CN115802078A - Video stream transmission method, device, electronic device, and computer-readable storage medium - Google Patents

Abstract

The present application discloses a video stream transmission method, device, electronic equipment, and computer-readable storage medium, which are applied to a server. The video stream transmission method includes: obtaining buffer size information of a virtual buffer area of a server, wherein the The virtual buffer area is used to simulate the real video transmission buffer area of the client; according to the obtained network state parameters and the size information of the buffer area, select the target transmission rate required for video stream transmission to the client; according to the target The transmission rate is to transmit the video stream to the client. The application solves the technical problem of low stability of video stream transmission.

Description

Video stream transmission method, device, electronic device, and computer-readable storage medium

technical field

The present application relates to the technical field of video transmission, and in particular to a video stream transmission method, device, electronic equipment, and computer-readable storage medium.

Background technique

At present, when performing video streaming, the client usually needs to establish a cache area to relieve the transmission pressure of the server and speed up the loading speed of the client. The cache area of the client needs to continuously feed back its real-time status to the server. The basis for network transmission rate decision-making, but when the real-time status is fed back from the client to the server, it takes up a lot of network bandwidth, which will affect the stability of video streaming.

Contents of the invention

The main purpose of the present application is to provide a video stream transmission method, device, electronic equipment and computer-readable storage medium, aiming at solving the technical problem of low stability of video stream transmission.

In order to achieve the above purpose, this application provides a video stream transmission method, which is applied to the server, and the video stream transmission method includes:

Obtain the buffer size information of the virtual buffer area of the server, wherein the virtual buffer area is used to simulate the real video transmission buffer area of the client;

According to the obtained network state parameters and the size information of the buffer area, select the target transmission rate required for video stream transmission to the client;

Perform video stream transmission to the client according to the target transmission rate.

Optionally, the step of obtaining the buffer size information of the server virtual buffer includes:

Obtaining the video stream data of the server, according to the time feature extractor, performing time feature extraction on the video stream data of the server, obtaining the first time feature sequence;

receiving a second time feature sequence sent by the client, wherein the second time feature sequence is obtained by the client performing time feature extraction on the client video stream data corresponding to the server video stream data;

Determine buffer size information corresponding to the real video transmission buffer according to the first time feature sequence and the second time feature sequence.

Optionally, the buffer size information includes a video stream time difference, the first time feature sequence includes a first target time feature corresponding to a video to which a preset time offset is applied, and the second time feature sequence includes the The second target time feature corresponding to the first target time feature, the step of determining the buffer size information corresponding to the real video transmission buffer according to the first time feature sequence and the second time feature sequence includes :

calculating a feature distance between the first temporal feature of interest and the second temporal feature of interest;

Determine the video stream time difference according to the characteristic distance and the preset time offset.

Optionally, the step of selecting a target transmission rate required for video stream transmission to the client according to the obtained network state parameters and the buffer size information includes:

According to the obtained network state parameters and the size information of the buffer area, construct the video transmission state feature;

By inputting the characteristics of the video transmission state into a preset transmission rate prediction model, the target transmission rate required for video stream transmission between the clients is predicted.

Optionally, the step of constructing video transmission status features according to the obtained network status parameters and the buffer size information includes:

Obtain network status parameters, wherein the network status parameters include network bandwidth, video stream bit rate and video stream weight coefficient, and the video stream weight coefficient is used to characterize the frequency of video streams being clicked by users;

The buffer size information, the network bandwidth, the video stream bit rate, and the video stream weight coefficient are concatenated into the video transmission status feature.

Optionally, obtain video stream weight coefficients, including:

Obtain the video stream ID corresponding to the video stream to be transmitted, the corresponding request bit rate, the corresponding request time and the corresponding video stream parameters;

Splicing the video stream ID, the request bit rate, the request time and the video stream parameters into a video stream weight feature;

The video stream weight feature is mapped to a corresponding video stream weight coefficient.

Optionally, after the step of predicting the target transmission rate required for video stream transmission between the clients by inputting the video transmission state characteristics into a preset transmission rate prediction model, the video stream transmission Methods also include:

Acquiring model parameter information of a preset transmission rate prediction model deployed on at least one video transmission thread at the current time step, wherein each video transmission thread is in a different video transmission environment;

Aggregating the model parameter information to obtain the aggregated model parameter information;

According to the aggregated model parameter information, the preset transmission rate prediction model is updated in real time to predict the target transmission rate in the next time step.

The present application also provides a video stream transmission method, which is applied to a client, and the video stream transmission method includes:

Obtain the client video stream data, according to the time feature extractor, carry out time feature extraction to the client video stream data, obtain the client time feature sequence;

Sending the client time characteristic sequence to the server, so that the server can transmit the video stream to the client according to the target transmission rate determined by the client time characteristic sequence.

The present application also provides a video streaming device, which is applied to the server, and the video streaming device includes:

An acquisition module, configured to acquire buffer size information of a virtual buffer area of the server, wherein the virtual buffer area is used to simulate a real video transmission buffer area of the client;

The transmission rate selection module is used to select the target transmission rate required for video stream transmission to the client according to the obtained network state parameters and the buffer size information;

The transmission module is configured to perform video stream transmission to the client according to the target transmission rate.

Optionally, the acquisition module is also used for:

Obtaining the video stream data of the server, according to the time feature extractor, performing time feature extraction on the video stream data of the server, obtaining the first time feature sequence;

receiving a second time feature sequence sent by the client, wherein the second time feature sequence is obtained by the client performing time feature extraction on the client video stream data corresponding to the server video stream data;

Determine buffer size information corresponding to the real video transmission buffer according to the first time feature sequence and the second time feature sequence.

Optionally, the buffer size information includes a video stream time difference, the first time feature sequence includes a first target time feature corresponding to a video to which a preset time offset is applied, and the second time feature sequence includes the The second target time feature corresponding to the first target time feature, the acquisition module is also used for:

calculating a feature distance between the first temporal feature of interest and the second temporal feature of interest;

Determine the video stream time difference according to the characteristic distance and the preset time offset.

