Network quality optimization method and device, electronic equipment and storage medium

Abstract

The invention provides a network quality optimization method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining multi-dimensional real-time network operation data; based on the multi-dimensional real-time network operation data, training through a network quality evaluation model to obtain a real-time network quality evaluation result output by the network quality evaluation model; and dynamically performing network quality optimization based on the real-time network quality evaluation result. According to the network quality optimization method provided by the invention, the change trend of the network state is accurately perceived by acquiring the multi-dimensional real-time network operation data and utilizing the network quality evaluation model, so that the method can adapt to a complex and changeable network environment to realize accurate evaluation of the network quality, and the network quality is optimized based on the real-time network quality evaluation result. The network quality can be dynamically optimized, the efficient utilization and stability of network resources are ensured, and adaptive and intelligent network management is realized, so that the network operation cost is effectively reduced, and the network investment is saved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a network quality optimization method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of network technology, the impact of network quality on user experience and business efficiency is becoming increasingly significant. Traditional network quality perception methods often rely on fixed thresholds and rules. After perceiving the network quality, operation and maintenance personnel further find network problems and optimize network quality. This is difficult to adapt to complex and changing network environments.

[0003] The high-quality development of operators is inseparable from the effective growth of revenue and profit. If large-scale network investment and technology upgrades cannot generate effective revenue and profit growth, operations will inevitably become unsustainable. Therefore, the process from traditional network quality perception to network quality optimization requires a large amount of network operation costs. Summary of the invention

[0004] The present invention provides a network quality optimization method, device, electronic equipment and storage medium, which are used to solve the problem that the network quality optimization method in the prior art needs to invest a lot of network operation costs.

[0005] In a first aspect, the present invention provides a network quality optimization method, comprising: Obtain multi-dimensional real-time network operation data; Based on the multi-dimensional real-time network operation data, a network quality assessment model is trained to obtain a real-time network quality assessment result output by the network quality assessment model; the network quality assessment model is obtained by model training based on multi-dimensional network operation data samples and their corresponding label data; Based on the real-time network quality evaluation result, network quality optimization is dynamically performed.

[0006] In one embodiment, the multi-dimensional real-time network operation data includes at least bandwidth usage, delay, packet loss rate, jitter and error rate.

[0007] In one embodiment, the real-time network operation data based on the multi-dimensional network is trained through a network quality assessment model to obtain a real-time network quality assessment result output by the network quality assessment model, including: Performing data preprocessing on the multi-dimensional real-time network operation data to obtain multi-dimensional target network operation data; The multi-dimensional target network operation data is input into a network quality assessment model to obtain a real-time network quality assessment result output by the network quality assessment model.

[0008] In one embodiment, the data preprocessing of the multi-dimensional real-time network operation data to obtain multi-dimensional target network operation data includes: Performing data cleaning on the multi-dimensional real-time network operation data to obtain multi-dimensional first intermediate data; Performing data integration on the multi-dimensional first intermediate data to obtain multi-dimensional second intermediate data; The multi-dimensional second intermediate data is normalized to obtain multi-dimensional target network operation data.

[0009] In one embodiment, dynamically optimizing network quality based on the real-time network quality evaluation result includes: If the real-time network quality assessment result meets the preset network abnormality standard, a network problem analysis is performed based on the real-time network quality assessment result to obtain a network problem analysis result; Based on the network problem analysis result, generate a network alarm level; Based on the network problem analysis results and the network alarm level, network quality optimization is dynamically performed.

[0010] In one embodiment, the network quality optimization includes at least routing optimization, bandwidth allocation adjustment and fault early warning.

[0011] In one embodiment, the network quality assessment model is obtained by: Obtain multi-dimensional network operation data samples; Performing network quality analysis based on the multi-dimensional network operation data samples to obtain label data corresponding to the multi-dimensional network operation data samples; Based on the multi-dimensional network operation data samples and their corresponding label data, the preset model is trained to obtain the network quality assessment model.

