Data acquisition method and device, equipment and storage medium

Abstract

The invention discloses a data acquisition method and device, equipment and a storage medium. The method comprises the following steps: acquiring design parameters (the working frequency of the sample all-dielectric broadband absorber, the heights of a substrate layer, a dielectric layer and a resonant layer and the side length of the cross section) of the sample all-dielectric broadband absorber and a corresponding absorption spectrum, and sampling the absorption spectrum at equal intervals according to the working frequency to obtain sample output data; determining the size of a dielectric-harmonic mapping matrix of the sample all-dielectric broadband absorber according to preset grid density and the side length of the cross section of the dielectric layer, and determining the value of each element in the dielectric-harmonic mapping matrix according to the heights of the dielectric layer and the resonant layer and the side length of the cross section of the resonant layer to obtain the dielectric-harmonic mapping matrix; determining the dielectric harmonic mapping matrix, the height and the side length of the cross section of the substrate layer and the side length of the cross section of the dielectric layer as sample input data; and determining the sample output data and the sample input data as target data, wherein the target data is used for training an absorption spectrum prediction model of the all-dielectric broadband absorber.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of all-dielectric broadband absorbers, and in particular to a data acquisition method, device, equipment and storage medium. Background Art

[0002] With the rapid development of modern science and technology, all-dielectric broadband absorbers have shown great application potential in the fields of communications, radar, stealth technology, optoelectronics, etc. This absorber can efficiently absorb electromagnetic waves in a wide frequency band, thereby achieving functions such as stealth, shielding or energy conversion of electromagnetic waves. For this reason, it is particularly important to predict the absorption spectrum of all-dielectric broadband absorbers.

[0003] At present, although the absorption spectrum prediction model of all-dielectric broadband absorber can realize the prediction function of the absorption spectrum of all-dielectric broadband absorber to a certain extent, there is a problem that the model training time is too long, resulting in overall low efficiency.

[0004] Therefore, it is urgent to propose a new method to solve the above problems. Summary of the invention

[0005] The present invention provides a data acquisition method, device, equipment and storage medium, which can reduce the training time of an absorption spectrum prediction model of an all-dielectric broadband absorber.

[0006] In a first aspect, an embodiment of the present invention provides a data acquisition method, the method comprising:

[0007] Obtaining a sample absorption spectrum corresponding to a sample all-dielectric broadband absorber, and obtaining sample design parameters of the sample all-dielectric broadband absorber, wherein the sample design parameters include a sample operating frequency and sample geometric parameters of the sample all-dielectric broadband absorber; the sample geometric parameters include the height and cross-sectional side length of a sample base layer, a sample dielectric layer, and a sample resonant layer of the sample all-dielectric broadband absorber;

[0008] Sampling the sample absorption spectrum at equal intervals according to the sample operating frequency to obtain target sample output data;

[0009] Determine the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to the preset grid density and the cross-sectional side length of the sample dielectric layer, and determine the value of each element in the sample dielectric harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer, to obtain the sample dielectric harmonic mapping matrix;

[0010] Determine the sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample medium layer as target sample input data;

[0011] The target sample output data and the target sample input data are determined as target sample data, wherein the target sample data is used for training an absorption spectrum prediction model, and the absorption spectrum prediction model is used to predict the absorption spectrum of a target all-dielectric broadband absorber.

