CN114363677A - Mobile network video code rate real-time adjustment method and device based on deep learning - Google Patents
Mobile network video code rate real-time adjustment method and device based on deep learning Download PDFInfo
- Publication number
- CN114363677A CN114363677A CN202111467265.9A CN202111467265A CN114363677A CN 114363677 A CN114363677 A CN 114363677A CN 202111467265 A CN202111467265 A CN 202111467265A CN 114363677 A CN114363677 A CN 114363677A
- Authority
- CN
- China
- Prior art keywords
- network
- video
- mobile network
- deep learning
- code rate
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000013135 deep learning Methods 0.000 title claims abstract description 49
- 238000013528 artificial neural network Methods 0.000 claims abstract description 63
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 230000005540 biological transmission Effects 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims description 22
- 238000003860 storage Methods 0.000 claims description 14
- 238000011176 pooling Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 6
- 238000003062 neural network model Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 10
- 238000005457 optimization Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 6
- 238000011217 control strategy Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000008713 feedback mechanism Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a method and a device for adjusting video code rate of a mobile network in real time based on deep learning, wherein the method comprises the following steps: acquiring network parameters used for code rate adjustment decision of a mobile network in real time; based on the network parameters, adjusting the video transmission code rate in real time by a pre-established neural network; updating parameters of the neural network according to a maximum jackpot algorithm based on the received feedback signal. Compared with the prior art, the scheme of the invention dynamically adjusts the video code rate in real time according to the current mobile network parameters through the neural network based on deep learning, thereby effectively resisting network fluctuation and simultaneously improving the video playing effect.
Description
Technical Field
The invention relates to the technical field of video transmission, in particular to a method and a device for adjusting video code rate of a mobile network in real time based on deep learning.
Background
When audio and video are transmitted on a mobile network, due to the characteristics of the mobile network, the throughput, delay and the like of an end-to-end terminal in the mobile network have high time-varying property, and the network states dynamically fluctuate along with time due to network resource competition among different users, so that the existing fixed rule code rate adjustment algorithm is difficult to realize good code rate control.
Thus, there is still a need for improvement and development of the prior art.
Disclosure of Invention
The invention mainly aims to provide a method and a device for adjusting video code rate of a mobile network in real time based on deep learning, an intelligent terminal and a storage medium, and aims to solve the problem that the code rate of a transmitted video is difficult to automatically adjust according to the network signal quality of the mobile network by a fixed rule code rate adjusting algorithm in the prior art.
In order to achieve the above object, the present invention provides a method for adjusting video bitrate of a mobile network in real time based on deep learning, wherein the method comprises:
acquiring network parameters used for code rate adjustment decision of a mobile network in real time;
based on the network parameters, adjusting the video transmission code rate in real time by a pre-established neural network;
acquiring a feedback signal generated during video playing;
updating parameters of the neural network according to a maximum jackpot algorithm based on the feedback signal.
Optionally, the method for generating a feedback signal during video playing includes:
acquiring a real-time error rate and a frame loss rate during video playing;
and combining the real-time bit error rate and the frame dropping rate to form the feedback signal.
Optionally, the method for pre-establishing the neural network includes:
collecting training parameters of a mobile network;
obtaining a decision result according to a network congestion control algorithm based on the training parameters;
training the neural network based on the training parameters and the decision results.
Optionally, the training parameters include: the method comprises the steps of code stream size, packet loss rate, network mode, network state and video playing state.
Optionally, the adjusting, in real time, the video transmission code rate by the pre-established neural network based on the network parameter includes:
based on the network parameters, the neural network generating a rate adjustment decision;
and adjusting the video transmission code rate in real time according to the code rate adjustment decision.
Optionally, the obtaining, in real time, network parameters used for a code rate adjustment decision by the mobile network includes:
acquiring a coding buffer state of the video based on the current code rate of the video;
acquiring the wireless signal quality and the network state of a mobile network in the current mode;
acquiring the current playing state of a video;
and the coding buffer state, the wireless signal quality, the network state and the playing state are combined in a weighting mode to form the network parameter.
Optionally, the neural network includes three convolutional layers, two pooling layers, and two fully-connected layers.
