Video Transmission Delay Prediction Method, Electronic Device, and Computer-Readable Storage Medium

Abstract

The present application discloses a method for predicting video transmission delay, an electronic device, and a computer-readable storage medium. The method is applied to a sending end. The sending end obtains the wireless signal state in real time, including: in response to establishing a connection with a receiving end, obtaining a video packet corresponding to a video frame, and sending a target video packet of the current period to the receiving end; in response to receiving feedback information from the receiving end for the target video packet within the current period, determining the network transmission parameters of the current period based on the target video packet and the feedback information, and obtaining the estimated delay of a subsequent specified period based on the current wireless signal state and the network transmission parameters of the current period; in response to not receiving feedback information from the receiving end for the target video packet within the current period, obtaining the estimated delay of a subsequent specified period based on the current wireless signal state; wherein the estimated delay is used to adjust the sending strategy of video packets within a subsequent specified period. Through the above manner, the present application can improve the timeliness and accuracy of delay prediction.

Description

Technical Field

[0001] This application relates to the technical field of data transmission, and particularly to a method for predicting video transmission delay, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the increasingly wide application of wireless networks in the process of data transmission, in the process of video transmission, usually the sending end connects to the cloud platform through the wireless network, and the receiving end accesses the cloud platform through the wireless network or mobile network to view the video. After the sending end accesses the wireless network, affected by many factors such as installation location, wireless interference, network delay, and wireless resource competition, the existing methods for predicting video transmission delay are difficult to predict the round-trip time (RTT) in a timely manner, and the accuracy of the delay is not high. In view of this, how to improve the timeliness and accuracy of delay prediction has become an urgent problem to be solved. Summary of the Invention

[0003] The main technical problem to be solved by this application is to provide a method for predicting video transmission delay, an electronic device, and a computer-readable storage medium, which can improve the timeliness and accuracy of delay prediction.

[0004] To solve the above technical problem, in the first aspect of this application, a method for predicting video transmission delay is provided. The method is applied to the sending end, and the sending end obtains the wireless signal state in real time, including: in response to establishing a connection with the receiving end, obtaining the video packet corresponding to the video frame, and sending the target video packet of the current cycle to the receiving end; in response to receiving the feedback information of the receiving end for the target video packet within the current cycle, based on the target video packet and the feedback information, determining the network transmission parameters of the current cycle, and based on the current wireless signal state and the network transmission parameters of the current cycle, obtaining the estimated delay of the subsequent specified cycle; in response to not receiving the feedback information of the receiving end for the target video packet within the current cycle, based on the current wireless signal state, obtaining the estimated delay of the subsequent specified cycle; wherein, the estimated delay is used to adjust the sending strategy of the video packet in the subsequent specified cycle.

[0005] To solve the above technical problem, in the second aspect of this application, an electronic device is provided. The electronic device includes: a memory and a processor coupled to each other, wherein the memory stores program data, and the processor calls the program data to execute the method described in the first aspect above.

[0006] To solve the above technical problem, in the third aspect of this application, a computer-readable storage medium is provided, on which program data is stored, and when the program data is executed by a processor, the method described in the first aspect above is implemented.

[0007] In the above solution, after the sender and the receiver establish a connection, the video packets corresponding to the video frames required by the receiver are obtained, and the target video packets to be sent in the current cycle are sent to the receiver. When the feedback information for the target video packets is received from the receiver within the current cycle, based on the target video packets and the feedback information, the actually measured network transmission parameters in the current cycle are determined, the wireless signal state obtained in real time by the sender is acquired, and based on the current wireless signal state and the actually measured network transmission parameters in the current cycle, the round-trip delay in the subsequent specified cycle is predicted to obtain the estimated delay in the subsequent specified cycle. Thus, in the case of receiving the feedback information from the receiver, the delay in the subsequent specified cycle is predicted through multi-dimensional data, improving the accuracy of delay prediction. When the feedback information for the target video packets is not received from the receiver within the current cycle, the wireless signal state obtained in real time by the sender is acquired, and based on the current wireless signal state, the round-trip delay in the subsequent specified cycle is predicted to obtain the estimated delay in the subsequent specified cycle. Thus, in the case of not receiving the feedback information from the receiver, the dependence on the feedback information is reduced, and the wireless state information is timely used to predict the delay in the subsequent specified cycle, improving the timeliness of delay prediction. Among them, the estimated delay is used to adjust the sending strategy of the video packets in the subsequent specified cycle, so as to timely adjust and confirm the sending strategy according to the estimated delay, improving the quality of the video received by the receiver. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. Among them:

[0009] Figure 1 is a schematic flowchart of an implementation manner of the video transmission delay prediction method of the present application;

[0010] Figure 2 is a schematic flowchart of another implementation manner of the video transmission delay prediction method of the present application;

[0011] Figure 3 is a schematic diagram of an application scenario of an implementation manner of the video transmission delay prediction method of the present application;

[0012] Figure 4 is a schematic structural diagram of an implementation manner of an electronic device of the present application;

[0013] Figure 5 is a schematic structural diagram of an implementation manner of a computer-readable storage medium of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments, and adaptive combinations can be made between different embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0015] The terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after. In addition, "multiple" in this article means two or more than two.

[0016] The video transmission delay prediction method provided by the present application is applied to the sending end. The sending end obtains the wireless signal state in real time for predicting the round-trip delay RTT of video transmission, and its corresponding execution entity is the processing unit of the sending end.

[0017] Please refer to Figure 1 , Figure 1 is a schematic flowchart of an embodiment of the video transmission delay prediction method of the present application. The method includes:

[0018] S101: In response to establishing a connection with the receiving end, obtain the video packet corresponding to the video frame and send the target video packet of the current cycle to the receiving end.

[0019] Specifically, after the sending end and the receiving end establish a connection, obtain the video packet corresponding to the video frame required by the receiving end, and send the target video packet that needs to be sent in the current cycle to the receiving end.

[0020] It should be noted that the requirement for establishing a connection is usually initiated by the receiving end. After obtaining the requirement for establishing a connection, it enters the handshake stage, and the sending end attempts to establish a connection with the receiving end. Among them, taking the sending end as a network camera and the receiving end as a mobile terminal as an example, when the mobile terminal attempts to receive the video stream, the network camera attempts to establish a connection with the mobile terminal.

[0021] Optionally, the sending end and the receiving end communicate through the Reliable User Datagram Protocol (UDP) to establish a reliable connection based on the reliable UDP protocol and be able to obtain the feedback information sent by the receiving end to the sending end in a timely manner.

[0022] In some implementation scenarios, after the sender and the receiver establish a connection, obtain the video frames required by the receiver. Based on the data volume of the video frames, split the video frames into multiple video packets, and determine the video packets that need to be sent to the receiver in the current cycle as the target video packets. Among them, the number of target video packets is at least one, and send the target video packets that need to be sent in the current cycle to the receiver.

[0023] In some implementation scenarios, after the sender and the receiver establish a connection, obtain the video frames required by the receiver. Based on the image size of the video frames, split the video frames into multiple video packets with the same size and obtain the data volume corresponding to the video packets. Determine the video packets that need to be sent to the receiver in the current cycle as the target video packets. Among them, the number of target video packets is at least one, and send the target video packets that need to be sent in the current cycle to the receiver.

[0024] S102: In response to the feedback information of the receiver for the target video packet received in the current cycle, based on the target video packet and the feedback information, determine the network transmission parameters of the current cycle. Based on the current wireless signal state and the network transmission parameters of the current cycle, obtain the estimated delay of the subsequent specified cycle.

[0025] Specifically, when the feedback information of the receiver for the target video packet is received in the current cycle, based on the target video packet and the feedback information, determine the actually measured network transmission parameters of the current cycle. Obtain the wireless signal state obtained by the sender in real time. Based on the current wireless signal state and the actually measured network transmission parameters of the current cycle, predict the round-trip delay of the subsequent specified cycle, and obtain the estimated delay of the subsequent specified cycle.

