Data distribution method and apparatus, computer device, and storage medium

Abstract

The application relates to a data distribution method and device, computer equipment and a storage medium. The method comprises the following steps: predicting a predicted use proportion of target content data on an edge node after simulating an increase in the number of edge nodes for launching the target content data, determining a cost saving rate state of the target content data and a target launch quantity of the target content data on the edge node by comparing a predicted use proportion with an actual current use proportion, and distributing only target content data with a high cost saving rate to a plurality of target edge nodes with the target launch quantity, so as to improve the use rate of the target content data on the target edge nodes, and to improve the utilization rate of each edge node by preferentially distributing content data with a high cost saving rate to a plurality of edge nodes in this way, thereby solving the problem of low utilization rate of edge nodes caused by the existing content distribution mode.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a data distribution method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the development of the Internet, the central server of content playback platform will face great traffic pressure during peak traffic periods, and it is necessary to use the lower-cost edge nodes for traffic distribution. However, the existing content distribution method relies on fixed rules to distribute to various edge nodes, without considering the access situation of different content on different edge nodes, resulting in low utilization of edge nodes. Summary of the Invention

[0003] This application provides a data distribution method, apparatus, computer equipment, and storage medium to address the problem of low edge node utilization caused by existing content distribution methods.

[0004] In a first aspect, this application provides a data distribution method, the method comprising: Obtain the attribute information of the target content data and the current content delivery information, wherein the current content delivery information includes the current delivery quantity of the target content data for different delivery objects, and the current usage ratio of the target content data in different delivery objects, wherein the delivery object is the central server or the edge node; Using a prediction model based on the attribute information, the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity is predicted, wherein the simulated delivery quantity is greater than the current delivery quantity; Based on the comparison between the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity and the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity, the cost saving rate status of the target content data and the target delivery quantity of the target content data on the edge nodes are determined. When the cost saving rate of the target content data is in a high saving rate state, the target content data is distributed to multiple target edge nodes corresponding to the target delivery quantity.

[0005] Secondly, this application provides a data distribution apparatus, the apparatus comprising: The acquisition module is used to acquire attribute information of target content data and current content delivery information, wherein the current content delivery information includes the current delivery quantity of the target content data for different delivery objects, and the current usage ratio of the target content data on each edge node under the current delivery quantity; The prediction module is used to use a prediction model based on the attribute information to predict the predicted usage ratio of the target content data on multiple edge nodes under the simulated delivery quantity, wherein the simulated delivery quantity is greater than the current delivery quantity; The determination module is used to determine the cost saving rate status of the target content data and the target deployment quantity of the target content data on the edge nodes based on the comparison result between the current usage ratio of the target content data on multiple edge nodes under the current deployment quantity and the predicted usage ratio of the target content data on multiple edge nodes under the simulated deployment quantity. The distribution module is used to distribute the target content data to multiple target edge nodes corresponding to the target delivery quantity when the cost saving rate of the target content data is in a high saving rate state.

[0006] Thirdly, this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described data distribution method.

[0007] Fourthly, this application also provides a computer storage medium storing computer-executable instructions for executing the above-described data distribution method.

[0008] Compared with the prior art, the technical solution provided in this application has the following advantages: The method provided in this application obtains attribute information and current content delivery information of target content data, wherein the current content delivery information includes the current delivery quantity of the target content data for different delivery objects, and the current usage ratio of the target content data in different delivery objects, wherein the delivery object is a central server or the edge node; using a prediction model based on the attribute information, the predicted usage ratio of the target content data on multiple edge nodes under the simulated delivery quantity is predicted, wherein the simulated delivery quantity is greater than the current delivery quantity; based on the comparison result between the current usage ratio of the target content data on multiple edge nodes under the current delivery quantity and the predicted usage ratio of the target content data on multiple edge nodes under the simulated delivery quantity, the cost saving rate status of the target content data and the target delivery quantity of the target content data on the edge nodes are determined; when the cost saving rate status of the target content data is a high saving rate status, the target content data is distributed to multiple target edge nodes corresponding to the target delivery quantity.