[0012] In a second aspect, the present invention further provides a network quality optimization device, comprising: The acquisition module is used to obtain multi-dimensional real-time network operation data; A network quality assessment module, which is used to train a network quality assessment model based on the multi-dimensional real-time network operation data to obtain a real-time network quality assessment result output by the network quality assessment model; the network quality assessment model is obtained by model training based on multi-dimensional network operation data samples and their corresponding label data; The network quality optimization module is used to dynamically optimize the network quality based on the real-time network quality evaluation result.

[0013] In a third aspect, the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned network quality optimization methods are implemented.

[0014] In a fourth aspect, the present invention further provides a storage medium, comprising a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the network quality optimization methods described above are implemented.

[0015] The network quality optimization method, device, electronic device and storage medium provided by the present invention can achieve accurate evaluation of network quality by acquiring multi-dimensional real-time network operation data and using a network quality evaluation model to accurately perceive the changing trend of network status, and can adapt to complex and changeable network environments. Based on the real-time network quality evaluation results, the network quality can be dynamically optimized, the network performance and user experience can be improved, the efficient use and stability of network resources can be ensured, and adaptive and intelligent network management can be achieved, thereby effectively reducing network operating costs and saving network investment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of the network quality optimization method provided by the present invention.

[0018] Figure 2 It is a structural schematic diagram of the network quality optimization device provided by the present invention.

[0019] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein.

[0022] Combine the following Figure 1-Figure 3 The present invention describes a network quality optimization method, device, electronic device and storage medium.

[0023] It should be noted that the network quality optimization method provided in the embodiment of the present invention is implemented by a network quality optimization device. The network quality optimization method of the present invention realizes accurate perception and prediction of network quality by intelligently learning and analyzing multi-dimensional real-time network operation data, and then dynamically optimizes network quality according to the perceived network quality evaluation results, thereby optimizing network configuration and improving user experience. The network quality optimization method of the present invention has good scalability and can be extended to multiple network devices and scenarios to achieve comprehensive network quality perception and optimization.

[0024] The embodiment of the present invention describes the network quality optimization method by taking a network quality optimization device as an execution subject as an example. The network quality optimization device is referred to as an evaluation device for short.

[0025] Reference Figure 1 , Figure 1 It is a flow chart of the network quality optimization method provided by the present invention.

[0026] like Figure 1 As shown, the method includes the following: Step 101: Acquire multi-dimensional real-time network operation data; Step 102: Based on the multi-dimensional real-time network operation data, a network quality assessment model is trained to obtain a real-time network quality assessment result output by the network quality assessment model; Step 103: Dynamically optimize network quality based on the real-time network quality evaluation result.

[0027] Specifically, data collection is the first step in network quality perception, and its goal is to obtain key data on network operation. Therefore, the network quality optimization device uses network monitoring tools to capture multi-dimensional real-time network operation data of network equipment. Real-time may involve a time range of several seconds to several minutes. Real-time perception and dynamic optimization of network quality for network operation data within this small time range can ensure that data analysis and network optimization can keep up with actual changes.

[0028] Among them, multi-dimensional real-time network operation data includes at least bandwidth usage, latency, packet loss rate, jitter and error rate. Bandwidth usage refers to the actual usage of upstream and downstream bandwidth collected through the ports or links of network devices, which can be used to understand the utilization and bottlenecks of network resources; latency refers to the measurement of the transmission delay of data packets in the network, including round-trip time and one-way delay, which can be used to evaluate network response speed and performance; packet loss rate refers to the proportion of data packets lost during network transmission, which can be used to reflect the reliability and stability of the network; jitter refers to the measurement of the rate of change of data packet arrival time, which can be used to evaluate the stability of the network; error rate refers to the proportion of data packets that have errors during transmission, which can be used to identify potential hardware problems or signal interference.

