Intelligent reflecting surface based cross-technology wireless signal coordination optimization method and system

Abstract

This application relates to a method and system for cross-standard wireless signal cooperative optimization based on intelligent reflectors. The method includes: detecting uplink reference signals transmitted by user terminals within a preset communication space via any communication operator's network using a deployed RIS array cluster; evaluating the environmental quality within the preset communication space based on these signals to obtain a communication environment quality score; adaptively enabling a RIS gain strategy for user terminals based on the communication environment quality score; and providing cross-standard wireless signal cooperative optimization for user terminals. This application overcomes the limitations of single-operator network RIS optimization schemes by utilizing a general-purpose RIS array cluster, achieving unified optimization across standards. Furthermore, it provides adaptive RIS gain strategies for user terminals based on communication environment quality, dynamically adjusting according to real-time service demands and environmental changes, thereby improving resource allocation efficiency.

Description

Technical Field

[0001] This application relates to the field of mobile communication technology, and in particular to a cross-standard wireless signal cooperative optimization method and system based on intelligent reflective surfaces. Background Technology

[0002] In recent years, with the large-scale deployment of 5G networks and the rapid development of 6G technology, wireless communication systems are facing increasingly complex coverage requirements and high-density connection challenges. Especially in indoor environments, a wide variety of terminals require wireless networks, including smart home devices, office and learning devices, mobile and portable devices, smart robots, and smart healthcare devices, all of which require a strong wireless signal indoors. Therefore, different frequency bands and different standards of wireless networks simultaneously exist within the same indoor space. Furthermore, indoor environments are complex due to decorations, partitions, and equipment, and each network suffers from multipath effects, signal attenuation, and interference, making it difficult to meet the high-quality connectivity requirements of smart homes, industrial IoT, and immersive multimedia applications.

[0003] Currently, RIS (Reconfigurable Intelligent Surface; also known as IRS, Intelligent Reflection Surface) is a revolutionary technology that dynamically adjusts the propagation characteristics of electromagnetic waves to achieve signal enhancement, interference suppression, and coverage expansion, while also possessing advantages such as low power consumption, low cost, and high flexibility. RIS technology has made significant progress in terms of form (including curved, planar, flexible, and transparent types), materials (including metals, graphene, semiconductors, and metamaterials), and functions (including reflective, projective, and holographic types), and has gradually become a solution for performance optimization in wireless communication networks. However, existing RIS technology solutions still have many areas for improvement. For example, they are usually only used to serve a single operator's network, making it difficult to achieve unified optimization across different standards.

[0004] Currently, no effective solution has been proposed for optimizing the application of RIS technology in indoor wireless communication. Summary of the Invention

[0005] This application provides a cross-standard wireless signal collaborative optimization method and system based on a smart reflector, to at least solve the problem of how to optimize the application of RIS technology in indoor wireless communication in related technologies.

[0006] In a first aspect, embodiments of this application provide a cross-standard wireless signal cooperative optimization method based on a smart reflector, the method comprising: The uplink reference signal sent by a user terminal within a preset communication space is detected by a deployed RIS array cluster, wherein the uplink reference signal is transmitted through any communication operator network. Based on the uplink reference signal, the environmental quality within the preset communication space is evaluated to obtain a communication environment quality score for the preset communication space. Based on the communication environment quality score, adaptively enable the RIS gain strategy for the user terminal; Based on the RIS panel in the RIS array cluster, the user terminal is provided with cross-standard wireless signal collaborative optimization through the RIS gain strategy.

[0007] In some embodiments, adaptively enabling a RIS gain strategy for the user terminal based on the communication environment quality score includes: Based on the communication environment quality score, determine whether to enable the RIS array cluster for the user terminal: If the communication environment quality score is greater than or equal to the first score threshold, it indicates that the communication environment quality within the preset communication space is good, and the RIS gain strategy is not enabled to save energy, reduce system complexity and signal processing overhead. If the communication environment quality score is less than the second score threshold, it indicates that the communication environment quality within the preset communication space is poor, and the RIS gain strategy is activated to reconstruct the communication link. If the communication environment quality score is less than the first score threshold and greater than or equal to the second score threshold, then the RIS gain strategy is adaptively enabled for the user terminal.

[0008] In some embodiments, adaptively enabling the RIS gain strategy for the user terminal includes: The target RIS gain strategy is determined based on the communication service requirements of the user terminal, and the target RIS panel corresponding to the communication service requirements is activated. The communication service requirements include enhanced mobile broadband (eMBB) service requirements, ultra-reliable low-latency communication (uRLLC) service requirements, and massive machine-type communication (mMTC) service requirements.