[0009] Based on the above method, by simulating an increase in the number of edge nodes to which target content data is distributed, the predicted usage ratio of the target content data on edge nodes after the simulated increase in the number of edge nodes is predicted. By comparing the predicted usage ratio with the actual current usage ratio, the cost-saving rate of the target content data and the target distribution quantity of the target content data on edge nodes are determined. Only target content data with high cost-saving rates are distributed to multiple target edge nodes with the target distribution quantity, thereby improving the utilization rate of the target content data on the target edge nodes. In this way, high cost-saving content data is preferentially distributed to multiple edge nodes, thereby improving the utilization rate of each edge node, thus solving the problem of low edge node utilization caused by existing content distribution methods. Attached Figure Description

[0010] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0013] Figure 1 An application environment diagram of a data distribution method provided in an embodiment of this application; Figure 2 A flowchart illustrating a data distribution method provided in an embodiment of this application; Figure 3 A structural block diagram of a data distribution device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0015] The following disclosure provides numerous different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0016] Figure 1 This is a diagram illustrating the application environment of a data distribution method in one embodiment. (Refer to...) Figure 1 This data distribution method is applied to a data distribution system. The data distribution system includes a terminal 110, a data distribution device 120, and delivery targets 130. The terminal 110 and the data distribution device 120 are connected via a network. The terminal 110 is used to upload content data to the data distribution device 120 or request content data from the delivery targets 130, which may be a central server or an edge node. The data distribution device 120 is used to distribute the content data to the edge nodes or the central server. The terminal 110 can be a desktop terminal or a mobile terminal; a mobile terminal can be at least one of a mobile phone, tablet computer, or laptop computer. The data distribution device 120 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0017] In one embodiment, Figure 2 This is a flowchart illustrating a data distribution method in one embodiment, with reference to... Figure 2 This invention provides a data distribution method. This embodiment primarily applies this method to a data distribution device 120, and the data distribution method specifically includes the following steps: Step S210: Obtain the attribute information of the target content data and the current content delivery information, wherein the current content delivery information includes the current delivery quantity of the target content data for different delivery objects, and the current usage ratio of the target content data in different delivery objects, wherein the delivery object is the central server or the edge node.

[0018] Specifically, the target content data refers to any published content data, and the data type can be short video, long video, text content, audio content, or image and text content. Attribute information includes content duration, bitrate, Internet Service Provider (ISP), regional traffic weight, historical usage percentage of different target audiences, etc., and the target audience is either a central server or edge nodes.

[0019] Current content delivery information indicates the current delivery status of target content data. Specifically, it includes different delivery targets, the current delivery quantity for each target, and the current usage percentage for each target. For example, a current delivery quantity of 1 for a central server and 2 for edge nodes indicates that the target content data has been delivered to one central server and two edge nodes, and can be obtained through these targets. Current usage percentage indicates the ratio of the access frequency to obtain target content data through the current delivery target within a preset time period to the total access frequency to obtain target content data through all delivery targets within the preset time period. The current delivery target is either a central server or an edge node. The current usage percentage reflects the actual usage rate of the target content data by each delivery target storing it.

[0020] Step S220: Using a prediction model based on the attribute information, predict the predicted usage ratio of the target content data on multiple edge nodes under the simulated delivery quantity, wherein the simulated delivery quantity is greater than the current delivery quantity.

[0021] Specifically, by simulating the increase in the number of target content data delivered to edge nodes, a simulated delivery quantity is obtained, which in turn predicts the predicted usage percentage of the target content data after increasing the delivery quantity to edge nodes.

[0022] Step S230: Based on the comparison between the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity and the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity, determine the cost saving rate status of the target content data and the target delivery quantity of the target content data on the edge nodes.

[0023] Specifically, based on the comparison between the predicted usage percentage and the current actual usage percentage, it can be determined whether increasing the number of edge nodes increases the cost savings rate for the target content data. The cost savings rate indicates the cost of delivering the target content data at the current usage percentage (including the current usage percentage of the central server and the current usage percentage of the edge nodes) minus the cost of delivering the target content data at the predicted usage percentage (including the predicted usage percentage of the central server and the predicted usage percentage of the edge nodes), and then divided by the cost of delivering the target content data at the current usage percentage (including the current usage percentage of the central server and the current usage percentage of the edge nodes). The cost savings rate status is either high cost savings rate or low cost savings rate. The high cost savings rate status indicates that the target content data can save a significant amount of delivery costs by increasing the number of edge nodes. The low cost savings rate status indicates that the target content data can save a small amount or no delivery costs by increasing the number of edge nodes. For content data in the low cost savings rate status, even increasing the number of edge nodes cannot improve the delivery cost and will also result in low utilization of edge nodes.

[0024] The target delivery quantity refers to the number of deliveries to edge nodes when the cost savings rate is highest. The target content data is delivered to edge nodes according to the target delivery quantity to maximize the benefits.

