Wireless resource service quality full-dimensional evaluation method, system, storage medium and terminal

Abstract

The present invention provides a method, system, storage medium, and terminal for full-dimensional evaluation of wireless resource service quality. The method includes: obtaining multi-dimensional network service quality perception information provided by a user terminal for spectrum resources, environment, and computing power resources; based on the multi-dimensional network service quality perception information, obtaining an evaluation result of the wireless resource service quality according to a multi-task learning neural network, so that a scheduling module prioritizes and dynamically reschedules wireless resources based on the evaluation result; obtaining a scheduling execution result of the dynamic rescheduling, and correcting the multi-task learning neural network based on the scheduling execution result and the multi-dimensional network service quality perception information. The method, system, storage medium, and terminal for full-dimensional evaluation of wireless resource service quality of the present invention realize panoramic perception and dynamic optimization of spectrum, environment, and computing power resources based on a full-dimensional indicator system, which helps to realize intelligent resource allocation and multi-dimensional guarantee of service quality.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless communications, and in particular to a method, system, storage medium, and terminal for full-dimensional evaluation of wireless resource service quality. Background Art

[0002] As wireless communication technology accelerates its evolution from the fifth generation mobile communication system (5G) to the sixth generation mobile communication system (6G), wireless networks are facing unprecedented challenges of scenario complexity and service diversification.

[0003] On the application demand side, emerging scenarios such as the Internet of Things, Industrial Internet, Intelligent Transportation, and Holographic Communications are placing stringent and refined demands on service quality. For example, industrial automation control demands extreme performance with end-to-end latency below 1ms and jitter error below 1μs; while holographic communications require a 10Gbps peak rate and submillimeter spatial synchronization accuracy. These demands far exceed the capabilities of traditional wireless resource evaluation systems. Existing evaluation systems, centered around single-dimensional metrics such as throughput and packet loss rate, have their limitations systematically amplified in the context of 6G multi-domain convergence. They are unable to dynamically quantify the synergistic effectiveness of multi-domain resources such as spectrum, environment, and computing power, and struggle to address the differentiated service requirements of scenarios such as ultra-reliable low-latency communications and massive machine-type communications (mMTC). This exposes a fundamental contradiction between static evaluation models and the dynamic business environment.

[0004] On the technology supply side, 6G is driving a structural shift in the wireless resource management paradigm through the deep integration of disruptive cutting-edge technologies such as artificial intelligence (AI), terahertz communications, smart metasurfaces, and quantum communications. For example, AI-driven dynamic spectrum sharing strategies can integrate deep reinforcement learning methods to achieve real-time awareness and rational allocation of spectrum holes. This requires the introduction of new metrics such as dynamic spectrum efficiency and interference tolerance. Terahertz communications are susceptible to environmental temperature, humidity, and obstruction, necessitating the development of multimodal environmental data fusion accuracy and real-time modeling metrics to maintain link stability. Deep collaboration between edge computing and network functions requires leveraging metrics such as heterogeneous computing scheduling flexibility and resource fragmentation index to achieve global optimization of task offloading and resource allocation. This technological evolution is increasingly driving the intelligent, high-dimensional, and heterogeneous nature of wireless resources. Traditional evaluation systems, due to their static and isolated nature, are unable to adapt to the dynamic environmental response, cross-domain collaborative optimization, and fine-grained parameter measurement requirements of these new technologies. These systems are even becoming a bottleneck hindering the unleashing of 6G's enormous potential.

[0005] Therefore, it can be seen that the limitations of the existing wireless resource service quality (QoRS) evaluation system, which focuses on single-dimensional indicators such as throughput, packet loss rate, and spectrum efficiency, have been systematically magnified in the 6G multi-domain integration scenario, exposing the following deficiencies.

[0006] a) Traditional models only evaluate single resource dimensions such as spectrum, power, and time slots in isolation, and are unable to quantify the synergistic effectiveness of cross-domain resources (such as the joint optimization of dynamic congestion avoidance in the terahertz band and edge computing scheduling).

[0007] b) Static threshold assessment mechanisms (such as fixed-threshold signal-to-noise ratio measurements) are seriously out of touch with dynamic service environments. In complex scenarios with sudden interference, the system bit error rate will face a sudden increase.

[0008] c) The existing system lacks measurement standards for new AI-driven resource management parameters (such as the convergence of federated learning models and the accuracy of intelligent reflector beamforming), resulting in significant efficiency losses in actual deployment of AI-enabled spectrum sharing strategies.

[0009] The international standardization process further highlights the urgency of system innovation. The ITU-R listed "native intelligent radio resource management" as a core capability of 6G in its IMT-2030 Framework Recommendation, and 3GPP focused on resource optimization models enabled by machine learning. These initiatives point to a shared consensus: the urgent need to establish an evaluation system compatible with the standardization process and capable of quantifying the performance of emerging technologies. Furthermore, the demand for deterministic quality of service (QoS) (such as bounded latency and self-healing capabilities) in scenarios like the industrial metaverse and digital twins is driving a shift in network architecture from best-effort to precise assurance. Summary of the Invention

[0010] In view of the above-mentioned problems, the purpose of the present invention is to provide a full-dimensional evaluation method, system, storage medium and terminal for wireless resource service quality. Based on a full-dimensional indicator system, it realizes panoramic perception and dynamic optimization of spectrum, environment and computing power resources, which helps to realize intelligent resource allocation and multi-dimensional guarantee of service quality.

