Network transmission method and device based on non-perceptual calculation, storage medium and electronic equipment

Abstract

The invention provides a network transmission method and device based on non-perceptual computing, a storage medium and electronic equipment, and relates to the technical field of computer networks, the method comprises the following steps: receiving a transmission request sent by user equipment, and predicting a network resource demand of the user equipment according to a network bandwidth demand and a state parameter of the user equipment; based on the load and delay of the node server, screening out a target server meeting the network resource requirement from the server cluster, and establishing a target transmission channel between the user equipment and the target server; and in the transmission process, the transmission rate is adjusted based on the trigger type transmission control strategy until the data transmission is completed. According to the network transmission method and device based on non-perceptual calculation, the storage medium and the electronic equipment provided by the invention, efficient and reliable data transmission can be realized on the premise of not depending on a user to know the state of an underlying server, and the method and the device have important significance for improving the network service quality and the user experience.

Description

Technical Field

[0001] This application relates to the field of computer network technologies, and in particular, to a network transmission method, device, storage medium, and electronic device based on oblivious computing. Background Art

[0002] With the rapid development of cloud computing, virtualization, and distributed computing technologies, users' demands for computing resources have become increasingly complex and diverse.

[0003] In the network transmission methods in related technologies, users often need to understand and configure specific server resources in detail, such as the geographical location, current status, and load conditions of the servers, to ensure the efficiency and reliability of data transmission.

[0004] However, such a network transmission method not only poses high technical requirements on users but also increases the operation complexity, making it inconvenient for users to manage computing resources and being unfavorable for the flexible allocation and dynamic scheduling of resources. Summary of the Invention

[0005] The purpose of this application is to provide a network transmission method, device, storage medium, and electronic device based on oblivious computing, which can achieve efficient and reliable data transmission without relying on users' understanding of the underlying server status, and is of great significance for improving network service quality and user experience.

[0006] This application provides a network transmission method based on oblivious computing, including: Receiving a transmission request sent by a user device, and predicting the network resource requirements of the user device according to the network bandwidth requirements and status parameters of the user device; screening out a target server that meets the network resource requirements from a server cluster based on the load and latency of the node server, and establishing a target transmission channel between the user device and the target server; performing data transmission through the target transmission channel, and adjusting the transmission rate based on a trigger-based transmission control strategy during the transmission process until the data transmission is completed; wherein, the trigger-based transmission control strategy includes: dynamically adjusting the transmission rate at a preset transmission interval based on the difference between the transmission rate at the current moment and the initial bandwidth requirement until the bandwidth upper limit value is reached.

[0007] Optionally, predicting the network resource requirements of the user equipment according to the network bandwidth requirements and status parameters of the user equipment includes: using the network bandwidth requirements and status parameters of the user equipment as inputs, and predicting the network resource requirements of the user equipment by using a target network model; wherein, the target network model is constructed based on historical data; the target network model adapts to different network resource requirements based on the gradient descent of historical data; the historical data includes: the network bandwidth requirements and status parameters of different user equipment, and the corresponding network resource requirements.

[0008] Optionally, screening out a target server that meets the network resource requirements from the server cluster based on the load and latency of the node server includes: obtaining the real-time load and latency of each node server in the server cluster, and calculating the first product and the second product of each node server; the first product is: the product of the reciprocal of the real-time load and the load weight; the second product is: the product of the reciprocal of the latency and the latency weight; based on the sum of the first product and the second product, using linear programming to solve the target optimization problem to screen out the node server with the maximum performance value from the server cluster as the target server; wherein, the target optimization problem includes: solving the maximum performance value when the real-time load is less than the maximum load limit and the latency is less than the maximum latency limit.

[0009] Optionally, the performance value of the node server is calculated based on the following formula: Wherein, is the performance value of the i th node server, is the real-time load of the i th node server, is the latency of the i th node server, is the packet loss rate of the node server during the previous data transmission, is the load weight, is the latency weight, is the packet loss rate weight.

[0010] Optionally, adjusting the transmission rate based on a trigger-based transmission control strategy during the transmission until the data transmission is completed includes: calculating the rate difference between the initial bandwidth requirement and the transmission rate at the current moment, and multiplying the rate difference by an adjustment coefficient to obtain a third product; adding the third product to the transmission rate at the current moment to obtain the transmission rate for the next transmission cycle.

