Frame-level network packet loss simulation method, device and equipment based on receiving end buffer area duration and bandwidth correction and storage medium

Abstract

The invention discloses a frame-level network packet loss simulation method, device and equipment based on receiving end buffer time length and bandwidth correction and a storage medium, and relates to the technical field of video coding, decoding and transmission, and the method comprises the steps: obtaining the receiving end buffer time length, the network available bandwidth and a video frame split data packet; resolving the basic probability of a video frame corresponding to a data packet which cannot arrive in the split data packets of the video frame based on the time length of the buffer area of the receiving end, and determining the basic probability of a late packet loss frame; correcting the basic probability of the late packet loss frame based on the time length of the buffer area of the receiving end, the available bandwidth of the network and the total data volume of the video frames corresponding to the split data packets of the video frames, and determining the probability of the late packet loss frame after correction; and performing simulation truncation on a data packet in a corresponding target frame based on the late packet loss frame probability to complete frame-level network packet loss simulation based on the duration and bandwidth correction of the buffer area of the receiving end.

Description

Technical Field

[0001] This application relates to the field of video encoding and decoding and transmission technology, and in particular to a frame-level network packet loss simulation method, apparatus, device and storage medium based on receiver buffer duration and bandwidth correction. Background Technology

[0002] In the fields of real-time video communication and streaming media transmission, network packet loss can severely impact user experience and system stability. To evaluate the performance of video codecs, congestion control, and adaptive algorithms under different network environments, it is necessary to accurately simulate packet loss behavior in a controlled experimental environment during the research and development and testing phases to verify the system's fluctuations in real networks.

[0003] Currently, existing methods include using a fixed packet loss rate model to randomly drop data packets at a fixed ratio, or dropping packets based on a time threshold when a packet times out, as well as tail-end dropping and congestion dropping methods that prioritize dropping later-arriving packets when the network is congested. However, these methods are difficult to realistically simulate the incomplete frame phenomenon caused by insufficient receive windows in low-latency scenarios, and they lack packet loss triggering and execution mechanisms at the frame level. This leads to test results being out of touch with real business scenarios and makes it difficult to adapt to the testing and verification needs of different business scenarios. Therefore, how to perform frame-level network packet loss simulation more efficiently and accurately has become an urgent problem to be solved.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, device, and storage medium for simulating frame-level network packet loss based on receiver buffer duration and bandwidth correction, aiming to solve the technical problem of how to perform frame-level network packet loss simulation more efficiently and accurately.

[0006] To achieve the above objectives, this application proposes a frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction. The method includes: Obtain the receiver buffer duration, available network bandwidth, and video frame splitting data packets; Based on the duration of the receiving end buffer, the basic probability of video frames corresponding to the video frames that failed to arrive in the video frame split data packets is calculated to determine the basic probability of late packet loss frames. The base probability of late packet loss frames is corrected based on the receiver buffer duration, the available network bandwidth, and the total data volume of video frames corresponding to the video frame split data packets, and the corrected probability of late packet loss frames is determined. Based on the probability of late packet loss, the data packets in the corresponding target frame are simulated to be truncated, thus completing the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction.

[0007] In one embodiment, the step of calculating the basic probability of video frames corresponding to data packets that failed to arrive in the video frame splitting data packets based on the receiver buffer duration, and determining the basic probability of late-arriving lost frames, includes: Based on the video frame splitting data packets, the video frames corresponding to data packets that failed to arrive within the duration of the receiving end buffer are detected to determine the late packet loss frames; The base probability of a late packet loss frame is calculated based on the duration of the receiver buffer and the late packet loss frame.

[0008] In one embodiment, the step of detecting video frames corresponding to data packets that failed to arrive within the receiver buffer duration based on the video frame splitting data packets, and determining late-arriving lost frames, includes: The timing is started when the first data packet of any video frame corresponding to the video frame split data packet is received, and the start time information is determined. The corresponding end time information is determined based on the start time information and the duration of the receiving buffer. Based on the start time information and the end time information, the video frames corresponding to the data packets that failed to arrive within the duration of the receiving end buffer are detected to obtain late packet loss frames.

[0009] In one embodiment, the step of calculating the base probability of the late packet loss frame based on the receiver buffer duration and the late packet loss frame includes: Obtain network data information; Based on the network data information, a basic packet loss probability model is constructed by establishing the dependency relationship between the corresponding receiver buffer duration and the late packet loss frame. Based on the receiver buffer duration and the input of the late packet loss frame into the basic packet loss probability model, the basic probability of the late packet loss frame is calculated to determine the basic probability of the late packet loss frame.

[0010] In one embodiment, the step of correcting the base probability of late packet loss frames based on the receiver buffer duration, the available network bandwidth, and the total data volume of video frames corresponding to the video frame split data packets, and determining the corrected probability of late packet loss frames includes: The video frame is parsed to split the data packets to obtain the total data volume of the video frame, and the theoretical transmission time is calculated based on the available network bandwidth and the total data volume of the video frame; A corresponding bandwidth correction weight model is constructed based on the ratio between the theoretical transmission duration and the receiver buffer duration. Based on the theoretical transmission duration, the receiver buffer duration, and the available network bandwidth, the bandwidth correction weight model is used to perform a weighted correction on the base probability of the late packet loss frame, thereby obtaining the probability of the late packet loss frame.

[0011] In one embodiment, the step of simulating truncation of data packets in the corresponding target frame based on the probability of late packet loss, and completing the frame-level network packet loss simulation based on receiver buffer duration and bandwidth correction, includes: Get a random seed; Generate a corresponding random number based on the random seed; Based on the random number and the probability of late packet loss, the data packets in the corresponding target frame are simulated to be truncated, thereby completing the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction. The simulated truncation is used to simulate receiver buffer overflow or timeout scenarios and discard data packets with sequence numbers at the end of the target frame.

[0012] In one embodiment, after the step of simulating truncation of data packets in the corresponding target frame based on the probability of late packet loss, and completing the frame-level network packet loss simulation based on receiver buffer duration and bandwidth correction, the method further includes: Obtain simulated information from the sending end; When the probability of late packet loss frames predicted by the transmitter in the simulated information of the transmitter exceeds a predefined threshold, the transmitter coding strategy is determined. The transmitter coding strategy includes at least one of reducing the target bit rate, increasing the quantization parameter, reducing the resolution, or reducing the frame rate. Based on the aforementioned encoding strategy at the sending end, the amount of data or the number of data packets generated for the video frame splitting of subsequent video frames to be simulated are adjusted.