[0025] Step S240: When the cost saving rate of the target content data is in a high saving rate state, the target content data is distributed to multiple target edge nodes corresponding to the target delivery quantity.

[0026] Specifically, high-cost-saving target content data is distributed to multiple target edge nodes with a target delivery volume, thereby improving the utilization rate of target content data on target edge nodes. In this way, high-cost-saving content data is preferentially distributed to multiple edge nodes, thereby improving the utilization rate of each edge node and solving the problem of low edge node utilization caused by existing content distribution methods.

[0027] In one embodiment, the step of using a prediction model based on the attribute information to predict the predicted usage percentage of the target content data across multiple edge nodes under simulated delivery quantities includes: The simulated number of times the target content data is delivered to the edge node is obtained by adding a preset number of times the target content data is delivered to the edge node based on the current number of times the target content data is delivered to the edge node. The current delivery quantity of the central server, the simulated delivery quantity of the edge nodes, and the attribute information of the target content data are input into the prediction model. The prediction model is then used to output the predicted usage percentage of the target content data on different delivery objects. The predicted usage percentage of the target content data on different delivery objects includes the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity, and the predicted usage percentage of the target content data on the central server.

[0028] Specifically, the preset delivery quantity can be customized according to specific business scenarios. The preset delivery quantity is added to the current delivery quantity to obtain the simulated delivery quantity. The target content data is simulatedly delivered to multiple edge nodes corresponding to the simulated delivery quantity. Then, the prediction model is used to combine the current delivery quantity of the central server, the simulated delivery quantity of the edge nodes, and the attribute information of the target content data to predict the predicted usage ratio of the target content data on different delivery objects. The attribute information specifically includes content playback duration, bitrate, network service provider (ISP), regional traffic weight, historical usage ratio of the target content data on different delivery objects, and traffic data of the target content data on different delivery objects. The prediction model is a pre-trained XGBoost model.

[0029] By customizing preset delivery quantities, delivery strategies can be flexibly adjusted based on the unique needs of different business scenarios. This allows target content data to reach the appropriate audience more accurately. For example, for popular film and television content, the preset delivery quantity can be increased during peak viewing periods to ensure more users can access the content in a timely manner, thereby improving content exposure and usage. Simultaneously, by simulating delivery to multiple edge nodes and combining predictive models to accurately analyze the predicted usage ratio of target content data across different audiences, it helps optimize the allocation of delivery resources. Taking Internet Service Providers (ISPs) as an example, by rationally allocating delivery quantities based on the user traffic and usage habits of different ISPs, the smoothness of content playback and user experience across ISP networks can be improved.

[0030] During simulated deployment, combining the current deployment quantity from the central server with the simulated deployment quantity from edge nodes allows for a more comprehensive assessment of resource utilization. By considering the attribute information of the target content data, such as playback duration and bitrate, predictive models can avoid over- or under-deployment of resources. For content with shorter playback duration and lower bitrate, deployment resources can be appropriately reduced, allocating more resources to high-demand content, thereby improving overall resource utilization efficiency and reducing operating costs.

[0031] By considering the attribute information of regional traffic weight, precise targeting of content can be achieved based on the needs of users in different regions. For regions with high traffic, the number of simulated campaigns can be increased to ensure that users in those regions can quickly access the target content data, thereby improving the content's dissemination effect in that region. Simultaneously, by combining the historical usage percentage and traffic data of the target content in different regions, the regional targeting strategy can be further optimized to balance traffic distribution across regions and avoid situations where traffic is overloaded or insufficient in certain areas.

[0032] The predictive model incorporates historical usage percentages and traffic data of target content across different audiences, fully leveraging the value of historical data. Through analysis and learning from historical data, the predictive model can more accurately predict future usage percentages, providing strong support for adjusting targeting strategies. For example, if a target audience has historically had a high usage percentage for a particular type of content, the number of simulated campaigns targeting that audience can be appropriately increased in subsequent campaigns to enhance the relevance and appeal of the content.

