Data transmission method and device, nonvolatile storage medium and electronic equipment

Abstract

The invention discloses a data transmission method and device, a nonvolatile storage medium and electronic equipment. The method comprises the steps that a target path between a server and terminal equipment is determined, and in the target path, network performance parameters of data transmitted by the server and the terminal equipment meet preset conditions; in a preset detection period, according to the change condition of the network performance parameters in the target path, adjusting a preset adaptive factor to obtain a target adaptive factor; determining a data transmission rate between the server and the terminal equipment according to the target adaptive factor and a data transmission bandwidth between the server and the terminal equipment; and sending the data transmission rate to the server, the data transmission rate being used for indicating the server to perform data transmission with the terminal device based on the data transmission rate. According to the invention, the technical problem that the transmission efficiency is unstable when the server and the terminal equipment carry out data interaction is solved.

Description

Technical Field

[0001] The present application relates to the field of cloud computing technology, and more specifically, to a data transmission method and device, a non-volatile storage medium, and an electronic device. Background Art

[0002] Desktop virtualization technology is based on remote desktop technology, and its core function is to achieve remote execution of applications. Figure 1 As shown, in the desktop virtual environment, multiple virtual machines are created on the cloud server, each of which runs a customized operating system and is provided to users.

[0003] The user inputs instructions through the peripheral device, and the cloud server performs all computing tasks and feeds back the results to the user through the network in the form of screen updates. This method matches the computing tasks of different devices with their computing capabilities, which not only makes rational use of resources, but also improves the flexibility of operating system access, while reducing operating costs and security risks.

[0004] However, the user experience quality of desktop virtualization is highly dependent on the stability of the network environment. When the network condition is poor, the performance of the desktop virtualization system will be significantly reduced, mainly manifested in the slowdown of screen update speed. Screen update transmission is very sensitive to latency because any user operation needs to be responded to and displayed on the screen as soon as possible. If the screen update is lost or delayed during the transmission process, the result seen by the user will be inconsistent with the result on the cloud server, thus affecting the user experience.

[0005] In summary, no effective solution has been proposed for the above problems. Summary of the invention

[0006] The embodiments of the present application provide a data transmission method and apparatus, a non-volatile storage medium, and an electronic device to at least solve the technical problem of unstable transmission efficiency when a server and a terminal device interact with each other.

[0007] According to one aspect of an embodiment of the present application, a data transmission method is provided, including: determining a target path between a server and a terminal device, wherein, in the target path, network performance parameters of data transmitted between the server and the terminal device meet preset conditions; within a preset detection period, adjusting a preset adaptive factor according to changes in the network performance parameters in the target path to obtain a target adaptive factor; determining a data transmission rate between the server and the terminal device according to the target adaptive factor and a data transmission bandwidth between the server and the terminal device; and sending the data transmission rate to the server, wherein the data transmission rate is used to indicate that the server transmits data with the terminal device based on the data transmission rate.

[0008] Optionally, adjusting the preset adaptive factor according to changes in network performance parameters in the target path includes: detecting changes in network performance parameters in the target path, wherein the network performance parameters include at least one of the following: bandwidth, latency, and packet loss rate; if the parameter value of the network performance parameter in the (i+1)th detection cycle is greater than the parameter value of the network performance parameter in the (i)th detection cycle, and the difference between the parameter value of the network performance parameter in the (i+1)th detection cycle and the parameter value of the network performance parameter in the (i)th detection cycle does not exceed a first preset threshold, based on proportional control in a preset PID controller, reducing the value of the preset adaptive factor, wherein i is a positive integer.

[0009] Optionally, the preset adaptive factor is adjusted according to the change of the network performance parameter in the target path, including: if the parameter value of the network performance parameter within a preset number of detection cycles is greater than a second preset threshold, based on the integral control in the preset PID controller, the value of the preset adaptive factor is reduced by a first preset rate; if the parameter value of the network performance parameter within the j+1th detection cycle is greater than the parameter value of the network performance parameter within the jth detection cycle, and the difference between the parameter value of the network performance parameter within the j+1th detection cycle and the parameter value of the network performance parameter within the jth detection cycle exceeds the first preset threshold, based on the differential control in the preset PID controller, the value of the preset adaptive factor is reduced by a second preset rate.

[0010] Optionally, adjusting the preset adaptive factor according to the change of the network performance parameters in the target path to obtain the target adaptive factor includes: obtaining an initialization action value table, wherein the initialization action value table includes multiple two-dimensional arrays and an action value function corresponding to each two-dimensional array, and each two-dimensional array includes: a state parameter and an action parameter, the state parameter is a network performance parameter, and the action parameter is an adjusted preset adaptive factor; determining a reward function according to the network performance parameter, a first delay, and a second delay, wherein the first delay is the time delay between the target object performing a writing operation and the display board displaying the writing result in a cloud desktop conference system in a virtualized cloud desktop running in a terminal device, and the second delay is the transmission time delay of voice data and / or video data between two terminal devices in the cloud desktop conference system; using a Q learning algorithm to update the initialization action value table according to the reward function to obtain the target adaptive factor.

[0011] Optionally, the data transmission rate between the server and the terminal device is determined according to the target adaptive factor and the data transmission bandwidth between the server and the terminal device, including: obtaining a conference tag of the target conference in the cloud desktop conference system, wherein the conference tag is used to characterize the importance of the conference; determining a first preset weight corresponding to the conference tag in the cloud desktop management system, using the first preset weight corresponding to the conference tag to weightedly process the target adaptive factor, and determining the data transmission rate between the server and the terminal device according to the weighted target adaptive factor and the data transmission bandwidth.

[0012] Optionally, determining the target path between the server and the terminal device includes: determining target data corresponding to the port of the virtualized cloud desktop running in the terminal device in the data transmitted between the server and the terminal device; and using an open shortest path first protocol to determine the target path for transmitting the target data between the server and the terminal device.