[0026] It can be understood that in the case of obtaining the feedback information of the receiver, the delay of the subsequent specified cycle is predicted through multi-dimensional data, improving the accuracy of delay prediction.

[0027] Optionally, the feedback information can be an Acknowledge character (ACK), or other reply messages set based on the communication protocol. This application does not make specific restrictions on this.

[0028] In some implementation scenarios, when the feedback information of the receiver for the target video packet is received in the current cycle, based on the target video packet and the feedback information, determine the network transmission parameters corresponding to the process from the sending of the target video packet to the receipt of the feedback information from the receiver in the current cycle. Obtain the wireless signal state obtained by the sender in real time. Input the current wireless signal state and the actually measured network transmission parameters of the current cycle into the pre-trained dual-input prediction model, and obtain the estimated delay of the subsequent specified cycle output by the dual-input prediction model. Among them, the dual-input prediction model is obtained by supervised training using training data with training labels.

[0029] In some implementation scenarios, when feedback information for a target video packet is received within the current cycle, based on the target video packet and the feedback information, determine the network transmission parameters corresponding to the process from the time the target video packet is sent until the feedback information is received from the receiving end within the current cycle, obtain the wireless signal state obtained in real time by the sending end, construct a prompt text that matches the network transmission parameters and the wireless signal state, and input the prompt text, the current wireless signal state, and the network transmission parameters measured in the current cycle into a fine-tuned large language model to obtain the estimated delay for the subsequent specified cycle output by the large language model. Among them, the large language model is fine-tuned using the wireless signal state, network transmission parameters, and actual delay in historical cycles.

[0030] In a specific implementation scenario, based on the timestamps of the target video packet and the feedback information, determine the actual delay of the current cycle, and use the actual delay as the network transmission parameter for the current cycle.

[0031] In a specific implementation scenario, based on the timestamps of the target video packet and the feedback information, determine the actual delay of the current cycle, and based on the data volume corresponding to the target video packet, determine the data transmission rate of the current cycle. Use the actual delay and the data transmission rate as the network transmission parameters for the current cycle.

[0032] It should be noted that the subsequent specified cycle can be the next cycle of the current cycle or the Nth cycle after the current cycle, where N is greater than 1.

[0033] Optionally, if feedback information for the target video packet is received within the current cycle, based on the current wireless signal state and the network transmission parameters measured in the current cycle, determine the number of intervals between the subsequent specified cycle and the current cycle, where the number of intervals is greater than 1. Thus, when high-precision estimated delays can be obtained by predicting delays based on multi-dimensional parameters, increase the number of intervals to reduce resource consumption caused by delay prediction.

[0034] S103: In response to not receiving feedback information for the target video packet within the current cycle, based on the current wireless signal state, obtain the estimated delay for the subsequent specified cycle; where the estimated delay is used to adjust the video packet sending strategy within the subsequent specified cycle.

[0035] Specifically, when feedback information for the target video packet is not received within the current cycle, obtain the wireless signal state obtained in real time by the sending end, and based on the current wireless signal state, predict the round-trip delay for the subsequent specified cycle to obtain the estimated delay for the subsequent specified cycle.

[0036] It is understandable that, in the case of not receiving feedback information from the receiving end, the dependence on feedback information is reduced, and the wireless state information is timely utilized to predict the delay of the subsequent specified period, improving the timeliness of delay prediction. Among them, the estimated delay is used to adjust the sending strategy of video packets in the subsequent specified period, so as to timely adjust and confirm the sending strategy according to the estimated delay, improving the quality of the video received by the receiving end.

[0037] Optionally, if feedback information regarding the target video packet is received within the current period, the subsequent specified period is the next period of the current period, thereby reducing the number of intervals and improving the accuracy of delay prediction when only predicting the delay based on the wireless signal state.

[0038] In some implementation scenarios, when feedback information regarding the target video packet is not received within the current period, the wireless signal state obtained in real time by the sending end is acquired, and the current wireless signal state is input into a pre-trained single-input prediction model to obtain the estimated delay of the subsequent specified period output by the single-input prediction model. Among them, the single-input prediction model is obtained through supervised training using training data with training labels.

