Network optimization method and device, terminal equipment and computer readable storage medium

Abstract

The application discloses a network optimization method and device, terminal equipment and a computer readable storage medium. The method comprises the following steps: acquiring current network data of an access point and a network load value of the access point; determining a first failure probability of the access point according to the current network data; correcting the first failure probability based on the network load value to obtain a second failure probability; and optimizing the network of the access point according to the second failure probability. The method can correct the first failure probability in combination with the predetermined network load value under the premise of ensuring real-time performance, improve the response speed and accuracy of network optimization, and adjust in advance before network failure occurs, thereby improving user experience.

Description

Technical Field

[0001] This application relates to the field of network communication data processing technology, specifically to a network optimization method, apparatus, terminal equipment, and computer-readable storage medium. Background Technology

[0002] Existing network optimization solutions include passive optimization schemes, which repair network failures after they occur, and proactive optimization schemes, which predict future network conditions based on current network data and optimize the network in advance. While proactive network optimization schemes can predict network changes and take corresponding measures to some extent, they still have shortcomings. For example, customer devices have limited computing power and cannot efficiently handle complex prediction tasks, while the cloud, although possessing powerful computing capabilities, has a certain transmission latency due to data needing to be transmitted over the network, resulting in long response times and making it difficult to meet the needs of real-time network optimization. Summary of the Invention

[0003] This application provides a network optimization method, apparatus, terminal device, and computer-readable storage medium. It can improve the response speed and accuracy of network optimization by combining a predetermined network load value to correct the first failure probability while ensuring real-time performance. It can also make adjustments in advance before network failures occur, thereby improving the user experience.

[0004] The technical solution adopted by this invention to solve the problem is as follows: On the one hand, this application provides a network optimization method, including: Obtain the current network data and network load value of the access point; Based on current network data, determine the first probability of failure of the access point; The first failure probability is corrected based on the network load value to obtain the second failure probability; The network at the access point is optimized based on the second failure probability.

[0005] In some embodiments of this application, determining the first failure probability of an access point based on current network data includes: The current network data is input into the first processing model, and the first failure probability is output through the first processing model. Network load values ​​are obtained as follows: Historical network data is input into the second processing model, and the network load value is output through the second processing model.

[0006] In some embodiments of this application, a second failure probability is obtained by correcting the first failure probability based on the network load value, including: The correction value is determined based on the first failure probability and the network load value; The second failure probability is obtained by weighting and fusing the first failure probability and the corrected value.

[0007] In some embodiments of this application, the correction value is determined based on the first failure probability and the network load value, including: Obtain the sensitivity coefficient; The difference between the first failure probability and the network load value is used as the first value; The product of the sensitivity coefficient and the first value is used as the second value; The third value is obtained by exponentiation of the second value with the opposite of the natural constant. The ratio obtained by dividing the first failure probability by the sum of the third value and a predetermined constant is used as the correction value.

[0008] In some embodiments of this application, the network of the access point is optimized based on a second failure probability, including: Based on the second failure probability, the network optimization strategy for the access point is obtained; Based on network optimization strategies, the network at the access point is optimized.

[0009] In some embodiments of this application, a network optimization strategy for the access point is obtained based on a second failure probability, including: When the second failure probability is greater than or equal to the first threshold, a multi-objective optimization algorithm is used to solve multiple decision variables to determine the first optimization strategy; the first optimization strategy is determined as the network optimization strategy of the access point. If the second failure probability is less than the first threshold and greater than or equal to the second threshold, the second optimization strategy is determined as the network optimization strategy for the access point.

[0010] In some embodiments of this application, a multi-objective optimization algorithm is used to solve for multiple decision variables to determine a first optimization strategy, including: Based on the pre-set objective optimization function, a multi-objective optimization algorithm is used to solve multiple decision variables to obtain the objective solution set; Obtain the current usage scenario of the access point; The solution that matches the current use case is selected from the target solution set as the first optimization strategy.

