Video playing quality prediction method, electronic equipment and storage medium

Abstract

The invention provides a video playing quality prediction method, electronic equipment and a storage medium, relates to the technical field of computers, and is used for predicting the playing quality of a video. The method comprises the following steps: acquiring a video service message of a target video application in a current time period; determining traffic characteristic data of the target video application in the current time period according to the video service message of the target video application in the current time period; and inputting the traffic feature data of the target video application in the current time period into a video playing quality prediction model based on a convolutional neural network to obtain the video playing quality of the target video application in the future time period.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method for predicting video playback quality, an electronic device, and a storage medium. Background Art

[0002] With the rapid development of communication technology, the popularity of online video viewing services has been promoted. The status of online video viewing services in Internet applications is getting higher and higher, and the number of video users is also increasing. In order to improve user retention and growth rate, the prediction of video playback quality and timely intervention guarantee are the focus of network operators. In addition, as the Internet industry pays more and more attention to user privacy and security, the trend of network traffic encryption is becoming more and more obvious, which also brings great difficulty to the prediction of video playback quality. Therefore, there is an urgent need for a more efficient and more versatile method to predict video playback quality in order to improve the user's viewing experience and provide better service guarantees for network operators. Summary of the invention

[0003] The embodiments of the present application provide a method for predicting video playback quality, an electronic device, and a storage medium for predicting video playback quality.

[0004] On the one hand, a method for predicting video playback quality is provided, the method comprising:

[0005] Obtain the video service packets of the target video application in the current time period;

[0006] Determine traffic characteristic data of the target video application in the current time period according to the video service packets of the target video application in the current time period;

[0007] The traffic feature data of the target video application in the current time period is input into the video playback quality prediction model based on the convolutional neural network to obtain the video playback quality of the target video application in the future time period.

[0008] In another aspect, a device for predicting video playback quality is provided, the device comprising:

[0009] The communication module obtains the video service message of the target video application in the current time period;

[0010] A processing module, used to determine the traffic characteristic data of the target video application in the current time period according to the video service message of the target video application in the current time period;

[0011] The processing module is also used to input the traffic feature data of the target video application in the current time period into the video playback quality prediction model based on the convolutional neural network to obtain the video playback quality of the target video application in the future time period.

[0012] On the other hand, an electronic device is provided, comprising: a memory and a processor; the memory and the processor are coupled; the memory is used to store computer program instructions executable by the processor; and when the processor executes the computer program instructions, the method for predicting the video playback quality of any of the above embodiments is implemented.

[0013] On the other hand, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed on an electronic device, the method for predicting video playback quality of any of the above embodiments is implemented.

[0014] On the other hand, a computer program product is provided, which includes computer program instructions, and when the computer program instructions are executed, the method for predicting video playback quality of any of the above embodiments is implemented.

[0015] The technical solution provided by the embodiment of the present application determines the traffic feature data of the target video application in the current time period according to the video service message of the target video application in the current time period, and inputs it into the video playback quality prediction model based on the convolutional neural network to predict the video playback quality in the future time period. On the one hand, the video playback quality prediction model is established by using the idea of ​​the more mature convolutional neural network in the image field, which improves the prediction efficiency and accuracy; on the other hand, regardless of whether the video service message is encrypted, the video playback quality can be predicted by extracting the traffic feature data, which has strong versatility. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the structure of a video playback quality prediction system provided in an embodiment of the present application;

[0017] Figure 2 A flowchart of a method for predicting video playback quality provided in an embodiment of the present application;

[0018] Figure 3 A flowchart of a method for training a video playback quality prediction model provided in an embodiment of the present application;

[0019] Figure 4 A schematic diagram of the structure of a sample provided in an embodiment of the present application;

[0020] Figure 5 A schematic diagram of the structure of raw data provided in an embodiment of the present application;

[0021] Figure 6 A schematic diagram of the structure of a device for predicting video playback quality provided in an embodiment of the present application;

[0022] Figure 7A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "plurality" means two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different.

[0025] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of "exemplary" or "for example" should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way.