[0033] In one embodiment, determining the target deployment quantity of the target content data on edge nodes based on a comparison between the current usage percentage of the target content data on multiple edge nodes under the current deployment quantity and the predicted usage percentage of the target content data on multiple edge nodes under the simulated deployment quantity includes: When the difference between the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity and the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity is greater than or equal to a preset percentage difference, the simulated delivery quantity is taken as the current delivery quantity of the target content data for the edge nodes. The steps of adding a preset delivery quantity to the current delivery quantity of the target content data for the edge nodes to obtain the simulated delivery quantity of the target content data for the edge nodes, and inputting the current delivery quantity of the central server, the simulated delivery quantity of the edge nodes, and the attribute information of the target content data into the prediction model, and using the prediction model to output the predicted usage percentage of the target content data on different delivery objects, and accumulating the number of iterations; Until the number of iterations exceeds the preset number of iterations, and the difference between the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity and the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity is less than or equal to the preset percentage difference, the current simulated delivery quantity is determined as the target delivery quantity of the target content data for the edge nodes.

[0034] Specifically, if the difference between the predicted distribution ratio of the target content data on multiple edge nodes under the simulated distribution quantity and the current usage ratio of the target content data on multiple edge nodes under the current distribution quantity is greater than or equal to the preset ratio difference, it means that increasing the number of edge nodes distributed to the target content data can significantly improve the cost-saving rate. In this case, the simulated distribution quantity is used as the current distribution quantity to continue simulating an increase in the number of edge nodes distributed to the target content data. This process is repeated to determine whether the predicted usage ratio after increasing the distribution quantity of edge nodes can significantly exceed the current usage ratio. The simulated distribution quantity is then added in this way until the difference between the predicted usage ratio and the current usage ratio is less than the preset ratio difference, and the number of iterations is greater than the preset number of iterations. At this point, the simulation distribution quantity is stopped. That is, at this time, the multiple edge nodes simulated for the target content data result in the highest cost-saving rate for the target content data. The simulated distribution quantity corresponding to the point where the iteration stops is then used as the target distribution quantity.

[0035] The preset number of times is greater than or equal to 1, that is, at least one cycle in which the difference between the predicted delivery ratio of the target content data on multiple edge nodes under the simulated delivery quantity and the current usage ratio of the target content data on multiple edge nodes under the current delivery quantity is greater than or equal to the preset ratio difference.

[0036] By continuously iterating and overlaying simulated delivery quantities to determine the target delivery quantity, the most cost-effective delivery strategy can be precisely identified. This means that businesses can achieve maximum return on investment with minimal cost during content distribution. For example, for online education platforms, distributing content such as course videos requires significant storage and bandwidth resources. By using this technology to determine the target delivery quantity, the platform can significantly reduce resource investment costs at edge nodes while ensuring normal user access and content usage. Furthermore, for content with highly fluctuating traffic, such as promotional materials for popular events or limited-time sales information, the delivery quantity can be dynamically adjusted based on actual conditions, avoiding resource waste and maximizing cost-effectiveness.

[0037] As time goes by and the market environment changes, users' content needs and usage habits will continue to evolve. Through continuous simulation and iterative analysis, the system can automatically adapt to these changes and adjust its content delivery strategy accordingly. For example, with the development of mobile internet and the increasing proportion of users accessing content via mobile devices, the system can optimize the number of deliveries to relevant edge nodes on mobile devices to better meet user needs.

[0038] In one embodiment, after determining the current simulated delivery quantity as the target delivery quantity for the target content data at the edge nodes until the number of iterations exceeds a preset number, and the difference between the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity and the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity is less than or equal to the preset percentage difference, the method further includes: The predicted delivery parameter value is determined by multiplying the predicted usage percentage of the target content data on multiple edge nodes with the delivery traffic of the target content data on multiple edge nodes. The current delivery parameter value is determined by multiplying the current usage percentage of the target content data on multiple edge nodes with the delivery traffic of the target content data on multiple edge nodes. When the predicted delivery parameter value is greater than the current delivery parameter value, the cost saving rate of the target content data is determined to be a high saving rate state. When the predicted delivery parameter value is less than or equal to the current delivery parameter value, the cost saving rate of the target content data is determined to be in a low saving rate state.

[0039] Specifically, the predicted targeting parameter value is determined by multiplying the predicted usage percentage by the targeted traffic, or by the weighted sum of the predicted usage percentage and the targeted traffic. Similarly, the current targeting parameter value is determined by multiplying the current usage percentage by the targeted traffic, or by the weighted sum of the current usage percentage and the targeted traffic.