[0029] Optionally, network monitoring tools can use Simple Network Management Protocol (SNMP) or traffic monitoring software. Using SNMP or traffic monitoring software to capture network operation data of network devices in real time can provide a comprehensive view of network performance. These tools can detect key indicators such as device traffic, bandwidth usage, latency, and error rates to help identify potential problems in a timely manner.

[0030] Furthermore, the network quality optimization device is based on multi-dimensional real-time network operation data, and is trained through a network quality assessment model to obtain a real-time network quality assessment result output by the network quality assessment model, wherein the network quality assessment model is obtained by model training based on multi-dimensional network operation data samples and their corresponding label data.

[0031] Furthermore, the network quality optimization device dynamically adjusts the network configuration based on the real-time network quality evaluation results to optimize the network quality and improve the user experience.

[0032] The network quality optimization method provided by the present invention obtains multi-dimensional real-time network operation data, uses a network quality evaluation model to accurately perceive the changing trend of the network status, and can adapt to complex and changeable network environments to achieve accurate evaluation of network quality. Based on the real-time network quality evaluation results, the network quality can be dynamically optimized, network performance and user experience can be improved, efficient utilization and stability of network resources can be ensured, and adaptive and intelligent network management can be achieved, thereby effectively reducing network operating costs and saving network investment.

[0033] Further, based on step 102, the real-time network operation data based on the multi-dimensional network is trained through a network quality assessment model to obtain a real-time network quality assessment result output by the network quality assessment model, including: Performing data preprocessing on the multi-dimensional real-time network operation data to obtain multi-dimensional target network operation data; The multi-dimensional target network operation data is input into a network quality assessment model to obtain a real-time network quality assessment result output by the network quality assessment model.

[0034] Specifically, since the original network operation data may contain noise, outliers or inconsistent formats, the network quality optimization device will perform data preprocessing on the multi-dimensional real-time network operation data to obtain multi-dimensional target network operation data.

[0035] Furthermore, the network quality optimization device inputs the multi-dimensional target network operation data into the network quality assessment model, analyzes and learns the distribution law and change trend of the network quality through the network quality assessment model, and obtains the real-time network quality assessment result output by the network quality assessment model. This network quality assessment result is for the multi-dimensional network status, that is, the network quality assessment result at least includes the network quality corresponding to the network operation data such as bandwidth usage, delay, packet loss rate, jitter and error rate, and can also include the overall network quality that integrates the network operation data such as bandwidth usage, delay, packet loss rate, jitter and error rate.

[0036] Through the learning and analysis of the artificial intelligence model, the embodiment of the present invention can more accurately perceive the changing trend of network quality, avoid misjudgment and missed judgment, and improve the accuracy of network quality perception. In addition, the artificial intelligence model can automatically adjust the perception strategy according to changes in the network environment to adapt to the complex and changeable network environment.

[0037] Furthermore, the data preprocessing is performed on the multi-dimensional real-time network operation data to obtain multi-dimensional target network operation data, including: Performing data cleaning on the multi-dimensional real-time network operation data to obtain multi-dimensional first intermediate data; Performing data integration on the multi-dimensional first intermediate data to obtain multi-dimensional second intermediate data; The multi-dimensional second intermediate data is normalized to obtain multi-dimensional target network operation data.

[0038] It should be noted that data preprocessing of the acquired network operation data usually involves operations such as data cleaning, data integration and normalization to form a standard data set to facilitate subsequent artificial intelligence model training and analysis.

[0039] Specifically, the network quality optimization device performs data cleaning on multi-dimensional real-time network operation data to obtain multi-dimensional first intermediate data. This process is to ensure the quality and consistency of the data.

[0040] Optionally, data cleaning can include specific operations such as removing duplicate data, handling missing values, outlier detection, and format standardization.

[0041] Furthermore, the network quality optimization device integrates the multi-dimensional first intermediate data to obtain multi-dimensional second intermediate data. This process is to integrate data from different sources into a unified data set.

