A method for calibrating performance parameters of a mobile phone mainboard based on artificial intelligence

Abstract

The application discloses a kind of based on artificial intelligence's mobile phone mainboard performance parameter calibration method, belong to mobile phone mainboard technical field.The present application solves the problem that existing technology cannot carry out mobile phone mainboard performance parameter calibration, the artificial intelligence model is trained by training set data, and the artificial intelligence model after training is evaluated and optimized, can improve the accuracy of artificial intelligence model prediction, and the optimized artificial intelligence model is applied to the calibration of mobile phone mainboard performance parameter, so that artificial intelligence model can predict mobile phone mainboard performance, so as to help the difference between the predicted mobile phone mainboard performance parameter of artificial intelligence model and actual performance, then according to the prediction result, point out the optimization suggestion that mobile phone mainboard exists, and then adjust the parameter of mobile phone mainboard, to optimize the performance of mobile phone mainboard, finally, the effect of mobile phone mainboard performance parameter calibration can be verified by testing, to ensure the accuracy of mobile phone mainboard performance parameter calibration.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of mobile phone mainboards, and particularly relates to a method for calibrating performance parameters of a mobile phone mainboard based on artificial intelligence. BACKGROUND

[0002] A mobile phone mainboard, also known as a mainboard or a system board, is one of the core components in a mobile phone. It is like a central hub that connects various components inside the mobile phone, such as the CPU, memory, storage chip, communication module, etc., to ensure that they can work together. The performance and stability of the mobile phone mainboard directly determine the overall performance of the mobile phone. An excellent mainboard design can ensure that the mobile phone runs at high speed while maintaining stability and prolonging the service life of the mobile phone. However, the existing mobile phone mainboard cannot calibrate performance parameters, and the performance parameters of the mobile phone mainboard cannot be calibrated, which will reduce the communication quality and increase the cost of the equipment, thereby failing to ensure that each mobile phone leaving the factory can meet the preset performance standards, failing to provide better user experience, increasing the cost, and failing to achieve economic benefits. Therefore, it does not meet the existing needs, and for this purpose, the application provides a method for calibrating performance parameters of a mobile phone mainboard based on artificial intelligence. SUMMARY

[0003] The application aims to provide a method for calibrating performance parameters of a mobile phone mainboard based on artificial intelligence. By training an artificial intelligence model and evaluating and optimizing the trained artificial intelligence model, the accuracy of the artificial intelligence model prediction is improved. The optimized artificial intelligence model is applied to the calibration of the performance parameters of the mobile phone mainboard. By obtaining and inputting the current state data of the mobile phone mainboard, the artificial intelligence model can predict the performance of the mobile phone mainboard, thereby helping to predict the difference between the predicted performance parameters of the mobile phone mainboard and the actual performance. Then, according to the prediction result, the optimization suggestions for the mobile phone mainboard are pointed out, and the parameters of the mobile phone mainboard are adjusted to optimize the performance of the mobile phone mainboard. The effect of the calibration of the performance parameters of the mobile phone mainboard is verified through testing, and the problems in the background technology are solved.

[0004] To achieve the above-mentioned purpose, the application provides the following technical scheme: a method for calibrating performance parameters of a mobile phone mainboard based on artificial intelligence, comprising the following steps:

[0005] Step 1: Collecting relevant performance data of the mobile phone mainboard, and at the same time, establishing an artificial intelligence model, preprocessing and integrating the collected performance data of the mobile phone mainboard into training set data;

[0006] Step 2: Training the artificial intelligence model using the training set data, so that the trained artificial intelligence model can predict the performance of the mobile phone mainboard;

[0007] Step three: after the training is completed, the artificial intelligence model is evaluated, and the artificial intelligence model is optimized according to the evaluation result;

[0008] Step four: apply the optimized artificial intelligence model to the calibration of the performance parameters of the mobile phone mainboard to realize the calibration of the performance parameters of the mobile phone mainboard;

[0009] Step five: based on the prediction of the artificial intelligence model, adjust the parameters of the mobile phone mainboard to optimize the performance of the mobile phone mainboard;

[0010] Step six: test the mobile phone mainboard after parameter adjustment, and verify the effect of mobile phone mainboard performance parameter calibration through testing.

[0011] Further, the step one specifically includes the following steps:

[0012] Data collection: collect the relevant performance data of the mobile phone mainboard through special sensors or testing tools, and the collected performance data is the basis for model training;

[0013] Model establishment: establish an artificial intelligence model according to the collected performance data;

[0014] Data preprocessing: preprocess the collected performance data, including data cleaning, data conversion and data reduction;

[0015] Data integration: integrate the preprocessed performance data into training set data, which is used to train the established artificial intelligence model.

[0016] Further, the preprocessing includes:

[0017] Data cleaning: remove errors, missing values and noise in the performance data;

[0018] Data conversion: convert the performance data into a unified data format or data type;

[0019] Data reduction: reduce the dimensionality of the performance data through feature extraction to reduce the computational cost and improve the performance of the artificial intelligence model.