[0026] With the rapid development of communication technology, online video viewing services have become more and more popular. The status of online video viewing services in Internet applications is getting higher and higher, and the number of video users is also increasing. In order to improve user retention and growth rate, the prediction and timely intervention of video service playback quality are the focus of network operators. On the other hand, as the Internet industry pays more and more attention to user privacy and security, the trend of network traffic encryption is becoming more and more obvious, which also makes it extremely difficult to predict the quality of video service playback.

[0027] Currently, existing methods for predicting video playback quality include prediction methods based on bitrate value extraction and prediction methods based on traditional machine learning methods.

[0028] Among them, the prediction method based on bit rate value extraction is to first analyze the application layer load of the online video service message, try to extract the video bit rate information carried therein, and then calculate the video buffer size required for smooth viewing through the bit rate and playback time, and compare it with the current amount of data downloaded. If the amount of downloaded data does not have a certain slack margin relative to the video buffer size, it is predicted that a freeze is about to occur. The premise of using this method is that the traffic is transmitted in plain text, and the application developer writes the correct bit rate information into the message payload. At present, the trend of Internet traffic encryption is obvious, and the presence or absence of bit rate characteristics and the method of extracting the bit rate are strongly related to the specific video service, so this method is not universal.

[0029] The prediction method based on traditional machine learning methods is to analyze the packet length, timestamp, uplink and downlink statistics of a video playback time slice, and process it into a set of more advanced features with business characteristics, such as average traffic, delay distribution, etc., and then use machine learning algorithms such as random forests to predict the video playback quality at the next moment. This method can solve the problem that encrypted video traffic cannot decode the message payload to a certain extent, but it is highly dependent on feature engineering and specific services, and the trained model is not reusable, and the overall efficiency is not high.

[0030] In view of this, the present invention provides a method for predicting video playback quality, which includes obtaining video service messages of a target video application in a current time period; determining traffic feature data of the target video application in the current time period according to the video service messages of the target video application in the current time period; inputting the traffic feature data of the target video application in the current time period into a video playback quality prediction model based on a convolutional neural network to obtain the video playback quality of the target video application in a future time period. On the one hand, the video playback quality prediction model is established by using the idea of ​​a relatively mature convolutional neural network in the field of images, thereby improving the prediction efficiency and accuracy; on the other hand, regardless of whether the video service message is encrypted, the video playback quality can be predicted by extracting traffic feature data, which has strong versatility.

[0031] The embodiment of the present invention provides a method for predicting video playback quality, which can be applied to a device for predicting video playback quality. Exemplarily, the device for predicting video playback quality can be a system architecture for predicting video playback quality. Optionally, the device for predicting video playback quality can also be deployed on a physical machine through a virtual machine (VM), and the device for predicting video playback quality can also implement the function to be implemented by the device for predicting video playback quality. The device for predicting video playback quality can also be deployed on a terminal device.

[0032] In some embodiments, the terminal device may be a device with wireless transceiver function, which may be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it may also be deployed on the water surface (such as ships, etc.); it may also be deployed in the air (such as airplanes, balloons and satellites, etc.). The terminal device may be a mobile phone, a tablet computer (Pad), a computer with wireless transceiver function, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. The embodiments of the present application do not limit the application scenarios. The terminal may sometimes also be referred to as a user, user equipment (UE), access terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal, mobile device, UE terminal, wireless communication equipment, UE agent or UE device, etc., but the embodiments of the present application are not limited to this.

[0033] For example, Figure 1 A schematic diagram of a video playback quality prediction system architecture provided in the present application, wherein the video playback quality prediction system architecture includes a data acquisition module 11, a data processing module 12, a model training module 13 and an online operation module 14.

[0034] The data collection module 11 is used to collect video service messages generated by the target video application to support the subsequent training process, by obtaining the video service messages of the target video application in a historical time period when the terminal where the target video application is installed is in a preset scenario.

[0035] The data processing module 12 is used to process the video service messages of the target video application obtained by the data acquisition module 11 within the historical time period, and determine the traffic characteristic data of the target video application in the historical time period; the traffic characteristic data of the target video application in the historical time period is used to form a sample corresponding to the preset scene, and the video playback quality of the target video application in the next time period after the historical time period is used as a label to obtain a training set.