[0042] Furthermore, the network quality optimization device normalizes the multi-dimensional second intermediate data to obtain multi-dimensional target network operation data. This process is to convert data of different dimensions into the same dimension to facilitate subsequent data analysis and model training.

[0043] The embodiment of the present invention generates multi-dimensional target network operation data through data cleaning, data integration and normalization processing, which can effectively solve the problems of noise, outliers or inconsistent formats in the original network data, etc., which not only improves the quality of the data, but also provides a solid data foundation for subsequent analysis, and provides important data support for network management and optimization.

[0044] Further, based on step 103, dynamically optimizing network quality based on the real-time network quality evaluation result includes: If the real-time network quality assessment result meets the preset network abnormality standard, a network problem analysis is performed based on the real-time network quality assessment result to obtain a network problem analysis result; Based on the network problem analysis result, generate a network alarm level; Based on the network problem analysis results and the network alarm level, network quality optimization is dynamically performed.

[0045] Specifically, the network quality optimization device compares the real-time network quality evaluation result with the preset network anomaly standard.

[0046] The preset network anomaly standard is set according to the actual situation. For example, it is set that a network anomaly will occur when the packet loss rate exceeds a threshold and the delay is too high at the same time.

[0047] Furthermore, if the results of the network quality assessment meet the preset network anomaly standards, the network quality optimization device uses a variety of analysis tools and methods to analyze the network problems and obtain network problem analysis results, wherein the network problem analysis results include various types of network anomalies, such as insufficient bandwidth (indicating that the network bandwidth is overloaded), delay problems (indicating abnormal transmission delays), packet loss (indicating frequent data packet losses), and equipment failure (indicating that the network equipment is faulty or misconfigured).

[0048] Optionally, use a variety of analysis tools and methods to analyze network problems, including traffic analysis, performance benchmarking, log analysis, network topology analysis, etc. Traffic analysis is to check network traffic patterns and identify traffic peaks; performance benchmarking is to benchmark network devices and links to detect performance bottlenecks; log analysis is to analyze the log files of network devices to find abnormal events and error information; network topology analysis is to check the network topology to find possible configuration errors or bottleneck locations.

[0049] Furthermore, the network quality assessment device matches the network problem analysis results with the preset alarm level rules to obtain the network alarm level corresponding to the network problem analysis results, so as to take corresponding measures, wherein the preset alarm level rules are set according to actual conditions, and the preset alarm level rules may include the correlation mapping relationship between the severity of the network problem, the scope of impact and the network alarm level.

[0050] Optionally, the network alarm level can be divided into severe alarm level, medium alarm level and minor alarm level according to the severity from high to low. The severe alarm level reflects that the network problem will affect the core business functions or large-scale users and needs to be handled immediately; the medium alarm level reflects that the network problem will affect some functions and needs attention and adjustment; the minor alarm level has little impact on the business and can be solved in regular maintenance.

[0051] Furthermore, the network quality optimization device dynamically optimizes the network quality based on the network problem analysis results and the network alarm level.

[0052] Optionally, network quality optimization may include route optimization, bandwidth allocation adjustment, and fault warning. Route optimization can select the best route path based on the network quality evaluation results to avoid network congestion and delay. Bandwidth allocation can dynamically adjust bandwidth allocation based on the needs of each business and the real-time situation of network quality to ensure the smooth operation of key businesses. Fault warning can issue a warning notification in advance when the model predicts that a problem is about to occur in the network, so that timely measures can be taken to avoid the failure.

[0053] For different network alarm levels, different measures will be taken by the three optimization methods of route optimization, bandwidth allocation adjustment and fault warning.

