Operator bandwidth allocation method based on network video traffic QoE (Quality of Experience) identification

Abstract

The invention discloses an operator bandwidth allocation method based on network video traffic QoE (Quality of Experience) identification, and relates to the technical field of computer networks, and the method comprises the steps: inputting a set video into a trained bandwidth allocation model based on users playing the set video at the same time, so as to output a bandwidth allocation strategy of the users; the training process of the bandwidth allocation model is as follows: N set videos are stipulated in advance as optimization targets; a set video and QoE are obtained based on a webpage fine-grained recognition module and a user QoE recognition module, for one set video and one set bandwidth, the value corresponding to the QoE is unique, and a recurrent neural network is used for fitting the QoE and bandwidth function; maximizing the sum of user QoE values of N set videos as a final target, combining the set constraint and boundary conditions and the QoE and bandwidth function, and obtaining an optimal bandwidth allocation strategy based on Bayesian optimization; according to the operator bandwidth allocation method, the accuracy and effectiveness of bandwidth allocation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer networks, and in particular to an operator bandwidth allocation method based on network video traffic QoE identification. Background Art

[0002] In recent years, with the vigorous development of communication technology and smart devices, the number of Internet users has continued to grow, and network transmission speeds have continued to accelerate, resulting in a significant increase in network traffic, most of which is generated by video services. It is of great significance for operators to optimize the quality of experience of users watching videos by allocating bandwidth, which directly affects user satisfaction, network operation efficiency and corporate competitiveness.

[0003] IP bandwidth control is a rate control method implemented by operators on routers or network devices. It limits the network speed of specific devices by checking the IP addresses of devices connected to the network. Operators can pre-set the upload and download bandwidth size of each user or device based on a certain policy according to the total network bandwidth and the number of users. Through software-defined networking (SDN), operators can flexibly and dynamically adjust bandwidth allocation strategies according to specific algorithms to optimize the utilization of network resources to cope with real-time traffic changes. Since video streaming usually has high requirements for bandwidth stability, especially during real-time transmission. If the bandwidth fluctuates, it may cause video freezes or quality degradation. The existing leaky bucket algorithm ensures that the transmission rate of the video stream remains stable by controlling the rate at which data flows in, avoiding bursts of traffic affecting video playback.

[0004] In the process of bandwidth allocation, QoE is a key indicator for measuring the quality of video streaming experience, involving multiple dimensions such as visual quality, rebuffering (stuttering) frequency and duration, and the magnitude of quality change. These indicators often have trade-offs. For example, improving visual quality may lead to insufficient buffering, thereby increasing the risk of stuttering.

[0005] Previous bandwidth allocation algorithms mostly focused on Quality of Service (QoS) indicators such as latency, jitter, and packet loss rate. These technical indicators mainly measure the performance and stability of network transmission, ensuring that data can be transmitted from the source node to the destination node effectively and quickly. However, although these QoS indicators are very important in improving network efficiency and reliability, they do not fully consider the user's subjective experience (QoE), that is, the user's actual feelings and satisfaction when using the network. For applications such as video streaming, user experience depends not only on QoS indicators such as jitter and latency, but also on factors such as visual quality, rebuffering (stuttering) frequency, and quality fluctuations.

[0006] The main reason for this limitation is that operators cannot directly know the actual viewing experience of users. For example, operators can monitor technical indicators such as bandwidth utilization, data transmission delay and packet loss rate through network equipment, but these indicators cannot accurately reflect the visual quality or lags felt by users when watching videos. Visual quality involves the resolution of the video, while lags are related to the frequency and duration of buffering events, which are the experience factors that users care about most when watching videos. However, since many streaming media transmissions in the network are encrypted (for example, via HTTPS or TLS), it is difficult for operators to obtain fine-grained client status information, and they cannot directly monitor the video encoding rate or the frequency of rebuffering events.