[0012] The embodiment of the present invention provides a data acquisition method, comprising: acquiring a sample absorption spectrum corresponding to a sample all-dielectric broadband absorber, and acquiring sample design parameters of the sample all-dielectric broadband absorber, wherein the sample design parameters include a sample operating frequency and sample geometric parameters of the sample all-dielectric broadband absorber; the sample geometric parameters include the height and cross-sectional side length of a sample substrate layer, a sample dielectric layer and a sample resonant layer of the sample all-dielectric broadband absorber; sampling the sample absorption spectrum at equal intervals according to the sample operating frequency to obtain target sample output data; determining the size of a sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to a preset grid density and the cross-sectional side length of the sample dielectric layer, and determining the value of each element in the sample dielectric harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer and the cross-sectional side length of the sample resonant layer to obtain the sample dielectric harmonic mapping matrix; determining the sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample substrate layer and the cross-sectional side length of the sample dielectric layer as target sample input data; determining the target sample output data and the target sample input data as target sample data, wherein the target sample data is used for training an absorption spectrum prediction model, and the absorption spectrum prediction model is used for predicting the absorption spectrum of the target all-dielectric broadband absorber. The above technical scheme first obtains the sample absorption spectrum corresponding to the sample all-dielectric broadband absorber, and obtains the sample design parameters of the sample all-dielectric broadband absorber, which provides a data basis for determining the target sample output data and the target sample input data. Then, the sample absorption spectrum is sampled at equal intervals according to the sample working frequency to obtain the target sample output data, which effectively reduces the data volume of the target sample output data, not only laying a solid foundation for the subsequent generation of target sample data, but also significantly improving the training speed of the subsequent model. Then, the size of the sample medium harmonic mapping matrix of the sample all-dielectric broadband absorber is determined according to the preset grid density and the cross-sectional side length of the sample dielectric layer, and the value of each element in the sample medium harmonic mapping matrix is ​​determined according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer, and the sample medium harmonic mapping matrix is ​​obtained, which realizes the dimensionality reduction of the original data and provides a data basis for the subsequent determination of the target sample input data. Then, the sample medium harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample dielectric layer are determined as the target sample input data, which reduces the input data volume, thereby reducing the computational complexity of the subsequent training, thereby shortening the time of the subsequent model training and improving the training efficiency of the subsequent model. Finally, the target sample output data and the target sample input data are determined as the target sample data, and the absorption spectrum prediction model is trained with the target sample data, which reduces the model training time and improves the model training efficiency. Therefore, the present invention solves the problem that the training time of the absorption spectrum prediction model of the existing all-dielectric broadband absorber is too long, resulting in low overall efficiency.

[0013] In a second aspect, an embodiment of the present invention further provides a data acquisition device, the device comprising:

[0014] An acquisition module, used to acquire a sample absorption spectrum corresponding to a sample all-dielectric broadband absorber, and acquire sample design parameters of the sample all-dielectric broadband absorber, wherein the sample design parameters include a sample operating frequency and sample geometric parameters of the sample all-dielectric broadband absorber; the sample geometric parameters include a height and a cross-sectional side length of a sample base layer, a sample dielectric layer, and a sample resonant layer of the sample all-dielectric broadband absorber;

[0015] An output data determination module, used for sampling the sample absorption spectrum at equal intervals according to the sample operating frequency to obtain target sample output data;

[0016] a matrix determination module, used to determine the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to a preset grid density and the cross-sectional side length of the sample dielectric layer, and to determine the value of each element in the sample dielectric harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer, so as to obtain the sample dielectric harmonic mapping matrix;

[0017] An input data determination module, used to determine the sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample dielectric layer as target sample input data;

[0018] The target data determination module is used to determine the target sample output data and the target sample input data as target sample data, wherein the target sample data is used to train an absorption spectrum prediction model, and the absorption spectrum prediction model is used to predict the absorption spectrum of a target all-dielectric broadband absorber.

[0019] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0020] at least one processor; and a memory communicatively coupled to the at least one processor;

[0021] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute any data acquisition method described in the first aspect.

[0022] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute any of the data acquisition methods described in the first aspect when executed by a computer processor.

[0023] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium, wherein the computer-readable storage medium may be packaged together with the processor of the data acquisition device, or may be packaged separately from the processor of the data acquisition device, which is not limited in this application.

[0024] The description of the second, third and fourth aspects in this application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second, third and fourth aspects can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.

[0025] In this application, the name of the above data acquisition device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they fall within the scope of the claims of this application and their equivalent technologies.

[0026] These and other aspects of the present application will become more clearly understood in the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1a A flow chart of a data acquisition method provided by an embodiment of the present invention;

[0029] Figure 1b A schematic structural diagram of a sample all-dielectric broadband absorber provided in an embodiment of the present invention;

[0030] Figure 2 A flowchart of another data acquisition method provided by an embodiment of the present invention;

[0031] Figure 3 A schematic diagram of the structure of a data acquisition device provided by an embodiment of the present invention;

[0032] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0034] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0035] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0036] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0037] It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe various operations (or steps) as sequential processes, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to methods, functions, procedures, subroutines, subprograms, etc. In addition, the embodiments in the present invention and the features in the embodiments can be combined with each other without conflict.