[0011] Secondly, embodiments of the present invention also provide a network optimization device, comprising: The acquisition module is used to acquire the current network data and network load value of the access point; The determination module is used to determine the first failure probability of the access point based on the current network data; The correction module is used to correct the first failure probability based on the network load value to obtain the second failure probability; The optimization module is used to optimize the network of the access point based on the second failure probability.

[0012] Thirdly, this application also provides a terminal device, which includes: One or more processors; Memory; and One or more applications, wherein the applications are stored in memory and configured to be executed by a processor to implement the network optimization method of any of the first aspects.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps of the network optimization method of any of the first aspects.

[0014] The beneficial effects of this invention are as follows: By acquiring the current network data and network load value of the access point, predicting the first failure probability of the access point based on the current network data, and then correcting the first failure probability based on the network load value to obtain the second failure probability, and then performing optimization measures based on the corrected failure probability, it is possible to improve the response speed and accuracy of network optimization by combining the first failure probability with the predetermined network load value while ensuring real-time performance. This allows for adjustments to be made in advance before network failures occur, thereby improving the user experience. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of a network optimization system provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating one embodiment of the network optimization method provided in this invention. Figure 3 This is a schematic diagram of the structure of the end-to-cloud joint network optimization system provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the process for determining and implementing optimization strategies provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the data processing flow provided in an embodiment of the present invention; Figure 6 This is a schematic block diagram of the network optimization device provided in the embodiments of the present invention; Figure 7 This is a schematic diagram of an embodiment of the terminal device provided in this invention. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] In the description of this application, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of the stated features.

[0019] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0020] It should be noted that since the method in this application embodiment is executed in a terminal device, the processing objects of each terminal device exist in the form of data or information, such as time, which is essentially time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they are all corresponding data that exist so that the terminal device can process them. Specific details will not be elaborated here.

[0021] This application provides a network optimization method, apparatus, terminal device, and computer-readable storage medium, which will be described in detail below.

[0022] Please see Figure 1 , Figure 1 This is a schematic diagram of a network optimization system provided in an embodiment of this application. The network optimization system may include a terminal device 100, which integrates a network optimization device, such as... Figure 1Terminal devices in the process.

[0023] In this embodiment, the terminal device 100 is mainly used to obtain the current network data and network load value of the access point; determine the first failure probability of the access point based on the current network data; correct the first failure probability based on the network load value to obtain the second failure probability; and optimize the network of the access point based on the second failure probability. Under the premise of ensuring real-time performance, the first failure probability can be corrected in conjunction with the predetermined network load value, thereby improving the response speed and accuracy of network optimization, making adjustments in advance before network failures occur, and improving user experience.

[0024] In this embodiment, the terminal device 100 can be an independent server, a server network, or a server cluster. For example, the terminal device 100 described in this embodiment includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0025] It is understood that the terminal device 100 used in the embodiments of this application can be a device that includes both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. Such a device may include: cellular or other communication devices having a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. Specifically, the terminal device 100 may be a desktop terminal or a mobile terminal, and the terminal device 100 may also be one of a mobile phone, tablet computer, laptop computer, etc.

[0026] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario of the solution in this application and does not constitute a limitation on the application scenario of the solution in this application. Other application environments may include those that are more specific to this application. Figure 1 The number of more or fewer terminal devices shown, for example Figure 1 Only one terminal device is shown in the diagram. It is understood that the network optimization system may also include one or more other services, which are not specified here.

[0027] In addition, such as Figure 1 As shown, the network optimization system may also include a memory 200 for storing data such as fault probabilities, such as first fault probability, second fault probability, etc., network load values, current network data, etc.

