Network resource allocation method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a network resource allocation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring multi-dimensional data corresponding to a service, wherein the multi-dimensional data comprises user side data, network side performance indexes and wireless load data; performing poor quality evaluation based on the multi-dimensional data, and determining target poor quality data; if the wireless load data meets the terminal side performance index and a poor quality condition is determined to be met based on the target poor quality data, generating a target resource guarantee strategy; and distributing a target network resource to the user through the target resource guarantee strategy. Through adoption of the method, demand prediction, resource prediction and poor quality evaluation are performed based on the multi-dimensional data, user experience perceptibility and demand predictability are realized, matching of user demands and resource guarantee is guaranteed, user experience is improved, and the utilization rate of network resources is further improved.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for allocating network resources. Background Technology

[0002] With the increasing demand for differentiated services in 5G networks, the industry has proposed a service differentiation assurance solution based on NWDAF (Network Data Analytics Function). This solution uses network monitoring of key performance indicators (KPIs) to make decisions on manually predefined assurance strategies, and implements the distribution and resource reclamation of these predefined strategies. However, the network-side NWDAF cannot obtain the actual needs of users or services, nor the actual user experience data. It directly allocates network resources to users, resulting in a disconnect between the network-side resource allocation strategy and actual user needs, leading to low utilization of network resources. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for allocating network resources that can improve the matching degree between network resources and resource demand and further improve the efficiency of network resource allocation, in order to address the above-mentioned technical problems.

[0004] Firstly, this application provides a method for allocating network resources, applied to the Network Data Analysis Function (NWDAF), comprising:

[0005] Acquire multi-dimensional data corresponding to the business, including user-side data, network-side performance indicators, and wireless load data; the user-side data includes business operation data, user operation data, and terminal-side performance indicators.

[0006] Based on the multi-dimensional data, a quality assessment is performed to determine the target quality data.

[0007] If the wireless load data meets the terminal-side performance indicators, and the target poor quality data determines that the poor quality conditions are met, then a target resource guarantee strategy is generated.

[0008] The target resource guarantee strategy allocates target network resources to the user.

[0009] In one embodiment, the step of performing a quality defect assessment based on the multi-dimensional data to determine the target quality defect data includes:

[0010] Based on the user-side data and / or the network-side performance indicators, a quality defect assessment is performed to determine the initial quality defect data;

[0011] If it is determined that the wireless load data does not meet the terminal-side performance indicators, the terminal-side performance indicators are adjusted based on the network-side performance indicators to obtain updated terminal-side performance indicators, and the initial poor quality data is adjusted based on the updated terminal-side performance indicators to obtain updated poor quality data, and the updated poor quality data is determined as the target poor quality data.

[0012] In one embodiment, the method further includes:

[0013] Based on the user operation data, forecasts are made to determine demand forecast data; and based on the wireless load data, forecasts are made to determine load forecast data.

[0014] If the load prediction data meets the demand prediction data, a resource pre-guarantee strategy is generated based on the user operation data, and network resources are allocated to the user within the operation time period corresponding to the user operation data using the resource pre-guarantee strategy.

[0015] In one embodiment, the method further includes:

[0016] The judgment is made based on the business operation data, network-side performance indicators, and the target poor quality data. If it is determined that the abnormal operation conditions are met, then the poor quality conditions are determined to be met.

[0017] In one embodiment, allocating target network resources to the user through the target resource guarantee policy includes:

[0018] A dedicated transport is established through the target resource guarantee strategy, and target network resources are allocated to the user through the dedicated transport.

[0019] In one embodiment, the method further includes:

[0020] The resource feedback results of the user are collected periodically by NEF; the resource feedback results are obtained after the target network resources are allocated to the user.

[0021] If the resource feedback results determine that the poor quality condition is met, an enhanced resource guarantee strategy is generated; the enhanced resource guarantee strategy includes a low-latency guarantee strategy and / or a high-bandwidth guarantee strategy; or,

[0022] If the resource feedback results indicate that the poor quality conditions are not met, the target resource guarantee strategy will continue to operate until the poor quality conditions are met or the business is completed.

[0023] In one embodiment, the method further includes:

[0024] An enhanced dedicated load is established through the enhanced resource guarantee strategy, and enhanced network resources are allocated to the user through the enhanced dedicated load.

[0025] Secondly, this application also provides a network resource allocation device for use in the Network Data Analysis Function (NWDAF), comprising:

[0026] The first acquisition module is used to acquire multi-dimensional data corresponding to the service. The multi-dimensional data includes user-side data, network-side performance indicators, and wireless load data. The user-side data includes service operation data, user operation data, and terminal-side performance indicators.

[0027] The first determining module is used to perform a quality defect assessment based on the multi-dimensional data and determine the target quality defect data.

[0028] The first generation module is used to generate a target resource guarantee strategy if the wireless load data meets the terminal-side performance indicators and the target poor quality data determines that the poor quality conditions are met.

[0029] The allocation module is used to allocate target network resources to the user through the target resource guarantee policy.

[0030] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0031] Acquire multi-dimensional data corresponding to the business, including user-side data, network-side performance indicators, and wireless load data; the user-side data includes business operation data, user operation data, and terminal-side performance indicators.

[0032] Based on the multi-dimensional data, a quality assessment is performed to determine the target quality data.

[0033] If the wireless load data meets the terminal-side performance indicators, and the target poor quality data determines that the poor quality conditions are met, then a target resource guarantee strategy is generated.

[0034] The target resource guarantee strategy allocates target network resources to the user.

[0035] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0036] Acquire multi-dimensional data corresponding to the business, including user-side data, network-side performance indicators, and wireless load data; the user-side data includes business operation data, user operation data, and terminal-side performance indicators.

[0037] Based on the multi-dimensional data, a quality assessment is performed to determine the target quality data.

[0038] If the wireless load data meets the terminal-side performance indicators, and the target poor quality data determines that the poor quality conditions are met, then a target resource guarantee strategy is generated.

[0039] The target resource guarantee strategy allocates target network resources to the user.

[0040] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0041] Acquire multi-dimensional data corresponding to the business, including user-side data, network-side performance indicators, and wireless load data; the user-side data includes business operation data, user operation data, and terminal-side performance indicators.

