CN119815131A - Video bit rate adjustment method, device, equipment and storage medium - Google Patents
Video bit rate adjustment method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN119815131A CN119815131A CN202411782582.3A CN202411782582A CN119815131A CN 119815131 A CN119815131 A CN 119815131A CN 202411782582 A CN202411782582 A CN 202411782582A CN 119815131 A CN119815131 A CN 119815131A
- Authority
- CN
- China
- Prior art keywords
- network
- data
- video
- network quality
- index data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
本申请提供了一种视频码率调整方法、装置、设备及存储介质，包括：针对预先获取的当前时刻的第一网络指标数据预测下一个时刻对应的第二网络指标数据；获取每个所述第二网络指标数据对应的网络质量评分；根据预先设置的贡献系数对每个所述网络质量评分进行加权求和，得到目标网络质量总分；根据所述目标网络质量总分在视频传输过程中调整视频对应的码率。本申请实施例不仅能够实时评估视频传输过程中的网络质量，还能通过动态调整预测模型和加权系数，提高网络质量评估的准确性和稳定性。
The present application provides a method, device, equipment and storage medium for adjusting video bit rate, including: predicting the second network indicator data corresponding to the next moment for the first network indicator data at the current moment obtained in advance; obtaining the network quality score corresponding to each of the second network indicator data; weighted summing each of the network quality scores according to a preset contribution coefficient to obtain a target network quality total score; adjusting the bit rate corresponding to the video during video transmission according to the target network quality total score. The embodiments of the present application can not only evaluate the network quality during video transmission in real time, but also improve the accuracy and stability of network quality evaluation by dynamically adjusting the prediction model and weighting coefficient.
Description
Technical Field
The embodiment of the application relates to the technical field of deep learning, in particular to a video code rate adjusting method, a device, equipment and a storage medium.
Background
In the video code rate adjustment technology widely used at present, direct prediction of transmission bandwidth information is a common method. However, this approach faces significant challenges. Firstly, the uncertainty of bandwidth prediction is more, and the frequent fluctuation of bandwidth can be caused by factors such as dynamic change of network topology, diversity of user behaviors, fluctuation of application program demands and the like. The fluctuation not only makes code rate adjustment frequent, but also directly influences user experience, and reduces satisfaction degree of users on network services.
Second, the lack of bandwidth forecast data is also a critical issue. In the data acquisition process, errors often exist in the quantification of uplink and downlink bandwidths, and the errors are further influenced by factors such as network topology change, user behavior change and the like, so that the quality of acquired data is poor. Such low quality data input directly affects the accuracy of the predictive model, making it difficult for the bandwidth predicted results to achieve the desired effect.
Thus, current bandwidth prediction methods present significant limitations in facing the complexity of the network environment and instability of data quality.
Disclosure of Invention
The embodiment of the application provides a video code rate adjusting method, a device, a system, electronic equipment and a computer readable storage medium.
In a first aspect, an embodiment of the present application provides a method for adjusting a video bitrate, where the method includes:
predicting second network index data corresponding to the next moment aiming at the first network index data of the current moment acquired in advance;
Acquiring a network quality score corresponding to each piece of second network index data;
And carrying out weighted summation on each network quality score according to a preset contribution coefficient to obtain a target network quality total score, wherein the target network quality total score is used for determining the network quality in the video transmission process.
Optionally, before the step of predicting the second network indicator data corresponding to the next time for the first network indicator data of the current time acquired in advance, the method includes:
Acquiring historical network index data under different service scenes;
Determining the network index score corresponding to each historical index data according to the preset corresponding relation between the network index data and the network index score;
Dividing all the historical index data according to a preset quality scoring range, and sampling network index data of each preset quality scoring range to obtain target network index data, wherein the target network index data are used for training a preset initial prediction model.
Optionally, predicting the second network index data corresponding to the next time for the first network index data of the current time acquired in advance includes:
training the preset initial prediction model through the target network index data to generate a prediction model;
And inputting the first network index data at the current time acquired in advance into a prediction model, and predicting the second network index data corresponding to the next time.
Optionally, the second network index data includes transmission delay data, packet loss rate and network jitter data, and the obtaining the network quality score corresponding to each second network index data includes:
Generating a first network quality score corresponding to the transmission delay data according to the delay adjustment factor and the transmission delay data;
generating a second network quality score corresponding to the packet loss rate according to the packet loss rate predicted value;
and generating a third network quality score corresponding to the network jitter data according to the network jitter data and the jitter adjustment factor.