[0013] Furthermore, to achieve the above objectives, this application also proposes a frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction, wherein the frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction includes: The acquisition module is used to acquire the receiver buffer duration, available network bandwidth, and video frame splitting data packets; The processing module is used to calculate the basic probability of video frames corresponding to data packets that failed to arrive in the video frame split data packets based on the duration of the receiving end buffer, and to determine the basic probability of late packet loss frames. The processing module is also used to correct the base probability of the late packet loss frame based on the receiver buffer duration, the available network bandwidth, and the total data volume of the video frames corresponding to the video frame split data packets, and to determine the corrected probability of the late packet loss frame. The execution module is used to simulate truncation of data packets in the corresponding target frame based on the probability of late packet loss, and to complete the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction.

[0014] Furthermore, to achieve the above objectives, this application also proposes a frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction. The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction as described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This embodiment proposes a frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction. The method obtains the receiver buffer duration, available network bandwidth, and video frame split data packets. Based on the receiver buffer duration, it calculates the basic probability of video frames corresponding to data packets that failed to arrive in the video frame split data packets to determine the basic probability of late-arriving packet loss frames. Based on the receiver buffer duration, the available network bandwidth, and the total data volume of the video frames corresponding to the video frame split data packets, the basic probability of late-arriving packet loss frames is corrected to determine the corrected probability of late-arriving packet loss frames. Based on the probability of late-arriving packet loss frames, the data packets in the corresponding target frames are simulated and truncated, thus completing the frame-level network packet loss simulation based on receiver buffer duration and bandwidth correction. This application calculates the basic probability of late-arriving and lost frames using the obtained receiver buffer duration, and performs weighted correction based on the available network bandwidth and video frame data volume. According to the corrected probability, the target frame is truncated and discarded, realizing a refined simulation of frame-level network packet loss. It highly reproduces the frame truncation phenomenon caused by insufficient receiver window and limited bandwidth in low-latency video services, accurately characterizes the combined impact of latency accumulation and bandwidth competition on frame integrity in real networks, and flexibly adapts to the testing requirements of different service scenarios, making the simulation process repeatable, verifiable, and highly realistic in terms of the characteristics of real network packet loss. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction in this application. Figure 2 This diagram illustrates the probability of late packet loss frames under different receiver buffer durations in the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction of this application. Figure 3 This is a flowchart illustrating Embodiment 2 of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction in this application. Figure 4 This is a schematic diagram of the module structure of the frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction according to an embodiment of this application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction in the embodiments of this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of this application embodiment is as follows: Obtain the receiver buffer duration, available network bandwidth, and video frame split data packets; calculate the basic probability of video frames corresponding to data packets that failed to arrive in the video frame split data packets based on the receiver buffer duration, and determine the basic probability of late-arriving packet loss frames; correct the basic probability of late-arriving packet loss frames based on the receiver buffer duration, available network bandwidth, and the total data volume of video frames corresponding to the video frame split data packets, and determine the corrected probability of late-arriving packet loss frames; simulate truncation of data packets in the corresponding target frame based on the probability of late-arriving packet loss frames, thus completing the frame-level network packet loss simulation based on receiver buffer duration and bandwidth correction.

[0024] In this embodiment, for ease of description, the following description will focus on identifying a frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction.

[0025] Because existing technologies cannot realistically simulate the incomplete frame phenomenon caused by insufficient receiving window in low-latency scenarios, and lack a packet loss triggering and execution mechanism at the frame level, the test results are out of touch with real business scenarios, making it difficult to adapt to the testing and verification needs of different business scenarios.

[0026] This application provides a solution that obtains the receiver buffer duration, available network bandwidth, and video frame split data packets; calculates the basic probability of video frames corresponding to data packets that failed to arrive in the video frame split data packets based on the receiver buffer duration, and determines the basic probability of late packet loss frames; corrects the basic probability of late packet loss frames based on the receiver buffer duration, available network bandwidth, and the total data volume of video frames corresponding to the video frame split data packets, and determines the corrected probability of late packet loss frames; and simulates truncation of data packets in the corresponding target frame based on the probability of late packet loss frames, thus completing frame-level network packet loss simulation based on receiver buffer duration and bandwidth correction.

[0027] As can be seen from the above embodiments, this application calculates the basic probability of late-arriving and packet-lost frames by obtaining the receiver buffer duration, and performs weighted correction by combining the available network bandwidth and the amount of video frame data. Based on the corrected probability, the target frame is truncated and discarded, thereby realizing a refined simulation of frame-level network packet loss. It highly restores the frame truncation phenomenon caused by insufficient receiving window and limited bandwidth in low-latency video services, accurately characterizes the comprehensive impact of latency accumulation and bandwidth competition on frame integrity in real networks, and flexibly adapts to the testing requirements of different service scenarios, making the simulation process repeatable, verifiable, and highly realistic in terms of the characteristics of real network packet loss.

[0028] Based on this, embodiments of this application provide a frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction in this application.

[0029] In this embodiment, the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction includes steps S10~S40: Step S10: Obtain the receiver buffer duration, available network bandwidth, and video frame split data packets; It should be noted that the receiving buffer duration refers to the maximum dwell time parameter preset in the receiving buffer to smooth network jitter. It represents the maximum time window in which data packets are allowed to stay in the receiving buffer before playback or decoding. The available network bandwidth is the bandwidth resource that can actually be used for data transmission under the current network conditions. It is used to represent the instantaneous transmission capability of the network. The video frame split data packet is a set of multiple data packets formed by dividing the encoded single video frame according to the network's maximum transmission unit (MTU) size.

[0030] It is understood that the duration of the receiving buffer can be configured according to the specific service type. For example, highly interactive VR services require less than 20 milliseconds, general video conferencing requires about 250 milliseconds, while weakly interactive live streaming services can be set to the second level. During the simulation, the timer starts from the first arriving data packet of a certain frame. If all the split data packets of the frame fail to arrive within this time, the subsequent arriving data packets will be considered lost, thereby triggering frame-level packet loss judgment. The available network bandwidth can be used to calculate the theoretical transmission time of the frame. By comparing it with the duration of the receiving buffer, it is determined whether the frame reception timeout is caused by insufficient bandwidth or excessive data volume, thereby dynamically correcting the packet loss probability. The video frame split data packet is to split the encoded complete video frame. When splitting, it is necessary to ensure that each data packet does not exceed the MTU limit and to adopt a uniform or non-uniform packet splitting strategy to facilitate network transmission and error recovery. It is divided into several smaller data packets suitable for independent network transmission. Each split data packet is accompanied by frame identification information and sequence number to ensure that the receiving end can correctly identify the frame to which it belongs and reassemble it in sequence.