[0009] In some embodiments, determining the target RIS gain strategy based on the communication service requirements of the user terminal includes: The communication service flow characteristics of the user terminal are analyzed to identify the communication service requirements of the user terminal in real time. The communication service requirements are mapped to corresponding wireless channel KPI requirement vectors using the service QoS feature library. Based on the wireless channel KPI demand vector, and with the goal of maximizing the service satisfaction of the RIS array cluster, a corresponding target RIS gain strategy is created for the user terminal.

[0010] In some embodiments, activating the target RIS panel corresponding to the communication service requirement includes: Activate the target RIS panel in the RIS array cluster corresponding to the communication service requirement, and drive the target RIS panel to point at the user terminal for motion tracking.

[0011] In some embodiments, driving the target RIS panel to point at the user terminal for motion tracking includes: For the activated target RIS panel in the RIS array cluster, the trained liquid neural network model is invoked to calculate the optimal phase configuration; The target RIS panel is driven to form a dynamic beam through the optimal phase configuration, and the dynamic beam is pointed at the user terminal for motion tracking.

[0012] In some embodiments, based on the RIS panel in the RIS array cluster, providing cross-standard wireless signal cooperative optimization for the user terminal through the RIS gain strategy includes: When the target RIS panel activated in the RIS array cluster continuously points to the user terminal, the target RIS gain strategy provides cross-standard wireless signal cooperative optimization for the user terminal.

[0013] In some embodiments, the method includes: With the effective aperture of the RIS panel being equal to half the target wavelength as the objective, the array size and cell spacing of the RIS panel are determined by using the equivalent oscillator size calculation formula. Based on the array size and cell spacing of the RIS panels, determine the RIS panels to be deployed in the RIS array cluster.

[0014] In some embodiments, based on the uplink reference signal, the environmental quality within a preset communication space is evaluated to obtain a communication environment quality score for the preset communication space, including: Based on the uplink reference signal, the signal strength, signal quality, data transmission speed, and transmission reliability within the preset communication space are calculated respectively. Based on the signal strength, signal quality, data transmission speed, and transmission reliability, the environmental quality within the preset communication space is evaluated to obtain a communication environment quality score Q for the preset communication space. env .

[0015] In a second aspect, embodiments of this application provide a cross-standard wireless signal cooperative optimization system based on an intelligent reflector, the system being used to execute the method described in the first aspect above, the system including a RIS intelligent controller; The RIS intelligent controller is used to detect uplink reference signals sent by user terminals within a preset communication space through a deployed RIS array cluster, wherein the uplink reference signals are sent through any communication operator network. The RIS intelligent controller is used to evaluate the environmental quality inside the preset communication space based on the uplink reference signal, and obtain the communication environment quality score of the preset communication space. The RIS intelligent controller is used to adaptively enable the RIS gain strategy for the user terminal based on the communication environment quality score. The RIS intelligent controller is used to provide cross-standard wireless signal collaborative optimization for the user terminal based on the RIS panels in the RIS array cluster and through the RIS gain strategy.

[0016] Compared to related technologies, this application provides a cross-standard wireless signal collaborative optimization method and system based on intelligent reflectors. The method utilizes a deployed RIS array cluster to detect uplink reference signals transmitted by user terminals within a preset communication space, where the uplink reference signals are transmitted through any communication operator's network. Based on the uplink reference signals, the environmental quality within the preset communication space is evaluated to obtain a communication environment quality score. Based on the communication environment quality score, an adaptive RIS gain strategy is enabled for the user terminal. Based on the RIS panels in the RIS array cluster, cross-standard wireless signal collaborative optimization is provided to the user terminal through the RIS gain strategy. This achieves the use of a general-purpose RIS array cluster to overcome the limitations of single-operator network RIS optimization schemes, completing unified optimization across standards. Furthermore, by providing an adaptive RIS gain strategy for the user terminal based on communication environment quality, it can dynamically adjust according to real-time service requirements and environmental changes, improving resource allocation efficiency and solving the problem of how to optimize the application of RIS technology in indoor wireless communication. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of the steps of the cross-standard wireless signal cooperative optimization method based on a smart reflector according to an embodiment of this application; Figure 2This is a schematic diagram of the RIS optimization process of the liquid neural network model according to an embodiment of this application; Figure 3 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to 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. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0019] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0020] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0021] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0022] This application provides a cross-standard wireless signal cooperative optimization method based on a smart reflector. Figure 1 This is a flowchart illustrating the steps of a cross-standard wireless signal cooperative optimization method based on a smart reflector according to an embodiment of this application, as follows: Figure 1 As shown, the method includes the following steps: Step S102, by deploying a RIS array cluster, the uplink reference signal sent by the user terminal within the preset communication space is detected, wherein the uplink reference signal is sent through any communication operator network; For the deployment of the RIS array cluster in step S102, specifically, with the effective aperture of the RIS panel being equal to half the target wavelength as the target, the array size and cell spacing of the RIS panel are determined by using the equivalent oscillator size calculation formula; based on the array size and cell spacing of the RIS panel, each RIS panel to be deployed in the RIS array cluster is determined.