[0020] Further, the preprocessing also includes:

[0021] Extract the data information before removing noise;

[0022] According to the numerical value of the data information before removing noise, obtain the data distribution diagram of the data information before removing noise as the first data distribution diagram;

[0023] According to the numerical value of the data information after removing noise, obtain the data distribution diagram of the data information after removing noise as the second data distribution diagram;

[0024] comparing the first data distribution map and the second data distribution map to obtain a similarity value of the first data distribution map and the second data distribution map;

[0025] comparing the similarity value of the first data distribution map and the second data distribution map with a preset similarity threshold value;

[0026] when the similarity value of the first data distribution map and the second data distribution map is not lower than the preset similarity threshold value, performing data quality evaluation on the data information after removing noise;

[0027] when the similarity value of the first data distribution map and the second data distribution map is lower than the preset similarity threshold value, traversing each data information of the first data distribution map and each data information of the second data distribution map to obtain a distribution position of each data information in the first data distribution map and the second data distribution map;

[0028] obtaining a straight line distance of the distribution position according to the distribution position of each data information in the first data distribution map and the second data distribution map;

[0029] obtaining a data distortion degree coefficient according to the straight line distance corresponding to the distribution position of each data information in the first data distribution map and the second data distribution map; wherein the data distortion degree coefficient is obtained by the following formula:

[0030]

[0031] wherein S represents the data distortion degree coefficient; k represents the number of data information contained in the first data distribution map and the second data distribution map; L i represents the straight line distance of the distribution position corresponding to the i-th data information; L yi represents the minimum straight line distance allowed for the distribution position corresponding to the i-th data information satisfying the similarity threshold value; m represents the number of data information in the k data information whose distribution position straight line distance exceeds the minimum straight line distance allowed for the corresponding distribution position; n represents the number of data information in the k data information whose distribution position straight line distance is 0; q represents the number of data information in the k data information whose distribution position straight line distance does not exceed the minimum straight line distance allowed for the corresponding distribution position, and the straight line distance is not zero; s 01 , s 02 and s 03 respectively represent the first adjustment coefficient, the second adjustment coefficient and the third adjustment coefficient;

[0032] wherein the first adjustment coefficient is obtained by the following formula:

[0033]

[0034] wherein s 01 represents the first adjustment coefficient; m represents the number of data information whose linear distance of distribution position exceeds the minimum linear distance allowed by the corresponding distribution position in the k data information; L 01i represents the linear distance of the data information whose linear distance of the i-th distribution position exceeds the minimum linear distance allowed by the corresponding distribution position; L y01i represents the minimum linear distance allowed by the distribution position of the data information whose linear distance of the i-th distribution position exceeds the minimum linear distance allowed by the corresponding distribution position;

[0035] Meanwhile, the second adjustment coefficient is obtained by the following formula:

[0036]

[0037] wherein s 02 represents the second adjustment coefficient; n represents the number of data information whose linear distance of distribution position is 0 in the k data information; L 02xi and L 02hi respectively represent the linear distance corresponding to the preceding data information and the linear distance corresponding to the following data information adjacent to the data information whose linear distance of the i-th distribution position is 0; L yx02i and L yh02i respectively represent the minimum linear distance allowed by the distribution position corresponding to the preceding data information and the minimum linear distance allowed by the distribution position corresponding to the following data information;

[0038] Meanwhile, the third adjustment coefficient is obtained by the following formula:

[0039]

[0040] wherein s 03 represents the third adjustment coefficient; q represents the number of data information whose linear distance of distribution position does not exceed the minimum linear distance allowed by the corresponding distribution position, and the linear distance is non-zero in the k data information; L 03i represents the linear distance corresponding to the data information whose linear distance of the i-th distribution position does not exceed the minimum linear distance allowed by the corresponding distribution position, and the linear distance is non-zero; L y03i represents the minimum linear distance allowed by the distribution position corresponding to the data information whose linear distance of the i-th distribution position does not exceed the minimum linear distance allowed by the corresponding distribution position, and the linear distance is non-zero;

[0041] When the data distortion degree coefficient exceeds the preset coefficient threshold value, an abnormal alarm of denoising operation is performed;

[0042] When the data distortion degree coefficient does not exceed the preset coefficient threshold, the data information before noise removal is re-cleaned.

[0043] Further, when the similarity value of the first data distribution graph and the second data distribution graph is not lower than the preset similarity threshold, the data quality of the data information after noise removal is evaluated, including:

[0044] When the similarity value of the first data distribution graph and the second data distribution graph is not lower than the preset similarity threshold, the signal-to-noise ratio, data integrity and noise residual of the data information after noise removal are extracted;

[0045] The data quality evaluation parameter corresponding to the data information after noise removal is obtained by using the signal-to-noise ratio, data integrity and noise residual of the data information after noise removal; wherein the data quality evaluation parameter corresponding to the data information after noise removal is obtained by the following formula:

[0046]

[0047] Wherein, W represents the data quality evaluation parameter corresponding to the data information after noise removal; p represents the data integrity of the i-th data information; R i represents the noise residual corresponding to the i-th data information; C i represents the maximum allowed noise residual corresponding to the i-th data information; B i represents the signal-to-noise ratio of the i-th data information after noise removal; B xi represents the signal-to-noise ratio of the i-th data information before noise removal;

[0048] The data quality evaluation parameter corresponding to the data information after noise removal is compared with the preset data quality evaluation parameter threshold;

[0049] When the data quality evaluation parameter corresponding to the data information after noise removal is lower than the preset data quality evaluation parameter threshold, data quality abnormality alarm is performed.

[0050] Further, the step two specifically includes the following steps:

[0051] The integrated training set data is substituted into the artificial intelligence model for training and learning;

[0052] The artificial intelligence model learns and trains the patterns and features in the training set data based on a deep learning algorithm or a machine learning algorithm;

[0053] Through learning the patterns and features in the training set data, the artificial intelligence model can predict the performance of the mobile phone motherboard.