[0011] Optionally, when the concurrency number of the target server is greater than a preset concurrency threshold, the M / D / C queuing model is used to manage bandwidth requests; the steady-state idle probability of the M / D / C queuing model is calculated based on the following steps: obtain the service rate and arrival rate of the target server, calculate the fourth product of the service rate and the number of parallel containers, and the quotient of the arrival rate and the fourth product to obtain the utilization rate; based on the ratio of the arrival rate to the service rate, the utilization rate, and the number of parallel containers, calculate the steady-state idle probability of the M / D / C queuing model.

[0012] Optionally, during the transmission process, the transmission rate is adjusted based on the trigger-based transmission control strategy until the data transmission is completed, including: during the transmission process, obtain the interruption probability detected each time, and perform cumulative calculation based on the interruption probability detected each time to obtain the total transmission interruption probability of the target server; when the total transmission interruption probability is greater than a preset interruption threshold, perform a switch of the node server.

[0013] This application also provides a network transmission device based on oblivious computing, including: A request receiving module, configured to receive a transmission request sent by a user device; a demand determination module, configured to predict the network resource demand of the user device according to the network bandwidth demand and status parameters of the user device; a data transmission module, configured to screen out a target server that meets the network resource demand from a server cluster based on the load and latency of the node server, and establish a target transmission channel between the user device and the target server; the data transmission module is further configured to perform data transmission through the target transmission channel, and adjust the transmission rate based on the trigger-based transmission control strategy during the transmission process until the data transmission is completed; wherein, the trigger-based transmission control strategy includes: dynamically adjusting the transmission rate at a preset transmission interval based on the difference between the transmission rate at the current moment and the initial bandwidth demand until the bandwidth upper limit value is reached.

[0014] Optionally, the demand determination module is specifically configured to use the network bandwidth demand and status parameters of the user device as inputs, and predict the network resource demand of the user device by using a target network model; wherein, the target network model is constructed based on historical data; the target network model adapts to different network resource demands based on the gradient descent of historical data; the historical data includes: the network bandwidth demands and status parameters of different user devices, and the corresponding network resource demands.

[0015] Optionally, the data transmission module is specifically configured to obtain the real-time load and latency of each node server in the server cluster, and calculate the first product and the second product of each node server; the first product is the product of the reciprocal of the real-time load and the load weight; the second product is the product of the reciprocal of the latency and the latency weight; the data transmission module is further specifically configured to, based on the sum of the first product and the second product, use linear programming to solve the target optimization problem to screen out the node server with the maximum performance value from the server cluster as the target server; wherein, the target optimization problem includes: solving for the maximum performance value when the real-time load is less than the maximum load limit and the latency is less than the maximum latency limit.

[0016] Optionally, the performance value of the node server is calculated based on the following formula: Wherein, is the performance value of the i th node server, is the real-time load of the i th node server, is the latency of the i th node server, is the packet loss rate during the last data transmission of the node server, is the load weight, is the latency weight, is the packet loss rate weight.

[0017] Optionally, the data transmission module is specifically configured to calculate the rate difference between the initial bandwidth requirement and the transmission rate at the current moment, and multiply the rate difference by the adjustment coefficient to obtain the third product; the data transmission module is further specifically configured to add the third product to the transmission rate at the current moment to obtain the transmission rate for the next transmission cycle.

[0018] Optionally, when the number of concurrent requests of the target server is greater than the preset concurrent threshold, the M / D / C queuing model is used to manage bandwidth requests; the data transmission module is specifically configured to obtain the service rate and arrival rate of the target server, and calculate the fourth product of the service rate and the number of parallel containers, and the quotient of the arrival rate and the fourth product to obtain the utilization rate; the data transmission module is further specifically configured to calculate the steady-state idle probability of the M / D / C queuing model based on the ratio of the arrival rate to the service rate, the utilization rate, and the number of parallel containers.

[0019] Optionally, the data transmission module is specifically configured to obtain the interruption probability detected each time during the transmission process, and perform cumulative calculation based on the interruption probability detected each time to obtain the total transmission interruption probability of the target server; the data transmission module is further specifically configured to switch the node server when the total transmission interruption probability is greater than a preset interruption threshold.

[0020] The present application also provides a computer program product, including computer programs / instructions, which when executed by a processor implement the steps of the network transmission method based on oblivious computing as described in any one of the above.

[0021] The present application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the steps of the network transmission method based on oblivious computing as described in any one of the above.

[0022] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the network transmission method based on oblivious computing as described in any one of the above.