[0054] Route optimization will take different measures according to different network alarm levels. At the severe alarm level, comprehensive route optimization is adopted, and it may even be necessary to configure redundant routes or redesign the network topology. Load balancing technology can be considered to immediately alleviate network congestion and ensure the continuity and stability of key businesses. At the medium alarm level, a more in-depth route analysis is performed to select a better route path. It may be necessary to reconfigure the settings of routers or switches to reduce delays and jitters and ensure that network performance is within an acceptable range. At the minor alarm level, monitor changes in network traffic and conduct regular route checks. Simple route adjustments can be made to balance traffic in order to avoid potential congestion or delay problems in the network and maintain network stability.

[0055] Bandwidth allocation adjustment will take different measures according to different network alarm levels. At the severe alarm level, comprehensive bandwidth adjustment and expansion will be taken. It may be necessary to introduce additional bandwidth resources or optimize the network structure to handle high loads in order to completely solve the bandwidth bottleneck problem and ensure the overall performance and reliability of the network. At the medium alarm level, bandwidth allocation will be adjusted dynamically to give priority to the bandwidth needs of key businesses. It may be necessary to temporarily increase bandwidth or reallocate existing bandwidth in order to ensure the smooth operation of key businesses and reduce the impact on other businesses. At the minor alarm level, the bandwidth allocation strategy will be adjusted to balance the load, but the adjustment will be small. It may only optimize the bandwidth usage of certain businesses in order to maintain network traffic within the normal range and prevent the problem from further deteriorating.

[0056] Fault warning will issue emergency warning notifications according to different network alarm levels, provide specific solution steps and possible impacts, and initiate emergency response procedures, including mobilizing more resources to solve the problem, in order to respond quickly and take effective measures to prevent network failures from causing serious impacts on the business. At the medium alarm level, a detailed warning notification will be issued, including the possible scope of impact and recommended measures. It may be necessary to prepare backup plans and conduct related tests in order to provide timely information so that network administrators can take quick measures to prevent network problems from further expanding. At the minor alarm level, a standard warning notification will be issued to remind network administrators to pay attention to changes in network status, monitor the situation and prepare countermeasures, in order to warn in advance to prevent potential small problems from turning into big problems.

[0057] The embodiments of the present invention accurately identify and respond to network anomalies through real-time network quality assessment and problem analysis, automatically analyze network problems based on real-time data, and generate corresponding alarm levels, thereby dynamically optimizing network quality. It can not only solve network problems in a timely manner and improve the efficiency of handling network faults, but also improve the stability and performance of the network and ensure the efficient use of network resources.

[0058] Furthermore, the network quality assessment model is obtained in the following manner: Obtain multi-dimensional network operation data samples; Performing network quality analysis based on the multi-dimensional network operation data samples to obtain label data corresponding to the multi-dimensional network operation data samples; Based on the multi-dimensional network operation data samples and their corresponding label data, the preset model is trained to obtain the network quality assessment model.

[0059] Specifically, the network quality optimization device obtains multi-dimensional network operation data samples of the network equipment, wherein the multi-dimensional network operation data samples at least include bandwidth usage samples, delay samples, packet loss rate samples, jitter samples and error rate samples.

[0060] Furthermore, the network quality optimization device performs data preprocessing on the acquired multi-dimensional network operation data samples to obtain multi-dimensional target network operation data samples after data preprocessing.

[0061] Furthermore, the network quality optimization device performs network quality analysis based on the multi-dimensional target network operation data samples to obtain network quality analysis results of the multi-dimensional target network operation data samples, and determines the network quality analysis results of the multi-dimensional target network operation data samples as label data corresponding to the multi-dimensional target network operation data samples.

[0062] Furthermore, the network quality optimization device trains a preset model based on multi-dimensional target network operation data samples and their corresponding label data to obtain a network quality assessment model, wherein the preset model is selected according to the characteristics of the network problem and the characteristics of the data, and a suitable deep learning model is selected, such as a recurrent neural network (RNN), a long short-term memory network (LSTM) or a convolutional neural network (CNN).