[0023] Preferably, the logic "array" combination of the RIS panel is based on the smallest millimeter-wave (shortest wavelength) unit to build a reconfigurable multi-band oscillator array and achieves frequency adaptation through electromagnetic coupling.

[0024] Formula for calculating equivalent oscillator size:

[0025] Where, deff For the effective aperture or effective distance, d mmWave N×M represents the aperture or physical size of a single millimeter-wave antenna element, and N×M represents the array size of the RIS panel.

[0026] Among them, K coupling Let be the inter-cell coupling coefficient of the RIS panel, used to correct the performance loss caused by inter-cell mutual coupling effect; α is the amplitude coefficient related to the maximum coupling strength; β is the factor controlling the coupling attenuation rate with spacing; S is the cell spacing of the RIS panel; Λtarget is the target operating wavelength; and the objective function is:

[0027] Constraints: N min ≤N≤N max M min ≤M≤M max K coupling ∈[K min ,K max ] To achieve the best radiation effect, the effective aperture d should be... eff As close as possible to the target wavelength λ target Half of the objective function (i.e., the above objective function). By selecting appropriate array sizes (N, M) and cell pitch (S), the effective aperture of the entire RIS array is precisely tuned to meet both performance specifications and engineering manufacturing constraints.

[0028] Step S104: Based on the uplink reference signal, evaluate the environmental quality inside the preset communication space to obtain the communication environment quality score of the preset communication space. Specifically, step S104 involves calculating the signal strength, signal quality, data transmission speed, and transmission reliability within a preset communication space based on the uplink reference signal; and evaluating the environmental quality within the preset communication space based on the signal strength, signal quality, data transmission speed, and transmission reliability to obtain a communication environment quality score Q for the preset communication space. env .

[0029] Preferably, in step S104, an environmental quality comprehensive evaluation system is established, and the current network performance of the user terminal (UE) is classified as excellent, medium, or poor based on the initial wireless environment, so as to realize the intelligent start-stop decision of RIS technology.

[0030] Among them, w n RSRP represents the weighting coefficient, reflecting the importance of each indicator; normSINR represents the normalized reference signal received power. norm This represents the ratio of normalized signal to interference plus noise; Throughput norm 1 represents normalized throughput; BLER represents block error rate; 1-BLER represents transmission reliability.

[0031] By normalizing and weighting the four key wireless network performance metrics—Signal Strength Responsibility (RSRP), Signal Quality Indicator (SINR), Throughput, and BLER—a single, comparable environmental quality score, Q, is obtained. env .

[0032] Step S106: Based on the communication environment quality score, adaptively enable the RIS gain strategy for the user terminal. Step S106 determines whether the RIS array cluster is enabled for the user terminal based on the communication environment quality score, specifically including the following steps: Step S1061: If the communication environment quality score is greater than or equal to the first score threshold, it means that the communication environment quality inside the preset communication space is good, and the RIS gain strategy is not enabled to save energy, reduce system complexity and signal processing overhead. Step S1062: If the communication environment quality score is less than the second score threshold, it indicates that the communication environment quality inside the preset communication space is poor, and the RIS gain strategy is enabled to reconstruct the communication link. Step S1063: If the communication environment quality score is less than the first score threshold and greater than or equal to the second score threshold, then the RIS gain strategy is adaptively enabled for the user terminal.

[0033] Step S106 Preferably, the RIS enables the decision function:

[0034] When Q env ≥θ high When the wireless environment has good signal and channel quality, there is no need for RIS technology to provide additional gain. Disabling RIS at this time can save energy, reduce system complexity, and lower signal processing overhead. When Q env <θ low When the wireless environment has poor signal quality, RIS technology needs to be enabled to reconstruct the channel and establish or maintain a basic communication link.