[0023] The network transmission method, device, storage medium, and electronic device based on oblivious computing provided by the present application first receive a transmission request sent by a user device, and predict the network resource requirements of the user device according to the network bandwidth requirements and status parameters of the user device; then, based on the load and latency of the node server, screen out a target server that meets the network resource requirements from the server cluster, and establish a target transmission channel between the user device and the target server; finally, perform data transmission through the target transmission channel, and adjust the transmission rate based on a trigger-based transmission control strategy during the transmission process until the data transmission is completed; wherein, the trigger-based transmission control strategy includes: dynamically adjusting the transmission rate at a preset transmission interval based on the difference between the current transmission rate and the initial bandwidth requirement until the bandwidth upper limit value is reached. In this way, it is possible to achieve efficient and reliable data transmission without relying on the user's understanding of the underlying server status, which is of great significance for improving network service quality and user experience. Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 It is one of the flow diagrams of the network transmission method based on oblivious computing provided by this application; Figure 2 It is the second flow diagram of the network transmission method based on oblivious computing provided by this application; Figure 3 It is the schematic diagram of the principle of data transmission bandwidth convergence approximation provided by this application; Figure 4 It is the structural diagram of the network transmission device based on oblivious computing provided by this application; Figure 5 It is the structural diagram of the electronic device provided by this application. Detailed implementation manners

[0026] To make the objectives, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below with reference to the accompanying drawings in this application. Apparently, the described embodiments are some but not all of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in this application belong to the scope of protection of this application.

[0027] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of this application can be implemented in an order different from those illustrated or described here, and the objects distinguished by "first", "second", etc. generally belong to the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the associated objects before and after.

[0028] In view of the above technical problems existing in the related art, the embodiments of this application provide a network transmission method based on oblivious computing. Oblivious computing is a new computing architecture. In this architecture, when users use computing resources, they do not need to pay attention to the specific details of the underlying servers, such as the location of the servers, the load status, etc. The system can handle the allocation and scheduling of resources through an automated resource management mechanism. This architecture usually combines virtualization technology, load balancing technology, and intelligent resource scheduling algorithms to achieve automatic scaling and high availability of resources. Oblivious computing not only simplifies the operation process of users, reduces the management complexity, but also greatly improves the stability and response speed of the system, making the utilization of computing resources more flexible and efficient.

[0029] The following will, in conjunction with the accompanying drawings, elaborate on the network transmission method provided by the embodiments of the present application based on oblivious computing through specific embodiments and their application scenarios.

[0030] As Figure 1 shown, a network transmission method based on oblivious computing provided by an embodiment of the present application may include the following steps 101 to 103: Step 101: Receive a transmission request sent by a user device, and predict the network resource requirements of the user device according to the network bandwidth requirements and status parameters of the user device.

[0031] Exemplarily, the above status parameters may include: the current network connection type (such as WiFi, 4G, 5G, wired, etc.), network delay, packet loss rate, jitter, channel quality indicators (such as SNR, RSSI, CQI), the activity status of the user device (such as screen on / off, foreground / background tasks), and historical data of the current connection stability, etc.; the above network resource requirements may include: the required bandwidth (the maximum transmission capacity desired per unit time), the required transmission throughput (i.e., the data rate expected to be achieved during the actual transmission process), the maximum acceptable delay, the maximum allowable packet loss rate, and the number of concurrent connections, etc.

[0032] Specifically, for the prediction of the network resource requirements of the user device, step 101 may further include the following step 101a: Step 101a: Use the network bandwidth requirements and status parameters of the user device as inputs, and use the target network model to predict the network resource requirements of the user device.

[0033] Among them, the target network model is constructed based on historical data; the target network model adapts to different network resource requirements based on the gradient descent of historical data; the historical data includes: the network bandwidth requirements and status parameters of different user devices, and the corresponding network resource requirements.

[0034] Exemplarily, when the user device initiates a transmission request, the system enters the request initialization module. The system, according to the network bandwidth requirements and status parameters of the user device, establishes a preliminary network model through historical data to predict network resource requirements. This network model can be expressed as: and are adjustment coefficients, and adapt to different network requirements through the gradient descent of historical data.

[0035] Step 102: Based on the load and latency of the node servers, screen out target servers that meet the network resource requirements from the server cluster, and establish a target transmission channel between the user device and the target servers.

[0036] Exemplarily, after determining the network resource requirements of the user device, appropriate node servers can be screened out from the server cluster for data transmission with the user device.