[0040] The predicted and current delivery parameter values ​​are compared. This, combined with the delivery traffic of the target content data and its usage percentage on edge nodes, comprehensively assesses the change in cost savings rate after simulating an increase in the number of edge nodes. If the predicted delivery parameter value is greater than the current value, it indicates that increasing the number of target content data deliveries on edge nodes can improve the cost savings rate, and this state is considered high. Conversely, if the predicted delivery parameter value is less than or equal to the current value, it indicates that increasing the number of target content data deliveries on edge nodes cannot improve the cost savings rate, and this state is considered low.

[0041] By leveraging the aforementioned mechanism for assessing the relationship between the quantity of target content data deployed at edge nodes and cost savings, precise cost optimization can be achieved. When the target content data is determined to be in a high-saving state, appropriately increasing the quantity of target content data deployed at edge nodes can significantly reduce overall operating costs. For example, for large video distribution platforms, increasing the deployment of popular videos at edge nodes reduces the traffic pressure on central servers, lowers bandwidth costs, improves user access speed, reduces user churn caused by network latency, and indirectly increases the revenue of the content platform.

[0042] When the target content data is at a low cost-saving rate, this avoids the waste of resources caused by blindly increasing the number of deployments. Instead, it concentrates limited edge node resources on content that can generate high cost savings. Taking cloud storage services as an example, for frequently accessed files, the deployment of these files on edge nodes is increased, while for files with extremely low access volume, the deployment quantity is kept low, thereby improving the resource utilization of the entire storage system.

[0043] As the number of edge nodes increases, the number of copies of the target content data also increases accordingly, which improves data security to some extent. Even if a certain edge node fails or is attacked, the data copies on other edge nodes can still provide services normally, ensuring data availability. By increasing the deployment of transaction data on edge nodes, the risk of data loss or leakage due to single points of failure is reduced.

[0044] In one embodiment, when the cost saving rate of the target content data is in a high saving rate state, distributing the target content data to multiple target edge nodes corresponding to the target delivery quantity includes: When the cost saving rate of the target content data is in a high saving rate state, obtain the node information of each edge node; Edge nodes whose node information satisfies the distribution conditions of the target content data are selected as candidate nodes; Select multiple candidate nodes corresponding to the target deployment quantity as target edge nodes; The target content data is distributed to the target edge nodes corresponding to the target delivery quantity.

[0045] Specifically, when the cost-saving rate of the target content data is determined to be high, it is also necessary to determine the node information of each edge node in order to select the target edge nodes that support the storage of the target content data. Multiple edge nodes whose node information meets the distribution conditions for the target content data are selected as the target edge nodes for the target delivery quantity, thereby distributing the target content data to the multiple target edge nodes corresponding to the target delivery quantity.

[0046] Edge nodes are located at the edge of the network, closer to end users. When a user requests target content data, the data can be obtained directly from the nearest edge node without having to travel a long distance through the network to the central server and back, greatly shortening the data transmission path and significantly reducing data access latency. Therefore, distributing target content data to multiple target edge nodes is equivalent to performing data redundancy backup. Even if one edge node fails or cannot function properly due to network problems, other edge nodes can still continue to provide data services to users, ensuring data availability.

[0047] The target content data is stored and distributed at the edge nodes, enabling most data access requests to be completed within the edge network. This reduces the traffic pressure and application costs on the central server, lowers the traffic requirements of the central server, and improves the utilization rate of the edge nodes.

[0048] In one embodiment, edge nodes whose node information satisfies the distribution conditions of the target content data are selected as candidate nodes, including: When the remaining available capacity of the current edge node is greater than the data capacity of the target content data, and the service capability of the current edge node meets the service requirements of the target content data, the current edge node is determined as the candidate node.

[0049] Specifically, the ability of an edge node to store target content data is determined by comprehensively considering its remaining available capacity and data service capabilities. If the remaining available capacity of an edge node exceeds the data capacity of the target content data, and the edge node's service capabilities meet the service requirements of the target content data, then the edge node is considered a candidate node for storing the target content data. The edge node's service capabilities specifically include concurrent request count, query rate per second, cache hit rate, data transmission bandwidth, transmission latency and jitter, failure rate, fault tolerance, operational response efficiency, multi-bitrate adaptive capability, format compatibility, and content security storage capabilities. The service requirements for the target content data specifically include the hardware requirements of the requesting device and the user's request requirements for the target content data.

