators during transmission, such as transmission rate, delay, and throughput, through a data transmission test platform or computer system. Compare the actual measured signal quality data with the data under ideal transmission conditions to evaluate the performance of the data line under different conditions. By analyzing these signal quality data (such as bit error rate, signal strength, noise ratio, etc.), potential performance bottlenecks can be identified.

[0058] The signal quality data includes a signal transmission bit error rate increase index, and the method for obtaining the signal transmission bit error rate increase index is as follows:

[0059] The bit error rate is a function based on the signal-to-noise ratio and other factors (such as electromagnetic interference). In signal transmission, the relationship between the bit error rate BER and the signal-to-noise ratio SNR is: Where B is the function term and M is the order of the modulation method (such as BPSK, QPSK, etc.). Construct a bit error rate sequence, which is expressed as: {BER i}; where i represents the bit error rate value measured for the i-th time. For the calculation of the bit error rate increase index, the likelihood function can be expressed as: Among them, P(BERi |θ) represents the bit error rate BER obtained in the i-th experiment under the given parameter θ i The parameter θ usually involves factors such as the signal SNR and interference strength. To simplify the calculation, the log-likelihood function lnL(θ) is used, and the expression is: By log-transforming, the likelihood function becomes more tractable, especially when data from multiple experiments are involved.

[0060] The core task of maximum likelihood estimation is to find the optimal parameter θ* to maximize the log-likelihood function: After obtaining the optimal parameters, the bit error rate BER0 under interference-free conditions is calculated, and the bit error rate BER1 under interference conditions is calculated, that is, the bit error rate measured in an environment containing factors such as electromagnetic interference, and the signal transmission bit error rate increase index is calculated. The expression is: Where MK is the signal transmission bit error rate increase index.

[0061] The larger the signal transmission bit error rate increase index, the worse the signal quality of the data line during high-speed data transmission. When the bit error rate increase index is large, it means that after being affected by interference or noise, the transmission quality of the data line has been significantly reduced, and the proportion of error bits has increased. This usually indicates that the data line cannot effectively maintain the integrity of the data when facing factors such as electromagnetic interference (EMI) and signal attenuation. In high-speed data transmission, a large signal transmission bit error rate increase index may cause frequent transmission errors, packet loss or severe delays, ultimately affecting the communication stability between devices. Therefore, a large signal transmission bit error rate increase index is a sign of poor signal quality, low transmission efficiency, and high error rate.

[0062] The smaller the signal transmission bit error rate increase index, the better the signal quality of the data line during high-speed data transmission. Conversely, a smaller bit error rate increase index indicates that the data line can maintain higher stability and lower error rate during transmission. Even in the presence of external interference or noise, the loss of signal quality is relatively small, and the increase in bit error rate is limited. This generally means that the data line has a strong anti-interference ability and can maintain high transmission efficiency and accuracy in high-speed data transmission. For high-frequency and high-speed data transmission tasks, a smaller signal transmission bit error rate increase index helps reduce data loss, improve system response speed, and reduce the probability of equipment failure or maintenance. Therefore, when the signal transmission bit error rate increase index is small, the signal quality of the data line is better, and the transmission process is more stable and reliable.

[0063] The signal quality data includes a signal transmission delay fluctuation index, and the method for obtaining the signal transmission delay fluctuation index is as follows:

[0064] Collect delay data during signal transmission. Delay data refers to the transmission delay L(t) of the signal at each time point t, which is monitored in real time by speed measurement tools (such as oscilloscopes and signal analyzers). The collected delay data is {(t1, L1), (t2, L2), ..., (t n ,L n )}, where t n It's time, L n is the signal delay at the corresponding time point; in Gaussian process regression, the kernel function determines the similarity between input data points. The kernel function is used to measure the similarity between different time points t i and t j The common kernel functions include: square exponential kernel and Mattern kernel. After selecting a suitable kernel function, it will be used to calculate the covariance matrix between the input data points. According to the selected kernel function, the covariance matrix K between the delayed data points is calculated: Among them, k(t n ,t n ) is the covariance value calculated by the kernel function. If the signal delay data is affected by noise, the noise term needs to be added The expression is: Where I is the unit matrix. Through Gaussian process regression, the predicted value of the delay data is obtained. The new time point is predicted to obtain its corresponding delay value. Input X = {t1, t2, ..., t n}, output y = {L1, L2, ..., L n}; Prediction data: prediction point t * . Calculate the covariance matrix: K(X,X) is the covariance matrix between the training data. K(X,t * ) is the covariance matrix between the training data and the prediction points. K(t * ,t * ) is the covariance matrix between the prediction points. The predicted mean μ * is: μ * =K(t * ,X)K(X,X) -1 y; prediction variance for: The standard deviation of the signal is extracted from the prediction variance, and the standard deviation of the delay fluctuation calculated at several time points is weighted averaged to obtain the signal transmission delay fluctuation index.