[0037] Specifically, the above Step 102 may further include the following Steps 102a1 and 102a2: Step 102a1: Obtain the real-time load and latency of each node server in the server cluster, and calculate the first product and the second product of each node server.

[0038] Wherein, the first product is: the product of the reciprocal of the real-time load and the load weight; the second product is: the product of the reciprocal of the latency and the latency weight.

[0039] Step 102a2: Based on the sum of the first product and the second product, use linear programming to solve the target optimization problem to screen out the node server with the maximum performance value from the server cluster as the target server.

[0040] Wherein, the target optimization problem includes: solving for the maximum performance value under the condition that the real-time load is less than the maximum load limit and the latency is less than the maximum latency limit.

[0041] Exemplarily, based on the network resource requirements of the user device and the real-time load situation of the server cluster, the optimal node server is dynamically selected. Assume that the server cluster has node servers, and for any i th node server, the real-time load is , and the latency is , then the target performance function of the node server can be represented by the following Formula 1: (Formula 1) Wherein, and respectively represent the weights of the load and the latency. The resource scheduling module selects the optimal node by using linear programming to solve the following optimization problem (i.e., the above target optimization problem), which can be specifically referred to the following Formula 2: (Formula 2) Exemplarily, this optimization problem is that the real-time load is less than the maximum load limit , and the latency is less than the maximum latency limit In the case of, solve for the maximum performance value .

[0042] Step 103: Perform data transmission through the target transmission channel, and adjust the transmission rate based on the trigger-based transmission control strategy during the transmission process until the data transmission is completed.

[0043] Among them, the trigger-based transmission control strategy includes: dynamically adjusting the transmission rate at a preset transmission interval based on the difference between the transmission rate at the current moment and the initial bandwidth requirement until the bandwidth upper limit value is reached.

[0044] Further, after establishing a transmission channel between the user equipment and the target server node, during the transmission process, the embodiment of the present application adopts a feedback-based trigger-based transmission control strategy to achieve transmission optimization by adjusting the sending rate.

[0045] Specifically, the above step 102 may further include the following steps 103a1 and 103a2: Step 103a1: Calculate the rate difference between the initial bandwidth requirement and the transmission rate at the current moment, and multiply the rate difference by an adjustment coefficient to obtain a third product.

[0046] Step 103a2: After adding the third product to the transmission rate at the current moment, obtain the transmission rate for the next transmission cycle.

[0047] Exemplarily, as Figure 2 , the transmission rate can be dynamically adjusted periodically until the bandwidth upper limit (convergence) is reached. Let the initial bandwidth requirement be , the transmission rate adjustment formula can be the following formula three: (Formula Three) (Formula Three) Among them, is the adjustment coefficient, is the above rate difference.

[0048] Exemplarily, to further reduce traffic consumption and the "long tail" traffic problem, the data transmission module uses the M / D / C queuing model to manage bandwidth requests in the case of large-scale concurrency. That is, in the case where the concurrency number of the target server is greater than the preset concurrency threshold, the M / D / C queuing model is used to manage bandwidth requests.

[0049] Specifically, in the above step 102, for the calculation of the steady-state idle probability of the M / D / C queuing model, it may include the following steps 103b1 and 103b2: Step 103b1: Obtain the service rate and arrival rate of the target server, calculate the fourth product of the service rate and the number of parallel containers, and the quotient of the arrival rate and the fourth product to obtain the utilization rate.

[0050] Step 103b2: Based on the ratio of the arrival rate to the service rate, the utilization rate, and the number of parallel containers, calculate the steady-state idle probability of the M / D / C queuing model.

[0051] Exemplarily, assume that the system arrival rate is (i.e., the number of requests arriving per unit time), and the service rate is (i.e., the number of requests that can be processed per unit time). Then, the utilization rate of the system can be expressed by the following formula four: (Formula Four) Where, represents the current number of parallel containers of the target server. This model helps the system maintain service stability under different request intensities. In the M / D / C queuing model, the steady-state idle probability of the system can be expressed by the Erlang loss formula through the following formula five: (Formula Five) In a possible implementation, during the transmission process, if a server node failure or network anomaly is detected, the system will trigger a fault detection and transfer mechanism.

[0052] Specifically, the above Step 102 may further include the following Step 103c1 and Step 103c2: Step 103c1: During the transmission process, obtain the interruption probability detected each time, and perform cumulative calculation based on the interruption probability detected each time to obtain the total transmission interruption probability of the target server.