In order to achieve the above object, a second aspect of the present invention further provides a device for adjusting video bitrate in a mobile network in real time based on deep learning, including:
the network parameter acquisition module is used for acquiring network parameters used for code rate adjustment decision of the mobile network in real time;
the code rate adjusting module is used for adjusting the video transmission code rate in real time by a pre-established neural network based on the network parameters;
the feedback signal acquisition module is used for acquiring a feedback signal generated during video playing;
an update module to update a parameter of the neural network according to a maximum jackpot algorithm based on the feedback signal.
The third aspect of the present invention provides an intelligent terminal, where the intelligent terminal includes a memory, a processor, and a mobile network video code rate real-time adjustment program based on deep learning, stored in the memory and operable on the processor, and when the mobile network video code rate real-time adjustment program based on deep learning is executed by the processor, the method implements any one of the steps of the mobile network video code rate real-time adjustment method based on deep learning.
A fourth aspect of the present invention provides a computer-readable storage medium, where a deep learning-based mobile network video bitrate real-time adjustment program is stored on the computer-readable storage medium, and when being executed by a processor, the deep learning-based mobile network video bitrate real-time adjustment program implements any one of the steps of the deep learning-based mobile network video bitrate real-time adjustment method.
According to the method, the device, the intelligent terminal and the storage medium for the real-time adjustment of the video code rate of the mobile network based on deep learning, disclosed by the invention, the network parameters of the mobile network for code rate adjustment decision are obtained in real time; adjusting the video transmission code rate in real time through a pre-established neural network based on the network parameters; acquiring a feedback signal generated during video playing; updating parameters of the neural network according to a maximum jackpot algorithm based on the feedback signal. The video code rate is dynamically adjusted in real time according to the current mobile network parameters through the neural network based on deep learning, so that the smooth video playing effect can be realized under the condition that mobile network signals are unstable.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a method for adjusting video bitrate in a mobile network in real time based on deep learning according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating the implementation of step S200 in FIG. 1;
FIG. 3 is a schematic flow chart illustrating the implementation of step S300 in FIG. 1;
fig. 4 is a schematic structural diagram of a device for adjusting video bitrate in a mobile network based on deep learning according to an embodiment of the present invention;
fig. 5 is a schematic block diagram of an internal structure of an intelligent terminal according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when …" or "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted depending on the context to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings of the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
When audio and video are transmitted on a mobile network, due to the characteristics of the mobile network, the throughput, delay and the like of an end-to-end terminal in the mobile network have high time-varying performance, and the network states dynamically fluctuate along with time due to network resource competition among different users. The code rate adjustment algorithm of the fixed rule generated according to the network and the video content is difficult to realize good code rate control.
The invention dynamically adjusts the video code rate in real time according to the current mobile network parameters through the neural network based on deep learning, thereby effectively resisting network fluctuation and simultaneously improving the video playing effect.
Examples of the inventionSexual method
As shown in fig. 1, an embodiment of the present invention provides a method for adjusting video bitrate of a mobile network in real time based on deep learning, and specifically, the method includes the following steps:
step S100: acquiring network parameters used for code rate adjustment decision of a mobile network in real time;
the network parameters comprise a coding buffer state, wireless signal quality, a network state and a video playing state, and the parameters are input into the neural network, so that the neural network can generate a code rate adjustment decision according to the parameters, and the adjustment of the video code rate is realized. Specifically, the encoding buffer state refers to the size of a code stream of video real-time encoding and the use condition of a cache region under the current code rate of the video, and the encoding buffer state of the video can be acquired based on the current code rate of the video; the current mode of the mobile network can be obtained from a wireless module of the mobile device, and the existing real-time network modes mainly include: 5G SA, 5G NSA, 4G, 3G. The radio Signal quality can be measured by RSRP (Reference Signal Receiving Power) and RSSI (Received Signal Strength Indicator). The mobile network state refers to real-time network delay and jitter parameters in the current network mode.
Furthermore, different weights can be set for the encoding buffer state, the wireless signal quality, the network state and the video playing state, and the parameters are weighted and combined to be used as network parameters for inputting into the neural network.