[0013] Optionally, the data transmission rate between the server and the terminal device is determined based on the target adaptive factor and the data transmission bandwidth between the server and the terminal device, including: obtaining the process name corresponding to the application running in the virtualized cloud desktop running in the terminal device; determining a second preset weight corresponding to the process name in the cloud desktop management system, using the second preset weight corresponding to the process name to weightedly process the target adaptive factor, and determining the data transmission rate between the server and the terminal device based on the weighted target adaptive factor and the data transmission bandwidth.

[0014] According to another aspect of the embodiment of the present application, a data transmission device is also provided, including: a first determination module, used to determine a target path between a server and a terminal device, wherein, in the target path, network performance parameters of data transmitted between the server and the terminal device meet preset conditions; an acquisition module, used to adjust a preset adaptive factor according to changes in the network performance parameters in the target path within a preset detection period to obtain a target adaptive factor; a second determination module, used to determine a data transmission rate between the server and the terminal device according to the target adaptive factor and a data transmission bandwidth between the server and the terminal device; a sending module, used to send the data transmission rate to the server, wherein the data transmission rate is used to instruct the server to perform data transmission with the terminal device based on the data transmission rate.

[0015] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, the storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the above data transmission method.

[0016] According to another aspect of the embodiments of the present application, there is further provided an electronic device, including: a memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the above data transmission method is executed when the program is run.

[0017] According to yet another aspect of the embodiments of the present application, a computer program is further provided, wherein the above data transmission method is implemented when the computer program is executed by a processor.

[0018] According to another aspect of the embodiments of the present application, a computer program product is provided, which includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above data transmission method is implemented.

[0019] In an embodiment of the present application, a target path between a server and a terminal device is determined, wherein, in the target path, network performance parameters of data transmitted between the server and the terminal device meet preset conditions; within a preset detection period, a preset adaptive factor is adjusted according to changes in the network performance parameters in the target path to obtain a target adaptive factor; the data transmission rate between the server and the terminal device is determined according to the target adaptive factor and the data transmission bandwidth between the server and the terminal device; the data transmission rate is sent to the server, wherein the data transmission rate is used to indicate a manner in which the server transmits data with the terminal device based on the data transmission rate, thereby achieving the purpose of automatically adjusting the data transmission rate according to changes in the network performance parameters in the target path, thereby achieving the technical effect of improving the data transmission efficiency when the server and the terminal device perform data interaction, and further solving the technical problem of unstable transmission efficiency when the server and the terminal device perform data interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 A schematic diagram of a communication protocol between the cloud and the terminal is shown;

[0022] Figure 2 is a flow chart of a data transmission method according to an embodiment of the present application;

[0023] Figure 3 A cloud terminal fusion topology diagram is shown;

[0024] Figure 4 is a cloud terminal fusion topology diagram according to an embodiment of the present application;

[0025] Figure 5 This is a cloud-management fusion architecture diagram according to an embodiment of the present application;

[0026] Figure 6 is a schematic diagram of real-time flow monitoring according to an embodiment of the present application;

[0027] Figure 7 is a schematic diagram of a method for adjusting a preset adaptive factor according to an embodiment of the present application;

[0028] Figure 8 is a schematic diagram of adjusting the data transmission rate between a server and a terminal device according to an embodiment of the present application;

[0029] Fig. 9 is a simulation diagram of pacing gain optimization according to an embodiment of the present application;

[0030] Fig.10 is a schematic diagram of an average total reward per cycle according to an embodiment of the present application;

[0031] Fig.11 is a structural diagram of a data transmission device according to an embodiment of the present application;

[0032] Fig.12 It is a hardware structure block diagram of a computer terminal according to a data transmission method of an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims 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.

[0035] According to an embodiment of the present application, a method embodiment of a data transmission method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] It should be noted that Figure 3 A cloud terminal fusion topology diagram is shown. Figure 4 is a cloud terminal fusion topology diagram according to an embodiment of the present application, comprising Figure 4 It can be seen that compared with the relevant cloud-terminal fusion topology diagram, the embodiment of the present application proposes an intelligent management platform, wherein the data transmission method in the embodiment of the present application can be deployed on the intelligent management platform. Figure 5 This is a cloud-management fusion architecture diagram according to an embodiment of the present application, using Figure 5 The architecture shown in the figure can be managed by the intelligent management platform Figure 2 The steps shown ensure low latency in network communication between the cloud desktop server and terminal devices. Figure 2 is a flow chart of a data transmission method according to an embodiment of the present application. Figure 2 As shown, the method includes the following steps.

[0037] Step S202, determining a target path between the server and the terminal device, wherein, in the target path, network performance parameters of data transmitted between the server and the terminal device meet preset conditions.

[0038] In cloud desktop services, the data transmission performance between the server and the terminal device directly affects the user experience. In order to ensure the efficiency and stability of data transmission, it is necessary to select a target path between the cloud server and the terminal device whose network performance parameters meet the preset conditions. This embodiment will show how to determine such a target path through the intelligent management platform, combined with real-time network monitoring and path calculation strategy.

[0039] 1. Real-time network monitoring: Figure 6As shown in the figure, the intelligent management platform uses Cacti to monitor real-time traffic and evaluate the link performance between the server and the terminal device. Cacti is an open source network traffic monitoring tool that uses RRDTool for data storage and graphics generation. It can monitor the traffic of the network interface in real time, including upload and download rates, data packet statistics and other information. In the cloud desktop network transmission adaptive optimization method of the smart cloud screen, Cacti can be used to monitor the traffic of the smart cloud screen port in real time, identify key traffic types and give priority to them, which is the basis for ensuring the stable operation of the cloud desktop service under different network conditions. Through Cacti, the intelligent management platform can obtain real-time network bandwidth usage, packet loss rate, delay and other key parameters, so as to dynamically adjust the network strategy, optimize the data transmission path, and ensure the smoothness and low latency of video transmission.

[0040] When monitoring traffic, the intelligent cloud screen port traffic is specially identified and given a higher priority. Through real-time network monitoring, key network performance parameters such as link bandwidth, delay, and packet loss rate are collected.