Optionally, the transmission rate selection module is also used for:

According to the obtained network state parameters and the size information of the buffer area, construct the video transmission state feature;

By inputting the characteristics of the video transmission state into a preset transmission rate prediction model, the target transmission rate required for video stream transmission between the clients is predicted.

Optionally, the transmission rate selection module is also used for:

Obtain network status parameters, wherein the network status parameters include network bandwidth, video stream bit rate and video stream weight coefficient, and the video stream weight coefficient is used to characterize the frequency of video streams being clicked by users;

The buffer size information, the network bandwidth, the video stream bit rate, and the video stream weight coefficient are concatenated into the video transmission status feature.

Optionally, the transmission rate selection module is also used for:

Obtain the video stream ID corresponding to the video stream to be transmitted, the corresponding request bit rate, the corresponding request time and the corresponding video stream parameters;

Splicing the video stream ID, the request bit rate, the request time and the video stream parameters into a video stream weight feature;

The video stream weight feature is mapped to a corresponding video stream weight coefficient.

Optionally, the video streaming device is also used for:

Acquiring model parameter information of a preset transmission rate prediction model deployed on at least one video transmission thread at the current time step, wherein each video transmission thread is in a different video transmission environment;

Aggregating the model parameter information to obtain the aggregated model parameter information;

According to the aggregated model parameter information, the preset transmission rate prediction model is updated in real time to predict the target transmission rate in the next time step.

The present application also provides a video streaming device, which is applied to a client, and the video streaming device includes:

A feature extraction module is used to obtain client video stream data, and perform temporal feature extraction on the client video stream data according to a temporal feature extractor to obtain a client temporal feature sequence;

The sending module is configured to send the client time characteristic sequence to the server, so that the server can transmit the video stream to the client according to the target transmission rate determined by the client time characteristic sequence.

The present application also provides an electronic device, the electronic device is a physical device, and the electronic device includes: a memory, a processor, and the video stream transmission method stored in the memory and operable on the processor A program of the video stream transmission method, when the program of the video stream transmission method is executed by the processor, the steps of the above video stream transmission method can be realized.

The present application also provides a computer-readable storage medium, the computer-readable storage medium stores a program for realizing the video stream transmission method, and when the program of the video stream transmission method is executed by a processor, the above-mentioned video stream transmission is realized method steps.

The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the above video stream transmission method are realized.

The present application provides a video stream transmission method, device, electronic equipment, and computer-readable storage medium. Compared with the client side, a cache area usually needs to be established to relieve the transmission pressure of the server and speed up the loading speed of the client side. The buffer area needs to continuously feed back its real-time status to the server. As a technical means for determining the network transmission rate of the server, this application sets up a virtual buffer area on the server side to simulate the real video transmission buffer area of the client. Using the virtual buffer The area can determine the buffer size information of the real video transmission buffer area, and then the obtained network status parameters and the determined buffer size information can be used as the basis for selecting the transmission rate for video stream transmission to the client, and the target transmission rate can be selected , performing video stream transmission to the client according to the target transmission rate. Therefore, in this application, when performing video stream transmission, the buffer area of the client does not need to feed back its real-time status to the server in real time, which can save the interaction process between the buffer area of the client and the server for buffer state feedback, thereby saving The network bandwidth is increased, so it overcomes the technical defect that the network bandwidth is too high when the real-time status is sent from the client to the server, which will affect the stability of the video stream transmission, and the stability of the video stream transmission is improved.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application.

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, In other words, other drawings can also be obtained from these drawings without paying creative labor.

FIG. 1 is a schematic flow diagram of the first embodiment of the video stream transmission method of the present application;

Fig. 2 is a schematic flow diagram of selecting a target transmission rate based on a state-action decision network in the video stream transmission method of the present application;

FIG. 3 is a schematic diagram of model deployment for deploying a preset transmission rate prediction model in an embodiment of the present application;

FIG. 4 is a schematic flow diagram of a second embodiment of the video stream transmission method of the present application;

FIG. 5 is a schematic flowchart of a third embodiment of the video stream transmission method of the present application;

FIG. 6 is a schematic diagram of interaction between the server and the client when performing video stream transmission in an embodiment of the present application;

FIG. 7 is a schematic diagram of a device structure of a hardware operating environment involved in a video stream transmission method in an embodiment of the present application.

The realization of the purpose, functions and advantages of the present application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

Detailed ways

In order to make the above objects, features and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Apparently, the described embodiments are only some of the embodiments of this application, not all of them. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

At present, when video streaming is being transmitted, the client usually needs to establish a cache area to relieve the transmission pressure of the server and speed up the loading speed of the client, while the server needs to send a detection request to the client, and the client receives the detection request. The real-time status information of the cache area will be fed back to the server. After receiving the real-time status information of the cache area, the server will inform the client that it has received the real-time status information. Therefore, when the server confirms the real-time status information of the client, the server needs to Multiple interactions with the client will seriously occupy the network bandwidth, which will affect the stability of video streaming transmission. The process of the server detecting the real-time status information of the client cache area takes time. Due to the existence of feedback inertia, It will reduce the responsiveness of the network, and this part of the transmission is uncontrollable and highly volatile, which will further affect the stability of video streaming transmission.

Referring to FIG. 1 , the embodiment of the present application provides a video stream transmission method applied to a server. In the first embodiment of the video stream transmission method of the present application, the video stream transmission method includes:

Step S10, acquiring the buffer size information of the virtual buffer area of the server, wherein the virtual buffer area is used to simulate the real video transmission buffer area of the client;

Step S20, according to the obtained network status parameters and the buffer size information, select the target transmission rate required for video stream transmission to the client;

Step S30, performing video stream transmission to the client according to the target transmission rate.