[0011] In the first aspect, the present invention provides a full-dimensional evaluation method for wireless resource service quality, the method comprising the following steps: obtaining multi-dimensional network service quality perception information provided by the user terminal for spectrum resources, environment and computing power resources; based on the multi-dimensional network service quality perception information, obtaining the evaluation result of the wireless resource service quality according to the multi-task learning neural network, so that the scheduling module prioritizes and dynamically rescheduling the wireless resources based on the evaluation result; obtaining the scheduling execution result of the dynamic rescheduling, and correcting the multi-task learning neural network based on the scheduling execution result and the multi-dimensional network service quality perception information.

[0012] In an implementation of the first aspect, obtaining multi-dimensional network service quality perception information provided by a user terminal includes the following steps:

[0013] Normalize spectrum resource perception information, environment perception information, and computing resource perception information to obtain normalized perception information;

[0014] Performing spatiotemporal alignment on the normalized perception information to obtain aligned perception information;

[0015] Performing semantic encoding on the alignment perception information to obtain perception features;

[0016] Vector compression is performed on the perception feature to obtain a multi-dimensional network service quality perception vector as the multi-dimensional network service quality perception information.

[0017] In an implementation of the first aspect, the evaluation results include the total score of the wireless resource service quality and the dimension score values ​​of different evaluation dimensions; the evaluation dimensions include the performance, security, overhead and autonomy of the wireless resources; the performance includes digital performance sub-items, algorithm performance sub-items, computing power performance sub-items and connection performance sub-items; the security includes data security sub-items and algorithm security sub-items; the overhead includes storage overhead sub-items, computing overhead sub-items, transmission overhead sub-items and energy consumption overhead sub-items; the autonomy includes data autonomy sub-items and algorithm autonomy sub-items.

[0018] In an implementation of the first aspect, obtaining an evaluation result of the wireless resource service quality according to a multi-task learning neural network based on the multi-dimensional network service quality perception information includes the following steps:

[0019] Inputting the multi-dimensional network service quality perception information into a trained multi-task learning neural network;

[0020] Obtain the total wireless resource service quality score output by the multi-task learning neural network ,in N Indicates the total number of sub-items in each evaluation dimension. x i Indicates the i Multi-dimensional network service quality perception information corresponding to the evaluation dimension sub-items, f i (·) indicates the i The sub-scoring function corresponding to the evaluation dimension sub-item, α i Indicates the i The weight coefficients corresponding to the evaluation dimension sub-items and ∑ α i =1;

[0021] Get the dimension score value of any evaluation dimension ,in M Indicates the total number of sub-items corresponding to the evaluation dimension. x j Indicates the evaluation dimension j The multi-dimensional network service quality perception information corresponding to the sub-items, f j (·) indicates the first dimension of the evaluation j The sub-scoring function corresponding to the sub-items, α j Indicates the evaluation dimension j The weight coefficient corresponding to each sub-item;

[0022] The total score of the wireless resource service quality and the dimension score values ​​of the evaluation dimensions are used as the evaluation results.

[0023] In an implementation of the first aspect, the dynamic scheduling module prioritizing and dynamically rescheduling the radio resources based on the evaluation result includes the following steps:

[0024] Get the i Radio resource scheduling priority for each user , where QoRS (i) For the i The total score of wireless resource service quality of each user, β ∈[0,1] is the adjustable weight coefficient; , QoRS (i) best For the i The user achieves the best total score of wireless resource service quality within the historical window. ε It is a small positive number introduced to prevent the denominator from being zero;

[0025] Based on the radio resource scheduling priority p i and the schedulable resource set, the system obtains the dynamic scheduling results , where A=[ a ij ], a ij ∈{0,1} indicates whether the resource j Assign to user i , w ij resource j Assign to user i The weight of .

[0026] In an implementation of the first aspect, correcting the multi-task learning neural network based on the scheduling execution result and the multi-dimensional network service quality perception information includes the following steps:

[0027] Calculate the deviation index between the scheduling execution result and the multi-dimensional network service quality perception information , where QoS post (i) Indicates the i The actual measurement value of multi-dimensional network service quality perception information, QoS pred (i) Indicates that before this round of scheduling i The predicted value of multi-dimensional network service quality perception information, δ i Indicates the i Deviation index between multi-dimensional network service quality perception information and corresponding scheduling execution results;

[0028] When the deviation index is greater than a preset threshold, the multi-task learning neural network is retrained or fine-tuned to adjust the weight coefficient of the wireless resource priority.

[0029] In a second aspect, the present invention provides a full-dimensional evaluation system for wireless resource service quality, the system comprising an acquisition module, an evaluation module, and a feedback module;

[0030] The acquisition module is used to obtain multi-dimensional network service quality perception information provided by the user terminal for spectrum resources, environment and computing power resources;

[0031] The evaluation module is configured to obtain an evaluation result of the wireless resource service quality based on the multi-dimensional network service quality perception information according to a multi-task learning neural network, so that the scheduling module prioritizes and dynamically reschedules the wireless resources based on the evaluation result;

[0032] The feedback module is used to obtain the scheduling execution result of the dynamic rescheduling, and to correct the multi-task learning neural network based on the scheduling execution result and the multi-dimensional network service quality perception information.

