Data processing method and system, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a data processing method and system, electronic equipment and a storage medium, and relates to the technical field of network communication. The method comprises the following steps: acquiring initial data, and recording time for acquiring the initial data to obtain current time; acquiring a link layer state parameter at the current time through a link sensing layer of the sending end; the data round-trip delay and the network bandwidth at the current time are obtained through a network sensing layer of the sending end; performing packet loss rate prediction according to the link layer state parameters to obtain a predicted packet loss rate; generating a code rate according to the predicted packet loss rate, the data round-trip delay and the network bandwidth to obtain a target code rate at the current time; and encoding the initial data according to the target code rate to obtain target data, and sending the target data to a receiving end. According to the embodiment of the invention, the data can be stably transmitted in a changeable wireless network environment, and the transmission delay of the data is reduced.

Description

Technical Field

[0001] The present application relates to the field of network communication technology, and in particular to a data processing method and system, an electronic device, and a storage medium. Background Art

[0002] A wireless network refers to a network that can interconnect various communication devices (including transmitters and receivers) without the need for wiring. For example, during aerial photography, transmitters such as aircraft need to wirelessly transmit a large amount of audio and video data. Specifically, the audio and video data is encoded and processed before being sent to receivers such as mobile phones or computers. At present, in the process of data transmission based on wireless networks, data is difficult to transmit stably and the transmission delay is large. The main reason is that the encoding processing technology is not suitable for the complex and changeable wireless network environment. For example, when the encoded audio and video data is transmitted in a weak network environment, there will be delays, freezes, and interruptions, which will affect the audio and video playback at the receiving end.

[0003] Therefore, how to stably transmit data in a changeable wireless network environment and reduce data transmission delay has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a data processing method and system, an electronic device, and a storage medium, the purpose of which is to stably transmit data in a changeable wireless network environment and reduce data transmission delay.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a data processing method, which is applied to a sending end, and the method includes:

[0006] Acquire initial data, and record the time when the initial data is acquired to obtain the current time;

[0007] Acquire the link layer state parameters at the current time through the link perception layer of the sending end;

[0008] Acquire the data round-trip delay and network bandwidth at the current time through the network perception layer of the sending end;

[0009] Predicting the packet loss rate according to the link layer state parameter to obtain a predicted packet loss rate;

[0010] Generate a bit rate according to the predicted packet loss rate, the data round-trip delay and the network bandwidth to obtain the target bit rate at the current time;

[0011] The initial data is encoded according to the target code rate to obtain target data, and the target data is sent to a receiving end.

[0012] In some embodiments, before generating a bit rate according to the predicted packet loss rate, the data round-trip delay, and the network bandwidth to obtain the target bit rate at the current time, the method further includes:

[0013] Comparing the predicted packet loss rate with a preset first packet loss rate threshold;

[0014] If the predicted packet loss rate is greater than or equal to the first packet loss rate threshold, the initial data is encoded according to a preset first bit rate to obtain the target data; wherein the first bit rate is less than the target bit rate.

[0015] In some embodiments, before generating a bit rate according to the predicted packet loss rate, the data round-trip delay, and the network bandwidth to obtain the target bit rate at the current time, the method further includes:

[0016] Comparing the predicted packet loss rate with a preset second packet loss rate threshold;

[0017] If the predicted packet loss rate is less than or equal to the second packet loss rate threshold, the initial data is encoded according to a preset second bit rate to obtain the target data; wherein the second bit rate is greater than or equal to half of a preset maximum bit rate threshold.

[0018] In some embodiments, the predicted packet loss rate is obtained by predicting the packet loss rate of the link layer state parameter using a preset adaptive Gaussian cloud transformation model;

[0019] The generating a bit rate according to the predicted packet loss rate, the data round-trip delay and the network bandwidth to obtain the target bit rate at the current time includes:

[0020] Using a preset Bayesian neural network classification model, classify the network quality according to the predicted packet loss rate, the data round-trip delay and the network bandwidth to obtain a target network quality level;

[0021] The target bit rate at the current time is determined according to the target network quality level.

[0022] In some embodiments, the initial data includes an initial video;

[0023] The determining the target bit rate at the current time according to the target network quality level includes:

[0024] Selecting a target resolution and a target frame rate corresponding to the target network quality level from a preset network quality coding relationship table;

[0025] The video bit rate is calculated according to the target resolution and the target frame rate to obtain the target bit rate.

[0026] In some embodiments, the step of predicting the packet loss rate according to the link layer state parameter to obtain the predicted packet loss rate includes:

[0027] Through the preset adaptive Gaussian cloud transformation model, the link layer state parameters are transformed into Gaussian distribution to obtain the link layer state parameter Gaussian distribution;

[0028] By using the adaptive Gaussian cloud transformation model, a membership degree is calculated according to the link layer state parameter Gaussian distribution and each of at least two preset link layer parameter thresholds to obtain a candidate membership degree;

[0029] The adaptive Gaussian cloud transformation model is used to perform expected value mapping based on the maximum candidate membership and the link layer state parameter Gaussian distribution to obtain the predicted packet loss rate.

[0030] In some embodiments, the link layer status parameters are at least two, and the link layer status parameters include signal-to-noise ratio, signal reception power, and signal reception quality;

[0031] The performing Gaussian distribution conversion on the link layer state parameter to obtain the Gaussian distribution of the link layer state parameter includes:

[0032] Performing a first Gaussian distribution conversion on each of the signal-to-noise ratios to obtain a Gaussian distribution of the signal-to-noise ratio;

[0033] Performing a second Gaussian distribution conversion on each of the signal receiving powers to obtain a signal receiving power Gaussian distribution;

[0034] Performing a third Gaussian distribution conversion on each of the signal reception qualities to obtain a signal reception quality Gaussian distribution;

[0035] Gaussian distribution averaging is performed on the signal-to-noise ratio Gaussian distribution, the signal reception power Gaussian distribution, and the signal reception quality Gaussian distribution to obtain the link layer state parameter Gaussian distribution.

[0036] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a data processing system, the data processing system comprising: a sending end, a server and a receiving end; wherein the sending end executes the data processing method described in the first aspect above;

[0037] The server is wirelessly connected with the sending end and the receiving end;

[0038] The sending end is used to send the target data to the server; the receiving end is used to receive the target data from the server and decode the target data to obtain initial data corresponding to the target data.

[0039] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the data processing method described in the first aspect when executing the computer program.

[0040] To achieve the above objectives, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the data processing method described in the first aspect.