Optionally, the preset contribution coefficient includes a first contribution coefficient corresponding to the transmission delay data, a second contribution coefficient corresponding to a packet loss rate, and a third contribution coefficient corresponding to network jitter data;
and performing weighted summation on each network quality score according to a preset contribution coefficient to obtain a target network quality total score, wherein the step of obtaining the target network quality total score comprises the following steps:
and multiplying the first contribution coefficient by the transmission delay data, multiplying the second contribution coefficient by the packet loss rate, and multiplying the third contribution coefficient by the network jitter data to sum so as to obtain a target network quality total score.
Optionally, after the step of performing weighted summation on each network quality score according to the preset contribution coefficient to obtain a target network quality total score, the method includes:
And adjusting the code rate corresponding to the video in the video transmission process according to the target network quality total score.
Optionally, the adjusting the code rate corresponding to the video in the video transmission process according to the total target network quality score includes:
When the current frame rate corresponding to the video is larger than a preset threshold value in the video transmission process, adjusting the frame rate corresponding to the video according to the total target network quality score, and adjusting the code rate corresponding to the video according to the total target network quality score;
And when the current frame rate corresponding to the video is smaller than or equal to a preset threshold value in the video transmission process, adjusting the code rate corresponding to the video according to the total target network quality score.
In a second aspect, an embodiment of the present application provides a video bitrate adjustment device, including:
The prediction module is used for predicting second network index data corresponding to the next moment aiming at the first network index data of the current moment acquired in advance;
The acquisition module is used for acquiring the network quality score corresponding to each piece of second network index data;
And the summation module is used for carrying out weighted summation on each network quality score according to a preset contribution coefficient to obtain a target network quality total score, wherein the target network quality total score is used for evaluating the network quality in the video transmission process.
Optionally, the apparatus further comprises:
the history acquisition module is used for acquiring historical network index data under different service scenes;
The determining module is used for determining the network index score corresponding to each historical index data according to the preset corresponding relation between the network index data and the network index score;
The sampling module is used for dividing all the historical index data according to a preset quality scoring range, and sampling network index data of each preset quality scoring range to obtain target network index data, wherein the target network index data are used for training a preset initial prediction model.
Optionally, the prediction module includes:
The first prediction submodule is used for training the initial prediction model preset through the target network index data to generate a prediction model;
And the second prediction sub-module is used for inputting the first network index data at the current moment acquired in advance into the prediction model and predicting the second network index data corresponding to the next moment.
Optionally, the second network indicator data includes transmission delay data, packet loss rate, and network jitter data, and the obtaining module includes:
The first acquisition submodule is used for generating a first network quality score corresponding to the transmission delay data according to the delay adjustment factor and the transmission delay data;
The second obtaining submodule is used for generating a second network quality score corresponding to the packet loss rate according to the packet loss rate predicted value;
and the third acquisition sub-module is used for generating a third network quality score corresponding to the network jitter data according to the network jitter data and the jitter adjustment factor.
Optionally, the preset contribution coefficient includes a first contribution coefficient corresponding to the transmission delay data, a second contribution coefficient corresponding to a packet loss rate, and a third contribution coefficient corresponding to network jitter data;
The summing module includes:
and the summation sub-module is used for multiplying the transmission delay data according to the first contribution coefficient, multiplying the second contribution coefficient by the packet loss rate, and multiplying the third contribution coefficient by the network jitter data to sum so as to obtain the total target network quality score.
Optionally, the adjusting module includes:
And the first adjusting sub-module is used for adjusting the frame rate corresponding to the video according to the total target network quality score and adjusting the code rate corresponding to the video according to the total target network quality score when the current frame rate corresponding to the video in the video transmission process is larger than a preset threshold.
Optionally, the adjusting module includes:
And the second adjusting sub-module is used for adjusting the code rate corresponding to the video according to the total target network quality score when the current frame rate corresponding to the video in the video transmission process is smaller than or equal to a preset threshold value.
In a third aspect, an embodiment of the present application further provides an electronic device, including a processor, and a memory for storing instructions executable by the processor, where the processor is configured to execute the instructions to implement the video code rate adjustment method according to any one of the above.
In a fourth aspect, an embodiment of the present application further provides a storage medium, where instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the video bitrate adjustment method according to any one of the above.