[0041] 2. Traffic type identification and priority allocation: The intelligent management platform identifies the data transmission type, such as video streaming, interactive data, file transfer, etc., and assigns priority to the smart cloud screen traffic according to the type. Priority allocation ensures that the smart cloud screen traffic can be transmitted first when congested, reducing the waiting time of data packets in the queue.

[0042] 3. Path calculation: Use OSPF protocol to calculate the optimal routing path (target path) from the server to the terminal device. OSPF protocol can select the link with the lowest cost and shortest path based on the link state database.

[0043] Among them, OSPF is a link state routing protocol that calculates the shortest path based on the Dijkstra algorithm (also known as the SPF algorithm). The following are the basic steps for calculating the optimal routing path using the OSPF protocol: First, the OSPF protocol enables routers to exchange link state information. Each router sends LSAs to describe the link status between it and its neighbor routers, including the cost (or metric, such as bandwidth, delay, or packet loss rate) of the link. Secondly, the router uses the received LSAs to build a complete network topology map, namely the LSDB. This database contains the link state information of all routers in the network. Thirdly, based on the LSDB, the router runs the Dijkstra algorithm to calculate the shortest path from itself to all other nodes in the network. The goal of the algorithm is to find the path with the lowest total cost (or metric). Then, the calculated shortest path is recorded in the routing table. The routing table contains the best next-hop router information to reach each destination. Finally, when the server needs to send data to the terminal device, it queries the routing table to query the optimal path to the terminal device. If the network conditions change, such as link failure or bandwidth changes, the OSPF protocol automatically updates the LSDB and recalculates the shortest path, thereby dynamically adjusting the route.

[0044] Preferably, considering the dynamic changes of the path, the intelligent management platform can update the link state database in real time to ensure the accuracy and timeliness of the path calculation results.

[0045] Step S204: within a preset detection period, according to changes in network performance parameters in the target path, adjust the preset adaptive factor to obtain a target adaptive factor.

[0046] It should be noted that the pacing rate formula in the BBR algorithm is sending rate (t) = k·2 t , where k is a constant scaling factor. This embodiment introduces a preset adaptive factor g, so that the pacing rate formula is changed to pacing rate (t) = g·est_bw (t), where est_bw (t) is the estimated bandwidth based on the BBR protocol.

[0047] In the traditional BBR algorithm, the estimated bandwidth est_bw(t) is the amount of round-trip data transmission:

[0048] est_bw(t) = data transmitted in a round trip (t), or est_bw(t) = data sent in a round trip (t-1).

[0049] In this embodiment, the data transmitted back and forth is expressed in an integral form:

[0050] Therefore, the new pacing rate can be expressed as:

[0051] Further simplification gives:

[0052] By calculating the integral, we can get:

[0053] In the cloud computer transmission scenario, the adaptive pacing gain design will dynamically adjust the value of g according to the real-time network conditions, so as to better adapt to different network conditions and optimize bandwidth utilization and data transmission efficiency.

[0054] Step S206: determining the data transmission rate between the server and the terminal device according to the target adaptive factor and the data transmission bandwidth between the server and the terminal device.

[0055] Specifically, the intelligent management platform obtains the real-time network performance parameters in the target path at the beginning of the preset detection cycle. Network performance parameters can be obtained through network monitoring tools or devices, such as using the SNMP protocol to monitor the status of network devices, or obtaining real-time performance information of the link through active detection technology. Then, the platform compares these real-time parameters with the preset network performance thresholds to evaluate the network status. For example, if the bandwidth is detected to be lower than the threshold, or the delay and packet loss rate are higher than the threshold, the system will consider that the current network condition is poor and the adaptive factor needs to be adjusted. Then, according to the changes in the network performance parameters, the intelligent management platform adjusts the preset adaptive factor g. The adjustment strategy can be based on the PID controller proposed above or other appropriate algorithms, such as adaptive adjustment based on neural networks. For example, when the bandwidth is limited, the value of g may be reduced to reduce the data transmission rate and avoid network congestion; when the network condition is stable, the value of g can be appropriately increased to improve the transmission efficiency.

[0056] Alternatively, the pacing rate between the server and the terminal device is determined based on the target adaptive factor and the data transmission bandwidth between the server and the terminal device. The pacing rate is used to control the rate at which data packets are sent to avoid network congestion and excessive use of bandwidth resources. The pacing rate refers to the rate at which the network sender sends data packets at a certain time interval or frequency when transmitting data. This rate control can prevent a large number of data packets from flooding into the network in a short period of time, causing network buffer overflow and data packet loss, which in turn causes network congestion. By adjusting the pacing rate, the network transmission algorithm can slow down the data transmission speed when congestion occurs to avoid further deterioration of the network condition; after the congestion is relieved, the rate is gradually increased to make full use of the available bandwidth.

[0057] Step S208: sending the data transmission rate to the server, wherein the data transmission rate is used to instruct the server to perform data transmission with the terminal device based on the data transmission rate.

[0058] In general, under the technical framework of the present invention, the embodiments relate to a data transmission rate dynamic feedback mechanism for optimizing the data transmission process between a cloud server and a terminal device. The core of this mechanism is that the terminal device can monitor its current network status in real time, including but not limited to bandwidth, delay and packet loss rate, and convert this information into an indicator of data transmission rate, and then send the indicator to the cloud server, so that the server can adjust its data transmission strategy based on the real-time data transmission rate information.

[0059] The terminal device is equipped with an intelligent network monitoring module, which can monitor key parameters such as network bandwidth, delay and packet loss rate in real time. These parameters will serve as the basis for calculating the data transmission rate. For example, when the terminal detects that the available bandwidth of the current network environment is 5Mbps, the average delay is 100ms, and the packet loss rate is 1%, the intelligent monitoring module will calculate an appropriate data transmission rate based on this information.