In this embodiment, it should be noted that the video stream transmission method is applied to a server, and the server and the client are connected in communication, the server is used to transmit the video stream to the client, and the client is used to play the video. The server end is provided with a virtual buffer area, which is used to simulate the real video transmission buffer area of the client, so the size of the real video buffer area of the client can be determined in real time by utilizing the virtual buffer area, and the buffer area size information can be In order to measure the measurement value of the real video buffer size of the client, for example, it can be the time difference between the video stream of the server before transmission and the video stream of the client after transmission, and the buffer size information can also be the size of the buffer itself, It is not limited here. The network state parameter is a parameter characterizing the network state between the server and the client, and the network state parameter may be one or more of network bandwidth, video stream bit rate, and video stream weight coefficient. The stream weight coefficient is a weight coefficient that characterizes the importance of the video stream, for example, it may be a measurement value that measures the frequency of video streams being clicked, and the larger the video stream weight coefficient is, the higher the frequency of video streams being clicked.

As an example, steps S10 to S30 include: obtaining buffer size information of a server virtual buffer, wherein the virtual buffer is used to simulate a real video transmission buffer of the client; obtaining network status parameters, wherein the The network status parameters include at least one of network bandwidth, video stream code rate, and video stream weight coefficient; according to the network status parameters and the buffer size information, a video transmission status feature is constructed, and the video transmission status feature is used to Inputting a preset transmission rate prediction model to predict a target transmission rate required for video stream transmission between the clients; and performing video stream transmission to the clients at the target transmission rate. Wherein, the preset transmission rate prediction model may be a convolutional neural network model, or a reinforcement learning model, which is not limited here.

As an example, the step of constructing video transmission status features according to the network status parameters and the buffer size information includes:

The network status parameter and the buffer size information are concatenated into a corresponding feature vector, and the feature vector is used as the video transmission status feature.

In addition, it should be noted that when video streaming is being transmitted, the higher the network bandwidth occupation, the higher the network delay during video transmission, and black screens and freezes are likely to occur during video switching. In the embodiment of this application, When performing video stream transmission, the buffer area of the client does not need to feed back its real-time status to the server in real time, which can save the interaction process between the buffer area of the client and the server for buffer status feedback, and save network bandwidth. Reduce network delays and reduce the probability of black screens and stuttering during video switching.

Wherein, the step of selecting the target transmission rate required for video stream transmission to the client according to the obtained network state parameters and the buffer size information includes:

Step S21, according to the obtained network state parameters and the buffer size information, constructing video transmission state features;

Step S22, by inputting the characteristics of the video transmission state into a preset transmission rate prediction model, predicting a target transmission rate required for video stream transmission between the clients.

As an example, steps S21 to S22 include: acquiring network status parameters, wherein the network status parameters include at least one of network bandwidth, video stream bit rate, and video stream weight coefficient; according to the network status parameters and The buffer size information constructs video transmission status features; by inputting the video transmission status features into a preset transmission rate prediction model, the video transmission status features are mapped to the required video stream transmission to the client Target transfer rate.

Wherein, the step of constructing video transmission status features according to the obtained network status parameters and the buffer size information includes:

Step S211, obtaining network status parameters, wherein the network status parameters include network bandwidth, video stream bit rate and video stream weight coefficient, and the video stream weight coefficient is used to represent the frequency of video streams being clicked by users;

Step S212, splicing the buffer size information, the network bandwidth, the video stream bit rate, and the video stream weight coefficient into the video transmission status feature.

As an example, steps S211 to S212 include: obtaining network bandwidth, video stream bit rate and video stream coefficient, wherein the video stream weight coefficient is used to characterize the frequency of video streams being clicked by users; The information, the network bandwidth, the bit rate of the video stream, and the weight coefficient of the video stream are concatenated into a state feature vector, and the state feature vector is used as a video transmission state feature. The embodiment of the present application realizes that according to the buffer size information, network bandwidth, video stream bit rate and video stream weight coefficient, the video transmission status feature has more characteristic information, and provides more decision-making basis for the prediction of the target transmission rate , thus improving the prediction accuracy of the video streaming rate.

Among them, the weight coefficient of the video stream is obtained, including:

Step A10, obtaining the video stream ID corresponding to the video stream to be transmitted, the corresponding request bit rate, the corresponding request time and the corresponding video stream parameters;

Step A20, splicing the video stream ID, the request bit rate, the request time and the video stream parameters into a video stream weight feature;

Step A30, mapping the video stream weight features to corresponding video stream weight coefficients.

In this embodiment, it should be noted that the video stream ID is the identity of the video stream, and the requested bit rate is the video bit rate requested by the client for transmission, specifically the number of bits transmitted per second. The time is the transmission time requested by the client to transmit the video stream, and the video stream parameters can be parameters such as video resolution or definition; the video stream to be transmitted is the video stream that the server needs to transmit to the client at the current time step .

As an example, steps A10 to A30 include: obtaining the video stream ID corresponding to the video stream to be transmitted, the corresponding request bit rate, the corresponding request time, and the corresponding video stream parameters; The bit rate, the request time and the video stream parameters are concatenated into a corresponding weight feature vector, and the weight feature vector is used as the video stream weight feature; and the video stream weight feature is mapped to a corresponding video stream weight coefficient.

As an example, the preset video stream weight prediction model may be a fully connected neural network, and the step of mapping the video stream weight features into corresponding video stream weight coefficients includes:

The video stream weight feature is fully connected by inputting the video stream weight feature into a fully connected neural network, and the video stream weight feature is mapped to a corresponding video stream weight coefficient.

As an example, the preset video stream weight prediction model may also be a decision tree model, the preset video stream weight prediction model may be a fully connected neural network, and the preset The video stream weight prediction model predicts the importance of the video stream to be transmitted, and the steps of obtaining the video stream weight coefficient include:

By inputting each feature value in the weight feature of the video stream into the decision tree model, the importance of the video stream to be transmitted is predicted, and the weight coefficient of the video stream is obtained.

