Link optimization method and device, equipment, storage medium and program product

Abstract

The invention provides a link optimization method and device, equipment, a storage medium and a program product, and relates to the technical field of network communication. The method comprises the following steps: acquiring a plurality of historical data transmitted by a service link and a plurality of target features extracted from the plurality of historical data; performing feature extraction on the plurality of pieces of historical data to obtain feature data of each piece of historical data at each time point; performing model construction according to the feature data of each piece of historical data at each time point to obtain a feature model corresponding to each piece of historical data; and predicting prediction data of each feature model in a second preset time period in the future, and adjusting the plurality of target features according to the plurality of prediction data. According to the method, each piece of historical data is subjected to personalized modeling and prediction, so that the change trend and subtle difference in the data can be flexibly captured, the target features are effectively adjusted, the prediction precision and reliability are improved, the method can better adapt to a complex link transmission environment, and the link optimization effect is improved.

Description

Technical Field

[0001] The present application relates to the field of network communication technology, and in particular to a link optimization method, device, equipment, storage medium and program product. Background Art

[0002] Link optimization refers to optimizing data transmission paths and resource allocation through a series of technologies and methods, such as dynamic routing protocols, load balancing, spectrum management, edge caching, and transmission protocol optimization, in order to improve transmission efficiency, reduce latency, reduce packet loss rates, and improve overall system performance, thereby ensuring that data can be transmitted and processed in the best manner in the network or system.

[0003] In the existing technology, the target features extracted from the historical data of the link are optimized in many ways, including using load balancers to distribute traffic, caching strategies to reduce repeated data transmission, data compression and encryption to improve transmission efficiency, service discovery and dynamic routing to achieve dynamic traffic management, and network protocol optimization and edge computing to reduce latency. By adjusting the target features of the link, higher bandwidth utilization, lower latency and lower error rate can be achieved, thereby improving the overall performance and reliability of network transmission.

[0004] However, when faced with sudden demand fluctuations or resource constraints, existing technologies have slow adjustment speeds and are difficult to quickly optimize and reorganize service links, affecting service quality and user experience. At the same time, existing technologies rely on preset rules or simple algorithms, lack the support of artificial intelligence technologies such as deep learning and reinforcement learning, and have limited intelligence levels, making it difficult to achieve accurate and personalized link optimization. Summary of the invention

[0005] The present application provides a link optimization method, device, equipment, storage medium and program product to solve the problems of low accuracy and low personalization of link optimization methods in the prior art.

[0006] In a first aspect, the present application provides a link optimization method, comprising:

[0007] Acquire multiple historical data transmitted by the service link, and multiple target features extracted from the multiple historical data; wherein each of the historical data refers to data transmitted by the service link within a first preset time period in the past;

[0008] Performing feature extraction on the plurality of historical data to obtain feature data of each historical data at each time point;

[0009] Constructing a model based on the feature data of each historical data at each time point to obtain a feature model corresponding to each historical data;

[0010] Prediction data of each feature model in a second preset time period in the future is predicted, and multiple target features are adjusted according to the multiple prediction data to optimize the performance of the service link.

[0011] In a possible design, the acquiring of a plurality of historical data transmitted by the service link and a plurality of target features extracted from the plurality of historical data includes:

[0012] Acquire a plurality of the historical data transmitted by the service link, and extract original features of each of the historical data;

[0013] Substituting each of the historical data into a preset regression model to obtain a regression coefficient of each of the historical data;

[0014] Each of the original features whose corresponding regression coefficient is greater than a preset value is determined as the target feature.

[0015] In a possible design, the feature extraction is performed on the plurality of historical data to obtain feature data of each historical data at each time point, including:

[0016] Preprocessing the plurality of historical data to obtain preprocessed data corresponding to each of the historical data;

[0017] At each of the time points, feature extraction is performed on each of the preprocessed data to obtain feature data of each of the historical data at each time point.

[0018] In a possible design, adjusting the plurality of target features according to the plurality of prediction data includes:

[0019] Performing abnormal analysis on each of the predicted data to obtain improvement points for each of the predicted data;

[0020] Calculating the adjustment range of each of the predicted data according to the improvement point of each of the predicted data;

[0021] The plurality of target features are adjusted according to the adjustment ranges of the plurality of prediction data.

[0022] In a possible design, after adjusting the plurality of target features according to the plurality of prediction data, the method further includes:

[0023] Acquire multiple feedback data, each of which refers to data transmitted by the service link after a second preset time period in the future;

[0024] respectively calculating the deviation between each of the predicted data and each of the feedback data;

[0025] According to the plurality of deviations, the plurality of feature models are iteratively optimized to optimize the performance of the plurality of feature models.