[0065] The larger the signal transmission delay fluctuation index, the worse the signal quality of the data line during high-speed data transmission. When the delay fluctuation index is large, it means that the signal has experienced large delay fluctuations during transmission, which means that unstable delay changes have occurred during data transmission. This fluctuation may be caused by factors such as electromagnetic interference, insufficient device performance, network congestion, or signal attenuation. A high fluctuation index usually causes data packets to be out of order, transmitted incorrectly or lost, and may cause communication failures between devices. As the delay fluctuation increases, the data transmission stability deteriorates, resulting in untimely system response or unpredictable delays, which is particularly dangerous for data transmission systems with high frequency and high bandwidth requirements, and may cause system crashes, data corruption, and even equipment damage.

[0066] The smaller the signal transmission delay fluctuation index, the better the signal quality of the data line during high-speed data transmission. A smaller delay fluctuation index means that the delay changes less during signal transmission and the transmission process is relatively stable. This means that the data line can maintain stable delay characteristics during high-speed data transmission, and data can be transmitted at a more uniform rate, reducing signal distortion or errors caused by delay fluctuations. A low fluctuation index usually reflects high-quality signal transmission, which can improve the reliability and response speed of the system. Especially in application scenarios that require high-precision data transmission, smaller delay fluctuations can significantly improve user experience and overall device performance.

[0067] The data analysis module is used to convert the signal transmission bit error rate increase index and the signal transmission delay fluctuation index into a comprehensive feature vector as the input of the machine learning model. After training the model, the signal quality index of the data line during high-speed data transmission is obtained.

[0068] The signal transmission bit error rate increase index and the signal transmission delay fluctuation index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as inputs of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the signal quality index label of the data line during high-speed data transmission as the prediction target, and takes minimizing the sum of prediction errors of the signal quality index labels of all data lines during high-speed data transmission as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The signal quality index of the data line during high-speed data transmission is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0069] The method for obtaining the signal quality index of the data line during high-speed data transmission is as follows: from the comprehensive feature vector training data of the trained machine learning model, the corresponding function expression is obtained: Q=F(MK, LH); wherein F is the output function of the model, MK is the signal transmission bit error rate increase index, LH is the signal transmission delay fluctuation index, and Q is the signal quality index of the data line during high-speed data transmission.

[0070] The comparison and analysis module is used to compare and analyze the signal quality index of the data line obtained during high-speed data transmission with a preset quality threshold, and divide the data line into a high-quality signal data line and a low-quality signal data line according to the analysis result.

[0071] The obtained signal quality index of the data line during high-speed data transmission is compared and analyzed with the preset quality threshold. If the signal quality index of the data line during high-speed data transmission is greater than or equal to the preset quality threshold, it means that the signal quality of the data line during high-speed data transmission is high and the data transmission is stable. At this time, no warning signal is generated, and the corresponding data line is divided into a high-quality signal data line; if the signal quality index of the data line during high-speed data transmission is less than the preset quality threshold, it means that the signal quality of the data line during high-speed data transmission is low and the data transmission is unstable. At this time, a warning signal is generated, and the corresponding data line is divided into a low-quality signal data line.

[0072] The optimization module recommends that high-quality signal data lines continue to be used; for low-quality signal data lines, the abnormality of their signal quality during high-speed data transmission is further predicted. If the abnormality is high, corresponding optimization measures are taken immediately.

[0073] The reason why we recommend continuing to use high-quality signal data cables is mainly because of their stability and reliability during high-speed data transmission. High-quality signal data cables can maintain low bit error rates and small delay fluctuations during high-speed transmission, indicating that they have strong signal protection capabilities and high anti-interference capabilities against external factors such as electromagnetic interference (EMI). Stable signal transmission performance ensures data integrity and transmission continuity, reducing the risk of data packet loss and transmission errors. Therefore, continuing to use high-quality signal data cables helps to ensure the stability of data transmission between devices, especially in application scenarios with high accuracy requirements (such as video transmission and data backup).