After the step of predicting the target transmission rate required for video stream transmission between the clients by inputting the video transmission state characteristics into a preset transmission rate prediction model, the video stream transmission method further includes:

Step B10, obtaining model parameter information of a preset transmission rate prediction model deployed on at least one video transmission thread at the current time step, wherein each video transmission thread is in a different video transmission environment;

Step B20, aggregating the model parameter information to obtain the aggregated model parameter information;

Step B30, update the preset transmission rate prediction model in real time according to the aggregated model parameter information, so as to predict the target transmission rate in the next time step.

In this embodiment, it should be noted that different preset transmission rate prediction models can be deployed on different video transmission threads, so that the model parameter information of the preset transmission rate prediction models on multiple different video transmission threads can be aggregated , to obtain the aggregated model parameter information, and then update the preset transmission rate prediction model on each video transmission thread with the aggregated model parameter information, so that the preset transmission rate prediction model can be optimized under different video transmission threads, which can Improve the robustness of the preset transmission rate prediction model, thereby improving the prediction accuracy of the preset transmission rate prediction model. The model parameter information may be any one of model loss, model gradient, model network parameters or decision value information.

As an example, steps B10 to B30 include: obtaining model gradient information of a preset transmission rate prediction model deployed on at least one video transmission thread at the current time step, wherein each video transmission thread is in a different video transmission environment ; Aggregating each of the model gradient information to obtain the aggregated model gradient information, wherein the aggregation method can be weighted summation or weighted average; according to the aggregated model parameter information, each of the preset The transmission rate prediction model is set to be updated in real time, so as to predict the target transmission rate of the next time step based on the preset transmission rate prediction model updated in real time.

As an example, the preset transmission rate prediction model may be a state-action decision network constructed based on reinforcement learning, the input of the state-action decision network is the video transmission state feature, and the action output by the state-action decision network is Which transmission rate to choose for video stream transmission, the reward is decision value information, and then according to the reward corresponding to the action output by the state-action decision network, the network parameters of the state-action decision network can be updated and optimized in real time, refer to Fig. 2. S _t is the video transmission state feature constructed according to the network bandwidth, buffer size information, video stream bit rate and video stream weight coefficient, π(θ) is the state-action decision network, and _at is the state-action decision network output action. Further referring to FIG. 3, FIG. 3 is a schematic diagram of model deployment of different preset transmission rate prediction models deployed on different video transmission threads in the embodiment of the present application. Subnetwork 1, subnetwork 2, subnetwork 3 and the main network are all Based on the state-action decision network constructed by reinforcement learning, the embodiment of this application is to place the sub-network with the same structure in multiple video transmission threads for synchronous training, and then concentrate the network parameters trained in the sub-network into the main network. After the main network obtains the network parameters of all sub-networks and completes the update, the parameters of the main network are then synchronized to each sub-network. In this way, the preset transmission rate prediction model can be built based on the sample data of different video transmission threads, and the preset transmission rate can be improved. Predict model adaptability to different video delivery threads.

The embodiment of this application provides a video stream transmission method. Compared with the client side, it is usually necessary to establish a buffer area to relieve the transmission pressure of the server and speed up the loading speed of the client. The client's buffer area needs to continuously feed back itself to the server The real-time status of the real-time status, as the technical means of the basis of the server network transmission rate decision, the embodiment of the present application sets a virtual buffer area on the server side to simulate the real video transmission buffer area of the client, and the real video transmission buffer area can be determined by using the virtual buffer area The size information of the buffer area of the region, and then the obtained network status parameters and the determined buffer size information can be used as the basis for selecting the transmission rate for video stream transmission between the server and the client, and the target transmission rate is selected. According to The target transmission rate is for video stream transmission to the client. Therefore, in the embodiment of the present application, when performing video stream transmission, the buffer area of the client does not need to feed back its real-time status to the server in real time, which can save the interaction process between the buffer area of the client and the server for the status feedback of the buffer area. In this way, the network bandwidth is saved, so it overcomes the technical defect that the network bandwidth is too high when the real-time status is sent from the client to the server, which will affect the stability of the video stream transmission, and improves the stability of the video stream transmission.

In another embodiment of the present application, for content that is the same as or similar to the above embodiment, reference may be made to the introduction above, and details will not be repeated hereafter. On this basis, with reference to Fig. 4, the cache area size information of described acquisition server virtual buffer area, wherein, the step that described virtual buffer area is used for simulating the real video transmission buffer area of client comprises:

Step S11, obtaining the video stream data of the server, and performing time feature extraction on the video stream data of the server according to the time feature extractor, to obtain a first time feature sequence;

Step S12, receiving the second time feature sequence sent by the client, wherein the second time feature sequence is obtained by the client performing time feature extraction on the client video stream data corresponding to the server video stream data ;

Step S13: Determine buffer size information corresponding to the real video transmission buffer according to the first time feature sequence and the second time feature sequence.

In this embodiment, it should be noted that when the video stream is transmitted from the server to the client, there will be a time difference. Usually, a buffer area is set on the client as a buffer to cache the video stream data transmitted within this time difference. Therefore, the time difference between the video stream of the server before transmission and the video stream of the client after transmission can be used as the buffer size information to measure the size of the buffer. The virtual cache area sets a virtual cache model, and the virtual cache model includes a time feature extractor and an estimator, the time feature extractor is used to extract the time feature sequence in the video stream data, and the estimator is used to predict transmission The time difference between the previous video stream on the server side and the video stream on the client side after transmission.

As an example, steps S11 to S13 include: obtaining the server video stream data transmitted by the server at the previous time step, and inputting the server video stream data into the time feature extractor to extract the server video Each video data in the stream data is mapped to a preset feature dimension to obtain a first time feature sequence; receiving a second time feature sequence sent by the client, wherein the second time feature sequence is due to the client’s understanding of the The client video stream data corresponding to the server video stream data is obtained by extracting time features, and the client video stream data is the server video stream data transmitted by the server at the previous time step received by the client; A temporal feature sequence and the second temporal feature sequence are input to the estimator, and the buffer size information corresponding to the real video transmission buffer is estimated.