[0028] It should be noted that, Figure 1The schematic diagram of the network optimization system shown is merely an example. The network optimization system and scenario described in this application are intended to more clearly illustrate the technical solutions of this application and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of network optimization systems and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0029] First, this application provides a network optimization method. The execution subject of the network optimization method is a network optimization device, which is applied to a terminal device. The network optimization method includes: obtaining the current network data and network load value of the access point; determining a first failure probability of the access point based on the current network data; correcting the first failure probability based on the network load value to obtain a second failure probability; and optimizing the network of the access point based on the second failure probability.

[0030] like Figure 2 The diagram shown is a flowchart of an embodiment of the network optimization method in this application. The network optimization method may include the following steps S201 to S203, as detailed below: Step S201: Obtain the current network data and network load value of the access point.

[0031] In one specific embodiment, an access point is a node in the network that connects user equipment to the wider network; specifically, it can be a router or base station. Current network data reflects the real-time operating status of the access point and may include Received Signal Strength Indicator (RSSI), throughput, number of connected devices, power consumption, etc., without specific limitations in this application. The network load value can be a benchmark value derived from historical data analysis, measuring the network load of the access point over a given period. The network load value can be predetermined, eliminating the need for real-time calculations and thus reducing the computational requirements.

[0032] Step S202: Determine the first failure probability of the access point based on the current network data.

[0033] In one specific embodiment, the first failure probability is the likelihood of a network failure or performance degradation at the access point. This first failure probability can be predicted by analyzing the access point's current network data within a short period. That is, based on the current network data obtained in step S201, such as signal strength and throughput, the risk of future access point failures can be assessed according to the current network conditions, thus deriving the first failure probability.

[0034] Step S203: Correct the first fault probability based on the network load value to obtain the second fault probability.

[0035] In one specific embodiment, the network load value can be derived from the analysis of historical network data, representing the trend of network load changes over a period of time, and can serve as a relatively stable network load reference value.

[0036] In this step, the network load value can be used to correct the initial failure probability determined solely by current network data. Specifically, the network load value can be seen as a trend prediction of the network's potential load over a certain period. Therefore, by incorporating the network load value to correct the already generated initial failure probability, a more accurate assessment of the network's future risks can be made. In other words, the network load value does not directly affect the failure probability itself, but rather serves as an auxiliary prediction result, correcting the failure probability calculated based on real-time network data to improve prediction accuracy.

[0037] Step S204: Optimize the network of the access point according to the second failure probability.

[0038] In one specific embodiment, after determining a relatively accurate network failure probability, corresponding optimization measures can be taken based on the specific failure probability value to adjust the network at the access point. This aims to optimize the network before failures occur, minimizing the risk of failure. Specific strategies for network optimization may include channel switching, power adjustment, and priority adjustment to ensure network stability and performance. Therefore, this invention enables accurate early identification of potential failures and effective intervention before they occur, reducing the frequency of network failures and improving user experience.

[0039] In one specific implementation, determining the first failure probability of the access point based on the current network data includes: inputting the current network data into a first processing model and outputting the first failure probability through the first processing model; the network load value is obtained by inputting historical network data into a second processing model and outputting the network load value through the second processing model.

[0040] In this embodiment, a model can be used to process the data. Specifically, an extreme gradient boosting (XGBoost) algorithm can be used to construct a first processing model to analyze the current network data collected in the short term, identify abnormal states or congestion probabilities in the near future, and output a first failure probability. A long short-term memory (LSTM) network can be used as a second processing model to analyze long-term historical time-series data, predict the trend of network load changes in the future, and output a baseline network load value for the corresponding time period.

[0041] Extreme Gradient Boosting (XGBoost) constructs multiple decision trees, sequentially weighting and optimizing the results of each tree to obtain the final prediction. The first processing model built by the XGBoost algorithm can quickly identify abnormal patterns in the current network data, predict potential short-term failures or congestion at access points, and output the first probability of failure for each access point. XGBoost consumes relatively little computational power and can frequently process the currently collected network data; for example, it can process data every five minutes to quickly respond to network changes and promptly detect potential failure risks.