[0038] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0039] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0040] Figure 1aA flowchart of a data acquisition method provided by an embodiment of the present invention. This embodiment is applicable to the situation where the training time of the absorption spectrum prediction model of the all-dielectric broadband absorber needs to be reduced. The method can be executed by the data acquisition device provided by the present invention. The device can be implemented in software and / or hardware. Specifically, the device can be integrated in an electronic device. Exemplarily, the electronic device can be a computer or a server. Figure 1a The data acquisition method of this embodiment may specifically include the following steps:

[0041] Step 110: Obtain a sample absorption spectrum corresponding to the sample all-dielectric broadband absorber, and obtain sample design parameters of the sample all-dielectric broadband absorber.

[0042] Specifically, a full dielectric broadband absorber refers to a device composed of all the same dielectric materials, which is used to absorb electromagnetic radiation and other energy within a wide frequency range (broadband). In this embodiment, the structure of the full dielectric broadband absorber is divided into three layers: upper, middle and lower. The lower layer is a substrate layer for providing stable support and necessary electromagnetic properties, the middle layer is a dielectric layer for regulating and absorbing electromagnetic radiation, and the top layer is a resonant layer for enhancing and absorbing electromagnetic radiation within a specific frequency range. The three layers are all made of the same dielectric material and the cross-sections of the three layers along the height direction are all squares with fixed side lengths. The sample full dielectric broadband absorber refers to a full dielectric broadband absorber used to form a training data set for an absorption spectrum prediction model. The absorption spectrum refers to the corresponding relationship between frequency and absorptivity. The sample absorption spectrum refers to the absorption spectrum of the sample full dielectric broadband absorber. The sample design parameters include the sample operating frequency and sample geometric parameters of the sample full dielectric broadband absorber. The sample operating frequency refers to the frequency range for which the sample full dielectric broadband absorber works normally. The sample geometric parameters include the height and cross-sectional side length of the sample substrate layer, sample dielectric layer and sample resonant layer of the sample full dielectric broadband absorber.

[0043] In a specific implementation, the sample absorption spectrum and sample design parameters corresponding to the sample all-dielectric broadband absorber can be obtained from a database storing the sample absorption spectrum and sample design parameters corresponding to the all-dielectric broadband absorber through a database query statement.

[0044] It should be noted that, in practical applications, the sample design parameters of the sample all-dielectric broadband absorber can also be determined according to actual needs or situations, and the simulation software and the sample design parameters can be used to determine the sample absorption spectrum corresponding to the sample all-dielectric broadband absorber.

[0045] In addition, in order to improve the universality of the absorption spectrum prediction model obtained later, such as Figure 1b As shown, the structure of the sample resonant layer may also include a cross shape, an I-shape, an "H" shape, a double open ring shape, a Jerusalem cross shape, and a single open ring shape.

[0046] In this embodiment, by obtaining the sample absorption spectrum corresponding to the sample all-dielectric broadband absorber and the sample design parameters of the sample all-dielectric broadband absorber, a data basis is provided for subsequently determining the target sample output data and the target sample input data.

[0047] Step 120: Sample the sample absorption spectrum at equal intervals according to the sample operating frequency to obtain target sample output data.

[0048] Specifically, the target sample output data refers to the data obtained after equally spaced sampling of the sample absorption spectrum according to the sample operating frequency. It serves as the training data at the output end of the absorption spectrum prediction model and represents the expected output result of the model.

[0049] In the specific implementation, the sampling interval is first determined according to the actual situation or demand, and then the frequency of each sampling point is determined according to the sample working frequency and the sampling interval. Then, the absorption rate of each sampling point is determined according to the frequency of each sampling point and the sample absorption spectrum. Finally, the frequency of each sampling point and the corresponding absorption rate are determined as the target sample output data.

[0050] In this embodiment, the sample absorption spectrum is sampled at equal intervals according to the sample operating frequency to obtain target sample output data, which effectively reduces the amount of target sample output data, not only laying a solid foundation for the subsequent generation of target sample data, but also significantly improving the training speed of subsequent models.

[0051] Step 130, determine the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to the preset grid density and the cross-sectional side length of the sample dielectric layer, and determine the value of each element in the sample dielectric harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer to obtain the sample dielectric harmonic mapping matrix.

[0052] Specifically, the preset network density refers to a parameter set in advance according to actual conditions or requirements for determining the size of the sample dielectric harmonic mapping matrix. The sample dielectric harmonic mapping matrix refers to a matrix constructed according to the geometric parameters (height and cross-sectional side length) of the sample dielectric layer and the sample resonant layer.