[0042] Based on the multi-dimensional data, a quality assessment is performed to determine the target quality data.

[0043] If the wireless load data meets the terminal-side performance indicators, and the target poor quality data determines that the poor quality conditions are met, then a target resource guarantee strategy is generated.

[0044] The target resource guarantee strategy allocates target network resources to the user.

[0045] The aforementioned network resource allocation method, apparatus, computer equipment, computer-readable storage medium, and computer program product, wherein the method includes: acquiring multi-dimensional data corresponding to a service, wherein the multi-dimensional data includes user-side data, network-side performance indicators, and wireless load data; the user-side data includes service operation data, user operation data, and terminal-side performance indicators; performing quality deviation assessment based on the multi-dimensional data to determine target quality deviation data; if the wireless load data meets the terminal-side performance indicators, and the quality deviation conditions are determined to be met based on the target quality deviation data, then generating a target resource guarantee strategy; and allocating target network resources to the user through the target resource guarantee strategy. By adopting this method, demand prediction, resource prediction, and quality deviation assessment based on multi-dimensional data are performed, achieving perceptible user experience and predictable demand, ensuring the matching of user demand and resource guarantee, improving user experience, and further improving the utilization rate of network resources. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is an application environment diagram of a network resource allocation method in one embodiment;

[0048] Figure 2 This is a flowchart illustrating a method for allocating network resources in one embodiment;

[0049] Figure 3 This is a flowchart illustrating the steps for determining target poor-quality data in one embodiment;

[0050] Figure 4 This is a flowchart illustrating a method for allocating network resources in one embodiment;

[0051] Figure 5 This is a flowchart illustrating a method for allocating network resources in another embodiment;

[0052] Figure 6 This is a structural block diagram of a network resource allocation device in one embodiment;

[0053] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0056] The network resource allocation method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with core network 104. Core network 104 includes multiple network functions, such as Network Exposure Function (NEF), Network Data Analytics Function (NWDAF), Policy Control Function (PCF), Operation Administration and Maintenance (OAM), Session Management Function (SMF), and User Plane Function (UPF). The Network Data Analytics Function (NWDAF) can communicate with the user through NEF and allocate target network resources to terminal 102 based on the generated target resource guarantee policy. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, etc. Terminal 102 can also be an application, etc.

[0057] This embodiment proposes a system and method for dynamically optimizing QoS assurance strategies based on multidimensional data analysis. Through real-time, dynamic, and comprehensive quality deviation analysis, it transforms assurance strategies from static configuration to dynamic intelligent adaptation. The proposed system enhances the policy analysis capabilities of NWDAF, comprehensively considering real-time user service experience data, user behavior, and service requirements from both the terminal and application sides. It dynamically sets quality deviation thresholds and predicts the required assurance resources based on user behavior and service needs. It also generates service optimization suggestions and dynamic assurance strategy suggestions, taking into account network load and service characteristics. After the assurance strategy is issued, the network side continuously monitors the strategy's execution effect. If poor service quality is detected, the assurance strategy is upgraded after comprehensive evaluation and analysis by NWDAF, provided network resources allow, to provide targeted assurance for the service. If poor quality still occurs when the network side reaches its capacity limit for providing assurance for the service, or if the service effect is unaffected after the service ends or a dedicated load is deleted, the network side reverts to the default strategy.

[0058] In one exemplary embodiment, such as Figure 2 As shown, a method for allocating network resources is provided, which can be applied to... Figure 1 Taking the Network Data Analysis Function (NWDAF) in the example, the explanation includes the following steps 202 to 206. Wherein:

[0059] Step 202: Obtain multi-dimensional data corresponding to the business.

[0060] The data includes multiple dimensions such as user-side data, network-side performance metrics, and wireless load data. User-side data includes service operation data, user operation data, and terminal-side performance metrics.

[0061] For example, the network data analysis function can initiate a data subscription request to the target device. After the data subscription request is verified, the target device can periodically return the data corresponding to the data subscription request to the network data analysis function, or return the data corresponding to the data subscription request to the network data analysis function when a trigger condition is met. The target device can be a terminal / application, a wireless OAM system, or an SMF, etc.

[0062] Optionally, the network data analysis function can initiate a data subscription request to the terminal / application. The terminal / application can return user-side data to the network data analysis function. This user-side data represents terminal-side data or application-side data. The business operation data in this user-side data refers to terminal business experience data, which represents the data generated by the terminal when performing business experiences, such as the percentage of time spent experiencing lag, the number of times the frame rate drops, and the operation response latency, etc. User operation data can represent user operation data on the terminal device or user operation data on the application, etc. This operation data can be ticket grabbing operations, multimedia data interactive operations, etc. Multimedia can be video, and interactive operations include browsing operations and download operations, etc. Terminal-side performance indicators represent the demand data when the terminal is running services, such as the video resolution, frame rate, and latency required by the terminal. Among them, the network data analysis function can initiate a data subscription request to the terminal / application side (terminal device) through NEF, and the terminal device returns user-side data to the network data analysis function through NEF.

[0063] Optionally, the network data analysis function can send a data subscription request to the wireless OAM system. The OAM system can then return wireless load data to the network data analysis function. This wireless load data can be wireless performance data, including information such as Physical Resource Blocks (PRBs). A Physical Resource Block is the smallest unit of time-frequency resources in 4G LTE and 5G NR networks. PRB utilization refers to the ratio of the total number of PRBs used to the total number of PRBs available from the system over a given period.

[0064] Optionally, the network data analysis function can send a data subscription request to the UPF to which the terminal device belongs via the SMF. The data subscription request is used to subscribe to network-side performance indicators, which refer to the key performance indicators of a specified service. The specified service can be a service processed on the terminal. The key performance indicators include uplink and downlink bandwidth, uplink and downlink packet loss rate, latency, etc.

[0065] In other words, the network data analysis function obtains multi-dimensional data returned by various target devices by sending data subscription requests to multiple target devices. That is, the network data analysis function can obtain real-time data from multiple dimensions such as user-side data, network-side performance indicators, and wireless load data.

[0066] Step 204: Conduct a quality assessment based on multi-dimensional data to determine the target quality data.

[0067] Here, the target quality defect data is represented by a dynamic quality defect threshold set for one or more indicators corresponding to the business. The one or more indicators corresponding to the business refer to one or more performance indicators that have a high degree of impact on the operation of the business.