[0063] During the model training process, the model parameters and structure are adjusted so that the model can accurately learn the distribution law and change trend of network quality. During the model evaluation process, the trained model is evaluated using the validation set to check the accuracy and generalization ability of the model. If the model performance is poor, the model parameters can be readjusted or other models can be tried.

[0064] The embodiments of the present invention utilize artificial intelligence technologies such as deep learning to construct a network quality perception model. By training the model with a large amount of historical data, the model can learn the distribution patterns and changing trends of network quality, so that the trained model can accurately evaluate network quality, help monitor and optimize network performance in real time, and thus improve network reliability and user experience.

[0065] The network quality optimization device provided by the present invention is described below. The network quality optimization device described below and the network quality optimization method described above can be referenced to each other.

[0066] Reference Figure 2 , Figure 2 It is a structural schematic diagram of the network quality optimization device provided by the present invention.

[0067] The network quality optimization device comprises: The acquisition module 210 is used to acquire multi-dimensional real-time network operation data.

[0068] The network quality assessment module 220 is used to train a network quality assessment model based on the multi-dimensional real-time network operation data to obtain a real-time network quality assessment result output by the network quality assessment model; the network quality assessment model is obtained by model training based on multi-dimensional network operation data samples and their corresponding label data.

[0069] The network quality optimization module 230 is used to dynamically optimize the network quality based on the real-time network quality evaluation result.

[0070] The network quality optimization device provided by the present invention acquires multi-dimensional real-time network operation data and uses a network quality evaluation model to accurately perceive the changing trend of the network status. It can adapt to complex and changeable network environments to achieve accurate evaluation of network quality. Based on the real-time network quality evaluation results, it can dynamically optimize network quality, improve network performance and user experience, ensure efficient use and stability of network resources, and achieve adaptive and intelligent network management, thereby effectively reducing network operating costs and saving network investment.

[0071] Furthermore, the network quality assessment module 220 is also used for: Performing data preprocessing on the multi-dimensional real-time network operation data to obtain multi-dimensional target network operation data; The multi-dimensional target network operation data is input into a network quality assessment model to obtain a real-time network quality assessment result output by the network quality assessment model.

[0072] Furthermore, the network quality assessment module 220 is also used for: Performing data cleaning on the multi-dimensional real-time network operation data to obtain multi-dimensional first intermediate data; Performing data integration on the multi-dimensional first intermediate data to obtain multi-dimensional second intermediate data; The multi-dimensional second intermediate data is normalized to obtain multi-dimensional target network operation data.

[0073] Furthermore, the network quality optimization module 230 is also used for: If the real-time network quality assessment result meets the preset network abnormality standard, a network problem analysis is performed based on the real-time network quality assessment result to obtain a network problem analysis result; Based on the network problem analysis result, generate a network alarm level; Based on the network problem analysis results and the network alarm level, network quality optimization is dynamically performed.

[0074] Furthermore, the network quality optimization device is also used for: Obtain multi-dimensional network operation data samples; Performing network quality analysis based on the multi-dimensional network operation data samples to obtain label data corresponding to the multi-dimensional network operation data samples; Based on the multi-dimensional network operation data samples and their corresponding label data, the preset model is trained to obtain the network quality assessment model.

[0075] Figure 3 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the network quality optimization method, which includes: obtaining multi-dimensional real-time network operation data; based on the multi-dimensional real-time network operation data, training through a network quality evaluation model to obtain a real-time network quality evaluation result output by the network quality evaluation model; the network quality evaluation model is obtained by model training based on multi-dimensional network operation data samples and their corresponding label data; based on the real-time network quality evaluation result, dynamically optimizing the network quality.

[0076] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0077] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the network quality optimization method provided in the above-mentioned embodiments, and the method includes: obtaining multi-dimensional real-time network operation data; based on the multi-dimensional real-time network operation data, training through a network quality assessment model to obtain a real-time network quality assessment result output by the network quality assessment model; the network quality assessment model is obtained by model training based on multi-dimensional network operation data samples and their corresponding label data; based on the real-time network quality assessment result, dynamically performing network quality optimization.