[0050] This comprehensive evaluation and screening mechanism ensures that target content data is stored on the most suitable edge nodes, effectively improving data storage quality and service efficiency. On one hand, appropriate node selection reduces latency and jitter during data transmission, providing users with a smoother and more stable experience when requesting data. For example, in video playback scenarios, low latency and stable transmission avoid video stuttering and buffering issues, allowing users to enjoy high-definition, smooth video content. On the other hand, considering the multi-bitrate adaptive capabilities and format compatibility of edge nodes meets the diverse needs of different requesting devices and users. Whether on mobile phones, tablets, or computers, users can obtain target content data at the optimal bitrate and format, improving data availability and applicability.

[0051] Storage strategies based on comprehensive edge node evaluation can optimize resource allocation and improve the overall performance of edge computing networks. By rationally allocating data storage tasks, it avoids situations where some edge nodes are overloaded while other nodes are idle, thus making fuller use of the network's resources. This not only helps reduce operating costs but also enhances the scalability and flexibility of the entire system, providing strong support for future business development and data growth.

[0052] In one embodiment, after determining the cost-saving rate status of the target content data and the target deployment quantity of the target content data on multiple edge nodes based on a comparison between the current usage percentage of the target content data on multiple edge nodes under the current deployment quantity and the predicted usage percentage of the target content data on multiple edge nodes under the simulated deployment quantity, the method further includes: When the cost saving rate of the target content data is in a low cost saving rate state, the target content data is cleared from each of the edge nodes where the target content data is stored.

[0053] Specifically, when the cost-saving rate of the target content data is in a low-cost-saving rate state, it indicates that the target content data is accessed less frequently. To improve the utilization of edge nodes, the target content data is removed from the edge nodes that store it. This effectively frees up storage space on the edge nodes, allowing more content data with high cost-saving rates to be stored, thereby improving the response speed of edge nodes to frequently accessed content. When users request this high-cost-saving content, the edge nodes can quickly provide services, reducing data transmission latency and greatly enhancing the user experience.

[0054] Because edge nodes no longer reserve storage space for infrequently accessed content data, unnecessary storage overhead is reduced. This also lowers the energy consumption of edge nodes, as storing and maintaining large amounts of data requires significant electricity. Furthermore, edge nodes are better able to handle sudden surges in traffic because they store high-value content data.

[0055] Figure 2 This is a flowchart illustrating a data distribution method in one embodiment. It should be understood that, although... Figure 2 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0056] In one embodiment, such as Figure 3 As shown, a data distribution device is provided, comprising: The acquisition module 310 is used to acquire attribute information of target content data and current content delivery information, wherein the current content delivery information includes the current delivery quantity of the target content data for different delivery objects, and the current usage ratio of the target content data on each edge node under the current delivery quantity; Prediction module 320 is used to use a prediction model to predict the predicted usage ratio of the target content data on multiple edge nodes under the simulated delivery quantity based on the attribute information, wherein the simulated delivery quantity is greater than the current delivery quantity; The determination module 330 is used to determine the cost saving rate status of the target content data and the target delivery quantity of the target content data on the edge nodes based on the comparison result between the current usage ratio of the target content data on multiple edge nodes under the current delivery quantity and the predicted usage ratio of the target content data on multiple edge nodes under the simulated delivery quantity. The distribution module 340 is used to distribute the target content data to multiple target edge nodes corresponding to the target delivery quantity when the cost saving rate of the target content data is in a high saving rate state.

[0057] In one embodiment, the prediction module 320 is further configured to: The simulated number of times the target content data is delivered to the edge node is obtained by adding a preset number of times the target content data is delivered to the edge node based on the current number of times the target content data is delivered to the edge node. The current delivery quantity of the central server, the simulated delivery quantity of the edge nodes, and the attribute information of the target content data are input into the prediction model. The prediction model is then used to output the predicted usage percentage of the target content data on different delivery objects. The predicted usage percentage of the target content data on different delivery objects includes the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity, and the predicted usage percentage of the target content data on the central server.

[0058] In one embodiment, the determining module 330 is further configured to: When the difference between the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity and the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity is greater than or equal to a preset percentage difference, the simulated delivery quantity is taken as the current delivery quantity of the target content data for the edge nodes. The steps of adding a preset delivery quantity to the current delivery quantity of the target content data for the edge nodes to obtain the simulated delivery quantity of the target content data for the edge nodes, and inputting the current delivery quantity of the central server, the simulated delivery quantity of the edge nodes, and the attribute information of the target content data into the prediction model, and using the prediction model to output the predicted usage percentage of the target content data on different delivery objects, and accumulating the number of iterations; Until the number of iterations exceeds the preset number of iterations, and the difference between the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity and the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity is less than or equal to the preset percentage difference, the current simulated delivery quantity is determined as the target delivery quantity of the target content data for the edge nodes.