In the embodiment of the application, the first network index data at the current moment is predicted to acquire the second network index data at the next moment, and the network quality scores corresponding to the second network index data are weighted and summed by combining the preset contribution coefficients, so that the total target network quality score is obtained. The method not only can evaluate the network quality in the video transmission process in real time, but also can improve the accuracy and stability of network quality evaluation by dynamically adjusting the prediction model and the weighting coefficient. In the video transmission process, when the current frame rate of the video is larger than a preset threshold, the frame rate and the code rate of the video are adjusted according to the total target network quality score so as to optimize the bandwidth utilization and the user experience, and when the current frame rate of the video is smaller than or equal to the preset threshold, the code rate of the video is only adjusted so as to ensure the video quality and reduce the bandwidth occupation. Through the self-adaptive adjustment strategy, the video transmission method and device can effectively improve the fluency and quality of video transmission and remarkably improve the viewing experience of users.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
Fig. 1 is a flowchart of steps of a video code rate adjustment method according to an embodiment of the present application;
fig. 2 is a block diagram of a video code rate adjusting apparatus according to an embodiment of the present application;
FIG. 3 is a block diagram of an electronic device according to an embodiment of the present application;
Fig. 4 is a schematic diagram of an exemplary video code rate adjustment method according to an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.
Fig. 1 is a flowchart of steps of a video code rate adjustment method according to an embodiment of the present application, where, as shown in fig. 1, the method may include:
Before step 101, before the step of predicting, for the first network index data at the current time acquired in advance, second network index data corresponding to the next time, the method includes:
Acquiring historical network index data under different service scenes;
Determining the network index score corresponding to each historical index data according to the preset corresponding relation between the network index data and the network index score;
Dividing all the historical index data according to a preset quality scoring range, and sampling network index data of each preset quality scoring range to obtain target network index data, wherein the target network index data are used for training a preset initial prediction model.
It should be noted that, in the embodiment of the present application, data is collected and sorted. And collecting and cleaning network index data of the business scene, and labeling each piece of data with a quality score.
Firstly, sampling and obtaining are carried out in real time from the service, and the original data can simultaneously obtain historical network index data under different service scenes every 200 ms.
Therefore, sampling is carried out on the original data every 2 seconds, and data of continuous time periods are acquired according to the days, so that historical network index data under different service scenes are obtained.
Each index is endowed with a quality index between [0 and 100], the data acquired by each index are clustered to acquire the range and the occurrence frequency of each index data, a set of ladder type grading criterion for the quality of each index is preliminarily formulated, for example, the value of transmission delay is set to be T x, and the quality grading Q score is:
In the above formula 1, [ Q 1,Q2 ] represents a quality score range of the transmission delay within [ T 1,T2 ], in this way, quality evaluation is performed on the transmission delay, the packet loss rate, and the network jitter, and when the value is 0, the quality is better. In order to adapt to the interference caused by network jitter, combining a plurality of service scenes, data sampling is carried out again on the data in each quality scoring range, and the ratio of training data with the quality lower than 50 of each index is ensured to reach 10%.
For example, a quality score between [0,100] is assigned to each indicator, ranging from 0 to 100, indicating that the data quality is from worst to best. The specific scoring ranges are 0-10, 11-20, 21-30, generally, 31-40, good, 41-50, good, 51-60, 61-70, 71-80, very good, 81-90, very good, 91-100.
In order to acquire the range and the occurrence frequency of each index data, cluster analysis is performed on the data acquired by each index. The method comprises the following specific steps:
The method comprises the steps of acquiring index data such as transmission delay, packet loss rate, network jitter and the like from a service scene in real time, removing abnormal values and noise, guaranteeing accuracy and reliability of the data, clustering the data by using a clustering algorithm (such as K-means, DBSCAN and the like), dividing the data into different clusters, and determining the data range and the occurrence frequency of each cluster according to a clustering result.
Based on the result of cluster analysis, a set of ladder type grading criteria is preliminarily formulated and used for evaluating the quality of transmission delay, packet loss rate and network jitter. The specific scoring criteria are as follows:
For example, transmission delays of 0-10ms:100 minutes, 11-20ms:90 minutes, 21-30ms:80 minutes, 31-40ms:70 minutes, 41-50ms:60 minutes, 51-60ms:50 minutes, 61-70ms:40 minutes, 71-80ms:30 minutes, 81-90ms:20 minutes, 91-100ms, and more than 10 minutes may be set.
The packet loss rate is 0 percent to 100 percent, 0.1 percent to 1 percent to 90 percent, 1.1 percent to 2 percent to 80 percent, 2.1 percent to 3 percent to 70 percent, 3.1 percent to 4 percent to 60 percent, 4.1 percent to 5 percent to 50 percent, 5.1 percent to 6 percent to 40 percent, 6.1 percent to 7 percent to 30 percent, 7.1 percent to 8 percent to 20 percent, 8.1 percent to 9 percent and more than 10 percent.