[0026] In a possible design, the target model is any one of the plurality of feature models;

[0027] For the target model, iteratively optimizing the plurality of feature models according to the plurality of deviations comprises:

[0028] adjusting a parameter of the target model according to at least one of the deviations corresponding to the target model;

[0029] The parameters are continuously adjusted according to the error of the adjusted target model until the error meets a preset standard.

[0030] In a second aspect, the present application provides a link optimization device, including:

[0031] An acquisition module, used to acquire a plurality of historical data transmitted by the service link, and a plurality of target features extracted from the plurality of historical data; wherein each of the historical data refers to data transmitted by the service link within a first preset time period in the past;

[0032] A feature extraction module, used to extract features from the plurality of historical data to obtain feature data of each historical data at each time point;

[0033] A model building module, used to build a model according to the feature data of each historical data at each time point, to obtain a feature model corresponding to each historical data;

[0034] The adjustment module is used to predict the prediction data of each feature model in a second preset time period in the future, and adjust the multiple target features according to the multiple prediction data to optimize the performance of the service link.

[0035] In a possible design, the acquisition module includes:

[0036] An acquisition unit, configured to acquire a plurality of the historical data transmitted by the service link, and extract an original feature of each of the historical data;

[0037] A first calculation unit, used for substituting each of the historical data into a preset regression model to obtain a regression coefficient of each of the historical data;

[0038] The determination unit is used to determine each of the original features whose corresponding regression coefficient is greater than a preset value as the target feature.

[0039] In a possible design, the feature extraction module includes:

[0040] A preprocessing unit, used for preprocessing the plurality of historical data to obtain preprocessed data corresponding to each of the historical data;

[0041] The feature extraction unit is used to extract features from each of the preprocessed data at each of the time points to obtain feature data of each of the historical data at each time point.

[0042] In a possible design, the adjustment module includes:

[0043] An abnormality analysis unit, used for performing abnormality analysis on each of the predicted data to obtain improvement points for each of the predicted data;

[0044] A second calculation unit, used for calculating the adjustment range of each of the predicted data according to the improvement point of each of the predicted data;

[0045] An adjustment unit is used to adjust the multiple target features according to the adjustment ranges of the multiple prediction data.

[0046] In one possible design, the link optimization device further includes:

[0047] A second acquisition module, used to acquire multiple feedback data, each of which refers to data transmitted by the service link after a second preset time period in the future;

[0048] A third calculation module, used to respectively calculate the deviation between each of the predicted data and each of the feedback data;

[0049] The optimization module is used to iteratively optimize the multiple feature models according to the multiple deviations to optimize the performance of the multiple feature models.

[0050] In a possible design, the target model is any one of the plurality of feature models;

[0051] For the target model, the optimization module includes:

[0052] A first adjustment unit, configured to adjust a parameter of the target model according to at least one of the deviations corresponding to the target model;

[0053] The second adjustment unit is used to continuously adjust the parameter according to the error of the adjusted target model until the error meets a preset standard.

[0054] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0055] The memory stores computer-executable instructions;

[0056] When the processor executes the computer-executable instructions stored in the memory, it is used to implement a link optimization method of the first aspect of the invention.

[0057] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement a link optimization method of the invention content of the first aspect.

[0058] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement a link optimization method of the invention content of the first aspect.

[0059] The present application provides a link optimization method, device, equipment, storage medium and program product, the method comprising: obtaining multiple historical data transmitted by the service link, and multiple target features extracted from the multiple historical data; wherein each of the historical data refers to the data transmitted by the service link in the past first preset time period; extracting features from the multiple historical data to obtain feature data of each historical data at each time point; constructing a model based on the feature data of each historical data at each time point to obtain a feature model corresponding to each historical data; predicting the predicted data of each feature model in the future second preset time period, and adjusting the multiple target features based on the multiple predicted data to optimize the performance of the service link. The link optimization method of the present application achieves more refined and accurate prediction by constructing a feature model for each historical data respectively, and using these feature models to predict future data respectively. This method can make full use of the unique features of each historical data, avoiding the generalization error and inaccurate prediction problems that may be caused by using a single feature model in traditional methods. By personalized modeling and prediction of each historical data, the changing trends and subtle differences in the data can be captured more flexibly, so as to more effectively adjust the target features and optimize the performance of the service link. This method improves the accuracy and reliability of prediction, can better adapt to complex and changeable link transmission environments, and ultimately improves the optimization effect of the overall link. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0061] Figure 1 A schematic diagram of an application scenario of the link optimization method provided in an embodiment of the present application;

[0062] Figure 2 Schematic diagram of the link optimization method provided in the embodiment of the present application Figure 1 ;

[0063] Figure 3 Schematic diagram of the link optimization method provided in the embodiment of the present application Figure 2 ;

[0064] Figure 4 A schematic diagram of the structure of a link optimization device provided in an embodiment of the present application;

[0065] Figure 5 An electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0067] In the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference. It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or design. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way. In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more.