[0036] The model training module 13 is used to train the initial model based on the training set output by the data processing module 12 to obtain a video playback quality prediction model. The video playback quality prediction model can predict the video playback quality of the target video application in the future time period based on the traffic feature data of the target video application in the current time period.

[0037] The online operation module 14 is used to load the video playback quality prediction model output by the model training module 13 on the terminal device. Then, according to the video service packets generated by the target video application in the current time period, the traffic characteristic data of the target video application in the current time period is determined. Finally, the traffic characteristic data of the target video application in the current time period is input into the video playback quality prediction model based on the convolutional neural network to obtain the video playback quality of the target video application in the future time period.

[0038] The following is a detailed description of the method for predicting video playback quality provided by an embodiment of the present invention in conjunction with the accompanying drawings.

[0039] The embodiment of the present invention provides a method for predicting video playback quality. Figure 2 As shown, the method comprises the following steps:

[0040] S101: Obtain video service messages of a target video application in a current time period.

[0041] In some embodiments, the duration of the current time period is a preset duration, for example, the duration of the current time period is 15 seconds.

[0042] In some embodiments, the preset duration is determined according to the service requirements of the target video application, and the service requirements include at least one of the following: delay requirement, bandwidth requirement, and jitter requirement.

[0043] The latency requirement refers to the transmission time delay from the data sender to the receiver. Video applications usually have a maximum tolerance for latency requirements, that is, the maximum allowable delay time for data transmission. Based on the latency requirements, a preset duration can be selected to keep the data transmission latency within the required range as much as possible and ensure that the performance of the video application meets the requirements.

[0044] Bandwidth is the data transmission rate supported by the system or network. The bandwidth requirements of video applications may be affected by factors such as video resolution, video encoding method, frame rate, etc. Based on the bandwidth requirements, the bandwidth consumption of the video application in a specific time period can be estimated, and a preset time period can be selected so that the network can provide sufficient bandwidth support to meet the requirements of the video application.

[0045] Jitter requirements refer to the latency fluctuations of data transmission. Video applications have a certain tolerance for latency fluctuations. Based on the jitter requirements, you can select a preset duration to keep the jitter of data transmission within the required range as much as possible and ensure that the playback experience of the video application meets the requirements.

[0046] It is understandable that, depending on the business requirements of the target video application, an appropriate preset duration is selected to ensure that the performance of the target video application meets the business requirements.

[0047] In some embodiments, the video service message includes an encrypted video service message and / or an unencrypted video service message. Thus, identifying and analyzing these messages can help monitor and improve the security of video transmission and enhance user trust and experience.

[0048] In some embodiments, packet capture software is used to capture network packets passing through a terminal device; based on the characteristics and protocols of a target video application, deep packet inspection (DPI) is performed on the captured network packets to obtain video service packets of the target video application in the current time period.

[0049] Among them, packet capture software is a tool used to capture network data packets and analyze them. It can monitor the network interface, capture the data packets transmitted through the interface, and provide corresponding analysis and display functions to help users gain a deeper understanding of network communications, network protocols, and data flows. Common packet capture software includes Wireshark, tcpdump, Microsoft Message Analyzer, and Fiddler.

[0050] DPI is a network traffic analysis technology that can identify packets corresponding to different applications, such as video service packets, by deeply analyzing and parsing the contents of network data packets.

[0051] S102: Determine traffic characteristic data of the target video application in the current time period according to video service messages of the target video application in the current time period.

[0052] The traffic characteristic data includes uplink traffic, downlink traffic, uplink packet count, and downlink packet count. Uplink traffic refers to the traffic sent from the terminal device to the network, while downlink traffic refers to the traffic sent from the network to the terminal device. The uplink packet count and downlink packet count refer to the number of data packets in the corresponding traffic.

[0053] As a possible implementation method, the video service messages of the target video application in the current time period are equally cut and feature calculated on the timeline from several dimensions included in the traffic feature data to obtain the upstream traffic, downstream traffic, number of upstream packets and number of downstream packets of the target video application at different time granularities in the current time period.

[0054] In some embodiments, the time granularity of the cutting is a preset value, which is determined according to the service requirements of the target video application. The service requirements include at least one of the following: delay requirements, bandwidth requirements, and jitter requirements. For example, the time granularity of the cutting is 0.1 seconds.

