Network resource allocation method and apparatus, computer program product, and electronic device

Abstract

The application discloses a network resource allocation method and device, a computer program product and an electronic device. It relates to the field of big data or other related fields. The method comprises: obtaining resource load data of a network platform in a preset time period, and obtaining network behavior data of users using the network platform in the preset time period; in the case that the network platform is in a first network state, generating a first resource scheduling strategy according to the resource load data and the network behavior data, and sending the first resource scheduling strategy to a client; in the case that the network platform is in a second network state, adjusting the first resource scheduling strategy to obtain a second resource scheduling strategy, and sending the second resource scheduling strategy to the client, wherein the client performs a resource scheduling operation according to the second resource scheduling strategy. Through the application, the technical problem of low resource utilization and poor response capability in network resource scheduling in the related art is solved.

Description

Technical Field

[0001] This application relates to the field of big data or other related fields, and more specifically, to a method, apparatus, computer program product, and electronic device for allocating network resources. Background Technology

[0002] With the rapid development of internet technology and the increasing popularity of digital services, the efficient management and rational scheduling of network resources have become key technical areas for ensuring online service performance and user experience. In today's highly interconnected network environment, user behavior exhibits unprecedented uncertainty and dynamism, leading to rapidly changing network resource demands. For example, online video platforms may experience sudden surges in bandwidth demand during certain periods due to a large influx of viewers, while e-commerce platforms may encounter a surge in server load during major promotional events. The network resource demands of different user groups vary significantly across different time periods, requiring network resource scheduling systems to possess high flexibility and responsiveness.

[0003] However, traditional network resource scheduling methods, especially static resource allocation strategies, are insufficient to meet these requirements. These methods typically rely on pre-defined resource allocation schemes and lack real-time monitoring and dynamic adjustment mechanisms. In practical applications, static allocation strategies often lead to unbalanced resource allocation. For example, some resources may be idle during off-peak hours, while others may be overused during peak hours. This not only wastes resources but may also affect service response speed and user satisfaction due to resource shortages. Furthermore, because predefined scheduling rules do not consider the complexity and variability of user behavior, such as event-driven patterns (holidays, major news events, etc.), the system often cannot accurately predict and respond to real-time traffic fluctuations, leading to network congestion or uneven resource allocation, thereby affecting overall network performance and user experience.

[0004] There is currently no effective solution to the technical problems of low resource utilization and poor response capability when scheduling network resources in related technologies. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, computer program product, and electronic device for allocating network resources, in order to solve the technical problems of low resource utilization and poor response capability in network resource scheduling in related technologies.

[0006] To achieve the above objectives, according to one aspect of this application, a method for allocating network resources is provided. The method includes: acquiring resource load data of a network platform within a preset time period, and acquiring network behavior data of users using the network platform within the preset time period; when the network platform is in a first network state, generating a first resource scheduling strategy based on the resource load data and network behavior data, and sending the first resource scheduling strategy to a client, wherein, upon receiving the first resource scheduling strategy, the client performs a resource scheduling operation according to the first resource scheduling strategy, the first resource scheduling strategy including resource allocation strategies of multiple dimensions; when the network platform is in a second network state, adjusting the first resource scheduling strategy to obtain a second resource scheduling strategy, and sending the second resource scheduling strategy to the client, wherein, upon receiving the second resource scheduling strategy, the client performs a resource scheduling operation according to the second resource scheduling strategy, the resource demand in the second network state is higher than the resource demand in the first network state, the second resource scheduling strategy including resource allocation strategies of multiple dimensions.

[0007] Furthermore, generating a first resource scheduling strategy based on resource load data and network behavior data includes: acquiring a resource analysis model, wherein the resource analysis model is used to identify user behavior patterns and network resource usage trends of the network platform in different time periods; inputting resource load data and network behavior data into the resource analysis model and outputting resource demand analysis results, wherein the resource demand analysis results include user behavior patterns and network resource usage trends within a preset time period; acquiring user distribution data and resource constraints of the network platform, determining a first optimization objective based on the user distribution data and resource constraints, processing the resource demand analysis results based on the first optimization objective, and generating a first resource scheduling strategy, wherein the resource constraints are used to indicate the restrictions that need to be met in resource scheduling.

[0008] Furthermore, the resource analysis model is trained in the following way: acquiring historical network behavior data and historical resource load data of the network platform within a historical time period, associating the historical network behavior data and historical resource load data to obtain associated data, wherein the association method is to match the resource load situation of historical network behavior data and historical resource load data at different time points within the historical time period; extracting feature data from the associated data to obtain a historical feature set, wherein the historical feature set includes at least one of the following: user access record information, resource usage data, and peak time; acquiring historical behavior results within the historical time period, and training the preset resource analysis model based on the historical feature set and historical behavior results to obtain the resource analysis model.

[0009] Further, adjusting the first resource scheduling strategy to obtain the second resource scheduling strategy includes: obtaining a resource scheduling model; adjusting the first resource scheduling strategy using the resource scheduling model to obtain a transitional resource scheduling strategy; adjusting the transitional resource scheduling strategy using a genetic algorithm to obtain N candidate resource scheduling sub-strategies, where N is a positive integer; selecting a target resource scheduling sub-strategy from the N candidate resource scheduling sub-strategies; constructing a resource scheduling structure based on the target resource scheduling sub-strategy; and adjusting the transitional resource scheduling strategy using the resource scheduling structure to obtain the second resource scheduling strategy.

[0010] Furthermore, adjusting the first resource scheduling strategy using a resource scheduling model to obtain a transitional resource scheduling strategy includes: acquiring user demand data, calculating the matching degree between the user demand data and the first resource scheduling strategy to obtain scheduling deviation information, wherein the scheduling deviation information includes at least one of the following: resource type, expected allocation amount, actual demand amount, and matching deviation value; acquiring resource rules, inputting the resource rules and scheduling deviation information into a dynamic scheduling model, and outputting resource scheduling results; analyzing the resource scheduling results using network resource analysis tools to generate a first resource allocation node, wherein the first resource allocation node is used to indicate the path node information in the network platform that needs to be adjusted, and the path node information includes at least one of the following: server node, storage device node, and bandwidth allocation node; and adjusting the first resource scheduling strategy based on the first resource allocation node using a resource optimization algorithm to obtain a transitional resource scheduling strategy.

[0011] Further, selecting the target resource scheduling sub-strategy from N candidate resource scheduling sub-strategies includes: obtaining a second optimization objective and determining the weight of each resource indicator in the second optimization objective to obtain Y resource indicator weights, wherein the second optimization objective includes at least one of the following: resource utilization indicator and response time indicator, and Y is a positive integer; for a candidate resource scheduling sub-strategy, obtaining the Y resource scheduling indicator values ​​of the candidate resource scheduling sub-strategy, calculating the scheme score of the candidate resource scheduling sub-strategy based on the Y resource indicator weights and Y resource scheduling indicator values, and obtaining the scheme score; extracting the candidate resource scheduling sub-strategy with the highest score from the N candidate resource scheduling sub-strategies based on the N scheme scores, and determining the candidate resource scheduling sub-strategy with the highest score as the target resource scheduling sub-strategy.

[0012] Furthermore, constructing the resource scheduling structure based on the target resource scheduling sub-policy includes: determining a second resource allocation node based on the target resource scheduling sub-policy, wherein the second resource allocation node is used to indicate the path node information that needs to be adjusted in the network platform, and the path node information includes at least one of the following: server nodes, storage device nodes, and bandwidth allocation nodes; determining the resource flow status between all nodes of the second resource allocation node through topology analysis tools, wherein the resource flow status is used to indicate the path of resources flowing from one node to another; acquiring user demand data, and determining the priority of all nodes in the second resource allocation node based on the user demand data and the target resource scheduling sub-policy; acquiring resource rules, and constructing a scheduling rule set using the resource rules, wherein the scheduling rule set includes resource allocation conditions, node load thresholds, and scheduling trigger conditions; and constructing the resource scheduling structure based on the scheduling rule set, resource flow status, the second resource allocation node, and the priorities of all nodes.