[0041] The data processing method and system, electronic device, and storage medium proposed in the present application use the time of obtaining the initial data as the current time; obtain the link layer state parameter at the current time through the link perception layer of the sending end, and the parameter can reflect the signal quality between the sending end and the receiving end. In addition, the packet loss rate is predicted according to the link layer state parameter to obtain the predicted packet loss rate, so that the link layer wireless signal transmission quality of the sending end at the current time can be evaluated, and the network environment can be further evaluated according to the predicted packet loss rate. Through the network perception layer of the sending end, the data round-trip delay and network bandwidth at the current time are obtained, and these two parameters can reflect the data transmission status of the network. Then, according to the predicted packet loss rate, the data round-trip delay and the network bandwidth, the code rate is generated, and the current network environment between the sending end and the receiving end can be comprehensively and in real time evaluated, and the generated target code rate is ensured to be suitable for the current network environment. Then, the initial data is encoded into target data according to the target code rate, so that the target data is sent to the receiving end. The present application adjusts the bit rate in real time according to the current network environment, and encodes the data according to the adjusted bit rate to send the data, thereby improving the data transmission stability, reducing the data transmission delay, and being able to adapt to the changing wireless network environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is a flow chart of a data processing method provided in an embodiment of the present application;

[0043] Figure 2 is a system architecture diagram of a data processing system provided in an embodiment of the present application;

[0044] Figure 3 is a system architecture diagram of a data processing system provided by another embodiment of the present application;

[0045] Figure 4 is a flow chart of a data processing method provided by another embodiment of the present application;

[0046] Figure 5 is a flow chart of a data processing method provided by another embodiment of the present application;

[0047] Figure 6 yes Figure 1 Flowchart of step 104 in;

[0048] Figure 7 yes Figure 6 Flow chart of step 401 in;

[0049] Figure 8 yes Figure 1 Flowchart of step 105 in;

[0050] Fig. 9 It is a schematic diagram of a specific implementation of the data processing method provided in the embodiment of the present application;

[0051] Fig.10 yes Figure 8 Flowchart of step 602 in FIG.

[0052] Fig.11 is a system architecture diagram of a data processing system provided by another embodiment of the present application;

[0053] Fig.12 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0057] First, some nouns involved in this application are analyzed:

[0058] Wireless Network: refers to a computer network that does not rely on physical line connections. It allows electronic devices to communicate and exchange data within a certain range through radio waves. Wireless network technology allows users to access the network more flexibly without being restricted by geographical location.

[0059] Artificial Intelligence (AI): It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence; AI is a branch of computer science. AI attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. Artificial intelligence can be a simulation of the information process of human consciousness and thinking. Artificial intelligence is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Basic AI technologies generally include technologies such as sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology and machine learning / deep learning. This application can acquire and process relevant data based on artificial intelligence technology.

[0060] Neural network: It is an important branch of artificial intelligence. Neural networks, especially artificial neural networks in deep learning, are computational models that imitate the connection structure and information processing methods of human brain neurons. Neural network models can learn complex patterns and features from large amounts of data and are widely used in a variety of scenarios such as image recognition, speech recognition, and natural language processing.

[0061] The data processing method and system, electronic device, and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the data processing method in the embodiments of the present application is described.

[0062] Figure 1 is an optional flowchart of the data processing method provided in the embodiment of the present application. Figure 1 The data processing method is applied to the sending end, and the data processing method may include but is not limited to steps 101 to 106.

[0063] Step 101, obtaining initial data, and recording the time of obtaining the initial data to obtain the current time;

[0064] Step 102, obtaining the link layer state parameters at the current time through the link perception layer of the sending end;

[0065] Step 103, obtaining the data round-trip delay and network bandwidth at the current time through the network perception layer of the sending end;

[0066] Step 104, predicting the packet loss rate according to the link layer state parameter to obtain a predicted packet loss rate;

[0067] Step 105, generating a bit rate according to the predicted packet loss rate, data round trip delay and network bandwidth to obtain a target bit rate at the current time;

[0068] Step 106, encoding the initial data according to the target bit rate to obtain target data, and sending the target data to the receiving end.

[0069] The beneficial effects of the embodiments of the present application include but are not limited to: taking the time of obtaining the initial data as the current time; obtaining the link layer state parameter at the current time through the link perception layer of the transmitting end, which can reflect the signal quality between the transmitting end and the receiving end. In addition, the packet loss rate is predicted according to the link layer state parameter to obtain the predicted packet loss rate, so that the link layer wireless signal transmission quality of the transmitting end at the current time can be evaluated, and the network environment can be further evaluated according to the predicted packet loss rate. Through the network perception layer of the transmitting end, the data round-trip delay and network bandwidth at the current time are obtained, and these two parameters can reflect the data transmission status of the network. Then, the code rate is generated according to the predicted packet loss rate, the data round-trip delay and the network bandwidth, which can comprehensively and in real time evaluate the current network environment between the transmitting end and the receiving end, and ensure that the generated target code rate is suitable for the current network environment. Then, the initial data is encoded into the target data according to the target code rate, so that the target data is sent to the receiving end. The present application adjusts the code rate in real time according to the current network environment, and encodes the data according to the adjusted code rate to send the data, which improves the transmission stability of the data, reduces the transmission delay of the data, and can adapt to the changing wireless network environment.

[0070] It should be noted that the transmitting end refers to a device used for data collection and data transmission. For example, the transmitting end may be an aircraft, such as a low-altitude aircraft, a drone, etc. The receiving end refers to a device used to receive data and use (such as display or play) data, such as a personal computer (PC), a handheld device or a portable device (such as a smart phone, a laptop), a tablet computer, a desktop computer, a multiprocessor system, a minicomputer, a mainframe computer, etc. Both the transmitting end and the receiving end can communicate based on a wireless network. For example, the transmitting end can transmit data based on wireless networks such as WIFI, a mobile network (such as 2G, 3G, 4G, 5G), etc.

[0071] In step 101 of some embodiments, the initial data is data collected by the transmitting end, and the data is encoded by the transmitting end and sent to the receiving end. The initial data includes audio and video data. For example, the audio and video data may include data of types such as audio, video, and image. For example, during aerial photography, environmental detection, live broadcast, etc., a drone shoots a video through a camera device, or collects audio through a sound sensor, encodes the captured video and the collected audio, and then sends them to the receiving end.

[0072] It should be noted that the current time refers to the time when the sender obtains the initial data. In the scenario of real-time data transmission, such as in the process of drone aerial live broadcast, since the drone needs to send the video data immediately after obtaining the video data for the user to watch the video, that is, the interval between the data acquisition time and the data transmission time is very small, it can be considered that the time when the sender obtains the initial data is equivalent to the time when the target data is sent. Therefore, the network environment parameters at the current time (such as link layer state parameters, data round-trip delay and network bandwidth) can be used to evaluate the network environment when data is sent.