[0054] Further, the step three specifically comprises the following steps:

[0055] Performance evaluation: the performance of the artificial intelligence model after training is evaluated, and the evaluation result is used for optimization and improvement of the artificial intelligence model;

[0056] Wherein, the performance evaluation adopts cross-validation method, and the training set data is divided into subsets for evaluation of the artificial intelligence model;

[0057] Wherein, the cross-validation method comprises:

[0058] Data set division: the training set data is divided into multiple mutually non-overlapping subset data;

[0059] Model evaluation: based on the cross-validation method, the multiple mutually non-overlapping subset data is substituted into the artificial intelligence model, and the artificial intelligence model is repeatedly evaluated by using different subset data, and finally the evaluation result is obtained;

[0060] Result analysis: analyze the evaluation result to find out the factors affecting the performance of the artificial intelligence model, and then optimize and improve the artificial intelligence model;

[0061] Model optimization and improvement: according to the evaluation result of the artificial intelligence model, the artificial intelligence model is optimized and improved, and the optimized artificial intelligence model is used for calibration of the performance parameters of the mobile phone mainboard in step four.

[0062] Further, the performance evaluation of the artificial intelligence model includes evaluation of the accuracy, stability, scalability and reliability of the artificial intelligence model, and the optimization and improvement of the artificial intelligence model includes improvement of the training method and addition or replacement of features.

[0063] Further, the step four specifically comprises the following steps:

[0064] The optimized artificial intelligence model is applied to the calibration of the performance parameters of the mobile phone mainboard;

[0065] Obtain and input the current mobile phone mainboard state data, and the artificial intelligence model predicts the performance of the mobile phone mainboard;

[0066] According to the prediction result, the optimization suggestion existing in the mobile phone mainboard is pointed out;

[0067] According to the optimization suggestion existing in the mobile phone mainboard, the performance parameters of the mobile phone mainboard are calibrated to determine the parameters that need to be adjusted.

[0068] Further, the step six specifically comprises the following steps:

[0069] After the parameter adjustment of the mobile phone mainboard in step five, the actual data of the mobile phone mainboard is obtained;

[0070] Integrating the acquired actual data into test set data;

[0071] Substituting the integrated test set data into the artificial intelligence model for verification;

[0072] According to the test results, the degree of coincidence between the prediction of the artificial intelligence model and the actual data is judged.

[0073] Compared with the prior art, the beneficial effects of the present application are:

[0074] The present application collects the relevant performance data of the mobile phone mainboard, pre-processes and integrates the collected performance data into training set data, at the same time, establishes an artificial intelligence model, substitutes the training set data into the artificial intelligence model for training and learning, evaluates and optimizes the trained artificial intelligence model, which can improve the prediction accuracy of the artificial intelligence model. The optimized artificial intelligence model is applied to the calibration of the performance parameters of the mobile phone mainboard, the state data of the current mobile phone mainboard is acquired and input, so that the artificial intelligence model can predict the performance of the mobile phone mainboard, thereby helping to predict the difference between the performance parameters of the mobile phone mainboard and the actual performance, and then according to the prediction result, pointing out the optimization suggestions of the mobile phone mainboard, and then adjusting the parameters of the mobile phone mainboard to optimize the performance of the mobile phone mainboard. Finally, the mobile phone mainboard after parameter adjustment is tested, and the effect of the performance parameter calibration of the mobile phone mainboard is verified through the test, so as to ensure the accuracy of the performance parameter calibration of the mobile phone mainboard. BRIEF DESCRIPTION OF DRAWINGS

[0075] Figure 1 The flowchart of the mobile phone mainboard performance parameter calibration method based on artificial intelligence of the present application;

[0076] Figure 2 The flowchart of data collection and model establishment of the present application;

[0077] Figure 3 The flowchart of artificial intelligence model training of the present application;

[0078] Figure 4 The flowchart of artificial intelligence model evaluation and optimization of the present application;

[0079] Figure 5 The flowchart of mobile phone mainboard performance parameter calibration of the present application;

[0080] Figure 6 The flowchart of mobile phone mainboard performance parameter calibration effect verification of the present application. DETAILED DESCRIPTION

[0081] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all the other embodiments obtained by those skilled in the art without creative efforts belong to the scope of the present application.

[0082] In order to solve the technical problem that the existing mobile phone mainboard cannot perform performance parameter calibration, the performance parameters of the mobile phone mainboard cannot be calibrated, the communication quality is reduced and the equipment cost is increased, and thus it is impossible to ensure that each mobile phone leaving the factory can reach the preset performance standard, it is impossible to provide better user experience, the cost is increased, and economic benefits cannot be achieved, please refer to Figures 1-6 The embodiment provides the following technical solutions.

[0083] A method for calibrating performance parameters of a mobile phone mainboard based on artificial intelligence, comprising the following steps:

[0084] Step one: collect the relevant performance data of the mobile phone mainboard, at the same time, establish an artificial intelligence model, pre-process and integrate the collected performance data of the mobile phone mainboard into training set data;

[0085] Step two: use the training set data to train the artificial intelligence model, so that the artificial intelligence model after training learns to predict the performance of the mobile phone mainboard;

[0086] Step three: after training, evaluate the artificial intelligence model, and optimize the artificial intelligence model according to the evaluation result;

[0087] Step four: apply the optimized artificial intelligence model to the calibration of the performance parameters of the mobile phone mainboard, so as to realize the calibration of the performance parameters of the mobile phone mainboard;

[0088] Step five: based on the prediction of the artificial intelligence model, adjust the parameters of the mobile phone mainboard to optimize the performance of the mobile phone mainboard;

[0089] Step six: test the mobile phone mainboard after parameter adjustment, and verify the effect of the calibration of the performance parameters of the mobile phone mainboard through testing.

[0090] The technical effect of the above content is that the method for calibrating performance parameters of a mobile phone mainboard based on artificial intelligence is composed of data collection and model establishment, model training, model evaluation and optimization, model application, parameter adjustment and calibration effect verification. Through the above process, the performance parameters of the mobile phone mainboard can be calibrated, and the calibration effect can be tested and verified, so as to improve the communication quality and reduce the equipment cost, and thus it is possible to ensure that each mobile phone leaving the factory can reach the preset performance standard.