Network jitter is 0-10ms:100 minutes, 11-20ms:90 minutes, 21-30ms:80 minutes, 31-40ms:70 minutes, 41-50ms:60 minutes, 51-60ms:50 minutes, 61-70ms:40 minutes, 71-80ms:30 minutes, 81-90ms:20 minutes, 91-100ms and more than 10 minutes.
To ensure diversity and representativeness of the training data set, data within each quality score range is again data sampled. The method comprises the following specific steps:
All data are divided according to quality scoring ranges, random sampling is carried out in each scoring interval to ensure that the data in each interval can be fully represented, and the intervals with quality scores lower than 50 are particularly concerned to ensure that the data in the intervals reach 10% in the training data set.
In this way, not only the data quality of each index can be evaluated, but also the diversity and representativeness of the training data set can be ensured through data sampling, thereby improving the prediction accuracy and stability of the model.
Step 101, predicting second network index data corresponding to the next moment aiming at the first network index data of the current moment acquired in advance;
Further, predicting the second network index data corresponding to the next time for the first network index data of the current time acquired in advance includes:
training the preset initial prediction model through the target network index data to generate a prediction model;
And inputting the first network index data at the current time acquired in advance into a prediction model, and predicting the second network index data corresponding to the next time.
In the embodiment of the present application, the preset initial prediction model is trained by the target network index data to generate a prediction model.
Specifically, target network index data is normalized to [0,1] as training data, transmission delay, packet loss rate and network jitter form 3 characteristics, the window sliding step length is 1, three different values of window sizes 15, 10 and 5 are used for comparison in order to compare the influence of different window sizes on model accuracy, the longer the window length model is more accurate to control the overall trend, but the prediction accuracy of mutation data is poor, the shorter the window is, the model is suitable for the enhancement of mutation data, but the overall trend is relatively weak. The combined traffic scenario, for example, uses a window length of 5.
After determining the window sliding step length, for model network design, 3, 4 and 5 numerical values are used for comparison experiments in the experiments, wherein 5 layers of LSTM perform optimally, possibly related to multi-feature input and output task complexity, 5 layers are used finally, the number of hidden layers of each layer is 128, 2 layers are arranged on each layer, three full-connection layers are connected finally, and three indexes of transmission delay, packet loss rate and network jitter are respectively predicted, for example, the dropout ratio of each layer of LSTM is 0.2 during training.
Finally, the loss function is selected, the transmission delay, the packet loss rate and the network jitter have positive correlation, one index is increased, and the other two indexes are increased, so that the same weight is given in the loss function design, namely the sum of three indexes loss is used as the final loss, the mean square error is selected as the loss function, the Adam optimizer is selected for training, and finally a model for simultaneously predicting the transmission delay, the packet loss rate and the network jitter is trained, for example, the training loss is 0.0012.
After training the prediction model, the first network index data at the current moment acquired in advance is input into the prediction model, and the second network index data corresponding to the next moment is predicted.
102, Obtaining a network quality score corresponding to each piece of second network index data;
further, the second network index data includes transmission delay data, packet loss rate and network jitter data, and the obtaining the network quality score corresponding to each second network index data includes:
Generating a first network quality score corresponding to the transmission delay data according to the delay adjustment factor and the transmission delay data;
generating a second network quality score corresponding to the packet loss rate according to the packet loss rate predicted value;
and generating a third network quality score corresponding to the network jitter data according to the network jitter data and the jitter adjustment factor.
In an actual service scene, firstly, a trained prediction model is used for predicting the transmission delay of the next time t according to the data of a past time window, the transmission delay is marked as latency t, the packet loss rate is marked as loss t, and the jitter is marked as jitter t. And then quantifying the three network indexes to obtain the scores of the three indexes respectively:
Firstly, the transmission delay quantization, namely the transmission delay t represents the time from a transmitting end to a receiving end, and the time is normalized firstly, and is expressed as:
Since the transmission delay is approximately in a stuck-at state when it reaches 400ms, transmission delays greater than 400ms are normalized to 400. The network quality score s 1 for the transmission delay is:
wherein, in the above formula 2, k represents the adjustment factor of the delay data, and in the current actual service scenario
Second, the packet loss rate quantization is that the packet loss rate loss t represents the packet loss ratio caused by network congestion, router failure and other reasons in the data transmission process, and the partial quality score s 2 of the packet loss rate is:
s 2＝(1-losst). Times.100 (equation 3)
Third, network jitter quantization, jitter t refers to the time jitter of a data packet in the transmission process, and the partial quality score s 3 of the jitter is:
Wherein d represents the adjustment factor of the network jitter data, and the adjustment factor is in the current actual service scene
And step 103, carrying out weighted summation on each network quality score according to a preset contribution coefficient to obtain a target network quality total score.