[0068] It should be noted that the "at..." in the embodiment of the present application can be the instant when a certain situation occurs, or can be a period of time after a certain situation occurs, and the embodiment of the present application does not specifically limit this. In addition, a link optimization method provided in the embodiment of the present application is only used as an example, and the link optimization method can also include more or less content.

[0069] In order to clearly describe the technical solutions of the embodiments of the present application, some terms and technologies involved in the embodiments of the present application are briefly introduced below:

[0070] Link: refers to a physical or logical channel used to connect two or more devices or nodes in a communication system. The main function of a link is to transmit data, enabling communication between different devices or nodes. The performance and quality of a link directly affects the speed, reliability, and stability of data transmission.

[0071] Link optimization method: is a technology used to improve network communication performance and efficiency. It involves adjusting and optimizing various parameters of network links to achieve higher transmission speed, lower latency, higher reliability and better resource utilization.

[0072] Regression model: An analytical method used to study the relationship between a dependent variable and one or more independent variables. The main purpose of a regression model is to predict the value of the dependent variable through the independent variables, or to understand the impact of the independent variables on the dependent variable.

[0073] Regression coefficient: A parameter in a regression model that quantifies the effect of an independent variable on a dependent variable. In regression analysis, the regression coefficient indicates the contribution of each independent variable to the dependent variable. Specifically, the regression coefficient reflects the expected change in the dependent variable when an independent variable increases by one unit.

[0074] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0075] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0076] In order to clearly understand the technical solution of the present application, the solution of the prior art is first introduced in detail. A link refers to a path or channel used to transmit data in a communication network, and a link can be wired or wireless. During link data transmission, various phenomena may occur in the link, such as bandwidth limitation, delay, jitter, packet loss, and signal attenuation. These phenomena will affect the efficiency and quality of data transmission, resulting in unstable communication or reduced speed. Therefore, it is necessary to optimize the link.

[0077] At present, the link optimization method usually uses load balancers, cache strategies, data compression and other methods to optimize the link. However, when faced with sudden demand fluctuations or resource constraints, the existing technology has a slow adjustment speed and is difficult to quickly optimize and reorganize the service link, affecting the service quality and user experience. At the same time, the existing technology relies on preset rules or simple algorithms, lacks the support of artificial intelligence technologies such as deep learning and reinforcement learning, has a limited level of intelligence, and is difficult to achieve accurate and personalized link optimization. Therefore, the current link optimization method has the problems of low accuracy and low personalization.

[0078] Therefore, in view of the problems of low accuracy and low personalization in the link optimization method in the existing technology, it is found in the research that in order to solve this problem, it is necessary to adjust the optimization strategy according to different application scenarios and user needs: ① By analyzing multiple historical data, extracting key features and building multiple feature models; ② Using artificial intelligence technologies such as deep learning and reinforcement learning to dynamically adjust link parameters to achieve intelligent and adaptive optimization; ③ Among the multiple features of the link, not all features need to be optimized. Among the features of the link, the features that have a greater impact on the link can be calculated, and only these feature moments are adjusted.

[0079] Specific:

[0080] A feature model can be constructed for each historical data, and the feature model can be used to predict the changing trend of the data, and the features corresponding to the historical data can be adjusted according to the changing trend. After adjusting the features of the link, the feature model can be iteratively optimized using the current data of the link to enhance the performance of the feature model. The importance or relevance of each feature of the link to the link can be calculated, and the features with high importance or relevance can be taken as target features, and only the target features of the link can be optimized.

[0081] The link optimization method of the embodiment of the present application achieves more refined and accurate predictions by building unique feature models for each historical data and using these models to predict future data. This method makes full use of the unique characteristics of each historical data to avoid generalization errors and inaccurate predictions that may be caused by a single model. Personalized modeling and prediction can flexibly capture changing trends and subtle differences in the data, thereby more effectively adjusting the target features, improving the accuracy and personalization of the prediction, and optimizing the performance of the link.

[0082] Based on the above creative findings, the technical solution of the present application is proposed.

[0083] The following introduces the application scenarios of the link optimization method provided by the embodiment of the present invention. Figure 1 Schematic diagram of application scenarios of the link optimization method provided in the embodiment of the present application. Figure 1As shown, 101 is a server, 102 is an electronic device, 103 is a link, and the server 101 and the electronic device 102 transmit data via the link 103. During the data transmission process, the electronic device 102 optimizes the link 102 according to the transmitted data.