[0055] For example, assuming that the current time period is equally divided into 5 time granularities in minutes, the following is an example showing how the target video application calculates the upstream traffic, downstream traffic, number of upstream packets, and number of downstream packets at each time granularity in the current time period.

[0056] Among them, it is assumed that the current time period is 2023-06-28 09:00:00 to 2023-06-28 10:00:00;

[0057] Upstream traffic (bytes): [1000, 2000, 1500, 1200, 1800];

[0058] Downstream traffic (bytes): [3000, 4000, 3500, 3200, 3800];

[0059] Number of uplink packets: [10, 15, 12, 8, 13];

[0060] Number of downlink packets: [20, 25, 22, 18, 23].

[0061] The current time period is divided into equal parts: time granularity 1 is 09:00-09:12; time granularity 2 is 09:12-09:24; time granularity 3 is 09:24-09:36; time granularity 4 is 09:36-09:48; time granularity 5 is 09:48-10:00.

[0062] After feature calculation, the video service packets in time granularity 1 have an upstream flow of 1000 bytes, a downstream flow of 3000 bytes, an upstream packet number of 10 packets, and a downstream packet number of 20 packets.

[0063] In time granularity 2, the upstream traffic is 2000 bytes, the downstream traffic is 4000 bytes, the number of upstream packets is 15 packets, and the number of downstream packets is 25 packets.

[0064] In time granularity 3, the upstream traffic is 1500 bytes, the downstream traffic is 3500 bytes, the number of upstream packets is 12 packets, and the number of downstream packets is 22 packets.

[0065] In time granularity 4, upstream traffic: 1200 bytes, downstream traffic: 3200 bytes, upstream packet number: 8 packets, downstream packet number: 18 packets;

[0066] In time granularity 5, the upstream traffic is 1800 bytes, the downstream traffic is 3800 bytes, the number of upstream packets is 13 packets, and the number of downstream packets is 23 packets.

[0067] S103: Input the traffic feature data of the target video application in the current time period into a video playback quality prediction model based on a convolutional neural network to obtain the video playback quality of the target video application in the future time period.

[0068] Among them, Convolutional Neural Network (CNN) is a deep learning model that is widely used in image recognition, computer vision, speech recognition and other fields. It is a special artificial neural network with basic components such as convolution layer, pooling layer and fully connected layer. The core idea of ​​CNN is to extract features of input traffic feature data through convolution operation, and to abstract and classify high-level features through stacked neural network structures.

[0069] Based on this, the traffic feature data of the target video application in the current time period is determined according to the video service packets of the target video application in the current time period, and then input into the video playback quality prediction model based on the convolutional neural network to predict the video playback quality in the future time period. On the one hand, the video playback quality prediction model is established by using the idea of ​​the more mature convolutional neural network in the image field, which improves the prediction efficiency and accuracy; on the other hand, regardless of whether the video service packets are encrypted, the video playback quality can be predicted by extracting the traffic feature data, which has strong versatility.

[0070] In some embodiments, the present application provides a method for training a video playback quality prediction model. Figure 3 As shown, the method comprises the following steps:

[0071] S201. Obtain a training set.

[0072] The training set includes multiple samples with labels, which include traffic feature data of the target video application in the historical time period, and the label is used to indicate the video playback quality of the target video application in the next time period after the historical time period. The traffic feature data includes uplink traffic, downlink traffic, the number of uplink packets, and the number of downlink packets.

[0073] In some embodiments, the duration of the historical time period is a preset duration.

[0074] In some embodiments, the preset duration is determined according to the service requirements of the target video application, and the service requirements include at least one of the following: delay requirement, bandwidth requirement, and jitter requirement.

[0075] In some embodiments, the labels of samples in the training set include excellent, good, and poor.

[0076] In some embodiments, based on the video quality evaluation index, the video playback quality of the target video application in the next time period after the historical time period is evaluated to obtain an evaluation score of the video playback quality of the target video application in the next time period after the historical time period; and the label of the sample is determined based on the evaluation score. The video quality evaluation index includes at least one of the resolution, frame rate, compression rate and loading speed of the video.