[0073] In some embodiments, the current time can be a moment or a period. For example, if the drone takes an image (that is, obtains initial data) at 10:00, the current time is 10:00 am. For another example, if the drone takes a video (that is, obtains initial data) between 18:00 and 18:30, the current time includes 18:00 to 18:30.

[0074] In step 102 of some embodiments, the transmitting end includes a network perception module, and the network perception module includes a link perception layer and a network perception layer. The network perception module refers to a virtual module for perceiving a network environment. Among them, the link perception layer refers to a virtual module for detecting the quality of a wireless signal between the transmitting end and the receiving end, and the link layer state parameters can be obtained through the link perception layer. As for the meaning and function of the network perception layer, please refer to the specific description of step 103 below.

[0075] It should be noted that the link layer state parameters are used to characterize the data transmission or reception state of the transmitter. The link layer state parameters include signal-to-noise ratio, signal reception power, and signal reception quality. For example, the signal-to-noise ratio is specifically the signal to interference plus noise ratio (SINR), which refers to the ratio of the strength of the received useful signal to the strength of the received interference signal (such as noise and interference). The signal reception power is specifically the reference signal reception power (RSRP). The signal reception quality is specifically the reference signal reception quality (RSRQ).

[0076] In one embodiment, the wireless network where the transmitter is located can be divided into a link layer, a network layer, a transport layer, and an application layer by using a TCP / IP four-layer network model. In this case, the link layer is equivalent to the physical layer. In another embodiment, the network layer division can also be performed in other ways, such as by using an OSI seven-layer network model (Open System Interconnection Model, referred to as OSI model), which is not limited here.

[0077] In step 103 of some embodiments, the network perception layer refers to a virtual module for detecting the network transmission status between the sender and the receiver. The network layer parameters can be obtained through the network perception layer, specifically the data round-trip time (RTT) and the network bandwidth. Among them, the data round-trip time is used to characterize the round-trip time of data between the sender and the receiver. The network bandwidth is also the communication bandwidth (CWB).

[0078] Specifically, the data round-trip delay can be detected by using a Ping command. The network bandwidth can be detected by using a network speed test tool. In addition, the sender can also use other methods to obtain the data round-trip delay and network bandwidth, which is not limited thereto.

[0079] In step 104 of some embodiments, the packet loss rate can be predicted according to the link layer state parameters by a preset packet loss rate evaluation model, or the predicted packet loss rate can be determined by threshold comparison. For example, the packet loss rate evaluation model is also called a PRR evaluation model. The link layer state parameters are input into the PRR evaluation model to predict the packet reception rate (PRR) at the current time. Among them, PRR reflects the ratio between the data packets received by the receiving end and the data packets sent by the sending end. The packet loss rate can be calculated based on the packet reception rate. For example, the packet loss rate and the packet reception rate are both in the form of percentages. Subtract the packet reception rate from 1 to calculate the packet loss rate.

[0080] It should be noted that the predicted packet loss rate refers to the packet loss rate predicted based on the link layer state parameters (such as signal-to-noise ratio) at the current time. The predicted packet loss rate is used to reflect the quality of the wireless signal between the transmitter and the receiver. In addition, since the communication quality of the wireless network between the transmitter and the receiver is affected by the quality of the wireless signal, the predicted packet loss rate can be used to determine the communication quality of the wireless network, that is, the overall wireless network environment.

[0081] In step 105 of some embodiments, the network quality assessment can be performed based on the predicted packet loss rate, data round trip delay and network bandwidth through a preset network quality assessment model to obtain the network quality assessment information (such as the target network quality level) at the current time, and then the target bit rate at the current time can be determined based on the network quality assessment information. Alternatively, the target bit rate can be determined based on the predicted packet loss rate, data round trip delay and network bandwidth through a threshold comparison method.

[0082] In some embodiments, the network quality evaluation model is also called an LQE evaluation model. The predicted packet loss rate, data round-trip delay, and network bandwidth are input into the LQE evaluation model to evaluate the link quality evaluation (Link Quality Estimate, LQE) result at the current time, that is, the target network quality level, so as to determine the target bit rate according to the target network quality level.

[0083] In some embodiments, the network quality assessment model is an artificial intelligence model. For example, the network quality assessment model may include a Bayesian neural network classification model. For another example, the network quality assessment model may also include other types of artificial intelligence models such as a convolutional neural network model and a linear regression machine learning model.

[0084] It should be noted that the target bit rate is determined based on the current network quality. Bit rate refers to the amount of data transmitted per second in a video stream or audio stream. The unit of bit rate can be bits per second (bps), Kbps (kilobits per second) or Mbps (megabits per second). The bit rate setting directly affects the picture clarity of the video. If the bit rate is low, the picture may appear blurry; if the bit rate is high, the picture will be clearer. Too high a bit rate may cause the data volume to be too large, which is not conducive to transmission; while too low a bit rate may cause the quality of the audio or video obtained after the data is decoded to deteriorate, affecting the audio or video playback effect. When transmitting in a weak network environment, problems such as delay, freeze and interruption may occur, affecting the audio and video playback at the receiving end.

[0085] In some embodiments, when an aircraft (such as a low-altitude aircraft such as a drone) collects audio and video data in the air, it is necessary to transmit a large amount of audio and video data to the receiving end based on a wireless network. The wireless network has the characteristics of a complex and changeable network environment. For example, parameters such as the bandwidth of the wireless network may change greatly in a short period of time. In particular, in the application scenario of the aircraft, since the flight altitude and the region where the drone is located may change frequently, it often faces the problem of unstable wireless signals when it relies on wireless signals for communication. If a fixed encoding strategy is used to encode audio and video data, it may cause a large data transmission delay and it is difficult to transmit data stably. For example, the transmitting end sends target data with a large bit rate to the receiving end based on a wireless network. If the target data is transmitted in a weak network environment, there will be delays, freezes and interruptions, which will affect the real-time communication between the receiving end and the aircraft, and then affect the subsequent operations of the receiving end, such as controlling the flight status of the aircraft based on the target data, playing videos, etc. In particular, in application scenarios with high real-time requirements (such as drone aerial photography live broadcast), the data transmission delay will greatly affect the user experience. In response to the above problems, the embodiments of the present application adjust the target bit rate in real time according to the current wireless network environment to avoid the bit rate being too high or too low. While ensuring the playback quality of audio and video data, the data transmission delay is reduced as much as possible, and the stability of data transmission is improved, thereby adapting to the changing wireless network environment, improving the flexibility of the data processing method, and improving the data transmission efficiency.

[0086] It can be understood that a weak network environment refers to a network environment with unstable network connection, slow data transmission rate and high packet loss rate.