[0084] The embodiments of the present invention are described below in conjunction with the accompanying drawings.

[0085] Figure 2 Schematic diagram of the link optimization method provided in the embodiment of the present application Figure 1 .like Figure 2 As shown, in this embodiment, the execution subject of the embodiment of the present invention is an electronic device. Then the link optimization method provided by this embodiment includes the following steps:

[0086] S201. Acquire multiple historical data transmitted by a service link, and multiple target features extracted from the multiple historical data; wherein each historical data refers to data transmitted by the service link within a first preset time period in the past.

[0087] Specifically, a data collector is set on the service link to regularly collect the transmission data of the link in a specific time period in the past (i.e., the first preset time period). These data may include, but are not limited to, key performance indicators such as latency, bandwidth utilization, and packet loss rate. These transmission data are stored in a database, and multiple target features are extracted from these historical data using data analysis and processing techniques. These target features can be the results obtained after analyzing the original data, feature engineering, or clustering analysis, such as average latency, maximum bandwidth utilization, packet loss rate distribution, etc.

[0088] S202: Extract features from multiple historical data to obtain feature data of each historical data at each time point.

[0089] Specifically, the collected historical data are usually recorded in time series, which may include timestamps, delays, bandwidth usage, and packet loss rates. Use feature extraction algorithms to process these raw data. For the data at each time point, calculate its features within a certain window, such as the average delay, maximum bandwidth usage, and packet loss rate in the past minute. Through these feature extraction methods, the original time series data can be converted into a set of feature data, which can better describe the status of the service link at each time point.

[0090] S203 , constructing a model according to the feature data of each historical data at each time point, to obtain a feature model corresponding to each historical data.

[0091] Specifically, select appropriate modeling methods and algorithms, such as time series analysis models, machine learning models, or deep learning models. Take the feature data at each time point as input and use these modeling methods to train the data. During the training process, cross-validation, grid search and other techniques can be used to optimize model parameters to ensure the generalization ability and prediction accuracy of the model. For each historical data set, build a feature model that can capture the patterns and regularities in the data. Ultimately, the trained and validated model will be able to accurately describe the feature relationship of each historical data at different time points, thereby forming a feature model corresponding to each historical data.

[0092] S204: predicting the prediction data of each feature model in a second preset time period in the future, and adjusting the multiple target features according to the multiple prediction data to optimize the performance of the service link.

[0093] Specifically, input the time point within the second preset time period in the future into the feature model, and the model will make predictions based on its internal rules and patterns, and the model will generate prediction data for the second preset time period in the future. These prediction data may include key performance indicators such as future latency, bandwidth utilization, and packet loss rate. Analyze the prediction data to identify key factors and potential problems that may affect the performance of the service link, such as predicted high latency or bandwidth bottlenecks. Based on these analysis results, formulate corresponding optimization strategies, which may include dynamically adjusting bandwidth allocation, optimizing routing paths, and adjusting service priorities. Through simulation and verification, select the optimal adjustment plan and apply it to the actual service link. Through the above steps, the prediction data can be effectively used to adjust the target features, thereby optimizing the overall performance of the service link.

[0094] This embodiment provides a link optimization method, which includes: obtaining multiple historical data transmitted by the service link, and multiple target features extracted from the multiple historical data; wherein each historical data refers to data transmitted by the service link in the past first preset time period; extracting features from the multiple historical data to obtain feature data of each historical data at each time point; constructing a model based on the feature data of each historical data at each time point to obtain a feature model corresponding to each historical data; predicting the predicted data of each feature model in the future second preset time period, and adjusting multiple target features based on the multiple predicted data to optimize the performance of the service link. A link optimization method achieves the following technical effects: by constructing feature models for each historical data respectively, and using these models to predict future data respectively, a more refined and accurate prediction is achieved. This method makes full use of the unique features of each historical data, avoiding the generalization error and inaccurate prediction problems that may be caused by using a single feature model in the traditional method. This method can more effectively adjust the target features, optimize the performance of the service link, improve the accuracy and reliability of the prediction, better adapt to the complex and changeable link transmission environment, and improve the optimization effect of the overall link.

[0095] In a possible design, S201, acquiring multiple historical data transmitted by the service link, and multiple target features extracted from the multiple historical data, include:

[0096] S2011. Acquire multiple historical data transmitted by the service link, and extract original features of each historical data.