[0035] When θ low ≤Q env <θ high When the wireless signal quality is in an intermediate state, an optimization strategy is needed to determine whether to enable RIS. This can be achieved through the decision function f(Q) mentioned above.env The `Traffic_Type` and `User_Priority` parameters are used to comprehensively consider various factors. For example, different service type requirements (eMBB services prioritize high speed, uRLLC services prioritize high reliability and low latency, mMTC services prioritize massive connections, etc.) correspond to different RIS (Reliability, Service, and Response) optimization goals. Furthermore, for user priorities (such as VIP users or emergency communications), high-priority users should be prioritized.

[0036] Specifically, in step S1063 above, the adaptive activation of the RIS gain strategy for the user terminal is determined based on the communication service requirements of the user terminal, and the target RIS panel corresponding to the communication service requirements is activated. The communication service requirements include enhanced mobile broadband (eMBB), ultra-reliable and low-latency communication (uRLLC), and massive machine-type communications (mMTC).

[0037] The preferred strategy for determining the target RIS gain based on the communication service requirements of user terminals is as follows: The communication service flow characteristics of user terminals are analyzed to identify the communication service requirements of user terminals in real time. Through the service QoS feature library, the communication service requirements are mapped to the corresponding wireless channel KPI requirement vector. Based on the wireless channel KPI requirement vector, a corresponding target RIS gain strategy is created for user terminals with the goal of maximizing the service satisfaction of the RIS array cluster.

[0038] It's important to note that a RIS control architecture is constructed that is decoupled from both the operator and the service type. By introducing a service-level QoS mapping feature library and cross-domain dynamic resource slicing technology, the RIS can identify the service types running on different terminals and provide them with tailored signal optimization services, ultimately achieving a paradigm shift from "connectivity" to "experience." Specifically: a) Service QoS Feature Library and Mapping Model Establish a standardized service QoS feature library. This library maps various services to corresponding key radio channel KPI requirements and defines them as service profile tuples B. profile :

[0039] in: Business ID_bThe business identifier (e.g., "augmented reality navigation", "4K video stream", "industrial sensor data") represents the key performance indicators (e.g., latency, throughput, SINR, reliability, coverage strength, etc.); the target value (e.g., latency <10ms); and the tolerance (e.g., allowable jitter of ±2ms).

[0040] b) Correlation between service flow identification and QoS requirements Analyze business flow characteristics to identify the type of business B that is running on user terminal u in real time. u(t) According to B u(t) From B profile Extract the corresponding KPI demand vector Q from the feature library. u(t) c) Cross-domain dynamic resource slicing algorithm The optimization objective is defined as maximizing the overall "business satisfaction" of the system, rather than the satisfaction of individual users, thereby achieving the goal of intelligent and coordinated optimization for all users of the entire system. Maximize: U total = Σ {u} Satisfaction u (KPI) u(t) | B profile_u ) Among them: U_ total Indicates overall satisfaction; Σ {u} This represents the sum of the service satisfaction scores for all terminals u in the system; Satisfaction u Indicates for B profile_u Each KPI (such as latency and throughput) defined in the code is converted into a sub-satisfaction score between 0 and 1 based on its target value and tolerance through a predefined monotonic nonlinear mapping function.

[0041] Panel resource constraints:

[0042] For a specific business slice b, the occupancy status n of all K panels is recorded. {b,k} In total, the number of RIS panels occupied by business slice b is n. {b,k} The variable value is 0 or 1, with 1 being the panel occupancy value and 0 otherwise; this prevents a single service from monopolizing all RIS panels, ensuring the fairness and availability of system resources.

[0043] Frequency band resource constraints: f k ∈F available Each RIS panel k operates at a frequency band f. k It must be from the set of frequency bands F supported by the panel hardware. available Select F available It depends on the N, M, S and other parameters determined during the deployment of the RIS array cluster mentioned above.

[0044] RIS panel phase offset constraint:

[0045] In this context, the phase offset of each cell l on each RIS panel k is... It can be continuously adjusted within the range of 0 to 2π.

[0046] According to Q of all online businesses u(t) The collection uses this cross-domain dynamic resource slicing algorithm to divide the RIS resource pool into multiple logical slices. b Each Slice b It serves a set of services with similar QoS requirements. Specifically, for latency-sensitive services: RIS panels capable of forming strong direct paths or the shortest reflection paths are allocated to actively compensate for signal propagation delay through beamforming; for bandwidth-sensitive services: RIS panels supporting wide bandwidth and high gain are allocated to form wide beams or multiple beams simultaneously to maximize throughput; for coverage-sensitive services: RIS panels capable of providing the widest coverage are allocated to compensate for signal blind spots.