[0091] Step one, specifically comprising the following steps:

[0092] Data collection: Collect relevant performance data of the mobile phone motherboard through special sensors or test tools. The collected performance data is the basis for model training.

[0093] Model establishment: Establish an artificial intelligence model based on the collected performance data.

[0094] Data preprocessing: Preprocess the collected performance data, including data cleaning, data conversion and data reduction.

[0095] Data integration: Integrate the preprocessed performance data into training set data, which is used to train the established artificial intelligence model.

[0096] The technical effects of the above content are as follows: First, the data for training the model needs to be collected, and an artificial intelligence model needs to be established. Data collection is the basis for model training, and the performance evaluation of the artificial intelligence model depends on high-quality data sets. For the calibration of the performance parameters of the mobile phone motherboard, relevant data sets need to be prepared first. These data sets should contain performance data of the mobile phone motherboard under different conditions, so that the artificial intelligence model can learn the variation law of the performance parameters during training. Data collection can be done through special sensors or test tools to collect relevant performance data of the mobile phone motherboard. After data cleaning, data conversion and data reduction, the collected performance data will be integrated into training set data, which can be used to train the established artificial intelligence model.

[0097] Preprocessing includes:

[0098] Data cleaning: Remove errors, missing values and noise in performance data.

[0099] Data conversion: Convert performance data into a unified data format or data type.

[0100] Data reduction: Reduce the dimensionality of performance data through feature extraction to reduce computational cost and improve the performance of artificial intelligence model.

[0101] The technical effect of the above is that the main purpose of data cleaning is to improve the quality of performance data, reduce the probability of errors occurring in data statistics, and ensure the accuracy and effectiveness of performance data. Through data cleaning, errors, inconsistencies, incomplete and redundant data in performance data can be removed or repaired, making performance data more accurate, reliable and useful, thereby improving the accuracy and reliability of model prediction. The method of data cleaning mainly includes the following steps: data review, comprehensive review of performance data, including checking the type of performance data, missing values, outliers, duplicate records, etc.; missing value processing, missing values can be deleted; outlier detection and processing: identify and process outliers, which can be detected and processed by setting a threshold; duplicate data processing, identify and process duplicate data, which can choose to delete duplicate records or merge duplicate records; data verification, verify performance data to ensure accuracy and completeness; the main purpose of data conversion is to ensure the consistency of performance data, through data format unification to ensure the consistency of data format, through data type conversion to convert performance data to a unified data type, and convert performance data to a unified data format or data type, which can improve the security and maintainability of performance data. Finally, the main purpose of data reduction is to reduce the dimensionality of performance data through feature extraction, thereby reducing the computational cost and improving the performance of artificial intelligence models. Through the above process, the original data can be made more standardized, accurate and useful, thereby improving the effect and accuracy of model prediction.

[0102] Specifically, the preprocessing further includes:

[0103] extracting data information before noise removal;

[0104] According to the numerical value of the data information before noise removal, a data distribution graph of the data information before noise removal is obtained as a first data distribution graph;

[0105] According to the numerical value of the data information after noise removal, a data distribution graph of the data information after noise removal is obtained as a second data distribution graph;

[0106] Compare the first data distribution graph and the second data distribution graph to obtain a similarity value of the first data distribution graph and the second data distribution graph;

[0107] Compare the similarity value of the first data distribution graph and the second data distribution graph with a preset similarity threshold;

[0108] When the similarity value of the first data distribution graph and the second data distribution graph is not less than the preset similarity threshold, the data quality of the data information after noise removal is evaluated;

[0109] When the similarity value of the first data distribution map and the second data distribution map is lower than a preset similarity threshold, each data information of the first data distribution map and each data information of the second data distribution map are traversed to obtain a distribution position of each data information in the first data distribution map and the second data distribution map;

[0110] A straight line distance is obtained according to the distribution position of each data information in the first data distribution map and the second data distribution map;

[0111] A data distortion degree coefficient is obtained according to the straight line distance corresponding to the distribution position of each data information in the first data distribution map and the second data distribution map; wherein the data distortion degree coefficient is obtained by the following formula:

[0112]

[0113] Wherein, S represents the data distortion degree coefficient; k represents the number of data information contained in the first data distribution map and the second data distribution map; L i represents the straight line distance of the i th data information corresponding to the distribution position; L yi represents the minimum straight line distance allowed by the distribution position corresponding to the i th data information meeting the similarity threshold; m represents the number of data information whose distribution position straight line distance exceeds the minimum straight line distance allowed by the corresponding distribution position in the k data information; n represents the number of data information whose distribution position straight line distance is 0 in the k data information; q represents the number of data information whose distribution position straight line distance does not exceed the minimum straight line distance allowed by the corresponding distribution position, and the straight line distance is not zero in the k data information; s 01 , s 02 and s 03 respectively represent the first adjustment coefficient, the second adjustment coefficient and the third adjustment coefficient;

[0114] Wherein, the first adjustment coefficient is obtained by the following formula:

[0115]

[0116] Wherein, s 01 represents the first adjustment coefficient; m represents the number of data information whose distribution position straight line distance exceeds the minimum straight line distance allowed by the corresponding distribution position in the k data information; L 01i represents the straight line distance corresponding to the data information whose distribution position straight line distance exceeds the minimum straight line distance allowed by the corresponding distribution position of the i th distribution position; L y01i represents the minimum straight line distance allowed by the distribution position corresponding to the data information whose distribution position straight line distance exceeds the minimum straight line distance allowed by the corresponding distribution position of the i th distribution position;

[0117] Meanwhile, the second adjustment coefficient is obtained by the following formula:

[0118]