[0087] It is understandable that the data processing method is not limited to the scenario where the drone transmits audio and video data, but can also be applied to other scenarios that rely on wireless networks for data transmission. The embodiments of the present application are not limited to this.

[0088] In step 106 of some embodiments, the target data refers to the data obtained after the transmitting end encodes the initial data. The target data is sent from the transmitting end to the receiving end so that the receiving end can perform subsequent operations on the target data. For example, the receiving end can play the audio or video corresponding to the target data (that is, the initial data), or send a feedback instruction to the transmitting end based on the target data.

[0089] Specifically, the target data may be a data frame, that is, the format of the target data is a frame format. For example, after the initial data is compressed according to the target bit rate, the initial data is encapsulated into a data frame (that is, the target data) in a format such as MP4 (MPEG-4 Part 14) or Audio Video Interleaved (AVI). It is understandable that after encapsulating an initial data, multiple data frames can be obtained.

[0090] It should be noted that the format of the target data is related to the format of the initial data. For example, when the initial data is audio data, the target data obtained after the encoding process is an audio frame. For another example, when the initial data is video data, the target data obtained after the encoding process is a video frame.

[0091] In some embodiments, when the initial data is audio and video data, the transmitting end encodes the audio and video data and sends it to the receiving end in a streaming media manner. It is understandable that streaming media refers to sending data in segments to achieve instant transmission. For example, the transmitting end encodes the video data into multiple video frames and then transmits the video frames, so the user at the receiving end does not have to wait for all the video data to be transmitted, and can play the video instantly, and can also pause, fast forward, etc. the video.

[0092] In some embodiments, the initial data may be encoded according to a preset network control protocol and a target bit rate. For example, the network control protocol includes any of the following: RTSP, RTMP, HLS, HTTP-FLV, WebSocket-FLV, GB28181, HTTP-TS, WebSocket-TS, HTTP-fMP4, WebSocket-fMP4, MP4, WebRTC, etc. The network control protocol may be set and changed as required, and protocol conversion may be performed for different network control protocols, such as converting the initial data based on the RTSP protocol into the target data based on the MP4 protocol.

[0093] In some embodiments, the target data in the frame format is sent to the receiving end. Specifically, the sending end sends the target data to the server, and the server sorts and converts the target data, and then forwards the target data to the receiving end to ensure that the receiving end can decode the target data normally. The receiving end decodes the target data to obtain the initial data, and then performs subsequent operations on the initial data, such as playing audio or video.

[0094] Specifically, the server can be configured as an independent physical server, or as a server cluster or distributed system consisting of multiple physical servers. It can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0095] In some embodiments, the target data is sent to the receiving end by sending the target data based on a wireless network such as WIFI, 3G, 4G, or 5G.

[0096] See also Figure 2 In some embodiments, the data processing method can be applied to a sending end in a data processing system. For example, the data processing system includes a sending end, a server, and a receiving end. The sending end includes: a data acquisition module, a network perception module, an adaptive coding module, and a data sending module; wherein the network perception module includes a link perception layer and a network perception layer;

[0097] The data acquisition module is used to acquire initial data and record the current time of acquiring the initial data. For example, the data acquisition module can be used to execute step 101.

[0098] The link perception layer is used to collect link layer parameters, such as signal-to-noise ratio, signal reception power, and signal reception quality, so as to evaluate the quality of the wireless signal between the transmitter and the receiver. For example, the link perception layer can be used to perform step 102.

[0099] The network perception layer is used to collect network layer parameters, such as data round trip delay and network bandwidth, so as to evaluate the network transmission quality between the sender and the receiver. For example, the network perception layer can be used to perform step 103.

[0100] The adaptive coding module is used to determine the quality level of the current wireless network according to the above parameters provided by the link perception layer and the network perception layer, and dynamically and in real time adjust the coding parameters of the data according to the target network quality level, for example, adjust the target bit rate, or adjust the frame rate (Frame Rate) and resolution (Resolution) to calculate the target bit rate, and then generate target data according to the target bit rate. For example, the adaptive coding module can be used to perform steps 104 to 105, and step 106 to encode the initial data according to the target bit rate to obtain the target data.

[0101] The data sending module is used to send the target data to the receiving end. Specifically, the data sending module can send the target data to the server so that the server forwards the target data to the receiving end after processing.

[0102] See also Figure 2 and Figure 3 In some embodiments, the data processing method can be applied to the distributed scenario of 5G communication. For example, the transmitting end sends the target data to the 5G base station. Specifically, the data sending module of the transmitting end sends the data frame (that is, the target data) to the 5G base station through streaming media. Then, the target data is forwarded to the server through at least one 5G base station, so that the server processes the target data and then sends it to the receiving end (see Figure 2 ), thereby achieving long-distance data transmission. Figure 3 In 5G, the server is a distributed system composed of multiple devices, such as the Open Radio Access Network (O-RAN) system, which can provide 5G communication services for the sender and receiver.

[0103] In some embodiments, the O-RAN system can transmit data through three networks: fronthaul, middlehaul, and backhaul. For example, the fronthaul network is used to transmit data sent by the sender to each node in the O-RAN system. The node refers to the physical device in the O-RAN system. The middlehaul network is used to transmit data from each node to the centralized unit in the O-RAN system. The centralized unit refers to the highest-level node, which is used to centrally process all data in the O-RAN system. The backhaul network is used to collect the processed data and route the data so that the data can be sent to the receiving end.

[0104] It is understandable that in Figure 2 and Figure 3In the figure, the arrow is used to indicate the direction of data transmission. In addition, data can also be transmitted between the sending end and the receiving end in other directions, for example, the receiving end can also send data or instructions to the sending end, which is not limited in the embodiments of the present application.

[0105] See also Figure 4 In some embodiments, before step 105, the data processing method may also include but is not limited to steps 201 to 202:

[0106] Step 201, comparing the predicted packet loss rate with a preset first packet loss rate threshold;

[0107] Step 202: if the predicted packet loss rate is greater than or equal to the first packet loss rate threshold, the initial data is encoded according to a preset first bit rate to obtain target data; wherein the first bit rate is less than the target bit rate.

[0108] The advantage of this embodiment is that if the predicted packet loss rate is greater than or equal to the first packet loss rate threshold, it indicates that the quality of the wireless signal between the receiving end and the transmitting end is poor. Since the quality of the wireless signal will affect the overall network communication quality, it can be inferred that the network communication quality will not be very high, and the first code rate that is less than the target code rate is directly selected for data encoding, and the encoded target data is sent, that is, a lower code rate is used for encoding processing to adapt to the network environment with unstable signals, avoiding the subsequent acquisition of network layer parameters (such as data round-trip delay and network bandwidth) to further judge the calculation cost and time cost brought by the network quality, reducing data transmission delay, reducing the probability of packet loss to improve the stability of data transmission, and adapting to the changeable wireless network environment.