[0013] Furthermore, the transitional resource scheduling strategy is adjusted using the resource scheduling structure to obtain a second resource scheduling strategy, which includes: inputting the target resource scheduling sub-strategy into a linear programming model and outputting primary resource allocation information, wherein the linear programming model is configured by the resource scheduling structure, and the primary resource allocation information is used to indicate the allocation scheme of network resources among different nodes; acquiring resource usage data and system performance data of the network platform, and determining resource allocation deviation information based on the resource usage data and system performance data; performing secondary optimization on the resource allocation deviation information based on the incremental optimization algorithm to obtain secondary resource allocation information, wherein the secondary optimization is used to adjust the distribution of resources among different nodes; and generating a second resource scheduling strategy based on the primary and secondary resource allocation information.

[0014] To achieve the above objectives, according to another aspect of this application, a network resource allocation apparatus is provided. The apparatus includes: an acquisition unit, configured to acquire resource load data of a network platform within a preset time period, and acquire network behavior data of users using the network platform within the preset time period; a generation unit, configured to generate a first resource scheduling strategy based on the resource load data and network behavior data when the network platform is in a first network state, and send the first resource scheduling strategy to a client, wherein, upon receiving the first resource scheduling strategy, the client performs a resource scheduling operation according to the first resource scheduling strategy, and the first resource scheduling strategy includes resource allocation strategies of multiple dimensions; and an adjustment unit, configured to adjust the first resource scheduling strategy to obtain a second resource scheduling strategy when the network platform is in a second network state, and send the second resource scheduling strategy to the client, wherein, upon receiving the second resource scheduling strategy, the client performs a resource scheduling operation according to the second resource scheduling strategy, the resource demand of the second network state is higher than the resource demand of the first network state, and the second resource scheduling strategy includes resource allocation strategies of multiple dimensions.

[0015] According to another aspect of the present invention, a computer storage medium is also provided for storing a program, wherein the program, when running, controls the device where the computer storage medium is located to execute a network resource allocation method.

[0016] According to another aspect of the present invention, an electronic device is also provided, comprising one or more processors and a memory; the memory stores computer-readable instructions, and the processor is configured to execute the computer-readable instructions, wherein the computer-readable instructions, when executed, perform a method for allocating network resources.

[0017] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, performs a method for allocating network resources.

[0018] This application employs the following steps: acquiring resource load data of a network platform within a preset time period, and acquiring network behavior data of users using the network platform within the preset time period; when the network platform is in a first network state, generating a first resource scheduling strategy based on the resource load data and network behavior data, and sending the first resource scheduling strategy to the client, wherein, upon receiving the first resource scheduling strategy, the client executes a resource scheduling operation according to the first resource scheduling strategy, the first resource scheduling strategy including resource allocation strategies of multiple dimensions; when the network platform is in a second network state, adjusting the first resource scheduling strategy to obtain a second resource scheduling strategy, and sending the second resource scheduling strategy to the client, wherein, upon receiving the second resource scheduling strategy, the client executes a resource scheduling operation according to the second resource scheduling strategy, the resource demand in the second network state is higher than the resource demand in the first network state, the second resource scheduling strategy including resource allocation strategies of multiple dimensions, thus solving the technical problems of low resource utilization and poor response capability in network resource scheduling in related technologies. By using resource load data and network behavior data to generate a first resource scheduling strategy, then performing one-time and two-time resource allocation on the first resource scheduling strategy, and finally generating and executing the second resource scheduling strategy, the technical effect of improving network resource utilization and response efficiency is achieved. Attached Figure Description

[0019] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 This is a flowchart of a network resource allocation method provided according to an embodiment of this application;

[0021] Figure 2 This is a schematic diagram of a network resource allocation system provided according to an embodiment of this application;

[0022] Figure 3 This is a schematic diagram of an optional network resource allocation method provided according to an embodiment of this application;

[0023] Figure 4 This is a schematic diagram of a network resource allocation device according to an embodiment of this application;

[0024] Figure 5 This is a schematic diagram of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are information and data authorized by the user or fully authorized by all parties. For example, this system has an interface with the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving consent from the aforementioned user or organization.

[0029] It should be noted that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize use or refuse use.

[0030] The present invention will now be described in conjunction with preferred implementation steps. Figure 1 This is a flowchart of a network resource allocation method provided according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0031] Step S101: Obtain resource load data of the network platform within a preset time period, and obtain network behavior data of users using the network platform within the preset time period.

[0032] Faced with increasingly complex demands in network resource scheduling, the limitations of traditional scheduling technologies have become particularly apparent. In order to achieve efficient utilization of network resources, improve service responsiveness and user satisfaction, and reduce costs and performance losses caused by resource over-configuration or shortage, we can first obtain the resource load data of the network platform within a preset time period, as well as the network behavior data of users using the network platform within the corresponding time period.

[0033] Network behavior data can be obtained through technologies such as log recording systems and user tracking systems, including data on web pages visited, links clicked, applications used, access times, usage durations, and data traffic generated within a preset time period. This collected behavior data is then preprocessed to obtain network behavior data. Resource load data refers to the usage of resources such as network servers, storage devices, and bandwidth. This can be achieved through real-time monitoring of CPU usage, memory consumption, and disk read / write speeds using server monitoring tools, or by collecting and analyzing network traffic data (including upload and download speeds, peak traffic times, etc.) within a preset time period using analyzers. It can also refer to storage device usage recorded by storage management systems (including storage space occupancy, read / write operation frequency, and data transfer speed). A network platform can refer to a specific application platform. By analyzing user behavior information, the usage of network resources within a specific time period can be determined. For example, if users concentrate on accessing resources on a website within a certain time period, it may increase the server load on that website. Load monitoring tools, such as server monitoring systems and bandwidth monitoring systems, collect and analyze this data in real time to generate resource load data.

[0034] It should be noted that after obtaining the above-mentioned data, the collected raw data needs to be cleaned to remove outliers, missing values, and irrelevant information to ensure the accuracy and reliability of the data; at the same time, the data should be converted into a unified format to facilitate subsequent analysis.

[0035] Step S102: When the network platform is in the first network state, a first resource scheduling policy is generated based on resource load data and network behavior data, and the first resource scheduling policy is sent to the client. When the client receives the first resource scheduling policy, it performs resource scheduling operations according to the first resource scheduling policy. The first resource scheduling policy includes resource allocation policies of multiple dimensions.

[0036] Specifically, the first network state can refer to a scenario that is simple, with low dynamic changes, or with relatively stable resource demand. In this state, the first resource scheduling strategy can be determined directly based on resource load data and network behavior data. Specifically, resource load data and network behavior data can be input into a resource analysis model for big data analysis to generate resource demand analysis results. Then, the first resource scheduling strategy can be determined based on the resource demand analysis results. This strategy can include resource allocation strategies in multiple dimensions, such as resource allocation strategies and priority settings. For example, based on the resource demand analysis results, it can be decided to prioritize critical services during peak hours, allocate more server and bandwidth resources to the video platform, and reduce the resource priority of some non-critical services.

[0037] Step S103: When the network platform is in the second network state, the first resource scheduling strategy is adjusted to obtain the second resource scheduling strategy, and the second resource scheduling strategy is sent to the client. When the client receives the second resource scheduling strategy, it performs resource scheduling operation according to the second resource scheduling strategy. The resource demand of the second network state is higher than that of the first network state. The second resource scheduling strategy includes resource allocation strategies in multiple dimensions.

[0038] Specifically, the second network state can refer to a complex and highly dynamic network environment. In this state, the first resource scheduling strategy mentioned above cannot meet the real-time resource requirements. It is necessary to adjust the first resource scheduling strategy, such as by performing local resource optimization, to obtain the second resource scheduling strategy.

[0039] For example, a large video streaming platform may face a surge in user traffic during peak periods, such as between 8 AM and 10 AM daily. This sudden increase in video playback can lead to excessive server load and insufficient bandwidth. During these peak periods, the CPU (Central Processing Unit) utilization of some server nodes may exceed 90%, and bandwidth utilization may approach saturation, thus affecting video playback smoothness and user experience. To optimize resource utilization and improve response speed, it is necessary to acquire resource load data and network behavior data. Network behavior data can include video playback volume, user dwell time, click behavior, and geographic location information, while resource load data can include server CPU utilization, bandwidth usage, and storage space usage.