[0031] In a specific embodiment, the receiver buffer duration is obtained by setting the receiver buffer duration T at the receiver end, with the unit being milliseconds. It represents the specific real-time requirements of the service, i.e., the maximum end-to-end latency that the service can tolerate. For example, in highly interactive VR / AR applications, T is required to be less than 20 milliseconds to ensure an immersive experience. In general interactive video conferencing scenarios, T can be set to around 250 milliseconds to balance real-time performance and smoothness. In weakly interactive live streaming or video-on-demand services, T can be relaxed to the second level. The available network bandwidth is obtained in real time through a bandwidth estimation algorithm deployed at the sender end or network path. The video frame splitting data packets originates from the output of the video encoder. The encoded video frames are split into packets according to the principle of not exceeding the network MTU size. Each video frame is split into multiple data packets, and each data packet is appended with frame identification information and a sequence number to ensure that the receiver end can correctly identify and reassemble them. The packet splitting process considers network transmission efficiency and error recovery capability. A uniform packet splitting strategy can be adopted to ensure that the size of each data packet is relatively balanced. Alternatively, a simple non-uniform packet splitting strategy can be used, where the amount of data in the first packet is set to a constant value, and the remaining data is allocated to the last packet.

[0032] Step S20: Based on the duration of the receiving end buffer, calculate the basic probability of video frames corresponding to data packets that failed to arrive in the video frame split data packets, and determine the basic probability of late packet loss frames. It should be noted that the base probability of a late-arriving lost frame is an initial probability that a frame is considered incomplete because the data packet fails to arrive completely within the receiver's buffer time.

[0033] It is understandable that the basic probability of a video frame is the potential frame-level packet loss risk caused solely by the strict real-time requirements of the business, under idealized conditions that do not consider specific network bandwidth and frame size. This probability can be obtained by analyzing the functional relationship fitted from real network data. Its value is negatively correlated with the receiver buffer duration. That is, the shorter the receiver buffer duration and the higher the real-time requirement, the greater the basic packet loss probability.

[0034] In a specific embodiment, based on the video frame splitting data packets, the video frames corresponding to data packets that failed to arrive within the receiving end buffer duration are detected to determine late-arriving lost frames. That is, a timing mechanism is started from the first arriving data packet of a certain frame. When the timer reaches the receiving end buffer duration T, the receiving channel of that frame is immediately closed. At this time, subsequent arriving data packets are considered lost and no longer received. This frame is recorded as a late-arriving lost frame, i.e., a frame with late packets. For example, when the first split data packet belonging to any video frame is received, its frame identifier is parsed and a timer for that frame is immediately started. At the same time, the cutoff time for receiving the data packet of that frame is calculated according to the preset receiving end buffer duration T. Within the time window from the start time to the cutoff time, all arriving data packets with the same frame identifier and their sequence numbers are monitored and recorded in real time. When the cutoff time is reached, the set of received data packet sequence numbers is compared with the expected total set of packets for that frame known from the frame splitting information. If any expected sequence number is missing, the frame is determined to be a late-arriving lost frame, and its frame identifier and missing packet information are recorded.

[0035] Based on the receiver buffer duration and the late packet loss frame, the base probability of the corresponding late packet loss frame is calculated. That is, by capturing a large amount of real network data, such as measured data with a total duration of 16,938 seconds and a total data volume of 9.21GB, the relationship between the receiver buffer duration T and the late packet loss frame can be analyzed, and the relationship between the receiver buffer duration T and the probability of late packet loss frame occurrence can be established. The quantitative relationship between them shows a relatively regular power-law relationship, such as... Figure 2 As shown, Figure 2 This diagram illustrates the probability of late-arriving packet loss frames under different receiver buffer durations in the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction proposed in this application. The basic probability of late-arriving packet loss frames can be calculated by setting the receiver buffer duration. ,function Presentation The negative correlation with T indicates that the shorter the receiver buffer duration, the higher the basic packet loss probability, reflecting the monotonic relationship between real-time requirements and packet loss probability. Simultaneously, when the receiver buffer duration is sufficient, time-constrained packet loss is extremely unlikely. An example of the function is , here as well as The constant determined through data fitting indicates that the shorter the preset receiver buffer duration T, the higher the real-time requirement, and the higher the corresponding base packet loss probability. The larger the buffer size, the lower the probability of packet loss. Conversely, when the receiver buffer duration is set sufficiently, the probability of packet loss due to timeout alone will approach zero.

[0036] Step S30: Based on the receiver buffer duration, the available network bandwidth, and the total data volume of the video frames corresponding to the video frame split data packets, the base probability of the late packet loss frame is corrected to determine the corrected probability of the late packet loss frame. It should be noted that the probability of late packet loss is a frame-level packet loss probability that is closer to real network conditions, obtained by weighting and correcting the probability of late packet loss by combining the available bandwidth of the current network and the total amount of data of the frames to be transmitted, based on the basic probability of late packet loss.

[0037] In a specific embodiment, the video frame is parsed to split data packets to obtain the total data volume of the video frame. The theoretical transmission time is calculated based on the available network bandwidth and the total data volume of the video frame. That is, the theoretical transmission time T_trans = L / B is estimated by combining the available network bandwidth B and the total data volume L of the frame. A corresponding bandwidth correction weight model is constructed based on the ratio between the theoretical transmission time and the receiver buffer time. The bandwidth correction weight model is then used to weight and correct the base probability of the late packet loss frame based on the theoretical transmission time, the receiver buffer time, and the available network bandwidth to obtain the probability of the late packet loss frame. That is, when T_trans > T, it indicates that even without network contention, the frame may not be received completely within the receiver buffer time, and the packet loss probability needs to be increased.

[0038] At this point, bandwidth correction can be performed. Bandwidth correction refers to a weighted correction operation on the basic packet loss probability based on the available network bandwidth, to characterize the actual impact of the current network transmission capacity on the frame-level packet loss probability. The actual packet loss probability is calculated using a weighted correction method. , is represented as:

[0039] function Presentation It is negatively correlated with the available bandwidth B of the current network, meaning that the larger the available bandwidth, the smaller the packet loss due to bandwidth limitations. It is positively correlated with the current frame data size L, meaning that the larger the current frame data size, the higher the probability of packet loss under limited bandwidth. They are positively correlated.