[0109] In step 201 of some embodiments, the first packet loss rate threshold is a packet loss rate value used to determine whether the quality of the wireless signal in the wireless network is poor. If the packet loss rate of the wireless network is greater than or equal to the first packet loss rate threshold, it indicates that the quality of the wireless signal of the wireless network is poor. For example, the predicted packet loss rate is a predicted packet loss rate based on the link layer state parameters of the wireless network between the receiving end and the transmitting end. If the predicted packet loss rate is greater than or equal to the first packet loss rate threshold, it indicates that the quality of the wireless signal between the receiving end and the transmitting end is poor.

[0110] In some embodiments, the first packet loss rate threshold may be a larger packet loss rate value, such as 5% to 10%. The first packet loss rate threshold may be set or adjusted as required. For example, if the stability of network transmission is required to be high, the first packet loss rate threshold may be set to 3%, that is, as long as the predicted packet loss rate is greater than or equal to 3%, low bit rate encoding is used.

[0111] In step 202 of some embodiments, the first bit rate may be a lower bit rate, for example, the value range of the first bit rate may include 0.9Mbps to 2Mbps. In one embodiment, when the predicted packet loss rate is greater than or equal to the first packet loss rate threshold, the preset first bit rate may be directly read from the storage unit of the transmitter. In another embodiment, when the predicted packet loss rate is greater than or equal to the first packet loss rate threshold, the resolution and frame rate may also be reduced. For example, a lower resolution and frame rate, such as a resolution of 360p and a frame rate of 30fps (frames persecond), is read from the storage unit of the transmitter, and then the corresponding bit rate is calculated based on the resolution and frame rate.

[0112] See also Figure 5 In some embodiments, before step 105, the data processing method may also include but is not limited to steps 301 to 302:

[0113] Step 301, comparing the predicted packet loss rate with a preset second packet loss rate threshold;

[0114] Step 302: If the predicted packet loss rate is less than or equal to the second packet loss rate threshold, the initial data is encoded according to a preset second bit rate to obtain target data; wherein the second bit rate is greater than or equal to half of the preset maximum bit rate threshold.

[0115] The advantage of this embodiment is that if the predicted packet loss rate is less than or equal to the second packet loss rate threshold, it indicates that the wireless signal quality between the transmitter and the receiver is good. Since the signal quality of the link layer will affect the overall network communication quality, it can be inferred that the communication quality of the network layer will not be very poor, and the preset second code rate is directly selected for data encoding and the encoded data (target data) is sent, wherein the second code rate is greater than or equal to half of the preset maximum code rate threshold, that is, a higher code rate is used for encoding, thereby improving the data playback quality as much as possible on the basis of a good network environment, such as improving the playback smoothness of audio or video, avoiding the calculation cost and time cost brought by further judging the quality of the network layer, adapting to the changing wireless network environment, and improving the user experience.

[0116] In step 301 of some embodiments, the second packet loss rate threshold is a packet loss rate value used to determine whether the wireless signal quality in the wireless network is good. If the packet loss rate of the wireless network is greater than or equal to the second packet loss rate threshold, it indicates that the wireless signal quality of the wireless network is good, that is, the current network environment is good, and there is almost no packet loss.

[0117] It should be noted that the second packet loss rate threshold may be a smaller packet loss rate value, such as 1% to 2%.

[0118] In some embodiments, the first packet loss rate threshold is greater than the second packet loss rate threshold. It is understandable that since the first packet loss rate threshold is used to determine whether the signal quality of the link layer is poor, and the second packet loss rate threshold is used to determine whether the signal quality of the link layer is good, the first packet loss rate threshold is set to be greater than the second packet loss rate threshold.

[0119] In some embodiments, the first packet loss rate threshold is greater than the second packet loss rate threshold, and the interval between the first packet loss rate threshold and the second packet loss rate threshold is greater than or equal to 2%. For example, the first packet loss rate threshold is 3%, and the second packet loss rate threshold is 1%, and the numerical interval between the two is 2%. By setting the first packet loss rate threshold and the second packet loss rate threshold as two thresholds with a certain interval, two different situations of good and poor wireless signal quality can be more significantly distinguished, so as to adjust the encoding strategy to adapt to different wireless signal qualities.

[0120] In step 302 of some embodiments, the second bit rate is a larger bit rate, and the second bit rate is used to improve data quality when the network quality is good. It can be understood that if the predicted packet loss rate is less than or equal to the second packet loss rate threshold, it means that the signal quality of the link layer is good, so the bit rate can be appropriately increased to improve the playback quality of the audio or video corresponding to the target data. For example, the second packet loss rate threshold is 1%, and the predicted packet loss rate is 0.5%. Since the predicted packet loss rate (0.5%) is less than the second packet loss rate threshold (1%), the second bit rate is adopted, where the second bit rate can be half of the maximum bit rate threshold of 10Mbps (megabits per second), that is, 5Mbps.

[0121] It can be understood that when the predicted packet loss rate is less than or equal to the second packet loss rate threshold, although the wireless signal quality is good, considering that the overall network communication quality may also be affected by other network environment factors (such as device performance in the network), the second bit rate is not directly set to the maximum bit rate threshold. Instead, the second bit rate is set to half of the maximum bit rate threshold, so as to maintain a balance between audio and video data transmission delay and audio and video playback quality as much as possible.

[0122] See also Figure 6 In some embodiments, step 104 may include but is not limited to steps 401 to 403:

[0123] Step 401, performing Gaussian distribution conversion on the link layer state parameters through a preset adaptive Gaussian cloud transformation model to obtain a Gaussian distribution of the link layer state parameters;

[0124] Step 402, using an adaptive Gaussian cloud transformation model, performing membership calculation according to the link layer state parameter Gaussian distribution and each of at least two preset link layer parameter thresholds to obtain a candidate membership;

[0125] Step 403, using an adaptive Gaussian cloud transformation model, an expected value mapping is performed according to the maximum candidate membership and the link layer state parameter Gaussian distribution to obtain a predicted packet loss rate.

[0126] The advantage of this embodiment is that, through the adaptive Gaussian cloud transformation model, the link layer state parameters are converted to Gaussian distribution, so as to more accurately simulate the randomness and uncertainty in the wireless network environment, and obtain the Gaussian distribution of the link layer state parameters for subsequent packet loss rate prediction. The membership calculation is performed according to the link layer state parameter Gaussian distribution and each of the at least two preset link layer parameter thresholds to calculate the association between each link layer state parameter and each link layer parameter threshold. Then, the expected value mapping is performed according to the maximum candidate membership and the link layer state parameter Gaussian distribution to obtain the predicted packet loss rate to reflect the wireless signal quality of the wireless network. In addition, the overall network communication quality can be further judged based on the predicted packet loss rate, so as to adjust the data encoding strategy according to the network communication quality, that is, to adjust the target code rate in real time to adapt to the current wireless network environment, so as to achieve more stable data transmission and lower transmission delay in a changeable wireless network environment, and provide users with a smoother and more reliable network communication experience.