[0033] In a third aspect, the present invention provides a storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned full-dimensional evaluation method for wireless resource service quality.

[0034] In a fourth aspect, the present invention provides an evaluation terminal, comprising: a processor and a memory;

[0035] The memory is used to store computer programs;

[0036] The processor is configured to execute the computer program stored in the memory, so that the evaluation terminal executes the above-mentioned full-dimensional evaluation method for wireless resource service quality.

[0037] In a fifth aspect, the present invention provides a full-dimensional evaluation system for wireless resource service quality, comprising the above-mentioned evaluation terminal, perception module, scheduling module, and edge control module;

[0038] The perception module is used to collect multi-dimensional network service quality perception information provided by the user evaluation terminal for spectrum resources, environment and computing power resources, and provide it to the evaluation terminal;

[0039] The scheduling module is used to prioritize and dynamically reschedule wireless resources based on the evaluation results provided by the evaluation terminal;

[0040] The edge control module is used to generate the scheduling execution result of the dynamic rescheduling and provide it to the evaluation terminal.

[0041] As described above, the method, system, storage medium, and terminal for full-dimensional evaluation of wireless resource service quality of the present invention have the following beneficial effects.

[0042] (1) A multi-dimensional and multi-granular evaluation index system has been constructed, integrating the four core dimensions of performance, security, overhead, and autonomy, covering multiple levels from link physical status and resource usage to service response performance and user experience perception. For typical application scenarios in 6G, a customizable and evolvable service quality index system can be implemented to ensure the accuracy and practicality of evaluation under complex communication conditions. Through the multi-dimensional integration based on quality of service (QoS), user experience (QoE), and network capabilities (such as resource status, channel quality, and energy consumption), the impact of wireless resource allocation on service quality in the 6G network environment can be more accurately portrayed, improving evaluation accuracy and coverage.

[0043] (2) The introduction of a state perception mechanism based on machine learning can realize real-time monitoring of the current integrated space-air-ground network resources (such as low-orbit satellite channels, edge computing nodes, air platform spectrum resources, etc.), and can track the status of wireless resources and changes in user needs in real time. It combines machine learning methods for feature extraction and model optimization to support rapid evaluation before scheduling decisions, improve the foresight and accuracy of resource scheduling, and dynamically update the evaluation model through a feedback mechanism to achieve rapid response to network changes and improve the agility and adaptability of the system.

[0044] (3) By using the multi-dimensional QoRS evaluation results as the key input of the resource scheduling algorithm, the upper-layer intelligent control module can achieve cross-layer and cross-domain intelligent collaborative optimization of multiple resources such as spectrum, power, cache, and routing. This not only significantly improves the system's throughput and energy efficiency, but also effectively reduces communication latency, optimizes key indicators, and enhances the network's robustness and service reliability in complex scenarios.

[0045] (4) It can provide differentiated, multi-level service quality assurance strategies based on different business scenarios, including enhanced mobile broadband (eMBB), massive machine-type communication (mMTC), ultra-reliable low-latency communication (uRLLC), etc., to achieve the transition from "resource priority" to "service priority", and ultimately improve the user's comprehensive perceived experience.

[0046] (5) Compared with the traditional "black box" scheduling strategy, it provides a clear structure and logical closed-loop evaluation framework, making the 6G network operation process more verifiable and the scheduling results more explainable, enhancing the trust of both service providers and users, and helping to build a transparent, fair and reliable new network governance ecosystem.

[0047] (6) It provides core methodological support for the paradigm upgrade of 6G networks from "connectivity empowerment" to "service intelligence connection". Its innovation lies in upgrading network resource configuration from "experience-driven" to "service-defined", realizing cross-domain elastic scheduling of spectrum-environment-computing resources, and providing a quantifiable, verifiable and scalable methodological foundation for 6G communication networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 FIG2 is a flow chart of a method for full-dimensional evaluation of wireless resource service quality in one embodiment of the present invention.

[0049] Figure 2 FIG2 is a schematic diagram showing the radio resource service quality evaluation dimensions and indicators in one embodiment of the present invention.

[0050] Figure 3 FIG. 1 is a schematic diagram showing the structure of a full-dimensional evaluation system for wireless resource service quality according to an embodiment of the present invention.

[0051] Figure 4 FIG. 1 is a schematic structural diagram of an evaluation terminal according to an embodiment of the present invention.

[0052] Figure 5 FIG2 is a schematic structural diagram of another embodiment of the wireless resource service quality full-dimensional evaluation system of the present invention. DETAILED DESCRIPTION

[0053] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0054] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0055] The present invention's full-dimensional wireless resource quality of service (QoS) assessment method, system, storage medium, and terminal are designed for intelligent scheduling and QoS assurance of wireless resources in multiple service scenarios, including enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (uRLLC) in wireless networks. The method, system, storage medium, and terminal aim to provide a unified and scalable solution for multi-dimensional QoS assessment in complex and dynamic wireless environments. This approach integrates multiple core dimensions, including but not limited to performance, security, overhead, and autonomy, and maps them to technical implementation layers, such as spectrum resource QoS (Quality of Service), environmental information QoS, and computing resource QoS. Ultimately, it establishes a unified assessment framework covering the entire lifecycle of wireless resources, thereby overcoming the contradiction between static assessment paradigms and dynamic technological evolution. This framework provides wireless networks with a QoS benchmark that is both accurate and adaptable, enabling comprehensive awareness and dynamic optimization of wireless resources. It should be noted that the present invention's full-dimensional wireless resource QoS assessment method, system, storage medium, and terminal are particularly suitable for 6G networks.