[0068] For example, the network data analysis function can also perform quality and performance evaluation based on user-side data and / or network-side performance indicators in multi-dimensional data, determine at least one dynamic quality and performance threshold corresponding to at least one indicator type that matches the service type, and determine each dynamic quality and performance threshold as initial quality and performance data. If it is determined that the wireless load data in the currently acquired multi-dimensional data does not meet the service requirements, that is, the current wireless load data cannot meet the terminal-side performance indicators, the network data analysis function can update the terminal-side performance indicators to obtain updated terminal-side performance indicators, and adjust the initial quality and performance data based on the updated terminal-side performance indicators to obtain updated quality and performance data, and determine the updated quality and performance data as the target quality and performance data.

[0069] Step 206: If the wireless load data meets the terminal-side performance indicators and the quality condition is met based on the target poor-quality data, then a target resource guarantee policy is generated. The target network resources are then allocated to the user using the target resource guarantee policy.

[0070] Among them, the quality defect condition is used to determine whether a quality defect has occurred. The content of the quality defect condition can be that the current indicator value does not match the dynamic quality defect threshold corresponding to that indicator. The target resource guarantee strategy is a target resource guarantee strategy to ensure the basic availability of services running on user terminals, i.e., the basic resource guarantee strategy / initial guarantee strategy.

[0071] For example, if the network data analysis function determines that the network load in the current multi-dimensional data meets the terminal-side performance indicators, i.e., determines that the network load meets the terminal's service requirements, and the network data analysis function determines that the quality deterioration conditions are met based on the target quality deterioration data, i.e., determines that service quality deterioration has occurred based on the target quality deterioration data, then the network data analysis function can generate a target resource guarantee policy that ensures the basic availability of the service running on the user terminal, and allocate various target network resources to the user terminal running the service through the various target network resources indicated in the target resource guarantee policy. The target resource guarantee policy can be a basic guarantee policy, an initial guarantee policy, etc.

[0072] Optionally, different services correspond to different initial protection strategies. The correspondence between services and initial protection records can be pre-set based on the needs of actual application scenarios. The specific types and values ​​of various network resources indicated in the target resource protection strategy can also be determined based on actual application scenarios. For example, network resources may include one or more of 5G QoS Identifier (5G Quality of Service Identifier, 5QI), minimum uplink bandwidth, and minimum downlink bandwidth, and may also include other types of network resources. This embodiment does not specifically limit this.

[0073] In the aforementioned network resource allocation method, multi-dimensional data corresponding to the service is acquired. These multi-dimensional data include user-side data, network-side performance indicators, and wireless load data. The user-side data includes service operation data, user operation data, and terminal-side performance indicators. Quality deviation assessment is performed based on the multi-dimensional data to determine target quality deviation data. If the wireless load data meets the terminal-side performance indicators, and the quality deviation conditions are met based on the target quality deviation data, a target resource guarantee strategy is generated. Target network resources are allocated to the user using this target resource guarantee strategy. By employing this method, demand prediction, resource prediction, and quality deviation assessment based on multi-dimensional data are performed, achieving perceptible user experience and predictable demand, ensuring the matching of user needs with resource guarantees, improving user experience, and further enhancing network resource utilization.

[0074] In one embodiment, such as Figure 3 As shown, the specific processing steps for the step "Perform quality assessment based on multi-dimensional data and determine the target quality data" include:

[0075] Step 302: Perform a quality defect assessment based on user-side data and / or network-side performance metrics to determine the initial quality defect data.

[0076] The initial quality defect data can be a dynamic quality defect threshold.

[0077] For example, the network data analysis function evaluates the service operation data, user operation data, and terminal-side performance indicators in the currently acquired user-side data to obtain initial quality defect data, i.e., the initial dynamic quality defect threshold. This can be a dynamic quality defect threshold set for one or more indicators such as uplink / downlink bandwidth, latency, and frame rate. Alternatively, the network data analysis function can also evaluate based on terminal-side performance indicators to obtain initial quality defect data. Specifically, the network data analysis function can determine the types of indicators for which dynamic quality defect thresholds need to be set based on the type of real-time user service experience data from the terminal / application side. Based on the real-time user service experience data, user behavior, and service requirements from the terminal / application side, the function determines the value of the dynamic quality defect threshold corresponding to each indicator. This value can be, for example, the value of the indicator when service interruptions or other abnormal phenomena occur. For instance, the value of each indicator under service interruption conditions can be used as the dynamic quality defect threshold for that indicator, thus obtaining the initial quality defect data.

[0078] Optionally, the network data analysis function can determine one or more indicator types corresponding to the dynamic quality difference threshold to be set based on the type of service processed on the terminal. That is, the indicator type is the one with a high degree of impact on the service processed on the terminal. Different service types correspond to different indicator types. The network data analysis function can pre-store the correspondence between services and indicators. For example, when the service type is gaming, the corresponding indicator type for the dynamic quality difference threshold could be latency or frame rate; when the service type is video, the corresponding indicator type could be downlink bandwidth; and when the service type is live streaming, the corresponding indicator type could be uplink bandwidth. In one example, if the indicator exists on both the terminal side and the network side, the network data analysis function can evaluate based on the terminal-side performance indicators to obtain a first dynamic quality difference threshold, and evaluate based on the network-side performance indicators to obtain a second dynamic quality difference threshold. For example, the initial quality difference data could be the first latency quality difference threshold and the second latency quality difference threshold set for the latency indicator when the service type is gaming.

[0079] Step 304: If it is determined that the wireless load data does not meet the terminal-side performance indicators, the terminal-side performance indicators are adjusted based on the network-side performance indicators to obtain updated terminal-side performance indicators, and the initial poor quality data is adjusted based on the updated terminal-side performance indicators to obtain updated poor quality data, and the updated poor quality data is determined as the target poor quality data.

[0080] For example, if the network data analysis function determines that the current network load in the multi-dimensional data cannot meet the terminal-side performance indicators, i.e., the network load does not meet the terminal's service requirements, it can generate service optimization suggestions based on the current state of the network side, i.e., the network-side performance indicators. Based on these suggestions, the terminal-side performance indicators are adjusted to obtain updated terminal-side performance indicators. In this way, the network data analysis function can update and adjust the dynamic quality defect thresholds corresponding to each indicator in the initial quality defect data based on the updated terminal-side performance indicators, obtaining updated quality defect data. Furthermore, it can obtain target quality defect data based on the updated quality defect data; for example, the updated quality defect data can be designated as the target quality defect data.