[0053] Step 103c2: In the case where the total transmission interruption probability is greater than a preset interruption threshold, perform a switch of the node server.

[0054] Exemplarily, assume that the current probability of transmission interruption is , and the total probability of transmission interruption calculated by the system through cumulative calculation of the interruption probability each time can be expressed by the following formula six: (Formula Six) Where, is the transmission interruption probability each time. When exceeds the set threshold , the system automatically switches to a new server node to ensure the continuity of data transmission.

[0055] Exemplarily, after the data transmission is completed, the average value of the transmission rate can be calculated by the following formula seven to measure the transmission quality: (Formula Seven) Meanwhile, the packet loss rate during the transmission process is calculated from the total number of data packets and the number of lost data packets and can specifically refer to the following formula eight: (Formula Eight) Exemplarily, the feedback result after the transmission is completed incorporates the packet loss rate feedback into the scheduling optimization function as a weight factor to optimize the subsequent resource scheduling strategy, which can specifically refer to the following formula nine: (Formula Nine) Wherein, is the performance value of the i th node server, is the real-time load of the i th node server, is the latency of the i th node server, is the packet loss rate during the last data transmission of the node server, is the load weight, is the latency weight, is the packet loss rate weight.

[0056] For example, as Figure 3 shown, the network transmission method based on oblivious computing provided by the embodiments of the present application can be modularly divided, specifically including the following modules: 1. Request Initialization Module: The user device sends a data transmission request to the server cluster, and the system automatically identifies the user's network status and bandwidth requirements and transmits this information to the resource scheduling module. This step does not require the user to specify a specific server, and the system automatically completes the initialization of resource allocation.

[0057] 2. Resource Scheduling Module: According to the network status, bandwidth requirements, and real-time load conditions of the user device, the resource scheduling module selects the most suitable server node for data transmission through a dynamic load balancing algorithm. The resource scheduling module also continuously monitors the load conditions of each server node and adjusts the resource allocation in real time to ensure that in case of network congestion or server failure, it can automatically switch to other available server nodes to ensure the continuity and stability of the transmission process.

[0058] 3. Data Transmission Module: Data is transmitted between the user device and the selected server node by establishing a secure transmission channel. During the transmission process, based on the concept of oblivious computing, the system automatically hides the specific information of the underlying server, so that users do not need to care about the data source or the specific transmission path. At the same time, the system will automatically adjust the data transmission rate and path according to the network conditions to optimize the transmission efficiency and reduce the transmission delay.

[0059] 4. Fault Detection and Transfer Module: During the transmission process, if a fault or network anomaly is detected in the current server node, the system will automatically trigger the fault detection and transfer mechanism, transfer the data transmission task to other available server nodes, and ensure seamless connection to avoid transmission interruption or data loss caused by server failure.

[0060] 5. Transmission Completion and Feedback Module: After the data transmission is completed, the system will feedback the transmission result to the user and update the status information of the server cluster for subsequent resource scheduling. This feedback includes performance metrics such as transmission speed, latency, and retransmission rate to optimize subsequent scheduling decisions.

[0061] The network transmission method based on oblivious computing provided by the embodiments of this application has the following advantages: 1. Improve user experience: Through the oblivious computing architecture, users do not need to pay attention to the specific server situation during the transmission process, realizing simplified operations and optimized experience. 2. Improve transmission reliability: The system has dynamic load balancing and fault transfer capabilities, can automatically select the optimal path, and seamlessly switch to other nodes when the server fails, ensuring the stability of the transmission. 3. Optimize resource utilization: The present invention uses a resource scheduling algorithm to flexibly allocate computing resources according to the real-time network status and server load conditions, improve the utilization efficiency of the server, and reduce the performance degradation caused by server overload or failure. 4. Reduce operation and maintenance complexity: The present invention realizes the centralized management and automatic allocation of computing resources, without the need for users or administrators to manually manage server details, simplifies the operation and maintenance process, and reduces the management cost.

[0062] The network transmission method based on oblivious computing provided by the embodiments of the present application first receives a transmission request sent by a user device, and predicts the network resource requirements of the user device according to the network bandwidth requirements and status parameters of the user device; then, based on the load and latency of the node server, filters out a target server that meets the network resource requirements from the server cluster, and establishes a target transmission channel between the user device and the target server; finally, performs data transmission through the target transmission channel, and adjusts the transmission rate based on a trigger-based transmission control strategy during the transmission process until the data transmission is completed; wherein, the trigger-based transmission control strategy includes: dynamically adjusting the transmission rate at a preset transmission interval based on the difference between the transmission rate at the current moment and the initial bandwidth requirement until the bandwidth upper limit value is reached. In this way, it is possible to achieve efficient and reliable data transmission without relying on the user's understanding of the underlying server status, which is of great significance for improving network service quality and user experience.