[0056] The technical solutions in the embodiments of the present invention will be described in detail below with reference to the accompanying drawings in the embodiments of the present invention.

[0057] like Figure 1 As shown, in one embodiment, the method for full-dimensional evaluation of wireless resource service quality of the present invention includes steps S1 to S3.

[0058] Step S1: Acquire multi-dimensional network service quality perception information provided by the user terminal with respect to spectrum resources, environment, and computing power resources.

[0059] Specifically, the multi-source heterogeneous access mechanism based on the perception module in the present invention realizes global monitoring of core parameters such as the dynamic distribution of spectrum resources, environmental interference fluctuations, and computing load status through real-time data collection and collaborative feedback from global nodes such as ground base stations, satellite links, and unmanned platforms, obtains multi-dimensional network service quality perception information (multi-dimensional network QoRS perception information), and uploads it through the 6G access gateway node.

[0060] In terms of spectrum resource perception, by identifying the cyclostationary characteristics of wireless signals, cyclic autocorrelation operations are performed on user signals to extract parameters such as spectrum utilization, idle frequency band distribution, channel occupancy and interference characteristics in the user area, thereby reducing the negative effects such as false alarm fluctuations, detection probability distortion, and user misidentification, and realizing non-intrusive perception and classification of spectrum status.

[0061] In terms of environmental perception, the system integrates multi-source environmental information collected by user terminals and edge nodes, combines indicators such as dynamic channel quality, occlusion change trends, and user movement trajectories, and constructs an environmental state evolution model to assist in identifying channel degradation risks and service interruption hazards in complex scenarios.

[0062] In terms of computing resource perception, the system conducts status perception of computing resource nodes such as edge nodes and access base stations associated with user access paths, covering key indicators such as the utilization of heterogeneous computing resources such as CPU, GPU, DPU, and NPU, operating load, and response capability. This enables standardized classification of computing nodes and quantitative evaluation of resource capabilities, and can also identify service priorities and required resource capabilities through computing demand instructions, thereby achieving dynamic adaptation and efficient matching of services and computing power.

[0063] In one embodiment, obtaining multi-dimensional network service quality perception information provided by a user terminal includes the following steps.

[0064] 11) Normalize spectrum resource perception information, environmental perception information, and computing resource perception information to eliminate dimensional differences between different indicators and obtain normalized perception information.

[0065] 12) Performing spatiotemporal alignment on the normalized perception information to obtain aligned perception information.

[0066] The normalized perception information is synchronized in time and space dimensions by combining the user's location movement trajectory with the network topology evolution information to ensure the temporal consistency and context relevance of the input information.

[0067] 13) Performing semantic encoding on the alignment perception information to obtain perception features.

[0068] Among them, an embedded encoder is used to semantically annotate and map the heterogeneous information in the aligned perception information, and discrete information such as behavioral preferences, business types, and node attributes are converted into computable vector form; for continuous indicators, a sliding window aggregation strategy is used for feature extraction to retain trend characteristics and short-term fluctuation patterns, thereby obtaining perception features.

[0069] 14) Performing vector compression on the perception feature to obtain a multi-dimensional network service quality perception vector as the multi-dimensional network service quality perception information.

[0070] Among them, all perception features are mapped into a multi-dimensional network QoRS perception vector in a unified format through vector compression. This vector constitutes a comprehensive multi-dimensional network service quality perception view of user resource status, behavioral characteristics and environmental conditions, providing an interpretable and quantifiable input basis for QoRS evaluation, significantly improving the evaluation system's sensitivity and responsiveness to service quality assurance.

[0071] Step S2: Based on the multi-dimensional network service quality perception information, obtain the evaluation result of the wireless resource service quality according to the multi-task learning neural network, so that the scheduling module prioritizes and dynamically reschedules the wireless resources based on the evaluation result.

[0072] Specifically, in the evaluation module of the present invention, the multi-dimensional network service quality perception information is input into a trained multi-task learning neural network to obtain the evaluation result of the wireless resource service quality.

[0073] The evaluation results include the total score of wireless resource service quality and the dimension score values ​​of different evaluation dimensions. Figure 2 As shown, in one embodiment, the evaluation dimensions include wireless resource performance, security, overhead, and autonomy. The performance sub-item includes digital performance, algorithm performance, computing power performance, and connection performance. The digital performance sub-item includes data quality and accuracy assurance, as well as data update and timeliness management. The algorithm performance sub-item includes the selection and application of efficient algorithms, as well as algorithm optimization and performance improvement. The computing power performance sub-item includes the rational allocation of computing resources and technical approaches to computing power improvement. The connection performance sub-item includes technical implementations for stable connections and connection speed optimization strategies. Security includes data security and algorithm security sub-items. The data security sub-item includes data encryption and privacy protection, as well as data backup and recovery mechanisms. The algorithm security sub-item includes detection and prevention of algorithm vulnerabilities and an algorithm security assessment system. Overhead includes storage overhead, computing overhead, transmission overhead, and energy consumption overhead. The storage overhead sub-item includes the selection and configuration of storage devices and storage cost control methods. The computing overhead sub-item includes the efficient utilization of computing resources and computing cost optimization strategies. The transmission overhead sub-item includes the optimal selection of transmission protocols and transmission cost reduction measures. The energy consumption expenditure sub-item includes the application and practice of energy-saving technologies and energy cost management solutions. The autonomy sub-item includes the data autonomy sub-item and the algorithm autonomy sub-item. The data autonomy sub-item includes the data autonomy management model and the implementation path of digital autonomy. The algorithm autonomy sub-item includes the algorithm self-optimization mechanism and the evaluation indicators of algorithm autonomy.