[0097] Specifically, use network monitoring tools or log systems to continuously record the transmission data of the link within the first preset time period. These data may include key performance indicators such as timestamp, delay, bandwidth utilization and packet loss rate. Use data processing tools or write scripts to extract the original features of each data point from the stored historical data. These original features can be basic indicators directly obtained from the original data, such as the delay value, bandwidth utilization value and packet loss rate value at each time point.

[0098] S2012. Substitute each historical data into a preset regression model to obtain the regression coefficient of each historical data.

[0099] Specifically, select and build an appropriate regression model, which can be a linear regression or a ridge regression. The original features of each historical data extracted are used as input variables and substituted into the preset regression model for training. During the training process, the model will perform parameter estimation based on the input original feature data and the corresponding target variable (such as link performance indicators) and calculate the regression coefficient of each feature. The regression coefficient reflects the degree of influence of each feature on the target variable. Through iterative optimization algorithms (such as gradient descent), the model continuously adjusts the regression coefficient to minimize the prediction error. Finally, after the training is completed, the model outputs the regression coefficient of each historical data.

[0100] S2013. Determine each original feature whose corresponding regression coefficient is greater than a preset value as a target feature.

[0101] Specifically, after completing the regression model training and obtaining the regression coefficient of each historical data, a preset value is set as a threshold, which is used to screen out features that have a significant impact on the target variable (such as link performance indicators). Traverse the regression coefficient of each historical data and compare the size of each regression coefficient with the preset value. If the regression coefficient of an original feature is greater than the preset value, it is considered that the feature has a greater impact on the target variable and is determined as the target feature. In this way, a group of features that are most critical to link performance optimization can be screened out, and those features with less impact or irrelevant features can be removed, thereby simplifying the model and improving the accuracy and efficiency of prediction and optimization.

[0102] The technical effect of the scheme in this embodiment is: through regression analysis, features that have a significant impact on link performance are screened out, and irrelevant or less influential features are removed, thereby simplifying the model, improving the accuracy and efficiency of prediction and optimization, and ultimately optimizing the performance of the service link.

[0103] In a possible design, S202, feature extraction is performed on multiple historical data to obtain feature data of each historical data at each time point, including:

[0104] S2021. Preprocess multiple historical data to obtain preprocessed data corresponding to each historical data.

[0105] Specifically, the multiple historical data collected may contain noise, missing values ​​or outliers, and these problems need to be solved in the preprocessing stage. Clean the data to remove or correct missing values ​​and outliers; normalize or standardize the data to eliminate the differences between different feature dimensions and ensure that the data is compared on the same scale; if the data has a timestamp, time alignment and synchronization can be performed to ensure the temporal consistency of the data. In addition, data smoothing can also be performed, such as using moving averages or filters to reduce random fluctuations in the data. Through the above preprocessing steps, the original historical data can be converted into preprocessed data with higher quality and unified format, providing a reliable data foundation for subsequent feature extraction and model building.

[0106] S2022. Perform feature extraction on each preprocessed data at each time point to obtain feature data of each historical data at each time point.

[0107] Specifically, the preprocessed historical data is first divided into time points, and each time point corresponds to a set of data. For the data at each time point, feature extraction methods are applied to extract key features. Through these methods, feature data that can reflect link performance can be extracted from the data at each time point. Finally, the feature data extracted at each time point is summarized to form complete feature data, which provides input for subsequent model construction and prediction.

[0108] The technical effect of the scheme in this embodiment is: improve data quality through preprocessing steps, eliminate noise and outliers, and extract key features at each time point to ensure that the feature data can accurately reflect the link status, thereby providing high-quality input data for subsequent model construction and prediction, and improving the accuracy and effect of link optimization.

[0109] Figure 3 Schematic diagram of the link optimization method provided in the embodiment of the present application Figure 2 In this embodiment, Figure 2 Based on the provided embodiment, the link optimization method is further explained. The link optimization method includes:

[0110] S301. Acquire multiple historical data transmitted by a service link, and multiple target features extracted from the multiple historical data; wherein each historical data refers to data transmitted by the service link within a first preset time period in the past.

[0111] S302: Extract features from multiple historical data to obtain feature data of each historical data at each time point.

[0112] S303 , constructing a model according to the feature data of each historical data at each time point, to obtain a feature model corresponding to each historical data.

[0113] S304: predict the prediction data of each feature model in a second preset time period in the future.

[0114] S301 - S304 are similar to S201 - S204 and will not be described in detail in this embodiment.

[0115] S305: Perform an abnormality analysis on each predicted data to obtain improvement points for each predicted data.