[0074] For low-quality signal data lines, the degree of abnormal signal quality during high-speed data transmission is further predicted, specifically:

[0075] The abnormal degree of signal quality is marked as E, and the calculation expression is: When Q < T, E is positive, and the larger the value, the higher the degree of signal quality abnormality. Set a high abnormal threshold Ecritical and a low abnormal threshold Elow to predict and classify the degree of signal quality abnormality E. Further divide the degree of abnormality into "low", "medium", and "high" levels to take corresponding optimization measures. If E < Elow, the degree of abnormality is low, and usually no immediate optimization is required, but close monitoring is needed. If Elow ≤ E < Ecritical, the degree of abnormality is medium, and optimization or replacement can be considered. If E ≥ Ecritical, the degree of abnormality is high, and immediate optimization measures should be taken.

[0076] In the case of a relatively high degree of abnormality, take optimization measures to improve the signal quality index Q by improving the error rate increase index MK of signal transmission and the delay fluctuation index LH of signal transmission. Obtain a new signal quality index Q′ through adjustment. The expression is: Q′ = f(MK′, LH′); where MK′ = MK - ΔMK; MK′ is the optimized error rate increase index, and ΔMK represents the improvement amplitude; LH′ = LH - ΔLH; LH′ is the optimized delay fluctuation index, and ΔLH represents the improvement amplitude; f is the output function of the polynomial regression model. After optimization, calculate the new degree of abnormality E′, and the expression is: If E′ reaches the expected improvement goal (such as E′ < Elow), it is considered that the optimization measure is effective, and the data cable can continue to be used. If E′ is still higher than the set threshold, further optimization or replacement of the data cable may be required.

[0077] In this embodiment, first, a test environment suitable for high-speed data transmission of mobile phone data cables is created through a test environment construction module, equipped with devices such as an oscilloscope, a signal analyzer, and a data transmission test platform to detect signal quality. On this basis, the data monitoring module connects the data cable to the computer and performs high-speed transmission under the conditions of external electromagnetic interference and no interference respectively, and real-time monitors key data such as the error rate increase index of signal transmission and the delay fluctuation index of signal transmission. Then, the data analysis module converts the collected signal characteristics into a comprehensive feature vector as the input item of the machine learning model, and generates a signal quality index after training the model. Subsequently, the comparison and analysis module compares the signal quality index of the data cable with the preset quality threshold, and divides the data cable into two categories: high quality and low quality. Finally, the optimization module recommends continuing to use the high-quality data cable, while further predicting the degree of abnormality of the low-quality data cable. If the degree of abnormality is high, immediate optimization measures are taken to improve its signal quality.

[0078] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0079] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0080] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A mobile phone data line detection and analysis system, characterized in that: It includes test environment construction module, data monitoring module, data analysis module, comparative analysis module and optimization module; The test environment construction module is used to build a test environment for data transmission over a mobile phone data line and select test equipment that can perform high-speed data transmission and is equipped with corresponding interference detection functions. The test equipment includes an oscilloscope, a signal analyzer, and a data transmission test platform. The data monitoring module is used to conduct tests under external electromagnetic interference sources and non-interference environments respectively, connect the data line to the computer and perform high-speed data transmission, and use an oscilloscope and a signal analyzer to monitor the signal quality data in real time. The signal quality data includes the signal transmission bit error rate increase index and the signal transmission delay fluctuation index; A data analysis module is used to convert the signal transmission bit error rate increase index and the signal transmission delay fluctuation index into a comprehensive feature vector as an input item of the machine learning model, and obtain the signal quality index of the data line during high-speed data transmission after training the model; A comparison and analysis module, used to compare and analyze the signal quality index of the data line obtained during the high-speed data transmission process with a preset quality threshold, and divide the data line into a high-quality signal data line and a low-quality signal data line according to the analysis result; The optimization module recommends that high-quality signal data lines continue to be used; for low-quality signal data lines, the abnormality of their signal quality during high-speed data transmission is further predicted. If the abnormality is high, corresponding optimization measures are taken immediately.

2. A mobile phone data line detection and analysis system according to claim 1, characterized in that: In the data monitoring module, the signal quality data includes the signal transmission bit error rate increase index, and the method for obtaining the signal transmission bit error rate increase index is: In signal transmission, the relationship between the bit error rate BER and the signal-to-noise ratio SNR is: Where B is the function term, M is the order of the modulation method, and a bit error rate sequence is constructed. The bit error rate sequence is expressed as {BERi}; where i represents the bit error rate value of the i-th measurement. For the calculation of the bit error rate increase index, the likelihood function is expressed as: Among them, P(BERi|θ) represents the probability of the bit error rate BERi obtained in the i-th experiment under the given parameter θ. In order to simplify the calculation, the log-likelihood function lnL(θ) is used, and the expression is: The core task of maximum likelihood estimation is to find the optimal parameter θ* to maximize the log-likelihood function: After obtaining the optimal parameters, the bit error rate BER0 under interference-free conditions is calculated, and the bit error rate BER1 under interference conditions is calculated, that is, the bit error rate measured in an environment containing factors such as electromagnetic interference, and the signal transmission bit error rate increase index is calculated. The expression is: Where MK is the signal transmission bit error rate increase index.