[0042] The XGBoost algorithm takes the current network data as input and outputs the sum of the outputs of K regression trees. By converting these values ​​into probabilities, we can obtain the probability that the network will experience severe congestion or deterioration in the future (e.g., within the next minute).

[0043] Long Short-Term Memory (LSTM) networks are well-suited for processing time-series data, capable of remembering long-term information to predict historical trends. LSTM, as a secondary processing model, analyzes long-term historical network data to identify periodic fluctuations and tidal effects in traffic, thereby predicting future network load trends and outputting a baseline network load value. This value reflects the overall network load over a future period, allowing for correction against the probability of initial failures. LSTM networks consume significant computational power and require substantial historical data; therefore, processing can be performed periodically, such as hourly or every few hours, with the results applicable to the next hour or several hours.

[0044] The LSTM network utilizes long-term historical data to uncover periodic patterns in traffic and interference (e.g., "peak hours are around 8 PM every night"), providing trend references for the real-time prediction (XGBoost) layer. The input layer processes the input historical network data into a data matrix, including time and feature dimensions; the hidden layer consists of 2-3 stacked LSTM units, each containing several memory units for forgetting old information and remembering new information; the output layer, the fully connected layer, outputs the predicted values ​​for the next k time steps as the baseline for the prediction load.

[0045] XGBoost models provide short-term fault risk prediction, enabling rapid detection of network anomalies and quick responses. LSTM networks, on the other hand, analyze long-term historical data to predict network load trends, providing a more stable and accurate reference value for fault probability correction. Combining these two approaches achieves more precise network fault prediction. In practical applications, LSTM can output network load values ​​hourly. Within this hour, the XGBoost model generates a first fault probability every five minutes. These twelve first fault probabilities can be combined with the corresponding network load values ​​for that hour to calculate a more accurate second fault probability, achieving more efficient network optimization and fault prediction, significantly improving network stability and user experience.

[0046] In one specific implementation, the first fault probability is corrected based on the network load value to obtain the second fault probability, including: determining the correction value based on the first fault probability and the network load value; and weighting and fusing the first fault probability and the correction value to obtain the second fault probability.

[0047] In this embodiment, a correction value can first be determined based on the first failure probability and the network load value. Then, the first failure probability and this correction value are weighted and fused to obtain the second failure probability. The correction value reflects how the original failure probability is adjusted according to the trend of the network load. For example, when the network load value differs significantly from the first failure probability, it indicates that the anomaly is not periodic but sudden. In this case, the correction value is also larger, and the first failure probability can be adjusted accordingly using this correction value. Finally, the first failure probability and the correction value can be weighted and fused to obtain the second failure probability. Specifically, the weight corresponding to the first failure probability can be a basic weight, with a specific value of 0.6, and the weight corresponding to the correction value can be the difference between 1 and the basic weight, with a specific value of 0.4.

[0048] Compared to single prediction methods that rely solely on current or historical data, the revised second failure probability can more accurately reflect the overall failure risk of access points in the present and future. Therefore, it can identify potential network risks in advance and take more precise optimization measures to avoid network failures or congestion, thereby improving network stability and user experience.

[0049] In one specific implementation, determining a correction value based on a first failure probability and a network load value includes: obtaining a sensitivity coefficient; subtracting the network load value from the first failure probability as a first value; multiplying the sensitivity coefficient and the first value as a second value; using the opposite of the second value as the exponent of a natural constant as a third value; and using the ratio of the first failure probability divided by the sum of the third value and a predetermined constant as the correction value.

[0050] In this embodiment, the definition is... The first failure probability is the real-time output of the first processing model (i.e., the XGBoost model); defined The baseline normalized value of the network load at this moment is the prediction of the second processing module (i.e., the LSTM network model).

[0051] The probability of the second failure can then be calculated using the following formula. :

[0052] in, This is the base weight (e.g., 0.6), representing the probability of the first failure that is more trusted in real time; This is a correction value, if the first failure probability Significantly higher than the historical baseline network load value (Right now This indicates that the anomaly is not periodic but sudden, and the correction value will amplify the risk value; β is the sensitivity coefficient, used to control the degree of influence of trend deviation on the final result.