[0127] In step 401 of some embodiments, the adaptive Gaussian cloud transformation model is a statistical model based on Gaussian distribution (normal distribution), which can calculate the probability of unknown data based on known data. In an embodiment of the present application, the adaptive Gaussian cloud transformation model is used to calculate the packet loss rate based on the link layer state parameters. It should be noted that the Gaussian distribution conversion of the link layer state parameters refers to converting the link layer state parameters into the form of Gaussian distribution. Gaussian distribution, also known as normal distribution, is a continuous probability distribution.

[0128] In step 402 of some embodiments, at least two link layer parameter thresholds may be preset. The membership of the link layer state parameter Gaussian distribution and each link layer parameter threshold is calculated by the membership function of the adaptive Gaussian cloud transformation model to obtain at least two candidate memberships. Then, the largest candidate membership is selected from each candidate membership. The candidate membership is used to characterize the degree of association between the link layer state parameter and the link layer parameter threshold.

[0129] For example, assume that the link layer state parameter Gaussian distribution is x. Through the membership function, according to x and the first link layer parameter threshold A1, the first membership A1(x) is calculated; according to x and the second link layer parameter threshold A2, the second membership A2(x) is calculated. If the first membership A1(x) is greater than the second membership A2(x), that is, the first membership A1(x) is the largest candidate membership, it means that the link layer state parameter Gaussian distribution x has the highest correlation with the first link layer parameter threshold A1.

[0130] In step 403 of some embodiments, the cloud mapping function of the adaptive Gaussian cloud transformation model is parameter updated according to the link layer parameter threshold corresponding to the maximum candidate membership. Then, the expected value mapping of the link layer state parameter Gaussian distribution is performed through the cloud mapping function to obtain the predicted packet loss rate.

[0131] In some embodiments, at least two link layer state parameters can be obtained, and an initial packet loss rate can be calculated based on each link layer state parameter. Then, an average value of each initial packet loss rate is calculated to obtain a final predicted packet loss rate, thereby improving the accuracy of packet loss rate prediction by taking the average value through multiple calculations.

[0132] In some embodiments, in addition to predicting the packet loss rate using the adaptive Gaussian cloud transformation model, the packet loss rate corresponding to the link layer state parameter Gaussian distribution can be found in a preset link layer state parameter packet loss rate table by looking up a table to obtain the predicted packet loss rate. Other methods can also be used to predict the packet loss rate, not limited to this.

[0133] See also Figure 7 , in some embodiments, the link layer state parameters are at least two, and the link layer state parameters include signal-to-noise ratio, signal reception power, and signal reception quality;

[0134] Step 401 may include but is not limited to steps 501 to 504:

[0135] Step 501, performing a first Gaussian distribution conversion on each signal-to-noise ratio to obtain a Gaussian distribution of the signal-to-noise ratio;

[0136] Step 502, performing a second Gaussian distribution conversion on each signal receiving power to obtain a Gaussian distribution of the signal receiving power;

[0137] Step 503, performing a third Gaussian distribution conversion on each signal reception quality to obtain a signal reception quality Gaussian distribution;

[0138] Step 504 , performing Gaussian distribution averaging processing according to the signal-to-noise ratio Gaussian distribution, the signal reception power Gaussian distribution and the signal reception quality Gaussian distribution to obtain a link layer state parameter Gaussian distribution.

[0139] The advantage of this embodiment is that by converting the signal-to-noise ratio, signal reception power, and signal reception quality into Gaussian distribution forms, respectively, and then performing Gaussian distribution averaging processing according to the signal-to-noise ratio Gaussian distribution, the signal reception power Gaussian distribution, and the signal reception quality Gaussian distribution, a link layer state parameter Gaussian distribution is obtained, so that the membership degree is subsequently calculated according to the link layer state parameter Gaussian distribution to obtain a predicted packet loss rate, thereby evaluating the wireless network environment, and adjusting the bit rate to adapt to a changeable wireless network environment, thereby improving the efficiency and stability of data transmission and reducing data transmission delay.

[0140] In step 501 of some embodiments, the signal-to-noise ratio Gaussian distribution is a Gaussian distribution (i.e., normal distribution) of the signal-to-noise ratio. Each signal-to-noise ratio refers to the signal-to-noise ratio of the wireless network between the receiving end and the transmitting end at the current time. For example, the current time is from 10:30 to 11:00, and multiple signal-to-noise ratios are detected within the current time, and then Gaussian distribution fitting is performed according to each signal-to-noise ratio to obtain a Gaussian distribution of the signal-to-noise ratio.

[0141] In step 502 of some embodiments, the signal receiving power Gaussian distribution is a Gaussian distribution of the signal receiving power. Each signal receiving power refers to the signal receiving power of the wireless network between the receiving end and the transmitting end at the current time.

[0142] In step 503 of some embodiments, the signal reception quality Gaussian distribution is a Gaussian distribution of signal reception quality. Each signal reception quality refers to the signal reception quality of the wireless network between the receiving end and the transmitting end at the current time.

[0143] In step 504 of some embodiments, the first Gaussian cloud parameter (such as expected value, entropy, and super entropy) of the signal-to-noise ratio Gaussian distribution, the second Gaussian cloud parameter of the signal reception power Gaussian distribution, and the third Gaussian cloud parameter of the signal reception quality Gaussian distribution can be obtained; the Gaussian cloud parameter of each Gaussian distribution is respectively calculated to obtain the conceptual ambiguity value, that is, the first conceptual ambiguity value, the second conceptual ambiguity value, and the third conceptual ambiguity value are calculated. Then, the first conceptual ambiguity value, the second conceptual ambiguity value, and the third conceptual ambiguity value are averaged to obtain the target conceptual ambiguity value; Gaussian distribution fitting is performed according to the Gaussian cloud parameter corresponding to the target conceptual ambiguity value to obtain the link layer state parameter Gaussian distribution.

[0144] It should be noted that the target concept confusion value is the averaged concept confusion value (Confusion Degree, CD). In the adaptive Gaussian cloud change model, the concept confusion value can be calculated by entropy (En) and super entropy (He). For example, the calculation formula of the concept confusion value is: CD = 3He / En. Among them, CD represents the concept confusion value, En represents entropy, and He represents super entropy.