[0040] Therefore, this can be achieved by constructing a bandwidth-corrected weight model, for example, by using the following implementable correction function. For example, let the base probability of packet loss due to lateness be... The available network bandwidth is The total data size of the video frames is The receiver buffer duration is First, calculate the theoretical transmission time. At this point, the bandwidth correction weight model can be expressed as:

[0041] in, The corrected probability of delayed packet loss is given by α∈[0,1], where α is the weighting coefficient, which can be configured according to the specific test scenario. This corrected model maintains 0≤ The constraint is ≤1, while As a constraint function, when the calculated value is less than 0.0, it is output as 0.0; when the calculated value is greater than 1.0, it is output as 1.0. This ensures the validity of the calculation results. This model reflects insufficient bandwidth, i.e. When this occurs, it has a positive corrective effect on the probability of packet loss.

[0042] For example, in a practical application, assuming the frame size L is approximately 200KB and the available bandwidth B = 4Mbps, the theoretical transmission time T_trans = L / B = 200 * 8 / (4 * 1024) = 0.3906s, approximately 391ms. If the receiver buffer time T = 40ms, then T is much smaller than T_trans, indicating a significantly insufficient receive window. In this case, delayed packet loss is highly likely. , The example formula calculates... , That is, according to the formula Calculate the baseline probability of delayed packet loss. =0.51%, set α=0.8, according to the formula Calculate the probability of late-arriving lost frames after correction. =72.33%, meaning that under the current network conditions, there is a 72.33% probability of packet loss or delay when transmitting this amount of data.

[0043] In one feasible implementation, step S30 may include steps A11 to A13: Step A11: Parse the video frame to split the data packets to obtain the total data volume of the video frame, and calculate the theoretical transmission time based on the available network bandwidth and the total data volume of the video frame; It should be noted that the theoretical transmission time is the estimated time required to fully transmit a video frame under ideal conditions assuming exclusive network path, no contention, and stable bandwidth. It is used to quantify the degree of matching between network transmission capacity and data load. By comparing the theoretical transmission time T_trans with the actual service-allowed receiver buffer time T, it is possible to intuitively determine whether the current network bandwidth constitutes a bottleneck. If T_trans>T, it indicates that even under ideal conditions without other interference, the frame cannot be fully transmitted within the time limit, thus significantly increasing the risk of packet loss due to insufficient reception.

[0044] It is understood that the total data volume of the video frame is the total size of the complete data payload to be transmitted over the network after a single video frame is encoded and compressed. From the video frame that has been split into multiple network data packets, the effective payload size of all data packets is parsed and accumulated to obtain the total data volume of the video frame, which is measured in bytes or bits and represents the content complexity of the frame and the bit rate usage after encoding.

[0045] Step A12: Construct a corresponding bandwidth correction weight model based on the ratio between the theoretical transmission duration and the receiver buffer duration; It should be noted that the bandwidth correction weight model is a mathematical function that combines network transmission capacity with service time limit requirements to dynamically adjust the frame-level packet loss probability. By calculating the ratio between the theoretical transmission time of a video frame and the service's receiving buffer time, it can quantify whether the bandwidth is sufficient to transmit the frame within the time limit. When the bandwidth is sufficient, the correction term has a small impact or is even negative. When the bandwidth is insufficient, the basic packet loss probability is significantly positively corrected, thereby obtaining a final packet loss probability that is closer to the real network competition situation, ensuring that the probability of late packet loss frames is limited to an effective range.

[0046] Step A13: Based on the theoretical transmission duration, the receiver buffer duration, and the available network bandwidth, the bandwidth correction weight model is used to perform a weighted correction on the base probability of the late packet loss frame to obtain the probability of the late packet loss frame.

[0047] Understandably, the probability of late packet loss can characterize the impact of the dynamic competition between network transmission capacity and data load on frame integrity under specific service time constraints. By calculating the theoretical transmission duration T_trans = L / B and comparing it with the receiver buffer duration T, the additional packet loss risk caused by insufficient bandwidth can be quantified. Then, by using a predefined correction function for weighted adjustment, the actual packet loss probability between 0 and 1 can be obtained. This correction probability is used to make the packet loss simulation reflect the real-time requirements of the service and accurately characterize the real situation where the packet loss probability increases significantly when network resources are strained.

[0048] Step S40: Based on the probability of late packet loss, simulate truncation of data packets in the corresponding target frame to complete frame-level network packet loss simulation based on receiver buffer duration and bandwidth correction.

[0049] It is understandable that simulated truncation is an operation that actively and controllably discards data packets during network packet loss simulation. After being triggered by a random decision mechanism, a portion of the data packets in the sequence of packets that have arrived or are yet to be processed in the frame are selectively discarded, rather than being passively lost in a real network, thus artificially creating the effect that the frame is not received completely.

[0050] In a specific embodiment, a random seed is obtained; a corresponding random number is generated based on the random seed; and data packets in the corresponding target frame are simulated to be truncated based on the random number and the probability of late packet loss, thus completing the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction. The simulated truncation is used to simulate receiver buffer overflow or timeout scenarios, discarding data packets with sequence numbers at the end of the target frame. That is, after receiving the first arriving data packet of the target frame, a random number generator is initialized using a preset fixed random seed, and a random number X uniformly distributed in the interval [0,1) is generated. This random number X is then combined with the probability of late packet loss calculated for that frame. Compare, if X < If the frame is not received completely, it is determined that the frame will be incomplete, thus triggering a frame-level packet loss operation. This random determination mechanism ensures the long-term statistical frequency and probability of packet loss events. Consistency and the use of a fixed seed ensure the repeatability of the simulation process. Once packet loss is triggered, the tail-first discard strategy is executed. In the data packet sequence corresponding to the frame, data packets with larger sequence numbers are discarded first, according to the order of sequence numbers from largest to smallest. This simulates the typical frame truncation characteristics caused by the accumulation of delay in a real low-latency network environment, thereby completing the frame-level network packet loss simulation based on the correction of the receiver buffer duration and bandwidth.