[0040] At this point, after obtaining the aforementioned data, a first resource scheduling strategy can be determined using resource load data and network behavior data. This strategy can then be further optimized using dynamic scheduling models to obtain a second resource scheduling strategy. After generating the second resource scheduling strategy, the client first deploys it to the actual network environment using an automated configuration management tool, deploying it to various resource nodes, such as servers, storage devices, and bandwidth allocation nodes. With the deployment of the second resource scheduling strategy complete, network resource scheduling begins, coordinating and managing resource allocation and scheduling operations between various resource nodes. Computing resources, storage resources, and network bandwidth are dynamically allocated according to the priorities, resource flows, and scheduling rules defined in the optimization scheme.

[0041] The network resource allocation method provided in this application involves acquiring resource load data of a network platform within a preset time period and acquiring network behavior data of users using the network platform within the preset time period. When the network platform is in a first network state, a first resource scheduling strategy is generated based on the resource load data and network behavior data, and this strategy is sent to the client. Upon receiving the first resource scheduling strategy, the client executes a resource scheduling operation according to the strategy. The first resource scheduling strategy includes resource allocation strategies across multiple dimensions. When the network platform is in a second network state, the first resource scheduling strategy is adjusted to obtain a second resource scheduling strategy. The second resource scheduling strategy is sent to the client. Upon receiving the second resource scheduling strategy, the client executes resource scheduling operations according to the second resource scheduling strategy. The resource demand of the second network state is higher than that of the first network state. The second resource scheduling strategy includes resource allocation strategies in multiple dimensions, which solves the technical problems of low resource utilization and poor response capability in network resource scheduling in related technologies. By using resource load data and network behavior data to generate the first resource scheduling strategy, and then performing one-time and two-time resource allocation on the first resource scheduling strategy, the second resource scheduling strategy is finally generated and executed, thereby achieving the technical effect of improving network resource utilization and response efficiency.

[0042] Optionally, in the network resource allocation method provided in this application embodiment, generating a first resource scheduling strategy based on resource load data and network behavior data includes: acquiring a resource analysis model, wherein the resource analysis model is used to identify user behavior patterns and network resource usage trends of the network platform in different time periods; inputting resource load data and network behavior data into the resource analysis model and outputting resource demand analysis results, wherein the resource demand analysis results include user behavior patterns and network resource usage trends within a preset time period; acquiring user distribution data and resource constraints of the network platform, determining a first optimization objective based on the user distribution data and resource constraints, processing the resource demand analysis results based on the first optimization objective, and generating a first resource scheduling strategy, wherein the resource constraints are used to indicate the restrictions that need to be met in resource scheduling.

[0043] Specifically, resource analysis models can be based on machine learning algorithms, such as Long Short-Term Memory (LSTM) networks, which are trained on large amounts of historical data to identify user behavior patterns and network resource usage trends across different time periods. During the analysis process, this model can process the input data and identify user behavior patterns. For example, it can identify certain user groups that frequently access certain resources within specific time periods, or changes in user behavior under specific external conditions, such as holidays or events. Simultaneously, it can analyze network resource usage trends, such as how access to a particular type of resource, like video streams, changes over time, or the peak times of network traffic, thereby obtaining user behavior analysis results.

[0044] To generate the first resource scheduling strategy, resource load data and network behavior data can first be input into the resource analysis model to analyze user behavior patterns and network resource usage trends, thus obtaining user behavior analysis results. Then, based on these user behavior analysis results, resource demand analysis results can be generated. The resource demand analysis results can include resource demand forecasting and resource load assessment. Resource demand forecasting is based on inferring user behavior trends to determine which resources will be heavily used in the future. Resource load assessment evaluates how these predicted resource demands will affect the existing network resource load. For example, if the demand for video streaming services will increase significantly in a certain period of time in the future, then the corresponding network resources, such as servers and bandwidth, will also face higher load pressure.

[0045] Furthermore, based on the resource demand analysis results described above, heuristic algorithms, such as genetic algorithms and particle swarm optimization algorithms, can be used to determine the optimal allocation of resources to different services or users, thus obtaining the first resource scheduling strategy. This first resource scheduling strategy can include scheduling strategies with two dimensions: resource allocation strategy and priority setting strategy. Priority setting can be determined based on the importance of the service, the priority of the user, and the scarcity of resources, using multi-objective optimization techniques to ensure that critical services or users can obtain resources preferentially when resources are insufficient. This embodiment utilizes a resource analysis model to identify user behavior patterns and resource usage trends, thereby generating a first resource scheduling strategy that meets the optimization objectives, achieving efficient resource utilization and dynamic adjustment, and improving network performance and user experience.

[0046] Optionally, in the network resource allocation method provided in this application embodiment, the resource analysis model is trained in the following manner: acquiring historical network behavior data and historical resource load data of the network platform within a historical time period, associating the historical network behavior data and historical resource load data to obtain associated data, wherein the association method is to match the resource load situation of the historical network behavior data and historical resource load data at different time points within the historical time period; extracting feature data from the associated data to obtain a historical feature set, wherein the historical feature set includes at least one of the following: user access record information, resource usage data, and peak time; acquiring historical behavior results within the historical time period, and training a preset resource analysis model based on the historical feature set and historical behavior results to obtain the resource analysis model.

[0047] Specifically, to improve the accuracy of the analysis, historical network behavior data and historical resource load data can be obtained first, along with historical behavior results for historical time periods. To analyze the relationship between historical network behavior data and historical resource load data, these two types of data can be correlated, that is, matching specific user behaviors with resource usage at corresponding points in time to obtain correlated data. Through correlation analysis, we can understand how user behavior affects network resource usage within a specific time period. For example, how does the server's CPU and bandwidth load change when a large number of users access a video streaming service? Historical network behavior data can include access records, click-through rates, dwell time information, page navigation paths, etc., for multiple users within historical time periods; while historical resource load data includes server CPU utilization, bandwidth occupancy, storage space usage, etc.

[0048] Furthermore, historical network behavior data and historical resource load data are preprocessed and feature extracted to obtain a historical feature set, which includes user access frequency, resource usage patterns, and peak times. Based on the historical feature set and historical behavior results, a big data analysis model is constructed.

[0049] Then, a resource analysis model is constructed based on the extracted historical feature set and historical behavior results. This model can be trained using machine learning algorithms such as decision trees, random forests, and deep learning models to identify patterns and regularities in historical data. For example, the random forest model integrates multiple decision trees to capture the complex nonlinear relationship between user behavior and resource load, thereby improving prediction accuracy. During model training, the model's parameters and structure are continuously adjusted based on the input historical feature set to improve prediction accuracy and generalization ability, ultimately completing the construction of the big data analysis model. The trained resource analysis model can effectively predict future user behavior patterns and resource demands, supporting intelligent scheduling of network resources. This embodiment, by training the resource analysis model, can accurately predict the resource demands of the network platform in different time periods, including the usage of computing resources, storage resources, and network bandwidth. This ensures that resource allocation accurately matches user needs, reduces resource waste, improves resource utilization efficiency, avoids over-allocation of resources, and effectively controls operating costs, providing crucial predictive basis for intelligent resource scheduling.

[0050] Optionally, in the network resource allocation method provided in this application embodiment, adjusting the first resource scheduling strategy to obtain the second resource scheduling strategy includes: obtaining a resource scheduling model; adjusting the first resource scheduling strategy using the resource scheduling model to obtain a transitional resource scheduling strategy; adjusting the transitional resource scheduling strategy using a genetic algorithm to obtain N candidate resource scheduling sub-strategies, where N is a positive integer; selecting a target resource scheduling sub-strategy from the N candidate resource scheduling sub-strategies; constructing a resource scheduling structure based on the target resource scheduling sub-strategy; and adjusting the transitional resource scheduling strategy using the resource scheduling structure to obtain the second resource scheduling strategy.

[0051] Specifically, after obtaining the first resource scheduling strategy, if the network platform is in a complex and highly dynamic network environment, the first resource scheduling strategy needs to be adjusted to obtain a second resource scheduling strategy. The resource scheduling model can be built based on complex mathematical models and machine learning algorithms, such as deep reinforcement learning and multi-objective optimization models. It can intelligently adjust resource allocation strategies while considering multiple constraints (such as resource type, geographical distribution, and business priority). Therefore, the first resource scheduling strategy can be input into the resource scheduling model, allowing the model to perform multi-objective optimization based on the current network state, user behavior predictions, and resource constraints. This allows for adjustments to resource allocation ratios and priority settings within the strategy, resulting in a transitional resource scheduling strategy aimed at balancing resource supply and demand and improving the rationality and efficiency of resource allocation.