Step S200: adjusting the video transmission code rate in real time through a pre-established neural network based on the network parameters;
specifically, after the network parameters are obtained, the network parameters are input into the neural network model, and the neural network can adjust the transmission code rate of the current video in real time, so that the self-adaptive adjustment of the video coding parameters is realized, and the video playing effect is effectively improved while the network fluctuation is effectively resisted.
It should be noted that the neural network is pre-established through a learning training process, and is obtained by adopting a current mainstream real-time streaming media network congestion control algorithm to run in an actual mobile network for a long time. Specifically, in the learning phase, by collecting training parameters of the mobile network, the training parameters may include: the size of the code stream, the packet loss rate, the network mode, the network state, the video playing state and the like. And then based on the training parameters, obtaining a decision result according to a network congestion control algorithm, and training the neural network according to the training parameters and the decision result. The real-time streaming media network congestion control algorithm mainly senses network congestion through packet loss rate, or senses the network congestion through a time delay-based method, or senses the network congestion through a mixed method of the two methods.
And predicting an output value by the neural network according to the parameter information and the historical information of the mobile network at the current moment. Therefore, the neural network takes the congestion control algorithm of the real-time streaming media network as a prediction model, and the prediction model has the function of predicting the future dynamic behavior. Therefore, as in simulation, the future control strategy can be arbitrarily given, and the output change under different control strategies can be observed, so that a basis is provided for comparing the advantages and the disadvantages of the control strategies.
The neural Network in the embodiment specifically adopts a Deep Q Network (DQN) algorithm, which includes three convolutional layers, two pooling layers, and two full-link layers, and is used for mining video content and potential characteristics of the Network in video encoding and transmission processes, and making a decision of setting a code rate.
Step S300: acquiring a feedback signal generated during video playing;
step S400: based on the feedback signal, parameters of the neural network are updated according to a maximum jackpot algorithm.
Specifically, after the mobile network receiving end performs decoding playing, a new playing state is generated, and a feedback signal of the current code rate decision is sent to the neural network in real time. Based on this feedback signal, neural network parameters are continually updated according to a maximum jackpot algorithm. The feedback signal mainly comprises parameters reflecting the video playing state, such as the acquired real-time error rate, the frame loss rate and the like.
That is, the present invention adopts the principle of closed-loop optimization control, and in the prediction control, the output value is compared with the predicted value of the neural network model to obtain the prediction error of the neural network model, and then the prediction value of the neural network model is corrected by using the prediction error of the neural network model. Due to the process of applying feedback correction to the neural network model, the predictive control has strong disturbance resistance and capability of overcoming system uncertainty. Therefore, the neural network optimization of the invention is different from the common discrete optimal control algorithm, and adopts a rolling type limited time domain optimization strategy instead of a constant global optimal target. I.e. the optimization process is not done off-line at a time, but repeatedly on-line.
In summary, the scheme of the present invention obtains the network parameters of the mobile network for the code rate adjustment decision in real time; based on the network parameters, adjusting the video transmission code rate in real time by a pre-established neural network; updating parameters of the neural network according to a maximum jackpot algorithm based on the received feedback signal. The video code rate is dynamically adjusted in real time according to the current mobile network parameters through the neural network based on deep learning, so that the network fluctuation is effectively resisted, and the video playing effect is improved.
In one embodiment, the step S200 includes more specifically the steps as shown in fig. 2:
step S210: generating a code rate adjustment decision by the neural network based on the network parameters;
step S220: adjusting the video code rate in real time according to the code rate adjustment decision;
specifically, according to the obtained network parameters, the neural network adjusts the video bitrate according to the indexes such as available bandwidth and buffer size, so as to select a proper bitrate for the next video segment, thereby generating a bitrate adjustment decision. Namely: the neural network controls optimization through a prediction model, and predicts a proper code rate. And then adjusting the video coding rate and the transmission rate on the current mobile network in real time according to the generated rate adjustment decision.
As can be seen from the above, the present embodiment realizes dynamic adjustment of video coding rate and transmission rate of the mobile network by using the prediction model of the neural network.