[0051] The process involves: acquiring the sender's simulation information; determining a sender's encoding strategy when the predicted probability of a late-arriving lost frame exceeds a predefined threshold, including at least one of reducing the target bitrate, increasing the quantization parameter, reducing the resolution, or reducing the frame rate; adjusting the data volume or number of data packets generated for subsequent video frames to be simulated based on the encoding strategy, i.e., obtaining the preset receiver buffer duration T by parsing the RTCP messages or application layer signaling fed back by the receiver, monitoring the current available network bandwidth B using a real-time bandwidth estimation algorithm, and obtaining the total data volume L of the current frame from the encoder; and substituting T, B, and L into the packet loss probability calculation formula consistent with the receiver's simulation model to calculate the predicted probability that the frame will become an incomplete frame at the receiver. ,when When the preset decision threshold θ (θ∈[0,1]) is exceeded, an adaptive coding strategy adjustment is immediately triggered. Based on the preset rule base and the real-time system status, one or more adjustment measures are automatically selected and executed, and tried in priority order. For example, it is given priority to try to reduce the amount of data per frame by increasing the quantization parameter QP while keeping the resolution and frame rate unchanged. If further control is still needed, the target bit rate is reduced simultaneously. If the network condition continues to be severe, the output resolution or the coding frame rate can be further reduced to reduce the amount of data in subsequent frames or change their data generation structure directly from the source of coding, thereby reducing their theoretical transmission time. This proactively avoids the risk of high packet loss, enabling the sender to predict and proactively avoid the risk of high packet loss before actual transmission, thus forming a verifiable adaptive control closed loop for the sender in the packet loss simulation test.

[0052] In one feasible implementation, step S40 may include steps B11-B13: Step B11, obtain a random seed; It should be noted that the random seed is the initial value or parameter used to initialize the pseudo-random number generator.

[0053] Understandably, setting a fixed random seed during packet loss simulation ensures that the random number sequence generated by the pseudo-random number generator is exactly the same and predictable in each simulation run. That is, under the same network parameters and probability model, using the same random seed can reproduce the same packet loss judgment sequence and packet loss events, thus making the entire frame-level network packet loss simulation process a stable and reliable testing tool, which is convenient for performance evaluation and comparative analysis.

[0054] Step B12: Generate a corresponding random number based on the random seed; It should be noted that the random number is a value generated by a pseudo-random number generator that follows a uniform distribution within a specified interval.

[0055] Understandably, during frame-level packet loss simulation, the system generates a random number for each target frame and compares it with the probability of late packet loss frames for that frame. This ensures that in a large number of repeated simulations, the statistical frequency of packet loss events can accurately match the theoretical probability value, thereby transforming the probability model into an executable specific packet loss operation.

[0056] Step B13: Based on the random number and the probability of late packet loss, simulate truncation of the data packets in the corresponding target frame to complete the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction. The simulated truncation is used to simulate receiver buffer overflow or timeout scenarios and discard data packets with sequence numbers at the end of the target frame.

[0057] Understandably, in order to more realistically simulate the common phenomenon that late-arriving data packets are more likely to be lost due to accumulated network latency, this operation follows a tail-first discard strategy. That is, it simulates the packet loss behavior triggered by insufficient buffer space or waiting timeout at the receiving end in a real network environment. When the system determines that the probability of late packet loss of the current frame is valid, it will simulate the scenario that the receiving end buffer is full or the receiving time window is closed. According to the tail-first discard strategy, it will actively discard data packets with larger sequence numbers in the frame, restore the phenomenon that the arrival order of data packets is disordered and late-arriving packets are more likely to be lost due to accumulated network latency, congestion or sudden jitter in actual transmission. This will more realistically reproduce the scenario in low-latency video services where incomplete frames or decoding failures are caused by the late arrival of some data packets.

[0058] In another feasible implementation, steps C11-C13 may be included after step S40: Step C11: Obtain simulated information from the sending end; It should be noted that the simulated information at the sending end is the set of parameters that the sending end needs to obtain in the network packet loss simulation test environment in order to predict the risk of packet loss at the receiving end for the current or subsequent video frames and make adaptive encoding decisions, thereby assessing the risk and triggering the encoding strategy adjustment, so that the entire simulation test can form a verifiable evaluation closed loop including the feedforward control link at the sending end.

[0059] Step C12: When the probability of late packet loss frames predicted by the transmitter in the simulated information of the transmitter exceeds a predefined threshold, the transmitter coding strategy is determined. The transmitter coding strategy includes at least one of reducing the target bit rate, increasing the quantization parameter, reducing the resolution, or reducing the frame rate. It should be noted that the aforementioned sending-end encoding strategy is a set of control instructions that reduce the amount of video frame data or adjust the encoding structure in order to proactively avoid risks when the sending end predicts that the current or subsequent video frames have a high risk of packet loss at the receiving end.

[0060] Understandably, reducing the target bitrate directly constrains the upper limit of the encoder's output bitrate, which is the most direct way to control the amount of data. Increasing the quantization parameter increases the quantization step size during the compression process, sacrificing some image details in the encoding stage to significantly reduce the data size of each frame. Reducing the resolution reduces the amount of raw information in each frame by reducing the total number of image pixels. Reducing the frame rate reduces the overall data throughput requirements by reducing the number of frames per unit time. These strategies can be enabled individually or in combination depending on network conditions and system policies. By adjusting the encoding parameters, the data volume or transmission load of the video stream can be reduced from the source, thereby reducing the risk of frame-level packet loss caused by insufficient network bandwidth or reception window time limits.

[0061] Step C13: Based on the sending end encoding strategy, adjust the data volume or number of data packets generated for the video frame splitting of subsequent video frames to be simulated.

[0062] Understandably, when the sending end takes measures such as reducing the target bit rate and increasing the quantization parameters, the amount of data in a single video frame output by the encoder will change, or the number of frames generated per unit time will decrease due to the reduced frame rate. Therefore, the system needs to recalculate or generate the split data packets of subsequent video frames to be transmitted based on these new encoding parameters. That is, the size of each packet and the total number of data packets into which the frame is split are determined based on the updated data amount of each frame. This ensures that the packet loss simulation environment can realistically represent the actual impact of the sending end's adaptive strategy on the network load and transmission process, thereby forming a complete test closed loop from prediction and decision-making to effect simulation.

