Control method and system of intelligent metasurface device

Abstract

The embodiment of the invention provides a control method and system for intelligent metasurface equipment. The method comprises the following steps: receiving an electromagnetic signal sent by a target terminal in an uplink frequency band; converting the electromagnetic signal into a digital signal; sampling the digital signal in a preset time period to generate a characteristic signal vector; according to a matching result of the feature signal vector and a pre-constructed feature library, a control strategy for the metasurface device is generated, and the feature library comprises a plurality of signal vector templates obtained through division and collection based on a plurality of communication dimensions in a scene having use requirements for the intelligent metasurface device; and according to the control strategy, enabling or shutting down a signal regulation and control function of the intelligent metasurface equipment. According to the method, the electromagnetic wave signal in the uplink frequency band is analyzed in real time, so that the network requirement can be intelligently sensed, and the starting and closing states of equipment functions are automatically adjusted.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent metasurfaces, and in particular relates to a control method and system for intelligent metasurface equipment. Background Art

[0002] Reconfigurable Intelligent Surfaces (RIS) are widely used to improve network coverage and user experience due to their controllable and low-power characteristics. However, large-scale deployment and activation of RIS can lead to increased interference and wasted energy, especially when used in areas with no demand.

[0003] The solutions currently proposed generally rely on fixed-time control or remote instructions, which have poor flexibility and make it difficult to respond to user needs in a timely manner.

[0004] Therefore, how to achieve flexible and accurate control of RIS equipment has become a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The embodiments of the present invention provide a control method and system for an intelligent metasurface device, which can accurately and flexibly control the activation of the intelligent metasurface device.

[0006] In a first aspect, an embodiment of the present invention provides a method for controlling an intelligent metasurface device, the method comprising:

[0007] Receive electromagnetic signals in the uplink frequency band;

[0008] Convert electromagnetic signals into digital signals;

[0009] Sampling a digital signal within a preset time period to generate a characteristic signal vector;

[0010] Generate a control strategy for the smart metasurface device based on the matching results of the characteristic signal vector and a pre-built feature library. The feature library includes multiple signal vector templates divided and collected based on multiple communication dimensions in scenarios where the smart metasurface device is needed;

[0011] According to the control strategy, the signal control function of the intelligent metasurface device is enabled or disabled.

[0012] In a second aspect, an embodiment of the present invention provides a control device for an intelligent metasurface device, the device comprising:

[0013] a sensing unit, configured to receive electromagnetic signals in an uplink frequency band, convert the electromagnetic signals into digital signals, and sample the digital signals within a preset time period to generate a characteristic signal vector;

[0014] A controller is used to generate a control strategy for the intelligent metasurface device based on the matching results of the characteristic signal vector and a pre-built feature library, where the feature library includes multiple signal vector templates divided and collected based on multiple communication dimensions in scenarios where there is a demand for the use of the intelligent metasurface device; and is used to enable or disable the signal regulation function of the intelligent metasurface device according to the control strategy.

[0015] In a third aspect, an embodiment of the present application provides an intelligent metasurface device, including a sensing unit, a controller, and a service unit;

[0016] a sensing unit, configured to receive electromagnetic signals in an uplink frequency band, convert the electromagnetic signals into digital signals, and sample the digital signals within a preset time period to generate characteristic signal vectors, and send the characteristic signal vectors to a controller;

[0017] A controller for generating a control strategy for the intelligent metasurface device based on the matching results of the characteristic signal vector with a pre-built feature library, the feature library including multiple signal vector templates divided and collected based on multiple communication dimensions in scenarios where the intelligent metasurface device is required to be used; and for enabling or disabling the signal regulation function of the business unit in the intelligent metasurface device according to the control strategy;

[0018] Business unit, used to perform signal control functions.

[0019] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement any one of the methods in the above-mentioned first aspect.

[0020] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, which implement any one of the methods in the first aspect above when the computer program instructions are executed by a processor.

[0021] In a sixth aspect, an embodiment of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements any one of the methods in the first aspect above.

[0022] The control method for an intelligent metasurface device proposed in the present application embodiment achieves dynamic perception and precise control of the state of the intelligent metasurface device by introducing a characteristic signal recognition and template matching mechanism, significantly optimizing the start-stop strategy and energy efficiency management of its signal control function. Specifically, this solution receives electromagnetic signals in the uplink frequency band and sequentially performs current-voltage conversion and analog-to-digital conversion on the signals to obtain a processable digital signal. This digital signal is continuously sampled within a preset time period to generate a characteristic signal vector reflecting the terminal communication state. This characteristic signal vector is matched with signal templates collected under multiple typical communication scenarios in a pre-built feature library. Based on the matching results, it is determined whether there is actual user terminal demand for the RIS device, and a corresponding control strategy is adaptively generated. The signal control function of the intelligent metasurface device is started and stopped accordingly. This mechanism effectively compensates for the problem that traditional RIS devices cannot actively perceive terminal needs and have rigid control function start-stop strategies. It enables RIS to accurately intervene in scenarios with communication value, avoids ineffective energy consumption, and improves the overall communication perception capability, response efficiency, and resource utilization of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0024] Figure 1 1 is a flow chart of a control method for an intelligent metasurface device provided by an embodiment of the present invention;

[0025] Figure 2 1 is a flow chart of a control method for an intelligent metasurface device provided by an embodiment of the present invention;

[0026] Figure 3 1 is a schematic structural diagram of a control system of an intelligent metasurface device provided by an embodiment of the present invention;

[0027] Figure 4 1 is a schematic structural diagram of an intelligent metasurface device provided by an embodiment of the present invention;

[0028] Figure 5 This is a schematic structural diagram of a sensing unit provided by an embodiment of the present invention;

[0029] Figure 6 is a schematic structural diagram of a controller provided by an embodiment of the present invention;

[0030] Figure 7 1 is a schematic structural diagram of a high-pass filter circuit provided by an embodiment of the present invention;

[0031] Figure 8 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. In order to make the objects, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can be implemented without the need for some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.

[0033] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0034] With the continuous evolution of wireless communication technology, reconfiguring the propagation environment has become a key approach to improving network performance. Reconfigurable Intelligent Surface (RIS), a new technology, enables fine-grained control of electromagnetic wave propagation at the physical layer, dynamically adjusting its reflection, refraction, and other characteristics to enhance signal coverage and quality. RIS devices, due to their low cost, low energy consumption, and flexible deployment, have been widely used to enhance signal coverage and improve the communication experience for users in obstructed areas. They can effectively address blind spots in networks that are difficult for traditional base stations to cover, improving the perception of edge users.

[0035] However, as mentioned in the background section, the deployment of RIS also increases network complexity. If improperly deployed and scheduled, the signals reflected by RIS may become a source of interference in non-target areas, affecting the overall stability of the network. In addition, maintaining the RIS operation when the network load is low or user demand is insufficient can also result in unnecessary energy waste.

[0036] Therefore, in the process of promoting and applying RIS technology, we should consider how to achieve flexible and precise control and intelligent scheduling of RIS equipment so that it can play a role in the time and space areas where it is really needed, avoiding interference with non-target areas and waste of resources.

[0037] Existing technologies typically use preset time policies to control the activation and deactivation of RIS devices. This policy essentially turns devices on and off within fixed time periods, failing to dynamically adjust based on actual network load or user distribution. This static control approach lacks flexibility and is difficult to adapt to rapidly changing communication needs. Especially during periods when devices are off, this can lead to decreased communication quality for users within the coverage area, impacting overall service perception.

[0038] To address this technical problem, an embodiment of the present invention provides a control method and system for an intelligent metasurface device. By real-time analysis of electromagnetic wave signals in the uplink frequency band, intelligently sensing network requirements, and automatically adjusting the enabled and disabled states of the device's signal control function, the system's flexibility is effectively improved, the impact of fixed-time control is avoided, and the user experience is significantly enhanced.

[0039] The following first introduces the control method of the intelligent metasurface device provided by the embodiment of the present invention.

[0040] Figure 1 A flow chart of a control method for an intelligent metasurface device provided by an embodiment of the present invention is shown.

[0041] It should be noted that the control method of the intelligent metasurface device given in this embodiment is applied to the control system of the intelligent metasurface device, and its system structure will be described later.

[0042] like Figure 1 As shown, the method may include the following steps.

[0043] S110: Receive an electromagnetic signal in an uplink frequency band.

[0044] In this step, the intelligent metasurface device receives electromagnetic signals in the uplink frequency band in real time.

[0045] The uplink frequency band refers to the frequency band used to send signals from the user terminal to the network side (such as relay equipment or base stations).

[0046] For example, the uplink frequency band may be an uplink frequency band in a frequency division duplex (FDD) network supported by the smart metasurface panel design.

[0047] FDD is a duplex technology used in wireless communication systems. FDD networks achieve two-way communication without interference by allocating uplink and downlink signals to different frequency bands.

[0048] In this example, the RIS panel is configured to support the uplink frequency band in an FDD network, which is the frequency band for signals sent from user terminals to the network side (such as base stations). This frequency band design allows the RIS equipment to focus on processing and enhancing the data streams uploaded by users, thereby optimizing communication in a specific direction.

[0049] Electromagnetic signals refer to analog wireless signals sent by user terminals in the uplink frequency band. In essence, they are continuous-time signals propagating in space in the form of electromagnetic waves, containing the user's communication content and channel status information.

[0050] The purpose of receiving uplink frequency signals is to understand the communication status and network requirements of user terminals in real time, especially to provide key information when analyzing user signal strength, quality, and demand changes.

[0051] S120. Convert the electromagnetic signal into a digital signal.

[0052] In this step, the intelligent metasurface device processes the received uplink frequency band electromagnetic signal and converts it into a digital signal that can be used for subsequent digital analysis and processing.

[0053] Digital signals are signals expressed in discrete time and amplitude forms that can be recognized and processed by computing devices such as digital signal processors or embedded systems.

[0054] Since electromagnetic signals are essentially analog signals, and the control modules of intelligent metasurface systems usually rely on digital signals for judgment, calculation, and regulation, it is necessary to digitize the received analog signals through analog-to-digital conversion (ADC).

[0055] In one implementation, step S120 may include the following steps.

[0056] S121. Generate a corresponding current signal according to the electromagnetic signal.

[0057] Exemplarily, the principle of electromagnetic induction is used to convert the received electromagnetic signal into a continuously changing current signal.

[0058] It should be understood that step S122 can be performed using a sensing unit in the control system of the intelligent metasurface device, that is, using the sensing unit to convert the voltage signal into a digital signal.

[0059] S122. Convert the current signal into a voltage signal.

[0060] Exemplarily, the current signal is processed by hardware components such as a load resistor and a current-to-voltage conversion circuit (such as a transimpedance amplifier) ​​and converted into a corresponding voltage signal.

[0061] It should be understood that step S122 can be performed using a preset resistor in the control system of the smart metasurface device, that is, using the preset resistor to convert the current signal into a voltage signal.

[0062] S123. Convert the voltage signal into a digital signal.

[0063] Exemplarily, the voltage signal is sampled and quantized by an analog-to-digital converter, thereby converting the continuous analog signal into a discrete digital signal.

[0064] It should be understood that step S122 can be performed using an analog-to-digital converter in the control system of the intelligent metasurface device, that is, using the analog-to-digital converter to convert the voltage signal into a digital signal.

[0065] For example, after the sensing unit receives the electromagnetic signal in the uplink frequency band, the current signal generated is I t , the voltage signal obtained by the preset resistor conversion is V t =I t *r t After the voltage passes through the analog-to-digital converter, the digital output value is Output t It can be expressed as:

[0066] Output t =V t / V ref *2 n ; (1)

[0067] Among them, V t is the input voltage, V ref is the reference voltage, and n is the number of bits of resolution of the analog-to-digital converter.

[0068] Through the above-mentioned multi-level conversion process, the intelligent metasurface system can realize the complete link from receiving electromagnetic waves to obtaining processable digital data, providing basic support for subsequent intelligent decision-making and dynamic configuration.

[0069] The current signal is subject to various interferences during acquisition and transmission. Interference signals can cause fluctuations or glitches in the current signal, affecting the analysis and processing of the true current signal. Therefore, in one embodiment, before converting the current signal to a voltage signal, the method further includes performing inductive filtering and / or capacitive filtering on the current signal. This filtering removes interference components and extracts the desired pure current signal.

[0070] S130: Sampling the digital signal within a preset time period to generate a characteristic signal vector.

[0071] The preset time period refers to a fixed time length that is pre-set for sampling and feature extraction during the signal processing process.

[0072] Exemplarily, the time period can be set to 3 to 6 seconds, and the sampling frequency is 100 Hz. The purpose of setting this time period is to ensure that the system can still obtain representative data in scenarios where signal conditions are weak or intermittent. For example, in a typical business scenario, when a user attempts to initiate a voice call but is not connected due to network congestion or signal attenuation, the entire process from the user starting to dial, the network responding to the prompt tone (such as a busy tone), to the user terminating the operation, is usually between 3 and 6 seconds. Therefore, setting this time period can cover the shortest communication attempt time in this type of business, ensuring the effectiveness of signal sampling and business relevance.

[0073] In each preset time period, the system periodically samples the input digital signal at a fixed sampling frequency, forming a characteristic signal vector containing k sampling points in each time period.

[0074] A characteristic signal vector refers to a numerical sequence constructed by continuously sampling a digital signal within a single preset time period, which is used to characterize the overall change trend and instantaneous characteristics of the signal within that period.

[0075] For example, if the sampling frequency is set to 100 Hz and the preset time period is 3 seconds, 300 sampling points can be obtained in each analysis period, that is, the corresponding characteristic signal vector length is k=300.

[0076] The characteristic signal vector can be written as:

[0077] Output=[output1,output2,...output k ]; (2)

[0078] Among them, output i Represents the digital signal value corresponding to the i-th sampling moment, and k is the vector length.

[0079] S140: Generate a control strategy for the intelligent metasurface device based on the matching result between the characteristic signal vector and the pre-built characteristic library.

[0080] A feature library refers to a set of feature signal templates pre-built before system deployment or during operation, which is used to characterize the typical signal patterns generated by end users within the perception range of smart metasurface devices in different usage scenarios.

[0081] It should be understood that in one embodiment, the feature library can be divided based on a combination of multiple communication dimensions, and representative digital signal vector samples can be collected from actual or simulated scenarios for matching and identifying with feature signal vectors acquired in real time to determine whether there is an active communication demand in the current scenario.

[0082] Exemplarily, the communication dimensions involved may include but are not limited to the type of service, the distance between the user and the smart metasurface device, the number of simulated users, etc.

[0083] Table 1 shows the communication dimensions and their exemplary division methods in the process of constructing the feature library.

[0084] Business Type distance Number of simulated users Voice calls 10 1 Live Chat 30 5 Web Browsing 60 10 Short video business 90 15 Online Games 120 20 Long video business 150 25 … ... ...

[0085] As can be seen from Table 1:

[0086] The service type dimension may include instant messaging, voice calls, video services (such as short videos and long videos), web browsing, online games, etc. Because different services have significant differences in uplink resource scheduling frequency, data volume, transmission bandwidth requirements, etc., their corresponding digital signal characteristics are also significantly different.

[0087] The distance dimension can be divided according to the effective coverage distance of the RIS device. For example, a denser division can be set in the initial stage (such as increments of every 10 meters), and the division granularity can be gradually relaxed as the distance increases, with the maximum distance not exceeding 250 meters.

[0088] The simulated user number dimension simulates the differences in uplink signal characteristics generated by terminals within the RIS sensing area under different user densities. For example, the number of simulated users can be set from 1 to 25 to construct multiple scenario samples from low density to high density.

[0089] For each dimension combination and its division, collect digital signal samples generated by the user terminal in the corresponding scenario. The number of samples collected for each combination is n, and each sample is a feature signal vector, and its sampling length is set to S×k, where:

[0090] S is a configurable redundancy coefficient used to enhance the stability and generalization ability of the sample, and its value range can be set to [2–10];

[0091] k is the number of sampling points in a single cycle as described in the above step S130.

[0092] The total number of samples in the final feature library can be expressed as:

[0093] M=n*∏H i ; (3)

[0094] Here, Hi represents the number of divisions in each communication dimension, and n is the number of samples collected under each combination.

[0095] In one implementation, a template matching-based recognition method can be used to directly calculate the similarity between the real-time generated feature signal vector and the template vector in the feature library. For example, algorithms such as Euclidean distance, cosine similarity, and dynamic time warping can be used to calculate the degree of match between the two, and a threshold can be set to determine whether a valid recognition is achieved.

[0096] In one implementation, a machine learning-based recognition method can be used to classify and identify signals, and based on this, it can be inferred whether there is a demand for the use of intelligent metasurface devices. For example, a supervised learning model is trained using a pre-built feature library. For example, the M uplink signal vector templates in the pre-built feature library can be marked as positive samples, and combined with M randomly generated negative samples of the same sequence length, a recurrent neural network (RNN), a long short-term memory network (LSTM), or a gated recurrent unit (GRU) and other models are trained to determine whether the input signal is an uplink terminal signal that requires the use of the intelligent metasurface device, thereby realizing intelligent scheduling of the device.

[0097] The above identification method is used to determine whether there is a valid user service request at present, and accordingly generate the corresponding intelligent metasurface device control strategy:

[0098] If the identification result indicates that there is currently active communication behavior or potential usage demand, a corresponding control strategy is generated to trigger the activation of relevant units / modules in the smart metasurface device to achieve the purpose of regulating the incident electromagnetic signal;

[0099] If the current characteristic signal cannot establish a high-matching association with any template in the characteristic library, it means that it may be in a state of low business activity or no demand. Then a corresponding control strategy is generated to trigger the action of relevant units / modules in the dormant intelligent metasurface device, entering a low-power or dormant state to improve energy efficiency.

[0100] S150: Enable or disable the signal control function of the intelligent metasurface device according to the control strategy.

[0101] It should be understood that the signal modulation function refers to the ability of the intelligent metasurface device to modulate, reconstruct, control reflection or transmission of the incident electromagnetic signal.

[0102] To enable or disable this function, you can use the following strategies:

[0103] In one implementation, the signal control function can be enabled or disabled by waking up or putting the entire intelligent metasurface device into hibernation. This approach facilitates unified control, helps reduce power consumption when the device is idle, and improves the overall energy efficiency of the system.

[0104] In one implementation, only the relevant units or modules within a smart metasurface device responsible for signal control can be awakened or put into sleep mode, without affecting the operation of other functional units within the device. This approach offers greater flexibility and resource scheduling efficiency, making it particularly suitable for complex applications where smart metasurface devices have multiple functions and require modular operation and management.

[0105] The control method for the intelligent metasurface device proposed in the embodiment of the present application realizes dynamic perception and fine control of the state of the intelligent metasurface device by introducing a characteristic signal recognition and template matching mechanism, significantly optimizing the start-stop strategy and energy efficiency management of its signal control function. Specifically, this scheme receives the electromagnetic signal sent by the target terminal in the uplink frequency band and performs the current-voltage conversion and analog-to-digital conversion of the signal in sequence to obtain a processable digital signal. The digital signal is continuously sampled within a preset time period to generate a characteristic signal vector reflecting the terminal communication state. The characteristic signal vector is matched with the signal templates collected under multiple typical communication scenarios in a pre-built feature library. Based on the matching results, it is determined whether there is actual use demand of the user terminal for the RIS device, and a corresponding control strategy is adaptively generated. The signal modulation function of the intelligent metasurface device is started and stopped according to the strategy. This mechanism effectively compensates for the problem that traditional RIS devices cannot actively perceive terminal needs and have rigid function start-stop strategies. It enables RIS to accurately intervene in scenarios with communication value, avoids ineffective energy consumption, and improves the overall communication perception capability, response efficiency, and resource utilization of the system.

[0106] Figure 2 A flow chart of a control method for an intelligent metasurface device provided in an embodiment of the present application is shown.

[0107] It should be understood that Figure 2 The illustrated embodiment may be regarded as an example of step S140 .

[0108] like Figure 2 As shown, the method includes the following steps.

[0109] S210 : Based on a preset sliding window, match the characteristic signal vector with multiple signal vector templates to obtain a matching variance coefficient.

[0110] Sliding window is a matching method that refers to the process of sliding the signal vector template to be matched on the feature signal vector with a fixed step size during the signal matching process. Each slide forms a sub-segment, and the error between the segment and the template is calculated. The entire vector is traversed to obtain the optimal matching interval.

[0111] After completing the sliding matching, the matching variance coefficient (also called the matching error normalization coefficient) is introduced to measure the relative difference between the feature signal vector and a template. It is defined as:

[0112] Matching variation coefficient = matching error / min (mean value of elements at each sampling point of the characteristic signal vector).

[0113] S220: When the matching variance coefficient is less than a preset threshold, generate a first control strategy.

[0114] The preset threshold is a criterion for determining whether a feature signal vector highly matches a signal vector template in the feature library.

[0115] The first control strategy is used to enable the signal control function of the intelligent metasurface device.

[0116] In other words, the first control strategy is used to trigger the operation of the smart metasurface device to regulate the incident electromagnetic signal.

[0117] When the sliding matching process is completed, it is determined whether the minimum matching variance coefficient is less than a preset threshold. If the conditions are met, it is determined that the current characteristic signal vector is highly matched with a certain template, and a first control strategy is generated, which triggers the activation of the signal modulation function of the intelligent metasurface device. In one implementation, the control operation of the incident electromagnetic signal is performed by a business unit in the intelligent metasurface device. In other words, the business unit can be regarded as an example of the unit or module mentioned above for realizing the signal modulation function. Accordingly, after the first control strategy is generated, according to the first control strategy, the signal modulation function of the intelligent metasurface device is activated, which may include:

[0118] According to the first control strategy, the business unit in the intelligent metasurface device is activated so that it performs the operation of regulating the incident electromagnetic signal.

[0119] This implementation method, by having the business unit in the intelligent metasurface device perform signal control operations after identifying the matching signal, not only improves the energy efficiency and response speed of the system, but also realizes on-demand allocation and management of resources, helps to reduce power consumption, improve real-time performance, and support modular expansion and flexible scheduling of the system.

[0120] In one implementation, multiple feature templates can be set for matching, and multiple corresponding matching variance coefficients can be obtained. By selecting the minimum value or setting a threshold, it can be determined whether the current feature signal is highly consistent with a specific business scenario, providing a quantitative basis for the generation of subsequent control strategies. Correspondingly, step S210 can include the following steps:

[0121] S211 . Calculate a mean difference between the characteristic signal vector and each signal vector template in the plurality of signal vector templates.

[0122] Exemplarily, the mean of the characteristic signal vector and the mean of the signal vector template are calculated, and the absolute value of the difference between the two is calculated.

[0123] S212 . Prioritize the multiple signal vector templates according to the mean value difference to obtain a matching sequence.

[0124] All templates are sorted from small to large according to the mean difference between them and the characteristic signal vector. After sorting, an ordered template set is obtained, which is called a matching sequence. The templates with the highest probability of successful matching are processed first.

[0125] It should be understood that the smaller the mean difference is, the higher the matching priority of the corresponding template is.

[0126] In an optional implementation, to further improve efficiency, this step may also include:

[0127] Screening out a signal vector template whose mean difference exceeds a preset threshold from a plurality of signal vector templates;

[0128] According to the mean difference, the selected signal vector templates are prioritized to obtain the matching sequence.

[0129] The preset threshold refers to the difference tolerance boundary value used for preliminary screening of signal vector templates.

[0130] It should be understood that the preset threshold may be set to be a multiple higher than the matching threshold, and is used to filter out templates having a large difference from the mean of the characteristic signal vector greater than the preset threshold.

[0131] Exemplarily, the preset threshold=N*preset threshold, where N can be set to an integer ≥4.

[0132] This threshold ensures that the templates involved in the matching have a certain degree of similarity, avoids over-calculation of invalid templates, and improves matching efficiency.

[0133] By setting a preset threshold greater than the matching threshold, signal templates that are significantly different from the current characteristic signal mean are first screened out, reducing redundant matching objects from the source; and the screening results are prioritized based on the mean difference, so that templates that are more likely to be successfully matched are given priority in the calculation, thereby further reducing the complexity of the matching calculation and improving the matching efficiency and the response speed of the state switching of the intelligent metasurface device.

[0134] S213 . Match the characteristic signal with each signal vector template in the plurality of signal vector templates according to the matching sequence to obtain a corresponding matching variance coefficient.

[0135] According to the matching sequence obtained in step S212, a sliding window matching operation is performed one by one, and the matching variance coefficient corresponding to each template is calculated to quantify the matching degree.

[0136] This implementation, by introducing a mean difference calculation and priority sorting mechanism before sliding window matching, effectively eliminates signal templates that significantly differ from the current characteristic signal, reducing invalid matching operations. While maintaining matching accuracy, it significantly reduces computational complexity and matching time, thereby improving the real-time perception and response of intelligent metasurface devices and the system's operational efficiency.

[0137] S230: When the matching variance coefficients obtained by matching a plurality of consecutive characteristic signal vectors with the characteristic library are all greater than or equal to a preset threshold, a second control strategy is generated.

[0138] The second control strategy is used to shut down the signal control function of the intelligent metasurface device.

[0139] In other words, the second control strategy is used to stop the operation of the smart metasurface device to regulate the incident electromagnetic signal.

[0140] This step determines whether there is a persistent idle communication state in the current environment, thereby disabling the intelligent metasurface's signal control functions and entering a low-power or sleep mode. Specifically, after continuously collecting characteristic signal vectors for several cycles, the system matches them against the signal vector templates in the feature library and calculates the corresponding matching variance coefficient.

[0141] When all calculated matching variance coefficients are greater than or equal to the set matching threshold in multiple consecutive cycles (eg, 3 or more), that is, no matching is successful, it is considered that there is no obvious communication demand in the terminal area during the time period.

[0142] At this time, the system will determine that the intelligent metasurface device currently has no perceived value, and can generate a second control strategy, which will trigger the shutdown of the signal modulation function of the intelligent metasurface device to reduce power consumption and extend the service life of the system.

[0143] In one implementation, the control operation of the incident electromagnetic signal is performed by a business unit in the intelligent metasurface device. In other words, the business unit can be regarded as an example of the unit or module mentioned above for implementing the signal modulation function. Accordingly, after generating the second control strategy, shutting down the signal modulation function of the intelligent metasurface device according to the second control strategy may include:

[0144] According to the second control strategy, the service unit in the intelligent metasurface device is put into hibernation to stop performing operations that regulate the incident electromagnetic signal. This embodiment, by introducing a sliding window matching and matching variance coefficient judgment mechanism, achieves precise matching of characteristic signals with multiple templates, thereby more accurately identifying the actual usage needs of the terminal. Compared to simple signal strength judgment, this solution has greater robustness and recognition accuracy in dynamic communication environments, effectively improving the accuracy and timeliness of the start and stop control of the intelligent metasurface device's signal regulation function, and further optimizing the system's response efficiency and resource management capabilities.

[0145] Furthermore, by incorporating the matching variance coefficient over multiple consecutive cycles as a basis for decision making, the stability and anti-interference capabilities of the stop signal control operation are enhanced, preventing frequent starts and stops of the intelligent metasurface device due to short-term fluctuations or occasional anomalies. Compared to single-cycle judgment, this solution effectively reduces unnecessary energy consumption while ensuring the user's communication experience, improving the energy efficiency of the intelligent metasurface device and the overall stability of the system.

[0146] The method provided in this embodiment is described below through an example.

[0147] S1. Data preparation.

[0148] S11. Obtain the characteristic signal vector after the analog signal is converted to a digital signal, recorded as Output = [output1, output2, ...output k ], where k is the length of the vector.

[0149] S12, obtain the corresponding signal vector template from the feature library, denoted as Y = [y1, y2, ...y S*k ], where S*k is the length of the vector.

[0150] S13. Set the size w of the sliding window according to actual conditions, w=S*k, and the step size is 1.

[0151] S14. Set a threshold θ of the matching coefficient of variation based on experiments or experience.

[0152] S2, sliding window calculation.

[0153] S21. Initialize the minimum matching coefficient of variation: min_cv = +∞.

[0154] S22. Starting from the starting position of the feature signal vector, slide the window with a step size of 1 until the right boundary of the window reaches the end of the feature signal vector.

[0155] S23. For each window position i (i ranges from 0 to w - k), extract the signal vector template Y i = [y i+1 , y i+2,... y i+k .

[0156] S3. Calculate the matching coefficient of variation.

[0157] S31. For the signal vector template Y i within each window, calculate its matching error E i with the feature signal vector Output. To improve the calculation efficiency, the absolute error is used:

[0158]

[0159] where, Y i,j is the j-th element of the signal vector template Y i , and output j is the j-th element of the feature signal vector.

[0160] S32. Calculate the mean of the feature signal vector:

[0161]

[0162] S33. Calculate the matching coefficient of variation of the current window:

[0163]

[0164] S4. Matching judgment.

[0165] Update the minimum matching coefficient of variation: If cv i < min_cv, then update min_cv = cv i ;

[0166] When the window sliding ends, compare the minimum matching coefficient of variation min_cv with the threshold θ. If min_cv < θ, it is considered that the matching is successful, indicating that there is an end user who needs to use the RIS device, and generate the first control strategy; otherwise, loop through the above steps to match the signal vectors in the next feature library. If none of them can be matched, it means that there is no need to use the RIS device; if multiple consecutive cycles fail to match successfully (i.e., min_cv ≥ θ), then generate the second control strategy.

[0167] Figure 3It is a structural diagram of a control system of an intelligent metasurface device provided by an embodiment of the present invention.

[0168] like Figure 3 As shown, the control system 1000 may include a sensing unit 1001 and a controller 1002 .

[0169] The sensing unit 1001 is used to receive electromagnetic signals in the uplink frequency band, convert the electromagnetic signals into digital signals, and sample the digital signals within a preset time period to generate characteristic signal vectors.

[0170] The controller 1002 is used to generate a control strategy for the smart metasurface device based on the matching results of the characteristic signal vector and the pre-built characteristic library, and to enable or disable the signal control function of the smart metasurface device according to the control strategy.

[0171] Among them, the feature library includes multiple signal vector templates divided and collected based on multiple communication dimensions in scenarios where there is a need to use intelligent metasurface devices.

[0172] The control system for the intelligent metasurface device provided in this embodiment achieves local automatic sensing and control of the intelligent metasurface device's status by arranging a sensing unit and a controller for coordinated operation. This eliminates the need for remote communication modules or backend server configuration, reducing the complexity and cost of system implementation. In particular, the sensing unit directly collects and extracts features from user terminal uplink signals, combined with the controller's built-in multi-dimensional feature library for rapid matching and strategy generation. This enables the intelligent metasurface device to intelligently switch operating states based on actual communication needs, improving response efficiency and resource utilization, and enhancing the system's adaptability and deployment flexibility.

[0173] It should be noted that the control system of the intelligent metasurface device provided in the embodiment of the present application can be set up independently of the intelligent metasurface device, or it can be integrated inside the intelligent metasurface device, and this application does not limit this.

[0174] Figure 4 A structural schematic diagram of an intelligent metasurface device 100 provided in an embodiment of the present application is shown.

[0175] It should be understood that the intelligent metasurface device 100 in this embodiment integrates the above-mentioned control system 1000.

[0176] like Figure 4 As shown, the intelligent metasurface device may include at least: a sensing unit 1001, a controller 1002, and a service unit 1003. The sensing unit 1001 and the control unit 1002 constitute a control system 1000 of the intelligent metasurface device.

[0177] The sensing unit 1001 is used to receive electromagnetic signals in the uplink frequency band, convert the electromagnetic signals into digital signals, and sample the digital signals within a preset time period to generate characteristic signal vectors, and send the characteristic signal vectors to the controller 1002.

[0178] Controller 1002 is used to generate a control strategy for the intelligent metasurface device based on the matching results of the characteristic signal vector and the pre-built characteristic library, and to enable or disable the signal control function of the business unit 1003 in the intelligent metasurface device according to the control strategy.

[0179] The service unit 1003 is used to perform signal control operations.

[0180] Exemplarily, the business unit 1003 can be used to perform operations such as changing the reflection characteristics, transmission characteristics or phase response of the metasurface unit to achieve reconstruction and control of the incident electromagnetic signal.

[0181] This embodiment integrates perception, analysis, decision-making and regulation into the intelligent metasurface device itself, thereby realizing an intelligent response and resource management mechanism for actual communication scenarios, thereby improving the intelligence level and overall operating efficiency of the intelligent metasurface device. Figure 5 Figure 2 shows a schematic diagram of the structure of the perception unit. Figure 5 As shown, the sensing unit 1001 is composed of a PIN diode, which is placed on the top metal patch along the direction of the electric field. The surface of the metal patch is wrapped with a semi-arc metal structure. This design helps to enhance the perception effect of electromagnetic waves. One end of a wire is connected to the metal patch for drawing out current, and the other end is connected to the common wire of the controller module as the input signal; one end of another wire is connected to the metal patch, and the other end is connected to the common ground terminal to form a complete current loop. Under the irradiation of electromagnetic waves in space, the metal patch will excite current resonance in a specific frequency band, thereby producing different electromagnetic response characteristics of the metasurface unit.

[0182] The sensing unit 1001 consists of three layers: a dielectric plate in the center, flanked by metal plates. The first metal plate is connected to the circuit via wires embedded in the dielectric plate, ensuring signal transmission. The third metal plate covers the entire sensing unit, reflecting electromagnetic signals and enhancing its ability to sense electromagnetic waves. This structural design not only effectively senses changes in electromagnetic waves but also optimizes electromagnetic response, providing stable and precise electromagnetic control for the metasurface unit.

[0183] Figure 6 1 shows a schematic diagram of the structure of the controller 1002. Figure 6 As shown, the controller 1002 includes a resistor 10021 , an analog-to-digital converter 10022 , and a characteristic signal analyzer 10023 .

[0184] Resistor 10021 is used to convert the current signal into a voltage signal.

[0185] The analog-to-digital converter 10022 is used to convert the voltage signal into a digital signal.

[0186] The characteristic signal analyzer 10023 is used to execute steps S210-S230.

[0187] For example, the resistance value of the resistor may be set to 100 ohms.

[0188] In one embodiment, the sensing unit 1001 is integrated with a CL type high-pass filter circuit to suppress low-frequency noise interference and improve the system's recognition accuracy for high-frequency characteristic signals. Figure 7 The structural diagram of the high-pass filter circuit is given. Figure 7 As shown in Figure 1, the high-pass filter circuit consists of a series capacitor C and a parallel inductor L. The upper port on the left side is connected to the input signal conductor to receive the sensing signal from the metal patch, and the lower port is connected to the common ground conductor, which forms the reference ground for the input. The upper right end of the circuit is connected to the characteristic signal recognition circuit to transmit the high-frequency valid signal to the post-processing module. The lower right end is still connected to the common ground to ensure a closed loop.

[0189] In this embodiment, the capacitance of capacitor C is set to 10pF, and the inductance of inductor L is set to 1nH. This parameter configuration makes the cutoff frequency of the filter circuit in the GHz range, which is suitable for sensing scenarios in the radio frequency or microwave frequency band.

[0190] The formula for the inductive reactance of an inductor (i.e., its impedance to AC signals) is as follows:

[0191] X_L=2πfL; (7)

[0192] As defined, f is the frequency of the input signal and L is the inductance of the inductor. As can be seen, the higher the frequency of the interference signal, the greater the inductive reactance of the inductor, and the more effectively it can prevent high-frequency interference signals from flowing into the ground.

[0193] On the other hand, the capacitive reactance formula of a capacitor is as follows:

[0194] X_C=1 / 2πfC; (8)

[0195] Where f is the signal frequency and C is the capacitance value. When the interference signal frequency is higher, the capacitance reactance is smaller, making it easier to transmit the high-frequency signal to the subsequent feature recognition circuit, thereby enhancing the perception unit's ability to extract high-frequency feature components.

[0196] In summary, through the deployment of this CL-type high-pass filter circuit, the sensing unit can effectively attenuate low-frequency background noise, improve the response sensitivity to characteristic signals in specific frequency bands, and ensure that the intelligent metasurface device still has good signal recognition and status perception capabilities in complex electromagnetic environments.

[0197] Figure 8 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present application is shown.

[0198] The computer device may include a processor 7001 and a memory 7002 storing computer program instructions.

[0199] Specifically, the processor 7001 may include a central processing unit (CPU) or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0200] Memory 7002 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 7002 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In one example, memory 7002 may include removable or non-removable (or fixed) media, or memory 7002 may be a non-volatile solid-state memory. Memory 7002 may be inside or outside the integrated gateway disaster recovery device.

[0201] In one embodiment, the memory 7002 may be a read-only memory (ROM). In one embodiment, the ROM may be a mask-programmable ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0202] The memory 7002 may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0203] The processor 7001 reads and executes the computer program instructions stored in the memory 7002 to implement Figure 1 The control method of the intelligent metasurface device in the illustrated embodiment.

[0204] In one example, the computer device may further include a communication interface 7003 and a bus 7004. Figure 8 As shown, the processor 7001, the memory 7002, and the communication interface 7003 are connected via a bus 7004 and communicate with each other.

[0205] The communication interface 7003 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0206] Bus 7004 includes hardware, software or both, and couples the components of online data flow metering equipment to each other. For example, and not limitation, the bus may include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), Hyper Transport (HT) interconnection, Industry Standard Architecture (ISA) bus, InfiniBand interconnection, Low Pin Count (LPC) bus, memory bus, Micro Channel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or a combination of two or more of these. Where appropriate, bus 7004 may include one or more buses. Although the present application embodiment describes and illustrates a specific bus, the present application considers any suitable bus or interconnection.

[0207] In addition, in conjunction with the method for managing data access in the above embodiments, embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the control methods for the intelligent metasurface device in the above embodiments is implemented.

[0208] An embodiment of the present application also provides a computer program product, including a computer program, which, when processed and executed, implements any one of the control methods of the intelligent metasurface device in the above embodiments.

[0209] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0210] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memories (ROMs), flash memories, erasable read-only memories (EROMs), floppy disks, compact disc read-only memories (CD-ROMs), optical discs, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0211] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0212] The above is only a specific implementation method of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited to this. Any technician familiar with this technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the scope of protection of this application.

Claims

1. A control method for an intelligent metasurface device, characterized in that: include: Receive electromagnetic signals in the uplink frequency band; converting the electromagnetic signal into a digital signal; Sampling the digital signal within a preset time period to generate a characteristic signal vector; Generating a control strategy for the intelligent metasurface device based on a matching result between the characteristic signal vector and a pre-built feature library, wherein the feature library includes a plurality of signal vector templates divided and collected based on multiple communication dimensions in scenarios where the intelligent metasurface device is required to be used; According to the control strategy, the signal regulation function of the intelligent metasurface device is enabled or disabled.

2. The method according to claim 1, characterized in that Generating a control strategy for the intelligent metasurface device according to a matching result between the characteristic signal vector and a pre-built characteristic library includes: Based on a preset sliding window, the characteristic signal vector is matched with the multiple signal vector templates to obtain a matching variance coefficient; When the matching variation coefficient is less than a preset threshold, a first control strategy is generated, where the first control strategy is used to enable a signal control function of the smart metasurface.

3. The method according to claim 2, characterized in that The method further comprises: When the matching variation coefficients obtained by matching multiple consecutive characteristic signal vectors with the characteristic library are greater than or equal to the preset threshold, a second control strategy is generated, and the second control strategy is used to shut down the signal control function of the intelligent metasurface device.

4. The method according to claim 2, characterized in that The matching of the characteristic signal vector with a plurality of signal vector templates in the characteristic library based on a preset sliding window to obtain a matching variance coefficient includes: Calculating a mean difference between the characteristic signal vector and each signal vector template in the plurality of signal vector templates; Prioritizing the plurality of signal vector templates according to the mean difference to obtain a matching sequence; According to the matching sequence, the characteristic signal is matched with each signal vector template in the multiple signal vector templates to obtain the corresponding matching variance coefficient.

5. The method according to claim 4, characterized in that Prioritizing the multiple signal vector templates according to the mean difference to obtain a matching sequence includes: Filtering out the signal vector template whose mean difference exceeds a preset threshold from the multiple signal vector templates, where the preset threshold is greater than the preset threshold; The filtered signal vector templates are prioritized according to the mean value differences to obtain the matching sequence.

6. The method according to any one of claims 1 to 5, characterized in that The converting of the electromagnetic signal into a digital signal comprises: generating a corresponding current signal according to the electromagnetic signal; converting the current signal into a voltage signal; The voltage signal is converted into the digital signal.

7. The method according to claim 6, characterized in that Before converting the current signal into a voltage signal, the method further includes: Perform inductive filtering and / or capacitive filtering processing on the current signal.

8. A control system for an intelligent metasurface device, characterized in that: including a sensing unit and a controller; The sensing unit is configured to receive an electromagnetic signal in an uplink frequency band, convert the electromagnetic signal into a digital signal, and sample the digital signal within a preset time period to generate a characteristic signal vector; The controller is configured to generate a control strategy for the intelligent metasurface device based on a matching result between the characteristic signal vector and a pre-built feature library, wherein the feature library includes a plurality of signal vector templates divided and collected based on multiple communication dimensions in scenarios where the intelligent metasurface device is required to be used; The controller is further configured to enable or disable a signal control function of the intelligent metasurface device according to the control strategy.

9. An intelligent metasurface device, characterized in that: Includes perception unit, controller and business unit; The sensing unit is configured to receive an electromagnetic signal in an uplink frequency band, convert the electromagnetic signal into a digital signal, and sample the digital signal within a preset time period to generate a characteristic signal vector, and send the characteristic signal vector to the controller; The controller is configured to generate a control strategy for the intelligent metasurface device based on a matching result between the characteristic signal vector and a pre-built feature library, wherein the feature library includes a plurality of signal vector templates divided and collected based on multiple communication dimensions in scenarios where the intelligent metasurface device is required to be used; and for enabling or disabling a signal control function of the business unit in the intelligent metasurface device according to the control strategy; The service unit is used to perform the signal control function.

10. The smart metasurface according to claim 9, characterized in that: The sensing unit includes a three-layer structure of a first metal sheet-a dielectric plate-a second metal sheet, a first wire and a second wire; a PIN diode is provided on the first metal sheet; one end of the first wire is connected to the first metal sheet, and the other end of the first wire is connected to the common wire of the controller; one end of the second wire is connected to the second metal sheet, and the other end of the second wire is connected to the common ground.

11. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the method according to any one of claims 1 to 7.

12. A computer-readable storage medium, characterized in that The computer storage medium stores computer program instructions, which, when executed by a processor, implement the method according to any one of claims 1 to 7.

Images