In one embodiment, the step S300 includes more specifically the steps as shown in fig. 3:
step S310: acquiring a real-time error rate and a frame loss rate during video playing;
step S320: combining the real-time bit error rate and the frame loss rate to form the feedback signal;
specifically, when the mobile network receiving end receives the video and performs decoding playing, the error rate and the frame loss rate of the currently played video are counted in real time, and the combination of the real-time error rate and the frame loss rate is used as a feedback signal and sent to the neural network to form a reward feedback mechanism. The prediction accuracy of the neural network can be effectively improved through the feedback mechanism. Optionally, other video playing QoE index parameters may also be combined to form the feedback signal.
Exemplary device
As shown in fig. 4, corresponding to a method for adjusting a video bitrate of a mobile network in real time based on deep learning, an embodiment of the present invention further provides a device for adjusting a video bitrate of a mobile network in real time based on deep learning, where the device for adjusting a video bitrate of a mobile network in real time based on deep learning includes:
a network parameter obtaining module 600, configured to obtain, in real time, a network parameter used by the mobile network for a code rate adjustment decision;
the network parameters comprise a coding buffer state, wireless signal quality, a network state and a video playing state, and the parameters are input into the neural network, so that the neural network can generate a code rate adjustment decision according to the parameters, and the adjustment of the video code rate is realized. Specifically, the encoding buffer state refers to the size of a code stream of video real-time encoding and the use condition of a cache region under the current code rate of the video, and the encoding buffer state of the video can be acquired based on the current code rate of the video; the current mode of the mobile network can be obtained from a wireless module of the mobile device, and the existing real-time network modes mainly include: 5G SA, 5G NSA, 4G, 3G. The radio Signal quality can be measured by RSRP (Reference Signal Receiving Power) and RSSI (Received Signal Strength Indicator). The mobile network state refers to real-time network delay and jitter parameters in the current network mode.
Furthermore, different weights can be set for the encoding buffer state, the wireless signal quality, the network state and the video playing state, and the parameters are weighted and combined to be used as network parameters for inputting into the neural network.
A code rate adjusting module 610, configured to adjust a video transmission code rate in real time by using a pre-established neural network based on network parameters;
specifically, after the network parameters are obtained, the network parameters are input into the neural network model, and the neural network can adjust the transmission code rate of the current video in real time, so that the self-adaptive adjustment of the video coding parameters is realized, and the video playing effect is effectively improved while the network fluctuation is effectively resisted.
It should be noted that the neural network is pre-established through a learning training process, and is obtained by adopting a current mainstream real-time streaming media network congestion control algorithm to run in an actual mobile network for a long time. Specifically, in the learning phase, by collecting training parameters of the mobile network, the training parameters may include: the size of the code stream, the packet loss rate, the network mode, the network state, the video playing state and the like. And then based on the training parameters, obtaining a decision result according to a network congestion control algorithm, and training the neural network according to the training parameters and the decision result. The real-time streaming media network congestion control algorithm mainly senses network congestion through packet loss rate, or senses the network congestion through a time delay-based method, or senses the network congestion through a mixed method of the two methods.
And predicting an output value by the neural network according to the parameter information and the historical information of the mobile network at the current moment. Therefore, the neural network takes the congestion control algorithm of the real-time streaming media network as a prediction model, and the prediction model has the function of predicting the future dynamic behavior. Therefore, as in simulation, the future control strategy can be arbitrarily given, and the output change under different control strategies can be observed, so that a basis is provided for comparing the advantages and the disadvantages of the control strategies.
A feedback signal obtaining module 620, configured to obtain a feedback signal generated during video playing;
an updating module 630 for updating parameters of the neural network according to a maximum jackpot algorithm based on the feedback signal.
Specifically, after the mobile network receiving end performs decoding playing, a new playing state is generated, and a feedback signal of the current code rate decision is sent to the neural network in real time. Based on this feedback signal, neural network parameters are continually updated according to a maximum jackpot algorithm. The feedback signal mainly comprises parameters reflecting the video playing state, such as the acquired real-time error rate, the frame loss rate and the like.