[0119] wherein s 02 represents the second adjustment coefficient; n represents the number of data information whose linear distance is 0 at the distribution position in the k data information; L 02xi and L 02hi respectively represent the linear distance corresponding to the preceding data information and the linear distance corresponding to the following data information adjacent to the data information whose linear distance is 0 at the i-th distribution position; L yx02i and L yh02i respectively represent the minimum linear distance allowed at the distribution position corresponding to the preceding data information and the minimum linear distance allowed at the distribution position corresponding to the following data information;

[0120] Meanwhile, the third adjustment coefficient is obtained by the following formula:

[0121]

[0122] wherein s 03 represents the third adjustment coefficient; q represents the number of data information whose linear distance does not exceed the minimum linear distance allowed at the corresponding distribution position, and whose linear distance is non-zero in the k data information; L 03i represents the linear distance corresponding to the data information whose linear distance does not exceed the minimum linear distance allowed at the corresponding distribution position, and whose linear distance is non-zero at the i-th distribution position; L y03i represents the minimum linear distance allowed at the distribution position corresponding to the data information whose linear distance does not exceed the minimum linear distance allowed at the corresponding distribution position, and whose linear distance is non-zero at the i-th distribution position;

[0123] When the data distortion degree coefficient exceeds the preset coefficient threshold, an abnormal alarm of denoising operation is performed;

[0124] When the data distortion degree coefficient does not exceed the preset coefficient threshold, the data information before removing noise is re-cleaned.

[0125] The technical effect of the above technical solution is that by comparing the data distribution graphs before and after removing noise (the first data distribution graph and the second data distribution graph), and calculating the similarity values thereof, the technical solution preliminarily evaluates the effect of data denoising processing. This method not only considers the overall distribution change of data values, but also measures the influence of denoising processing on the overall structure of data through the quantitative index of similarity values.

[0126] When the similarity value is lower than the preset threshold, it means that the denoising process may have introduced data distortion or failed to effectively remove noise. At this time, by further analyzing the position change (straight-line distance) of each data point in the two data distribution graphs, the degree and specific location of data distortion can be accurately identified. This method improves the accuracy of anomaly detection and helps to quickly locate the problem.

[0127] By introducing the data distortion degree coefficient S, the technical solution realizes the quantitative evaluation of the degree of data distortion. This coefficient considers multiple factors, including the number of data points exceeding the allowed straight-line distance, the number of data points with a straight-line distance of 0, and the number of data points with a non-zero straight-line distance that does not exceed the allowed straight-line distance, and is adjusted by the first, second, and third adjustment coefficients. This quantitative evaluation provides a reliable basis for subsequent anomaly processing. When the data distortion degree coefficient exceeds the preset threshold, the system can timely alarm for denoising operation anomalies, reminding users or system administrators to pay attention to and handle possible denoising problems. This timeliness helps to reduce errors in subsequent analysis or decision-making due to data distortion. When the data distortion degree does not exceed the preset threshold, the system selects to re-clean the data information before removing noise. This flexibility ensures the continuity and effectiveness of data processing, while avoiding unnecessary repeated denoising operations.

[0128] In summary, the technical solution effectively improves the quality and efficiency of data processing through comprehensive evaluation of data denoising effect, accurate detection of data distortion, quantitative evaluation of distortion degree, and timely response to anomaly processing.

[0129] Specifically, when the similarity value of the first data distribution graph and the second data distribution graph is not lower than the preset similarity threshold, the data quality of the data information after removing noise is evaluated, including:

[0130] When the similarity value of the first data distribution graph and the second data distribution graph is not lower than the preset similarity threshold, the signal-to-noise ratio, data integrity, and noise residual of the data information after removing noise are extracted;

[0131] The signal-to-noise ratio, data integrity, and noise residual of the data information after removing noise are used to obtain the data quality evaluation parameter corresponding to the data information after removing noise; wherein the data quality evaluation parameter corresponding to the data information after removing noise is obtained by the following formula:

[0132]

[0133] Where W represents the data quality evaluation parameter corresponding to the data information after removing noise; p represents the data integrity of the i-th data information; R i represents the noise residual corresponding to the i-th data information; Ci represents the maximum allowed noise residual quantity corresponding to the i-th data information; B i represents the signal-to-noise ratio of the data information after removing noise corresponding to the i-th data information; B xi represents the signal-to-noise ratio of the data information before removing noise corresponding to the i-th data information;

[0134] comparing the data quality evaluation parameter corresponding to the data information after removing noise with a preset data quality evaluation parameter threshold;

[0135] when the data quality evaluation parameter corresponding to the data information after removing noise is lower than the preset data quality evaluation parameter threshold, data quality abnormality alarm is performed.

[0136] The technical effect of the above technical solution is that when the similarity of the data distribution graph after removing noise and the original data distribution graph meets the preset threshold, the technical solution further extracts multiple key quality indicators of the data information after removing noise, including signal-to-noise ratio, data integrity, and noise residual quantity. These indicators together constitute a comprehensive perspective for data quality evaluation, which can more carefully reflect the true situation of the data. The data quality evaluation parameter W corresponding to the information of the data after removing noise is calculated by formula, which comprehensively considers the data integrity, the proportion of the noise residual quantity relative to the maximum allowed value, and the change of the signal-to-noise ratio. This quantitative evaluation method makes the data quality have a comparable and measurable standard, which helps to objectively evaluate the effect of data processing.

[0137] The threshold of the data quality evaluation parameter is preset in the technical solution, and by comparing it with the actually calculated data quality evaluation parameter, it can be flexibly judged whether the data quality meets the requirements. This mechanism provides flexible adjustment space for data quality control in different application scenarios. When the data quality evaluation parameter is lower than the preset threshold, the system can timely perform data quality abnormality alarm. This timeliness helps to timely discover and handle data quality problems, avoiding subsequent analysis or decision-making errors caused by poor data quality. Through the above technical solution, the data processing process is more strictly and comprehensively monitored and evaluated. This helps to ensure that the processed data has higher reliability and accuracy, thereby improving the scientificity and effectiveness of data analysis and decision-making.