[0081] In one example, the terminal-side performance metrics could be that the user requires 8K resolution video and a large downlink bandwidth of 70Mbps to 200Mbps, while the current network status could be 60Mbps. If the network data analysis function determines that the current wireless load data does not meet (i.e. cannot meet) the terminal-side performance metrics, then the generated service optimization suggestion could be to adjust the resolution, for example, by reducing the resolution. Based on the downlink bandwidth value required for the reduced resolution, the dynamic quality defect threshold corresponding to the downlink bandwidth in the initial quality defect data would be adjusted to obtain the target quality defect threshold. For example, it could be adjusted from the first threshold in the initial quality defect data to the second threshold, where the second threshold is less than the first threshold.

[0082] In this embodiment, real-time data is used to make timely and accurate judgments on whether the network load meets business requirements. When it is determined that the network status cannot meet the requirements, the initial poor quality data is adjusted in a timely manner. This can accurately quantify the root causes of poor business quality, provide a reliable data foundation for generating differentiated protection strategies, and improve the utilization rate of network resources.

[0083] In one embodiment, the method further includes:

[0084] Based on the user operation data, a demand forecast data is determined; and based on the wireless load data, a load forecast data is determined. If the load forecast data meets the demand forecast data, a resource pre-guarantee strategy is generated based on the user operation data, and network resources are allocated to the user within the operation time period corresponding to the user operation data using the resource pre-guarantee strategy.

[0085] The demand forecast data represents the performance metrics required to ensure user operations. User operation data can be ticket-grabbing operations, and the corresponding demand forecast data can be the ticket-grabbing guarantee time, bandwidth, and scheduling priority required to ensure ticket-grabbing operations. The wireless load data can be historical wireless load data collected within a historical time period, and the load forecast data is the predicted wireless load data, such as the predicted wireless load data within a specified time period. This specified time period can be the scheduling time period required by the user operation data, such as the time period during which users perform ticket-grabbing operations.

[0086] For example, network data analysis can predict resource data—that ensures stable operation of user data—based on user-side data to obtain demand forecast data. Correspondingly, network data analysis can also predict load data for future time periods based on historical wireless load data and a pre-trained load prediction model. For instance, it can predict load data for a specified time period, i.e., the load forecast data for the time period required for operation. The load prediction model can be an AI model trained on neural networks, deep learning models, etc., based on load data and the corresponding time data.

[0087] In this way, the network data analysis function can make a judgment based on the matching between demand forecast data and load forecast data. That is, it can determine whether the load forecast data within the scheduling time period corresponding to the user operation data meets the demand forecast data. If it is determined that the load forecast data meets the demand forecast data, then the network data analysis function can provide a resource pre-guarantee strategy for the terminal device based on the user behavior data. That is, it can reserve the network resources corresponding to the resource pre-guarantee strategy for the terminal device. The network data analysis function can also allocate the network resources required by the user operation data (i.e., the reserved network resources corresponding to the resource pre-guarantee strategy) to the user device within the operation time period (scheduling time period) corresponding to the user operation data based on the resource pre-guarantee strategy.

[0088] Optionally, the network data analysis function can issue resource pre-guarantee policies to the PCF and allocate corresponding network resources to the terminal to meet business needs within the scheduling period. It can also establish dedicated loads according to the resource pre-guarantee policies to provide users with guaranteed resource support.

[0089] In this embodiment, resource demand prediction based on user behavior patterns and network capacity prediction based on historical load can be achieved, enabling predictive protection, avoiding over-allocation of resources, realizing perceptible user experience and predictable demand, and further improving the user experience.

[0090] In one embodiment, the method for allocating network resources further includes:

[0091] The judgment is made based on business operation data, network-side performance indicators, and target quality poor data. If it is determined that the abnormal operation conditions are met, then the quality poor conditions are determined to be met.

[0092] Among them, the business operation data can be the actual operation status of the terminal device when executing the business, such as the percentage of game frame drop duration or video stutter duration within a preset unit of time, which can be 5 minutes; the content of abnormal operation conditions can be that the business operation indicators corresponding to the business operation data are abnormal and the network side performance indicators do not match the dynamic quality difference threshold in the target quality difference data.

[0093] Specifically, network data analysis functions can determine business operation indicators based on the business operation data and judge whether the business operation indicators are abnormal. For example, network data analysis functions can determine business operation indicators based on business operation data, and determine that the business operation indicator corresponding to the business operation data is abnormal if the business operation indicator does not match the corresponding indicator threshold. In cases where the indicator value and business operation have an inverse incentive relationship (i.e., the larger the indicator value, the more unstable the business operation or the worse the business operation quality), the mismatch can be that the business operation indicator is greater than the corresponding indicator threshold. Such business operation indicators can be the percentage of stuttering time, the percentage of frame drop time, the number of frame drop times, the number of stutters, the number of frame rate drops, operation response latency, etc. For example, the percentage of stuttering time can be calculated based on the total video playback time and the stuttering time in the video, and if the percentage exceeds a preset percentage threshold, the business operation indicator corresponding to the business operation data is abnormal.

[0094] The network data analysis function can monitor performance indicators during service operation on the network side. For example, it can obtain the performance indicators of the service on the terminal side during operation, namely network-side performance indicators and / or terminal-side performance indicators. If it is determined that one of the performance indicators does not match the target poor quality data corresponding to the indicator type, and the service operation indicator corresponding to the service operation data is abnormal, the network data analysis function can determine that the current poor quality condition is met. This embodiment does not limit the specific type of performance indicator, such as the downlink bandwidth of the service monitored during service operation, etc.

[0095] In this embodiment, by combining business operation data and network-side performance indicators to determine whether the poor quality conditions are met, dynamic generation of network resource allocation strategies that vary from business to business and from user to user is achieved, thus realizing a balance between business experience and rational resource utilization.