[0077] In some embodiments, when the evaluation score is greater than a first preset score, the label of the sample is determined to be excellent; when the evaluation score is less than the first preset score and greater than a second preset score, the label of the sample is determined to be good; when the evaluation score is less than the second preset score, the label of the sample is determined to be poor.

[0078] For example, Figure 4 A schematic diagram of the structure of a sample is provided. Figure 4 As shown, the label of the sample is excellent. The sample includes the uplink traffic, downlink traffic, number of uplink packets, and number of downlink packets of the target video application in different time granularities in the historical time period. For example, the uplink traffic of the target video application in time granularity n of the historical time period is V1n; the downlink traffic of the target video application in time granularity n of the historical time period is V2n; the number of uplink packets of the target video application in time granularity n of the historical time period is V3n; the number of downlink packets of the target video application in time granularity n of the historical time period is V4n.

[0079] In some embodiments, when the terminal on which the target video application is installed is in a preset scenario, video service messages of the target video application within a historical time period are obtained; based on the video service messages of the target video application within the historical time period, traffic characteristic data of the target video application within the historical time period is determined; and the traffic characteristic data of the target video application within the historical time period is used to form a sample corresponding to the preset scenario.

[0080] In some embodiments, the preset scenarios include at least one of the following: the terminal is in a high-speed moving area; the terminal is in a non-high-speed moving area; the terminal accesses a base station in a high-load state; the terminal accesses a base station in a non-high-load state; the terminal is in a weak signal coverage area; the terminal is in a strong signal coverage area.

[0081] In some embodiments, the high-speed moving area is an area where the moving speed is greater than a first preset speed; the high-speed moving area is an area where the moving speed is less than a second preset speed.

[0082] In some embodiments, a base station in a high-load state is a base station whose load is greater than a first preset threshold; a base station in a non-high-load state is a base station whose load is less than a second preset threshold.

[0083] In some embodiments, the weak signal coverage area is an area where the signal strength is less than a third preset threshold; the strong signal coverage area is an area where the signal strength is greater than a fourth preset threshold.

[0084] In some embodiments, there are at least two samples in the training set corresponding to different preset scenarios.

[0085] For example, when the terminal with the target video application installed is in a preset scenario, the network packets passing through the target device are captured using tcpdump software to obtain the captured packet file in the preset scenario; then, the video playback quality at each time point in the historical time period is recorded using a manual or automated method to obtain a marked file, where every 5 seconds is recorded as a time point. The captured packet file and the marked file are used as one set of original data. Then, the terminal is placed in other preset scenarios, and the above steps are repeated to obtain multiple sets of original data. Figure 5 A schematic diagram of the structure of the raw data is provided.

[0086] Then, for each time point in each original data, the video playback quality corresponding to the time point is used as the label of each sample. The network message of the preset time before the time point is obtained, and the DPI detection and analysis are performed to obtain the video service message of the preset time before the time point; the video service message of the preset time before the time point is equally divided and feature calculated on the timeline according to the time granularity of 0.1 seconds, and the uplink traffic, downlink traffic, number of uplink packets and number of downlink packets of the video service message of the preset time before the time point at different time granularities are obtained; the uplink traffic, downlink traffic, number of uplink packets and number of downlink packets of the video service message of the preset time before the time point at different time granularities are used as the sample corresponding to the time point.

[0087] S202: Based on the training set, train the initial model to obtain a video playback quality prediction model.

[0088] In some embodiments, the model parameters of the initial model are determined according to the business type of the video played by the target video application and the sample structure contained in the training set; and the initial model is determined according to the model parameters of the initial model, wherein the model parameters of the initial model include the depth of the network and the size of the convolution kernel.

[0089] Exemplarily, a training set is obtained. Each sample among the multiple labeled samples in the training set is used as the input of an untrained convolutional neural network, the video playback quality corresponding to the input sample is used as the output of the convolutional neural network, and the convolutional neural network is trained using a machine learning method (such as a self-supervised learning method) to obtain a video playback quality prediction model.

[0090] During the training process, samples can be input into the convolutional neural network one by one to obtain the video playback quality output by the convolutional neural network. Then, the loss value can be determined based on the output video playback quality and the label value of the sample label corresponding to the input sample. The loss value can be used to characterize the difference between the video playback quality of the output target video application in the next time period after the historical time period and the video playback quality of the actual target video application in the next time period after the historical time period. The larger the loss value, the greater the difference. The loss value can be determined based on Euclidean distance, etc. Afterwards, the loss value can be used to update the parameters of the convolutional neural network. Thus, each time a sample is input, the parameters of the convolutional neural network can be updated based on the loss value.