[0007] This information asymmetry makes it impossible for operators' bandwidth allocation algorithms to incorporate user-side QoE into the optimization model. As a result, even if the network transmission performance reaches the expected QoS standard, the user's actual viewing experience (such as video clarity, smoothness, etc.) may still be poor. For example, in some cases, even if the network bandwidth is sufficient, if the adaptive algorithm for video playback selects a lower-quality encoding stream, the user will still feel a poor experience.

[0008] Before the popularity of encrypted traffic, the QoE evaluation of video services relied on direct analysis of unencrypted traffic. Operators could easily access specific data such as video encoding information, bit rate, and rebuffering (stuttering). However, with the popularity of encryption protocols such as HTTPS, traffic has become difficult to observe directly, making it difficult for operators to judge the user's viewing experience. Encrypted traffic hides the content details of the video, limiting the application of traditional QoE monitoring methods.

[0009] With the development of encrypted network traffic identification technology, operators can indirectly infer users' QoE by deeply analyzing patterns and network behaviors in encrypted traffic. For example, by analyzing the size of data packets, transmission time, traffic patterns, round-trip time (RTT), and the behavior of transport layer protocols, operators can identify key events in video streaming, such as resolution changes, number of freezes, and video clarity. This technology uses machine learning and traffic feature analysis methods to effectively infer users' actual viewing experience even when traffic is encrypted.

[0010] However, although operators can measure user QoE more accurately, it does not mean that they can directly use QoE indicators to replace the original QoS indicators for optimization. This is because:

[0011] 1. QoE evaluation usually involves complex algorithms and data processing, such as objective evaluation models in video quality measurement (such as PSNR, SSIM, etc.) or prediction models based on deep learning. These algorithms usually require a long computing time and it is difficult to achieve real-time feedback at the millisecond level. QoS indicators such as latency and packet loss rate can be quickly measured and adjusted on network devices, which are suitable for real-time optimization.

[0012] 2. Current network control mechanisms (such as traffic shaping, queuing strategies, and congestion control) are designed based on QoS indicators. Operators' equipment and protocols are accustomed to using specific indicators such as latency, jitter, and packet loss rate for management and optimization. If QoE indicators are used directly, existing control mechanisms may need to be significantly adjusted, and these adjustments are often very complex, which may significantly increase the cost and complexity of network management.

[0013] Therefore, operators need to design a new solution, such as saving actual network data (such as bandwidth) and user experience data (such as QoE indicators) for subsequent black box model training to provide a basis for bandwidth allocation decisions to optimize future network management and service quality. Due to the different sizes of different videos and different resolution decision algorithms, it is also necessary to identify what specific videos the user is watching in order to know the mapping relationship between each video bandwidth and QoE indicators.

[0014] Based on encrypted network traffic identification technology, QoE and application identification are performed. Existing network application identification technology can solve this problem well. Operators can represent network traffic as a graph structure and use the powerful feature learning and pattern recognition capabilities of graph neural networks (GNNs) to identify the web pages that users are viewing in a fine-grained manner. Specifically, each data packet in the network traffic can be regarded as a node in the graph, and the communication relationship or transmission direction between these nodes constitutes the edge of the graph. In this way, the encrypted traffic originally presented as time series data is converted into a graph model that can capture complex relationships and structures. Even if the data is encrypted and the specific content cannot be directly obtained, the characteristics of the traffic (such as packet size, time interval, transmission direction, etc.) can still provide sufficient identification information to help the model identify the differences between different applications, thereby realizing application classification.

[0015] In summary, it is unreasonable to optimize network bandwidth resource allocation based on QoS. Since the existing encrypted network traffic identification technology can perform QoE and application identification, operators can consider optimizing bandwidth resource allocation by establishing a mathematical model of different video bandwidths and QoE. Summary of the invention

[0016] Based on the technical problems existing in the background technology, the present invention proposes an operator bandwidth allocation method based on network video traffic QoE identification, which improves the accuracy and effectiveness of bandwidth allocation.