That is, the present invention adopts the principle of closed-loop optimization control, and in the prediction control, the output value is compared with the predicted value of the neural network model to obtain the prediction error of the neural network model, and then the prediction value of the neural network model is corrected by using the prediction error of the neural network model. Due to the process of applying feedback correction to the neural network model, the predictive control has strong disturbance resistance and capability of overcoming system uncertainty. Therefore, the neural network optimization of the invention is different from the common discrete optimal control algorithm, and adopts a rolling type limited time domain optimization strategy instead of a constant global optimal target. I.e. the optimization process is not done off-line at a time, but repeatedly on-line.
In this embodiment, specific functions of each module of the device for adjusting a video bitrate of a mobile network based on deep learning may refer to corresponding descriptions in the method for adjusting a video bitrate of a mobile network based on deep learning, and are not described herein again.
Based on the above embodiment, the present invention further provides an intelligent terminal, and a schematic block diagram thereof may be as shown in fig. 5. The intelligent terminal comprises a processor, a memory, a network interface and a display screen which are connected through a system bus. Wherein, the processor of the intelligent terminal is used for providing calculation and control capability. The memory of the intelligent terminal comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a mobile network video bitrate real-time adjustment program based on deep learning. The internal memory provides an environment for the operation of an operating system in a nonvolatile storage medium and a mobile network video bitrate real-time adjustment program based on deep learning. The network interface of the intelligent terminal is used for being connected and communicated with an external terminal through a network. When being executed by a processor, the mobile network video code rate real-time adjusting program based on deep learning realizes the steps of any one of the mobile network video code rate real-time adjusting methods based on deep learning. The display screen of the intelligent terminal can be a liquid crystal display screen or an electronic ink display screen.
It will be understood by those skilled in the art that the block diagram shown in fig. 5 is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation to the intelligent terminal to which the solution of the present invention is applied, and a specific intelligent terminal may include more or less components than those shown in the figure, or combine some components, or have a different arrangement of components.
In one embodiment, an intelligent terminal is provided, where the intelligent terminal includes a memory, a processor, and a deep learning based mobile network video bitrate real-time adjustment program stored on the memory and executable on the processor, and when executed by the processor, the deep learning based mobile network video bitrate real-time adjustment program performs the following operations:
acquiring network parameters used for code rate adjustment decision of a mobile network in real time;
based on the network parameters, adjusting the video transmission code rate in real time by a pre-established neural network;
updating parameters of the neural network according to a maximum jackpot algorithm based on the received feedback signal.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium is stored with a mobile network video code rate real-time adjusting program based on deep learning, and the mobile network video code rate real-time adjusting program based on deep learning is executed by a processor to realize the steps of any one of the mobile network video code rate real-time adjusting methods based on deep learning provided by the embodiment of the invention.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned functions may be distributed as different functional units and modules according to needs, that is, the internal structure of the apparatus may be divided into different functional units or modules to implement all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art would appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the above modules or units is only one logical division, and the actual implementation may be implemented by another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
The integrated modules/units described above, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium and can implement the steps of the embodiments of the method when the computer program is executed by a processor. The computer program includes computer program code, and the computer program code may be in a source code form, an object code form, an executable file or some intermediate form. The computer readable medium may include: any entity or device capable of carrying the above-mentioned computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signal, telecommunication signal, software distribution medium, etc. It should be noted that the contents contained in the computer-readable storage medium can be increased or decreased as required by legislation and patent practice in the jurisdiction.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein.
Claims (10)
1. The method for adjusting the video code rate of the mobile network in real time based on deep learning is characterized by comprising the following steps:
acquiring network parameters used for code rate adjustment decision of a mobile network in real time;
adjusting the video transmission code rate in real time through a pre-established neural network based on the network parameters;
acquiring a feedback signal generated during video playing;
updating parameters of the neural network according to a maximum jackpot algorithm based on the feedback signal.
2. The method for adjusting video bitrate in mobile network based on deep learning of claim 1, wherein the method for generating feedback signals during playing video comprises:
acquiring a real-time error rate and a frame loss rate during video playing;
and combining the real-time bit error rate and the frame dropping rate to form the feedback signal.
3. The method for adjusting video bitrate in a mobile network based on deep learning of claim 1, wherein the method for pre-establishing the neural network comprises:
collecting training parameters of a mobile network;
obtaining a decision result according to a network congestion control algorithm based on the training parameters;
training the neural network based on the training parameters and the decision results.