[0053] The first value is The second value is The third value is .

[0054] In one specific implementation, the network of the access point is optimized based on the second failure probability, including: obtaining a network optimization strategy for the access point based on the second failure probability; and optimizing the network of the access point based on the network optimization strategy.

[0055] In this embodiment, the current fault risk of the access point can first be determined based on the second fault probability, and it can be decided whether network optimization is needed and what optimization measures to take, i.e., the network optimization strategy for the access point can be determined. Then, based on the optimization strategy, the optimization operation of the access point network can be executed. Specifically, the optimization strategy determined based on the second fault probability can be divided into multiple levels, which can execute corresponding optimization strategies for different risk levels, effectively improving the stability and fault prevention capability of the network.

[0056] In one specific implementation, the network optimization strategy for the access point is obtained based on the second fault probability, including: when the second fault probability is greater than or equal to a first threshold, using a multi-objective optimization algorithm to solve multiple decision variables to determine a first optimization strategy; determining the first optimization strategy as the network optimization strategy for the access point; and when the second fault probability is less than the first threshold but greater than or equal to the second threshold, determining the second optimization strategy as the network optimization strategy for the access point.

[0057] In this embodiment, when the second failure probability is greater than or equal to the first threshold, indicating that the network is at high risk, a multi-objective optimization algorithm can be used to solve for multiple decision variables to obtain a first optimization strategy. The multi-objective optimization algorithm can be an algorithm capable of simultaneously optimizing multiple objectives or constraints, considering multiple optimization variables (such as channel selection, bandwidth allocation, power adjustment, etc.) to take optimal network optimization measures. The first optimization strategy is the optimal solution obtained based on the above variables. Under high-risk conditions, the access point network can be actively optimized immediately according to the first optimization strategy.

[0058] When the second failure probability is less than the first threshold but greater than or equal to the second threshold, indicating that the network is at medium risk, a relatively conservative second optimization strategy can be adopted. This involves fine-tuning only some key network parameters (such as adjusting the roaming threshold without switching channels) to reduce the impact on network performance. The goal of the second optimization strategy is to avoid unnecessary system interference caused by over-optimization through appropriate adjustments.

[0059] When the second failure probability is less than the second threshold, no network processing is required; only the failure probability needs to be continuously calculated and the network's operating status monitored in real time.

[0060] By employing the aforementioned optimization strategies and making corresponding decisions based on different levels of failure probability, we can accurately determine optimization needs and make appropriate adjustments according to different risk scenarios to improve the overall performance of the network. In particular, when the network failure risk is high, we can introduce multi-objective optimization algorithms to balance and optimize multiple optimization objectives, ensuring the maximum reliability and stability of the network under extreme conditions.

[0061] In one specific implementation, a multi-objective optimization algorithm is used to solve multiple decision variables to determine a first optimization strategy. This includes: solving multiple decision variables using a multi-objective optimization algorithm based on a pre-set objective optimization function to obtain an objective solution set; obtaining the current usage scenario of the access point; and selecting the solution that matches the current usage scenario from the objective solution set as the first optimization strategy.

[0062] In this embodiment, a multi-objective optimization algorithm can be used to solve multiple decision variables using a pre-set objective optimization function to obtain an objective solution set. Then, based on the current usage scenario of the access point, the system selects a solution from this solution set that matches the current scenario as the first optimization strategy.

[0063] First, multiple decision variables are factors that can influence network optimization, such as channel, transmit power, roaming threshold, client load, and multimedia service priority. These decision variables may have different importance in different scenarios, so they need to be considered comprehensively. By setting an objective optimization function, a multi-objective optimization algorithm based on genetic algorithm (Non-dominated Sorting Genetic Algorithm II, NSGA-II) is adopted. By performing non-dominated sorting of the solution space and calculating congestion distance, a set of Pareto optimal solutions is effectively searched (the Pareto optimal solution set represents the set of solutions where no other solution can surpass a certain solution on all objectives simultaneously). That is, each solution in the Pareto optimal solution set achieves a reasonable balance among different objectives, and no single solution is better than other solutions on all objectives.