[0138] In summary, the technical solution effectively improves the reliability of data processing and the control level of data quality through careful data quality evaluation, quantitative data quality evaluation parameters, flexible threshold setting, and timely data quality abnormality alarm.

[0139] Step two specifically includes the following steps:

[0140] The integrated training set data is substituted into the artificial intelligence model for training and learning;

[0141] The artificial intelligence model learns patterns and features in the training set data based on a deep learning algorithm or a machine learning algorithm.

[0142] Through learning patterns and features in the training set data, the artificial intelligence model can predict the performance of the mobile phone motherboard.

[0143] The technical effect of the above is that the integrated training set data is substituted into the artificial intelligence model for training and learning, and then trained based on a deep learning algorithm or a machine learning algorithm. The deep learning algorithm or the machine learning algorithm can process and analyze a large amount of data, thereby training an artificial intelligence model that can predict performance data. Through processing and learning of the data, patterns and features in the training set data are learned, and the regularity and pattern in the data are gradually identified, thereby enhancing the accuracy and generalization ability of the artificial intelligence model. Through learning patterns and features in the training set data, the artificial intelligence model can predict the performance of the mobile phone motherboard.

[0144] Step three specifically includes the following steps:

[0145] Performance evaluation: the performance of the artificial intelligence model after training is evaluated, including the accuracy, stability, scalability and reliability of the artificial intelligence model. The evaluation results will be used for optimization and improvement of the artificial intelligence model.

[0146] The performance evaluation adopts a cross-validation method, and the training set data is divided into subsets for evaluation of the artificial intelligence model.

[0147] The cross-validation method includes:

[0148] Data set division: the training set data is divided into multiple non-overlapping subset data.

[0149] Model evaluation: based on the cross-validation method, the multiple non-overlapping subset data is substituted into the artificial intelligence model, and the artificial intelligence model is repeatedly evaluated using different subset data to obtain the evaluation results.

[0150] Result analysis: the evaluation results are analyzed to find out the factors affecting the performance of the artificial intelligence model, and the artificial intelligence model is optimized and improved.

[0151] Model optimization and improvement: according to the evaluation results of the artificial intelligence model, the artificial intelligence model is optimized and improved, including improving the training method and adding or replacing features. The optimized artificial intelligence model will be used for calibration of the performance parameters of the mobile phone motherboard in step four.

[0152] The technical effect of the above is that after the artificial intelligence model is trained and before it is applied, the artificial intelligence model needs to be evaluated and optimized, the performance evaluation of the artificial intelligence model is performed by using a cross-validation method, the training set data is divided into multiple mutually non-overlapping subset data, the divided subset data is substituted into the artificial intelligence model, the artificial intelligence model is repeatedly evaluated through different subset data, and finally an evaluation result is obtained, then the evaluation result is analyzed to find out factors affecting the performance of the artificial intelligence model, and the artificial intelligence model is optimized and improved, the optimization and improvement can be performed by improving the training method and adding or replacing features, and through the evaluation and optimization of the artificial intelligence model, the performance of the artificial intelligence model can be effectively evaluated and optimized, and it is ensured that the artificial intelligence model can achieve the expected effect in actual application.

[0153] Step four specifically includes the following steps:

[0154] The optimized artificial intelligence model is applied to the calibration of the performance parameters of the mobile phone mainboard;

[0155] The artificial intelligence model predicts the performance of the mobile phone mainboard by inputting the state data of the current mobile phone mainboard;

[0156] According to the prediction result, the optimization suggestion existing in the mobile phone mainboard is pointed out;

[0157] According to the optimization suggestion existing in the mobile phone mainboard, the performance parameters of the mobile phone mainboard are calibrated to determine the parameters that need to be adjusted.

[0158] Step six specifically includes the following steps:

[0159] After the parameter adjustment of the mobile phone mainboard in step five, the actual data of the mobile phone mainboard is obtained;

[0160] The obtained actual data is integrated into test set data;

[0161] The integrated test set data is substituted into the artificial intelligence model for verification;

[0162] According to the test result, the degree of coincidence between the prediction of the artificial intelligence model and the actual data is judged.

[0163] The technical effect of the above is that the artificial intelligence model can be applied to the calibration of the performance parameters of the mobile phone mainboard after optimization and improvement. During calibration, the state data of the current mobile phone mainboard needs to be obtained and input, so that the artificial intelligence model can predict the performance of the mobile phone mainboard, and then the optimization suggestions for the mobile phone mainboard can be pointed out according to the prediction results. The performance parameters of the mobile phone mainboard are calibrated according to the optimization suggestions, and the parameters that need to be adjusted are determined. Through the calibration of the performance parameters of the mobile phone mainboard, the difference between the predicted performance parameters and the actual performance can be predicted, and the calibration of the performance parameters can be completed. After determining the difference between the performance parameters of the mobile phone mainboard and the actual performance, the performance parameters are adjusted according to the calibration results, so as to ensure that the mobile phone mainboard reaches the preset performance standard. After the parameter adjustment of the mobile phone mainboard, the actual data of the mobile phone mainboard can be obtained and integrated into test set data, and then the test set data is substituted into the artificial intelligence model for verification. According to the test results, the degree of coincidence between the prediction of the artificial intelligence model and the actual data is judged. Through the test, the effect of the calibration of the performance parameters of the mobile phone mainboard can be verified, so as to ensure the accuracy of the calibration of the performance parameters of the mobile phone mainboard.