[0039] In some implementation scenarios, when feedback information regarding the target video packet is not received within the current period, the wireless signal state obtained in real time by the sending end is acquired, and the current wireless signal state is input into a fine-tuned large language model to obtain the estimated delay of the subsequent specified period output by the large language model. Among them, the large language model is fine-tuned using the wireless signal state and actual delay of historical periods.

[0040] Optionally, when feedback information is obtained within the current period, the estimated delay of the subsequent specified period is obtained using a dual-input prediction model; among them, the dual-input prediction model is obtained by training using multiple training samples, and the training samples of the dual-input prediction model include the wireless signal state and network transmission parameters of historical periods as training data, and the actual delay of the subsequent specified period of historical periods as training labels; when feedback information is not obtained within the current period, the estimated delay of the subsequent specified period is obtained using a single-input prediction model; among them, the single-input prediction model is obtained by training using multiple training samples, and the training samples of the single-input prediction model include the wireless signal state of historical periods as training data, and the actual delay of the subsequent specified period of historical periods as training labels.

[0041] It is understandable that training data is usually obtained offline. The actual data obtained in the historical period is used as training data, and the actual time delay in the subsequent specified period of the historical period is used as a training label. For different situations where network transmission parameters can be obtained based on feedback information and where network transmission parameters cannot be obtained, prediction models matching different situations are trained respectively to improve the efficiency and accuracy of time delay prediction.

[0042] Optionally, the estimated time delay in the subsequent specified period is obtained using a large language model, which may include but is not limited to Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), and Generative Pretrained Transformer models, etc. There is no specific limitation on the specific structure and specific deployment of the large language model here.

[0043] In the above solution, after the sender and the receiver establish a connection, the video packets corresponding to the video frames required by the receiver are obtained, and the target video packets to be sent in the current period are sent to the receiver. When the feedback information for the target video packet is received from the receiver within the current period, based on the target video packet and the feedback information, the actually measured network transmission parameters in the current period are determined, the wireless signal state obtained in real time by the sender is acquired, and based on the current wireless signal state and the actually measured network transmission parameters in the current period, the round-trip time delay in the subsequent specified period is predicted to obtain the estimated time delay in the subsequent specified period. Thus, in the case of receiving the feedback information from the receiver, the time delay in the subsequent specified period is predicted through multi-dimensional data, improving the accuracy of time delay prediction. When the feedback information for the target video packet is not received from the receiver within the current period, the wireless signal state obtained in real time by the sender is acquired, and based on the current wireless signal state, the round-trip time delay in the subsequent specified period is predicted to obtain the estimated time delay in the subsequent specified period. Thus, in the case of not receiving the feedback information from the receiver, the dependence on the feedback information is reduced, and the wireless state information is timely used to predict the time delay in the subsequent specified period, improving the timeliness of time delay prediction. Among them, the estimated time delay is used to adjust the sending strategy of video packets in the subsequent specified period, so as to timely adjust and confirm the sending strategy according to the estimated time delay, improving the quality of the video received by the receiver.

[0044] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of another implementation manner of the video transmission time delay prediction method of this application. The method includes:

[0045] S201: Obtain an initial estimated delay based on the current wireless signal state.

[0046] Specifically, after the receiving end initiates a connection establishment request, the sending end prepares to establish a connection with the receiving end. Since no data is being sent for this connection, the current network transmission parameters cannot be obtained. Thus, the wireless signal state obtained by the sending end in real time is acquired, and based on the current wireless signal state, the delay in the handshake phase is predicted to obtain an initial estimated delay, so as to use the initial estimated delay for transmission control in the handshake phase and improve the control accuracy.

[0047] Optionally, in the case where network transmission parameters are not obtained, the initial estimated delay is obtained using a single-input prediction model. Among them, the single-input prediction model is trained using multiple training samples. The training samples of the single-input prediction model include the wireless signal state of the historical period as training data, and the actual delay of the subsequent specified period of the historical period as training labels.

[0048] S202: Try to establish a connection with the receiving end in the handshake phase using the initial estimated delay; among them, when the handshake phase times out, use the initial estimated delay for timeout retransmission.

[0049] Specifically, try to establish a connection with the receiving end in the handshake phase using the initial estimated delay, and determine whether the handshake phase times out. If it times out, use the initial estimated delay for timeout retransmission to establish a connection with the receiving end as soon as possible.

[0050] S203: In response to establishing a connection with the receiving end, obtain the video packets corresponding to the video frames and send the target video packets of the current period to the receiving end.

[0051] Specifically, after the sending end establishes a connection with the receiving end, obtain the video packets corresponding to the video frames required by the receiving end, and send the target video packets that need to be sent in the current period to the receiving end.

[0052] Please refer to Figure 3 , Figure 3 which is a schematic diagram of the application scenario of an embodiment of the video transmission delay prediction method of this application. After the sending end establishes a connection with the receiving end, the video frames are segmented based on the data volume of the video frames to obtain the video packets corresponding to the video frames. Among them, the key frames and non-key frames correspond to different data volumes, and different numbers of video packets can be obtained.

[0053] In some implementation scenarios, in response to establishing a connection with the receiving end, obtain video packets corresponding to video frames, and send the target video packets of the current cycle to the receiving end, including: in response to establishing a connection with the receiving end, obtain the video frames received by the receiving end, and based on the data volume of the video frames, divide the video frames into multiple video packets; obtain the target video packets that match the sending strategy of the current cycle, and send the target video packets of the current cycle to the receiving end.

[0054] Specifically, when the sending end establishes a connection with the receiving end, obtain the video frames received by the receiving end, and based on the data volume of the video frames, divide the video frames into multiple video packets, so as to divide the video frames with different data volumes as evenly as possible, make the transmission of video packets more stable, and facilitate adjusting the transmission strategy according to the estimated delay.

[0055] Further, determine the sending strategy of the current cycle, obtain the video packets required to be sent by the sending strategy as the target video packets, and send the target video packets of the current cycle to the receiving end, so as to ensure that the video packets are sent to the receiving end according to the sending strategy of each cycle.

[0056] S204: In response to receiving feedback information from the receiving end for the target video packets within the current cycle, based on the target video packets and the feedback information, determine the network transmission parameters of the current cycle, and based on the current wireless signal state and the network transmission parameters of the current cycle, obtain the estimated delay of the subsequent specified cycle.

[0057] Specifically, when receiving feedback information from the receiving end for the target video packets within the current cycle, based on the target video packets and the feedback information, determine the actually measured network transmission parameters of the current cycle, obtain the wireless signal state obtained by the sending end in real time, and based on the current wireless signal state and the actually measured network transmission parameters of the current cycle, predict the round-trip delay of the subsequent specified cycle to obtain the estimated delay of the subsequent specified cycle.

[0058] In some implementation scenarios, based on the target video packets and the feedback information, determine the network transmission parameters of the current cycle, and based on the current wireless signal state and the network transmission parameters of the current cycle, obtain the estimated delay of the subsequent specified cycle, including: based on the target video packets and the feedback information, determine the actual delay of the current cycle, and based on the data volume corresponding to the target video packets, determine the data sending rate of the current cycle; wherein, the network transmission parameters include the actual delay and the data sending rate; based on the current wireless signal state, the actual delay and the data sending rate of the current cycle, obtain the estimated delay of the subsequent specified cycle.

[0059] Specifically, please refer to again Figure 3, when the receiving end successfully receives the target video packet in the current cycle, it sends feedback information to the sending end. When receiving the feedback information from the receiving end for the target video packet in the current cycle, it is determined that the receiving end has successfully received the target video packet. Based on the timestamps corresponding to the target video packet and the feedback information, the actual delay of the current cycle is determined. Based on the data volume corresponding to the target video packet, the data sending rate of the current cycle is determined. Among them, the network transmission parameters include the actual delay and the data sending rate. Thus, through the actual delay and data sending rate obtained by measurement, the network state of the current cycle is evaluated to obtain a detailed and accurate network state.

[0060] Furthermore, based on the parameters of multiple dimensions composed of the current wireless signal state, the actual delay and the data sending rate of the current cycle, the delay of the subsequent specified cycle is predicted to obtain the estimated delay of the subsequent specified cycle.

[0061] It should be noted that obtaining the estimated delay of the subsequent specified cycle based on the current wireless signal state, the actual delay and the data sending rate of the current cycle includes: determining the current signal state characteristics based on the current wireless signal state, and determining the network transmission characteristics of the current cycle based on the actual delay and the data sending rate of the current cycle; fusing the signal state characteristics and the network transmission characteristics to obtain the target fusion characteristics, and determining the estimated delay of the subsequent specified cycle based on the target fusion characteristics.

[0062] Specifically, the current wireless signal state is normalized and the current signal state characteristics are extracted. The actual delay and the data sending rate of the current cycle are normalized and the network transmission characteristics of the current cycle are extracted. The signal state characteristics that can reflect the signal quality and the network transmission characteristics of the network transmission quality are fused to obtain the high-precision target fusion characteristics after multi-dimensional fusion. Based on the target fusion characteristics, the delay of the subsequent specified cycle is predicted to determine the estimated delay of the subsequent specified cycle, improving the accuracy of delay prediction.

[0063] S205: In response to not receiving the feedback information from the receiving end for the target video packet in the current cycle, based on the current wireless signal state, obtain the estimated delay of the subsequent specified cycle; where the estimated delay is used to adjust the sending strategy of the video packet in the subsequent specified cycle.

[0064] Specifically, when not receiving the feedback information from the receiving end for the target video packet in the current cycle, obtain the wireless signal state obtained by the sending end in real time, and based on the current wireless signal state, predict the round-trip delay of the subsequent specified cycle to obtain the estimated delay of the subsequent specified cycle.

[0065] In some implementation scenarios, the wireless signal state corresponds to a signal change threshold; in response to not receiving feedback information from the receiving end for the target video packet within the current period, based on the current wireless signal state, the estimated delay for a subsequent specified period is obtained, including: in response to not receiving feedback information from the receiving end for the target video packet within the current period and the change in the wireless signal state exceeding the signal change threshold before the end of the current period, based on the current wireless signal state, the estimated delay for a subsequent specified period is obtained; in response to not receiving feedback information from the receiving end for the target video packet until the end of the current period, based on the current wireless signal state, the estimated delay for a subsequent specified period is obtained.

[0066] Specifically, please refer to Figure 3 again. The video packet sends data to the receiving end through the wireless network transmission control module and the wireless driver module. The wireless driver module obtains the wireless signal state in real time and determines whether the wireless signal state exceeds the signal change threshold. The wireless network transmission control module is used to predict the delay for a subsequent specified period and adjust the sending strategy of the video packet within the subsequent specified period.

[0067] It can be understood that when no feedback information from the receiving end for the target video packet is received within the current period, it is judged whether the change in the current wireless signal state exceeds the signal change threshold. If the change in the wireless signal state exceeds the signal change threshold before the end of the current period, the delay for a subsequent specified period is immediately predicted based on the current wireless signal state, so that when the wireless signal state fluctuates greatly, the delay for a subsequent specified period is timely predicted, and the estimated delay for a subsequent specified period is obtained, improving the timeliness of delay prediction.

[0068] Furthermore, if the change in the wireless signal state does not exceed the signal change threshold before the end of the current period, continue to monitor whether feedback information from the receiving end is obtained and the change in the wireless signal state until no feedback information from the receiving end for the target video packet is received at the end of the current period, then the delay for a subsequent specified period is timely predicted based on the current wireless signal state, and the estimated delay for a subsequent specified period is obtained.

[0069] It should be noted that the wireless signal state includes wireless signal strength, channel utilization rate, wireless packet loss rate, wireless negotiation rate, and wireless received signal-to-noise ratio as signal state parameters. Multiple signal state parameters can affect the amount of data transmitted, and the signal change threshold corresponds to the data volume change threshold.

[0070] Specifically, the wireless signal state includes wireless signal strength, channel utilization rate, wireless packet loss rate, wireless negotiation rate, and wireless received signal-to-noise ratio as signal state parameters, so as to comprehensively reflect the wireless signal state through multiple signal state parameters and improve the accuracy of the wireless signal state.

[0071] It should be noted that multiple signal state parameters can affect the amount of data transmitted. The signal change threshold corresponds to the data volume change threshold, so as to quantify the impact of different signal state parameters on data transmission. When the change of multiple signal state parameters exceeds the data volume change threshold, the delay of the subsequent specified period is predicted in a timely manner, and the accuracy of the time node for predicting the delay of the subsequent specified period is improved.

[0072] In this embodiment, after the receiving end initiates a connection establishment request, the sending end prepares to establish a connection with the receiving end. Since no data is sent in this connection, the current network transmission parameters cannot be obtained. Therefore, the wireless signal state obtained by the sending end in real time is acquired, and based on the current wireless signal state, the delay in the handshake phase is predicted to obtain an initial estimated delay, so as to use the initial estimated delay for handshake phase transmission control to improve the control accuracy. The initial estimated delay is used to attempt to establish a connection with the receiving end in the handshake phase, and it is judged whether the handshake phase times out. If it times out, the initial estimated delay is used for timeout retransmission to establish a connection with the receiving end as soon as possible. When the sending end establishes a connection with the receiving end, the video frames received by the receiving end are acquired, and based on the data volume of the video frames, the video frames are divided into multiple video packets, so as to evenly divide the video frames with different data volumes as much as possible, make the video packet transmission more stable, and facilitate adjusting the transmission strategy according to the estimated delay. When the feedback information for the target video packet is received from the receiving end within the current period, based on the parameters of multiple dimensions composed of the current wireless signal state, the actual delay of the current period, and the data sending rate, the delay of the subsequent specified period is predicted to obtain the estimated delay of the subsequent specified period, and the accuracy of the delay prediction is improved. When the feedback information for the target video packet is not received from the receiving end within the current period, it is judged whether the change of the current wireless signal state exceeds the signal change threshold. If the change of the wireless signal state exceeds the signal change threshold before the end of the current period, the delay of the subsequent specified period is immediately predicted based on the current wireless signal state, so as to predict the delay of the subsequent specified period in a timely manner when the wireless signal state fluctuates greatly, and obtain the estimated delay of the subsequent specified period, and improve the timeliness of the delay prediction.

[0073] Please refer to Figure 4 , Figure 4 FIG. is a schematic structural diagram of an embodiment of an electronic device according to the present application. The electronic device 30 includes a memory 301 and a processor 302 that are coupled to each other. Among them, the memory 301 stores program data (not shown in the figure), and the processor 302 calls the program data to implement the method in any of the above embodiments. For the description of related content, please refer to the detailed description of the method embodiment above, and will not be repeated here.

[0074] Please refer to Figure 5 , Figure 5FIG. 0 is a schematic structural diagram of an embodiment of a computer-readable storage medium of the present application. The computer-readable storage medium 40 stores program data 400, and when the program data 400 is executed by a processor, the method in any of the above embodiments is implemented. For the description of related content, please refer to the detailed description of the above method embodiments, which will not be repeated here.

[0075] It should be noted that the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0076] In addition, in each embodiment of the present application, the functional units may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0077] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0078] The above description is only the embodiments of the present application, and does not limit the protection scope of the present application. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be included in the protection scope of the present application by the same token.

Claims

1. A method for predicting video transmission delay, characterized in that, Applied to the sending end, the sending end obtains the wireless signal state in real time, and the method includes: In response to establishing a connection with the receiving end, obtain the video packets corresponding to the video frames, and send the target video packets of the current period to the receiving end; In response to receiving the feedback information of the receiving end for the target video packet within the current period, based on the target video packet and the feedback information, determine the network transmission parameters of the current period, and based on the current wireless signal state and the network transmission parameters of the current period, obtain the estimated delay of the subsequent specified period; In response to not receiving the feedback information of the receiving end for the target video packet within the current period, based on the current wireless signal state, obtain the estimated delay of the subsequent specified period; wherein, the estimated delay is used to adjust the sending strategy of the video packets within the subsequent specified period; The wireless signal state corresponds to a signal change threshold; The step of obtaining the estimated delay of the subsequent specified period based on the current wireless signal state in response to not receiving the feedback information of the receiving end for the target video packet within the current period includes: If the feedback information of the receiving end for the target video packet is not received within the current period, and the change in the wireless signal state exceeds the signal change threshold before the end of the current period, then obtain the estimated delay of the subsequent specified period based on the current wireless signal state; If the feedback information of the receiving end for the target video packet is not received until the end of the current period, then obtain the estimated delay of the subsequent specified period based on the current wireless signal state.

2. The video transmission delay prediction method according to claim 1, wherein The steps for the sending end to establish a connection with the receiving end include: Based on the current wireless signal state, obtain the initial estimated delay; Use the initial estimated delay to attempt to establish a connection with the receiving end during the handshake phase; wherein, when the handshake phase times out, use the initial estimated delay for timeout retransmission.

3. The video transmission delay prediction method according to claim 1, wherein The step of obtaining the video packets corresponding to the video frames and sending the target video packets of the current period to the receiving end in response to establishing a connection with the receiving end includes: In response to establishing a connection with the receiving end, obtain the video frames received by the receiving end, and divide the video frames into multiple video packets based on the data volume of the video frames; Obtain the target video packets matching the sending strategy of the current period, and send the target video packets of the current period to the receiving end.

4. The video transmission delay prediction method according to claim 1, wherein The step of determining the network transmission parameters of the current period based on the target video packet and the feedback information, and obtaining the estimated delay of the subsequent specified period based on the current wireless signal state and the network transmission parameters of the current period includes: Based on the target video packet and the feedback information, determine the actual delay of the current period, and based on the data volume corresponding to the target video packet, determine the data sending rate of the current period; wherein, the network transmission parameters include the actual delay and the data sending rate; Based on the current wireless signal state, the actual delay and the data sending rate of the current period, obtain the estimated delay of the subsequent specified period.

5. The video transmission delay prediction method according to claim 4, wherein Obtaining the estimated delay for a subsequent specified period based on the current wireless signal state, the actual delay in the current period, and the data transmission rate includes: Determining the current signal state characteristics based on the current wireless signal state, and determining the network transmission characteristics in the current period based on the actual delay and the data transmission rate in the current period; Fusing the signal state characteristics and the network transmission characteristics to obtain target fusion characteristics, and determining the estimated delay for a subsequent specified period based on the target fusion characteristics.

6. The video transmission delay prediction method according to claim 1, wherein The wireless signal state includes wireless signal strength, channel utilization rate, wireless packet loss rate, wireless negotiation rate, and wireless received signal-to-noise ratio as signal state parameters. Multiple such signal state parameters affect the amount of data transmitted, and the signal change threshold corresponds to the data volume change threshold.

7. The video transmission delay prediction method according to any one of claims 1-6, wherein When the feedback information is obtained in the current period, the estimated delay for the subsequent specified period is obtained by using a dual-input prediction model; wherein, the dual-input prediction model is obtained by training with multiple training samples, and the training samples of the dual-input prediction model include the wireless signal state and network transmission parameters in the historical period as training data, and the actual delay in the subsequent specified period of the historical period as a training label; When the feedback information is not obtained in the current period, the estimated delay for the subsequent specified period is obtained by using a single-input prediction model; wherein, the single-input prediction model is obtained by training with multiple training samples, and the training samples of the single-input prediction model include the wireless signal state in the historical period as training data, and the actual delay in the subsequent specified period of the historical period as a training label.

8. An electronic device, characterized in that, Including: A memory and a processor coupled to each other, wherein the memory stores program data, and the processor calls the program data to execute the method according to any one of claims 1-7.

9. A computer-readable storage medium having program data stored thereon, characterized in that, When the program data is executed by the processor, the method according to any one of claims 1-7 is implemented.

Images