[0063] It should be noted that for the network transmission method based on oblivious computing provided by the embodiments of the present application, the execution subject can be a network transmission device based on oblivious computing, or a control module in the network transmission device based on oblivious computing for executing the network transmission method based on oblivious computing. In the embodiments of the present application, the network transmission method based on oblivious computing provided by the embodiments of the present application is described by taking the network transmission device based on oblivious computing as an example to execute the network transmission method based on oblivious computing, so as to illustrate the network transmission device based on oblivious computing provided by the embodiments of the present application.

[0064] It should be noted that in the embodiments of the present application, the network transmission method based on oblivious computing shown in each of the above method drawings is exemplarily described by taking one drawing in the embodiments of the present application as an example. Specifically, when implemented, the network transmission method based on oblivious computing shown in each of the above method drawings can also be implemented in combination with any other combinable drawings schemed in the above embodiments, which will not be elaborated here.

[0065] The network transmission device based on oblivious computing provided by the present application will be described below, and the description below can be correspondingly referred to the network transmission method based on oblivious computing described above.

[0066] Figure 4 is a schematic structural diagram of the network transmission device based on oblivious computing provided by the embodiments of the present application, as Figure 4 shown, specifically including: A request receiving module 401 for receiving a transmission request sent by a user device; a demand determining module 402 for predicting the network resource demand of the user device according to the network bandwidth demand and status parameters of the user device; a data transmission module 403 for screening out a target server that meets the network resource demand from a server cluster based on the load and latency of a node server, and establishing a target transmission channel between the user device and the target server; the data transmission module 403 is further configured to perform data transmission through the target transmission channel, and adjust the transmission rate based on a trigger-based transmission control policy during the transmission process until the data transmission is completed; wherein, the trigger-based transmission control policy includes: dynamically adjusting the transmission rate at a preset transmission interval based on the difference between the transmission rate at the current moment and the initial bandwidth demand until the bandwidth upper limit value is reached.

[0067] Optionally, the demand determining module 402 is specifically configured to use the network bandwidth demand and status parameters of the user device as inputs, and predict the network resource demand of the user device by using a target network model; wherein, the target network model is constructed based on historical data; the target network model adapts to different network resource demands based on the gradient descent of historical data; the historical data includes: the network bandwidth demands and status parameters of different user devices, and the corresponding network resource demands.

[0068] Optionally, the data transmission module 403 is specifically configured to obtain the real-time load and latency of each node server in the server cluster, and calculate the first product and the second product of each node server; the first product is: the product of the reciprocal of the real-time load and the load weight; the second product is: the product of the reciprocal of the latency and the latency weight; the data transmission module 403 is specifically further configured to screen out the node server with the largest performance value from the server cluster as the target server by using linear programming to solve a target optimization problem based on the sum of the first product and the second product; wherein, the target optimization problem includes: solving for the maximum performance value when the real-time load is less than the maximum load limit value and the latency is less than the maximum latency limit value.

[0069] Optionally, the performance value of a node server is calculated based on the following formula: Wherein, is the performance value of the i th node server, is the real-time load of the i th node server, is the latency of the i th node server, is the packet loss rate of the node server during the previous data transmission, is the load weight, is the delay weight, is the packet loss rate weight.

[0070] Optionally, the data transmission module 403 is specifically configured to calculate the rate difference between the initial bandwidth requirement and the transmission rate at the current moment, and multiply the rate difference by an adjustment coefficient to obtain a third product; the data transmission module 403 is further specifically configured to add the third product to the transmission rate at the current moment to obtain the transmission rate for the next transmission cycle.

[0071] Optionally, when the number of concurrent connections of the target server is greater than a preset concurrent threshold, the M / D / C queuing model is used to manage bandwidth requests; the data transmission module 403 is specifically configured to obtain the service rate and arrival rate of the target server, calculate a fourth product of the service rate and the number of parallel containers, and a quotient of the arrival rate and the fourth product to obtain the utilization rate; the data transmission module 403 is further specifically configured to calculate the steady-state idle probability of the M / D / C queuing model based on the ratio of the arrival rate to the service rate, the utilization rate, and the number of parallel containers.