[0116] Specifically, we first define the standards and indicators for abnormal analysis, such as setting a threshold range or a normal range for historical data. We compare each predicted data with these standards to identify abnormal data points that are outside the normal range or do not meet expectations. For each detected abnormal data point, we further analyze its specific causes and influencing factors to determine the areas that need improvement, i.e., improvement points. These improvement points may include performance bottlenecks in a specific time period or abnormal fluctuations in specific features. In this way, we can systematically identify and locate anomalies in the predicted data, provide targeted improvement suggestions, and thus optimize the performance of the service link.

[0117] S306: Calculate the adjustment range of each predicted data according to the improvement point of each predicted data.

[0118] Specifically, for each improvement point of the predicted data, determine its specific abnormality type and severity, such as excessive latency, insufficient bandwidth, or abnormal packet loss rate. Set the calculation rules for the adjustment range, and then use these rules to perform quantitative analysis on each improvement point to calculate the specific range that needs to be adjusted. For example, if the delay at a certain point in time exceeds the normal range by 10%, the amount of delay that needs to be reduced can be calculated. In this way, a specific adjustment range can be determined for each improvement point of the predicted data, thereby providing clear guidance for subsequent optimization measures, and ultimately achieving effective adjustment of multiple target features and optimizing the performance of the service link.

[0119] S307: Adjust multiple target features according to the adjustment ranges of the multiple prediction data.

[0120] Specifically, the adjustment range of each predicted data is summarized to determine the specific amount by which each target feature needs to be adjusted. Next, based on these adjustment ranges, specific optimization strategies are formulated, such as adjusting network configuration parameters, allocating more bandwidth, optimizing routing paths, or adjusting quality of service settings. These optimization strategies are then gradually implemented, and the performance of the adjusted links is monitored in real time to ensure that the adjustment measures are effective and do not introduce new problems. In this way, multiple target features can be accurately adjusted based on the adjustment range of the predicted data, thereby optimizing the overall performance of the service link.

[0121] S308. Acquire multiple feedback data, where each feedback data refers to data transmitted by the service link after a second preset time period in the future.

[0122] Specifically, after optimizing and adjusting the service link, the transmission data of the link after the second preset time period in the future is continuously monitored and recorded. These data include the actual operation of the link, such as performance indicators such as latency, bandwidth utilization, and packet loss rate. In this way, the actual performance of the link after adjustment can be obtained, thus providing a real and reliable data basis for subsequent deviation analysis and model optimization.

[0123] S309: Calculate the deviation between each predicted data and each feedback data respectively.

[0124] Specifically, collect and organize the feedback data actually transmitted after the second preset time period in the future, which should correspond to the previously predicted data in terms of time and features. Match each predicted data with its corresponding feedback data one by one. Then, calculate the difference between each pair of predicted data and feedback data, which can be achieved through a simple subtraction operation, that is, deviation = feedback data - predicted data. For different features, their deviation values ​​can be calculated separately, such as delay, bandwidth utilization, and packet loss rate. In this way, the difference between the predicted data and the actual data can be quantified, providing a basis for subsequent model optimization.

[0125] S310: Iteratively optimize multiple feature models according to multiple deviations to optimize performance of the multiple feature models.

[0126] Specifically, the deviations between each predicted data and its corresponding feedback data are collected and sorted. These deviations reflect the difference between the model prediction and the actual situation. The distribution and trend of these deviations are analyzed to identify the deficiencies of the model at specific features or time points. Then, using this deviation information, the feature model is iteratively optimized by adjusting model parameters, introducing new features, or improving feature extraction methods. The optimization algorithm in machine learning can be used to gradually reduce the deviation and improve the prediction accuracy of the model. Through multiple iterative optimizations, the performance of the feature model is gradually improved so that it can more accurately reflect the actual situation of the service link, thereby achieving more effective link optimization.

[0127] The technical effect of the scheme in this embodiment is: by systematically identifying and quantifying anomalies in the prediction data, clear adjustment guidance is provided, thereby achieving accurate optimization of the target features. This not only improves the stability and efficiency of link performance, but also responds to and corrects potential problems in a timely manner, ensuring the reliability and efficient operation of the service link; by introducing feedback data and deviation analysis, it is possible to identify and correct errors in the prediction model, gradually improve the accuracy and reliability of the model, thereby achieving more accurate link optimization and improving the overall performance of the service link.

[0128] In one possible design, the target model is any one of multiple feature models.

[0129] For the target model, S310, iteratively optimize multiple feature models according to multiple deviations, including:

[0130] S3101. Adjust parameters of the target model according to at least one deviation corresponding to the target model.