[0145] See also Figure 8 , in some embodiments, the predicted packet loss rate is obtained by predicting the packet loss rate of the link layer state parameters using a preset adaptive Gaussian cloud transformation model;

[0146] Step 105 may include but is not limited to steps 601 to 602:

[0147] Step 601, using a preset Bayesian neural network classification model, classify network quality according to predicted packet loss rate, data round-trip delay and network bandwidth to obtain a target network quality level;

[0148] Step 602: Determine the target bit rate at the current time according to the target network quality level.

[0149] The advantage of this embodiment is that by classifying the network quality according to the three network performance indicators of different angles, namely, the predicted packet loss rate, the round-trip delay of data, and the network bandwidth, the target network quality level is obtained, and the current state of the network can be comprehensively evaluated. Then, according to the target network quality level, the target bit rate at the current time is determined, so as to maintain the stability and efficiency of data transmission in a changeable wireless network environment, reduce the data transmission delay, and improve the user experience.

[0150] In step 601 of some embodiments, the Bayesian neural network classification model is a machine learning model that combines Bayesian theory and neural networks and can classify data under uncertain conditions. In an embodiment of the present application, the Bayesian neural network classification model is used to determine the network quality level based on the network layer state parameters.

[0151] In one embodiment, before the predicted packet loss rate, data round-trip delay and network bandwidth are input into the Bayesian neural network classification model, the predicted packet loss rate, data round-trip delay and network bandwidth can be converted into preset data formats respectively. For example, the unit of the data round-trip delay can be converted into a unified unit (such as seconds, milliseconds, etc.) for subsequent model processing.

[0152] It should be noted that the target network quality level is used to characterize the network communication quality between the sender and the receiver, that is, the wireless network environment in which the sender is located. For example, the target network quality level can be any of the following: very good, good, good, average, poor, and very poor. The network quality level can also be divided in other ways, not limited to this.

[0153] In some embodiments, for example, the value of the network quality level can be any of the following: good, medium, and poor. If the predicted packet loss rate is 5%, the data round-trip delay is 30ms, and the network bandwidth is 5Mbps, the target network quality level output by the Bayesian neural network classification model is poor. If the predicted packet loss rate is 3%, the data round-trip delay is 20ms, and the network bandwidth is 7Mbps, the target network quality level output by the Bayesian neural network classification model is medium. If the predicted packet loss rate is 1%, the data round-trip delay is 10ms, and the network bandwidth is 10Mbps, the target network quality level output by the Bayesian neural network classification model is good.

[0154] In step 602 of some embodiments, the target network quality level has a corresponding relationship with the value range of the target bit rate, and the target network quality level provides a clear adjustment basis for the adjustment of the target bit rate. For example, if the target network quality level is "poor", a bit rate belonging to a lower bit rate threshold range is adopted, such as [1,3), in Mbps. If the target network quality level is "medium", a bit rate belonging to a medium bit rate threshold range is adopted, such as [3,5) Mbps. If the target network quality level is "good", a bit rate belonging to a higher bit rate threshold range is adopted, such as [5,10] Mbps.

[0155] In some embodiments, before step 601, the data processing method may further include:

[0156] Get sample network layer status parameters;

[0157] Input the sample network layer state parameters into the preset Bayesian neural network classification model to obtain the loss function value;

[0158] The parameters of the Bayesian neural network classification model are adjusted according to the loss function value to obtain the trained Bayesian neural network classification model.

[0159] The advantage of this embodiment is that the sample network layer state parameters are input into a preset initial Bayesian neural network classification model to obtain a loss function value, and the parameters of the initial Bayesian neural network classification model are adjusted according to the loss function value to obtain a Bayesian neural network classification model that can accurately judge the network quality, so as to improve the accuracy of the target network quality level, thereby adjusting the target bit rate in real time according to the target network quality level, so that the data encoding method adapts to the current network environment, improves the data transmission stability, and reduces the data transmission delay.

[0160] It should be noted that the sample network layer state parameters are parameters used to train the initial Bayesian neural network classification model. The sample network layer state parameters are of the same type as the target network layer state parameters, and the sample network layer state parameters include three types of parameters: sample packet loss rate, sample round trip delay, and sample bandwidth.

[0161] In some embodiments, the sample network layer state parameters can be obtained from a network database, or from a historical network parameter record. For example, the historical parameters of the sender corresponding to the target network layer state parameters can be obtained from the historical network parameter record as the sample network layer state parameters, thereby improving the pertinence of the trained Bayesian neural network classification model, so that the Bayesian neural network classification model can accurately determine the network environment in which the sender is located. In another embodiment, the historical parameters of other senders can also be used as sample network layer state parameters without limitation.

[0162] See also Fig. 9 In some embodiments, the wireless network environment can be jointly evaluated by a packet loss rate evaluation model and a network quality evaluation model to adjust the bit rate based on the wireless network environment. For example, the signal-to-noise ratio, signal reception power, and signal reception quality are obtained. Then, the signal-to-noise ratio, signal reception power, and signal reception quality are input into the packet loss rate evaluation model to calculate the packet loss rate, and the packet loss rate (i.e., the predicted packet loss rate) is output. The round-trip delay (i.e., the data round-trip delay) and the network bandwidth are obtained. In addition, the packet loss rate, round-trip delay, and network bandwidth are input into the network quality evaluation model to classify the network quality, and the network quality level (i.e., the target network quality level) is output so as to adjust the bit rate according to the network quality level.

[0163] Specifically, the packet loss rate assessment model may include an adaptive Gaussian cloud transformation model, and the network quality assessment model may include a Bayesian neural network classification model.

[0164] See also Fig.10 In some embodiments, the initial data includes an initial video; step 602 may include, but is not limited to, steps 701 to 702:

[0165] Step 701, selecting a target resolution and a target frame rate corresponding to a target network quality level from a preset network quality coding relationship table;

[0166] Step 702, calculate the video bit rate according to the target resolution and the target frame rate to obtain the target bit rate.

[0167] The advantage of this embodiment is that after obtaining the target network quality level at the current time, the target resolution and target frame rate corresponding to the target network quality level are selected from the preset network quality coding relationship table, and the target bit rate at the current time is calculated based on the target resolution and target frame rate. The encoding parameters of the video can be dynamically adjusted according to the current network quality, thereby reducing the transmission delay and improving the transmission stability in the process of transmitting the encoded target data, and adapting to the changing wireless network environment.

[0168] In step 701 of some embodiments, the network quality coding relationship table includes at least two correspondences between the target network quality level and the resolution and frame rate. For example, the target network quality level may include any one of good, medium, and poor. In the network quality coding relationship table, if the network quality level is good, the resolution corresponding to the network quality level is 4K and the frame rate is 120fps. If the network quality level is poor, the resolution corresponding to the network quality level is 360p and the frame rate is 30fps.