[0078] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the network quality optimization method provided in the above-mentioned embodiments, the method comprising: obtaining multi-dimensional real-time network operation data; based on the multi-dimensional real-time network operation data, training a network quality assessment model to obtain a real-time network quality assessment result output by the network quality assessment model; the network quality assessment model is obtained by model training based on multi-dimensional network operation data samples and their corresponding label data; based on the real-time network quality assessment result, dynamically performing network quality optimization.

[0079] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those of ordinary skill in the art may understand and implement the present invention without creative effort.

[0080] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A network quality optimization method, characterized in that: include: Obtain multi-dimensional real-time network operation data; Based on the multi-dimensional real-time network operation data, a network quality assessment model is trained to obtain a real-time network quality assessment result output by the network quality assessment model; the network quality assessment model is obtained by model training based on multi-dimensional network operation data samples and their corresponding label data; Based on the real-time network quality evaluation result, network quality optimization is dynamically performed.

2. The network quality optimization method according to claim 1, characterized in that: The multi-dimensional real-time network operation data includes at least bandwidth usage, delay, packet loss rate, jitter and error rate.

3. The network quality optimization method according to claim 1, characterized in that: The real-time network operation data based on the multi-dimensional network is trained through a network quality assessment model to obtain a real-time network quality assessment result output by the network quality assessment model, including: Performing data preprocessing on the multi-dimensional real-time network operation data to obtain multi-dimensional target network operation data; The multi-dimensional target network operation data is input into a network quality assessment model to obtain a real-time network quality assessment result output by the network quality assessment model.

4. The network quality optimization method according to claim 3, characterized in that: The performing data preprocessing on the multi-dimensional real-time network operation data to obtain multi-dimensional target network operation data includes: Performing data cleaning on the multi-dimensional real-time network operation data to obtain multi-dimensional first intermediate data; Performing data integration on the multi-dimensional first intermediate data to obtain multi-dimensional second intermediate data; The multi-dimensional second intermediate data is normalized to obtain multi-dimensional target network operation data.

5. The network quality optimization method according to claim 1, characterized in that: The dynamically optimizing network quality based on the real-time network quality evaluation result includes: If the real-time network quality assessment result meets the preset network abnormality standard, a network problem analysis is performed based on the real-time network quality assessment result to obtain a network problem analysis result; Based on the network problem analysis result, generate a network alarm level; Based on the network problem analysis results and the network alarm level, network quality optimization is dynamically performed.

6. The network quality optimization method according to claim 5, characterized in that: The network quality optimization at least includes routing optimization, bandwidth allocation adjustment and fault early warning.

7. The network quality optimization method according to any one of claims 1 to 6, characterized in that: The network quality assessment model is obtained in the following way: Obtain multi-dimensional network operation data samples; Performing network quality analysis based on the multi-dimensional network operation data samples to obtain label data corresponding to the multi-dimensional network operation data samples; Based on the multi-dimensional network operation data samples and their corresponding label data, the preset model is trained to obtain the network quality assessment model.

8. A network quality optimization device, characterized in that: include: The acquisition module is used to obtain multi-dimensional real-time network operation data; A network quality assessment module, which is used to train a network quality assessment model based on the multi-dimensional real-time network operation data to obtain a real-time network quality assessment result output by the network quality assessment model; the network quality assessment model is obtained by model training based on multi-dimensional network operation data samples and their corresponding label data; The network quality optimization module is used to dynamically optimize the network quality based on the real-time network quality evaluation result.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the network quality optimization method according to any one of claims 1 to 7 are implemented.

10. A storage medium, comprising a non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the network quality optimization method according to any one of claims 1 to 7 are implemented.

Images