[0063] This embodiment proposes a frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction. The method obtains the receiver buffer duration, available network bandwidth, and video frame split data packets. Based on the receiver buffer duration, it calculates the basic probability of video frames corresponding to data packets that failed to arrive in the video frame split data packets to determine the basic probability of late-arriving packet loss frames. Based on the receiver buffer duration, the available network bandwidth, and the total data volume of the video frames corresponding to the video frame split data packets, the basic probability of late-arriving packet loss frames is corrected to determine the corrected probability of late-arriving packet loss frames. Based on the probability of late-arriving packet loss frames, the data packets in the corresponding target frames are simulated and truncated, thus completing the frame-level network packet loss simulation based on receiver buffer duration and bandwidth correction. This invention addresses the technical challenge of performing frame-level network packet loss simulation more efficiently and accurately. Compared to existing technologies, this application calculates the basic probability of late-arriving lost frames using the obtained receiver buffer duration, performs weighted correction based on available network bandwidth and video frame data volume, and then truncates and discards data packets from the target frame according to the corrected probability. This achieves refined simulation of frame-level network packet loss, highly reproducing the frame truncation phenomenon caused by insufficient receiver window and limited bandwidth in low-latency video services. It accurately characterizes the combined impact of latency accumulation and bandwidth competition on frame integrity in real networks, and flexibly adapts to the testing requirements of different service scenarios, making the simulation process repeatable, verifiable, and highly realistic in terms of the characteristics of real network packet loss.

[0064] Based on the first embodiment of this application, in the second embodiment of this application, the same or similar content as the first embodiment can be referred to the above description, and will not be repeated hereafter.

[0065] In this embodiment, refer to Figure 3 , Figure 3This is a flowchart illustrating Embodiment 2 of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction in this application. Step S20 specifically includes steps S21 to S22: Step S21: Based on the video frame split data packet, detect the video frames corresponding to data packets that failed to arrive within the duration of the receiving end buffer to determine the late packet loss frames. It should be noted that the late packet loss frame is a video frame that is determined to be received incompletely, indicating that the frame is at risk of being discarded because it does not meet the real-time requirements of the service.

[0066] In a specific embodiment, timing begins when the first arriving data packet of any video frame corresponding to the video frame split data packet is received, and start time information is determined. Based on the start time information and the receiver buffer duration, corresponding end time information is determined. Based on the start time information and end time information, video frames corresponding to data packets for which the video frame split data packets failed to arrive within the receiver buffer duration are detected to obtain late-arriving lost frames. That is, the system starts timing from the moment the first arriving data packet of a certain video frame is received, and immediately closes the receiving channel for that frame when the receiver buffer duration T is reached. Thereafter... Any data packets arriving belonging to this frame are considered lost and no longer processed. This frame is then recorded as a late-arriving lost frame, meaning a frame with late packets. When the first fragmented data packet of any video frame is received, its frame identifier is parsed and a dedicated timer is started for this frame. At the same time, the reception deadline for this frame is calculated based on the preset T. Within this time window, the system continuously monitors and records all arriving data packets with the same frame identifier and their sequence numbers. When the deadline is reached, a callback function is triggered to compare the set of sequence numbers of the arrived data packets with the expected total set of packets for this frame. If any expected sequence number is missing, the frame is determined to be a late-arriving lost frame.

[0067] In one feasible implementation, step S21 may include steps D11 to D13: Step D11: Start timing when the first data packet of any video frame corresponding to the video frame split data packet is received, and determine the start time information; It should be noted that the start time information is the precise moment recorded when the receiving end successfully receives the first split data packet of the video frame.

[0068] It is understood that the start time information can be used as the unique time reference for receiving and integrity detection of the frame, and can be obtained and stored in the form of a system timestamp and bound to the unique identifier of the frame.

[0069] Step D12: Determine the corresponding end time information based on the start time information and the receiver buffer duration; It should be noted that the aforementioned end time information is the final deadline by which all split data packets of this frame must arrive completely.

[0070] Understandably, once the system time reaches this final moment, the receive channel will close the frame and immediately initiate an integrity check.

[0071] Step D13: Based on the start time information and the end time information, detect the video frames corresponding to the data packets that failed to arrive within the duration of the receiving end buffer, and obtain the late packet loss frames.

[0072] It is understood that the late packet loss frame is counted from the arrival time of the first arriving data packet of the frame. If all the split data packets of the frame fail to arrive within the preset receiver buffer time, the receiving channel of the frame is immediately closed and the frame is marked as a late packet loss frame.

[0073] Step S22: Calculate the base probability of the late packet loss frame based on the duration of the receiving end buffer and the late packet loss frame.

[0074] Understandably, by analyzing large-scale real network transmission data and statistically analyzing the proportion of frames actually marked as late and lost to the total number of frames under different receiver buffer duration settings, an empirical dataset is established between receiver buffer duration and the probability of late packet loss. This dataset is then modeled as a deterministic mathematical function, exhibiting a power-law-like negative correlation.

[0075] In a specific embodiment, network data information is acquired; based on the network data information, a corresponding basic packet loss probability model is constructed by establishing the dependency relationship between the corresponding receiver buffer duration and late packet loss frames; based on the receiver buffer duration and the late packet loss frames, the basic probability of late packet loss frames is calculated using the basic packet loss probability model to determine the basic probability of late packet loss frames. That is, by capturing and analyzing a large amount of real network transmission data, such as a measured video stream with a total duration of 16,938 seconds and a total data volume of 9.21GB, a relationship between the receiver buffer duration T and the probability of late packet loss frames can be established. The quantitative relationship model between the two shows a relatively regular power-law negative correlation, which can be fitted as a function. ,function Presentation The negative correlation with T indicates that the shorter the receiver buffer duration, the higher the basic packet loss probability, reflecting the monotonic relationship between real-time requirements and packet loss probability. Simultaneously, when the receiver buffer duration is sufficient, time-constrained packet loss is extremely unlikely. An example of the function is , here as well as The constant determined through data fitting indicates that the shorter the preset receiver buffer duration T, the higher the real-time requirement, and the higher the corresponding base packet loss probability. The larger the buffer size, the lower the probability of packet loss. Conversely, when the receiver buffer duration is set sufficiently, the probability of packet loss due to timeout alone will approach zero.

[0076] In one feasible implementation, step S22 may include steps E11 to E13: Step E11: Obtain network data information; It should be noted that the network data information mentioned comes from a massive collection of transmission logs and statistical data from a real network environment.