[0052] Furthermore, genetic algorithms can be used to further adjust the transitional resource scheduling strategy. Through the evolutionary process of the genetic algorithm, multiple candidate resource scheduling sub-strategies are generated. The genetic algorithm solves complex multi-objective optimization problems by simulating the process of natural selection. That is, in each generation, the algorithm selects based on the evaluation results of each sub-strategy (such as resource utilization, system response time, user satisfaction, etc.), generates new combinations of sub-strategies through crossover operations, and introduces randomness through mutation to ensure the comprehensiveness of the search space. After multiple iterations, it gradually converges to multiple candidate resource scheduling sub-strategies.

[0053] Specifically, firstly, multiple optimization objectives are defined, such as resource utilization and response time. Then, a genetic algorithm generates a population from transitional resource scheduling strategies, with each individual representing a candidate resource scheduling sub-strategy. Through selection, crossover, and mutation operations, the algorithm progressively optimizes these candidate resource scheduling sub-strategies in each generation, allowing individuals with higher fitness to dominate the population. The fitness function is calculated based on the weighted sum of the various optimization objectives, reflecting the overall performance of each scheme. The fitness function is... , The fitness value represents the candidate resource scheduling sub-strategy x; a larger value indicates a better sub-strategy. U(x) is the resource utilization rate, representing the weighted average of the resource utilization rates of candidate resource scheduling sub-strategy x across all resource nodes. T(x) is the response time, representing the average response time of candidate resource scheduling sub-strategy x when processing user requests. and With pre-defined weights, the genetic algorithm generates multiple candidate resource scheduling sub-strategies through multiple generations of evolution.

[0054] Then, the candidate resource scheduling sub-strategies are evaluated. For example, a multi-objective optimization method can be used to comprehensively consider indicators such as resource utilization, cost, service quality, and user experience, calculating a comprehensive score for each sub-strategy. Based on the score results, the sub-strategy with the best performance is selected as the target resource scheduling sub-strategy. Finally, network topology analysis methods can be used to construct a resource scheduling structure that defines the allocation method and scheduling rules of resources among different nodes based on the target resource scheduling sub-strategy. The resource scheduling structure can include resource allocation of server clusters, bandwidth management, storage device optimization, etc., and can characterize the current distribution of network resources, the connection relationship between nodes, and the resource flow.

[0055] Furthermore, the transitional resource scheduling strategy is fine-tuned based on the resource scheduling structure to generate a second resource scheduling strategy. This includes dynamically adjusting resource priorities, reallocating specific types of resources (such as increasing server resources for computationally intensive tasks and reducing bandwidth allocation during off-peak periods), and optimizing network traffic distribution to ensure that resource allocation not only meets demand but also achieves maximum efficiency. This embodiment, by utilizing a resource scheduling model and genetic algorithm, enables fine-grained adjustment of resource allocation strategies, ensuring reasonable resource allocation across different services, user groups, and geographical locations. This avoids resource waste and over-configuration, allowing the network platform to quickly respond to changes in user demand and fluctuations in the network environment. Especially during peak periods or when resources are scarce, it can rapidly adjust resource allocation to ensure the normal operation of critical services and user experience.

[0056] Optionally, in the network resource allocation method provided in this application embodiment, adjusting the first resource scheduling strategy using a resource scheduling model to obtain a transitional resource scheduling strategy includes: acquiring user demand data, calculating the matching degree between the user demand data and the first resource scheduling strategy, and obtaining scheduling deviation information, wherein the scheduling deviation information includes at least one of the following: resource type, expected allocation amount, actual demand amount, and matching deviation value; acquiring resource rules, inputting the resource rules and scheduling deviation information into a dynamic scheduling model, and outputting resource scheduling results; analyzing the resource scheduling results using a network resource analysis tool, and generating a first resource allocation node, wherein the first resource allocation node is used to indicate the path node information that needs to be adjusted in the network platform, and the path node information includes at least one of the following: server node, storage device node, and bandwidth allocation node; and adjusting the first resource scheduling strategy according to the first resource allocation node using a resource optimization algorithm to obtain a transitional resource scheduling strategy.

[0057] Specifically, before adjusting the first resource scheduling strategy using the resource scheduling model, the resource scheduling model can first be constructed by verifying the matching degree between the first resource scheduling strategy and user needs. That is, after obtaining user demand data, the matching degree between the first resource scheduling strategy and user demand data is calculated through data query statements or big data processing frameworks to obtain scheduling deviation information. Specifically, the dataset of the first resource scheduling strategy and the dataset of actual user access and demand are first extracted from the database. Then, a difference analysis algorithm is used to calculate the difference between resource allocation in the first resource scheduling strategy and user demand data, thereby quantifying the deviation between the two and generating scheduling deviation information. The scheduling deviation information can include timestamps, resource types, expected allocation amounts, actual demand amounts, and the calculated matching deviation value.

[0058] Furthermore, based on scheduling deviation information, a dynamic scheduling model is constructed using a rule engine (i.e., resource rules) to determine dynamic scheduling. The resource rules and scheduling deviation information are then input into the dynamic scheduling model, which outputs resource scheduling results. Based on these results, the resource allocation node requiring optimization is located, thus obtaining the first resource allocation node. The rule engine (i.e., resource rules) can define a set of business rules to determine whether the scheduling plan needs adjustment based on the magnitude and type of the scheduling deviation. For example, when the resource load of a node exceeds a set threshold, a rescheduling rule is triggered. If adjustment is deemed necessary, resource usage and user demand are continuously monitored. Real-time data is collected using real-time monitoring tools. Once the deviation between actual resource usage and the scheduling plan exceeds a preset threshold, a response is immediately made according to the rules. When a rule is triggered, the corresponding adjustment strategy is executed, including reallocating resources, switching service nodes, and increasing resource redundancy.

[0059] When analyzing resource scheduling results using network resource analysis tools, network topology analysis tools can be used to analyze the nodes and connections in the network, identify nodes with high load or low resource utilization efficiency in the current scheduling plan, and then combine them with resource flow analysis tools to determine the allocation and usage path of resources in the network, thereby more accurately locating the first resource allocation node that needs adjustment. The first resource allocation node is used to indicate path node information, which includes at least one of the following: server node, storage device node, and bandwidth allocation node.

[0060] Furthermore, a transitional resource scheduling strategy is obtained by adjusting the first resource scheduling strategy based on the resource allocation nodes using resource optimization algorithms. These resource optimization algorithms can be heuristic algorithms, such as simulated annealing. These algorithms are suitable for complex optimization problems and can quickly find near-optimal resource allocation schemes through random search and evolutionary strategies. For example, a genetic algorithm first generates an initial set of solutions (i.e., the first resource scheduling strategy), and then iteratively generates better solutions through operations such as selection, crossover, and mutation. After each iteration, the fitness of each solution, i.e., the effectiveness of resource allocation, is calculated, and the optimal solution is retained for the next generation's evolution. A heuristic scheduling algorithm is then used to perform secondary scheduling on the first resource allocation nodes, adjusting and locally optimizing the first resource scheduling strategy to obtain the transitional resource scheduling strategy. The goal of local optimization is to improve the overall network performance through finer adjustments within specific resource allocation nodes or a local area. This is achieved by using local search algorithms (such as gradient descent or hill climbing) to find the optimal resource allocation method within a local area. For example, in a server cluster, the load distribution of each server is fine-tuned using gradient descent to optimize overall resource utilization. During local optimization, real-time monitoring tools are used to monitor node load and network traffic, and resource scheduling strategies are adjusted in real time to cope with sudden changes in demand. This embodiment achieves intelligent and efficient resource allocation by meticulously adjusting and optimizing the first resource scheduling strategy, combining the advantages of intelligent models and genetic algorithms, thereby improving network performance and user experience while effectively controlling operating costs.