[0164] Working principle: collect the relevant performance data of the mobile phone mainboard, preprocess and integrate the collected performance data into training set data, at the same time, establish an artificial intelligence model, substitute the training set data into the artificial intelligence model for training and learning, through training the artificial intelligence model, and evaluating and optimizing the trained artificial intelligence model, the prediction accuracy of the artificial intelligence model can be improved. The optimized artificial intelligence model can be applied to the calibration of the performance parameters of the mobile phone mainboard, which can help the artificial intelligence model to predict the difference between the predicted performance parameters and the actual performance. Through the evaluation and optimization of the artificial intelligence model, the performance of the artificial intelligence model can be effectively evaluated and optimized, so as to ensure that the artificial intelligence model can achieve the expected effect in actual application. The optimized artificial intelligence model can be applied to the calibration of the performance parameters of the mobile phone mainboard, so as to realize the calibration of the performance parameters of the mobile phone mainboard. Finally, the mobile phone mainboard after parameter adjustment is tested, and the degree of coincidence between the prediction of the artificial intelligence model and the actual data is judged according to the test results, so as to ensure the accuracy of the calibration of the performance parameters of the mobile phone mainboard.

[0165] It should be noted that in this text, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.

[0166] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary of the principles and application of the present application. Numerous modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the application.

Claims

1. A method for calibrating performance parameters of a mobile phone motherboard based on artificial intelligence, characterized in that: The following steps are involved: Step 1: Collect relevant performance data of mobile phone motherboards. At the same time, build an artificial intelligence model to pre-process the collected performance data of mobile phone motherboards and integrate it into training set data; The preprocessing further includes: Extract data information before noise removal; obtaining, according to the values ​​of the data information before noise removal, a data distribution graph of the data information before noise removal as a first data distribution graph; Obtaining, according to the values ​​of the data information after the noise is removed, a data distribution graph of the data information after the noise is removed as a second data distribution graph; Comparing the first data distribution graph and the second data distribution graph to obtain a similarity value between the first data distribution graph and the second data distribution graph; Comparing the similarity value between the first data distribution graph and the second data distribution graph with a preset similarity threshold; When the similarity value between the first data distribution graph and the second data distribution graph is not lower than a preset similarity threshold, performing a data quality evaluation on the data information after noise removal; When the similarity value between the first data distribution graph and the second data distribution graph is lower than a preset similarity threshold, traversing each piece of data information in the first data distribution graph and each piece of data information in the second data distribution graph, and obtaining a distribution position of each piece of data information in the first data distribution graph and the second data distribution graph; Obtaining a distribution position straight-line distance according to the distribution position of each piece of data information in the first data distribution graph and the second data distribution graph; The data distortion coefficient is obtained according to the straight-line distance corresponding to the distribution position of each data information in the first data distribution map and the second data distribution map; wherein the data distortion coefficient is obtained by the following formula: Where S represents the data distortion coefficient; k represents the number of data information contained in the first data distribution graph and the second data distribution graph; L i Indicates the straight-line distance of the distribution location corresponding to the i-th data information; L yi represents the minimum straight-line distance allowed for the distribution position corresponding to the i-th data information that meets the similarity threshold; m represents the number of data information whose straight-line distances among the k data information exceed the minimum straight-line distance allowed for their corresponding distribution positions; n represents the number of data information whose straight-line distances among the k data information are 0; q represents the number of data information whose straight-line distances among the k data information do not exceed the minimum straight-line distance allowed for their corresponding distribution positions and whose straight-line distances are non-zero; s 01 、s 02 and s 03 Respectively represent the first adjustment coefficient, the second adjustment coefficient and the third adjustment coefficient; When the data distortion coefficient exceeds a preset coefficient threshold, an abnormal denoising operation alarm is issued; When the data distortion coefficient does not exceed the preset coefficient threshold, the data information before noise removal is re-cleaned; Step 2: Use the training set data to train the artificial intelligence model, so that the trained artificial intelligence model can predict the performance of the mobile phone motherboard; Step 3: After training is completed, the AI ​​model is evaluated and optimized based on the evaluation results; Step 4: Apply the optimized artificial intelligence model to the calibration of the performance parameters of the mobile phone motherboard to achieve the calibration of the performance parameters of the mobile phone motherboard; Step 5: Based on the predictions of the artificial intelligence model, adjust the parameters of the mobile phone motherboard to optimize the performance of the mobile phone motherboard; Step 6: Test the mobile phone motherboard after parameter adjustment to verify the effect of the calibration of the performance parameters of the mobile phone motherboard.

2. The method for calibrating mobile phone motherboard performance parameters based on artificial intelligence according to claim 1, characterized in that: The step 1 specifically includes the following steps: Data collection: Use specialized sensors or testing tools to collect relevant performance data of the mobile phone motherboard. The collected performance data is the basis for model training; Model building: Building AI models based on collected performance data; Data preprocessing: preprocessing the collected performance data, including data cleaning, data conversion, and data reduction; Data integration: The pre-processed performance data is integrated into training set data, which is used to train the established artificial intelligence model.

3. The method for calibrating mobile phone motherboard performance parameters based on artificial intelligence according to claim 2, characterized in that: The preprocessing comprises: Data cleaning: remove errors, missing values, and noise from performance data; Data conversion: converting performance data into a unified data format or data type; Data reduction: Reduce the dimensionality of performance data through feature extraction, reducing computational costs and improving AI model performance.