Further, the preset contribution coefficients include a first contribution coefficient corresponding to the transmission delay data, a second contribution coefficient corresponding to the packet loss rate, and a third contribution coefficient corresponding to the network jitter data;
and performing weighted summation on each network quality score according to a preset contribution coefficient to obtain a target network quality total score, wherein the step of obtaining the target network quality total score comprises the following steps:
and multiplying the first contribution coefficient by the transmission delay data, multiplying the second contribution coefficient by the packet loss rate, and multiplying the third contribution coefficient by the network jitter data to sum so as to obtain a target network quality total score.
It should be noted that, based on the network quality score corresponding to each second network index data calculated in the above, the weighted summation is performed to obtain the network quality at the time t:
s=α×s 1+β×s2+γ×s3 (formula 5)
In formula 5, α, β and γ are contribution factors of three indexes, and have different parameter sets in different application scenarios. For example, in a real-time audio and video communication scene, transmission delay and jitter are key indexes, and the lower actual data of the two indexes can provide faster response time and better user experience, so the weight ratio of [ alpha, beta, gamma ] = [0.4,0.2,0.4] can be adopted when the network quality is calculated.
And 104, adjusting the code rate corresponding to the video in the video transmission process according to the target network quality total score.
Further, the adjusting the code rate corresponding to the video in the video transmission process according to the target network quality total score includes:
when the current frame rate corresponding to the video is larger than a preset threshold in the video transmission process, the frame rate corresponding to the video is adjusted according to the total target network quality score, and the code rate corresponding to the video is adjusted according to the total target network quality score.
Further, the adjusting the code rate corresponding to the video in the video transmission process according to the target network quality total score includes:
And when the current frame rate corresponding to the video is smaller than or equal to a preset threshold value in the video transmission process, adjusting the code rate corresponding to the video according to the total target network quality score.
If the current frame rate is more than 20, the frame rate is adjusted preferentially, namely, the video frame rate is adjusted first, then the code rate is adjusted, otherwise, the compression quality is adjusted directly to reduce the code rate.
It should be noted that, in the embodiment of the present application, the frame rate of the transmission video may be dynamically adjusted according to the total target network quality score. If the network quality is good, the frame rate can be increased to improve smoothness and sharpness, and if the network quality is poor, the frame rate can be reduced to avoid video jamming.
Recording the current frame rate as f, and adjusting the frame rate f 1:
Where f max is the maximum frame rate that can be transmitted.
According to the total target network quality score, the code rate can be further adjusted by changing the compression quality, so that the bandwidth use is optimized, and the method is suitable for different network environments.
Recording the current code rate as m, and adjusting the frame rate m 1:
In addition, referring to fig. 4, the video rate adjustment process of the present application is divided into a data preprocessing, a model training and a prediction adjustment.
According to the embodiment of the application, the first network index data at the current moment is predicted by utilizing the LSTM model to acquire the second network index data at the next moment, and the network quality scores corresponding to the second network index data are weighted and summed by combining the preset contribution coefficients, so that the total target network quality score is obtained. The method not only can evaluate the network quality in the video transmission process in real time, but also can improve the accuracy and stability of network quality evaluation by dynamically adjusting the prediction model and the weighting coefficient. In the video transmission process, when the current frame rate of the video is larger than a preset threshold, the frame rate and the code rate of the video are adjusted according to the total target network quality score so as to optimize the bandwidth utilization and the user experience, and when the current frame rate of the video is smaller than or equal to the preset threshold, the code rate of the video is only adjusted so as to ensure the video quality and reduce the bandwidth occupation. Through the self-adaptive adjustment strategy, the video transmission method and device can effectively improve the fluency and quality of video transmission and remarkably improve the viewing experience of users. The video transmission quality can be improved, the problems of video jamming, picture blurring and the like are reduced, better user experience is provided, the bandwidth utilization rate is optimized, the transmission resources are effectively utilized to avoid network congestion and transmission delay, the system stability is improved, the strategy is timely adjusted to deal with network state changes, and the continuity and stability of video transmission are maintained.
In correspondence to the method provided by the embodiment of the video rate adjustment method of the present application, referring to fig. 2, the present application further provides a block diagram of a device for adjusting video rate, where in this embodiment, the device includes:
A prediction module 201, configured to predict, for first network index data at a current time acquired in advance, second network index data corresponding to a next time;
an obtaining module 202, configured to obtain a network quality score corresponding to each of the second network indicator data;
and the summation module 203 is configured to perform weighted summation on each network quality score according to a preset contribution coefficient, so as to obtain a target network quality total score.