[0061] Optionally, in the network resource allocation method provided in this application embodiment, selecting a target resource scheduling sub-strategy from N candidate resource scheduling sub-strategies includes: obtaining a second optimization objective and determining the weight of each resource indicator in the second optimization objective to obtain Y resource indicator weights, wherein the second optimization objective includes at least one of the following: resource utilization indicator and response time indicator, and Y is a positive integer; for a candidate resource scheduling sub-strategy, obtaining the Y resource scheduling indicator values ​​of the candidate resource scheduling sub-strategy, calculating the scheme score of the candidate resource scheduling sub-strategy based on the Y resource indicator weights and the Y resource scheduling indicator values ​​to obtain the scheme score; extracting the candidate resource scheduling sub-strategy with the highest score from the N candidate resource scheduling sub-strategies based on the N scheme scores, and determining the candidate resource scheduling sub-strategy with the highest score as the target resource scheduling sub-strategy.

[0062] Specifically, after generating multiple candidate resource scheduling sub-policies, these policies can be evaluated. For example, a weighted evaluation method can be used to score each policy. First, a second optimization objective can be obtained, which may include resource utilization metrics (such as server CPU utilization, memory utilization, and bandwidth utilization), response time metrics (such as the average response time of user requests), cost control (such as total operating costs), service quality metrics (such as the clarity and smoothness of video streams), and user experience metrics (such as user satisfaction scores). Then, weights are assigned to each resource metric in the second optimization objective, such as resource utilization and response time, where these weights can be set based on business needs or policy priorities.

[0063] Then, based on the performance of each candidate resource scheduling sub-strategy across various metrics, a weighted scheme score is calculated. That is, after determining the resource scheduling metric values ​​for each candidate resource scheduling sub-strategy, the score is calculated based on the weights of the resource metrics and the individual resource scheduling metric values, thus obtaining the scheme score. For example, a scheme with a high score of 85 points in resource utilization, with a weight of 0.35 for resource utilization, will have a score of 30.25 for resource utilization. Finally, the scheme scores of all candidate resource scheduling sub-strategies are compared, and the strategy with the highest score is selected as the target resource scheduling sub-strategy. This embodiment, by using a weighted approach to determine the target resource scheduling sub-strategy, avoids system performance imbalances caused by optimizing a single metric, thereby more accurately reflecting the comprehensive advantages and disadvantages of the strategy, optimizing resource allocation, and reducing overall operating costs.

[0064] Optionally, in the network resource allocation method provided in this application embodiment, constructing a resource scheduling structure based on a target resource scheduling sub-policy includes: determining a second resource allocation node based on the target resource scheduling sub-policy, wherein the second resource allocation node is used to indicate path node information that needs to be adjusted in the network platform, and the path node information includes at least one of the following: server nodes, storage device nodes, and bandwidth allocation nodes; determining the resource flow status between all nodes of the second resource allocation node through a topology analysis tool, wherein the resource flow status is used to indicate the path of resources flowing from one node to another; obtaining user demand data, and determining the priority of all nodes in the second resource allocation node based on the user demand data and the target resource scheduling sub-policy; obtaining resource rules, and constructing a scheduling rule set using the resource rules, wherein the scheduling rule set includes resource allocation conditions, node load thresholds, and scheduling trigger conditions; and constructing a resource scheduling structure based on the scheduling rule set, resource flow status, the second resource allocation node, and the priorities of all nodes.

[0065] Specifically, after obtaining the target resource scheduling sub-policy, a resource scheduling structure representing the current distribution of network resources, the connection relationships between nodes, and the resource flow can be constructed based on this policy and using network topology analysis tools. First, the second resource allocation nodes can be determined according to the target resource scheduling sub-policy. These second resource allocation nodes can also include server nodes, storage device nodes, and bandwidth allocation nodes. Server nodes are responsible for handling computing tasks, storage device nodes are responsible for data storage and access, and bandwidth allocation nodes manage the allocation of network traffic. Then, the network topology analysis tool defines the connection relationships and resource flow between the second resource allocation nodes. This tool constructs and analyzes the nodes and their connection relationships in the network. During this process, the dependencies between nodes can be identified, and the path of resource flow from one node to another can be determined. For example, server nodes are connected to storage devices via high-speed links, while bandwidth allocation nodes are responsible for allocating network traffic between different servers.

[0066] Furthermore, the priority of each resource allocation node is assigned based on resource demand (i.e., user demand data) and the target resource scheduling sub-strategy. That is, after clarifying the resource flow, the Analytic Hierarchy Process (AHP) is used to assign priority to each second resource allocation node. AHP, as a multi-criteria decision-making method, can handle complex priority allocation problems. First, the importance factors of resource nodes (such as task criticality, response time, and resource utilization) are decomposed into multi-level evaluation criteria. Then, the weight of each criterion is calculated using a pairwise comparison method, and the priority of each node is calculated comprehensively. For example, the computing power of server nodes, the network latency of bandwidth nodes, and the data read speed of storage nodes are comprehensively compared to ultimately determine the priority of each node.

[0067] To effectively manage resource scheduling, a rule engine (i.e., resource rules) can be used to construct a scheduling rule set. This rule set includes resource allocation conditions, node load thresholds, and scheduling trigger conditions. Based on a predefined rule set, the rule engine can automatically handle complex decisions in resource scheduling: First, it defines a set of resource allocation conditions, such as bandwidth utilization and CPU utilization, to determine under what circumstances resources should be reallocated. Then, it sets load thresholds for each node; for example, when CPU utilization exceeds 80%, load balancing is triggered. Finally, it sets scheduling trigger conditions, such as when the load of a node exceeds a set threshold or network traffic suddenly increases, automatically adjusting resource allocation according to preset rules to ensure that resources are used rationally under various conditions. Finally, the scheduling rule set, resource flow status, secondary resource allocation nodes, and the priorities of all nodes can be integrated to form a resource scheduling structure. This embodiment forms a resource scheduling structure through resource allocation node identification, resource flow status analysis, priority setting, and the construction of a scheduling rule set, ensuring the rational flow and allocation of resources among different nodes, thereby improving the resource utilization efficiency, responsiveness, and user experience of the network platform, while controlling operating costs.

[0068] Optionally, in the network resource allocation method provided in this application embodiment, adjusting the transitional resource scheduling strategy using a resource scheduling structure to obtain a second resource scheduling strategy includes: inputting the target resource scheduling sub-strategy into a linear programming model and outputting primary resource allocation information, wherein the linear programming model is configured by the resource scheduling structure, and the primary resource allocation information is used to indicate the allocation scheme of network resources among different nodes; acquiring resource usage data and system performance data of the network platform, and determining resource allocation deviation information based on the resource usage data and system performance data; performing secondary optimization on the resource allocation deviation information based on an incremental optimization algorithm to obtain secondary resource allocation information, wherein the secondary optimization is used to adjust the distribution of resources among different nodes; and generating a second resource scheduling strategy based on the primary resource allocation information and the secondary resource allocation information.

[0069] Specifically, after obtaining the resource scheduling structure, a one-time resource allocation can be performed. This involves using a static resource allocation algorithm to distribute currently available resources to various nodes and tasks according to the optimal strategy. In other words, the target resource scheduling sub-strategy is input into a linear programming model for one-time resource allocation, ensuring that the initial resource configuration meets the needs of most services. Simultaneously, based on the strategy defined in the resource scheduling structure, the resource requirements of each node or service are calculated, and resources are allocated according to priority and allocation conditions, forming one-time resource allocation information. It should be noted that during one-time resource allocation, to maximize resource utilization or minimize total cost, an objective function for resource allocation can first be defined, where the objective function can be expressed as: ,in, It is the resource utilization rate. It's about cost. and Let i represent the amount of resources allocated to the i-th node and the cost of the j-th node, respectively. Then, the requirements of each resource allocation node, such as servers, storage devices, and bandwidth allocation nodes, are used as constraints and input into the linear programming model. Finally, by solving this model, the optimal allocation scheme of resources among the nodes is calculated, forming one-time resource allocation information.