[0096] In one embodiment, the specific processing steps of "allocating target network resources to users through the target resource guarantee policy" include:

[0097] Dedicated transport is established through a target resource guarantee strategy, and target network resources are allocated to users through the dedicated transport.

[0098] Among them, the target resource guarantee strategy can be the basic resource guarantee strategy, that is, the initial guarantee strategy.

[0099] Specifically, the network data analysis function, through interaction with other functions in the core network, establishes dedicated bearers in the core network based on the network resources indicated in the target resource guarantee policy and the specific values ​​of each network resource. Through these dedicated bearers, it allocates the target network resources in the core network to the user's corresponding terminal device / application. Specifically, the network data analysis function can distribute the target resource guarantee policy to the PCF (Programmable Framework Function), and through interaction between the PCF and other network elements in the core network, establish dedicated bearers. The target resource guarantee policy could be, for example, 5QI=a1 and a minimum bandwidth of b1. For instance, a dedicated bearer with 5QI=a1 and a minimum bandwidth of b1 can be established for the user in the core network. This dedicated bearer facilitates data interaction between the user and the core network, enabling the allocation of target network resources to the user through the dedicated bearer.

[0100] In this embodiment, by establishing a dedicated network that matches the target resource protection strategy, corresponding target network resources are allocated to each user. This can provide targeted resource protection for user terminals, realize dynamic adaptation of resources to actual business and needs of users, and further improve the utilization rate of network resources.

[0101] In one embodiment, such as Figure 4 As shown, the method for allocating network resources also includes:

[0102] Step 402: Periodically collect user resource feedback results via NEF. These resource feedback results are obtained after allocating target network resources to the user.

[0103] Step 404: If the resource feedback results determine that the poor quality conditions are met, an enhanced resource guarantee strategy is generated. The enhanced resource guarantee strategy includes a low-latency guarantee strategy and / or a high-bandwidth guarantee strategy. Alternatively, if the resource feedback results determine that the poor quality conditions are not met, the basic resource guarantee strategy is maintained until the poor quality conditions are met or the service is completed.

[0104] Specifically, after the terminal communicates with the core network through the dedicated bearer corresponding to the target resource guarantee strategy, i.e., after the target network resources have been allocated to the terminal, the terminal can report resource feedback results to the network data analysis function through NEF. This feedback result is the experience result of service processing based on the target network resources, such as various performance indicators and service operation data corresponding to the current terminal running the service. After the network data analysis function receives the resource feedback result, if it determines that the current service has not yet been completed, it can continue to determine whether the poor quality condition is met based on the resource feedback result. If the performance indicators in the service operation process represented by the resource feedback data can determine that the poor quality condition is no longer met, the basic resource guarantee strategy can be used again to allocate the network resources corresponding to the basic resource guarantee strategy to the terminal device, and the step of periodically collecting the user's resource feedback results through NEF in the above embodiment can be re-executed until it is determined that the service running on the terminal device has been completed, or the poor quality condition has been met based on the resource feedback result.

[0105] Optionally, if the poor quality condition is met based on resource feedback results, the network data analysis function can determine the targeted indicators corresponding to the service type running on the terminal device, and generate an enhanced resource guarantee strategy corresponding to the targeted indicators. The enhanced resource guarantee strategy is a strategy that matches the service requirements of the service running on the terminal. For example, for services with high latency requirements, the enhanced resource guarantee strategy could be a low-latency guarantee strategy; for services with high uplink / downlink bandwidth requirements, the enhanced resource guarantee strategy could be a large uplink / downlink bandwidth guarantee strategy, and so on.

[0106] It should be noted that this disclosure does not limit the order or scope of execution of the above steps 402 and 404. The terminal may execute the above steps 402 and 404 simultaneously, or execute steps 402 and 404 sequentially, or execute one or more of steps 402 and 404. Those skilled in the art can determine the specific execution based on the actual application scenario.

[0107] In this embodiment, timely and accurate allocation and adjustment of network resources are achieved.

[0108] In one embodiment, the method for allocating network resources further includes:

[0109] Enhanced dedicated loads are established through enhanced resource guarantee strategies, and enhanced network resources are allocated to users through these enhanced dedicated loads.

[0110] Specifically, the network data analysis function, through interaction with other functions in the core network, establishes dedicated bearers in the core network based on the network resources indicated in the enhanced resource guarantee strategy and the specific values ​​of each network resource. Through these dedicated bearers, it allocates the target network resources from the core network to the user's corresponding terminal device / application. Specifically, the network data analysis function can distribute the enhanced resource guarantee strategy to the PCF (Programmable Framework Function). Through interaction between the PCF and other functions in the core network, the establishment of enhanced dedicated bearers is achieved. For example, the enhanced resource guarantee strategy could be 5QI=a2 and a minimum bandwidth of b2. For instance, a dedicated bearer with 5QI=a2 and a minimum bandwidth of b2 can be established for the user in the core network. This dedicated bearer facilitates data interaction between the user and the core network, enabling the allocation of target network resources to the user through the dedicated bearer. The network resources allocated to the terminal device by the enhanced resource guarantee strategy are greater than the network resources corresponding to the initial guarantee strategy.

[0111] Optionally, if the terminal reports a target number of resource feedback results indicating poor service experience, but the network data analysis function determines that the resources currently allocated to the terminal meet the service requirements of that terminal, then the network data analysis function will not guarantee the terminal and will not accept resource allocation request reports from that terminal within a preset period, i.e., it will reject resource allocation request reports from that terminal within the preset period. The specific value corresponding to the target number can be determined based on the actual application scenario, such as 3, 5, etc.

[0112] In other words, if a terminal continuously reports poor service experience such as lag, but the network side assesses that the resource allocation far meets the service needs, NWDAF will not provide guarantees and will not accept the terminal's request reports for a certain period.

[0113] In this embodiment, enhanced network resources are allocated to the terminal through the established enhanced dedicated load, realizing dynamic resource allocation that is adapted to the terminal's running services, terminal-side performance indicators, and network-side performance indicators. Through real-time interaction between the terminal and application side and the core network, the dynamic policy adaptation mechanism of the core network is enhanced, providing a basis for the dynamic adjustment and optimization of the guarantee policy.