[0131] Specifically, by calculating the gradient of the deviation to the model parameters, the direction and magnitude of the parameter adjustment are determined, and then the model parameters are updated to reduce the prediction error. This process is repeated, and the model parameters are gradually adjusted until the prediction error of the model meets the preset standard or reaches the minimum value. Through this iterative optimization, the accuracy and performance of the target model can be significantly improved, thereby optimizing the service link more effectively.

[0132] S3102. Continue to adjust parameters according to the error of the adjusted target model until the error meets the preset standard.

[0133] Specifically, after each parameter adjustment, the error of the target model is calculated. This is usually achieved by comparing the model prediction value with the actual feedback data. The error can be measured using indicators such as mean square error and mean absolute error. The optimization algorithm is used to calculate the gradient of the error to the model parameters to determine the direction and magnitude of the parameter adjustment. Then, the model parameters are updated based on the gradient information to reduce the error. This process is repeated to continuously monitor and calculate the adjusted model error and gradually optimize the model parameters. This iterative process continues until the model error drops below the preset standard or reaches the minimum value, thereby ensuring that the prediction accuracy and performance of the model meet the optimization requirements.

[0134] The technical effect of the solution in this embodiment is: by continuously iterating and optimizing model parameters, the prediction error is gradually reduced, and the accuracy and reliability of the model are improved. This iterative optimization process can significantly improve the performance of the feature model, thereby achieving more accurate link optimization.

[0135] Figure 4 This is a schematic diagram of the structure of the link optimization device provided in the embodiment of the present application. Figure 4As shown, the link optimization device includes:

[0136] The acquisition module 401 is used to acquire multiple historical data transmitted by the service link and multiple target features extracted from the multiple historical data; wherein each historical data refers to data transmitted by the service link within a first preset time period in the past.

[0137] The feature extraction module 402 is used to extract features from multiple historical data to obtain feature data of each historical data at each time point.

[0138] The model building module 403 is used to build a model according to the feature data of each historical data at each time point to obtain a feature model corresponding to each historical data.

[0139] The adjustment module 404 is used to predict the prediction data of each feature model in the future second preset time period, and adjust the multiple target features according to the multiple prediction data to optimize the performance of the service link.

[0140] In a possible design, the acquisition module 401 includes:

[0141] The acquisition unit is used to acquire multiple historical data transmitted by the service link and extract the original features of each historical data.

[0142] The first calculation unit is used to substitute each historical data into a preset regression model to obtain a regression coefficient of each historical data.

[0143] The determination unit is used to determine each original feature whose corresponding regression coefficient is greater than a preset value as a target feature.

[0144] In one possible design, the feature extraction module 402 includes:

[0145] The preprocessing unit is used to preprocess the multiple historical data to obtain preprocessed data corresponding to each historical data.

[0146] The feature extraction unit is used to extract features from each preprocessed data at each time point to obtain feature data of each historical data at each time point.

[0147] In one possible design, the adjustment module 404 includes:

[0148] The abnormality analysis unit is used to perform abnormality analysis on each prediction data to obtain improvement points for each prediction data.

[0149] The second calculation unit is used to calculate the adjustment range of each prediction data according to the improvement point of each prediction data.

[0150] The adjustment unit is used to adjust the multiple target features according to the adjustment ranges of the multiple prediction data.

[0151] In one possible design, the link optimization device further includes:

[0152] The second acquisition module is used to acquire multiple feedback data, each feedback data refers to data transmitted by the service link after a second preset time period in the future.

[0153] The third calculation module is used to respectively calculate the deviation between each prediction data and each feedback data.

[0154] The optimization module is used for iteratively optimizing the multiple feature models according to the multiple deviations to optimize the performance of the multiple feature models.

[0155] In one possible design, the target model is any one of multiple feature models.

[0156] For the target model, the optimization modules include:

[0157] The first adjustment unit is used to adjust a parameter of the target model according to at least one deviation corresponding to the target model.

[0158] The second adjustment unit is used to continuously adjust the parameters according to the error of the adjusted target model until the error meets the preset standard.

[0159] The link optimization device provided in this embodiment can be executed Figure 2-Figure 3 The technical solution of the method embodiment shown in the figure has the same implementation principle and technical effect as Figure 2-Figure 3 The method embodiments shown are similar and will not be described in detail here.

[0160] Figure 5 The electronic device provided in the embodiment of the present application. Figure 5 As shown, the electronic device includes: at least one processor 510 and a memory 520. The electronic device also includes a communication component 530. The processor 510, the memory 520 and the communication component 530 are connected via a bus 540.

[0161] In a specific implementation process, at least one processor 510 executes the computer execution instructions stored in the memory 520, so that the at least one processor 510 is used to implement the link optimization method of the above embodiment.