[0070] After the initial resource allocation is completed and the system enters the operational phase, monitoring tools can be used to track key performance indicators such as CPU utilization, memory usage, bandwidth utilization, and response time. This allows for real-time monitoring of resource usage, system performance, and resource consumption during the initial allocation process. This information helps identify potential resource bottlenecks or imbalances in utilization. Based on this information, a secondary resource allocation is then performed, employing deviation analysis to assess bottlenecks and efficiency issues, thus generating resource allocation deviation information. Deviation analysis compares actual resource usage with expected values ​​from the initial allocation to identify shortcomings in resource allocation. Specifically, it compares the actual load of each node with the allocated resources, identifying nodes with excessive or insufficient resource allocation. For example, one server's CPU utilization might far exceed expectations, while another server's resource utilization is low. This analysis generates resource allocation deviation information.

[0071] To further optimize resource utilization, incremental optimization algorithms are used to adjust these imbalances or inefficiencies, such as reallocating bandwidth and adjusting server load, thereby achieving more refined resource utilization and higher service quality. This involves secondary optimization based on resource allocation deviation information, adjusting the distribution of resources among nodes to obtain secondary resource allocation information. Finally, the primary and secondary resource allocation information are combined using methods such as weighted averaging to generate a second resource scheduling strategy. Incremental optimization, as a gradual adjustment method, can progressively improve system performance through small resource adjustments. When using this algorithm, the resource allocation nodes that need optimization are first identified, i.e., nodes that are bottlenecks due to insufficient initial allocation or nodes with excess but underutilized resources. Then, the incremental optimization algorithm reallocates resources to these nodes. For example, if some nodes are overloaded, the resource allocation to other low-load nodes is reduced, and these resources are redistributed to high-load nodes to balance the load across nodes, thus generating secondary resource allocation information through adjustment. This embodiment utilizes a resource scheduling structure to adjust the transitional resource scheduling strategy, thereby obtaining a second resource scheduling strategy. This achieves self-learning and optimization of the scheduling strategy, improves the intelligence and flexibility of the strategy, and ultimately enhances the technical effect of improving network resource utilization and response efficiency.

[0072] This application also provides a network resource allocation system. Figure 2 This is a schematic diagram of a network resource allocation system provided according to an embodiment of this application. The system includes: a real-time information acquisition module, a resource demand analysis module, a transitional resource scheduling strategy acquisition module, a second resource scheduling strategy determination module, and a network resource scheduling module. The real-time information acquisition module acquires network behavior data in real time and determines resource load data. The resource demand analysis module performs big data analysis based on network behavior data and resource load data to generate network resource demand analysis results and determine a first resource scheduling strategy. The transitional resource scheduling strategy acquisition module constructs a dynamic scheduling judgment model by verifying the matching degree between the first resource scheduling strategy and user demand data, locates resource allocation nodes, and performs secondary scheduling and local resource optimization to obtain a transitional resource scheduling strategy. The second resource scheduling strategy determination module optimizes the transitional resource scheduling strategy, determines a target resource scheduling sub-strategy, constructs a scheduling structure, performs one-time resource allocation and secondary resource allocation based on internal strategy information, and determines the second resource scheduling strategy. The network resource scheduling module executes network resource scheduling based on the second resource scheduling strategy.

[0073] Furthermore, the system can input network behavior data and resource load data into a big data analysis model to analyze user behavior patterns and network resource usage trends, obtaining user behavior analysis results; based on the user behavior analysis results, it generates network resource demand analysis results, including resource demand prediction and resource load assessment; based on the network resource demand analysis results, it determines a first resource scheduling strategy, which includes resource allocation strategy and priority settings. By acquiring historical user behavior data and historical network resource load data (corresponding to each other), it obtains historical behavior results corresponding to the historical user behavior data and historical network resource load data; it performs data preprocessing and feature extraction on the historical user behavior data and historical network resource load data to obtain a historical feature set, including user access frequency, resource usage patterns, and peak times; based on the historical feature set and historical behavior results, it constructs a big data analysis model.

[0074] Furthermore, the matching degree between the first resource scheduling strategy and user demand data is calculated to obtain scheduling deviation information. Based on the scheduling deviation information, a dynamic scheduling judgment method using a rule engine is employed to construct a dynamic scheduling judgment model and locate resource allocation nodes. A heuristic scheduling algorithm is used to perform secondary scheduling on the resource allocation nodes, adjusting the first resource scheduling strategy to obtain a preliminary optimized resource scheduling plan. The preliminary optimized resource scheduling plan is then locally optimized to obtain a transitional resource scheduling strategy. Based on the transitional resource scheduling strategy, a multi-objective optimization algorithm is used to optimize the resource allocation strategy, obtaining multiple candidate resource allocation schemes. These candidate schemes are evaluated to determine the first optimal resource allocation strategy. Based on the first optimal resource allocation strategy, a resource scheduling structure is constructed. Based on the first optimal resource allocation strategy, resource allocation nodes are determined, including servers, storage devices, and bandwidth allocation nodes. A network topology analysis method is used to define the connection relationships and resource flows between resource allocation nodes. According to resource demand and the first optimal resource allocation strategy, the priority of each resource allocation node is assigned. A scheduling rule set is constructed, including resource allocation conditions, node load thresholds, and scheduling trigger conditions. Finally, resource allocation nodes, resource flows, priorities, and scheduling rules are integrated to form the resource scheduling structure. A static resource allocation algorithm is used to perform a one-time resource allocation for the first optimal resource allocation strategy to obtain one-time resource allocation information. Resource usage and system performance data are collected, and deviation analysis is used to evaluate the bottlenecks and efficiency problems of resource allocation to obtain resource allocation deviation information. Based on the resource allocation deviation information, a second optimization is performed to adjust the distribution of resources among nodes to obtain second-time resource allocation information. The first-time resource allocation information and the second-time resource allocation information are combined to generate a second resource scheduling strategy.

[0075] Figure 3This is a schematic diagram of an optional network resource allocation method provided according to an embodiment of this application. This optional network resource allocation method is applied to the aforementioned network resource allocation system, such as... Figure 3 As shown, the method includes: acquiring network behavior data in real time and determining resource load data; performing big data analysis based on the network behavior data and resource load data to generate network resource demand analysis results and determine a first resource scheduling strategy; constructing a dynamic scheduling judgment model by verifying the matching degree between the first resource scheduling strategy and user demand data, locating resource allocation nodes and performing secondary scheduling and local resource optimization to obtain a transitional resource scheduling strategy; optimizing the transitional resource scheduling strategy, determining a target resource scheduling sub-strategy and constructing a scheduling structure, performing one-time resource allocation and secondary resource allocation based on the internal information of the strategy to determine a second resource scheduling strategy; and executing network resource scheduling based on the second resource scheduling strategy.

[0076] This embodiment, through a first optimal resource allocation strategy based on an optimized scheduling structure, can better manage the allocation and flow of resources among different nodes, avoid bottlenecks in resource allocation, and ensure that resource allocation not only meets current needs but also reaches an optimal state, maximizing resource utilization efficiency. Secondary resource allocation based on information within the strategy: The secondary allocation adjusts the first optimal resource allocation strategy in real time according to actual operating conditions and resource usage feedback, ensuring that resource allocation can dynamically respond to changes in the network environment and user needs.

[0077] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0078] This application also provides a network resource allocation device. It should be noted that the network resource allocation device of this application can be used to execute the network resource allocation method provided in this application. The network resource allocation device provided in this application will be described below.

[0079] Figure 4 This is a schematic diagram of a network resource allocation device provided according to an embodiment of this application, such as... Figure 4 As shown, the device includes: an acquisition unit 40, a generation unit 41, and an adjustment unit 42.

[0080] The acquisition unit 40 is used to acquire resource load data of the network platform within a preset time period, and to acquire network behavior data of users using the network platform within the preset time period.

[0081] The generation unit 41 is used to generate a first resource scheduling policy based on resource load data and network behavior data when the network platform is in a first network state, and send the first resource scheduling policy to the client. When the client receives the first resource scheduling policy, it performs resource scheduling operations according to the first resource scheduling policy. The first resource scheduling policy includes resource allocation policies of multiple dimensions.

[0082] The adjustment unit 42 is used to adjust the first resource scheduling strategy when the network platform is in the second network state to obtain a second resource scheduling strategy, and send the second resource scheduling strategy to the client. When the client receives the second resource scheduling strategy, it performs resource scheduling operation according to the second resource scheduling strategy. The resource demand of the second network state is higher than that of the first network state. The second resource scheduling strategy includes resource allocation strategies in multiple dimensions.