[0072] Optionally, the data transmission module 403 is specifically configured to, during the transmission process, obtain the interruption probability detected each time a detection is performed, and perform cumulative calculation based on the interruption probability detected each time a detection is performed to obtain the total transmission interruption probability of the target server; the data transmission module 403 is further specifically configured to switch the node server when the total transmission interruption probability is greater than a preset interruption threshold.

[0073] The network transmission device based on oblivious computing provided by this application first receives a transmission request sent by a user device, and predicts the network resource requirements of the user device according to the network bandwidth requirements and status parameters of the user device; then, based on the load and delay of the node server, filters out a target server that meets the network resource requirements from the server cluster, and establishes a target transmission channel between the user device and the target server; finally, performs data transmission through the target transmission channel, and adjusts the transmission rate based on a trigger-based transmission control strategy during the transmission process until the data transmission is completed; wherein, the trigger-based transmission control strategy includes: dynamically adjusting the transmission rate at preset transmission intervals based on the difference between the transmission rate at the current moment and the initial bandwidth requirement until the bandwidth upper limit value is reached. In this way, it is possible to achieve efficient and reliable data transmission without relying on the user's understanding of the underlying server status, which is of great significance for improving network service quality and user experience.

[0074] Figure 5 Illustrates a schematic physical structure diagram of an electronic device, such asFigure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530, and a communication bus 540. Among them, the processor 510, the communications interface 520, and the memory 530 complete communication with each other through the communication bus 540. The processor 510 may call the logical instructions in the memory 530 to execute a network transmission method based on oblivious computing. The method includes: First, receive a transmission request sent by a user device, and predict the network resource requirements of the user device according to the network bandwidth requirements and status parameters of the user device; After that, based on the load and latency of the node server, screen out a target server that meets the network resource requirements from the server cluster, and establish a target transmission channel between the user device and the target server; Finally, perform data transmission through the target transmission channel, and adjust the transmission rate based on a trigger-based transmission control strategy during the transmission process until the data transmission is completed; Among them, the trigger-based transmission control strategy includes: Based on the difference between the current transmission rate and the initial bandwidth requirement, dynamically adjust the transmission rate at a preset transmission interval until the bandwidth upper limit value is reached. In this way, it is possible to achieve efficient and reliable data transmission without relying on the user's understanding of the underlying server status, which is of great significance for improving network service quality and user experience.

[0075] In addition, when the logical instructions in the above-mentioned memory 530 can be implemented in the form of software function units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0076] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the network transmission method based on oblivious computing provided by the above-mentioned various methods. The method includes: First, receiving a transmission request sent by a user device, and predicting the network resource requirements of the user device according to the network bandwidth requirements and status parameters of the user device; After that, based on the load and latency of the node server, screening out a target server that meets the network resource requirements from the server cluster, and establishing a target transmission channel between the user device and the target server; Finally, data is transmitted through the target transmission channel, and the transmission rate is adjusted based on a trigger-based transmission control strategy during the transmission process until the data transmission is completed; Wherein, the trigger-based transmission control strategy includes: dynamically adjusting the transmission rate at a preset transmission interval based on the difference between the transmission rate at the current moment and the initial bandwidth requirement until the bandwidth upper limit value is reached. In this way, it is possible to achieve efficient and reliable data transmission without relying on the user's understanding of the underlying server status, which is of great significance for improving network service quality and user experience.

[0077] On another aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the network transmission method based on oblivious computing provided by the above-mentioned various methods. The method includes: First, receiving a transmission request sent by a user device, and predicting the network resource requirements of the user device according to the network bandwidth requirements and status parameters of the user device; After that, based on the load and latency of the node server, screening out a target server that meets the network resource requirements from the server cluster, and establishing a target transmission channel between the user device and the target server; Finally, data is transmitted through the target transmission channel, and the transmission rate is adjusted based on a trigger-based transmission control strategy during the transmission process until the data transmission is completed; Wherein, the trigger-based transmission control strategy includes: dynamically adjusting the transmission rate at a preset transmission interval based on the difference between the transmission rate at the current moment and the initial bandwidth requirement until the bandwidth upper limit value is reached. In this way, it is possible to achieve efficient and reliable data transmission without relying on the user's understanding of the underlying server status, which is of great significance for improving network service quality and user experience.