[0169] In step 702 of some embodiments, the target resolution and the target frame rate may be multiplied to obtain the target bit rate. The bit rate may also be calculated in other ways. For example, when the initial data is compressed, the effect of compression efficiency on the target bit rate may be considered in the process of calculating the target bit rate. This is not limited in the embodiments of the present application.

[0170] See also Fig.11 , the embodiment of the present application also provides a data processing system, the data processing system includes: a sending end, a server and a receiving end; wherein the sending end executes the above-mentioned data processing method;

[0171] The server is wirelessly connected with the sending end and the receiving end;

[0172] The sending end is used to send the target data to the server; the receiving end is used to receive the target data from the server and decode the target data to obtain the initial data corresponding to the target data.

[0173] Understandably, Fig.11 The arrow in is used to indicate the transmission direction of the target data. In addition, the data processing system may have other data transmission directions, for example, the receiving end may also send data or instructions to the sending end, which is not limited in the embodiments of the present application.

[0174] The specific implementation of the data processing system is basically the same as the specific implementation of the above-mentioned data processing method, and will not be repeated here.

[0175] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above data processing method when executing the computer program. The electronic device may include any intelligent terminal such as a tablet computer and a car computer.

[0176] See also Fig.12 , Fig.12 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0177] The processor 1201 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0178] The memory 1202 may be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1202 may store an operating system and other application programs. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1202, and the processor 1201 calls and executes the data processing method of the embodiments of this application;

[0179] Input / output interface 1203, used to implement information input and output;

[0180] The communication interface 1204 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0181] A bus 1205 that transmits information between various components of the device (e.g., the processor 1201, the memory 1202, the input / output interface 1203, and the communication interface 1204);

[0182] The processor 1201 , the memory 1202 , the input / output interface 1203 and the communication interface 1204 are connected to each other in communication within the device via the bus 1205 .

[0183] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and the computer program implements the above-mentioned data processing method when executed by a processor.

[0184] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0185] It should be noted that the non-Company software tools or components appearing in the embodiments of the present application are merely examples and do not represent actual use.

[0186] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0187] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0188] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0190] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0191] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0192] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0193] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0194] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0195] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0196] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A data processing method, characterized in that: Applied to the sending end, the method includes: Acquire initial data, and record the time when the initial data is acquired to obtain the current time; Acquire the link layer state parameters at the current time through the link perception layer of the sending end; Acquire the data round-trip delay and network bandwidth at the current time through the network perception layer of the sending end; Predicting the packet loss rate according to the link layer state parameter to obtain a predicted packet loss rate; Generate a bit rate according to the predicted packet loss rate, the data round-trip delay and the network bandwidth to obtain the target bit rate at the current time; The initial data is encoded according to the target code rate to obtain target data, and the target data is sent to a receiving end.

2. The method according to claim 1, characterized in that Before generating a bit rate according to the predicted packet loss rate, the data round-trip delay, and the network bandwidth to obtain the target bit rate at the current time, the method further includes: Comparing the predicted packet loss rate with a preset first packet loss rate threshold; If the predicted packet loss rate is greater than or equal to the first packet loss rate threshold, the initial data is encoded according to a preset first bit rate to obtain the target data; wherein the first bit rate is less than the target bit rate.

3. The method according to claim 1, characterized in that: Before generating a bit rate according to the predicted packet loss rate, the data round-trip delay, and the network bandwidth to obtain the target bit rate at the current time, the method further includes: Comparing the predicted packet loss rate with a preset second packet loss rate threshold; If the predicted packet loss rate is less than or equal to the second packet loss rate threshold, the initial data is encoded according to a preset second bit rate to obtain the target data; wherein the second bit rate is greater than or equal to half of a preset maximum bit rate threshold.

4. The method according to any one of claims 1 to 3, characterized in that: The predicted packet loss rate is obtained by predicting the packet loss rate of the link layer state parameters using a preset adaptive Gaussian cloud transformation model; The generating a bit rate according to the predicted packet loss rate, the data round-trip delay and the network bandwidth to obtain the target bit rate at the current time includes: Using a preset Bayesian neural network classification model, classify the network quality according to the predicted packet loss rate, the data round-trip delay and the network bandwidth to obtain a target network quality level; The target bit rate at the current time is determined according to the target network quality level.

5. The method according to claim 4, characterized in that The initial data includes an initial video; The determining the target bit rate at the current time according to the target network quality level includes: Selecting a target resolution and a target frame rate corresponding to the target network quality level from a preset network quality coding relationship table; The video bit rate is calculated according to the target resolution and the target frame rate to obtain the target bit rate.

6. The method according to any one of claims 1 to 3, characterized in that: The step of predicting the packet loss rate according to the link layer state parameter to obtain the predicted packet loss rate includes: Through the preset adaptive Gaussian cloud transformation model, the link layer state parameters are transformed into Gaussian distribution to obtain the link layer state parameter Gaussian distribution; By using the adaptive Gaussian cloud transformation model, a membership degree is calculated according to the link layer state parameter Gaussian distribution and each of at least two preset link layer parameter thresholds to obtain a candidate membership degree; The adaptive Gaussian cloud transformation model is used to perform expected value mapping based on the maximum candidate membership and the link layer state parameter Gaussian distribution to obtain the predicted packet loss rate.

7. The method according to claim 6, characterized in that The link layer status parameters are at least two, and the link layer status parameters include signal-to-noise ratio, signal reception power, and signal reception quality; The performing Gaussian distribution conversion on the link layer state parameter to obtain the Gaussian distribution of the link layer state parameter includes: Performing a first Gaussian distribution conversion on each of the signal-to-noise ratios to obtain a Gaussian distribution of the signal-to-noise ratio; Performing a second Gaussian distribution conversion on each of the signal receiving powers to obtain a signal receiving power Gaussian distribution; Performing a third Gaussian distribution conversion on each of the signal reception qualities to obtain a signal reception quality Gaussian distribution; Gaussian distribution averaging is performed on the signal-to-noise ratio Gaussian distribution, the signal reception power Gaussian distribution, and the signal reception quality Gaussian distribution to obtain the link layer state parameter Gaussian distribution.

8. A data processing system, characterized in that: The data processing system comprises: a sending end, a server and a receiving end; wherein the sending end executes the data processing method according to any one of claims 1 to 7; The server is wirelessly connected with the sending end and the receiving end; The sending end is used to send the target data to the server; the receiving end is used to receive the target data from the server and decode the target data to obtain initial data corresponding to the target data.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the data processing method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the data processing method according to any one of claims 1 to 7 is implemented.

Images