4. The method for adjusting video bitrate for mobile networks based on deep learning of claim 3, wherein the training parameters comprise: the method comprises the steps of code stream size, packet loss rate, network mode, network state and video playing state.
5. The method for adjusting video bitrate on a mobile network based on deep learning of claim 1, wherein the adjusting video transmission bitrate in real time through a pre-established neural network based on the network parameters comprises:
based on the network parameters, the neural network generating a rate adjustment decision;
and adjusting the video transmission code rate in real time according to the code rate adjustment decision.
6. The method for adjusting video bitrate on a mobile network based on deep learning of claim 1, wherein the obtaining network parameters of the mobile network for bitrate adjustment decision in real time comprises:
acquiring a coding buffer state of the video based on the current code rate of the video;
acquiring the wireless signal quality and the network state of a mobile network in the current mode;
acquiring the current playing state of a video;
and the coding buffer state, the wireless signal quality, the network state and the playing state are combined in a weighting mode to form the network parameter.
7. The method for adjusting video bitrate on a mobile network based on deep learning of claim 1, wherein the neural network comprises three convolutional layers, two pooling layers and two fully connected layers.
8. Device for adjusting video code rate of mobile network in real time based on deep learning, which is characterized in that the device comprises:
the network parameter acquisition module is used for acquiring network parameters used for code rate adjustment decision of the mobile network in real time;
the code rate adjusting module is used for adjusting the video transmission code rate in real time through a pre-established neural network based on the network parameters;
the feedback signal acquisition module is used for acquiring a feedback signal generated during video playing;
an update module to update a parameter of the neural network according to a maximum jackpot algorithm based on the feedback signal.
9. An intelligent terminal, characterized in that the intelligent terminal comprises a memory, a processor and a deep learning based mobile network video bitrate real-time adjustment program stored on the memory and operable on the processor, and when the deep learning based mobile network video bitrate real-time adjustment program is executed by the processor, the steps of the deep learning based mobile network video bitrate real-time adjustment method according to any one of claims 1 to 7 are implemented.
10. Computer readable storage medium, wherein the computer readable storage medium stores thereon a deep learning based mobile network video bitrate real-time adjustment program, and when the deep learning based mobile network video bitrate real-time adjustment program is executed by a processor, the steps of the deep learning based mobile network video bitrate real-time adjustment method according to any one of claims 1 to 7 are implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111467265.9A CN114363677A (en) | 2021-12-02 | 2021-12-02 | Mobile network video code rate real-time adjustment method and device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111467265.9A CN114363677A (en) | 2021-12-02 | 2021-12-02 | Mobile network video code rate real-time adjustment method and device based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114363677A true CN114363677A (en) | 2022-04-15 |
Family
ID=81097659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111467265.9A Pending CN114363677A (en) | 2021-12-02 | 2021-12-02 | Mobile network video code rate real-time adjustment method and device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114363677A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115834924A (en) * | 2022-11-02 | 2023-03-21 | 华中科技大学 | Interactive video-oriented loosely-coupled coding rate-transmission rate adjusting method |
| WO2024120134A1 (en) * | 2022-12-09 | 2024-06-13 | 中兴通讯股份有限公司 | Video transmission method, apparatus and device, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108063961A (en) * | 2017-12-22 | 2018-05-22 | 北京联合网视文化传播有限公司 | A kind of self-adaption code rate video transmission method and system based on intensified learning |
| CN110087110A (en) * | 2019-06-12 | 2019-08-02 | 深圳市大数据研究院 | Using the method and device of deep search dynamic regulation video playing |
| CN111901642A (en) * | 2020-07-31 | 2020-11-06 | 成都云格致力科技有限公司 | Real-time video code rate self-adaptive control method and system based on reinforcement learning |