[0078] The device embodiments described above are merely illustrative. 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 to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0079] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A network transmission method based on oblivious computing, characterized in that Including: Receiving a transmission request sent by a user device, and predicting the network resource requirements of the user device according to the network bandwidth requirements and status parameters of the user device; Based on the load and latency of the node server, screening out a target server that meets the network resource requirements from the server cluster, and establishing a target transmission channel between the user device and the target server; Performing data transmission through the target transmission channel, and adjusting the transmission rate based on a trigger-based transmission control strategy during the transmission process until the data transmission is completed; Wherein, the trigger-based transmission control strategy includes: dynamically adjusting the transmission rate at a preset transmission interval based on the difference between the transmission rate at the current moment and the initial bandwidth requirement until the bandwidth upper limit value is reached.

2. The method according to claim 1, characterized in that, The predicting the network resource requirements of the user device according to the network bandwidth requirements and status parameters of the user device includes: Taking the network bandwidth requirements and status parameters of the user device as inputs, and predicting the network resource requirements of the user device by using a target network model; Wherein, the target network model is constructed based on historical data; the target network model adapts to different network resource requirements based on the gradient descent of historical data; the historical data includes: the network bandwidth requirements and status parameters of different user devices, and the corresponding network resource requirements.

3. The method according to claim 1, wherein The screening out a target server that meets the network resource requirements from the server cluster based on the load and latency of the node server includes: Obtaining the real-time load and latency of each node server in the server cluster, and calculating the first product and the second product of each node server; the first product is the product of the reciprocal of the real-time load and the load weight; the second product is the product of the reciprocal of the latency and the latency weight; Based on the sum of the first product and the second product, using linear programming to solve the target optimization problem to screen out the node server with the maximum performance value from the server cluster as the target server; Wherein, the target optimization problem includes: solving for the maximum performance value when the real-time load is less than the maximum load limit value and the latency is less than the maximum latency limit value.

4. The method according to claim 3, characterized in that, The performance value of the node server is calculated based on the following formula: Among them, is the performance value of the i th node server, is the real-time load of the i th node server, is the latency of the i th node server, is the packet loss rate during the last data transmission of the node server, is the load weight, is the latency weight, is the packet loss rate weight.

5. The method according to claim 1, characterized in that, The adjusting the transmission rate based on the trigger-based transmission control strategy during the transmission process until the data transmission is completed includes: Calculating the rate difference between the initial bandwidth requirement and the transmission rate at the current moment, and multiplying the rate difference by an adjustment coefficient to obtain a third product; Adding the third product to the transmission rate at the current moment to obtain the transmission rate for the next transmission cycle.

6. The method according to claim 4, wherein In the case where the concurrent number of the target server is greater than a preset concurrent threshold, using an M / D / C queuing model to manage bandwidth requests; The steady-state idle probability of the M / D / C queuing model is calculated based on the following steps: Obtaining the service rate and arrival rate of the target server, and calculating the fourth product of the service rate and the number of parallel containers, and the quotient of the arrival rate and the fourth product to obtain the utilization rate; Calculate the steady-state idle probability of the M / D / C queuing model based on the ratio of the arrival rate to the service rate, the utilization rate, and the number of parallel containers.

7. The method according to any one of claims 1, 5 or 6, characterized in that, During the transmission, adjust the transmission rate based on the trigger-based transmission control strategy until the data transmission is completed, including: During the transmission, obtain the interruption probability detected at each detection, and perform cumulative calculation based on the interruption probability detected at each detection to obtain the total transmission interruption probability of the target server; In the case where the total transmission interruption probability is greater than the preset interruption threshold, perform a handover of the node server.

8. A network transmission device based on oblivious computing, characterized in that, The device includes: A request receiving module, configured to receive a transmission request sent by a user equipment; A demand determining module, configured to predict the network resource demand of the user equipment according to the network bandwidth demand and status parameters of the user equipment; A data transmission module, configured to screen out a target server that meets the network resource demand from a server cluster based on the load and latency of the node server, and establish a target transmission channel between the user equipment and the target server; The data transmission module is further configured to perform data transmission through the target transmission channel, and adjust the transmission rate based on the trigger-based transmission control strategy during the transmission until the data transmission is completed; Wherein, the trigger-based transmission control strategy includes: dynamically adjusting the transmission rate at a preset transmission interval based on the difference between the transmission rate at the current moment and the initial bandwidth demand until the bandwidth upper limit value is reached.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the steps of the network transmission method based on oblivious computing according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored thereon. When the computer program is executed by a processor, it implements the steps of the network transmission method based on oblivious computing according to any one of claims 1 to 7.

Images