[0017] The present invention proposes an operator bandwidth allocation method based on network video traffic QoE identification. Based on users who play set videos at the same time, the set video traffic information and predicted bandwidth information are input into the trained bandwidth allocation model to output the user's bandwidth allocation strategy;

[0018] The training process of the bandwidth allocation model is as follows:

[0019] Step 1: Specify N set videos as optimization targets in advance, and select the first k seconds of each video for optimization to align the video lengths;

[0020] Step 2: The web page fine-grained recognition module and the user QoE recognition module are arranged at the network egress node. The multi-stream network traffic is screened based on the web page fine-grained recognition module to obtain the set video. The recognition interval of the user QoE recognition module is recorded as t seconds. In the video length of k seconds, a total of k / t QoEs are recognized;

[0021] Step 3: Monitor the user's bandwidth. Based on the fact that the recognition interval of the user's QoE recognition module is consistent with the time length of the video website switching resolution, the bandwidth of k / t monitoring times is obtained. For a set video and a set of set bandwidths, the corresponding QoE mn The value of is unique, so the recurrent neural network is used to fit the QoE and bandwidth function;

[0022] Step 4: Taking maximizing the sum of the user QoE values ​​of N set videos as the final goal, combining the set constraints and boundary conditions as well as the QoE and bandwidth functions, the optimal bandwidth allocation strategy is obtained based on Bayesian optimization.

[0023] Furthermore, in step 4, the final goal is specifically:

[0024]

[0025] Among them, i is the index of the set video, l i is the number of users who watched the i-th set video, Z i The bandwidth required for setting the i-th video, QoE i is the QoE of the i-th set video recognition.

[0026] Furthermore, in step 4, the constraints and boundary conditions are:

[0027] Constraint: In any time period, the sum of the bandwidth allocated to each set video is less than or equal to the total bandwidth;

[0028] Boundary condition: The bandwidth allocated to each set video is not negative and is less than or equal to the total bandwidth.

[0029] Furthermore, in step 4, the optimal bandwidth allocation strategy is obtained based on Bayesian optimization, which is specifically:

[0030] Assuming that the bandwidth allocation scheme Z is given, a prediction model of the objective function is constructed based on the Gaussian process. The prediction model takes the bandwidth allocation scheme Z as input and outputs the predicted mean μ(Z) and uncertainty σ(Z).

[0031] Based on the acquisition function that introduces constraints and boundary conditions, the next bandwidth allocation scheme to be evaluated is selected, and the acquisition function is optimized using an optimization algorithm to maximize the improvement value of the current solution relative to the optimal solution. The bandwidth allocation scheme corresponding to the improvement value is used as the optimal bandwidth allocation strategy.

[0032] Furthermore, the acquisition function of constraints and boundary conditions is introduced, specifically:

[0033] α CEI (Z) = α EI (Z)·P(c1(Z)≤0)·P(c2(Z)≤0)·P(c3(Z)≤0);

[0034]

[0035] Among them, α CEI is the improvement value of the current solution corresponding to the acquisition function that introduces constraints and boundary conditions relative to the optimal solution, α EI is the improvement value of the current solution corresponding to the acquisition function without introducing constraints and boundary conditions relative to the optimal solution, Z * is the optimal bandwidth allocation scheme, Φ and φ are the cumulative distribution function and probability density function of the standard normal distribution, c1(Z) is the constraint condition that the sum of the bandwidth allocated to each set video is less than or equal to the total bandwidth, c2(Z) is the boundary condition that the bandwidth allocated to each set video is less than or equal to the total bandwidth, c3(Z) is the boundary condition that the bandwidth allocated to each set video is not negative, and P(·) represents the probability of the occurrence of constraints and boundary conditions.

[0036] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned operator bandwidth allocation method when executing the computer program.

[0037] A computer-readable storage medium stores a plurality of classification programs, wherein the plurality of classification programs are used to be called by a processor and execute the operator bandwidth allocation method as described above.

[0038] Signal connections include wired connections and wireless connections; wired connections include broadband connections and fiber optic connections; wireless connections include WIFI connections and radio connections.