[0074] In one embodiment, based on the multi-dimensional network service quality perception information, obtaining an evaluation result of the wireless resource service quality according to a multi-task learning neural network includes the following steps.

[0075] 21) Inputting the multi-dimensional network service quality perception information into a trained multi-task learning (MTL) neural network.

[0076] The multi-task learning neural network takes multi-dimensional network QoRS perception information as input, constructs feature prediction sub-channels corresponding to each dimension, and introduces an adaptive attention mechanism in the shared layer to model the implicit correlation between features of each dimension and dynamically adjust the weights. The alignment of heterogeneous perception information is achieved through feature normalization and embedding layers, and combined with scenario weight factors, the adaptability to typical business scenarios (such as eMBB, uRLLC, and mMTC) is enhanced while maintaining the generalization ability of indicators, thereby realizing wireless resource service quality evaluation.

[0077] When training the multi-task learning neural network, historical multi-dimensional network QoS perception data, network behavior feedback, and user satisfaction evaluations are used as annotation signals to construct a multi-objective loss function and jointly optimize it, enabling the multi-task learning neural network to have a highly sensitive recognition capability for abnormal conditions such as performance mutations, channel degradation, and computational congestion. The multi-task learning neural network outputs include an overall wireless resource service quality score and dimensional score values ​​for the evaluation dimensions, and dimensional evaluation metrics that significantly deviate from the target values ​​are risk-labeled, providing an accurate and explainable decision-making basis for subsequent resource scheduling.

[0078] 22) Obtaining the total wireless resource service quality score output by the multi-task learning neural network ,in N Indicates the total number of sub-items in each evaluation dimension. x i Indicates the i Multi-dimensional network service quality perception information corresponding to the evaluation dimension sub-items, f i (·) indicates the i The sub-scoring function corresponding to the evaluation dimension sub-item, α i Indicates the i The weight coefficients corresponding to the evaluation dimension sub-items and ∑ α i =1.

[0079] Among them, the sub-scoring function f i (·) can be implemented by neural network sub-model or regressor, α i Dynamically adjust based on task scenarios, user preferences, or historical feedback.

[0080] 23) Get the dimension score value of any evaluation dimension ,in M Indicates the total number of sub-items corresponding to the evaluation dimension. x j Indicates the evaluation dimension j The multi-dimensional network service quality perception information corresponding to the sub-items,f j (·) indicates the first dimension of the evaluation j The sub-scoring function corresponding to the sub-items, α j Indicates the evaluation dimension j The weight coefficient corresponding to each sub-item.

[0081] The total wireless resource service quality score and the dimension score values ​​of the evaluation dimensions are expressed in standardized dimensions to facilitate unified comparison of cross-domain indicators.

[0082] 24) The total score of the wireless resource service quality and the dimension score values ​​of the evaluation dimensions are used as the evaluation result.

[0083] It should be noted that the present invention also includes, based on the evaluation module, outputting a score confidence interval and a risk label based on the total wireless resource service quality score and the dimension score values ​​of the dimensions, to identify the degree of deviation of the current wireless resource service quality status from the set target value and the urgency of triggering a scheduling response. For example, if the autonomous dimension score is significantly lower than the set threshold, a resource rescheduling recommendation signal will be automatically triggered to support priority judgment at the scheduling control layer.

[0084] In one embodiment, the evaluation results are delivered to the scheduling module in the form of a structured QoRS evaluation report, the content of which includes but is not limited to: the current total wireless resource service quality score, the dimension score value of each evaluation dimension, the indicator deviation trend, the potential performance bottleneck, and the service level recommendation for the adapted service type, thereby providing a clear guide for subsequent resource reconstruction and service guarantee.

[0085] The scheduling module prioritizes and dynamically reschedules wireless resources based on the evaluation results. First, a resource scheduling priority vector P is constructed based on the dimension score values ​​of each evaluation dimension. p 1 , p 2 ,…, p n ].in n Indicates the number of users, i Radio resource scheduling priority for each user , QoRS (i) For the i The total wireless resource service quality score of each user, Δ i Indicates the degree of deviation between the optimal total score of the current QoRS and the optimal total score of the historical optimal QoRS, Δ i The larger it is, the more obvious the degradation of the current resource state compared to the historical optimal state is; i When it approaches 0, it means that the current service is close to or reaches the optimal level.β ∈[0,1] is an adjustable weight coefficient, which is used to balance the reference weight of current performance and historical evolution trend. , QoRS (i) best For the i The user achieves the best total score of wireless resource service quality within the historical window. ε is a small positive number introduced to prevent the denominator from being zero. Then, all users are sorted using the priority vector, and a feasible scheduling solution set is constructed by combining the resource availability prediction within the sliding window. For example, a dynamic scheduling algorithm based on weighted maximum matching and integer linear programming constraint optimization can be used. In order to fully reflect the guiding role of priority in the resource allocation process, priority is introduced as a scheduling weighting factor to participate in the construction of the dynamic scheduling optimization model. The dynamic scheduling results are based on Get, where the resource allocation matrix A=[ a ij ], a ij ∈{0,1} indicates whether the resource j Assign to user i , w ij resource j Assign to user i The weight constraint ensures that each user can only occupy limited resources and each resource is not allocated repeatedly.