[0060] Furthermore, based on the monitored network conditions, the intelligent monitoring module uses a preset algorithm to calculate the most suitable data transmission rate at the moment. The algorithm takes into account all monitored parameters to ensure that the data transmission rate is neither too high to increase packet loss nor too low to affect data transmission efficiency. For example, the algorithm uses the available bandwidth of 5Mbps as the theoretical maximum transmission rate, and then adjusts it according to the delay and packet loss rate, and finally obtains an optimal data transmission rate under the current network conditions. The calculated data transmission rate is then sent to the cloud server through a secure communication channel. This channel may utilize the multi-path load balancing and integrated VPN functions of the previously mentioned intelligent management platform to ensure the security and low latency of information transmission. After receiving the data transmission rate information, the server will use it as the basis for adjusting its own data transmission strategy.

[0061] Furthermore, after receiving the data transmission rate information sent by the terminal device, the cloud server will dynamically adjust its data transmission rate based on this information. For example, if the data transmission rate indication received by the server is 4Mbps, the server will adjust its transmission rate to 4Mbps or slightly lower to avoid network congestion. At the same time, the server will also optimize the size and transmission frequency of its data packets based on the delay and packet loss rate information to further improve transmission efficiency.

[0062] It should be noted that the above mechanism is not a one-time operation, but a continuous cycle. The terminal device regularly re-monitors the network status, recalculates the data transmission rate according to the new network conditions, and sends it to the cloud server again. The server will adjust its sending strategy according to the new rate information, forming a dynamic feedback and adjustment cycle to ensure the efficiency and stability of data transmission.

[0063] According to the above steps, a target path between a server and a terminal device is determined, wherein, in the target path, network performance parameters of data transmitted between the server and the terminal device meet preset conditions; within a preset detection period, a preset adaptive factor is adjusted according to changes in the network performance parameters in the target path to obtain a target adaptive factor; a data transmission rate between the server and the terminal device is determined according to the target adaptive factor and the data transmission bandwidth between the server and the terminal device; and the data transmission rate is sent to the server, wherein the data transmission rate is used to indicate a method in which the server transmits data to the terminal device based on the data transmission rate, thereby achieving the purpose of automatically adjusting the data transmission rate according to changes in the network performance parameters in the target path, thereby achieving the technical effect of improving the data transmission efficiency when the server and the terminal device perform data interaction.

[0064] The following Figure 2 The steps shown are exemplary and explanatory.

[0065] According to some optional embodiments of the present application, adjusting the preset adaptive factor according to changes in network performance parameters in the target path can be achieved by the following method: detecting changes in network performance parameters in the target path, wherein the network performance parameters include at least one of the following: bandwidth, latency, and packet loss rate; if the parameter value of the network performance parameter in the i+1th detection cycle is greater than the parameter value of the network performance parameter in the ith detection cycle, and the difference between the parameter value of the network performance parameter in the i+1th detection cycle and the parameter value of the network performance parameter in the ith detection cycle does not exceed a first preset threshold value, based on the proportional control in the preset PID controller, reducing the value of the preset adaptive factor, wherein i is a positive integer.

[0066] For example, assume that the cloud desktop system of operator A is providing services to multiple remote office users. The intelligent management platform is deployed on each cloud desktop server, responsible for real-time monitoring of the data transmission rate between the terminal device and the target path, and detecting changes in network performance parameters in the target path, including but not limited to bandwidth, delay and packet loss rate. Specifically, the preset adaptive factor can be adjusted by the following method: 1. Each terminal device periodically (for example, every 5 seconds) reports its data transmission rate to the corresponding cloud desktop server. The intelligent management platform receives this rate information and compares it with the data of the previous detection cycle. 2. The intelligent management platform simultaneously detects the network performance parameters in the target path (i.e., the connection path between the terminal device and the cloud desktop server), including bandwidth, delay and packet loss rate. These parameters are recorded in the platform's database for subsequent analysis. 3. If in the second detection cycle, the parameter value of any of the above network performance parameters is greater than the parameter value in the first detection cycle, and the difference between the parameter values ​​in the two detection cycles does not exceed the first preset threshold (for example, the bandwidth changes by no more than 5%, the delay increases by no more than 10ms, and the packet loss rate increases by no more than 0.5%), the platform will trigger the proportional control part in the PID controller. 4. When these subtle but steady increases in network performance parameters are detected, the platform automatically adjusts the value of the adaptive factor g based on the proportional control principle of the PID controller. Specifically, the g value will decrease according to the proportion of the parameter change. For example, if the bandwidth increases by 3%, the g value may decrease by 1.5%; if the latency increases by 8ms, the g value may decrease by 0.8%. The purpose of this adjustment strategy is to ensure data transmission efficiency and stability. By reducing the g value, the data transmission rate will be adjusted more conservatively, avoiding sudden increases in data transmission rates that cause network congestion and packet loss, which in turn affects video transmission quality and user experience.

[0067] In summary, the intelligent management platform will continuously monitor changes in network performance parameters and dynamically adjust the value of the preset adaptive factor g according to real-time conditions. This continuous monitoring and adjustment capability enables the cloud desktop system to quickly adapt to minor changes in the network environment and maintain efficient and stable data transmission.

[0068] Figure 7 is a schematic diagram of a method for adjusting a preset adaptive factor according to an embodiment of the present application, such as Figure 7 As shown in the figure, the change of the adaptive factor g in each simulation round is intuitively shown. Through the proportional, integral and differential control of the PID controller, it can respond to changes in network conditions in a timely manner and dynamically adjust the value of g.

[0069] Figure 8 is a schematic diagram of adjusting the data transmission rate between a server and a terminal device according to an embodiment of the present application, such as Figure 8As shown in the figure, the change of data transmission speed in each simulation round is intuitively shown. By dynamically adjusting the adaptive factor g, the data transmission speed can respond to network changes in a timely manner and optimize data transmission efficiency and stability.

[0070] Furthermore, adjusting the preset adaptive factor according to the change of the network performance parameter in the target path can be achieved by the following method: if the parameter value of the network performance parameter within a preset number of detection cycles is greater than a second preset threshold, based on the integral control in the preset PID controller, the value of the preset adaptive factor is reduced by a first preset rate; if the parameter value of the network performance parameter within the j+1th detection cycle is greater than the parameter value of the network performance parameter within the jth detection cycle, and the difference between the parameter value of the network performance parameter within the j+1th detection cycle and the parameter value of the network performance parameter within the jth detection cycle exceeds the first preset threshold, based on the differential control in the preset PID controller, the value of the preset adaptive factor is reduced by a second preset rate.