[0039] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0040] The advantages of the operator bandwidth allocation method based on network video traffic QoE identification provided by the present invention are: comprehensively considering the QoE characteristics and web page fingerprint characteristics that the operator can identify through encrypted traffic, allocating bandwidth with the goal of maximizing user QoE; concentrating and then allocating the bandwidth of users watching set videos, and improving the QoE of users watching set videos without affecting irrelevant user experience; inputting encrypted traffic into a graph neural network and a convolutional neural network to construct a QoE-bandwidth data set, and then using a recurrent neural network fitting function, so that the operator can estimate the user QoE experience under different bandwidth conditions, and use a Bayesian optimization algorithm to make reasonable bandwidth allocation decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Figure 1. Training framework diagram for bandwidth allocation model.

[0042] Figure 2 The execution framework diagram of the bandwidth allocation model after training is completed. DETAILED DESCRIPTION

[0043] Below, the technical solution of the present invention is described in detail through specific embodiments. Many specific details are set forth in the following description to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific implementation disclosed below.

[0044] like Figure 1 and 2As shown, the present invention proposes an operator bandwidth allocation method based on network video traffic QoE identification. Based on users who play set videos at the same time, the set video traffic information and the predicted bandwidth information are input into the trained bandwidth allocation model to output the user's bandwidth allocation strategy.

[0045] The bandwidth allocation model is divided into a training phase and an application phase. In the training phase, the operator deploys the QoE identification module and the web page fine-grained identification module at the network exit node (such as the exit node of the campus network). When the web page fine-grained identification module detects a set video web page, the corresponding web page information, QoE information, and bandwidth information are added to the data set. When the number of data sets is large enough, the QoE-bandwidth curve of each set video is fitted using a feedforward neural network (RNN), and the fitted model is saved.

[0046] In the application stage, videos played within a time interval of b seconds are considered to be "played simultaneously". For users who play the set videos simultaneously, their bandwidth vectors for a period of time in the future are predicted, and these bandwidths are added up as the total bandwidth. Then, the Bayesian optimization algorithm is used to calculate the appropriate bandwidth vector for each video from the total bandwidth and allocate it to the relevant users. At the same time, new QoE-bandwidth data will be generated and added to the data set. When the data set is expanded to a certain number, the QoE-bandwidth function will continue to be fitted to improve the accuracy of the fitting.

[0047] Specifically, the training process of the bandwidth allocation model is as follows:

[0048] Step 1: Specify N set videos as optimization targets in advance, and select the first k seconds of each set video for optimization to align the video lengths;

[0049] Step 2: Place the web page fine-grained recognition module and the user QoE recognition module at the network exit node. Based on the web page fine-grained recognition module, screen the multi-stream network traffic to obtain the set video. The recognition interval time of the user QoE recognition module is recorded as t seconds. In the video length of k seconds, a total of k / t QoEs are recognized.

[0050] Web page fine-grained recognition module

[0051] In order to understand what video the user is watching, the technology of fine-grained web page recognition is used. In the existing technology, the graph neural network (GNN) can extract effective information based on the characteristics of network data streams and the spatiotemporal correlation between network data streams to achieve fine-grained classification of web pages. The multi-stream network traffic is input into the web page fine-grained recognition module (FWI module), and the pre-trained GNN model outputs the video of which web page the operator user is visiting. If the video is one of the N videos that need to be optimized, further operations such as bandwidth prediction can be performed.

[0052] User QoE Identification Module

[0053] In order to optimize user QoE, it is necessary for operators to understand the QoE of users watching videos under different bandwidth conditions. Existing experiments have shown that the observation results of using data packet round-trip time (RTT) information to infer fine-grained QoE indicators are more effective and can better identify heavy buffering events and video resolutions. The user QoE identification module is deployed at the network egress node, combined with bandwidth monitoring and web page fine-grained identification modules to provide effective data for bandwidth-QoE fitting. Since resolution switching will affect the overall QoE, the QoE identification interval of the user QoE identification module needs to be consistent with the time length of the video website switching resolution, recorded as t seconds. In the video length of k seconds, a total of k / t QoEs are identified; that is, for the i-th set video, the QoE size of the p-th identification is QoE ip , p∈[1,k / t].