[0162] The specific implementation process of the processor 510 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0163] In the above embodiments, it should be understood that the processor 510 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The steps of the method disclosed in the invention may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0164] The memory 520 may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0165] The bus 540 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus 540 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus 540 in the drawings of the present application is not limited to only one bus or one type of bus.

[0166] The above-mentioned functions implemented by the electronic device and the main control device introduce the scheme provided by the embodiment of the present invention. It can be understood that in order to implement the above-mentioned functions, the electronic device or the main control device includes a hardware structure and / or software module corresponding to the execution of each function. In combination with the units and algorithm steps of each example described in the embodiment disclosed in the embodiment of the present invention, the embodiment of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiment of the present invention.

[0167] The embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the link optimization method of the above embodiment. In the specific implementation of the aforementioned multi-protocol label switching message transmission method, each module can be implemented as a processor.

[0168] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0169] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in an electronic device or a main control device.

[0170] An embodiment of the present application also provides a computer program product, including a computer program, which is used to implement the link optimization method of the above embodiment when the computer program is executed by a processor.

[0171] The computer program is stored in a readable storage medium. At least one processor can read the computer program from the readable storage medium. At least one processor executes the computer program to execute the solution provided in any of the above embodiments.

[0172] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by hardware related to program instructions. The above program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above method embodiments are executed; and the above storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0173] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A link optimization method, It is characterized in that include: Acquire multiple historical data transmitted by the service link, and multiple target features extracted from the multiple historical data; wherein each of the historical data refers to data transmitted by the service link within a first preset time period in the past; Performing feature extraction on the plurality of historical data to obtain feature data of each historical data at each time point; Constructing a model based on the feature data of each historical data at each time point to obtain a feature model corresponding to each historical data; Prediction data of each feature model in a second preset time period in the future is predicted, and multiple target features are adjusted according to the multiple prediction data to optimize the performance of the service link.

2. The link optimization method according to claim 1, It is characterized in that The acquiring of a plurality of historical data transmitted by the service link and a plurality of target features extracted from the plurality of historical data includes: Acquire a plurality of the historical data transmitted by the service link, and extract original features of each of the historical data; Substituting each of the historical data into a preset regression model to obtain a regression coefficient of each of the historical data; Each of the original features whose corresponding regression coefficient is greater than a preset value is determined as the target feature.

3. The link optimization method according to claim 1, It is characterized in that The feature extraction of the plurality of historical data to obtain feature data of each historical data at each time point includes: Preprocessing the plurality of historical data to obtain preprocessed data corresponding to each of the historical data; At each of the time points, feature extraction is performed on each of the preprocessed data to obtain feature data of each of the historical data at each time point.

4. The link optimization method according to claim 1, It is characterized in that The adjusting the plurality of target features according to the plurality of prediction data comprises: Performing abnormal analysis on each of the predicted data to obtain improvement points for each of the predicted data; Calculating the adjustment range of each of the predicted data according to the improvement point of each of the predicted data; The plurality of target features are adjusted according to the adjustment ranges of the plurality of prediction data.

5. The link optimization method according to any one of claims 1 to 4, It is characterized in that After adjusting the plurality of target features according to the plurality of prediction data, the method further comprises: Acquire multiple feedback data, each of which refers to data transmitted by the service link after a second preset time period in the future; respectively calculating the deviation between each of the predicted data and each of the feedback data; According to the plurality of deviations, the plurality of feature models are iteratively optimized to optimize the performance of the plurality of feature models.

6. The link optimization method according to claim 5, It is characterized in that The target model is any one of the plurality of feature models; For the target model, iteratively optimizing the plurality of feature models according to the plurality of deviations comprises: adjusting a parameter of the target model according to at least one of the deviations corresponding to the target model; The parameters are continuously adjusted according to the error of the adjusted target model until the error meets a preset standard.

7. A link optimization device, It is characterized in that include: An acquisition module, used to acquire a plurality of historical data transmitted by the service link, and a plurality of target features extracted from the plurality of historical data; wherein each of the historical data refers to data transmitted by the service link within a first preset time period in the past; A feature extraction module, used to extract features from the plurality of historical data to obtain feature data of each historical data at each time point; A model building module, used to build a model according to the feature data of each historical data at each time point, to obtain a feature model corresponding to each historical data; The adjustment module is used to predict the prediction data of each feature model in a second preset time period in the future, and adjust the multiple target features according to the multiple prediction data to optimize the performance of the service link.

8. An electronic device, It is characterized in that include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; When the processor executes the computer-executable instructions stored in the memory, it is used to implement the link optimization method according to any one of claims 1 to 6.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the link optimization method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program is used to implement the link optimization method according to any one of claims 1 to 6.

Images