[0071] For example, within a preset number of detection cycles (e.g., 5 consecutive cycles), the network performance parameters, such as changes in packet loss rate, are continuously monitored. If the parameter value of the packet loss rate continues to exceed the second preset threshold value (e.g., the packet loss rate exceeds 5%) within these detection cycles, the system will gradually reduce the value of g by using a first preset rate (e.g., reducing the g value by 10% each time) based on the integral control part in the PID controller. This step is to cope with the long-term decline in network performance, and the adjustment of the g value is accumulated through integral control until the network performance rises back below the preset threshold. Next, differential control is introduced for sudden changes in network conditions between detection cycles. For example, if the parameter value of the network performance parameter (e.g., packet loss rate) is 4% in the first detection cycle, and the parameter value suddenly increases to 8% in the second detection cycle, that is, the difference is 4%, and this difference exceeds the first preset threshold value (e.g., 3%), the system will quickly reduce the value of g by using a second preset rate (e.g., reducing the g value by 20% each time) based on the differential control part in the PID controller to cope with sudden changes in the network and reduce the freeze and delay of video transmission.

[0072] According to some other optional embodiments of the present application, adjusting the preset adaptive factor according to the change of the network performance parameters in the target path to obtain the target adaptive factor can also be achieved by the following method: obtaining an initialization action value table, wherein the initialization action value table includes multiple two-dimensional arrays and an action value function corresponding to each two-dimensional array, and each two-dimensional array includes: a state parameter and an action parameter, the state parameter is a network performance parameter, and the action parameter is an adjustment of the preset adaptive factor; determining a reward function according to the network performance parameter, a first delay and a second delay, wherein the first delay is the time delay between the target object performing a writing operation and the display board displaying the writing result in a cloud desktop conferencing system in a virtualized cloud desktop running in a terminal device, and the second delay is the transmission time delay of voice data and / or video data between two terminal devices in the cloud desktop conferencing system; using a Q learning algorithm, updating the initialization action value table according to the reward function to obtain the target adaptive factor.

[0073] The following is a detailed introduction on how to apply the Q-learning algorithm in an actual cloud desktop conference system to dynamically adjust the adaptive factor g, optimize network transmission performance, and improve user experience. This embodiment mainly focuses on reducing the delay of writing operations (first delay) and the delay of voice / video data transmission (second delay) in the cloud desktop conference system by learning and adjusting the preset adaptive factor g through the Q-learning algorithm.

[0074] Step 1, assume that the following network performance parameters are used as state parameters: bandwidth (B), delay (D), packet loss rate (L). For each state parameter combination, three possible action parameters can be defined: increase the adaptive factor (g+), keep it unchanged (g=), and reduce the adaptive factor (g-). Each element in the initialization action value table represents the action value function Q(s,a) under a specific network state, where s is the state parameter and a is the action parameter.

[0075] Step 2: The reward function is designed as R(s,a)=f(B,D,L,T1,T2), where T1 is the first delay and T2 is the second delay. The function f can be a linear combination, for example:

[0076] R(s,a)=w1*B+w2*(-D)+w3*(-L)-w4*T1-w5*T2.

[0077] Among them, w1, w2, w3, w4, and w5 are weight factors, which indicate the contribution of different network performance parameters and delays to the reward function. The appropriate weight values ​​are determined through field tests to maximize the reward function.

[0078] Step 3: In each cloud desktop meeting, the system determines the current state s based on the real-time monitored network performance parameters (bandwidth, latency, packet loss rate), and calculates the reward value R(s',a') based on the state and action of the previous step. Then, the Q-learning algorithm is used to update the action value table. The specific formula is as follows:

[0079] Q(s,a)=Q(s,a)+α*r+γmax a′ Q(s′,a′)-Q(s,a)+

[0080] Among them, α is the learning rate, r is the discount factor, s′ is the new state after executing action a, a′ is the action executed in this state, and max a′ Q(s′,a′) is the maximum Q value of the next state.

[0081] Step 4: After updating the action value table, the system will select the action with the maximum Q value, that is, the best way to adjust the adaptive factor g. In each cycle, the value of the adaptive factor g is dynamically adjusted to optimize the network transmission performance of the cloud desktop conference system and reduce freezes and delays.

[0082] Fig. 9 is a simulation diagram of pacing gain optimization according to an embodiment of the present application, Fig.10 is a schematic diagram of an average total reward per cycle according to an embodiment of the present application, Fig. 9 and Fig.10 It can be seen that as the training process progresses, the total reward gradually increases and tends to be stable, indicating that the reinforcement learning algorithm has gradually learned the strategy of selecting the optimal bit rate under different network conditions.

[0083] Through simulation experiments, this embodiment verifies the superior performance of the rate adaptation algorithm based on reinforcement learning in cloud computer video conferencing and local terminal transmission. Experimental results show that compared with traditional algorithms, this embodiment can significantly improve the average bit rate of network transmission, reduce the number and time of freezes, and reduce transmission delays, thereby improving the user viewing experience. Specifically, in a low-bandwidth environment: the average bit rate is increased by about 25%, the number of freezes is reduced by 30%, and the transmission delay is reduced by 15%. In a high-latency environment: the average bit rate is increased by about 20%, the number of freezes is reduced by 25%, and the transmission delay is reduced by 20%. In a high packet loss rate environment: the average bit rate is increased by about 30%, the number of freezes is reduced by 35%, and the transmission delay is reduced by 25%.

[0084] In summary, through the Q-learning algorithm optimization of this embodiment, the preset adaptive factor g can be dynamically adjusted, significantly reducing the delay and jamming phenomenon in the cloud desktop conference system, and improving the efficiency of voice and video data transmission. This adaptive optimization method can adapt to various network conditions, thereby improving user experience and network transmission quality.