[0047] d) Configuration, execution, and coordination Instruction generation: The scheduler outputs the final RIS configuration instructions. Among them, phase configuration The optimization goal of the RIS generation process is no longer solely SINR, but rather service-specific KPIs (such as latency or reliability). Cross-domain service collaboration: To deliver service-level QoS guarantees, the scheduler uses a standardized northbound interface to notify each operator's core network of the service capability status of its service slices (e.g., "The slice allocated to your autonomous driving service is ready, with a theoretical channel latency of less than 10ms"). Upon receiving this information, each operator's core network can perform collaborative radio resource block scheduling and routing within its own network domain, thereby coordinating with the RIS's service capabilities to jointly achieve end-to-end QoS guarantees. During this process, operators do not directly interfere with the RIS's physical resource configuration; the scheduler maintains absolute control over the RIS resources.

[0048] The preferred target RIS panel for activating and meeting communication service requirements is: Activate the target RIS panel in the RIS array cluster that corresponds to the communication service requirements. For the activated target RIS panel in the RIS array cluster, call the trained liquid neural network model to calculate the optimal phase configuration. Drive the target RIS panel to form a dynamic beam through the optimal phase configuration. The dynamic beam points to the user terminal and performs motion tracking.

[0049] It should be noted that this study aims to address the real-time, accurate beamforming and user tracking challenges of RIS technology in dynamic environments. Traditional optimized beamforming methods suffer from high computational overhead and response latency in complex and rapidly changing wireless environments (such as user movement and obstacle obstruction), making it difficult to achieve optimal performance. Therefore, a Liquid Neural Networks (LNN) algorithm is introduced. Leveraging its continuous-time dynamic characteristics and superior time-series data processing capabilities, the RIS controller can, like a "biological neural network," instantaneously and adaptively calculate the optimal RIS configuration state based on the terminal's uplink channel state information (such as SRS) and the characteristics of its surrounding environment. This enables dynamic beamforming and stable signal tracking, maximizing the user's signal quality. The LNN algorithm model includes two stages: offline training, online inference, and fine-tuning. Figure 2 This is a schematic diagram of the RIS optimization process of the liquid neural network model according to an embodiment of this application, as shown below. Figure 2 As shown, specifically: 1) Input layer The input to the algorithm model is a feature vector x(t) that integrates real-time channel information and prior environmental knowledge, defined as follows:

[0050] in, Let M×N be a complex matrix, representing the uplink channel matrix extracted from the uplink sounding reference signal of the user terminal (UE) at time t, where M and N are the number of receive and transmit antennas, respectively; vec() represents... Vectorized function; P env L(t) represents the one-hot encoding derived from the environmental quality score Qenv, used to identify the area quality where the UE is currently located. [1,0,0] represents the "excellent" area, [0,1,0] represents the "medium" area, and [0,0,1] represents the "poor" area. L(t) represents the two-dimensional coordinate vector of the UE obtained at time t through positioning technology (such as GPS or fingerprint positioning).

[0051] 2) Liquid Neural Network (LNN) Processing Layer LNNs describe the continuous-time evolution of their hidden state s(t) using the following ordinary differential equation (ODE):

[0052] ds(t) represents the hidden state of the LNN at time t (D is the dimension of the hidden layer); -s(t) is a decay term that drives the system state back to zero, ensuring that the system remains stable when there is no external input, reflecting the characteristics of short-term memory, where recent information has a greater impact; ds(t) / dt represents the derivative of the hidden state s(t) with respect to time, i.e., the instantaneous rate of change of the state; T represents the time constant that controls the dynamic response speed of the network. The smaller the value, the better it adapts to rapidly changing channels. The larger the value, the smoother the state transition; W represents the trainable network weight matrix, connecting the input and hidden states; B represents the trainable bias vector; f() represents the non-linear activation function; [x(t); s(t)] represents concatenating the input vector x(t) with the hidden state s(t) from the previous time step.