[0054] Step 3: Monitor the user's bandwidth. Based on the fact that the recognition interval of the user's QoE recognition module is consistent with the time length of the video website switching resolution, the bandwidth of k / t monitoring times is obtained. For a set video and a set of set bandwidths, the corresponding QoE mn The value of is unique, so the recurrent neural network is used to fit the QoE and bandwidth function;

[0055] Bandwidth prediction module

[0056] Operators can collect bandwidth usage data from users over the past period of time from channels such as network logs and traffic monitoring systems. By analyzing users' historical bandwidth usage data, operators can predict users' future bandwidth usage. Specifically, users' bandwidth usage shows a certain regularity on a large scale, and the moving average method can be used to reveal potential long-term trends; while there is some randomness on a small scale, and the exponential smoothing algorithm can be used to give higher weights to the most recent data points. By superimposing the prediction algorithms on the two scales, the bandwidth usage of the next k / t times can be predicted more accurately.

[0057] Bandwidth-QoE relationship modeling module

[0058] The operator can monitor the user's bandwidth. For the i-th set video, the bandwidth monitored k / t times is listed as a vector B = [b1, b2, ..., b k / t ], and its corresponding QoE is ∑QoE ip For a given video n, and a specific bandwidth B m , which corresponds to QoE mnThe value of is unique, which depends on the size of the video itself and the download algorithm set by the content provider. Although the operator cannot directly know this information, the user QoE identification module and bandwidth monitoring module can provide the bandwidth vector and QoE corresponding data of each set video. When there is enough data, RNN can be used to fit QoE n The relationship between bandwidth B and QoE n Set the QoE of the video for the nth time.

[0059] Step 4: Taking maximizing the sum of the user QoE values ​​of N set videos as the final goal, combining the set constraints and boundary conditions as well as the QoE and bandwidth functions, the optimal bandwidth allocation strategy is obtained based on Bayesian optimization.

[0060] Bayesian Optimization Module

[0061] Bayesian optimization is a global optimization algorithm used to optimize black box functions that are computationally expensive or have no clear expression. It constructs a proxy model (usually a Gaussian process) to approximate the target function based on known data, giving the predicted value μ(Z) and uncertainty σ(Z) for each point.

[0062] Bayesian optimization then uses an acquisition function (such as expected improvement EI) to select the next point to evaluate in the input space. The acquisition function is used to balance exploring new areas and leveraging existing information to ensure that the global optimal solution is found faster.

[0063] Each time a new point is selected, the objective function is evaluated, and the new data point is added to the existing data, the proxy model is continuously updated, and this process is repeated until the optimal solution is reached or the termination condition is met.

[0064] In this embodiment, it is assumed that the N set videos are [l1,l2,..l N ] people watch and the total bandwidth is limited, l n For the number of users who watch the Nth set video, the amount that needs to be decided is how much bandwidth to allocate to these N set videos, such as the bandwidth Z that needs to be allocated for the i-th set video i =[z 1i ,z 2i ,...,z fi ],f=k / t,z fi is the bandwidth corresponding to the k / tth QoE identification; bandwidth Z i Divide by the number of users l i The result Z i / l i That is, the bandwidth allocated to each user. The ultimate goal is to maximize the sum of the QoE values ​​of all users watching these N set videos:

[0065]

[0066] Among them, i is the index of the set video, l i is the number of users who watched the i-th set video, Z i The bandwidth required for setting the i-th video, QoE i is the QoE of the i-th set video recognition.

[0067] ∑l i The total bandwidth X of each user is predicted, and the constraints and boundary conditions are: Constraint: In any time period, the sum of the bandwidth allocated to each set video must be less than or equal to the total bandwidth; Boundary condition: The bandwidth allocated to each set video is not negative and is less than or equal to the total bandwidth.

[0068]

[0069] Among them, c1(Z) is the constraint condition that the sum of the bandwidth allocated to each set video is less than or equal to the total bandwidth, c2(Z) is the boundary condition that the bandwidth allocated to each set video is less than or equal to the total bandwidth, c3(Z) is the boundary condition that the bandwidth allocated to each set video is not negative, and Z ij represents the bandwidth allocated to the i-th video in the j-th time period, X j It represents the total bandwidth that the operator can allocate in the jth time period.