4. The method for calibrating mobile phone motherboard performance parameters based on artificial intelligence according to claim 1, characterized in that: The first adjustment coefficient is obtained by the following formula: Among them, s 01 represents the first adjustment coefficient; m represents the number of data information whose straight-line distance of the distribution position among the k data information exceeds the minimum straight-line distance allowed by the corresponding distribution position; L 01i Indicates the straight-line distance corresponding to the data information whose straight-line distance of the i-th distribution position exceeds the minimum straight-line distance allowed by its corresponding distribution position; L y01i Indicates that the straight-line distance of the i-th distribution position exceeds the minimum straight-line distance allowed for the distribution position corresponding to the data information; At the same time, the second adjustment coefficient is obtained by the following formula: Among them, s 02 represents the second adjustment coefficient; n represents the number of data information whose distribution position linear distance is 0 among the k data information; L 02xi and L 02hi L represents the linear distance corresponding to the previous data information and the linear distance corresponding to the next data information of the i-th distribution position whose linear distance is 0 respectively; yx02i and L yh02i They respectively represent the minimum straight-line distance allowed at the distribution position corresponding to the previous data information and the minimum straight-line distance allowed at the distribution position corresponding to the next data information; At the same time, the third adjustment coefficient is obtained by the following formula: Among them, s 03 represents the third adjustment coefficient; q represents the number of data information whose straight-line distances among the distribution positions of k data information do not exceed the minimum straight-line distance allowed by their corresponding distribution positions, and whose straight-line distances are non-zero; L 03i Indicates that the straight-line distance of the i-th distribution position does not exceed the minimum straight-line distance allowed by its corresponding distribution position, and the straight-line distance corresponds to the data information with non-zero straight-line distance; L y03i It indicates that the straight-line distance of the i-th distribution position does not exceed the minimum straight-line distance allowed by its corresponding distribution position, and the data information with non-zero straight-line distance corresponds to the minimum straight-line distance allowed by the distribution position.

5. The method for calibrating mobile phone motherboard performance parameters based on artificial intelligence according to claim 4, characterized in that: When the similarity value between the first data distribution graph and the second data distribution graph is not lower than a preset similarity threshold, a data quality evaluation is performed on the data information after the noise is removed, including: When the similarity value between the first data distribution graph and the second data distribution graph is not less than a preset similarity threshold, extracting the signal-to-noise ratio, data integrity, and noise residual of the data information after noise removal; The signal-to-noise ratio, data integrity, and noise residual of the data information after the noise is removed are used to obtain a data quality evaluation parameter corresponding to the data information after the noise is removed; wherein the data quality evaluation parameter corresponding to the data information after the noise is removed is obtained by the following formula: Where W represents the data quality evaluation parameter corresponding to the data information after noise removal; p represents the data integrity of the i-th data information; R i represents the noise residual corresponding to the i-th data information; C i Indicates the maximum allowable noise residual corresponding to the i-th data information; B i represents the signal-to-noise ratio of the data information after noise removal corresponding to the i-th data information; B xi represents the signal-to-noise ratio of the data information before noise removal corresponding to the i-th data information; Comparing the data quality evaluation parameter corresponding to the noise-removed data information with a preset data quality evaluation parameter threshold; When the data quality evaluation parameter corresponding to the data information after noise removal is lower than a preset data quality evaluation parameter threshold, a data quality abnormality alarm is issued.

6. The method for calibrating mobile phone motherboard performance parameters based on artificial intelligence according to claim 1, characterized in that: The step 2 specifically includes the following steps: Substitute the integrated training set data into the artificial intelligence model for training and learning; Artificial intelligence models are based on deep learning algorithms or machine learning algorithms to learn patterns and features in the training set data; By learning patterns and features from the training set data, the AI ​​model can predict the performance of the mobile phone motherboard.

7. The method for calibrating mobile phone motherboard performance parameters based on artificial intelligence according to claim 1, characterized in that: The step three specifically includes the following steps: Performance evaluation: After training, the AI ​​model will be evaluated for performance. The evaluation results will be used to optimize and improve the AI ​​model. Among them, the performance evaluation uses the cross-validation method to divide the training set data into subsets to evaluate the artificial intelligence model; Among them, the cross-validation method includes: Dataset partitioning: Divide the training set data into multiple non-overlapping subsets; Model evaluation: Based on the cross-validation method, multiple non-overlapping subsets of data are substituted into the AI ​​model, and the AI ​​model is repeatedly evaluated using different subsets of data to ultimately obtain the evaluation results; Result analysis: Analyze the evaluation results to identify factors that affect the performance of the AI ​​model, and then optimize and improve the AI ​​model; Model optimization and improvement: Based on the evaluation results of the artificial intelligence model, the artificial intelligence model is optimized and improved. The optimized artificial intelligence model will be used in the calibration of the mobile phone motherboard performance parameters in step four.

8. The method for calibrating mobile phone motherboard performance parameters based on artificial intelligence according to claim 7, characterized in that: Performance evaluation of AI models, including evaluation of their accuracy, stability, scalability, and reliability; and optimization and improvement of AI models, including improving training methods and adding or replacing features.

9. The method for calibrating mobile phone motherboard performance parameters based on artificial intelligence according to claim 1, characterized in that: The step 4 specifically includes the following steps: Apply the optimized AI model to calibrate the performance parameters of mobile phone motherboards; By inputting the current status data of the mobile phone motherboard, the artificial intelligence model predicts the performance of the mobile phone motherboard; Based on the prediction results, point out the optimization suggestions for the mobile phone motherboard; Calibrate the performance parameters of the mobile phone motherboard according to the existing optimization suggestions and determine the parameters that need to be adjusted.

10. The method for calibrating mobile phone motherboard performance parameters based on artificial intelligence according to claim 1, characterized in that: The step six specifically includes the following steps: After the parameters of the mobile phone motherboard are adjusted in step 5, the actual data of the mobile phone motherboard is obtained; Integrate the acquired actual data into test set data; Substitute the integrated test set data into the artificial intelligence model for verification; The test results are used to determine how closely the AI ​​model’s predictions match the actual data.

Images