As an example, the temporal feature extractor includes a first 3D convolutional neural network and a second 3D convolutional neural network, wherein the first 3D neural convolutional network is used to perform temporal feature extraction on image information, so The second 3D convolutional neural network is used to extract temporal features from the audio information. The server video stream data includes at least one frame of video data, the video data includes image information and audio information, and the first time feature sequence includes at least a first time feature.

The step of obtaining the first temporal feature sequence by inputting the server video stream data into the temporal feature extractor and mapping each video data in the server video stream data to a preset feature dimension includes:

By inputting the image information in the video data into a first 3D convolutional neural network, and mapping the image information to a first preset feature dimension, to perform temporal feature extraction on the image information in the video data to obtain an image Temporal features; the audio information in the video data is converted into corresponding mel spectrum features, and the mel spectrum features are mapped to the preset first 3D convolutional neural network by inputting the mel spectrum features Two feature dimensions, to extract time features from the audio information in the video data to obtain audio time features; splicing the image time features and the audio time features to obtain the first time features corresponding to the video data .

As an example, the client video stream data includes client video data corresponding to each frame of video data in the server video stream data, and the second time feature sequence includes a second time feature sequence corresponding to each frame of client video data. For the time feature, the method for obtaining the second time feature may refer to the specific implementation manner of obtaining the first time feature in the server above, and details will not be repeated here.

Wherein, the buffer size information includes the video stream time difference, the first time feature sequence includes the first target time feature corresponding to the video to which the preset time offset is applied, and the second time feature sequence includes the first time feature sequence A second target time feature corresponding to a target time feature, the step of determining the buffer size information corresponding to the real video transmission buffer according to the first time feature sequence and the second time feature sequence includes:

Step S131, calculating a feature distance between the first target time feature and the second target time feature;

Step S132: Determine the video stream time difference according to the characteristic distance and the preset time offset.

In this embodiment, it should be noted that, in order to determine the video stream time difference, when the server sends the server video stream data to the client, it selectively applies a The preset time offset enables the frame of video data to be transmitted from the server to the client in advance or delayed by a preset time offset.

As an example, steps S131 to S132 include: determining a first target time feature to which a preset time offset has been applied among the first time features in the first time feature sequence, and determining, at the second time Determining a second target time feature corresponding to the first target time feature in the feature sequence; obtaining a feature distance between the first target time feature and the second target time feature, wherein the feature distance can be Euclidean distance: calculate the product between the feature distance and the preset time offset to obtain the video stream time difference. For example, the preset time offset is 40ms. Suppose the video stream data on the server includes the first frame of video data A, the second frame of video data B, and the third frame of video data C. If the server can choose to delay the second frame of video data B 40ms transmission, the client will correspondingly delay receiving the second frame of video data B by 80ms. Further, assuming that the server calculates the first target time feature b1 corresponding to the delayed second frame of video data B, the client calculates the delayed reception For the second target time feature b2 corresponding to the second frame of video data B, further assuming that the server can calculate the target time feature distance between b1 and b2 as 5, the video stream time difference is 5*40ms.

As an example, the first target time feature to which a preset time offset is applied is determined in each first time feature in the first time feature sequence, and the first target time feature is determined in the second time feature sequence The step of the second target time characteristic corresponding to the first target time characteristic comprises:

Calculate the time feature distance between each first time feature and the second time feature corresponding to each first time feature; according to the value of each of the time feature distances, determine the deviation in each of the time feature distances The time feature distance with the farthest average value of each of the time feature distances is used as the target time feature distance; the first time feature corresponding to the target time feature distance is used as the first target time feature, and the target time feature The second time feature corresponding to the distance is used as the second target time feature. For example, assuming that each first time feature is (a1, b1, c1), and each second time feature is (a2, b2, c2), then the time feature distance between a1 and a2 is 1, and the time between b1 and b2 If the characteristic distance is 1.1, and the time characteristic distance between c1 and c2 is 5, then it can be determined that the time characteristic distance 5 is the target time characteristic distance farthest from the average value of each said time characteristic distance, thus c1 is the first target time feature, c2 is the second target time feature. In the embodiment of the present application, a preset time offset is applied to the server video data sent by the server. Since there is a time difference in video transmission, after the preset time offset, the first time of the server video data will be enlarged or reduced. The time feature distance between the feature and the second time feature of the corresponding client video data, so that the feature distance between the first target time feature and the second target time feature can be used as a measure of the preset time offset and the real video stream The reference value of the difference multiple between the time differences, thereby calculating the product between the characteristic distance between the first target time feature and the second target time feature and the preset time offset can be used as an estimated value of the time difference of the real video stream, Therefore, the embodiment of the present application realizes efficient estimation of the video stream time difference between the server and the client for video stream transmission.

As an example, the first target time feature to which a preset time offset is applied is determined in each first time feature in the first time feature sequence, and the first target time feature is determined in the second time feature sequence The step of the second target time characteristic corresponding to the first target time characteristic comprises:

According to the preset window size, selecting each first time feature to be screened in each of the first time features, and selecting a second time feature to be screened corresponding to each first time feature to be screened in each second time feature; Calculate the time feature distance between each first time feature to be screened and the second time feature to be screened corresponding to each first time feature to be screened; calculate the mean value of each described time feature distance to obtain the mean distance; detect each Whether the time feature distance has a target time feature distance whose distance deviation from the mean distance is greater than the preset distance deviation threshold; if it exists, the first time feature corresponding to the target time feature distance is used as the first time feature distance Target time feature, and the second time feature corresponding to the target time feature distance as the second target time feature; if it does not exist, return to the execution step: according to the preset window size, in each of the first time features Select each first time feature to be screened in each first time feature to be screened, and select the second time feature to be screened corresponding to each first time feature to be screened in each second time feature, until the first target time feature and the second target time feature are determined time features. In the embodiment of the present application, the first target time feature and the second target time feature are gradually screened and determined in a windowed manner, without the need to calculate the feature distances between all the first time features and the corresponding second time features at one time, thus saving Part of the calculation process is simplified, and the calculation efficiency of the time difference of the video stream is improved, thereby improving the transmission efficiency of the video stream.