[0083] The network resource allocation device provided in this application embodiment acquires resource load data of the network platform within a preset time period through an acquisition unit 40, and acquires network behavior data of users using the network platform within the preset time period; the generation unit 41 generates a first resource scheduling strategy based on the resource load data and network behavior data when the network platform is in a first network state, and sends the first resource scheduling strategy to the client, wherein, when the client receives the first resource scheduling strategy, it performs resource scheduling operations according to the first resource scheduling strategy, and the first resource scheduling strategy includes resource allocation strategies of multiple dimensions; the adjustment unit 42 adjusts the first resource scheduling strategy when the network platform is in a second network state, to obtain A second resource scheduling strategy is implemented and sent to the client. Upon receiving the second resource scheduling strategy, the client executes resource scheduling operations according to it. The resource demand of the second network state is higher than that of the first network state. The second resource scheduling strategy includes resource allocation strategies across multiple dimensions, addressing the technical problems of low resource utilization and poor response capabilities in network resource scheduling in related technologies. By generating a first resource scheduling strategy using resource load data and network behavior data, and then performing one-time and two-time resource allocations based on the first resource scheduling strategy, the second resource scheduling strategy is finally generated and executed, thereby achieving the technical effect of improving network resource utilization and response efficiency.

[0084] Optionally, in the network resource allocation apparatus provided in this application embodiment, the generation unit 41 includes: a first acquisition module, used to acquire a resource analysis model, wherein the resource analysis model is used to identify user behavior patterns and network resource usage trends of the network platform in different time periods; a first input module, used to input resource load data and network behavior data into the resource analysis model and output resource demand analysis results, wherein the resource demand analysis results include user behavior patterns and network resource usage trends within a preset time period; and a second acquisition module, used to acquire user distribution data and resource constraints of the network platform, determine a first optimization objective based on the user distribution data and resource constraints, process the resource demand analysis results based on the first optimization objective, and generate a first resource scheduling strategy, wherein the resource constraints are used to indicate the restrictions that need to be met in resource scheduling.

[0085] Optionally, in the network resource allocation device provided in this application embodiment, the generation unit 41 includes: a third acquisition module, used to acquire historical network behavior data and historical resource load data of the network platform within a historical time period, and associate the historical network behavior data and historical resource load data to obtain associated data, wherein the association method is to match the resource load situation of the historical network behavior data and historical resource load data at different time points within the historical time period; a first extraction module, used to extract feature data from the associated data to obtain a historical feature set, wherein the historical feature set includes at least one of the following: user access record information, resource usage data, and peak time; and a fourth acquisition module, used to acquire historical behavior results within the historical time period, and train a preset resource analysis model based on the historical feature set and historical behavior results to obtain a resource analysis model.

[0086] Optionally, in the network resource allocation device provided in this application embodiment, the adjustment unit 42 includes: a fifth acquisition module, used to acquire a resource scheduling model, and use the resource scheduling model to adjust a first resource scheduling strategy to obtain a transitional resource scheduling strategy; a first adjustment module, used to use a genetic algorithm to adjust the transitional resource scheduling strategy to obtain N candidate resource scheduling sub-strategies, where N is a positive integer; and a screening module, used to screen out a target resource scheduling sub-strategy from the N candidate resource scheduling sub-strategies, construct a resource scheduling structure based on the target resource scheduling sub-strategy, and use the resource scheduling structure to adjust the transitional resource scheduling strategy to obtain a second resource scheduling strategy.

[0087] Optionally, in the network resource allocation device provided in this application embodiment, the adjustment unit 42 includes: a sixth acquisition module, used to acquire user demand data, calculate the matching degree between the user demand data and the first resource scheduling strategy, and obtain scheduling deviation information, wherein the scheduling deviation information includes at least one of the following: resource type, expected allocation amount, actual demand amount, and matching deviation value; a seventh acquisition module, used to acquire resource rules, input the resource rules and scheduling deviation information into a dynamic scheduling model, and output resource scheduling results; an analysis module, used to analyze the resource scheduling results using a network resource analysis tool, and generate a first resource allocation node, wherein the first resource allocation node is used to indicate the path node information that needs to be adjusted in the network platform, and the path node information includes at least one of the following: server node, storage device node, and bandwidth allocation node; and a second adjustment module, used to adjust the first resource scheduling strategy according to the first resource allocation node using a resource optimization algorithm to obtain a transitional resource scheduling strategy.

[0088] Optionally, in the network resource allocation device provided in this application embodiment, the adjustment unit 42 includes: an eighth acquisition module, used to acquire a second optimization objective and determine the weight of each resource indicator in the second optimization objective to obtain Y resource indicator weights, wherein the second optimization objective includes at least one of the following: resource utilization indicator and response time indicator, and Y is a positive integer; a ninth acquisition module, used to acquire Y resource scheduling indicator values ​​of a candidate resource scheduling sub-strategy for a candidate resource scheduling sub-strategy, calculate the scheme score of the candidate resource scheduling sub-strategy based on the Y resource indicator weights and Y resource scheduling indicator values, and obtain the scheme score; and a second extraction module, used to extract the candidate resource scheduling sub-strategy with the highest score from N candidate resource scheduling sub-strategies based on N scheme scores, and determine the candidate resource scheduling sub-strategy with the highest score as the target resource scheduling sub-strategy.

[0089] Optionally, in the network resource allocation apparatus provided in this application embodiment, the adjustment unit 42 includes: a first determining module, configured to determine a second resource allocation node according to a target resource scheduling sub-policy, wherein the second resource allocation node is used to indicate path node information that needs to be adjusted in the network platform, and the path node information includes at least one of the following: server node, storage device node, and bandwidth allocation node; a second determining module, configured to determine the resource flow state between all nodes of the second resource allocation node through a topology analysis tool, wherein the resource flow state is used to indicate the path of resource flow from one node to another; a tenth obtaining module, configured to obtain user demand data, and determine the priority of all nodes in the second resource allocation node according to the user demand data and the target resource scheduling sub-policy; an eleventh obtaining module, configured to obtain resource rules, and construct a scheduling rule set using the resource rules, wherein the scheduling rule set includes resource allocation conditions, node load thresholds, and scheduling trigger conditions; and a constructing module, configured to construct a resource scheduling structure based on the scheduling rule set, resource flow state, the second resource allocation node, and the priority of all nodes.

[0090] Optionally, in the network resource allocation device provided in this application embodiment, the adjustment unit 42 includes: a second input module, used to input the target resource scheduling sub-strategy into a linear programming model and output primary resource allocation information, wherein the linear programming model is configured by a resource scheduling structure, and the primary resource allocation information is used to indicate the allocation scheme of network resources among different nodes; a twelfth acquisition module, used to acquire resource usage data and system performance data of the network platform, and determine resource allocation deviation information based on the resource usage data and system performance data; an optimization module, used to perform secondary optimization on the resource allocation deviation information based on an incremental optimization algorithm to obtain secondary resource allocation information, wherein the secondary optimization is used to adjust the distribution of resources among different nodes; and a generation module, used to generate a second resource scheduling strategy based on the primary resource allocation information and the secondary resource allocation information.

[0091] The aforementioned network resource allocation device includes a processor and a memory. The aforementioned acquisition unit 40, generation unit 41, adjustment unit 42, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0092] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address technical issues such as low resource utilization and poor responsiveness in network resource scheduling.

[0093] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0094] This invention provides a computer storage medium for storing programs, wherein the programs, when running, control the device where the computer storage medium is located to execute a network resource allocation method.

[0095] Figure 5 This is a schematic diagram of an electronic device provided according to an embodiment of this application, such as... Figure 5 As shown, this embodiment of the invention provides an electronic device 50, which includes a processor, a memory, and a program stored in the memory and executable on the processor. The processor is used to execute computer-readable instructions, wherein the computer-readable instructions execute a network resource allocation method. The device in this document can be a server, PC, PAD, mobile phone, etc.

[0096] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of a network resource allocation method according to various embodiments of this application.