And the adjusting module 204 is configured to adjust a code rate corresponding to the video in the video transmission process according to the total target network quality score.
Optionally, the apparatus further comprises:
the history acquisition module is used for acquiring historical network index data under different service scenes;
The determining module is used for determining the network index score corresponding to each historical index data according to the preset corresponding relation between the network index data and the network index score;
The sampling module is used for dividing all the historical index data according to a preset quality scoring range, and sampling network index data of each preset quality scoring range to obtain target network index data, wherein the target network index data are used for training a preset initial prediction model.
Optionally, the prediction module includes:
The first prediction submodule is used for training the initial prediction model preset through the target network index data to generate a prediction model;
And the second prediction sub-module is used for inputting the first network index data at the current moment acquired in advance into the prediction model and predicting the second network index data corresponding to the next moment.
Optionally, the second network indicator data includes transmission delay data, packet loss rate, and network jitter data, and the obtaining module includes:
The first acquisition submodule is used for generating a first network quality score corresponding to the transmission delay data according to the delay adjustment factor and the transmission delay data;
The second obtaining submodule is used for generating a second network quality score corresponding to the packet loss rate according to the packet loss rate predicted value;
and the third acquisition sub-module is used for generating a third network quality score corresponding to the network jitter data according to the network jitter data and the jitter adjustment factor.
Optionally, the preset contribution coefficient includes a first contribution coefficient corresponding to the transmission delay data, a second contribution coefficient corresponding to a packet loss rate, and a third contribution coefficient corresponding to network jitter data;
The summing module includes:
and the summation sub-module is used for multiplying the transmission delay data according to the first contribution coefficient, multiplying the second contribution coefficient by the packet loss rate, and multiplying the third contribution coefficient by the network jitter data to sum so as to obtain the total target network quality score.
Optionally, the adjusting module includes:
And the first adjusting sub-module is used for adjusting the frame rate corresponding to the video according to the total target network quality score and adjusting the code rate corresponding to the video according to the total target network quality score when the current frame rate corresponding to the video in the video transmission process is larger than a preset threshold.
Optionally, the adjusting module includes:
And the second adjusting sub-module is used for adjusting the code rate corresponding to the video according to the total target network quality score when the current frame rate corresponding to the video in the video transmission process is smaller than or equal to a preset threshold value.
In summary, according to the video code rate adjusting device provided by the embodiment of the application, the second network index data at the next moment is obtained by predicting the first network index data at the current moment, and the network quality scores corresponding to each second network index data are weighted and summed by combining the preset contribution coefficients, so that the target network quality total score is obtained. The method not only can evaluate the network quality in the video transmission process in real time, but also can improve the accuracy and stability of network quality evaluation by dynamically adjusting the prediction model and the weighting coefficient. In the video transmission process, when the current frame rate of the video is larger than a preset threshold, the frame rate and the code rate of the video are adjusted according to the total target network quality score so as to optimize the bandwidth utilization and the user experience, and when the current frame rate of the video is smaller than or equal to the preset threshold, the code rate of the video is only adjusted so as to ensure the video quality and reduce the bandwidth occupation. Through the self-adaptive adjustment strategy, the video transmission method and device can effectively improve the fluency and quality of video transmission and remarkably improve the viewing experience of users.
Fig. 3 is a block diagram of an electronic device M00 according to an embodiment of the present application, where the electronic device M00 includes a processor M01 and a memory M02, and the electronic device includes a processor and a memory for storing instructions executable by the processor, where the processor is configured to execute the instructions to implement any one of the video code rate adjustment methods described above, and the same technical effects can be achieved, so that repetition is avoided and no further description is given here.
In an embodiment of the present application, the memory M02 may be used to store software programs as well as various data. The memory M02 may mainly include a first memory area storing programs or instructions and a second memory area storing data, wherein the first memory area may store an operating system, application programs or instructions (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like. Further, the memory M02 may include a volatile memory or a nonvolatile memory, or the memory x09 may include both volatile and nonvolatile memories. The nonvolatile memory may be Read-Only memory (ROM), programmable ROM (PROM), erasable Programmable ROM (EPROM), electrically Erasable EPROM (EEPROM), or flash memory. The volatile memory may be Random Access Memory (RAM), static Random Access memory (STATIC RAM, SRAM), dynamic Random Access memory (DYNAMIC RAM, DRAM), synchronous dynamic Random Access memory (Synchronous DRAM, SDRAM), double data rate Synchronous dynamic Random Access memory (Double DATA RATE SDRAM, DDRSDRAM), enhanced Synchronous dynamic Random Access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic Random Access memory (SYNCH LINK DRAM, SLDRAM), and Direct memory bus Random Access memory (DRRAM). Memory M02 in embodiments of the application includes, but is not limited to, these and any other suitable types of memory.