The embodiment of the present application provides a method for determining the size information of the buffer area, that is, to obtain the video stream data of the server, and perform time feature extraction on the video stream data of the server according to the time feature extractor to obtain the first time feature sequence ; receiving the second time feature sequence sent by the client, wherein the second time feature sequence is obtained by the client performing time feature extraction on the client video stream data corresponding to the server video stream data; according to The first time feature sequence and the second time feature sequence determine buffer size information corresponding to the real video transmission buffer. In the embodiment of the present application, when determining the buffer size information, the client only needs to send the second time feature sequence to the server once, and there is no need for multiple interactions between the server and the client, so it overcomes the need for the server to confirm the client. When receiving the real-time status information of the client, the server needs to interact with the client multiple times, which is a serious technical defect in the occupation of network bandwidth, so it can reduce the occupation of network bandwidth during video streaming.

Referring to FIG. 5 , an embodiment of the present application provides a video stream transmission method, which is applied to a client. In the first embodiment of the video stream transmission method of the present application, the video stream transmission method includes:

Step C10, acquiring the client video stream data, and performing temporal feature extraction on the client video stream data according to the temporal feature extractor to obtain the client temporal feature sequence;

Step C20, sending the client time feature sequence to the server, so that the server can transmit the video stream to the client according to the target transmission rate determined by the client time feature sequence.

As an example, steps C10 to C20 include: obtaining the video stream data transmitted from the server to the client at the previous time step as client video stream data; by inputting the client video stream data into the temporal feature extractor, Map each video data in the client video stream data to a preset feature dimension to obtain a client time feature sequence; send the client time feature sequence to a server for the server to obtain a previous time step The first time feature sequence corresponding to the transmitted server video stream data, and the received client time feature sequence as the second time feature sequence, the server according to the first time feature sequence and the second time feature sequence sequence, determining the buffer size information corresponding to the real video transmission buffer, so that the server selects the target transmission rate required for video stream transmission to the client according to the buffer size information and the acquired network status parameters ; Perform video stream transmission to the client according to the target transmission rate. Wherein, the specific content of the server selecting the target transmission rate required for video stream transmission between the server and the client can refer to the specific implementation content in steps S10 to S30, and will not be repeated here. .

As an example, the temporal feature extractor includes a first 3D convolutional neural network and a second 3D convolutional neural network, wherein the first 3D neural convolutional network is used to perform temporal feature extraction on image information, so The second 3D convolutional neural network is used to extract temporal features from the audio information. The client video stream data includes at least one frame of client video data, the client video data includes client image information and client audio information, the client time feature sequence includes at least a second time feature, the By inputting the client video stream data into the temporal feature extractor, each video data in the client video stream data is mapped to a preset feature dimension, and the steps of obtaining the client temporal feature sequence include:

By inputting the client image information into a first 3D convolutional neural network, the client image information is mapped to a first preset feature dimension, so as to perform temporal feature extraction on the client image information to obtain a client image Time feature; the client audio information is converted into a corresponding Mel spectrum feature, and the Mel spectrum feature is mapped to a preset second feature dimension by inputting the Mel spectrum feature into a second 3D convolutional neural network, so as to The client audio information is subjected to time feature extraction to obtain the client audio time feature; the client image time feature and the client audio time feature are spliced to obtain the second time feature.

Referring to FIG. 6, FIG. 6 is a schematic diagram of the interaction between the server and the client when transmitting video streams in an embodiment of the present application. The server extracts the audio features and video features in the video stream data of the server as embedded features to form the first A time feature sequence, the client extracts the audio features and video features in the client video stream data as embedded features to form a second time feature sequence, after the server receives the second time feature sequence sent by the client, it uses the first The time feature sequence and the second time feature sequence are calculated through the virtual cache model to obtain the video time difference. The server inputs the video time difference and network parameters (network state parameters) into the state-action decision network built based on reinforcement learning, and outputs for transmission The rate selection strategy, the server can select the target transmission rate of the next time step according to the strategy, and transmit the video stream to the client.

The embodiment of this application provides a video stream transmission method. Compared with the client side, it is usually necessary to establish a buffer area to relieve the transmission pressure of the server and speed up the loading speed of the client. The client's buffer area needs to continuously feed back itself to the server The real-time status of the real-time status is used as a technical means for determining the network transmission rate of the server. In the embodiment of this application, the video stream data of the client is obtained, and the time feature is extracted from the video stream data of the client according to the time feature extractor to obtain the client The terminal time characteristic sequence; sending the client time characteristic sequence to the server, so that the server can transmit the video stream to the client according to the target transmission rate determined by the client time characteristic sequence. When the server selects the target transmission rate, the client only needs to feed back the time feature sequence to the server once, and there is no need for multiple interactions between the server and the client, so it can reduce the network bandwidth occupation, so it overcomes the problem from the client. Sending feedback to the server to test the real-time status not only needs to occupy network bandwidth, which will affect the stability of video streaming transmission, but also improves the stability of video streaming transmission.

The embodiment of the present application also provides a video streaming device, which is applied to the server, and the video streaming device includes:

An acquisition module, configured to acquire buffer size information of a virtual buffer area of the server, wherein the virtual buffer area is used to simulate a real video transmission buffer area of the client;

The transmission rate selection module is used to select the target transmission rate required for video stream transmission to the client according to the obtained network state parameters and the buffer size information;

The transmission module is configured to perform video stream transmission to the client according to the target transmission rate.

Optionally, the acquisition module is also used for:

Obtaining the video stream data of the server, according to the time feature extractor, performing time feature extraction on the video stream data of the server, obtaining the first time feature sequence;

receiving a second time feature sequence sent by the client, wherein the second time feature sequence is obtained by the client performing time feature extraction on the client video stream data corresponding to the server video stream data;

Determine buffer size information corresponding to the real video transmission buffer according to the first time feature sequence and the second time feature sequence.