[0053] 3) Output layer and RIS state mapping The network's output layer performs a linear transformation on the final hidden state to generate the RIS control instruction y(t):

[0054] in, This represents the output vector. n∈{0, 1} K This represents a binary mask indicating which RIS panels in the distributed RIS network should be activated (K is the total number of panels). It corresponds to the adaptive activation of the target RIS panel mentioned above. 1 indicates that the panel is enabled, and 0 indicates that the panel is disabled. denoted as the phase offset matrix for configuring the L cells of each activated RIS panel; f represents the frequency band selected for each activated RIS panel, which is a frequency band selection vector corresponding to the deployment method of the RIS array cluster; G represents the output weight matrix that maps the hidden state to specific control commands.

[0055] 4) Training process Based on gradient descent, parameter optimization and convergence are achieved by learning and training the optimal parameter set θ = {W, b, G}.

[0056] Create a loss function:

[0057] Wherein, the expected value E[SINR] {down} ] represents the average performance of the user's downlink signal, regularization term Prevent overfitting.

[0058] Calculate the gradient of the above loss function with respect to θ. And update the parameters: Where η is the learning rate, controlling the update step size; the training process is iterative until the loss function is reached. When the change is less than a preset threshold or the maximum number of iterations is reached, it indicates that the model has converged to a stable state. At this point, the parameters... It is fixed for use in online inference.

[0059] 5) Online reasoning and fine-tuning After the model training converges, the trained LNN model is used to calculate the RIS configuration y(t) based on the real-time input x(t), thus achieving dynamic beamforming. Furthermore, to avoid performance drift, the system can periodically perform incremental training using new performance data (such as SINR below), fine-tuning and updating parameters online through small-step gradient descent to achieve continuous adaptation.

[0060] Step S108: Based on the RIS panel in the RIS array cluster, provide cross-standard wireless signal collaborative optimization for user terminals through RIS gain strategy.

[0061] Specifically, in step S108, when the target RIS panel activated in the RIS array cluster continuously points to the user terminal, cross-standard wireless signal collaborative optimization is provided to the user terminal through the target RIS gain strategy.

[0062] Through the methods and steps described in this application embodiment, the traditional model of RIS technology serving only a single operator for optimizing wireless signals is broken. The RIS equipment is owned by the owner and is responsible for optimizing the wireless network signals for all needs in the building space, thus breaking away from the relatively closed optimization model initiated by terminals and operators. Traditional models often enhance coverage by adding signal sources or antennas, which is not only costly but also requires terminals to transmit reference signals back to the core network, resulting in long links, low efficiency, and a lack of flexibility and specificity. In the era of the upcoming 6G, with increasingly complex indoor wireless signals and the Internet of Things and intelligent interconnection, if each type, standard, and frequency band terminal requires its own network operator or terminal manufacturer to provide optimization services, it will inevitably waste a lot of resources. Therefore, there is a great need for a co-construction and sharing mechanism for network optimization from a third-party perspective, similar to power supply and optical cables. The proposed invention localizes, improves efficiency, and shares optimization strategies; it aligns with the vision of greener, more energy-efficient, and more efficient; moreover, this optimization approach can be extended from indoors to outdoors, and even to a space-air-ground integrated system, contributing to achieving better seamless 6G coverage.

[0063] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0064] This application provides a cross-standard wireless signal collaborative optimization system based on intelligent reflectors. The system adopts an architecture of "centralized RIS intelligent controller + distributed RIS panel nodes". The RIS intelligent controller is deployed inside the building and is responsible for integrating the execution of all innovative algorithms in the above-mentioned method embodiments. The RIS panel nodes are pre-deployed during the building renovation stage (specific deployment locations include corner areas, partition areas, or areas with obstructions). It should be noted that each user terminal accessing the service needs to register on the RIS intelligent controller first, providing the following information: operating frequency band requirements, communication standard type, expected RSRP value range, and service type preference (optional). The RIS intelligent controller is used to detect uplink reference signals sent by user terminals within a preset communication space through a deployed RIS array cluster, wherein the uplink reference signals are sent through any communication operator's network. The RIS intelligent controller is used to evaluate the environmental quality within a preset communication space based on the uplink reference signal, and obtain the communication environment quality score of the preset communication space. The RIS intelligent controller is used to adaptively enable RIS gain strategies for user terminals based on the communication environment quality score. The RIS intelligent controller is used to provide cross-standard wireless signal collaborative optimization for user terminals based on the RIS panels in the RIS array cluster and through RIS gain strategies.

[0065] The system provided in this application consists of a controller and several RIS remote terminals. RIS technology utilizes the energy of wireless signals in the environment to power its own sensors, thereby achieving self-powered environmental sensing. Specifically, during the house renovation phase, RIS remote terminals can be pre-deployed in corner areas, partitioned areas, or areas with obstructions. Each terminal entering the house first registers with the controller, specifying its operating frequency band, network standard, and required RSRP value range. Then, it enters the RIS network optimization area. Regardless of whether it moves, the RIS will track the registered terminal and accurately provide network optimization services.