[0097] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0099] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0100] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0101] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0102] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0103] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0104] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0105] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method of allocating network resources, characterized by, The method comprises: obtaining resource load data of a network platform in a preset time period and obtaining network behavior data of users using the network platform in the preset time period; in a case where the network platform is in a first network state, generating a first resource scheduling strategy according to the resource load data and the network behavior data, and sending the first resource scheduling strategy to a client, wherein, in a case where the client receives the first resource scheduling strategy, a resource scheduling operation is performed according to the first resource scheduling strategy, and the first resource scheduling strategy comprises resource allocation strategies in multiple dimensions; in a case where the network platform is in a second network state, adjusting the first resource scheduling strategy to obtain a second resource scheduling strategy, and sending the second resource scheduling strategy to the client, wherein, in a case where the client receives the second resource scheduling strategy, a resource scheduling operation is performed according to the second resource scheduling strategy, the resource requirement of the second network state is higher than that of the first network state, and the second resource scheduling strategy comprises resource allocation strategies in multiple dimensions; wherein, generating the first resource scheduling strategy according to the resource load data and the network behavior data comprises: obtaining a resource analysis model, wherein the resource analysis model is used to identify user behavior patterns and network resource usage trends of the network platform in different time periods; inputting the resource load data and the network behavior data into the resource analysis model to output resource demand analysis results, wherein the resource demand analysis results comprise user behavior patterns and network resource usage trends in the preset time period; obtaining user distribution data and resource constraint conditions of the network platform, determining a first optimization target according to the user distribution data and the resource constraint conditions, processing the resource demand analysis results based on the first optimization target to generate the first resource scheduling strategy, wherein the resource constraint conditions are used to indicate the limitation conditions that need to be met in resource scheduling.

2. The method of claim 1, wherein, The resource analysis model is trained in the following manner: obtaining historical network behavior data and historical resource load data of the network platform in a historical time period, and associating the historical network behavior data and the historical resource load data to obtain associated data, wherein the association manner is to match the historical network behavior data with the resource load condition of the historical resource load data at different time points in the historical time period; extracting feature data of the associated data to obtain a historical feature set, wherein the historical feature set comprises at least one of the following: user access record information, resource usage data and peak time; obtaining historical behavior results in the historical time period, training a preset resource analysis model based on the historical feature set and the historical behavior results to obtain the resource analysis model.

3. The method of claim 1, wherein, adjusting the first resource scheduling strategy to obtain a second resource scheduling strategy comprises: obtaining a resource scheduling model, adjusting the first resource scheduling strategy by using the resource scheduling model to obtain a transition resource scheduling strategy; Adjusting the transition resource scheduling strategy by using a genetic algorithm to obtain N candidate resource scheduling sub-strategies, wherein N is a positive integer; Filtering a target resource scheduling sub-strategy from the N candidate resource scheduling sub-strategies, constructing a resource scheduling structure according to the target resource scheduling sub-strategy, adjusting the transition resource scheduling strategy by using the resource scheduling structure to obtain the second resource scheduling strategy.

4. The method of claim 3, wherein, Adjusting the first resource scheduling strategy by using the resource scheduling model to obtain a transition resource scheduling strategy, including: Obtaining user demand data, calculating the matching degree of the user demand data and the first resource scheduling strategy to obtain scheduling deviation information, wherein the scheduling deviation information at least includes one of the following: resource type, expected allocation amount, actual demand amount, and matching deviation value; Obtaining resource rules, inputting the resource rules and the scheduling deviation information into a dynamic scheduling model, and outputting a resource scheduling result; Analyzing the resource scheduling result by using a network resource analysis tool to generate a first resource allocation node, wherein the first resource allocation node is used to indicate path node information in the network platform that needs to be adjusted, and the path node information at least includes one of the following: server node, storage device node, and bandwidth allocation node; Adjusting the first resource scheduling strategy according to the first resource allocation node by using a resource optimization algorithm to obtain the transition resource scheduling strategy.

5. The method of claim 3, wherein, Filtering a target resource scheduling sub-strategy from the N candidate resource scheduling sub-strategies, including: Obtaining a second optimization target and determining the weight of each resource index in the second optimization target to obtain Y resource index weights, wherein the second optimization target at least includes one of the following: resource utilization index and response time index, and Y is a positive integer; For a candidate resource scheduling sub-strategy, obtaining Y resource scheduling index values of the candidate resource scheduling sub-strategy, calculating the scheme score of the candidate resource scheduling sub-strategy according to the Y resource index weights and the Y resource scheduling index values to obtain a scheme score; According to N scheme scores, extracting a candidate resource scheduling sub-strategy with the highest score from the N candidate resource scheduling sub-strategies, and determining the candidate resource scheduling sub-strategy with the highest score as the target resource scheduling sub-strategy.

6. The method of claim 3, wherein, Constructing a resource scheduling structure according to the target resource scheduling sub-strategy, including: Determining a second resource allocation node according to the target resource scheduling sub-strategy, wherein the second resource allocation node is used to indicate path node information in the network platform that needs to be adjusted, and the path node information at least includes one of the following: server node, storage device node, and bandwidth allocation node; Determining the resource flow state between all nodes of the second resource allocation node by using a topology analysis tool, wherein the resource flow state is used to indicate the path of resource flow from one node to another node; Obtaining user demand data, and determining the priority of all nodes in the second resource allocation node according to the user demand data and the target resource scheduling sub-strategy; Obtaining resource rules, and constructing a scheduling rule set by using the resource rules, wherein the scheduling rule set comprises resource allocation conditions, node load thresholds and scheduling trigger conditions; Based on the scheduling rule set, the resource flow state, the second resource allocation node and the priority of all nodes, the resource scheduling structure is constituted.

7. The method of claim 3, wherein, Adjusting the transition resource scheduling strategy by using the resource scheduling structure to obtain the second resource scheduling strategy comprises: Inputting the target resource scheduling sub-strategy into a linear programming model to output primary resource allocation information, wherein the linear programming model is configured by the resource scheduling structure, and the primary resource allocation information is used to indicate the allocation scheme of network resources among different nodes; Obtaining resource usage data and system performance data of the network platform, and determining resource allocation deviation information according to the resource usage data and the system performance data; Based on the incremental optimization algorithm, the resource allocation deviation information is secondarily optimized to obtain secondary resource allocation information, wherein the secondary optimization is used to adjust the distribution of resources among different nodes; According to the primary resource allocation information and the secondary resource allocation information, the second resource scheduling strategy is generated.

8. An apparatus for allocating network resources, characterized by Comprise: The acquisition unit is used for obtaining resource load data of a network platform in a preset time period, and obtaining network behavior data of users using the network platform in the preset time period; The generation unit is used for generating a first resource scheduling strategy according to the resource load data and the network behavior data when the network platform is in a first network state, and sending the first resource scheduling strategy to a client, wherein when the client receives the first resource scheduling strategy, a resource scheduling operation is performed according to the first resource scheduling strategy, and the first resource scheduling strategy comprises resource allocation strategies in multiple dimensions; The adjustment unit is used for adjusting the first resource scheduling strategy to obtain a second resource scheduling strategy when the network platform is in a second network state, and sending the second resource scheduling strategy to the client, wherein when the client receives the second resource scheduling strategy, a resource scheduling operation is performed according to the second resource scheduling strategy, the resource demand of the second network state is higher than that of the first network state, and the second resource scheduling strategy comprises resource allocation strategies in multiple dimensions; The generation unit comprises: a first acquisition module, configured to acquire a resource analysis model, wherein the resource analysis model is used to identify user behavior patterns and network resource usage trends of the network platform in different time periods; a first input module, configured to input the resource load data and the network behavior data into the resource analysis model, and output resource demand analysis results, wherein the resource demand analysis results comprise user behavior patterns and network resource usage trends in the preset time period; and a second acquisition module, configured to acquire user distribution data and resource constraint conditions of the network platform, determine a first optimization target according to the user distribution data and the resource constraint conditions, process the resource demand analysis results based on the first optimization target, and generate the first resource scheduling strategy, wherein the resource constraint conditions are used to indicate limit conditions that need to be met in resource scheduling.

9. An electronic device, comprising: The device comprises one or more processors and a memory, and the memory is configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method for allocating network resources according to any one of claims 1 to 7.

Images