[0114] In related technologies, policy decisions based on terminal service quality information or network-side indicator detection are somewhat one-sided and lack comprehensive analysis of actual user experience, business needs, and network resource conditions. This embodiment breaks through the limitations of traditional reliance on a single data point by innovatively using user service experience (KQI), user behavioral intent, and business needs as decision dimensions. Through deep integration with network-side KPIs, it achieves comprehensive data analysis across three dimensions: "user, network, and business," thereby supporting the accurate quantification of the root causes of poor service quality and the dynamic adaptation of protection strategies. Compared to related technologies that obtain single terminal or network service quality information, the network resource allocation method provided in this embodiment combines a multi-modal deep fusion analysis mechanism with terminal-side experience data (KQI), network-side performance data (KPI), and application-side service requirements. This enables network decision-making to simultaneously consider user, network, and service perspectives, achieving dynamic threshold setting. Furthermore, it allows NWDAF to accurately quantify the root causes of poor service quality and generate differentiated assurance strategies, thereby maximizing network resource utilization. It also provides signaling and interface process definitions based on end-network-cloud collaboration for QoS assurance services, addressing the shortcomings of 3GPP in end-to-end assurance analysis and promoting network intelligence. Based on the NWDAF network architecture and standardized network capability opening functions, real-time interaction between the terminal and application sides and the core network enhances the core network's dynamic policy adaptation mechanism, providing a basis for dynamic adjustment and optimization of assurance strategies and addressing the shortcomings of existing standard solutions in service assurance. The following describes the specific implementation steps of the above network resource allocation method in detail with reference to a specific embodiment:

[0115] In this embodiment, the terminal's application scenario can be cloud gaming, 4K live streaming, or other latency- and bandwidth-sensitive business scenarios. The network resource allocation method provided in this embodiment is a method for dynamically optimizing QoS guarantee strategies based on multi-dimensional data analysis. It can dynamically optimize QoS strategies by combining multi-dimensional data such as actual business needs, user behavior, terminal experience, and network service monitoring, achieving precise matching between user needs and network resources. Figure 5 As shown, this is applied to a communication system, which may include terminal equipment (terminal / application), NEF, NWDAF, PCF, SMF, UPF, and RAN / OAM; specific steps may include:

[0116] S1, after the contracted user goes online, PCF subscribes to the QoS guarantee policy dynamic optimization service from NWDAF, carrying the newly added Analysis ID: Analytics ID = QoS_DY_OPT, SMF identifier, user identifier, APPID, etc.

[0117] S2a: The network side opens up its capabilities to the terminal / application side through NEF. NWDAF initiates data subscription to the terminal and application sides through NEF, including terminal service experience, user behavior and service requirements (i.e., terminal performance indicators, such as video resolution, frame rate, latency, etc. required by the terminal). The above data is reported to NWDAF through NEF.

[0118] S2b, NWDAF subscribes to and collects wireless performance data / wireless load data from the wireless OAM system, including PRB and other information.

[0119] S2c, NWDAF subscribes to key performance indicators of specified services from the user's UPF via SMF, including uplink and downlink bandwidth, packet loss rate, latency, etc.

[0120] S3a, NWDAF can perform dynamic quality degradation threshold assessment, demand forecasting, and wireless load forecasting. Specifically, NWDAF performs predictions and analyses based on collected data: it assesses and sets dynamic quality degradation thresholds (such as uplink / downlink bandwidth / latency / frame rate) based on service demand; it predicts the resources users need to guarantee based on user behavior (such as the time required for ticket booking guarantee, the required bandwidth, and the required scheduling priority); and it predicts the wireless load status based on historical wireless load data to determine whether the guarantee conditions are available during the required scheduling period.

[0121] S3b and NWDAF perform business requirement and quality deviation analysis to generate assurance strategy recommendations. Specifically, the network data analysis function can analyze business support and quality deviation, and generate dynamic assurance strategies: for example, if the network load does not meet business requirements (such as users requesting 8K resolution video, requiring a large downlink bandwidth of 70Mbps~200Mbps, which the network cannot meet), NWDAF proposes business optimization suggestions based on the network status (such as adjusting the resolution). At the same time, NWDAF adjusts the dynamic quality deviation threshold according to changes in business and assesses the need for assurance resources. If the network load meets business requirements, NWDAF combines the dynamic quality deviation threshold with terminal business experience and key network performance indicators to jointly determine the quality deviation of the business (such as video stuttering time exceeding 20% ​​within 5 minutes, and network monitoring showing downlink bandwidth below the threshold, indicating poor business quality). When the business quality is poor, an initial assurance strategy is generated to ensure basic business availability. If the predicted network load meets the predicted business requirements, NWDAF provides pre-assistance strategies for the terminal based on user behavior requirements to ensure the stable operation of temporary short-term businesses with high demand and high assurance requirements.

[0122] S4, NWDAF sends dynamic updates to the QoS guarantee policy to PCF, that is, it sends dynamically generated initial guarantee policy to allocate corresponding network resources that meet the service requirements of the terminal.

[0123] In S5, each network element in the core network can establish dedicated carriers according to the protection strategy to provide users with protection resource support.

[0124] S6, the terminal side periodically reports the user experience to NWDAF via NEF; the user experience feedback data includes business experience, business requirements and other data reports.

[0125] S7 and NWDA perform quality degradation analysis and generate enhanced resource guarantee strategies. Specifically, if NWDAF determines that quality degradation will no longer occur, the existing guarantee strategy will be maintained until quality degradation occurs or the service ends. If, after evaluation, NWDAF determines that the service is still of poor quality, NWDAF will generate enhanced guarantee strategies based on user experience feedback and network status. For example, for services with high latency requirements, a low latency guarantee strategy will be adopted, and for services with high uplink / downlink bandwidth requirements, a large uplink / downlink bandwidth guarantee strategy will be adopted.

[0126] S8. If an enhanced protection policy is generated, the NWDAF sends a protection policy update to the PCF.

[0127] S9 establishes a dedicated carrier based on the enhanced protection strategy to further provide users with protection resource support.

[0128] The process of dynamically optimizing the above-mentioned protection strategy continues until the upper limit of the network-side protection capacity is reached. If the terminal service quality is still poor, the enhanced protection resources will be reclaimed to improve the utilization rate of network resources while ensuring that the terminal service is basically available.