[0066] The specific embodiments of this application combine the above-described methods and systems to specify the application scenario of this application in the context of a smart medical center, in which multiple network standards such as 6G, 5G, Wi-Fi, and IoT are deployed.

[0067] Building structure: 3-story medical center, including operating rooms (electromagnetic shielding), wards (high-density terminals), corridors (mobility needs), and pharmacy (dense IoT devices).

[0068] Wireless network requirements can be divided into two categories: medical work and external user behavior requirements. Medical work requirements include not only URLLC services requiring ultra-low latency, such as telemedicine in the operating room, but also high-bandwidth high-definition image transmission requirements, such as online academic seminars and exchanges, as well as high reliability requirements, such as real-time monitoring of medical equipment; external user behavior can mostly include a variety of needs such as voice, video, and gaming.

[0069] Table 1 is an example of a wireless network in a smart medical center scenario. The initial coverage of the wireless network can be described in Table 1 below. Different network standards will have their own coverage methods. Due to objective factors such as room partitions, ceilings, equipment, and human beings, the initial wireless network is passive, non-uniform, and inefficient.

[0070] Table 1

[0071] Step 1: The terminal enters the medical center and registers its identity, operating frequency band, and QoS requirements on the unified controller of the RIS technology system. When the terminal begins communication, the distributed multi-band RIS panel detects its uplink reference signal; Step 2: The RIS intelligent controller calculates the comprehensive environmental quality score Q based on indicators such as RSRP and SINR from the terminal. env The internal space of the medical center is dynamically divided into three quality levels: "excellent," "medium," and "poor."

[0072] Step 3: Then, through the service awareness engine, identify the type of service initiated by the terminal (e.g., operating room A initiates 4K live broadcast - eMBB service; vital signs monitor B initiates data reporting - mMTC service); the RIS intelligent controller retrieves the corresponding B from the QoS feature library according to the service type. profile Furthermore, separate resource slices are created for this business. For example, a RIS panel supporting high frequency bands and high gain is allocated for 4K live streaming; and a RIS panel that can provide the most stable link is allocated for vital sign monitoring.

[0073] Step 4: For each activated RIS technology resource slice, the controller invokes a Liquid Neural Network (LNN). The LNN takes real-time channel state, terminal location, and environmental region labels as input to calculate the optimal phase configuration. The panel activation state n and the working frequency band f drive the RIS to form a dynamic beam, accurately pointing to the target terminal and realizing motion tracking. Step 5: When Q in a certain region envWhen the status remains "excellent," the scheduler executes intelligent start-stop decisions, placing the RIS technology panel in that area into sleep or low-power monitoring mode to save energy. When the terminal service ends or the user leaves, the RIS technology resources it occupied are released and returned to the resource pool, where they are redistributed by the RIS intelligent controller, thereby achieving optimal global satisfaction for the entire system.

[0074] This embodiment provides an electronic device including a memory and a processor. The memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0075] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0076] Optionally, the electronic device may further include a processor, memory, network interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a cross-standard wireless signal cooperative optimization method based on a smart reflector. The display screen may be a liquid crystal display (LCD) or an e-ink display. The input device may be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0077] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0078] Furthermore, in conjunction with the cross-standard wireless signal cooperative optimization method based on intelligent reflectors in the above embodiments, this application embodiment can provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any of the cross-standard wireless signal cooperative optimization methods based on intelligent reflectors in the above embodiments.

[0079] In one embodiment, Figure 3 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application, such as... Figure 3 As shown, an electronic device is provided, which can be a server, and its internal structure diagram can be as follows. Figure 3As shown, the electronic device includes a processor, a network interface, internal memory, and non-volatile memory connected via an internal bus. The non-volatile memory stores the operating system, computer programs, and a database. The processor provides computing and control capabilities, the network interface communicates with external terminals via a network, the internal memory provides an environment for the operating system and computer programs to run, the computer programs are executed by the processor to implement a cross-standard wireless signal cooperative optimization method based on a smart reflector, and the database stores data.

[0080] Those skilled in the art will understand that Figure 3 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 electronic device to which the present application is applied. A specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0081] 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. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0082] Those skilled in the art should understand that 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 have been 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 specification.