Optionally, the buffer size information includes a video stream time difference, the first time feature sequence includes a first target time feature corresponding to a video to which a preset time offset is applied, and the second time feature sequence includes the The second target time feature corresponding to the first target time feature, the acquisition module is also used for:

calculating a feature distance between the first temporal feature of interest and the second temporal feature of interest;

Determine the video stream time difference according to the characteristic distance and the preset time offset.

Optionally, the transmission rate selection module is also used for:

According to the obtained network state parameters and the size information of the buffer area, construct the video transmission state feature;

By inputting the characteristics of the video transmission state into a preset transmission rate prediction model, the target transmission rate required for video stream transmission between the clients is predicted.

Optionally, the transmission rate selection module is also used for:

Obtain network status parameters, wherein the network status parameters include network bandwidth, video stream bit rate and video stream weight coefficient, and the video stream weight coefficient is used to characterize the frequency of video streams being clicked by users;

The buffer size information, the network bandwidth, the video stream bit rate, and the video stream weight coefficient are concatenated into the video transmission status feature.

Optionally, the transmission rate selection module is also used for:

Obtain the video stream ID corresponding to the video stream to be transmitted, the corresponding request bit rate, the corresponding request time and the corresponding video stream parameters;

Splicing the video stream ID, the request bit rate, the request time and the video stream parameters into a video stream weight feature;

The video stream weight feature is mapped to a corresponding video stream weight coefficient.

Optionally, the video streaming device is also used for:

Acquiring model parameter information of a preset transmission rate prediction model deployed on at least one video transmission thread at the current time step, wherein each video transmission thread is in a different video transmission environment;

Aggregating the model parameter information to obtain the aggregated model parameter information;

According to the aggregated model parameter information, the preset transmission rate prediction model is updated in real time to predict the target transmission rate in the next time step.

The video stream transmission device provided by the present application adopts the video stream transmission method in the above-mentioned embodiments, and solves the technical problem of low stability of video stream transmission. Compared with the prior art, the beneficial effect of the video stream transmission device provided by the embodiment of the present application is the same as that of the video stream transmission method provided by the above embodiment, and other technical features of the video stream transmission device are the same as those of the previous implementation The disclosed features of the example method are the same, and will not be repeated here.

The embodiment of the present application also provides a video streaming device, which is applied to a client, and the video streaming device includes:

A feature extraction module is used to obtain client video stream data, and perform temporal feature extraction on the client video stream data according to a temporal feature extractor to obtain a client temporal feature sequence;

The sending module is configured to send the client time characteristic sequence to the server, so that the server can transmit the video stream to the client according to the target transmission rate determined by the client time characteristic sequence.

The video stream transmission device provided by the present application adopts the video stream transmission method in the above-mentioned embodiments, and solves the technical problem of low stability of video stream transmission. Compared with the prior art, the beneficial effect of the video stream transmission device provided by the embodiment of the present application is the same as that of the video stream transmission method provided by the above embodiment, and other technical features of the video stream transmission device are the same as those of the previous implementation The disclosed features of the example method are the same, and will not be repeated here.

An embodiment of the present application provides an electronic device, and the electronic device includes: at least one processor; and a memory connected in communication with the at least one processor; wherein, the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor. The processor executes, so that at least one processor can execute the video stream transmission method in the first embodiment above.

Referring now to FIG. 7 , it shows a schematic structural diagram of an electronic device suitable for implementing an embodiment of the present disclosure. The electronic equipment in the embodiment of the present disclosure may include but not limited to such as mobile phone, notebook computer, digital broadcast receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia player), vehicle terminal (such as mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers and the like. The electronic device shown in FIG. 7 is only an example, and should not limit the functions and application scope of the embodiments of the present disclosure.

As shown in FIG. 7, an electronic device may include a processing device (such as a central processing unit, a graphics processing unit, etc.), which may be loaded into a random access memory (RAM) according to a program stored in a read-only memory (ROM) or loaded from a storage device. Various appropriate actions and processing are performed by the programs in the program. In RAM, various programs and data necessary for the operation of electronic equipment are also stored. The processing means, ROM, and RAM are connected to each other via a bus. Input/output (I/O) interfaces are also connected to the bus.

Typically, the following systems can be connected to the I/O interface: input devices including, for example, touch screens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCDs), speakers, vibrators output devices such as; storage devices including, for example, magnetic tapes, hard disks, etc.; and communication devices. A communication device may allow an electronic device to communicate with other devices wirelessly or by wire to exchange data. While an electronic device is shown with various systems in the figures, it should be understood that implementing or having all of the systems shown is not a requirement. More or fewer systems may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication means, or installed from a storage means, or installed from a ROM. When the computer program is executed by the processing device, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.

The electronic device provided by the present application adopts the video stream transmission method in the above-mentioned embodiments, and solves the technical problem of low stability of video stream transmission. Compared with the prior art, the beneficial effect of the electronic device provided by the embodiment of the present application is the same as that of the video stream transmission method provided by the first embodiment above, and other technical features of the electronic device are disclosed in the method of the previous embodiment The features are the same and will not be repeated here.

It should be understood that various parts of the present disclosure may be implemented in hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in an appropriate manner.

The above is only a specific implementation of the application, but the scope of protection of the application is not limited thereto. Anyone familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the application. Should be covered within the protection scope of this application. Therefore, the protection scope of the present application should be determined by the protection scope of the claims.

This embodiment provides a computer-readable storage medium, which has computer-readable program instructions stored thereon, and the computer-readable program instructions are used to execute the video stream transmission method in the first embodiment above.

The computer-readable storage medium provided in the embodiment of the present application may be, for example, a USB flash drive, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, system or device. Program code embodied on a computer readable storage medium may be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

The above-mentioned computer-readable storage medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

The computer-readable storage medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device: acquires the buffer size information of the server-side virtual buffer, wherein the virtual buffer It is used to simulate the real video transmission buffer area of the client; according to the obtained network state parameters and the size information of the buffer area, select the target transmission rate required for video stream transmission to the client; according to the target transmission rate, send The client performs video stream transmission.