[0129] It should be noted that if a terminal continuously reports poor service experience such as lag, but the network side assesses that the resource allocation is far from meeting the service needs, NWDAF will not provide guarantees and will not accept the terminal's request reports for a certain period.

[0130] The method provided in this embodiment is a scheme for dynamic optimization of QoS guarantee strategy based on multi-dimensional data analysis. By combining multi-dimensional data from the core network and the application / terminal side, it performs comprehensive quality difference analysis and service guarantee resource estimation for service experience, solving the limitations of manually predefined rules and the problem of disconnect between network resource allocation and actual user experience in related technologies.

[0131] Specifically, the network resource allocation method in this embodiment defines an Analysis ID for the dynamic optimization service of QoS guarantee policies. This is the first time a dedicated analysis identifier, Analytics ID = QoS_DY_OPT, has been defined. This identifier serves as a signaling parameter for the PCF to subscribe to the NWDAF for the closed-loop optimization service of the policy, changing the guarantee method based on fixed policy templates in related technologies. Through this Analysis ID, the NWDAF triggers a collaborative guarantee mechanism based on end-to-end multi-dimensional data to achieve linkage between network resources and actual user needs. This enables the network to accurately respond to differentiated service requirements, improving the experience of high-value services while avoiding resource waste.

[0132] Specifically, the network resource allocation method in this embodiment enhances the data dimensions of NWDAF's protection strategy analysis, expands the data dimensions of NWDAF strategy analysis, and constructs a "terminal-network-service" triple data fusion analysis framework. It adds terminal-side service experience data (such as video stuttering rate and operation response latency), user behavior data (such as service usage habits and urgency), and terminal native requirements (such as device-declared resolution / frame rate requirements). Simultaneously, it introduces predictive data dimensions, including resource demand prediction based on user behavior patterns and network capacity prediction based on historical load. This multi-dimensional data fusion mechanism enables NWDAF to accurately quantify the root causes of poor service quality and generate differentiated protection strategies, thereby maximizing network resource utilization. It also enhances the dynamic adaptation and analysis capabilities of NWDAF's protection strategies, achieving real-time adaptation and continuous optimization of protection strategies within NWDAF. It innovatively supports predictive protection, enabling resource reservation in advance based on user behavior predictions. Through continuous closed-loop optimization of strategies, it avoids insufficient protection or over-allocation of resources, significantly improving network resource utilization efficiency and service experience quality.

[0133] In other words, based on multidimensional data analysis, it achieves integrated analysis of multidimensional data from the terminal side, network side, and business side, enabling dynamic strategy generation and closed-loop optimization that vary depending on the business, user, and real-time status. This overcomes the inherent defects of traditional static configuration mode, such as sluggish response and resource mismatch. It achieves a fundamental shift from static and rigid configuration strategies to dynamic and intelligent personalized strategies that vary depending on the business, user, and real-time status, thereby significantly improving network resource utilization efficiency while ensuring user experience. Furthermore, it upgrades from "network-centralized" static configuration assurance to "end-network-cloud collaborative" dynamic intelligent adaptation, pioneering multidimensional data analysis based on NWDAF, solving the integration problem of the terminal side, network side, and application side. By introducing "predictive proactive assurance" and "closed-loop monitoring and decision-making," it breaks the rigidity of manually predefined rules and provides a more complete solution for intelligent network decision-making.

[0134] In other words, this embodiment proposes a system and method for dynamically optimizing QoS assurance strategies based on multidimensional data analysis. By providing dynamic optimization services for PCF (Network Flow Framework), NWDAF (Network Flow Assurance Optimization) combines multidimensional data from the core network and application / terminal sides to perform comprehensive quality difference analysis and service assurance resource estimation for service experience. This solves the limitations and rigidity of traditional NWDAF-based predefined service assurance strategies, aiming to improve user service experience, optimize network resource scheduling, and facilitate the evolution of intelligent networks. It also constructs a new type of network assurance service centered on user experience and based on data-driven principles. The value to user experience lies in the shift from "static configuration of equal assurance" to "precise adaptation of differentiated assurance." The proposed system and method for dynamically optimizing QoS assurance strategies through multidimensional data analysis achieves perceptible user experience and predictable needs, solving the problem of the disconnect between user needs and resource assurance, and improving user experience. The value to network operations lies in achieving dynamic threshold adjustment and dynamic generation, optimization, and recycling of policies through dynamic adaptation and predictive resource allocation. This reduces the cost of manual analysis and configuration, improves network resource efficiency, and provides differentiated service capabilities for high-value services. It also solves the problem in related technologies where resources are difficult to adapt to actual business and terminal needs due to manually predefined policies. This embodiment establishes a closed-loop optimization mechanism to achieve the linkage between user experience and QoS policies, as well as the dynamic adaptation between user needs and network resources. It is particularly suitable for high-value business scenarios that are sensitive to latency and bandwidth, such as cloud gaming and 4K live streaming, providing key technical support for operators to build intelligent and differentiated dynamic services.

[0135] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0136] Based on the same inventive concept, this application also provides a network resource allocation apparatus for implementing the network resource allocation method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations of one or more network resource allocation apparatus embodiments provided below can be found in the limitations of the network resource allocation method described above, and will not be repeated here.

[0137] In one exemplary embodiment, such as Figure 6 As shown, a network resource allocation device 600 is provided for use in the network data analysis function (NWDAF), comprising:

[0138] The first acquisition module 602 is used to acquire multi-dimensional data corresponding to the service. The multi-dimensional data includes user-side data, network-side performance indicators, and wireless load data. The user-side data includes service operation data, user operation data, and terminal-side performance indicators.

[0139] The first determining module 604 is used to perform a quality defect assessment based on the multi-dimensional data and determine the target quality defect data.

[0140] The first generation module 606 is used to generate a target resource guarantee strategy if the wireless load data meets the terminal-side performance indicators and the target quality defect data determines that the quality defect conditions are met.

[0141] The allocation module 608 is used to allocate target network resources to the user through the target resource guarantee strategy.

[0142] In one embodiment, the first determining module is specifically used for:

[0143] Based on the user-side data and / or the network-side performance indicators, a quality defect assessment is performed to determine the initial quality defect data;

[0144] If it is determined that the wireless load data does not meet the terminal-side performance indicators, the terminal-side performance indicators are adjusted based on the network-side performance indicators to obtain updated terminal-side performance indicators, and the initial poor quality data is adjusted based on the updated terminal-side performance indicators to obtain updated poor quality data, and the updated poor quality data is determined as the target poor quality data.