[0086] Step S3: Obtain the scheduling execution result of the dynamic rescheduling, and modify the multi-task learning neural network based on the scheduling execution result and the multi-dimensional network service quality perception information.

[0087] Specifically, the dynamic rescheduling is performed in the edge control module, which specifically includes the following operations.

[0088] A) Spectrum Migration: Users are switched to frequency bands with less interference or higher availability through central scheduling or terminal coordination.

[0089] B) Path Reconstruction: In multi-hop transmission or link instability scenarios, the forwarding path is updated based on the shortest delay or highest stability indicator.

[0090] C) Bandwidth reallocation: Dynamically adjust bandwidth allocation strategies based on service levels, prioritizing key service segments for users with low QoRS scores.

[0091] The edge control module obtains the scheduling execution result, i.e., the multi-dimensional network service quality perception information after scheduling, by executing the above dynamic rescheduling. Calculate the deviation index between the scheduling execution result and the multi-dimensional network service quality perception information. , where QoS post (i) Indicates the i The actual measurement value of multi-dimensional network service quality perception information, QoS pred (i) Indicates that before this round of scheduling i The predicted value of multi-dimensional network service quality perception information, δ i Indicates the i The deviation index between the multi-dimensional network service quality perception information and the corresponding scheduling execution results.

[0092] When the deviation index is greater than the preset threshold θ (Right now δ i > θ ), the evaluation module triggers the closed-loop correction process. Specifically, the evaluation module retrains or fine-tunes the multi-task learning neural network, adjusts the weight coefficient of the wireless resource priority, and strengthens the robust strategy. Wherein, the multi-task learning neural network is retrained or fine-tuned based on the scheduling execution result to improve the accuracy of the next round of prediction. Re-correct the resource priority weight coefficient according to the deviation distribution β , optimize the scheduling logic. For high-frequency deviation indicators, introduce elastic resource configuration, fault redundancy protection or link compensation mechanism.

[0093] Therefore, the present invention significantly enhances the adaptability to complex environmental disturbances through the closed-loop self-evolution optimization process among the evaluation of multi-task learning neural networks, resource reallocation strategy and evaluation feedback path, and provides strong guarantees for service continuity and user experience in wireless business scenarios such as 6G.

[0094] It should be noted that the multi-task learning neural network can adaptively adjust the policy parameters to adapt to different business sensitivity requirements. Among them, based on the identified business scenarios and their QoRS demand sensitivity, the scenario weight factors will be dynamically adjusted, and different priority weights will be assigned to the key indicators of the evaluation dimensions. For example, in telemedicine scenarios, the weight of factors related to delay jitter is significantly improved; in industrial control, the weight of factors related to the control instruction issuance rate will increase. The weight adjustment is iteratively optimized through the feedback learning mechanism to ensure that the strategy has the ability to respond quickly to business changes. By continuously testing and evaluating the scoring results, the parameter combination is automatically adjusted to achieve the best overall performance. At the same time, the resource reallocation strategy and evaluation feedback form a closed loop, collecting scheduling execution results and subsequent QoRS changes in real time, and correcting the multi-task learning neural network predictions and policy decisions through error feedback to ensure that it can continuously adapt to environmental fluctuations and changes in business needs, and realize the dynamic evolution of the strategy.

[0095] The protection scope of the full-dimensional evaluation method for wireless resource service quality described in the embodiment of the present invention is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, subtracting, or replacing steps in the existing technology based on the principles of the present invention are included in the protection scope of the present invention.

[0096] An embodiment of the present invention also provides a full-dimensional evaluation system for wireless resource service quality, which can implement the full-dimensional evaluation method for wireless resource service quality described in the present invention. However, the implementation device of the full-dimensional evaluation system for wireless resource service quality described in the present invention includes but is not limited to the structure of the full-dimensional evaluation system for wireless resource service quality listed in this embodiment. All structural deformations and replacements of the existing technology made according to the principles of the present invention are included in the protection scope of the present invention.

[0097] like Figure 3 As shown, in one embodiment, the wireless resource service quality full-dimensional evaluation system of the present invention includes an acquisition module 31, an evaluation module 32 and a feedback module 33.

[0098] The acquisition module 31 is used to obtain multi-dimensional network service quality perception information provided by the user terminal with respect to spectrum resources, environment and computing power resources.

[0099] The evaluation module 32 is connected to the acquisition module 31, and is used to obtain the evaluation results of the wireless resource service quality based on the multi-dimensional network service quality perception information according to the multi-task learning neural network, so that the scheduling module can prioritize and dynamically reschedule the wireless resources based on the evaluation results.

[0100] The feedback module 33 is connected to the evaluation module 32 and is used to obtain the scheduling execution result of the dynamic rescheduling and to modify the multi-task learning neural network based on the scheduling execution result and the multi-dimensional network service quality perception information.