[0085] Furthermore, determining the data transmission rate between the server and the terminal device based on the target adaptive factor and the data transmission bandwidth between the server and the terminal device can be achieved by the following method: obtaining a conference tag of the target conference in the cloud desktop conference system, wherein the conference tag is used to characterize the importance of the conference; determining a first preset weight corresponding to the conference tag in the cloud desktop management system, using the first preset weight corresponding to the conference tag to weight the target adaptive factor, and determining the data transmission rate between the server and the terminal device based on the weighted target adaptive factor and the data transmission bandwidth.

[0086] It should be noted that in large enterprises or organizations, cloud desktop conference systems are used for daily communication, remote training, and key decision-making meetings. However, the network resource requirements of these meetings vary. Especially when the network bandwidth is limited, the fluency and stability of important meetings become particularly important. In order to meet this demand, this embodiment proposes an adaptive data transmission rate adjustment method based on conference tags and preset weights. Specifically, it includes the following steps:

[0087] Step 1: Before the meeting begins, the meeting organizer or the system will assign a meeting tag to each meeting. For example, "critical decision-making meeting" can be marked as "high priority", "daily communication" can be marked as "medium priority", and "remote training" can be marked as "low priority". These tags can be set manually or automatically based on the positions of the meeting participants, the criticality of the meeting content, etc.

[0088] Step 2: A weight table is preset in the cloud desktop management system. Each meeting tag corresponds to a different weight value. For example, the weight value of a "high priority" meeting is 0.8, the weight value of a "medium priority" meeting is 0.5, and the weight value of a "low priority" meeting is 0.2. These weight values ​​reflect the importance of the meeting and are used for subsequent weighted processing.

[0089] Step 3: When the meeting starts, the cloud desktop management system obtains the meeting tag and weights the target adaptive factor according to the corresponding preset weight. The target adaptive factor g is dynamically adjusted based on the network status and is learned through the Q-learning algorithm. The weighted processing formula can be expressed as: weighted target adaptive factor = g*first preset weight.

[0090] Step 4: The system determines the data transmission rate between the server and the terminal device based on the weighted target adaptive factor and the currently available data transmission bandwidth. Specifically, the weighted target adaptive factor is used as the input of the Q-learning algorithm to dynamically adjust the video transmission bit rate and network transmission control. At the same time, considering the limitation of network bandwidth, the system will determine a suitable transmission rate based on the bandwidth size and the weighted factor to ensure high-quality transmission of conference data.

[0091] Through the above-mentioned data transmission rate adjustment method based on conference tag weighted processing, the cloud desktop conference system can more intelligently manage and optimize network resources, ensure the smoothness and stability of important meetings, and provide users with a better service experience. It not only solves the shortcomings of the existing cloud conference system in network resource allocation, but also improves the overall performance of the system and user satisfaction.

[0092] In some optional embodiments of the present application, determining the data transmission rate between the server and the terminal device based on the target adaptive factor and the data transmission bandwidth between the server and the terminal device can be achieved by the following method: obtaining the process name corresponding to the application running in the virtualized cloud desktop running in the terminal device; determining the second preset weight corresponding to the process name in the cloud desktop management system, using the second preset weight corresponding to the process name to weightedly process the target adaptive factor, and determining the data transmission rate between the server and the terminal device based on the weighted target adaptive factor and the data transmission bandwidth.

[0093] In the cloud desktop environment running on the smart cloud screen terminal device, the operation of the application will generate corresponding processes. The cloud desktop management system can monitor these processes in real time and obtain their names. For example, when a user opens the video conferencing software in the cloud desktop environment, the system will identify the process names such as "Zoom" or "Teams". A weight table is pre-set in the cloud desktop management system, which lists the weight values ​​corresponding to various applications. These weight values ​​reflect the sensitivity and priority of the application to the network transmission rate. For example, video conferencing software may be assigned a higher weight value because they have higher requirements for real-time performance and bandwidth; while text processing software may be assigned a lower weight value because they have relatively low requirements for network conditions. When the system recognizes that an application is running, it will find the corresponding second preset weight according to the process name of the application and apply it to the adjustment of the target adaptive factor g. The adjustment formula of the weighted factor g can be expressed as (g'=g*w), where (g') is the weighted adaptive factor, (g) is the original adaptive factor, and (w) is the second preset weight corresponding to the application. The cloud desktop management system calculates the optimized data transmission rate based on the weighted adaptive factor (g') and the currently available data transmission bandwidth. The above calculation process takes into account the real-time status of the network, including bandwidth, delay and packet loss rate, as well as the application's demand for the network to ensure that data transmission is both efficient and stable.

[0094] For example, assume that in a cloud desktop environment, a user runs video editing software and text editing software at the same time. The process name of the video editing software is "Adobe Premiere Pro", which is assigned a higher second preset weight (w1 = 0.8); the process name of the text editing software is "Microsoft Word", which is assigned a lower second preset weight (w2 = 0.5). When the video editing software is running, the original adaptive factor (g = 0.6). After weighted processing, (g' = g*w1 = 0.6*0.8 = 0.48). Assuming that the current available bandwidth is (B = 10Mbps), the data transmission rate is (R = B*g' = 10Mbps*0.48 = 4.8Mbps), which meets the video editing software's requirements for high bandwidth and low latency. When the text editing software is running, the original adaptive factor (g = 0.6). After weighted processing, (g' = g*w2 = 0.6*0.5 = 0.3). Still assuming that the current available bandwidth is (B=10Mbps), the data transmission rate is (R=B*g'=10Mbps*0.3=3Mbps), which is low but sufficient for text editing software while being able to reserve more bandwidth for other applications.

[0095] By implementing the above strategies, we can ensure that the network requirements of key applications are met, while reasonably allocating bandwidth resources, avoiding the waste of network resources and further optimizing the user experience of cloud desktops.

[0096] Fig.11 is a structural diagram of a data transmission device according to an embodiment of the present application, such as Fig.11 As shown, the device comprises:

[0097] The first determination module 1102 is used to determine a target path between the server and the terminal device, wherein in the target path, a network performance parameter of data transmitted between the server and the terminal device meets a preset condition.