[0083] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. 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 patent application should be determined by the appended claims.

Claims

1. A cross-standard wireless signal cooperative optimization method based on a smart reflector, characterized in that, The method includes: The uplink reference signal sent by a user terminal within a preset communication space is detected by a deployed RIS array cluster, wherein the uplink reference signal is transmitted through any communication operator network. Based on the uplink reference signal, the environmental quality within the preset communication space is evaluated to obtain a communication environment quality score for the preset communication space. Based on the communication environment quality score, determine whether to enable the RIS array cluster for the user terminal: If the communication environment quality score is greater than or equal to the first score threshold, it indicates that the communication environment quality within the preset communication space is good, and the RIS gain strategy is not enabled to save energy, reduce system complexity and signal processing overhead. If the communication environment quality score is less than the second score threshold, it indicates that the communication environment quality within the preset communication space is poor, and the RIS gain strategy is activated to reconstruct the communication link. If the communication environment quality score is less than the first score threshold and greater than or equal to the second score threshold, then the RIS gain strategy is adaptively enabled for the user terminal. The adaptive activation of the RIS gain strategy for the user terminal includes: analyzing the communication service flow characteristics of the user terminal to identify the communication service requirements of the user terminal in real time; mapping the communication service requirements to corresponding wireless channel KPI requirement vectors through a service QoS feature library; creating a corresponding target RIS gain strategy for the user terminal based on the wireless channel KPI requirement vectors, with the goal of maximizing the service satisfaction of the RIS array cluster; and activating the target RIS panel corresponding to the communication service requirements, wherein the communication service requirements include enhanced mobile broadband (eMBB) service requirements, ultra-reliable low-latency communication (uRLLC) service requirements, and massive machine-type communication (mMTC) service requirements. Based on the RIS panel in the RIS array cluster, the user terminal is provided with cross-standard wireless signal collaborative optimization through the RIS gain strategy.

2. The method according to claim 1, characterized in that, Activating the target RIS panel corresponding to the aforementioned communication service requirements includes: Activate the target RIS panel in the RIS array cluster corresponding to the communication service requirement, and drive the target RIS panel to point at the user terminal for motion tracking.

3. The method according to claim 2, characterized in that, Driving the target RIS panel to point at the user terminal for motion tracking includes: For the activated target RIS panel in the RIS array cluster, the trained liquid neural network model is invoked to calculate the optimal phase configuration; The target RIS panel is driven to form a dynamic beam through the optimal phase configuration, and the dynamic beam is pointed at the user terminal for motion tracking.

4. The method according to claim 2, characterized in that, Based on the RIS panel in the RIS array cluster, the cross-standard wireless signal cooperative optimization for the user terminal through the RIS gain strategy includes: When the target RIS panel activated in the RIS array cluster continuously points to the user terminal, the target RIS gain strategy provides cross-standard wireless signal cooperative optimization for the user terminal.

5. The method according to claim 4, characterized in that, The method includes: With the effective aperture of the RIS panel being equal to half the target wavelength as the objective, the array size and cell spacing of the RIS panel are determined by using the equivalent oscillator size calculation formula. Based on the array size and cell spacing of the RIS panels, determine the RIS panels to be deployed in the RIS array cluster.

6. The method according to claim 1, characterized in that, Based on the uplink reference signal, the environmental quality within the preset communication space is evaluated to obtain a communication environment quality score for the preset communication space, including: Based on the uplink reference signal, the signal strength, signal quality, data transmission speed, and transmission reliability within the preset communication space are calculated respectively. Based on the signal strength, signal quality, data transmission speed and transmission reliability, the environment quality inside the preset communication space is evaluated to obtain a communication environment quality score Q of the preset communication space env .

7. A cross-standard wireless signal cooperative optimization system based on an intelligent reflector, characterized in that, The system is used to perform the method according to any one of claims 1 to 6, the system comprising a RIS intelligent controller; The RIS intelligent controller is used to detect uplink reference signals sent by user terminals within a preset communication space through a deployed RIS array cluster, wherein the uplink reference signals are sent through any communication operator network. The RIS intelligent controller is used to evaluate the environmental quality inside the preset communication space based on the uplink reference signal, and obtain the communication environment quality score of the preset communication space. The RIS intelligent controller is used to adaptively enable the RIS gain strategy for the user terminal based on the communication environment quality score. The RIS intelligent controller is used to provide cross-standard wireless signal collaborative optimization for the user terminal based on the RIS panels in the RIS array cluster and through the RIS gain strategy.

Images