[0064] Then, based on the current usage scenario of the access point, the system can select the solution that best matches the current usage scenario from the Pareto optimal solution set. For example, when a user is playing an online game, low latency is the most critical requirement, so the network optimization strategy with the lowest latency can be selected from the Pareto set for execution. Conversely, if the user is downloading in standby mode, throughput becomes the most important optimization objective, so the system will select the strategy with the highest throughput. This scenario-based dynamic adaptive selection allows for flexible adjustment of optimization strategies according to the user's actual needs.

[0065] Multi-objective optimization algorithms can make trade-offs among multiple network performance objectives, find a set of optimization strategies with good performance as candidate strategies, and provide the most suitable optimization scheme for different network requirements (such as low latency or high throughput) in practical applications, without having to sacrifice a single objective.

[0066] like Figure 3As shown, the network optimization method can be implemented by a system composed of edge and cloud components. Specifically, the access point, as the edge, collects performance data in real time and uploads it to the cloud management platform. After receiving the performance data, the cloud processes the data, removes outliers according to the 3σ criterion and Z-score, and standardizes it. The XGBoost model performs real-time analysis, while the LSTM network performs offline analysis. The output results of the XGBoost model and LSTM are combined to predict faults. When the fault prediction results indicate a significant risk, an optimization decision is made and an alarm is issued. At the same time, the optimization strategy is sent to the access point, which executes the optimization strategy to optimize the network.

[0067] like Figure 4 As shown, when generating optimization strategies, the prediction result, i.e., the failure probability, is obtained first. When the failure probability indicates that the failure risk is high, optimization strategies such as channel switching, backhaul link adjustment, client load balancing, power parameter adjustment, and priority adjustment can be generated based on the multi-objective optimization algorithm NSGA-II and pre-set optimization objectives, including maximizing throughput, minimizing latency, load balancing, reducing power consumption, and media service stability. Then, these strategies are logically verified or simulated (for example, checking whether the target channel is also congested, or whether the switching action will cause a flow interruption). If the verification finds that the strategy is risky, the process reverts to the "multi-objective optimization algorithm NSGA-II" to confirm that the strategy is safe and feasible, and then enters the distribution stage.

[0068] like Figure 5 As shown, the model used for data processing comprises two layers: a real-time prediction layer and an offline analysis layer. The real-time prediction layer utilizes the XGBoost model to rapidly infer feature vectors extracted from real-time data (i.e., the latest data) to derive performance trends and failure probabilities, achieving millisecond-level real-time prediction. The offline analysis layer, based on historical long-term time-series data, uses an LSTM model for long-term modeling, outputting long-term trend periodic patterns, and can also optimize the model parameters of the real-time prediction layer. Specifically, after the latest feature vector data enters the real-time prediction layer, the failure probability is inferred by the XGBoost model and used as the real-time prediction result. Historical long-term time-series data is used for long-term modeling using an LSTM model to output long-term trend references. Furthermore, the offline analysis layer can provide feedback optimization to the model parameters of the real-time prediction layer based on the relevant results. Together, these two layers achieve rapid and accurate identification and optimization of network risks.

[0069] To better implement the network optimization method in the embodiments of this application, a network optimization device is also provided in the embodiments of this application, such as... Figure 6 As shown, the network optimization device 600 includes: The acquisition module 610 is used to acquire the current network data and network load value of the access point; The determination module 620 is used to determine the first failure probability of the access point based on the current network data; The correction module 630 is used to correct the first fault probability based on the network load value to obtain the second fault probability; The optimization module 640 is used to optimize the network of the access point based on the second failure probability.