[0077] It is understood that the network data information may include parameters recorded in a large number of video streaming sessions, such as the receiver buffer duration set for each session, the reception integrity status of video frames within that duration, and the corresponding network condition background data. By cleaning, aligning, and statistically analyzing this long-lasting and massive amount of raw information, the statistical regularity between the receiver buffer duration and the frequency of late packet loss can be extracted.

[0078] Step E12: Based on the network data information, construct the corresponding basic packet loss probability model by establishing the dependency relationship between the corresponding receiver buffer duration and the late packet loss frame. It should be noted that the basic packet loss probability model is a mathematical function established by analyzing historical real network data to quantitatively describe the statistical relationship between the receiver buffer duration and the basic probability of late packet loss frames.

[0079] It is understandable that the basic packet loss probability model can be obtained by fitting large-scale measured data. Once the real-time requirements of the service are known, the baseline probability of incomplete frames due to insufficient reception time window can be directly calculated without relying on the real-time network status.

[0080] Step E13: Calculate the basic probability of the late packet loss frame based on the receiver buffer duration and the input of the late packet loss frame into the basic packet loss probability model, and determine the basic probability of the late packet loss frame.

[0081] Understandably, in practical applications, when the receiver buffer duration is preset for a specific business scenario and a late packet loss frame is detected, there is no need to rely on real-time statistics again. The receiver buffer duration can be directly substituted into the fitted function to calculate the basic probability of late packet loss frames occurring in that scenario, representing the baseline value of frame incompleteness risk caused solely by time constraints.

[0082] This embodiment proposes a frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction. It detects video frames corresponding to data packets that fail to arrive within the receiver buffer duration by splitting video frame data packets, thus identifying late-arriving lost frames. The method calculates the base probability of the corresponding late-arriving lost frames based on the receiver buffer duration and the late-arriving lost frames. This solves the technical problem of how to perform frame-level network packet loss simulation more efficiently and accurately. Compared to existing technologies, this application monitors the arrival status of video frame split data packets in real time and accurately identifies late-arriving lost frames that fail to arrive completely within a specified time based on a preset receiver buffer duration. This allows for the calculation of the base probability of late-arriving lost frames, representing the packet loss risk under pure time constraints. This achieves a quantitative mapping from real-time business requirements to packet loss probability, making the simulation process closer to the frame truncation phenomenon caused by insufficient time windows in real low-latency scenarios. This improves the predictability and repeatability of packet loss behavior and enhances the realism of network packet loss simulation.

[0083] This application also provides a frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction. Please refer to... Figure 4 The frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction includes: The acquisition module 10 is used to acquire the receiver buffer duration, available network bandwidth, and video frame splitting data packets; Processing module 20 is used to calculate the basic probability of video frames corresponding to data packets that failed to arrive in the video frame split data packets based on the duration of the receiving end buffer, and to determine the basic probability of late packet loss frames. The processing module 20 is further configured to correct the base probability of the late packet loss frame based on the receiver buffer duration, the available network bandwidth, and the total data volume of the video frames corresponding to the video frame split data packets, and determine the corrected probability of the late packet loss frame. The execution module 30 is used to simulate truncation of data packets in the corresponding target frame based on the probability of late packet loss, and to complete the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction.

[0084] The processing module 20 is further configured to detect the video frames corresponding to data packets that failed to arrive within the duration of the receiving end buffer based on the video frame splitting data packets, and determine the late packet loss frames. The base probability of a late packet loss frame is calculated based on the duration of the receiver buffer and the late packet loss frame.

[0085] The processing module 20 is further configured to start timing when the first arriving data packet of any video frame corresponding to the video frame split data packet is received, and to determine the start time information; The corresponding end time information is determined based on the start time information and the duration of the receiving buffer. Based on the start time information and the end time information, the video frames corresponding to the data packets that failed to arrive within the duration of the receiving end buffer are detected to obtain late packet loss frames.

[0086] The processing module 20 is also used to acquire network data information; Based on the network data information, a basic packet loss probability model is constructed by establishing the dependency relationship between the corresponding receiver buffer duration and the late packet loss frame. Based on the receiver buffer duration and the input of the late packet loss frame into the basic packet loss probability model, the basic probability of the late packet loss frame is calculated to determine the basic probability of the late packet loss frame.

[0087] The processing module 20 is also used to parse the video frame split data packets to obtain the total data volume of the video frame, and calculate the theoretical transmission time based on the available network bandwidth and the total data volume of the video frame; A corresponding bandwidth correction weight model is constructed based on the ratio between the theoretical transmission duration and the receiver buffer duration. Based on the theoretical transmission duration, the receiver buffer duration, and the available network bandwidth, the bandwidth correction weight model is used to perform a weighted correction on the base probability of the late packet loss frame, thereby obtaining the probability of the late packet loss frame.

[0088] The execution module 30 is also used to obtain a random seed; Generate a corresponding random number based on the random seed; Based on the random number and the probability of late packet loss, the data packets in the corresponding target frame are simulated to be truncated, thereby completing the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction. The simulated truncation is used to simulate receiver buffer overflow or timeout scenarios and discard data packets with sequence numbers at the end of the target frame.

[0089] The execution module 30 is also used to acquire simulated information from the sending end; When the probability of late packet loss frames predicted by the transmitter in the simulated information of the transmitter exceeds a predefined threshold, the transmitter coding strategy is determined. The transmitter coding strategy includes at least one of reducing the target bit rate, increasing the quantization parameter, reducing the resolution, or reducing the frame rate. Based on the aforementioned encoding strategy at the sending end, the amount of data or the number of data packets generated for the video frame splitting of subsequent video frames to be simulated are adjusted.

[0090] The frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction provided in this application adopts the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction in the above embodiments, and can solve the technical problem of how to perform frame-level network packet loss simulation more efficiently and accurately. Compared with the prior art, the beneficial effects of the frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction provided in this application are the same as the beneficial effects of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction provided in the above embodiments, and other technical features in the frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0091] This application provides a frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction. The frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction in the above embodiment 1.

[0092] The following is for reference. Figure 5 This document illustrates a structural diagram of a frame-level network packet loss simulation device suitable for implementing the embodiments of this application based on receiver buffer duration and bandwidth correction. The frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction in the embodiments of this application can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The frame-level network packet loss simulation device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0093] like Figure 5As shown, a frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction to exchange data with other devices wirelessly or via wired communication. Although the figure shows a frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0094] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0095] The frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction provided in this application, employing the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction in the above embodiments, can solve the technical problem of how to perform frame-level network packet loss simulation more efficiently and accurately. Compared with the prior art, the beneficial effects of the frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction provided in this application are the same as the beneficial effects of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction provided in the above embodiments, and other technical features in this frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0096] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0097] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0098] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction in the above embodiments.