[0053] In a specific implementation, the number of rows and columns of the sample harmonic mapping matrix can be determined according to the ratio of the cross-sectional side length of the sample dielectric layer and the preset grid density. Since the cross-sectional area of ​​the sample dielectric layer is a square, the number of rows and columns of the sample harmonic mapping matrix are equal, that is, the number of rows of the sample harmonic mapping matrix = the number of columns of the sample harmonic mapping matrix = the cross-sectional side length of the sample dielectric layer / the preset grid density, so the size of the sample harmonic mapping matrix is ​​the square of the number of rows (or columns) of the sample harmonic mapping matrix. Then, the value of each element in the sample harmonic mapping matrix can be determined according to the height of the sample dielectric layer, the height of the sample resonance layer, and the cross-sectional side length of the sample resonance layer. Specifically, for each element, the position of the element on the cross-sectional area of ​​the sample dielectric layer can be determined according to the index of the element to obtain the target position of the sample dielectric layer; then, the target position of the sample resonance layer is determined according to the preset position correspondence relationship between the sample dielectric layer and the sample resonance layer, the cross-sectional side length of the sample resonance layer, and the target position of the sample dielectric layer; then, the height of the sample dielectric layer corresponding to the target position of the sample dielectric layer and the height of the sample resonance layer corresponding to the target position of the sample resonance layer are calculated to obtain the value of the element.

[0054] In this embodiment, by obtaining the sample harmonic mapping matrix, the dimensionality reduction of the original data is achieved, and at the same time, a data basis is provided for the subsequent determination of the target sample input data.

[0055] Step 140: Determine the sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample medium layer as target sample input data.

[0056] Specifically, the target sample input data refers to a data set consisting of a sample dielectric harmonic mapping matrix, a height and a cross-sectional side length of a sample substrate layer, and a cross-sectional side length of a sample dielectric layer, which serves as training data at the input end of the absorption spectrum prediction model.

[0057] In this embodiment, the sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample dielectric layer are determined as target sample input data, which reduces the amount of input data and further reduces the computational complexity of subsequent training, thereby shortening the time for subsequent model training and improving the training efficiency of subsequent models.

[0058] Step 150: Determine the target sample output data and the target sample input data as the target sample data.

[0059] Specifically, the target sample data is used to train an absorption spectrum prediction model, and the absorption spectrum prediction model is used to predict the absorption spectrum of the target all-dielectric broadband absorber.

[0060] In a specific implementation, after obtaining the target sample output data and the target sample input data, the target sample output data and the target sample input data are data aligned, that is, ensuring that the input features and output values ​​of each sample appear in pairs and these features and values ​​can uniquely identify the sample. Then, the target sample output data and the target sample input data after data alignment are integrated into the data structure for storing the target sample data to obtain the target sample data.

[0061] In this embodiment, since the target sample input data has achieved dimensionality reduction processing relative to the original data, the amount of input data has been effectively reduced. On this basis, the target sample output data and the target sample input data are used as target sample data, and the absorption spectrum prediction model is trained with the target sample data, which not only reduces the time required for model training but also improves the training efficiency of the model.

[0062] The data acquisition method provided by the embodiment of the present invention first obtains the sample absorption spectrum corresponding to the sample all-dielectric broadband absorber, and obtains the sample design parameters of the sample all-dielectric broadband absorber, which provides a data basis for determining the target sample output data and the target sample input data. Then, the sample absorption spectrum is sampled at equal intervals according to the sample working frequency to obtain the target sample output data, which effectively reduces the data volume of the target sample output data, not only laying a solid foundation for the subsequent generation of the target sample data, but also significantly improving the training speed of the subsequent model. Then, the size of the sample harmonic mapping matrix of the sample all-dielectric broadband absorber is determined according to the preset grid density and the cross-sectional side length of the sample dielectric layer, and the value of each element in the sample harmonic mapping matrix is ​​determined according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer, and the sample harmonic mapping matrix is ​​obtained, which realizes the dimensionality reduction of the original data and provides a data basis for the subsequent determination of the target sample input data. Then, the sample harmonic mapping matrix, the height and cross-sectional side length of the sample substrate layer, and the cross-sectional side length of the sample dielectric layer are determined as the target sample input data, which reduces the input data volume, thereby reducing the computational complexity of the subsequent training, thereby shortening the time of the subsequent model training and improving the training efficiency of the subsequent model. Finally, the target sample output data and the target sample input data are determined as the target sample data, and the absorption spectrum prediction model is trained with the target sample data, which reduces the model training time and improves the model training efficiency. Therefore, the present invention solves the problem that the training time of the absorption spectrum prediction model of the existing all-dielectric broadband absorber is too long, resulting in low overall efficiency.