[0070] In this embodiment, by obtaining the current network data and network load value of the access point, predicting the first failure probability of the access point based on the current network data, and then correcting the first failure probability based on the network load value to obtain the second failure probability, and then performing optimization measures based on the corrected failure probability, it is possible to improve the response speed and accuracy of network optimization by combining the first failure probability with the predetermined network load value while ensuring real-time performance. This allows for adjustments to be made in advance before network failures occur, thereby improving the user experience.

[0071] In some embodiments of this application, the determining module 620 determines the first failure probability of the access point based on current network data, including: The current network data is input into the first processing model, and the first failure probability is output through the first processing model. Network load values ​​are obtained as follows: Historical network data is input into the second processing model, and the network load value is output through the second processing model.

[0072] In some embodiments of this application, the correction module 630 corrects the first fault probability based on the network load value to obtain a second fault probability, including: The correction value is determined based on the first failure probability and the network load value; The second failure probability is obtained by weighting and fusing the first failure probability and the corrected value.

[0073] In some embodiments of this application, the correction module 630 determines a correction value based on a first failure probability and a network load value, including: Obtain the sensitivity coefficient; The difference between the first failure probability and the network load value is used as the first value; The product of the sensitivity coefficient and the first value is used as the second value; The third value is obtained by exponentiation of the second value with the opposite of the natural constant. The ratio obtained by dividing the first failure probability by the sum of the third value and a predetermined constant is used as the correction value.

[0074] In some embodiments of this application, the optimization module 640 optimizes the network of the access point based on a second failure probability, including: Based on the second failure probability, the network optimization strategy for the access point is obtained; Based on network optimization strategies, the network at the access point is optimized.

[0075] In some embodiments of this application, the optimization module 640 obtains a network optimization strategy for the access point based on a second failure probability, including: When the second failure probability is greater than or equal to the first threshold, a multi-objective optimization algorithm is used to solve multiple decision variables to determine the first optimization strategy; the first optimization strategy is determined as the network optimization strategy of the access point. If the second failure probability is less than the first threshold and greater than or equal to the second threshold, the second optimization strategy is determined as the network optimization strategy for the access point.

[0076] In some embodiments of this application, the optimization module 640 employs a multi-objective optimization algorithm to solve for multiple decision variables and determine a first optimization strategy, including: Based on the pre-set objective optimization function, a multi-objective optimization algorithm is used to solve multiple decision variables to obtain the objective solution set; Obtain the current usage scenario of the access point; The solution that matches the current use case is selected from the target solution set as the first optimization strategy.

[0077] This application embodiment also provides a terminal device that integrates any of the network optimization devices provided in this application embodiment. The terminal device includes: One or more processors; Memory; and One or more applications, wherein the applications are stored in memory and configured to be executed by a processor from the steps of the network optimization method in any of the embodiments described above.

[0078] This application also provides a terminal device that integrates any of the network optimization devices provided in this application. For example... Figure 7 As shown, it illustrates a structural schematic diagram of the terminal device involved in the embodiments of this application. Specifically: The terminal device may include components such as a processor 701 with one or more processing cores, a memory 702 with one or more computer-readable storage media, a power supply 703, and an input unit 704. Those skilled in the art will understand that... Figure 7The terminal device structure shown does not constitute a limitation on the terminal device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 701 is the control center of the terminal device. It connects various parts of the terminal device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 702, and by calling data stored in the memory 702, it performs various functions and processes data of the terminal device, thereby providing overall monitoring of the terminal device. Optionally, the processor 701 may include one or more processing cores; preferably, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 701.

[0079] The memory 702 can be used to store software programs and modules. The processor 701 executes various functional applications and data processing by running the software programs and modules stored in the memory 702. The memory 702 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 702 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 702 may also include a memory controller to provide the processor 701 with access to the memory 702.