| CN112367490A (en) * | 2020-09-11 | 2021-02-12 | 北京邮电大学 | Hybrid learning method, device and equipment for improving interactive video transmission quality |
| CN113572697A (en) * | 2021-07-20 | 2021-10-29 | 电子科技大学 | Load balancing method based on graph convolution neural network and deep reinforcement learning |
| CN113596021A (en) * | 2021-07-28 | 2021-11-02 | 中国人民解放军国防科技大学 | Streaming media code rate self-adaption method, device and equipment supporting neural network |
-
2021
- 2021-12-02 CN CN202111467265.9A patent/CN114363677A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108063961A (en) * | 2017-12-22 | 2018-05-22 | 北京联合网视文化传播有限公司 | A kind of self-adaption code rate video transmission method and system based on intensified learning |
| CN110087110A (en) * | 2019-06-12 | 2019-08-02 | 深圳市大数据研究院 | Using the method and device of deep search dynamic regulation video playing |
| CN111901642A (en) * | 2020-07-31 | 2020-11-06 | 成都云格致力科技有限公司 | Real-time video code rate self-adaptive control method and system based on reinforcement learning |
| CN112367490A (en) * | 2020-09-11 | 2021-02-12 | 北京邮电大学 | Hybrid learning method, device and equipment for improving interactive video transmission quality |
| CN113572697A (en) * | 2021-07-20 | 2021-10-29 | 电子科技大学 | Load balancing method based on graph convolution neural network and deep reinforcement learning |
| CN113596021A (en) * | 2021-07-28 | 2021-11-02 | 中国人民解放军国防科技大学 | Streaming media code rate self-adaption method, device and equipment supporting neural network |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115834924A (en) * | 2022-11-02 | 2023-03-21 | 华中科技大学 | Interactive video-oriented loosely-coupled coding rate-transmission rate adjusting method |
| CN115834924B (en) * | 2022-11-02 | 2024-05-14 | 华中科技大学 | Interactive video-oriented loose coupling coding code rate-transmission rate adjusting method |
| WO2024120134A1 (en) * | 2022-12-09 | 2024-06-13 | 中兴通讯股份有限公司 | Video transmission method, apparatus and device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114363677A (en) | Mobile network video code rate real-time adjustment method and device based on deep learning | |
| Xing et al. | A real-time adaptive algorithm for video streaming over multiple wireless access networks | |
| CN111431941B (en) | Real-time video code rate self-adaption method based on mobile edge calculation | |
| US8793557B2 (en) | Method and apparatus for real-time multidimensional adaptation of an audio coding system | |
| CN112954385B (en) | Self-adaptive shunt decision method based on control theory and data driving | |
| RU2277300C2 (en) | Method and device for monitoring and prediction of multi-thread load | |
| CN108924667B (en) | Available bandwidth self-adaptive video fragment request method supporting QoE maximization | |
| CN107534969A (en) | Strengthen encoding and decoding engine control | |
| US20140247722A1 (en) | Congestion level indication with explicit congestion notification in communication systems | |
| US8819523B2 (en) | Adaptive controller for a configurable audio coding system | |
| CN104394484A (en) | Wireless live streaming media transmission method | |
| Xing et al. | Rate adaptation strategy for video streaming over multiple wireless access networks | |
| CN111225209A (en) | Video data plug flow method, device, terminal and storage medium | |
| US20230262232A1 (en) | Video coding method and apparatus, computer-readable medium and electronic device | |
| Xu et al. | Reinforcement learning-based mobile AR/VR multipath transmission with streaming power spectrum density analysis | |
| CN102724502B (en) | The control method of code check and device in a kind of Video coding | |
| Lassoued et al. | A methodology for evaluating vertical handoff decision mechanisms | |
| WO2024120134A1 (en) | Video transmission method, apparatus and device, and storage medium | |
| Hafez et al. | Reinforcement learning-based rate adaptation in dynamic video streaming | |
| CN111385574A (en) | Code rate control method and device in video coding, mobile terminal and storage medium | |
| CN109787856B (en) | HAS bandwidth prediction method based on LTE network link state | |
| Mowafi et al. | Energy efficient fuzzy-based DASH adaptation algorithm | |
| CN113872873B (en) | Multi-scene cross-layer congestion control method suitable for 5G new application | |
| CN114827683A (en) | Video self-adaptive code rate control system and method based on reinforcement learning | |
| Liu et al. | Throughput Prediction-Enhanced RL for Low-Delay Video Application |
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 |