[0098] The acquisition module 1104 is used to adjust the preset adaptive factor according to the change of the network performance parameter in the target path within the preset detection period to obtain the target adaptive factor.

[0099] The second determination module 1106 is configured to determine a data transmission rate between the server and the terminal device according to the target adaptive factor and a data transmission bandwidth between the server and the terminal device.

[0100] The sending module 1108 is used to send the data transmission rate to the server, wherein the data transmission rate is used to instruct the server to perform data transmission with the terminal device based on the data transmission rate.

[0101] Optionally, the acquisition module 1104 is also used to perform the following steps: detecting changes in network performance parameters in the target path, wherein the network performance parameters include at least one of the following: bandwidth, delay, and packet loss rate; if the parameter value of the network performance parameter in the i+1th detection cycle is greater than the parameter value of the network performance parameter in the ith detection cycle, and the difference between the parameter value of the network performance parameter in the i+1th detection cycle and the parameter value of the network performance parameter in the ith detection cycle does not exceed a first preset threshold value, based on the proportional control in the preset PID controller, reducing the value of the preset adaptive factor, wherein i is a positive integer.

[0102] Optionally, the acquisition module 1104 is also used to perform the following steps: if the parameter value of the network performance parameter within a preset number of detection cycles is greater than a second preset threshold, based on the integral control in the preset PID controller, the value of the preset adaptive factor is reduced at a first preset rate; if the parameter value of the network performance parameter within the j+1th detection cycle is greater than the parameter value of the network performance parameter within the jth detection cycle, and the difference between the parameter value of the network performance parameter within the j+1th detection cycle and the parameter value of the network performance parameter within the jth detection cycle exceeds the first preset threshold, based on the differential control in the preset PID controller, the value of the preset adaptive factor is reduced at a second preset rate.

[0103] Optionally, the acquisition module 1104 is further used to perform the following steps: obtain an initialization action value table, wherein the initialization action value table includes multiple two-dimensional arrays and an action value function corresponding to each two-dimensional array, each two-dimensional array includes: a state parameter and an action parameter, the state parameter is a network performance parameter, and the action parameter is an adjustment preset adaptive factor; determine a reward function according to the network performance parameter, a first delay, and a second delay, wherein the first delay is the time delay between the target object performing a writing operation and the display board displaying the writing result in a cloud desktop conferencing system in a virtualized cloud desktop running in a terminal device, and the second delay is the transmission time delay of voice data and / or video data between two terminal devices in the cloud desktop conferencing system; adopt a Q learning algorithm to update the initialization action value table according to the reward function to obtain a target adaptive factor.

[0104] Optionally, the second determination module 1106 is also used to perform the following steps: obtaining a conference tag of a target meeting in the cloud desktop conference system, wherein the conference tag is used to characterize the importance of the meeting; determining a first preset weight corresponding to the conference tag in the cloud desktop management system, using the first preset weight corresponding to the conference tag to weightedly process the target adaptive factor, and determining the data transmission rate between the server and the terminal device based on the weighted target adaptive factor and the data transmission bandwidth.

[0105] Optionally, the first determination module 1102 is also used to perform the following steps: determining the target data corresponding to the port of the virtualized cloud desktop running in the terminal device in the data transmitted between the server and the terminal device; and using the open shortest path first protocol to determine the target path for transmitting the target data between the server and the terminal device.

[0106] Optionally, the second determination module 1106 is also used to perform the following steps: obtaining the process name corresponding to the application running in the virtualized cloud desktop running in the terminal device; determining the second preset weight corresponding to the process name in the cloud desktop management system, using the second preset weight corresponding to the process name to weightedly process the target adaptive factor, and determining the data transmission rate between the server and the terminal device based on the weighted target adaptive factor and the data transmission bandwidth.

[0107] It should be noted that the above Fig.11 The modules in the embodiment may be program modules (e.g., a set of program instructions for implementing a specific function) or hardware modules. For the latter, they may be expressed in the following forms, but are not limited thereto: the expression form of the above modules is a processor, or the functions of the above modules are implemented by a processor.

[0108] It should be noted that Fig.11 The preferred implementation of the illustrated embodiment can be found in Figure 2 The relevant description of the illustrated embodiment will not be repeated here.

[0109] Fig.12 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a data transmission method. Fig.12 As shown, the computer terminal 120 may include one or more (1202a, 1202b, ..., 1202n are used to illustrate) processors 1202 (the processor 1202 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1204 for storing data, and a transmission module 1206 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Fig.12 The structure shown is only for illustration and does not limit the structure of the above electronic device. Fig.12 More or fewer components as shown, or with Fig.12 Different configurations are shown.

[0110] It should be noted that the one or more processors 1202 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 120. As involved in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0111] The memory 1204 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the data transmission method in the embodiment of the present application. The processor 1202 executes various functional applications and data processing by running the software programs and modules stored in the memory 1204, that is, realizing the above-mentioned data transmission method. The memory 1204 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 1204 may further include a memory remotely arranged relative to the processor 1202, and these remote memories may be connected to the computer terminal 120 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.

[0112] The transmission module 1206 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 120. In one example, the transmission module 1206 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 1206 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0113] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 120 .

[0114] It should be noted that, in some optional embodiments, the above Fig.12 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Fig.12 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.

[0115] It should be noted that Fig.12 The computer terminal shown is used to execute Figure 2 The data transmission method shown, therefore the relevant explanations in the execution method of the above command are also applicable to the electronic device and will not be repeated here.

[0116] An embodiment of the present application further provides a non-volatile storage medium, which includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the above data transmission method.

[0117] A program for a non-volatile storage medium to perform the following functions: determining a target path between a server and a terminal device, wherein, in the target path, network performance parameters of data transmitted between the server and the terminal device meet preset conditions; adjusting a preset adaptive factor according to changes in the network performance parameters in the target path within a preset detection period to obtain a target adaptive factor; determining a data transmission rate between the server and the terminal device according to the target adaptive factor and a data transmission bandwidth between the server and the terminal device; and sending the data transmission rate to the server, wherein the data transmission rate is used to instruct the server to perform data transmission with the terminal device based on the data transmission rate.