The processor M01 may include one or more processing units, and optionally the processor M01 integrates an application processor that primarily processes operations involving an operating system, user interface, application program, etc., and a modem processor that primarily processes wireless communication signals, such as a baseband processor. It will be appreciated that the modem processor described above may not be integrated into the processor M01.
The embodiment of the application also provides a readable storage medium, on which a program or an instruction is stored, which when executed by a processor, implements each process of the video code rate adjustment method embodiment, and can achieve the same technical effects, so that repetition is avoided, and no further description is given here.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes computer readable storage medium such as computer readable memory ROM, random access memory RAM, magnetic or optical disk, etc.
The embodiment of the application further provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used for running programs or instructions to realize the processes of the video code rate adjusting method embodiment, and the same technical effects can be achieved, so that repetition is avoided, and the description is omitted here.
It should be understood that the chip according to the embodiments of the present application may also be referred to as a system-on-chip, a chip system, or a system-on-chip.
The embodiment of the application also provides a storage medium, which enables the electronic device to execute the video code rate adjustment method according to any one of the above when the instructions in the storage medium are executed by a processor of the electronic device.
Embodiments of the present application provide a computer program product stored in a storage medium, where the program product is executed by at least one processor to implement the respective processes of the video rate adjustment method embodiment, and achieve the same technical effects, and are not repeated herein.
The embodiment of the application also provides a vehicle, which comprises the video code rate adjusting device.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the related art in the form of a computer software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), including several instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present application.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are to be protected by the present application.
Claims (10)
1. A method for adjusting video code rate, the method comprising:
predicting second network index data corresponding to the next moment aiming at the first network index data of the current moment acquired in advance;
Acquiring a network quality score corresponding to each piece of second network index data;
Weighting and summing the network quality scores according to preset contribution coefficients to obtain a target network quality total score;
And adjusting the code rate corresponding to the video in the video transmission process according to the target network quality total score.
2. The method according to claim 1, wherein before the step of predicting the second network metric data corresponding to the next time instant for the first network metric data of the current time instant acquired in advance, the method comprises:
Acquiring historical network index data under different service scenes;
Determining the network index score corresponding to each historical index data according to the preset corresponding relation between the network index data and the network index score;
Dividing all the historical index data according to a preset quality scoring range, and sampling network index data of each preset quality scoring range to obtain target network index data, wherein the target network index data are used for training a preset initial prediction model.
3. The method of claim 2, wherein predicting the second network metric data corresponding to the next time instant for the previously acquired first network metric data of the current time instant comprises:
training the preset initial prediction model through the target network index data to generate a prediction model;
And inputting the first network index data at the current time acquired in advance into a prediction model, and predicting the second network index data corresponding to the next time.
4. The method of claim 1, wherein the second network metric data includes transmission delay data, packet loss rate, and network jitter data, and wherein the obtaining the network quality score corresponding to each of the second network metric data comprises:
Generating a first network quality score corresponding to the transmission delay data according to the delay adjustment factor and the transmission delay data;
generating a second network quality score corresponding to the packet loss rate according to the packet loss rate predicted value;
and generating a third network quality score corresponding to the network jitter data according to the network jitter data and the jitter adjustment factor.
5. The method of claim 4, wherein the preset contribution coefficients include a first contribution coefficient corresponding to the transmission delay data, a second contribution coefficient corresponding to a packet loss rate, and a third contribution coefficient corresponding to network jitter data;
and performing weighted summation on each network quality score according to a preset contribution coefficient to obtain a target network quality total score, wherein the step of obtaining the target network quality total score comprises the following steps:
and multiplying the first contribution coefficient by the transmission delay data, multiplying the second contribution coefficient by the packet loss rate, and multiplying the third contribution coefficient by the network jitter data to sum so as to obtain a target network quality total score.
6. The method of claim 1, wherein adjusting the code rate corresponding to the video during the video transmission according to the target network quality score comprises:
when the current frame rate corresponding to the video is larger than a preset threshold in the video transmission process, the frame rate corresponding to the video is adjusted according to the total target network quality score, and the code rate corresponding to the video is adjusted according to the total target network quality score.
7. The method of claim 1, wherein adjusting the code rate corresponding to the video during the video transmission according to the target network quality score comprises:
And when the current frame rate corresponding to the video is smaller than or equal to a preset threshold value in the video transmission process, adjusting the code rate corresponding to the video according to the total target network quality score.