[0099] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, 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 devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0100] The aforementioned computer-readable storage medium may be included in a frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction; or it may exist independently and not be assembled into a frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction.

[0101] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by a frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction, the device performs the following: acquires the receiver buffer duration, available network bandwidth, and video frame split data packets; calculates the basic probability of video frames corresponding to data packets that failed to arrive in the video frame split data packets based on the receiver buffer duration, and determines the basic probability of late-arriving packet loss frames; corrects the basic probability of late-arriving packet loss frames based on the receiver buffer duration, the available network bandwidth, and the total data volume of video frames corresponding to the video frame split data packets, and determines the corrected probability of late-arriving packet loss frames; and simulates truncation of data packets in the corresponding target frame based on the probability of late-arriving packet loss frames, thus completing the frame-level network packet loss simulation based on receiver buffer duration and bandwidth correction.

[0102] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0103] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0104] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0105] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction. This solves the technical problem of how to perform frame-level network packet loss simulation more efficiently and accurately. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction provided in the above embodiments, and will not be repeated here.

[0106] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction, characterized in that, The method includes: Obtain the receiver buffer duration, available network bandwidth, and video frame splitting data packets; Based on the duration of the receiving end buffer, the basic probability of video frames corresponding to the video frames that failed to arrive in the video frame split data packets is calculated to determine the basic probability of late packet loss frames. The base probability of the late packet loss frame is corrected based on the receiver buffer duration, the available network bandwidth, and the total data volume of the video frames corresponding to the video frame split data packets, and the corrected probability of the late packet loss frame is determined. Based on the probability of late packet loss, the data packets in the corresponding target frame are simulated to be truncated, thus completing the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction.

2. The method as described in claim 1, characterized in that, The step of calculating the basic probability of video frames corresponding to data packets that failed to arrive in the video frame splitting data packets based on the receiver buffer duration, and determining the basic probability of late-arriving lost frames, includes: Based on the video frame splitting data packets, the video frames corresponding to data packets that failed to arrive within the duration of the receiving end buffer are detected to determine the late packet loss frames; The base probability of a late packet loss frame is calculated based on the duration of the receiver buffer and the late packet loss frame.

3. The method as described in claim 2, characterized in that, The step of detecting video frames corresponding to data packets that failed to arrive within the receiver buffer time based on the video frame splitting data packets, and determining late-arriving lost frames, includes: The timing is started when the first data packet of any video frame corresponding to the video frame split data packet is received, and the start time information is determined. The corresponding end time information is determined based on the start time information and the duration of the receiving end buffer. Based on the start time information and the end time information, the video frame is split into video frames corresponding to data packets that failed to arrive within the duration of the receiving end buffer, and late packet loss frames are obtained.

4. The method as described in claim 2, characterized in that, The step of calculating the base probability of the late packet loss frame based on the receiver buffer duration and the late packet loss frame includes: Obtain network data information; Based on the network data information, a basic packet loss probability model is constructed by establishing the dependency relationship between the corresponding receiver buffer duration and the late packet loss frame. Based on the receiver buffer duration and the input of the late packet loss frame into the basic packet loss probability model, the basic probability of the late packet loss frame is calculated to determine the basic probability of the late packet loss frame.

5. The method as described in claim 1, characterized in that, The step of correcting the base probability of late packet loss frames based on the receiver buffer duration, the available network bandwidth, and the total data volume of the video frames corresponding to the video frame split data packets, and determining the corrected probability of late packet loss frames includes: The video frame is parsed to split the data packets to obtain the total data volume of the video frame, and the theoretical transmission time is calculated based on the available network bandwidth and the total data volume of the video frame; A corresponding bandwidth correction weight model is constructed based on the ratio between the theoretical transmission duration and the receiver buffer duration. Based on the theoretical transmission duration, the receiver buffer duration, and the available network bandwidth, the bandwidth correction weight model is used to perform a weighted correction on the base probability of the late packet loss frame, thereby obtaining the probability of the late packet loss frame.

6. The method as described in claim 1, characterized in that, The step of simulating truncation of data packets in the corresponding target frame based on the probability of late packet loss, and completing the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction, includes: Get a random seed; Generate a corresponding random number based on the random seed; Based on the random number and the probability of late packet loss, the data packets in the corresponding target frame are simulated to be truncated, thereby completing the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction. The simulated truncation is used to simulate receiver buffer overflow or timeout scenarios and discard data packets with sequence numbers located at the end of the target frame.

7. The method as described in claim 1, characterized in that, After the step of simulating truncation of data packets in the corresponding target frame based on the probability of late packet loss, and completing the frame-level network packet loss simulation based on receiver buffer duration and bandwidth correction, the method further includes: Obtain simulated information from the sending end; When the probability of late packet loss frames predicted by the transmitter in the simulated information of the transmitter exceeds a predefined threshold, the transmitter coding strategy is determined. The transmitter coding strategy includes at least one of reducing the target bit rate, increasing the quantization parameter, reducing the resolution, or reducing the frame rate. Based on the aforementioned encoding strategy at the sending end, the amount of data or the number of data packets generated for the video frame splitting of subsequent video frames to be simulated are adjusted.

8. A frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction, characterized in that, The device includes: The acquisition module is used to acquire the receiver buffer duration, available network bandwidth, and video frame splitting data packets; The processing module is used to calculate the basic probability of video frames corresponding to data packets that failed to arrive in the video frame split data packets based on the duration of the receiving end buffer, and to determine the basic probability of late packet loss frames. The processing module is also used to correct the base probability of the late packet loss frame based on the receiver buffer duration, the available network bandwidth, and the total data volume of the video frames corresponding to the video frame split data packets, and to determine the corrected probability of the late packet loss frame. The execution module is used to simulate truncation of data packets in the corresponding target frame based on the probability of late packet loss, and to complete the frame-level network packet loss simulation based on the receiver buffer duration and bandwidth correction.

9. A frame-level network packet loss simulation device based on receiver buffer duration and bandwidth correction, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the frame-level network packet loss simulation method based on receiver buffer duration and bandwidth correction as described in any one of claims 1 to 7.

Images