[0091] In some embodiments, the video playback quality prediction model can determine whether training is completed in a variety of ways. As an example, when the error between the video playback quality of the target video application output by the video playback quality prediction model in the next time period after the historical time period and the video playback quality of the actual target video application in the next time period after the historical time period is less than a preset value (e.g., 0.01), it can be determined that the training is completed. As another example, if the number of training times of the convolutional neural network is equal to the preset number of times, it can be determined that the training is completed. Here, when it is determined that the training is completed, the trained convolutional neural network can be determined as a video playback quality prediction model.

[0092] Based on this, the network traffic is represented as a one-dimensional image, and the idea of ​​a relatively mature convolutional neural network in the image field is used to train the initial model to obtain a video playback quality prediction model. Through the self-learning ability of the deep learning network, suitable high-level features are automatically found during the training process, which saves the complex feature engineering steps compared to traditional machine learning methods; and the good transfer learning characteristics of the convolutional neural network can be further utilized. Based on the model of a certain video application that has been learned, the remaining video application playback quality models can be assisted in learning, thereby speeding up the generation and deployment of new models and meeting the timeliness requirements of new services.

[0093] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the method. A video playback quality prediction device is also shown below, which is used to execute the video playback quality prediction method in any of the above embodiments and possible implementations thereof. It can be understood that the video playback quality prediction device includes hardware structures and / or software modules corresponding to the execution of each function in order to implement the video playback quality prediction method; those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiment of the present application, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0094] The embodiment of the present application can divide the functional modules of the prediction device for video playback quality according to the above method embodiment. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one functional module. The above integrated module can be implemented in the form of hardware or software. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. The following is an example of dividing each functional module corresponding to each function.

[0095] Figure 6 The video playback quality prediction device 30 provided in the embodiment of the present application includes: a communication module 31 , a processing module 32 and a model training module 33 .

[0096] The communication module 31 is used to obtain the video service message of the target video application in the current time period;

[0097] The processing module 32 determines the traffic characteristic data of the target video application in the current time period according to the video service message of the target video application in the current time period;

[0098] The processing module 32 is also used to input the traffic feature data of the target video application in the current time period into the video playback quality prediction model based on the convolutional neural network to obtain the video playback quality of the target video application in the future time period.

[0099] In some embodiments, the traffic characteristic data includes uplink traffic, downlink traffic, the number of uplink packets, and the number of downlink packets.

[0100] In some embodiments, the model training module 33 is used to obtain a training set, the training set includes a plurality of samples carrying labels, the samples include traffic feature data of the target video application in a historical time period, and the label is used to indicate the video playback quality of the target video application in the next time period after the historical time period;

[0101] The model training module 33 is also used to train the initial model based on the training set to obtain a video playback quality prediction model.

[0102] In some embodiments, the communication module 31 is used to obtain the video service message of the target video application in the historical time period when the terminal on which the target video application is installed is in a preset scenario. The processing module 32 is used to determine the traffic characteristic data of the target video application in the historical time period according to the video service message of the target video application in the historical time period; and the traffic characteristic data of the target video application in the historical time period constitutes a sample corresponding to the preset scenario.

[0103] In some embodiments, the preset scenario includes at least one of the following:

[0104] The terminal is in a high-speed moving area;

[0105] The terminal is in a non-high-speed mobile area;

[0106] The terminal accesses a base station in a high-load state;

[0107] The terminal accesses a base station that is not in a high-load state;

[0108] The terminal is in an area with weak signal coverage;

[0109] The terminal is in an area with strong signal coverage.

[0110] In some embodiments, there are at least two samples in the training set corresponding to different preset scenarios.

[0111] In some embodiments, the duration of the previous time period and the duration of the historical time period are both preset durations, which are determined based on the business requirements of the target video application. The business requirements include at least one of the following: delay requirements, bandwidth requirements, and jitter requirements.

[0112] In some embodiments, the video service packets include encrypted video service packets and / or unencrypted video service packets.