[0070] For the above problems, since the objective function is complex, QoE has no clear expression and the computational cost is high, Bayesian optimization can gradually find the optimal solution through evaluation of a small number of sample points without directly exploring the global objective function. Therefore, it is suitable for solving the above problems.

[0071] The steps of Bayesian optimization to solve the bandwidth allocation problem are as follows:

[0072] First, the Gaussian process is used to construct a prediction model for the objective function f(Z). Assuming a given bandwidth allocation scheme Z, the prediction model returns a predicted value (mean) μ(Z) and uncertainty (standard deviation) σ(Z). The objective function f(Z) represents the QoE value to be maximized, and the prediction model of the Gaussian process is

[0073]

[0074] Next, the acquisition function is used to select the next bandwidth allocation solution to be evaluated. A commonly used acquisition function is the expected improvement (EI), which measures the possible improvement of the current solution relative to the optimal solution. The formula for EI is:

[0075]

[0076] Among them, α EI is the improvement value of the current solution corresponding to the acquisition function without introducing constraints and boundary conditions relative to the optimal solution, Z * is the optimal bandwidth allocation scheme, Φ and φ are the cumulative distribution function and probability density function of the standard normal distribution, respectively. This acquisition function combines the mean and uncertainty to effectively explore the solution space.

[0077] The constraints and boundary conditions are then introduced into the acquisition function:

[0078] α CEI (Z) = α EI (Z)·P(c1(Z)≤0)·P(c2(Z)≤0)·P(c3(Z)≤0);

[0079] Among them, α CEI is the improvement value of the current solution corresponding to the acquisition function that introduces constraints and boundary conditions relative to the optimal solution. Φ and φ are the cumulative distribution function and probability density function of the standard normal distribution, respectively. c1(Z) is the constraint condition that the sum of the bandwidth allocated to each set video is less than or equal to the total bandwidth. c2(Z) is the boundary condition that the bandwidth allocated to each set video is less than or equal to the total bandwidth. c3(Z) is the boundary condition that the bandwidth allocated to each set video is not negative. P(·) represents the probability of the occurrence of constraints and boundary conditions.

[0080] Finally, an optimization algorithm (such as L-BFGS) is used to optimize the acquisition function that introduces constraints and boundary conditions to find the function that maximizes α CEI (Z) means that the optimal bandwidth allocation strategy can be found.

[0081] Bandwidth allocation module

[0082] Based on the calculated Z, the operator can allocate bandwidth to users who watch the specified video in k / t time periods in the next k seconds. It is worth noting that since the operator cannot accurately control the bandwidth allocation to be exactly the same as expected, the actual allocated bandwidth will be a normal distribution with the optimal bandwidth as the mean.

[0083] Through steps one to three, compared with the traditional bandwidth allocation algorithm, this embodiment comprehensively considers the QoE features and webpage fingerprint features that the operator can identify through encrypted traffic, and allocates bandwidth with the goal of maximizing user QoE; compared with the traditional method, this embodiment first concentrates and then allocates the bandwidth of users watching set videos, and improves the QoE of users watching set videos without affecting irrelevant user experiences; this embodiment inputs encrypted traffic into a graph neural network and a convolutional neural network to construct a QoE-bandwidth data set, and then uses a recurrent neural network fitting function, so that the operator can estimate the user QoE experience under different bandwidth conditions, and use the Bayesian optimization algorithm to make reasonable bandwidth allocation decisions.

[0084] This embodiment introduces joint optimization based on QoE indicators. Operators can use large-scale user data and traffic characteristics to train a more refined model to predict the impact of different bandwidth allocations on user experience, and then decide on the bandwidth required by different video viewing users. This can not only maximize the quality of video services, but also reduce unnecessary network congestion, optimize bandwidth usage efficiency, and thus improve the accuracy and effectiveness of bandwidth allocation.