[0080] The terminal device also includes a power supply 703 that supplies power to the various components. Preferably, the power supply 703 can be logically connected to the processor 701 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 703 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0081] The terminal device may also include an input unit 704, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0082] Although not shown, the terminal device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 701 in the terminal device loads the executable files corresponding to the processes of one or more applications into the memory 702 according to the following instructions, and the processor 701 runs the applications stored in the memory 702 to realize various functions, as follows: Obtain the current network data and network load value of the access point; Based on current network data, determine the first probability of failure of the access point; The first failure probability is corrected based on the network load value to obtain the second failure probability; The network at the access point is optimized based on the second failure probability.

[0083] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0084] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the network optimization methods provided in embodiments of this application. For example, the computer program loaded by the processor can execute the following steps: Obtain the current network data and network load value of the access point; Based on current network data, determine the first probability of failure of the access point; The first failure probability is corrected based on the network load value to obtain the second failure probability; The network at the access point is optimized based on the second failure probability.

[0085] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0086] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0087] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0088] The foregoing has provided a detailed description of a network optimization method, apparatus, terminal device, and computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A network optimization method, characterized in that, include: Obtain the current network data and network load value of the access point; Based on the current network data, determine the first failure probability of the access point; The first failure probability is corrected based on the network load value to obtain the second failure probability; The network of the access point is optimized based on the second failure probability.

2. The network optimization method according to claim 1, characterized in that, Determining the first failure probability of the access point based on the current network data includes: The current network data is input into the first processing model, and the first fault probability is output through the first processing model. The network load value is obtained in the following way: Historical network data is input into the second processing model, and the network load value is output through the second processing model.

3. The network optimization method according to claim 1, characterized in that, The step of correcting the first failure probability based on the network load value to obtain the second failure probability includes: The correction value is determined based on the first failure probability and the network load value; The second fault probability is obtained by weighted fusion of the first fault probability and the corrected value.

4. The network optimization method according to claim 3, characterized in that, The step of determining the correction value based on the first failure probability and the network load value includes: Obtain the sensitivity coefficient; The difference between the first failure probability and the network load value is used as the first value; The product of the sensitivity coefficient and the first value is taken as the second value; The third value is obtained by exponentiation of the second value with the opposite of the natural constant. The ratio obtained by dividing the first failure probability by the sum of the third value and a predetermined constant is used as the correction value.

5. The network optimization method according to claim 1, characterized in that, The optimization of the network of the access point based on the second failure probability includes: Based on the second failure probability, the network optimization strategy for the access point is obtained; Based on the network optimization strategy, the network of the access point is optimized.

6. The network optimization method according to claim 5, characterized in that, The step of obtaining the network optimization strategy for the access point based on the second failure probability includes: When the second failure probability is greater than or equal to the first threshold, a multi-objective optimization algorithm is used to solve multiple decision variables to determine a first optimization strategy; the first optimization strategy is determined as the network optimization strategy of the access point. If the second failure probability is less than the first threshold and greater than or equal to the second threshold, the second optimization strategy is determined as the network optimization strategy for the access point.

7. The network optimization method according to claim 6, characterized in that, The step of using a multi-objective optimization algorithm to solve for multiple decision variables and determine the first optimization strategy includes: Based on the pre-set objective optimization function, a multi-objective optimization algorithm is used to solve multiple decision variables to obtain the objective solution set; Obtain the current usage scenario of the access point; The solution that matches the current usage scenario is selected from the target solution set as the first optimization strategy.

8. A network optimization device, characterized in that, include: The acquisition module is used to acquire the current network data of the access point and the network load value of the access point; The determination module is used to determine the first failure probability of the access point based on the current network data; The correction module is used to correct the first fault probability based on the network load value to obtain a second fault probability; An optimization module is used to optimize the network of the access point based on the second failure probability.

9. A terminal device, characterized in that, The terminal device includes: one or more processors, a memory, and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the network optimization method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to perform the steps of the network optimization method according to any one of claims 1 to 7.

Images