[0118] An embodiment of the present application further provides an electronic device, including: a memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the above data transmission method is executed when the program is running.

[0119] The processor is used to run a program that performs the following functions: determining a target path between a server and a terminal device, wherein, in the target path, network performance parameters of data transmitted between the server and the terminal device meet preset conditions; adjusting a preset adaptive factor according to changes in the network performance parameters in the target path within a preset detection period to obtain a target adaptive factor; determining a data transmission rate between the server and the terminal device according to the target adaptive factor and a data transmission bandwidth between the server and the terminal device; and sending the data transmission rate to the server, wherein the data transmission rate is used to instruct the server to perform data transmission with the terminal device based on the data transmission rate.

[0120] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0121] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0122] In the above-mentioned embodiments of the present application, the collected information is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary protection measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0124] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0125] 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.

[0126] 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, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0127] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A data transmission method, characterized in that: include: Determining a target path between a server and a terminal device, wherein, in the target path, a network performance parameter of data transmitted between the server and the terminal device satisfies a preset condition; In a preset detection period, according to the change of the network performance parameter in the target path, adjusting the preset adaptive factor to obtain a target adaptive factor; determining a data transmission rate between the server and the terminal device according to the target adaptive factor and a data transmission bandwidth between the server and the terminal device; The data transmission rate is sent to the server, wherein the data transmission rate is used to instruct the server to perform data transmission with the terminal device based on the data transmission rate.

2. The method according to claim 1, characterized in that According to the change of the network performance parameter in the target path, adjusting the preset adaptive factor includes: Detecting changes in the network performance parameters in the target path, wherein the network performance parameters include at least one of the following: bandwidth, latency, and packet loss rate; If the parameter value of the network performance parameter in the i+1th detection cycle is greater than the parameter value of the network performance parameter in the i-th detection cycle, and the difference between the parameter value of the network performance parameter in the i+1th detection cycle and the parameter value of the network performance parameter in the i-th detection cycle does not exceed the first preset threshold value, based on the proportional control in the preset PID controller, reduce the value of the preset adaptive factor, where i is a positive integer.

3. The method according to claim 2, characterized in that According to the change of the network performance parameter in the target path, adjusting the preset adaptive factor includes: If the parameter value of the network performance parameter within the preset number of detection cycles is greater than a second preset threshold, based on the integral control in the preset PID controller, reducing the value of the preset adaptive factor at a first preset rate; If the parameter value of the network performance parameter in the j+1th detection cycle is greater than the parameter value of the network performance parameter in the jth detection cycle, and the difference between the parameter value of the network performance parameter in the j+1th detection cycle and the parameter value of the network performance parameter in the jth detection cycle exceeds the first preset threshold, based on the differential control in the preset PID controller, the value of the preset adaptive factor is reduced at a second preset rate.

4. The method according to claim 1, characterized in that According to the change of the network performance parameter in the target path, adjusting the preset adaptive factor to obtain the target adaptive factor includes: Obtaining an initialization action value table, wherein the initialization action value table includes a plurality of two-dimensional arrays and an action value function corresponding to each of the two-dimensional arrays, each of the two-dimensional arrays includes: a state parameter and an action parameter, the state parameter is the network performance parameter, and the action parameter is adjusting the preset adaptive factor; Determine a reward function according to the network performance parameter, the first delay and the second delay, wherein the first delay is the time delay between the target object performing a writing operation and the display board displaying the writing result in the cloud desktop conference system in the virtualized cloud desktop running in the terminal device, and the second delay is the transmission time delay of voice data and / or video data between the two terminal devices in the cloud desktop conference system; The Q learning algorithm is adopted to update the initialization action value table according to the reward function to obtain the target adaptive factor.

5. The method according to claim 4, characterized in that Determining a data transmission rate between the server and the terminal device according to the target adaptive factor and a data transmission bandwidth between the server and the terminal device includes: Obtain a conference tag of a target conference in the cloud desktop conference system, wherein the conference tag is used to characterize the importance of the conference; determine a first preset weight corresponding to the conference tag in the cloud desktop management system, use the first preset weight corresponding to the conference tag to perform weighted processing on the target adaptive factor, and determine the data transmission rate between the server and the terminal device according to the weighted target adaptive factor and the data transmission bandwidth.

6. The method according to claim 4, characterized in that Determine the target path between the server and the terminal device, including: Determining target data corresponding to a port of a virtualized cloud desktop running in the terminal device from data transmitted between the server and the terminal device; The target path for transmitting the target data between the server and the terminal device is determined using the open shortest path first protocol.

7. The method according to claim 1, characterized in that Determining a data transmission rate between the server and the terminal device according to the target adaptive factor and a data transmission bandwidth between the server and the terminal device includes: Obtain a process name corresponding to an application running in a virtualized cloud desktop running in the terminal device; determine a second preset weight corresponding to the process name in a cloud desktop management system, use the second preset weight corresponding to the process name to weightedly process the target adaptive factor, and determine the data transmission rate between the server and the terminal device based on the weighted target adaptive factor and the data transmission bandwidth.

8. A data transmission device, characterized in that: include: A first determination module is used to determine a target path between a server and a terminal device, wherein, in the target path, a network performance parameter of data transmitted between the server and the terminal device satisfies a preset condition; An acquisition module, configured to adjust a preset adaptive factor according to changes in the network performance parameters in the target path within a preset detection period to obtain a target adaptive factor; A second determination module, configured to determine a data transmission rate between the server and the terminal device according to the target adaptive factor and a data transmission bandwidth between the server and the terminal device; A sending module is used to send the data transmission rate to the server, wherein the data transmission rate is used to instruct the server to perform data transmission with the terminal device based on the data transmission rate.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the data transmission method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the data transmission method according to any one of claims 1 to 7 is executed when the program is run.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the data transmission method according to any one of claims 1 to 7 is implemented.

Images