[0085] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for allocating operator bandwidth based on network video traffic QoE identification, characterized in that: Based on the users who play the set videos at the same time, the set video traffic information and the predicted bandwidth information are input into the trained bandwidth allocation model to output the bandwidth allocation strategy of the users; The training process of the bandwidth allocation model is as follows: Step 1: Specify N set videos as optimization targets in advance, and select the first k seconds of each video for optimization to align the video lengths; Step 2: The web page fine-grained recognition module and the user QoE recognition module are arranged at the network egress node. The multi-stream network traffic is screened based on the web page fine-grained recognition module to obtain the set video. The recognition interval of the user QoE recognition module is recorded as t seconds. In the video length of k seconds, a total of k / t QoEs are recognized; Step 3: Monitor the user's bandwidth. Based on the fact that the recognition interval of the user's QoE recognition module is consistent with the time length of the video website switching resolution, the bandwidth of k / t monitoring times is obtained. For a set video and a set of set bandwidths, the corresponding QoEm n The value of is unique, so the recurrent neural network is used to fit the QoE and bandwidth function; Step 4: Taking maximizing the sum of the user QoE values ​​of N set videos as the final goal, combining the set constraints and boundary conditions as well as the QoE and bandwidth functions, the optimal bandwidth allocation strategy is obtained based on Bayesian optimization.

2. The method for allocating operator bandwidth based on network video traffic QoE identification according to claim 1, characterized in that: In step 4, the final goal is: Among them, i is the index of the set video, l i is the number of users who watched the i-th set video, Z i The bandwidth required for setting the i-th video, QoE i is the QoE of the i-th set video recognition.

3. The method for allocating operator bandwidth based on network video traffic QoE identification according to claim 1, characterized in that: In step 4, the constraints and boundary conditions are: Constraint: In any time period, the sum of the bandwidth allocated to each set video is less than or equal to the total bandwidth; Boundary condition: The bandwidth allocated to each set video is not negative and is less than or equal to the total bandwidth.

4. The method for allocating operator bandwidth based on network video traffic QoE identification according to claim 1, characterized in that: In step 4, the optimal bandwidth allocation strategy is obtained based on Bayesian optimization, which is: Assuming that the bandwidth allocation scheme Z is given, a prediction model of the objective function is constructed based on the Gaussian process. The prediction model takes the bandwidth allocation scheme Z as input and outputs the predicted mean μ(Z) and uncertainty σ(Z). Based on the acquisition function that introduces constraints and boundary conditions, the next bandwidth allocation scheme to be evaluated is selected, and the acquisition function is optimized using an optimization algorithm to maximize the improvement value of the current solution relative to the optimal solution. The bandwidth allocation scheme corresponding to the improvement value is used as the optimal bandwidth allocation strategy.

5. The method for allocating operator bandwidth based on network video traffic QoE identification according to claim 4, characterized in that: The acquisition function that introduces constraints and boundary conditions is as follows: α CEI (From)=α EI (Z) P(c1(Z)≤0) P(c2(Z)≤0) P(c3(Z)≤0) Among them, α CEI is the improvement value of the current solution corresponding to the acquisition function that introduces constraints and boundary conditions relative to the optimal solution, α EI is the improvement value of the current solution corresponding to the acquisition function without introducing constraints and boundary conditions relative to the optimal solution, Z * is the optimal bandwidth allocation scheme, Φ and φ are the cumulative distribution function and probability density function of the standard normal distribution, c1(Z) is the constraint condition that the sum of the bandwidth allocated to each set video is less than or equal to the total bandwidth, c2(Z) is the boundary condition that the bandwidth allocated to each set video is less than or equal to the total bandwidth, c3(Z) is the boundary condition that the bandwidth allocated to each set video is not negative, and P(·) represents the probability of the occurrence of constraints and boundary conditions.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the operator bandwidth allocation method according to any one of claims 1 to 5 is implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of classification programs, and the plurality of classification programs are used to be called by a processor and execute the operator bandwidth allocation method according to any one of claims 1 to 5.

Images