[0101] Among them, the structures and principles of the acquisition module 31, the evaluation module 32 and the feedback module 33 correspond one-to-one to the above-mentioned full-dimensional evaluation method of wireless resource service quality, so they are not repeated here.

[0102] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices or methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0103] Modules / units described as separate components may or may not be physically separate, and components displayed as modules / units may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules / units may be selected based on actual needs to achieve the objectives of the embodiments of the present invention. For example, the functional modules / units in various embodiments of the present invention may be integrated into a single processing module, each module / unit may exist physically separately, or two or more modules / units may be integrated into a single module / unit.

[0104] Those skilled in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0105] An embodiment of the present invention also provides a computer-readable storage medium. Persons skilled in the art will appreciate that all or part of the steps in the method for full-dimensional assessment of wireless resource service quality in the above embodiment can be performed by instructing a processor through a program. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disc, or any combination thereof. The storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, or magnetic tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0106] An embodiment of the present invention further provides a terminal comprising a processor and a memory.

[0107] The memory is used to store computer programs.

[0108] The memory includes various media that can store program codes, such as ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk.

[0109] The processor is connected to the memory and is used to execute the computer program stored in the memory, so that the terminal executes the above-mentioned full-dimensional evaluation method for wireless resource service quality.

[0110] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0111] like Figure 4As shown, the evaluation terminal of the present invention is implemented as a general-purpose computing device. Components of the evaluation terminal may include, but are not limited to, one or more processors or processing units 41, a memory 42, and a bus 43 connecting various system components (including the memory 42 and the processing unit 41).

[0112] Bus 43 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0113] The evaluation terminal typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the evaluation terminal, including volatile and non-volatile media, removable and non-removable media.

[0114] The memory 42 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 421 and / or cache memory 422. The evaluation terminal may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 423 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 Not shown, usually called a "hard drive"). Although Figure 4 Although not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), as well as an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) can be provided. In these cases, each drive can be connected to bus 43 via one or more data media interfaces. Memory 42 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0115] A program / utility 424 having a set (at least one) of program modules 4241 may be stored, for example, in memory 42. Such program modules 4241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 4241 generally implement the functions and / or methods of the embodiments described herein.

[0116] The evaluation terminal may also communicate with one or more external devices (e.g., a keyboard, a pointing device, a display, etc.), one or more devices that enable a user to interact with the evaluation terminal, and / or any device that enables the evaluation terminal to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 44. Furthermore, the evaluation terminal may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 45. Figure 4 As shown, network adapter 45 communicates with other modules of the evaluation terminal via bus 43. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the evaluation terminal, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0117] like Figure 5 As shown, in one embodiment, the wireless resource service quality full-dimensional evaluation system of the present invention includes the above-mentioned evaluation terminal 51, perception module 52, scheduling module 53 and edge control module 54.

[0118] The perception module 52 is connected to the evaluation terminal 51 and is used to collect multi-dimensional network service quality perception information provided by the user evaluation terminal regarding spectrum resources, environment and computing power resources, and provide the information to the evaluation terminal 51 .

[0119] The scheduling module 53 is connected to the evaluation terminal 51 and is configured to prioritize and dynamically reschedule wireless resources based on the evaluation result provided by the evaluation terminal 51 .

[0120] The edge control module 54 is connected to the evaluation terminal 51 and the scheduling module 53 , and is configured to generate a scheduling execution result of the dynamic rescheduling and provide the result to the evaluation terminal.

[0121] The evaluation terminal 51, the perception module 52, the scheduling module 53, and the edge control module 54 support distributed deployment and possess cross-domain resource collaboration capabilities. The entire architecture boasts excellent module decoupling and scalability, adapting to the heterogeneous, diverse, and intelligent features of future 6G networks. It serves as a crucial support platform for future network resource optimization and management.

[0122] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical principles disclosed herein are intended to be covered by the claims of the present invention.

Claims

1. A method for evaluating the quality of service of wireless resources in all dimensions, characterized by: The method comprises the following steps: Obtain multi-dimensional network service quality perception information provided by user terminals for spectrum resources, environment, and computing resources; Based on the multi-dimensional network service quality perception information, obtaining an evaluation result of the wireless resource service quality according to a multi-task learning neural network, so that a scheduling module prioritizes and dynamically reschedules the wireless resources based on the evaluation result; Obtaining a scheduling execution result of the dynamic rescheduling, and modifying the multi-task learning neural network based on the scheduling execution result and the multi-dimensional network service quality perception information; The dynamic scheduling module prioritizes and dynamically rescheduling the wireless resources based on the evaluation result, including the following steps: Get the wireless resource scheduling priority p of the i-th user i =β·QoRS (i) +(1-β)·Δ i , where QoRS (i) is the total score of wireless resource service quality of the i-th user, β∈[0,1] is the adjustable weight coefficient; QoRS (i) best is the optimal total score of the wireless resource service quality achieved by the i-th user within the historical window, and ε is a small positive number introduced to prevent the denominator from being zero; Based on the radio resource scheduling priority p i and the schedulable resource set, the system obtains the dynamic scheduling results where A=[a ij ], a ij ∈{0,1} indicates whether resource j is allocated to user i, w ij The weight of resource j assigned to user i.