3. A mobile phone data line detection and analysis system according to claim 2, characterized in that: The signal quality data includes a signal transmission delay fluctuation index, and the method for obtaining the signal transmission delay fluctuation index is as follows: Collect delay data during signal transmission. Delay data refers to the transmission delay L(t) of the signal at each time point t. The collected delay data is {(t1,L1),(t2,L2),...,(t n ,L n )}, where t n It's time, L n is the signal delay at the corresponding time point; in Gaussian process regression, the kernel function determines the similarity between input data points. The kernel function is used to measure the similarity between different time points t i and t j Based on the selected kernel function, the covariance matrix K between the delayed data points is calculated: Among them, k(t n ,t n ) is the covariance value calculated by the kernel function. If the signal delay data is affected by noise, the noise term needs to be added The expression is: Where I is the unit matrix. Through Gaussian process regression, the predicted value of the delay data is obtained. The new time point is predicted to obtain its corresponding delay value. Input X = {t1, t2, ..., t n }, output y = {L1, L2, ..., L n }; Prediction data: prediction point t * ; Calculate the covariance matrix: K(X,X) is the covariance matrix between the training data, K(X,t * ) is the covariance matrix between the training data and the prediction points, K(t * ,t * ) is the covariance matrix between the prediction points, and the prediction mean μ * is: μ * =K ( t * ,X ) K ( X,X )-1 y; prediction variance for: The standard deviation of the signal is extracted from the prediction variance, and the signal transmission delay fluctuation index is obtained by weighted averaging the standard deviations of the delay fluctuations calculated at several time points.

4. A mobile phone data line detection and analysis system according to claim 3, characterized in that: In the data analysis module, the signal transmission bit error rate increase index and the signal transmission delay fluctuation index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the signal quality index label of the data line during high-speed data transmission as the prediction target, and takes minimizing the sum of prediction errors of the signal quality index labels of all data lines during high-speed data transmission as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The signal quality index of the data line during high-speed data transmission is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

5. A mobile phone data line detection and analysis system according to claim 4, characterized in that: In the comparison and analysis module, the obtained signal quality index of the data line during the high-speed data transmission process is compared and analyzed with the preset quality threshold. If the signal quality index of the data line during the high-speed data transmission process is greater than or equal to the preset quality threshold, it means that the signal quality of the data line during the high-speed data transmission process is high and the data transmission is stable. At this time, no warning signal is generated, and the corresponding data line is divided into a high-quality signal data line; if the signal quality index of the data line during the high-speed data transmission process is less than the preset quality threshold, it means that the signal quality of the data line during the high-speed data transmission process is low and the data transmission is unstable. At this time, a warning signal is generated, and the corresponding data line is divided into a low-quality signal data line.

6. A mobile phone data line detection and analysis system according to claim 1, characterized in that: In the optimization module, the abnormal degree of signal quality is marked as E, and the calculation expression is: When Q < T, E is a positive value, and the larger the value, the higher the abnormal degree of signal quality. Set the high abnormal threshold Ecritical and the low abnormal threshold Elow to predict and classify the abnormal degree E of signal quality. If E < Elow, the abnormal degree is low, and there is no need for immediate optimization, but close monitoring is required. If Elow ≤ E < Ecritical, the abnormal degree is medium, and optimization or replacement should be carried out. If E ≥ Ecritical, the abnormal degree is high, and immediate optimization measures should be taken.

7. A mobile phone data line detection and analysis system according to claim 6, characterized in that: In the case of a high degree of abnormality, optimization measures are taken to improve the signal quality index Q by improving the error rate increase index MK of signal transmission and the delay fluctuation index LH of signal transmission. After adjustment, a new signal quality index Q′ is obtained, and the expression is: Q′ = f(MK′, LH′); where MK ′ = MK - ΔMK; MK ′ is the error rate increase index after optimization, and ΔMK represents the improvement amplitude; LH ′ = LH - ΔLH; LH ′ is the delay fluctuation index after optimization, and ΔLH represents the improvement amplitude; f is the output function of the polynomial regression model; After optimization, the new degree of abnormality E′ is calculated, and the expression is: If E′ < Elow, the optimization measure is effective, and the data cable can continue to be used; if E ≥ Ecritical, further optimization or replacement of the data cable is required.

Images