[0145] In one embodiment, the device further includes:

[0146] The second determining module is specifically used to make predictions based on the user operation data to determine demand prediction data; and to make predictions based on the wireless load data to determine load prediction data; if the load prediction data meets the demand prediction data, then a resource pre-guarantee strategy is generated based on the user operation data, and network resources are allocated to the user within the operation time period corresponding to the user operation data through the resource pre-guarantee strategy.

[0147] In one embodiment, the device further includes:

[0148] The third determining module is used to make a judgment based on the business operation data, network-side performance indicators and the target poor quality data. If it is determined that the abnormal operation conditions are met, then the poor quality conditions are met.

[0149] In one embodiment, the allocation module is specifically used for:

[0150] A dedicated transport is established through the target resource guarantee strategy, and target network resources are allocated to the user through the dedicated transport.

[0151] In one embodiment, the device further includes:

[0152] The acquisition module is used to periodically acquire the user's resource feedback results through NEF; the resource feedback results are obtained after allocating target network resources to the user.

[0153] The second generation module is configured to generate an enhanced resource guarantee strategy if the poor quality condition is determined to be met based on the resource feedback result; the enhanced resource guarantee strategy includes a low-latency guarantee strategy and / or a high-bandwidth guarantee strategy; or,

[0154] The maintenance module is used to maintain the basic resource protection strategy if it is determined from the resource feedback results that the poor quality conditions are not met.

[0155] In one embodiment, the device further includes:

[0156] A module is established to establish an enhanced dedicated load through the enhanced resource guarantee strategy, and to allocate enhanced network resources to the user through the enhanced dedicated load.

[0157] Each module in the aforementioned network resource allocation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0158] Figure 7This is a schematic diagram of the structure of a communication device provided in an embodiment of this application. The communication device may include a receiver 71, a memory 72, a processor 73, at least one communication bus 74, and a transmitter 75. The communication bus 74 is used to implement communication connections between components. The memory 72 may include a high-speed RAM memory, and may also include non-volatile memory (NVM), such as at least one disk storage device. The memory 72 can store various programs for performing various processing functions and implementing the method steps of this embodiment. In this embodiment, the transmitter 75 can be a radio frequency processing module or a baseband processing module in the communication device, and the receiver 71 can also be a radio frequency processing module or a baseband processing module in the communication device. The transmitter 75 and receiver 71 can be integrated together to form a transceiver. Both the transmitter 75 and receiver 71 can be coupled to the processor 73, and can perform receiving or transmitting actions under the instruction or control of the processor 73.

[0159] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0160] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0161] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0162] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0163] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0164] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0165] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0166] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for allocating network resources, characterized in that, The method, applied to the Network Data Analysis Function (NWDAF), includes: Acquire multi-dimensional data corresponding to the business, including user-side data, network-side performance indicators, and wireless load data; the user-side data includes business operation data, user operation data, and terminal-side performance indicators. Based on the multi-dimensional data, a quality assessment is performed to determine the target quality data. If the wireless load data meets the terminal-side performance indicators, and the target poor quality data determines that the poor quality conditions are met, then a target resource guarantee strategy is generated. The target resource guarantee strategy allocates target network resources to the user.

2. The method according to claim 1, characterized in that, The step of performing a quality defect assessment based on the multi-dimensional data to determine the target quality defect data includes: Based on the user-side data and / or the network-side performance indicators, a quality defect assessment is performed to determine the initial quality defect data; If it is determined that the wireless load data does not meet the terminal-side performance indicators, the terminal-side performance indicators are adjusted based on the network-side performance indicators to obtain updated terminal-side performance indicators, and the initial poor quality data is adjusted based on the updated terminal-side performance indicators to obtain updated poor quality data, and the updated poor quality data is determined as the target poor quality data.

3. The method according to claim 1, characterized in that, The method further includes: Based on the user operation data, forecasts are made to determine demand forecast data; and based on the wireless load data, forecasts are made to determine load forecast data. If the load prediction data meets the demand prediction data, a resource pre-guarantee strategy is generated based on the user operation data, and network resources are allocated to the user within the operation time period corresponding to the user operation data using the resource pre-guarantee strategy.

4. The method according to claim 1, characterized in that, The method further includes: The judgment is made based on the business operation data, network-side performance indicators, and the target poor quality data. If it is determined that the abnormal operation conditions are met, then the poor quality conditions are determined to be met.

5. The method according to claim 1, characterized in that, The allocation of target network resources to the user through the target resource guarantee policy includes: A dedicated transport is established through the target resource guarantee strategy, and target network resources are allocated to the user through the dedicated transport.

6. The method according to claim 1, characterized in that, The method further includes: The resource feedback results of the user are collected periodically by NEF; the resource feedback results are obtained after the target network resources are allocated to the user. If the resource feedback results determine that the poor quality condition is met, an enhanced resource guarantee strategy is generated; the enhanced resource guarantee strategy includes a low-latency guarantee strategy and / or a high-bandwidth guarantee strategy; or, If the resource feedback results indicate that the poor quality conditions are not met, the target resource guarantee strategy will continue to operate until the poor quality conditions are met or the business is completed.

7. The method according to claim 6, characterized in that, The method further includes: An enhanced dedicated load is established through the enhanced resource guarantee strategy, and enhanced network resources are allocated to the user through the enhanced dedicated load.

8. A network resource allocation device, characterized in that, The device, used for Network Data Analysis Function (NWDAF), includes: The first acquisition module is used to acquire multi-dimensional data corresponding to the service. The multi-dimensional data includes user-side data, network-side performance indicators, and wireless load data. The user-side data includes service operation data, user operation data, and terminal-side performance indicators. The first determining module is used to perform a quality defect assessment based on the multi-dimensional data and determine the target quality defect data. The first generation module is used to generate a target resource guarantee strategy if the wireless load data meets the terminal-side performance indicators and the target poor quality data determines that the poor quality conditions are met. The allocation module is used to allocate target network resources to the user through the target resource guarantee policy.

9. A communication device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

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

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

Images