[0059] In one embodiment, the determining module 330 is further configured to: The predicted delivery parameter value is determined by multiplying the predicted usage percentage of the target content data on multiple edge nodes with the delivery traffic of the target content data on multiple edge nodes. The current delivery parameter value is determined by multiplying the current usage percentage of the target content data on multiple edge nodes with the delivery traffic of the target content data on multiple edge nodes. When the predicted delivery parameter value is greater than the current delivery parameter value, the cost saving rate of the target content data is determined to be a high saving rate state. When the predicted delivery parameter value is less than or equal to the current delivery parameter value, the cost saving rate of the target content data is determined to be in a low saving rate state.

[0060] In one embodiment, the distribution module 340 is further configured to: When the cost saving rate of the target content data is in a high saving rate state, obtain the node information of each edge node; Edge nodes whose node information satisfies the distribution conditions of the target content data are selected as candidate nodes; Select multiple candidate nodes corresponding to the target deployment quantity as target edge nodes; The target content data is distributed to the target edge nodes corresponding to the target delivery quantity.

[0061] In one embodiment, the distribution module 340 is further configured to: When the remaining available capacity of the current edge node is greater than the data capacity of the target content data, and the service capability of the current edge node meets the service requirements of the target content data, the current edge node is determined as the candidate node.

[0062] In one embodiment, the distribution module 340 is further configured to: When the cost saving rate of the target content data is in a low cost saving rate state, the target content data is cleared from each of the edge nodes where the target content data is stored.

[0063] like Figure 4 As shown, this application provides a computer device including a processor 711, a communication interface 712, a memory 713, and a communication bus 714, wherein the processor 711, the communication interface 712, and the memory 713 communicate with each other through the communication bus 714. Memory 713 is used to store computer programs; When the processor 711 executes the program stored in the memory 713, it implements the data distribution method provided in any of the foregoing method embodiments.

[0064] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0065] In one embodiment, the data distribution apparatus provided in this application can be implemented as a computer program, which can be implemented in the form of, for example, Figure 4 It runs on the computer device shown. The computer device's memory can store the various program modules that make up the data distribution device, for example, Figure 3 The diagram shows an acquisition module 310, a prediction module 320, a determination module 330, and a distribution module 340. The computer program comprised of these modules causes the processor to execute the data distribution methods of the various embodiments of this application described in this specification.

[0066] Figure 4 The computer device shown can be used as follows Figure 3 The acquisition module 310 in the data distribution device shown acquires attribute information and current content delivery information of the target content data. The current content delivery information includes the current delivery quantity of the target content data for different delivery targets and the current usage percentage of the target content data on each edge node under the current delivery quantity. The computer device can use the prediction module 320 to use a prediction model based on the attribute information to predict the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity, where the simulated delivery quantity is greater than the current delivery quantity. The computer device can use the determination module 330 to determine the cost-saving rate status of the target content data and the target delivery quantity of the target content data on the edge nodes based on the comparison result between the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity and the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity. The computer device can use the distribution module 340 to distribute the target content data to multiple target edge nodes corresponding to the target delivery quantity when the cost-saving rate status of the target content data is a high-saving rate status.

[0067] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the data distribution method provided in any of the foregoing method embodiments.

[0068] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0069] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0070] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also mean including the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that alternatives or substitutions may be used.

[0071] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A data distribution method, characterized in that, The method includes: Obtain the attribute information of the target content data and the current content delivery information, wherein the current content delivery information includes the current delivery quantity of the target content data for different delivery objects, and the current usage ratio of the target content data in different delivery objects, wherein the delivery object is the central server or the edge node; Using a prediction model based on the attribute information, the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity is predicted, wherein the simulated delivery quantity is greater than the current delivery quantity; Based on the comparison between the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity and the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity, the cost saving rate status of the target content data and the target delivery quantity of the target content data on the edge nodes are determined. When the cost saving rate of the target content data is in a high saving rate state, the target content data is distributed to multiple target edge nodes corresponding to the target delivery quantity.