8. A video bitrate adjustment device, the device comprising:
The prediction module is used for predicting second network index data corresponding to the next moment aiming at the first network index data of the current moment acquired in advance;
The acquisition module is used for acquiring the network quality score corresponding to each piece of second network index data;
the summation module is used for carrying out weighted summation on each network quality score according to a preset contribution coefficient to obtain a target network quality total score;
And the adjusting module is used for adjusting the code rate corresponding to the video in the video transmission process according to the target network quality total score.
9. An electronic device is characterized by comprising a processor;
a memory for storing the processor-executable instructions;
Wherein the processor is configured to execute the instructions to implement the video bitrate adjustment method of any of claims 1 to 7.
10. A computer storage medium, a readable storage medium storing a program, wherein the program when executed by a processor implements the video code rate adjustment method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411782582.3A CN119815131A (en) | 2024-12-05 | 2024-12-05 | Video bit rate adjustment method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411782582.3A CN119815131A (en) | 2024-12-05 | 2024-12-05 | Video bit rate adjustment method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119815131A true CN119815131A (en) | 2025-04-11 |
Family
ID=95258419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411782582.3A Pending CN119815131A (en) | 2024-12-05 | 2024-12-05 | Video bit rate adjustment method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119815131A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120238923A (en) * | 2025-05-30 | 2025-07-01 | 灵长智能科技(杭州)有限公司 | Method, device, equipment and medium for dynamically optimizing aircraft network service quality |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111083535A (en) * | 2019-12-26 | 2020-04-28 | 天翼物联科技有限公司 | Video data transmission code rate adaptation method, system, device and storage medium |
| CN117319228A (en) * | 2022-06-21 | 2023-12-29 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment, storage medium and product |
-
2024
- 2024-12-05 CN CN202411782582.3A patent/CN119815131A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111083535A (en) * | 2019-12-26 | 2020-04-28 | 天翼物联科技有限公司 | Video data transmission code rate adaptation method, system, device and storage medium |
| CN117319228A (en) * | 2022-06-21 | 2023-12-29 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment, storage medium and product |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120238923A (en) * | 2025-05-30 | 2025-07-01 | 灵长智能科技(杭州)有限公司 | Method, device, equipment and medium for dynamically optimizing aircraft network service quality |
| CN120238923B (en) * | 2025-05-30 | 2025-08-22 | 灵长智能科技(杭州)有限公司 | Method, device, equipment and medium for dynamic optimization of aircraft network service quality |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111294812B (en) | Method and system for resource expansion planning | |
| Fiedler et al. | A generic quantitative relationship between quality of experience and quality of service | |
| CN108877839B (en) | Method and system for perceptual evaluation of speech quality based on speech semantic recognition technology | |
| CN110890930B (en) | Channel prediction method, related equipment and storage medium | |
| Zhou et al. | Network traffic modeling and prediction with ARIMA/GARCH | |
| US20230292142A1 (en) | Transfer learning of network traffic prediction model among cellular base stations | |
| US8611302B2 (en) | Dynamic network selection using kernels | |
| US7957303B2 (en) | Communication quality evaluation method, derivation device, communication quality evaluation system and computer program | |
| Edalat et al. | Smart experts for network state estimation | |
| CN114339879B (en) | A service migration method based on reinforcement learning in mobile edge computing | |
| Nandakumar et al. | Efficient spectrum management techniques for cognitive radio networks for proximity service | |
| CN115884195A (en) | Model training method, wireless resource scheduling method and device thereof, and electronic equipment | |
| CN119815131A (en) | Video bit rate adjustment method, device, equipment and storage medium | |
| US20250324123A1 (en) | Video transmission quality evaluation and optimization method and system based on user behavior | |
| CN115052190B (en) | Video playing method and device | |
| US8954053B2 (en) | Method for link adaptation and apparatus thereof | |
| CN116708207B (en) | Self-adaptive networking method and device for household equipment, electronic equipment and storage medium | |
| CN117793130A (en) | Information management method and system based on cloud-end pair edge nodes | |
| CN116566696B (en) | Security assessment system and method based on cloud computing | |
| EP2941857B1 (en) | Site-based server selection | |
| US20130211803A1 (en) | Method and device for automatic prediction of a value associated with a data tuple | |
| CN120321360B (en) | A 5G video call quality management system based on network analysis | |
| Zabetian et al. | Hybrid non-intrusive QoE assessment of VoIP calls based on an ensemble learning model | |
| Stojčić et al. | PCA modeling of extraction and selection of variables influencing LTE network delay in urban mobility conditions | |
| Ranjan et al. | GA optimized HMM error model for OFDM |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |