Parameter determination method and device for intelligent metasurface

Abstract

The embodiment of the invention provides a parameter determination method and device for an intelligent metasurface. According to the scheme, the multiple parameter sets and the corresponding signal intensities are used as the training samples to train the target model, so that the target model learns the mapping relation between the parameter sets and the signal intensities. Under the condition that the expected signal intensity is input, the target model can predict the corresponding target parameter set, the expected signal enhancement effect can be achieved by configuring the intelligent metasurface equipment through the target parameter set, errors caused by manual judgment are reduced, and then the accuracy of parameter determination is improved.

Description

Technical Field

[0001] The present application belongs to the technical field of intelligent supersurfaces, and in particular, relates to a method and device for determining parameters of an intelligent supersurface. Background Art

[0002] Reconfigurable Intelligent Surface (RIS) is a two-dimensional realization of electromagnetic metamaterials that can actively control electromagnetic waves through digital coding to achieve controllable reflection and projection of signals. Based on this feature, RIS can be deployed at specific locations to improve signal performance in blind spots and areas with poor quality.

[0003] However, when RIS is currently implemented and deployed, its parameter settings mainly rely on the operator's experience and judgment, which makes it difficult to ensure accuracy and affects the actual deployment effect.

[0004] Therefore, how to design a method to accurately determine RIS parameters has become a problem that needs to be solved urgently. Summary of the invention

[0005] The embodiments of the present application provide a method and device for determining parameters of an intelligent metasurface, which can accurately determine parameter values ​​used to configure the intelligent metasurface.

[0006] In a first aspect, an embodiment of the present application provides a method for determining parameters of a smart metasurface, the method comprising:

[0007] Acquire multiple parameter sets for deploying smart metasurface devices, the smart metasurface devices are used to enhance the signal of the target area, each parameter set includes a setting value of at least one parameter;

[0008] The signal strength of the target area when the smart metasurface device is deployed using each parameter set is obtained respectively;

[0009] A sample set is formed by combining multiple parameter sets and multiple signal strengths corresponding to the multiple parameter sets, and a target model is trained to learn a mapping relationship between any parameter set and the signal strength corresponding to the parameter set;

[0010] The trained target model is used to predict the parameter set corresponding to the expected signal strength based on the mapping relationship, and the predicted parameter set is determined as the target parameter set, which is used to configure the intelligent metasurface device.

[0011] In a possible implementation manner of the first aspect, the method further includes:

[0012] When a target parameter set is configured for the smart hypersurface, the following operations are performed at preset time intervals:

[0013] Obtain the actual signal strength of the target area, use the target parameter set and the actual signal strength as new samples, and continue to train the target model;

[0014] The trained target model is used to predict a new set of target parameters corresponding to the expected signal strength.

[0015] In a possible implementation manner of the first aspect, using a trained target model, based on a mapping relationship, predicting a parameter set corresponding to the expected signal strength, and determining the predicted parameter set as a target parameter set, including:

[0016] Any parameter set predicted by the target model and the signal strength corresponding to the parameter set are evaluated, the parameter set corresponding to the signal strength that meets the preset optimal condition is screened out, and the parameter set is determined as the target parameter set.

[0017] In a possible implementation manner of the first aspect, respectively acquiring a signal strength of a target area when deploying the smart metasurface device using each parameter set includes:

[0018] For each parameter set, after the intelligent metasurface device is configured with the parameter set, the signal strengths of multiple user terminals within a preset time range in the target area are collected;

[0019] The signal strength of the target area is determined according to the signal strengths of multiple user terminals.

[0020] In a possible implementation manner of the first aspect, for each parameter set, after the intelligent metasurface device configures the parameter set, signal strengths of multiple user terminals within a preset time range in the target area are collected, including:

[0021] When the target area is a completely outdoor area or a partially outdoor area, a user terminal whose positioning information falls within the contour longitude and latitude of the target area is confirmed as a target user terminal;

[0022] Collect the signal strength of the target user terminal within a preset time range.

[0023] In a possible implementation manner of the first aspect, for each parameter set, after the intelligent metasurface device configures the parameter set, signal strengths of multiple user terminals within a preset time range in the target area are collected, including:

[0024] When the target area is an indoor area, users whose signal time deviation and arrival angle information meet preset conditions are determined as target user terminals;

[0025] Collect the signal strength of the target user terminal within a preset time range.

[0026] In a possible implementation manner of the first aspect, determining the signal strength of the target area according to the signal strengths of multiple user terminals includes:

[0027] The average value of the signal strengths of the multiple user terminals is determined as the signal strength of the target area.

[0028] In a possible implementation manner of the first aspect, obtaining multiple parameter sets for deploying smart metasurface devices includes:

[0029] When the incident direction of the intelligent metasurface device is adjusted to a first preset direction and the exit direction is adjusted to a second preset direction, the setting values ​​of various parameters of the intelligent metasurface device are calculated through the three-dimensional coordinates of the intelligent metasurface device, and a first parameter set is determined based on the setting values ​​of various parameters. The first preset direction matches the coverage cell antenna, and the second preset direction points to the center position point of the target area. The first parameter set is one of multiple parameter sets for deploying intelligent metasurface devices.

[0030] In a possible implementation manner of the first aspect, the method further includes:

[0031] By adjusting the setting value of at least one parameter in the first parameter set, multiple parameter sets for deploying smart metasurface devices are generated.

[0032] In a possible implementation manner of the first aspect, the parameters include at least one of a horizontal incident angle, a pitch incident angle, a horizontal emergent angle, and a pitch emergent angle.

[0033] In a second aspect, an embodiment of the present application provides a device for determining parameters of an intelligent metasurface, the device comprising:

[0034] A first acquisition module is used to acquire a plurality of parameter sets for deploying an intelligent metasurface device, the intelligent metasurface device is used to enhance the signal of a target area, each parameter set includes a setting value of at least one parameter;

[0035] The second acquisition module is used to respectively acquire the signal strength of the target area when the intelligent metasurface device is deployed using each parameter set;

[0036] A training module, used to form a sample set from a plurality of parameter sets and a plurality of signal strengths corresponding to the plurality of parameter sets, and to train a target model to learn a mapping relationship between any parameter set and the signal strength corresponding to the parameter set;

[0037] The processing module is used to use the trained target model to predict the parameter set corresponding to the expected signal strength based on the mapping relationship, and determine the predicted parameter set as the target parameter set, which is used to configure the intelligent metasurface device.

[0038] In a third 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 first or second aspects above.

[0039] In a fourth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the method of any one of the first aspect or the second aspect described above is implemented.

[0040] The parameter determination method of the intelligent metasurface provided in the embodiment of the present application uses multiple parameter sets and their corresponding signal strengths as training samples to train the target model so that it learns the mapping relationship between the two. Under the condition of inputting the expected signal strength, the target model can predict the corresponding target parameter set, and the configuration of the intelligent metasurface device using the target parameter set can achieve the expected signal enhancement effect, reduce the error caused by human judgment, and thus improve the accuracy and efficiency of parameter determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1 It is a flow chart of a method for determining parameters of an intelligent metasurface provided in an embodiment of the present application;

[0043] Figure 2 It is a flow chart of a method for determining parameters of an intelligent metasurface provided in an embodiment of the present application;

[0044] Figure 3 It is a flow chart of a method for determining parameters of an intelligent metasurface provided in an embodiment of the present application;

[0045] Figure 4 It is a flow chart of a method for determining parameters of an intelligent metasurface provided in an embodiment of the present application;

[0046] Figure 5 It is a flow chart of a method for determining parameters of an intelligent metasurface provided in an embodiment of the present application;

[0047] Figure 6 It is a structural schematic diagram of a parameter determination device of an intelligent metasurface provided in an embodiment of the present application;

[0048] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application 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 application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0050] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0051] Based on the introduction of background technology, with the continuous development of mobile communication networks, the network structure has become more complex. The network has gradually tried to deploy RIS equipment for bridges, riverside roads, tunnels, dense urban residential areas, scenic spots, business district parking lot entrances and exits, low-altitude areas, etc., to solve the pain points of signal enhancement in non-line-of-sight scenarios, solve local signal voids, improve signal quality in multi-signal scenarios, and support edge users to improve perception, providing new ideas for further improving network coverage and capacity.

[0052] The existing RIS parameter planning method mainly relies on the operator's experience for configuration, but due to the dynamic complexity of the wireless network environment and the diverse scene requirements, the accuracy and optimization effect of manual settings are often difficult to meet the requirements. This manual configuration method is prone to problems such as resource waste, uneven coverage and signal interference, which limits the actual application effect of smart metasurfaces in complex environments.

[0053] In response to the above problems, the embodiments of the present application provide a method, device, electronic device and computer storage medium for determining parameters of an intelligent metasurface.

[0054] The following first introduces the parameter determination method of the smart metasurface provided in the embodiment of the present application.

[0055] Figure 1 FIG. 1 is a flow chart showing a method for determining parameters of an intelligent metasurface provided by an embodiment of the present application. Figure 1 As shown, the method may include the following steps:

[0056] S110. Obtain multiple parameter sets for deploying smart metasurface devices.

[0057] The application scenario of the embodiment of the present application is to enhance the signal coverage and quality in the target area through the intelligent metasurface device.

[0058] The target area refers to the area to be enhanced, that is, the area where the signal transmission effect needs to be strengthened.

[0059] As an example and not limitation, the target area may be a tunnel, a densely populated urban residential area, a parking lot entrance and exit in a shopping district, and the like.

[0060] Each parameter set may include a setting value of at least one smart metasurface parameter.

[0061] As an example but not limitation, the smart metasurface parameters may be parameters such as a horizontal incident angle, a pitch incident angle, a horizontal exit angle, or a pitch exit angle.

[0062] It should be understood that smart metasurface parameters refer to parameters that can control the reflection and refraction characteristics of smart metasurface devices and are used to deploy smart metasurface devices. By adjusting the smart metasurface parameters, the propagation path and intensity of the signal can be adjusted to enhance the signal coverage effect in the target area.

[0063] In one implementation, multiple parameter sets can be randomly generated based on the physical characteristics of the smart metasurface device and the requirements of the target area. This method can quickly generate a variety of parameter sets to adapt to different environments and requirements, thereby improving deployment flexibility and adaptability.

[0064] In one implementation, the relationship between historical signal strength data and parameter settings can be used to generate multiple parameter sets through regression analysis. This method can optimize parameter selection on a theoretical basis, improve the accuracy of signal enhancement effects, and reduce unnecessary trial and error costs.

[0065] In one implementation, multiple parameter sets can be generated based on a determined parameter set by randomly adjusting parameter values ​​in the parameter set. This method helps to explore the parameter space and find potential optimal configurations, thereby improving signal quality.

[0066] S120. Obtain the signal strength of the target area when the smart metasurface device is deployed using each parameter set.

[0067] That is, according to the settings of each parameter set, the smart metasurface device is configured and installed. After the device is deployed, the signal strength in the target area is measured to evaluate the performance of the device under that specific parameter setting.

[0068] It should be understood that each parameter set corresponds to a signal strength. By configuring multiple parameter sets respectively, multiple corresponding signal strengths can be obtained.

[0069] For example, when parameter set 1 is used to configure the smart metasurface device, a signal strength of 1 is obtained; when parameter set 2 is used, a signal strength of 2 is obtained; and when parameter set 3 is used, a signal strength of 3 is obtained.

[0070] In one implementation, the smart metasurface device can be deployed in the target area according to the configuration of each parameter set, and then the signal strength data can be collected at a fixed position using a signal measurement device. This method can obtain real-time, actual signal strength data, reflecting the performance of the device in a specific environment.

[0071] In one implementation, signal propagation simulation software can be used to simulate the signal propagation conditions under each parameter set in the target area. That is, by inputting environmental parameters, device location, and parameter set, a signal strength distribution map of the target area is generated. This method can quickly evaluate the effects of different parameter configurations and avoid the time and cost burden of field testing.

[0072] In one implementation, after deploying smart metasurface devices in the target area, the signal strength feedback of user terminals (such as smartphones, tablets, etc.) in the target area can be collected to analyze the user experience under different parameter sets. This method can directly reflect the signal quality perceived by users and provide signal performance in the actual use environment.

[0073] S130, multiple parameter sets and multiple signal strengths corresponding to the multiple parameter sets are combined into a sample set, and the target model is trained to learn the mapping relationship between any parameter set and the signal strength corresponding to the parameter set.

[0074] It should be understood that each sample in the sample set includes a parameter set and a signal strength corresponding to the set.

[0075] The pre-built target model is trained using the sample set, and the pre-built target model is used to learn the mapping relationship between any parameter set and the signal strength corresponding to the parameter set based on the sample set.

[0076] That is to say, the pre-built target model will analyze the data in the sample set, identify how a specific set of parameters affects the signal strength, and learn the mapping relationship between the two.

[0077] As an example but not limitation, the target model may be a linear regression model, a Gaussian process regression model, a neural network model, or the like.

[0078] In one implementation, multiple parameter sets and their corresponding signal strengths may be input into a target model in batches for training. In one implementation, incremental learning may be used to gradually add newly collected parameter sets and their corresponding signal strengths to an existing training set.

[0079] S140: using the trained target model, based on the mapping relationship, predicting a parameter set corresponding to the expected signal strength, and determining the predicted parameter set as the target parameter set.

[0080] The target model trained in step S130 is used to predict the signal strength.

[0081] It can be understood that the target model has learned the mapping relationship between the parameter set and the signal strength. By inputting a new signal strength target (expected signal strength), the parameter set that can achieve the signal strength can be found and the parameter set can be determined as the target parameter set.

[0082] Expected signal strength is the preset signal strength level that a smart surface device is expected to achieve.

[0083] It should be noted that, in actual applications, the expected signal strength can be set based on network performance requirements, user experience standards or specific application scenarios, and this application does not limit this.

[0084] The target parameter set refers to the parameter set predicted by the trained target model under the condition of inputting the expected signal strength.

[0085] The target parameter set is used to configure the smart metasurface device.

[0086] Configuring the intelligent metasurface device according to the target parameter set can achieve the expected signal strength in the target area, thereby optimizing the signal performance in the target area.

[0087] It should be noted that this application does not limit the configuration process of the target parameter set.

[0088] In one implementation, when the target model is a linear regression model, the step is: inputting the expected signal strength into the trained linear regression model, which can directly calculate the corresponding parameter set.

[0089] In one implementation, when the target model is a Gaussian process regression model, the step is: inputting the expected signal strength into the trained Gaussian process regression model, which can predict the corresponding parameter set.

[0090] In one implementation, step S140 may include the following steps:

[0091] Any parameter set predicted by the target model and the signal strength corresponding to the parameter set are evaluated, the parameter set corresponding to the signal strength that meets the preset optimal condition is screened out, and the parameter set is determined as the target parameter set.

[0092] The signal strength that meets the preset preferred condition is regarded as the expected signal strength.

[0093] Preset preference conditions refer to the screening criteria set in advance during the evaluation process.

[0094] In one example, the preset preferred condition may be defined as the highest signal strength value, which means that among multiple candidate parameter sets, the parameter set that can provide the best signal strength will be preferentially selected.

[0095] In one embodiment, the target model may be optimized using the expected improvement acquisition function to select a parameter set that is most likely to improve signal strength.

[0096] In the embodiment of the present application, multiple parameter sets and their corresponding signal strengths are used as training samples to train the target model so that it learns the mapping relationship between the two. Under the condition of inputting the expected signal strength, the target model can predict the corresponding target parameter set. Compared with the existing method of relying on operator experience to set parameters, this solution improves the accuracy and efficiency of parameter determination through model learning, eliminates errors in human judgment, and ensures that the expected signal enhancement effect can be achieved in different environments after parameter configuration.

[0097] It is understandable that, over time, the user distribution and network environment in the target area may change, resulting in the use of fixed parameter sets (such as Figure 1 The intelligent metasurface device configured with the target parameter set in the embodiment cannot effectively meet the new signal enhancement requirements. Therefore, in order to ensure that the intelligent metasurface device can still optimize the signal performance in a dynamic environment, the embodiment of the present application provides a parameter determination method to adapt to these changes.

[0098] Figure 2 A flow chart of a method for determining parameters of an intelligent metasurface provided in an embodiment of the present application is shown.

[0099] It should be understood that Figure 2 The illustrated embodiment can be viewed as Figure 1 An example of the embodiment shown, except Figure 1 In addition to steps S110 - S140 in the embodiment, the following steps may also be included.

[0100] S150. When configuring a target parameter set for the smart metasurface, execute steps S151-S152 at preset time intervals.

[0101] After configuring the target parameter set for the smart metasurface device, perform the following operations at preset time intervals to regularly evaluate and optimize the signal enhancement effect:

[0102] S151. Obtain the actual signal strength of the target area, and continue to train the target model using the target parameter set and the actual signal strength as new samples.

[0103] Get the actual signal strength of the target area. Combine the currently used target parameter set with the actual signal strength obtained as a new sample to further train the target model.

[0104] This step helps the target model capture changes in signal strength due to user changes or environmental changes, thereby achieving dynamic adjustments.

[0105] S152: using the trained target model, predicting a parameter set corresponding to the expected signal strength, and determining the predicted parameter set as a new target parameter set.

[0106] The trained target model is used to predict a new parameter set corresponding to the expected signal strength, and the predicted parameter set is determined as a new target parameter set to reconfigure the smart metasurface device.

[0107] In this embodiment, the signal strength of the target area is obtained within a preset time interval and combined with the current parameter set to form a new training sample. Subsequently, the target model is retrained using the updated training sample to ensure that the model can reflect the latest environment and user needs. Finally, by predicting a new parameter set corresponding to the expected signal strength, it is ensured that the intelligent metasurface device can provide an ideal signal strength under different user distributions and network conditions. Through a dynamic feedback mechanism and model learning, based on continuous monitoring of the actual signal strength of the target area and combined with dynamic updates of the target parameter set, the goal of optimizing the signal enhancement effect is achieved.

[0108] In one embodiment, Figure 2 The illustrated embodiment may further include the following steps: when the number of samples in the sample set reaches a preset threshold, deleting the first sample.

[0109] Exemplarily, the first sample may be the sample that has existed for the longest time in the sample set.

[0110] In this embodiment, a reasonable upper limit of the number of samples is set according to the actual application scenario to prevent data redundancy and waste of computing resources. In the sample set, the samples with the longest existence are identified according to the timestamp mark. Usually, these samples may reflect the earlier environmental conditions. Once the number of samples reaches the preset threshold, the first identified sample is immediately deleted from the sample set to ensure that the sample set always maintains the latest features and trends.

[0111] Illustratively, the following embodiment provides a training process when the target model is a Gaussian regression process model.

[0112] S1. Determine the objective function.

[0113] It should be understood that the objective function is regarded as a black box function, which is responsible for describing the mapping relationship between various parameters of the smart metasurface device and the signal strength. Since the form of the objective function may be complex and unknown, it needs to be evaluated through experimental or simulated data.

[0114] S2. Train the Gaussian process model to obtain the target model.

[0115] By associating the input (parameter set) with the output (signal strength) in the sample set, the Gaussian process model is used to learn and approximate the probability distribution of the target function. Using the input-output pairs obtained, the parameters of the Gaussian process model are optimized so that the model can better capture the relationship between input and output, and finally generate the target model.

[0116] S3. Select an evaluation point.

[0117] Use the sampling strategy from Bayesian optimization to select the next evaluation point.

[0118] In one implementation, an expected improvement (EI) function is used to evaluate the target model.

[0119] S4. Evaluate the objective function.

[0120] The objective function is evaluated at the selected evaluation point to obtain the corresponding signal strength data. The evaluation result is fed back to the target model to update the knowledge base of the target model. This process helps the model better fit the objective function and improve the accuracy of subsequent predictions.

[0121] S5. Iterative optimization.

[0122] Repeat steps S3 and S4 for multiple iterations until a stop condition is met. The stop condition may be that the signal strength meets a preset optimal condition.

[0123] It is understandable that obtaining multiple parameter sets in the prior art often relies on manual adjustment, which is not only time-consuming, but also easily limited by the operator's experience, resulting in low efficiency. Therefore, in order to improve the efficiency of obtaining parameter sets, the embodiment of the present application adopts a new parameter set acquisition strategy.

[0124] Figure 3 A flow chart of a method for obtaining multiple parameter sets provided in an embodiment of the present application is shown.

[0125] This embodiment can be regarded as an example of step S110.

[0126] like Figure 3 As shown, the method may include the following steps.

[0127] S111. Obtain a first parameter set by using three-dimensional coordinate calculation.

[0128] Obtaining the first parameter set by accurate three-dimensional coordinate calculation can reduce the number of subsequent parameter adaptive optimization iterations and improve the overall efficiency of the system. The method is as follows:

[0129] When the incident direction of the intelligent metasurface device is adjusted to a first preset direction and the exit direction is adjusted to a second preset direction, the setting values ​​of various parameters of the intelligent metasurface device are calculated through the three-dimensional coordinates of the intelligent metasurface, and a first parameter set is determined based on the setting values ​​of various parameters.

[0130] The first preset direction matches the coverage cell antenna.

[0131] The second preset direction points to the center point of the target area.

[0132] The first parameter set is one of a plurality of parameter sets for deploying a smart metasurface device.

[0133] The above method is described in detail below through an example.

[0134] Obtain basic information of the primary coverage cell, including the cell name, cell longitude, cell latitude, antenna azimuth, antenna tilt or antenna height.

[0135] It should be understood that the primary coverage cell refers to a base station that provides primary signal services, and its coverage affects the signal quality of the area to be enhanced. In other words, the primary coverage cell is a cell that provides signals for the area to be enhanced.

[0136] It should also be understood that the region to be enhanced herein is another expression of the target region.

[0137] Obtain basic information of the RIS device, such as the RIS panel longitude, RIS panel longitude, RIS panel azimuth, RIS panel inclination, or RIS panel hanging height.

[0138] The incident direction of the RIS device is matched with the main coverage cell antenna, and the outgoing direction of the RIS device is directed to the center point of the range position of the area to be enhanced. The center point is the centroid position point of the area to be enhanced and is set to (x, y, z).

[0139] Project the RIS device location point and the main coverage cell antenna location point onto the horizontal plane to form points A and B. An azimuth angle α can be formed along the radiation direction of AB. Assuming the RIS panel azimuth angle is β, the horizontal incident angle is calculated using the following formula:

[0140] Horizontal incident angle = (β-α+360) mod 360; (1)

[0141] Project the RIS device location point and the main coverage cell antenna location point onto the vertical plane to form points C and D. A downtilt angle γ can be formed along the radiation direction of CD. Assuming the downtilt angle of the RIS panel is δ, the following formula is used to calculate the elevation incident angle:

[0142] Pitch incident angle = 90 + δ - γ; (2)

[0143] Project the RIS device location point and the center point of the area to be enhanced onto the horizontal plane to form points E and F. An azimuth angle ∈ can be formed along the radiation direction of EF. Assuming the RIS panel azimuth angle is β, calculate the horizontal emission angle:

[0144] Horizontal emission angle = (β-∈+360) mod 360; (3)

[0145] Project the RIS device location point and the center point of the area to be enhanced onto the vertical plane to form points G and H. A downward tilt angle θ can be formed along the radiation direction of GH. Assuming the downward tilt angle of the RIS panel is δ, calculate the pitch emission angle:

[0146] Pitch angle = 90 + δ - θ; (4)

[0147] The calculated values ​​of the horizontal incident angle, the elevation incident angle, the horizontal exit angle, and the elevation exit angle form a first parameter set.

[0148] Combined with the above examples, it can be seen that in this step, a set of initial parameter setting values ​​is determined by the three-dimensional coordinate calculation method to form a first parameter set. The selection of the first parameter set takes into account the characteristics of the target area and the matching with the coverage cell antenna. Using this set as a benchmark provides a reasonable starting point and lays the foundation for the effective deployment of smart metasurface devices. This benchmark parameter set will be used to generate more parameter combinations in subsequent steps, thereby improving the flexibility and adaptability of signal enhancement.

[0149] S112. Generate multiple parameter sets for deploying smart metasurface devices by adjusting the setting value of at least one parameter in the first parameter set.

[0150] After obtaining the first parameter set, multiple parameter sets for deploying smart metasurface devices are generated by adjusting at least one parameter setting value in the set.

[0151] In this embodiment, multiple parameter sets are randomly generated based on one parameter set, which can not only expand the diversity of parameters, but also effectively improve the adaptability of the device in different environments.

[0152] It is understandable that after obtaining multiple parameter sets, it is necessary to evaluate the signal strength corresponding to each parameter set so as to combine the two into samples for training the target model. In this process, the standard for evaluating the configuration effect becomes crucial. The embodiment of the present application provides a spatiotemporal data association method based on the target area for effect evaluation. Specifically, by performing spatiotemporal correlation analysis on the signal strength data in the target area, the signal performance of each parameter set can be accurately obtained.

[0153] Figure 4 A flow chart of a method for determining parameters of an intelligent metasurface provided in an embodiment of the present application is shown.

[0154] It should be understood that Figure 4 The illustrated embodiment can be viewed as Figure 1 An example of step S120 in the embodiment.

[0155] like Figure 4 As shown, the method may include the following steps.

[0156] S410. For each parameter set, after the intelligent metasurface device is configured with the parameter set, signal strengths of multiple user terminals within a preset time range in the target area are collected.

[0157] When evaluating signal performance, the overall situation of user terminals in the target area should be considered. Therefore, this embodiment collects signal strength data of multiple user terminals in the target area after the smart metasurface device is configured with a specific parameter set to quantify the configuration effect of the parameter set.

[0158] In addition, in order to ensure the reliability of the evaluation results, this embodiment sets a preset time range. This design is intended to take into account the dynamic changes in signal performance in the target area and avoid inaccurate evaluation problems caused by relying on instantaneous signal data.

[0159] It should be understood that the preset time range can be set or adjusted according to the user mobility characteristics in the target area in actual applications, and this application does not limit this. For example, in a scenario with high user mobility, it is recommended to set a shorter time range to quickly capture changes in signal status; while in a scenario with low user mobility, a longer time range can be selected to more comprehensively reflect the stability of the signal. Exemplarily, the preset time range can be set to one week.

[0160] S411: When the target area is a completely outdoor area or a partially outdoor area, a user terminal whose positioning information falls within the contour longitude and latitude of the target area is confirmed as a target user terminal.

[0161] When the target area is a completely outdoor area or a partially outdoor area, the contour longitude and latitude of the target area are obtained; the positioning information of all user terminals inside and in the edge area of ​​the target area is obtained; and the user terminal whose positioning information falls within the contour longitude and latitude is confirmed as the target user terminal.

[0162] S412: When the target area is an indoor area, determine a user terminal whose signal time deviation and arrival angle information both meet preset conditions as a target user terminal.

[0163] S413: Collect signal strengths of target user terminals within a preset time range.

[0164] S420: Determine the signal strength of the target area according to the signal strengths of the multiple user terminals.

[0165] In one implementation, the average of the signal strengths of multiple user terminals can be determined as the signal strength of the target area. This method can fully consider the signal data of all users and reflect the overall signal strength level of the entire target area.

[0166] In one implementation, the median value of the signal strength of multiple user terminals can be determined as the signal strength of the target area. This method is less sensitive to extreme values, can more accurately represent the signal strength of most users, and is suitable for situations where the signal distribution is uneven or there are outliers, thereby providing a more stable signal strength evaluation result.

[0167] In this embodiment, the configuration effect of the parameter set is evaluated by associating time data with space data. Specifically, the signal strength data of the user terminals located in the target area within a specific time range are collected. By analyzing the signal strength data, the dynamic changes of the users and the environmental characteristics of the target area can be comprehensively considered, thereby more realistically reflecting the configuration effect of the parameter set.

[0168] This method can not only capture the instantaneous changes in signal strength, but also take into account the overall trend of user behavior within a time period, which helps to identify the pros and cons of parameter configuration under different conditions, thereby optimizing the deployment strategy of smart metasurface devices and improving the signal enhancement effect.

[0169] To better illustrate the method of the present application, the following Figure 5 A detailed example is shown for complete explanation.

[0170] S510: Obtain basic information of the primary coverage cell, the area to be enhanced, and the RIS device.

[0171] Get the basic information of the main coverage cell. The basic information of the main coverage cell may include: cell name, cell longitude, cell latitude, antenna azimuth, antenna tilt, and antenna height.

[0172] Get the basic information of the RIS device. The basic information of the RIS device can include: RIS panel longitude, RIS panel longitude, RIS panel azimuth, RIS panel inclination, and RIS panel hanging height.

[0173] Get the range location information of the area to be enhanced. When the area to be enhanced is a completely outdoor scene, the contour longitude and latitude of the area to be enhanced is used as the range location information. When the area to be enhanced is a partial outdoor scene and a partial indoor scene (such as tunnel entrance signal enhancement), only the contour longitude and latitude of the outdoor part of the area is used as the range location information. When the area to be enhanced is a completely indoor scene, the timing advance (TA) set and the angle of arrival (AOA) set of the transmission reception point (TRP) of the main coverage cell are obtained as the range location information.

[0174] S520: Calculate RIS initial parameter setting values.

[0175] The incident direction of the RIS device is matched with the main coverage cell antenna, and the outgoing direction of the RIS device is directed to the center point of the range position of the area to be enhanced. The center point is the centroid position point of the area to be enhanced and is set to (x, y, z).

[0176] Project the RIS device location point and the main coverage cell antenna location point onto the horizontal plane to form points A and B. An azimuth angle α can be formed along the radiation direction of AB. Assuming the RIS panel azimuth angle is β, the horizontal incident angle is calculated using the following formula:

[0177] Horizontal incident angle = (β-α+360) mod 360; (1)

[0178] Project the RIS device location point and the main coverage cell antenna location point onto the vertical plane to form points C and D. A downtilt angle γ can be formed along the radiation direction of CD. Assuming the downtilt angle of the RIS panel is δ, the following formula is used to calculate the elevation incident angle:

[0179] Pitch incident angle = 90 + δ - γ; (2)

[0180] Project the RIS device location point and the center point of the area to be enhanced onto the horizontal plane to form points E and F. An azimuth angle ∈ can be formed along the radiation direction of EF. Assuming the RIS panel azimuth angle is β, calculate the horizontal emission angle:

[0181] Horizontal emission angle = (β-∈+360) mod 360; (3)

[0182] Project the RIS device location point and the center point of the area to be enhanced onto the vertical plane to form points G and H. A downward tilt angle θ can be formed along the radiation direction of GH. Assuming the downward tilt angle of the RIS panel is δ, calculate the pitch emission angle:

[0183] Pitch angle = 90 + δ - θ; (4)

[0184] The calculated values ​​of the four corners are combined into a parameter set.

[0185] In view of the problem that the existing method is based on the operator's experience and the accuracy of manual setting is insufficient due to the complexity of the network, this step proposes a RIS parameter initialization determination method for the RIS coverage area to accurately calculate the configuration parameter values ​​and improve accuracy.

[0186] S530, performing effect evaluation based on spatiotemporal data association.

[0187] The parameter set obtained in step S520 is used to set multiple parameters of the RIS device, including the horizontal incidence angle u, the elevation incidence angle v, the horizontal emission angle w, and the elevation emission angle r. The parameter set is set to {u i ,v i ,w i ,r i}, where i represents the RIS device number of the enhanced area to be covered, and the time for parameter adjustment is t0.

[0188] Further collect precise positioning data of the area to be enhanced. For scenarios where the area to be enhanced is outdoor or partially outdoor, select data including but not limited to MDT (Minimization of Drive Tests) data and OTT (Over-The-Top) data. This type of data includes information such as longitude, latitude, downlink signal strength (Reference Signal Received Power, RSRP), and downlink signal-to-noise ratio (Signal to Interference plus Noise Ratio, SINR) when the user occupies the main coverage cell signal. For scenarios where the area to be enhanced is indoors, select data including but not limited to MR (Measurement Report) data and MDT (Minimization of Drive Tests). This type of data includes information such as TA, AOA, downlink signal strength RSRP, and downlink signal-to-noise ratio SINR when the user occupies the TRP signal of the main coverage cell.

[0189] Perform spatiotemporal data association. Take samples after time t_0 in the time dimension. For scenes where the area to be enhanced is outdoor or partially outdoor, take samples within the range of the longitude and latitude position that includes the area to be enhanced in the spatial dimension; for scenes where the area to be enhanced is indoor, take samples of the TA and AOA set that belong to the indoor area to be enhanced in the spatial dimension.

[0190] According to the aforementioned steps, N data samples are collected in time sequence, and the average signal strength RSRPa is calculated as the effect evaluation of the set of parameter settings.

[0191] The reason for not using SINR is that the signal-to-noise ratio is significantly affected by the overall network load, and the load varies greatly in different time periods, making it difficult to make effective comparisons.

[0192] The effect verification method of the existing methods usually adopts the means of field testing, which has obvious limitations. In this step, an effect verification method based on spatiotemporal data association calculation is proposed, so that the background statistical effect evaluation of RIS parameter settings can be performed to reduce the effect verification cost.

[0193] S540: Randomly adjust parameters and collect corresponding effects.

[0194] According to the RIS initial parameter setting value obtained in step S520 above, the random adjustment range is set. i The adjustment range is u i ±a, pitch angle v i The adjustment range is v i±b, horizontal angle of incidence w i The adjustment range is w i ±c, the pitch angle r i The adjustment range is r i ±d. Wherein, a, b, c, d are all positive integers. S RIS device parameter setting schemes are randomly generated within the above range, which are non-repetitive, do not contain the initial setting scheme, and do not exceed the adjustable range of the RIS device hardware, and the effect evaluation of the parameter setting value is obtained based on the method of step S530.

[0195] S550, adaptively adjust parameters based on Bayesian optimization.

[0196] Bayesian Optimization is an algorithm for global optimization, especially suitable for optimization problems of expensive and black-box functions. The main idea is to approximate the objective function by constructing a proxy model (usually a Gaussian process or a random forest), and gradually improve the estimation of the optimal solution using the Bayesian inference method. The specific objective function is the mean signal strength of the N sampling points in the area D to be enhanced under the RIS device parameter settings:

[0197] f(u i ,v i ,w i ,r i )=(∑ e∈D RSRP e ) / N; (5)

[0198] This proposal uses Bayesian optimization to determine the parameter setting values ​​of the RIS device used in a certain area to be enhanced, and adaptively configures the RIS parameters. The specific process is as follows:

[0199] First, based on the parameters obtained in steps S520-S540, {u i,j ,v i,j ,w i,j ,r i,j} and the corresponding effect average signal strength RSRP a,j Construct a proxy model, and further use the acquisition function combined with the proxy model to obtain the RIS device parameters {u i,j ,v i,j ,w i,j ,r i,j}; Set RIS parameters according to the result of the previous step and obtain the adjustment effect RSRP a,m ; Add the formed parameters and effects to the training data to further fit the agent model; Periodically perform the above steps to adaptively optimize and adjust the RIS deployment parameters.

[0200] (1) Build an agent model.

[0201] This proposal uses Gaussian process regression method to create a surrogate model Let the parameter vector be x, that is The proxy model is made to approximate the objective function and can predict the RSRP result by inputting the RIS parameter value. The Gaussian process regression method uses the Gaussian process model to fit the objective function f(x). The following is a Gaussian process model, where μ and K are the model parameters for fitting. μ uses a constant function, that is, the sample mean, and K is the sample covariance matrix function.

[0202]

[0203] The parameters in the Gaussian process regression model, including the parameters in the mean function and the kernel function, are estimated using the maximum a posteriori estimate (MAP) based on the sample data collected in steps S520-S540 to select the most likely parameter values ​​when the observed values ​​are known.

[0204] (2) Calculate the sampling function RIS equipment parameters.

[0205] The EI (Expected Improvement) acquisition function is used to calculate and evaluate the results of each RIS parameter combination. The higher the output value, the better the improvement effect. Assuming the sampling function is EI(x), the optimal RIS equipment parameter calculation formula is as follows:

[0206]

[0207] where μ(x) and δ(x) are The mean function and standard deviation function of φ(x) and Φ(x) are the probability density function and distribution function of the standard normal distribution respectively. The average RSRP value of the current optimal parameter setting.

[0208] (3) Adjust RIS equipment parameters.

[0209] According to the calculation in step S520 The parameter vector is used to adjust the horizontal incidence angle, the pitch incidence angle, the horizontal emission angle, and the pitch emission angle of the RIS device corresponding to the enhanced area, and the adjustment effect is collected using the method of step S530 And add this sample to the training dataset {u i,j ,v i,j ,w i,j ,r i,j ,RSRP a,j}middle.

[0210] (4) Periodically and adaptively adjust RIS equipment parameters.

[0211] The above steps are repeatedly executed every time t, where the time granularity of t is, for example, a day granularity.

[0212] If the cumulative number of added samples reaches S / E, the sample that was first added to the training data set used to fit the proxy model will be removed in chronological order.

[0213] S is the initial sample size, and E is an integer. For example, E can be [5, 10].

[0214] In view of the problem that the existing methods cannot perform adaptive optimization and therefore cannot obtain the best setting parameters, this step proposes an intelligent hypersurface parameter adaptive adjustment method based on Bayesian optimization to dynamically optimize the optimal RIS parameter setting value and improve the deployment quality.

[0215] Figure 6 Schematic diagram of a parameter determination device for an intelligent metasurface provided in an embodiment of the present application. Figure 6 As shown, the device 1000 may include the following modules.

[0216] The first acquisition module 1001 is used to acquire multiple parameter sets for deploying smart metasurface devices.

[0217] Smart metasurface devices are used to enhance the signal in the target area.

[0218] Each parameter set includes a setting value of at least one parameter.

[0219] The second acquisition module 1002 is used to respectively acquire the signal strength of the target area when the smart metasurface device is deployed using each parameter set.

[0220] The training module 1003 is used to form a sample set by combining multiple parameter sets and multiple signal strengths corresponding to the multiple parameter sets, and train the target model to learn the mapping relationship between any parameter set and the signal strength corresponding to the parameter set.

[0221] The processing module 1004 is used to use the trained target model to predict a parameter set corresponding to the expected signal strength based on the mapping relationship, and determine the predicted parameter set as the target parameter set.

[0222] The target parameter set is used to configure the smart metasurface device.

[0223] Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0224] The electronic device may include a processor 2001 and a memory 2002 storing computer program instructions.

[0225] Specifically, the processor 2001 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.

[0226] The memory 2002 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 2002 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, the memory 2002 may include a removable or non-removable (or fixed) medium, or the memory 2002 is a non-volatile solid-state memory. The memory 2002 may be inside or outside the integrated gateway disaster recovery device.

[0227] In one example, the memory 2002 may be a read-only memory (ROM). In one example, the ROM may be a mask-programmed 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.

[0228] The memory 2002 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) 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.

[0229] The processor 2001 reads and executes the computer program instructions stored in the memory 2002 to implement Figure 1 A method for determining parameters of the smart metasurface in the illustrated embodiment.

[0230] In addition, in combination with the method for determining parameters of the smart metasurface in the above embodiments, the embodiment 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 the processor, any method for determining parameters of the smart metasurface in the above embodiments is implemented.

[0231] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements any one of the methods for determining parameters of the smart metasurface in the above embodiments.

[0232] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0233] The functional blocks shown in the structural block diagram described above 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 (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, 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 communication link by a data signal carried in a carrier. "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 memory (Read-Only Memory, ROM), flash memory, erasable read-only memory (Erasable ReadOnly Memory, EROM), floppy disks, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical discs, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0234] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0235] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment 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 can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0236] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity 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 protection scope of the present application is not limited to this. Any technician familiar with the 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 protection scope of this application.

Claims

1. A method for determining parameters of an intelligent metasurface, characterized in that: include: Acquire a plurality of parameter sets for deploying an intelligent metasurface device, wherein the intelligent metasurface device is used to enhance a signal in a target area, each parameter set including a setting value of at least one parameter; Respectively obtaining the signal strength of the target area when the smart metasurface device is deployed using each parameter set; A plurality of parameter sets and a plurality of signal strengths corresponding to the plurality of parameter sets are combined into a sample set, and a target model is trained to learn a mapping relationship between any parameter set and the signal strength corresponding to the parameter set; The trained target model is used to predict a parameter set corresponding to the expected signal strength based on the mapping relationship, and the predicted parameter set is determined as a target parameter set, which is used to configure the intelligent metasurface device.

2. The method according to claim 1, characterized in that: The method further comprises: When configuring the target parameter set for the smart metasurface, the following operations are performed at preset time intervals: Acquire the actual signal strength of the target area, and continue to train the target model using the target parameter set and the actual signal strength as new samples; The target model after continued training is used to predict a new target parameter set corresponding to the expected signal strength.

3. The method according to claim 1, characterized in that The method of using the trained target model to predict a parameter set corresponding to the expected signal strength based on the mapping relationship, and determining the predicted parameter set as the target parameter set, includes: Any parameter set predicted by the target model and the signal strength corresponding to the parameter set are evaluated, the parameter set corresponding to the signal strength that meets the preset optimal condition is screened out, and the parameter set is determined as the target parameter set.

4. The method according to any one of claims 1 to 3, characterized in that The step of respectively obtaining the signal strength of the target area when the intelligent metasurface device is deployed using each parameter set includes: For each parameter set, after the intelligent metasurface device is configured with the parameter set, signal strengths of multiple user terminals within a preset time range in the target area are collected; The signal strength of the target area is determined according to the signal strengths of the multiple user terminals.

5. The method according to claim 4, characterized in that For each parameter set, after the intelligent metasurface device is configured with the parameter set, signal strengths of multiple user terminals within a preset time range in the target area are collected, including: When the target area is a completely outdoor area or a partially outdoor area, a user terminal whose positioning information falls within the longitude and latitude of the outline of the target area is confirmed as a target user terminal; The signal strength of the target user terminal within the preset time range is collected.

6. The method according to claim 5, characterized in that For each parameter set, after the intelligent metasurface device is configured with the parameter set, signal strengths of multiple user terminals within a preset time range in the target area are collected, including: When the target area is an indoor area, a user whose signal time deviation and arrival angle information both meet preset conditions is determined as a target user terminal; The signal strength of the target user terminal within the preset time range is collected.

7. The method according to claim 4, characterized in that The determining the signal strength of the target area according to the signal strengths of the multiple user terminals includes: An average value of the signal strengths of the multiple user terminals is determined as the signal strength of the target area.

8. The method according to any one of claims 1 to 3, characterized in that The step of obtaining a plurality of parameter sets for deploying the intelligent metasurface device includes: When the incident direction of the intelligent metasurface device is adjusted to a first preset direction and the exit direction is adjusted to a second preset direction, the setting values ​​of various parameters of the intelligent metasurface device are calculated through the three-dimensional coordinates of the intelligent metasurface device, and a first parameter set is determined based on the setting values ​​of the various parameters, the first preset direction matches the coverage cell antenna, the second preset direction points to the center position point of the target area, and the first parameter set is one of the multiple parameter sets for deploying the intelligent metasurface device.

9. The method according to claim 8, characterized in that The method further comprises: The multiple parameter sets for deploying the smart metasurface device are generated by adjusting the setting value of at least one parameter in the first parameter set.

10. The method according to claim 9, characterized in that The parameters include at least one of a horizontal incident angle, a pitch incident angle, a horizontal exit angle, and a pitch exit angle.

11. A device for determining parameters of an intelligent metasurface, characterized in that: include: A first acquisition module is used to acquire a plurality of parameter sets for deploying an intelligent metasurface device, wherein the intelligent metasurface device is used to enhance a signal in a target area, and each parameter set includes a setting value of at least one parameter; A second acquisition module is used to respectively acquire the signal strength of the target area when the smart metasurface device is deployed using each parameter set; A training module, used to form a sample set from a plurality of parameter sets and a plurality of signal strengths corresponding to the plurality of parameter sets, and to train a target model to learn a mapping relationship between any parameter set and the signal strength corresponding to the parameter set; A processing module is used to use the trained target model to predict a parameter set corresponding to the expected signal strength based on the mapping relationship, and determine the predicted parameter set as a target parameter set, and the target parameter set is used to configure the intelligent metasurface device.

12. 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 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images