Or obtain the client video stream data, according to the time feature extractor, carry out time feature extraction to the client video stream data, obtain the client time feature sequence; send the client time feature sequence to the server for The server transmits the video stream to the client according to the target transmission rate determined by the time characteristic sequence of the client.

Computer program code for carrying out the operations of the present disclosure can be written in one or more programming languages, or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, and conventional Procedural Programming Language - such as "C" or a similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more logical functions for implementing specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.

The modules involved in the embodiments described in the present disclosure may be implemented by software or by hardware. Wherein, the name of the module does not constitute a limitation of the unit itself under certain circumstances.

The computer-readable storage medium provided by the present application stores computer-readable program instructions for executing the above video stream transmission method, which solves the technical problem of low stability of video stream transmission. Compared with the prior art, the beneficial effect of the computer-readable storage medium provided by the embodiment of the present application is the same as the beneficial effect of the video stream transmission method provided by the foregoing embodiment, and details are not repeated here.

The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the above video stream transmission method are realized.

The computer program product provided by this application solves the technical problem of low stability of video stream transmission. Compared with the prior art, the beneficial effect of the computer program product provided by the embodiment of the present application is the same as the beneficial effect of the video stream transmission method provided by the foregoing embodiment, and details are not repeated here.

The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structures or equivalent process transformations made by using the description of the application and the accompanying drawings are directly or indirectly used in other related technical fields. , are all included in the patent processing scope of the present application in the same way.

Claims (12)

1. A video streaming method is applied to a server side, and the video streaming method comprises the following steps:

obtaining the size information of a cache region of a virtual cache region of a server, wherein the virtual cache region is used for simulating a real video cache region of a client;

selecting a target transmission rate required for transmitting the video stream to the client according to the acquired network state parameter and the size information of the cache region;

and carrying out video streaming transmission to the client according to the target transmission rate.

2. The video streaming method according to claim 1, wherein the step of obtaining the buffer size information of the server virtual buffer comprises:

acquiring server video stream data, and extracting time characteristics of the server video stream data according to a time characteristic extractor to obtain a first time characteristic sequence;

receiving a second time characteristic sequence sent by the client, wherein the second time characteristic sequence is obtained by performing time characteristic extraction on client video stream data corresponding to the server video stream data by the client;

and determining the size information of the cache region corresponding to the real video transmission cache region according to the first time characteristic sequence and the second time characteristic sequence.

3. The video streaming method according to claim 2, wherein the buffer size information includes a video streaming time difference, the first time characteristic sequence includes a first target time characteristic corresponding to a video to which a preset time offset is applied, the second time characteristic sequence includes a second target time characteristic corresponding to the first target time characteristic, and the step of determining the buffer size information corresponding to the real video transmission buffer according to the first time characteristic sequence and the second time characteristic sequence includes:

calculating a feature distance between the first target temporal feature and the second target temporal feature;

and determining the video stream time difference according to the characteristic distance and the preset time offset.

4. The video streaming method according to claim 1, wherein the step of selecting a target transmission rate required for video streaming to the client according to the obtained network status parameter and the buffer size information comprises:

constructing video transmission state characteristics according to the acquired network state parameters and the size information of the cache region;

and predicting a target transmission rate required by video streaming transmission between the clients by inputting the video transmission state characteristics into a preset transmission rate prediction model.

5. The video streaming method according to claim 4, wherein the step of constructing the video transmission status characteristic according to the obtained network status parameter and the buffer size information comprises:

acquiring network state parameters, wherein the network state parameters comprise network bandwidth, video stream code rate and a video stream weight coefficient, and the video stream weight coefficient is used for representing the frequency of clicking the video stream by a user;

and splicing the cache region size information, the network bandwidth, the video stream code rate and the video stream weight coefficient into the video transmission state characteristic.

6. The video streaming method of claim 5, wherein obtaining the video stream weight coefficient comprises:

acquiring a video stream ID corresponding to a video stream to be transmitted, a corresponding request bit rate, a corresponding request time and a corresponding video stream parameter;

splicing the video stream ID, the request bit rate, the request time and the video stream parameters into a video stream weight characteristic;

and mapping the video stream weight characteristics into corresponding video stream weight coefficients.

7. The video streaming method according to claim 4, wherein after the step of predicting the target transmission rate required for video streaming to the client by inputting the video transmission state characteristic to a preset transmission rate prediction model, the video streaming method further comprises:

acquiring model parameter information of a preset transmission rate prediction model deployed on at least one video transmission thread at the current time step, wherein each video transmission thread is in different video transmission environments;

aggregating the model parameter information to obtain aggregated model parameter information;

and updating the preset transmission rate prediction model in real time according to the aggregated model parameter information so as to predict the target transmission rate of the next time step.

8. A video streaming method applied to a client, the video streaming method comprising:

acquiring client video stream data, and performing time feature extraction on the client video stream data according to a time feature extractor to obtain a client time feature sequence;

and sending the client time characteristic sequence to a server side so that the server side can carry out video streaming transmission to the client side according to the target transmission rate determined by the client time characteristic sequence.

9. A video streaming apparatus, applied to a server, the video streaming apparatus comprising:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring the size information of a cache area of a virtual cache area of a server, and the virtual cache area is used for simulating a real video cache area of a client;

a transmission rate selection module, configured to select a target transmission rate required for video stream transmission to the client according to the acquired network state parameter and the size information of the cache area;

and the transmission module is used for transmitting the video stream to the client according to the target transmission rate.

10. A video streaming apparatus, applied to a client, the video streaming apparatus comprising:

the characteristic extraction module is used for acquiring client video stream data, and extracting time characteristics of the client video stream data according to the time characteristic extractor to obtain a client time characteristic sequence;

and the sending module is used for sending the client time characteristic sequence to a server so that the server can transmit video streams to the client according to the target transmission rate determined by the client time characteristic sequence.

11. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the video streaming method of any of claims 1 to 8.

12. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program implementing a video streaming method, the program implementing the video streaming method being executed by a processor to implement the steps of the video streaming method according to any one of claims 1 to 8.

Images