2. The method for full-dimensional evaluation of wireless resource service quality according to claim 1, characterized in that: Acquiring multi-dimensional network service quality perception information provided by a user terminal includes the following steps: Normalize spectrum resource perception information, environment perception information, and computing resource perception information to obtain normalized perception information; Performing spatiotemporal alignment on the normalized perception information to obtain aligned perception information; Performing semantic encoding on the alignment perception information to obtain perception features; Vector compression is performed on the perception feature to obtain a multi-dimensional network service quality perception vector as the multi-dimensional network service quality perception information.

3. The method for full-dimensional evaluation of wireless resource service quality according to claim 1, characterized in that: The evaluation dimensions of the wireless resource service quality include performance, security, overhead and autonomy of the wireless resource; The performance includes digital performance sub-items, algorithm performance sub-items, computing power performance sub-items and connection performance sub-items; the security includes data security sub-items and algorithm security sub-items; The overhead includes storage overhead sub-items, computing overhead sub-items, transmission overhead sub-items and energy consumption overhead sub-items; the autonomy includes data autonomy sub-items and algorithm autonomy sub-items.

4. The method for full-dimensional evaluation of wireless resource service quality according to claim 3, characterized in that: Based on the multi-dimensional network service quality perception information, obtaining an evaluation result of the wireless resource service quality according to a multi-task learning neural network includes the following steps: Inputting the multi-dimensional network service quality perception information into a trained multi-task learning neural network; Obtain the total wireless resource service quality score output by the multi-task learning neural network Where N represents the total number of sub-items in each evaluation dimension, x i represents the multi-dimensional network service quality perception information corresponding to the i-th evaluation dimension sub-item, f i (·) represents the sub-scoring function corresponding to the i-th evaluation dimension sub-item, α i represents the weight coefficient corresponding to the i-th evaluation dimension sub-item and ∑α i =1; Get the dimension score value of any evaluation dimension Where M represents the total number of sub-items corresponding to the evaluation dimension, x j represents the multi-dimensional network service quality perception information corresponding to the j-th sub-item of the evaluation dimension, f j (·) represents the sub-scoring function corresponding to the j-th sub-item of the evaluation dimension, α j Represents the weight coefficient corresponding to the j-th sub-item of the evaluation dimension; The total score of the wireless resource service quality and the dimension score values ​​of the evaluation dimensions are used as the evaluation results.

5. The method for full-dimensional evaluation of wireless resource service quality according to claim 1, characterized in that: Modifying the multi-task learning neural network based on the scheduling execution result and the multi-dimensional network service quality perception information includes the following steps: Calculate the deviation index between the scheduling execution result and the multi-dimensional network service quality perception information QoS post (i) represents the actual measurement value of the i-th multi-dimensional network service quality perception information, QoS pred (i) represents the predicted value of the i-th multi-dimensional network service quality perception information before this round of scheduling, δ i represents the deviation index between the i-th multi-dimensional network service quality perception information and the corresponding scheduling execution result; When the deviation index is greater than a preset threshold, the multi-task learning neural network is retrained or fine-tuned to adjust the weight coefficient of the wireless resource priority.

6. A full-dimensional evaluation system for wireless resource service quality, characterized by: The system includes an acquisition module, an evaluation module and a feedback module; The acquisition module is used to obtain multi-dimensional network service quality perception information provided by the user terminal for spectrum resources, environment and computing power resources; The evaluation module is configured to obtain an evaluation result of the wireless resource service quality based on the multi-dimensional network service quality perception information according to a multi-task learning neural network, so that the scheduling module prioritizes and dynamically reschedules the wireless resources based on the evaluation result; The feedback module is used to obtain the scheduling execution result of the dynamic rescheduling, and to modify the multi-task learning neural network based on the scheduling execution result and the multi-dimensional network service quality perception information; The dynamic scheduling module prioritizes and dynamically rescheduling the wireless resources based on the evaluation result, including the following steps: Get the wireless resource scheduling priority p of the i-th user i =β·QoRS (i) +(1-β)·Δ i , where QoRS (i) is the total score of wireless resource service quality of the i-th user, β∈[0,1] is the adjustable weight coefficient; QoRS (i) best is the optimal total score of the wireless resource service quality achieved by the i-th user within the historical window, and ε is a small positive number introduced to prevent the denominator from being zero; Based on the radio resource scheduling priority p i and the schedulable resource set, the system obtains the dynamic scheduling results where A=[a ij ], a ij ∈{0,1} indicates whether resource j is allocated to user i, w ij The weight of resource j assigned to user i.

7. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for full-dimensional evaluation of wireless resource service quality according to any one of claims 1 to 5 is implemented.

8. An evaluation terminal, characterized in that: include: processor and memory; The memory is used to store computer programs; The processor is configured to execute the computer program stored in the memory, so that the evaluation terminal executes the full-dimensional evaluation method for wireless resource service quality according to any one of claims 1 to 5.

9. A full-dimensional evaluation system for wireless resource service quality, characterized by: comprising the evaluation terminal, perception module, scheduling module, and edge control module as described in claim 8; The perception module is used to collect multi-dimensional network service quality perception information provided by the user evaluation terminal for spectrum resources, environment and computing power resources, and provide it to the evaluation terminal; The scheduling module is used to prioritize and dynamically reschedule wireless resources based on the evaluation results provided by the evaluation terminal; The edge control module is used to generate the scheduling execution result of the dynamic rescheduling and provide it to the evaluation terminal.

Images