[0113] In the case of implementing the functions of the above-mentioned integrated modules in the form of hardware, the embodiment of the present application also provides a possible structure of an electronic device, which is used to execute the method for predicting video playback quality provided by the embodiment of the present application. Figure 7 As shown, the electronic device 400 includes: a communication interface 403, a processor 402 and a bus 404. Optionally, the electronic device may further include a memory 401.

[0114] Processor 402 may be a processor that implements or executes various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of the present application. The processor 402 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the embodiments of the present application. The processor 402 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0115] The communication interface 403 is used to connect with other devices via a communication network, such as Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0116] The memory 401 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0117] As a possible implementation, the memory 401 may exist independently of the processor 402, and the memory 401 may be connected to the processor 402 via a bus 404 to store instructions or program codes. When the processor 402 calls and executes the instructions or program codes stored in the memory 401, the method for predicting the video playback quality provided in the embodiment of the present application can be implemented.

[0118] In another possible implementation, the memory 401 may also be integrated with the processor 402 .

[0119] The bus 404 may be an extended industry standard architecture (EISA) bus, etc. The bus 404 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0120] Some embodiments of the present application provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium), which stores computer program instructions. When the computer program instructions are executed on a computer, the computer executes the method for predicting video playback quality as described in any of the above embodiments.

[0121] In an exemplary implementation, the computer may be the above-mentioned video playback quality prediction device, and the present application does not limit the specific form of the computer.

[0122] In some examples, the above-mentioned computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes, etc.), optical disks (e.g., compact disks (CD), digital versatile disks (DVD), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROM), cards, sticks, or key drives, etc.). The various computer-readable storage media described in this application may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0123] An embodiment of the present application provides a computer program product comprising instructions. When the computer program product is run on a computer, the computer is enabled to execute the method for predicting video playback quality described in any of the above embodiments.

[0124] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for predicting video playback quality, characterized in that: The method comprises: Obtain the video service packets of the target video application in the current time period; Determining traffic characteristic data of the target video application in the current time period according to the video service messages of the target video application in the current time period; The traffic feature data of the target video application in the current time period is input into a video playback quality prediction model based on a convolutional neural network to obtain the video playback quality of the target video application in the future time period.

2. The method according to claim 1, characterized in that: The traffic characteristic data includes uplink traffic, downlink traffic, the number of uplink packets and the number of downlink packets.

3. The method according to claim 1, characterized in that The video playback quality prediction model is trained in the following way: Acquire a training set, wherein the training set includes a plurality of samples carrying labels, wherein the samples include traffic feature data of the target video application in a historical time period, and the labels are used to indicate the video playback quality of the target video application in a next time period after the historical time period; Based on the training set, the initial model is trained to obtain the video playback quality prediction model.

4. The method according to claim 3, characterized in that The method further comprises: When the terminal on which the target video application is installed is in a preset scenario, obtaining a video service message of the target video application in the historical time period; Determining traffic characteristic data of the target video application in the historical time period according to video service messages of the target video application in the historical time period; The traffic feature data of the target video application in the historical time period constitutes a sample corresponding to the preset scenario.

5. The method according to claim 4, characterized in that The preset scenario includes at least one of the following: The terminal is in a high-speed moving area; The terminal is in a non-high-speed mobile area; The terminal accesses a base station in a high-load state; The terminal accesses a base station in a non-high-load state; The terminal is in a weak signal coverage area; The terminal is in a strong signal coverage area.

6. The method according to claim 4 or 5, characterized in that: There are at least two samples in the training set corresponding to different preset scenarios.

7. The method according to claim 3, characterized in that The duration of the current time period and the duration of the historical time period are both preset durations, and the preset duration is determined according to the business requirements of the target video application, and the business requirements include at least one of the following: delay requirements, bandwidth requirements, and jitter requirements.

8. The method according to claim 1, characterized in that The video service message includes an encrypted video service message and / or an unencrypted video service message.

9. An electronic device, characterized in that: include: Memory and processor; Memory and processor coupling; The memory is used to store instructions executable by the processor; When the processor executes the instructions, the method according to any one of claims 1 to 8 is performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the method according to any one of claims 1 to 8.

Images