2. The method according to claim 1, characterized in that, The step of using a prediction model based on the attribute information to predict the predicted usage percentage of the target content data across multiple edge nodes under simulated delivery quantities includes: The simulated number of times the target content data is delivered to the edge node is obtained by adding a preset number of times the target content data is delivered to the edge node based on the current number of times the target content data is delivered to the edge node. The current delivery quantity of the central server, the simulated delivery quantity of the edge nodes, and the attribute information of the target content data are input into the prediction model. The prediction model is then used to output the predicted usage percentage of the target content data on different delivery objects. The predicted usage percentage of the target content data on different delivery objects includes the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity, and the predicted usage percentage of the target content data on the central server.

3. The method according to claim 2, characterized in that, Based on a comparison between the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity and the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity, the target delivery quantity of the target content data is determined at the edge nodes, including: When the difference between the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity and the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity is greater than or equal to a preset percentage difference, the simulated delivery quantity is taken as the current delivery quantity of the target content data for the edge nodes. The steps of adding a preset delivery quantity to the current delivery quantity of the target content data for the edge nodes to obtain the simulated delivery quantity of the target content data for the edge nodes, and inputting the current delivery quantity of the central server, the simulated delivery quantity of the edge nodes, and the attribute information of the target content data into the prediction model, and using the prediction model to output the predicted usage percentage of the target content data on different delivery objects, and accumulating the number of iterations; Until the number of iterations exceeds the preset number of iterations, and the difference between the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity and the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity is less than or equal to the preset percentage difference, the current simulated delivery quantity is determined as the target delivery quantity of the target content data for the edge nodes.

4. The method according to claim 3, characterized in that, The method further includes the following steps: Until the number of iterations exceeds a preset number, and the difference between the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity and the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity is less than or equal to the preset percentage difference, the method determines the current simulated delivery quantity as the target delivery quantity of the target content data for the edge nodes. The predicted delivery parameter value is determined by multiplying the predicted usage percentage of the target content data on multiple edge nodes with the delivery traffic of the target content data on multiple edge nodes. The current delivery parameter value is determined by multiplying the current usage percentage of the target content data on multiple edge nodes with the delivery traffic of the target content data on multiple edge nodes. When the predicted delivery parameter value is greater than the current delivery parameter value, the cost saving rate of the target content data is determined to be a high saving rate state. When the predicted delivery parameter value is less than or equal to the current delivery parameter value, the cost saving rate of the target content data is determined to be in a low saving rate state.

5. The method according to claim 4, characterized in that, When the cost saving rate of the target content data is in a high saving rate state, distributing the target content data to multiple target edge nodes corresponding to the target delivery quantity includes: When the cost saving rate of the target content data is in a high saving rate state, obtain the node information of each edge node; Edge nodes whose node information satisfies the distribution conditions of the target content data are selected as candidate nodes; Select multiple candidate nodes corresponding to the target deployment quantity as target edge nodes; The target content data is distributed to the target edge nodes corresponding to the target delivery quantity.

6. The method according to claim 5, characterized in that, Edge nodes whose node information satisfies the distribution conditions of the target content data are selected as candidate nodes, including: When the remaining available capacity of the current edge node is greater than the data capacity of the target content data, and the service capability of the current edge node meets the service requirements of the target content data, the current edge node is determined as the candidate node.

7. The method according to claim 1, characterized in that, Based on a comparison between the current usage percentage of the target content data on multiple edge nodes under the current delivery quantity and the predicted usage percentage of the target content data on multiple edge nodes under the simulated delivery quantity, after determining the cost saving rate status of the target content data and the target delivery quantity of the target content data on the edge nodes, the method further includes: When the cost saving rate of the target content data is in a low cost saving rate state, the target content data is cleared from each of the edge nodes where the target content data is stored.

8. A data distribution device, characterized in that, The device includes: The acquisition module is used to acquire attribute information of target content data and current content delivery information, wherein the current content delivery information includes the current delivery quantity of the target content data for different delivery objects, and the current usage ratio of the target content data on each edge node under the current delivery quantity; The prediction module is used to use a prediction model based on the attribute information to predict the predicted usage ratio of the target content data on multiple edge nodes under the simulated delivery quantity, wherein the simulated delivery quantity is greater than the current delivery quantity; The determination module is used to determine the cost saving rate status of the target content data and the target deployment quantity of the target content data on the edge nodes based on the comparison result between the current usage ratio of the target content data on multiple edge nodes under the current deployment quantity and the predicted usage ratio of the target content data on multiple edge nodes under the simulated deployment quantity. The distribution module is used to distribute the target content data to multiple target edge nodes corresponding to the target delivery quantity when the cost saving rate of the target content data is in a high saving rate state.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images