[0063] Figure 2 A flowchart of another data acquisition method provided by an embodiment of the present invention, which is specific based on the above embodiment. In this embodiment, the method may also include:

[0064] Step 210: Obtain a sample absorption spectrum corresponding to the sample all-dielectric broadband absorber, and obtain sample design parameters of the sample all-dielectric broadband absorber.

[0065] Step 211: Sample the sample absorption spectrum at equal intervals according to the sample operating frequency to obtain target sample output data.

[0066] Step 212: Determine the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to the ratio of the cross-sectional side length of the sample dielectric layer to the preset grid density.

[0067] Specifically, the number of rows and columns of the sample dielectric harmonic mapping matrix can be determined based on the ratio of the cross-sectional side length of the sample dielectric layer and the preset grid density. Since the cross-sectional area of ​​the sample dielectric layer is a square, the number of rows and columns of the sample dielectric harmonic mapping matrix are equal. Therefore, the size of the sample dielectric harmonic mapping matrix can be determined to be the square of (cross-sectional side length of the sample dielectric layer / preset grid density).

[0068] In this embodiment, by determining the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber, a data basis is provided for subsequently obtaining the sample dielectric harmonic mapping matrix.

[0069] Step 213: For the current element, determine the position of the current element on the cross section of the sample medium layer according to the index of the current element, and determine the target position of the sample medium layer.

[0070] Specifically, the index refers to an identifier used to locate the position of an element in the matrix, including a row index and a column index. The target position of the sample medium layer refers to the position coordinates determined according to the index of the current element on the cross section of the sample medium layer.

[0071] In the specific implementation, first determine the corresponding relationship between the index and the coordinate. For this purpose, the Cartesian coordinate system can be used to describe the cross-sectional position of the sample medium layer. In this coordinate system, the lower left corner of the cross section can be used as the origin, the horizontal direction is the x-axis, and the vertical direction is the y-axis. The row index is set to correspond to the coordinate information in the y-axis direction, and the column index is set to correspond to the coordinate information in the x-axis direction. Then determine the actual length represented by each grid (corresponding to an element of the matrix) on the cross section of the sample medium layer. In practical applications, it can be determined that the actual length represented by each grid = the cross-sectional side length of the sample medium layer / the number of rows (or columns) of the sample medium harmonic mapping matrix. After that, for the current element, the position of the current element on the cross section of the sample medium layer can be determined according to the index of the current element, thereby obtaining the target position of the sample medium layer. Specifically, it can be determined that the coordinate of the target position of the sample medium layer in the x-axis direction is the column index multiplied by the actual length represented by each grid, and the coordinate of the target position of the sample medium layer in the y-axis direction is the row index multiplied by the actual length represented by each grid.

[0072] In this embodiment, by determining the target position of the sample medium layer, a data basis is provided for subsequently determining the value of the current element.

[0073] Step 214 : determining the target position of the sample resonance layer according to the position correspondence between the sample dielectric layer and the sample resonance layer, the cross-sectional side length of the sample resonance layer, and the target position of the sample dielectric layer.

[0074] Specifically, the position correspondence between the sample medium layer and the sample resonance layer refers to the conversion relationship between the coordinates on the cross section of the sample medium layer and the coordinates on the cross section of the sample resonance layer. The target position of the sample resonance layer refers to the position of the current element on the sample resonance layer determined based on the position correspondence between the sample medium layer and the sample resonance layer, the side length of the cross section of the sample resonance layer, and the target position of the sample medium layer.

[0075] In a specific implementation, a Cartesian coordinate system can be first used to describe the cross-sectional position of the sample resonance layer. In this coordinate system, the lower left corner of the cross section can be selected as the origin, the horizontal direction is defined as the x-axis, the vertical direction is defined as the y-axis, and the range of values ​​of the coordinates on the cross section of the sample resonance layer is determined according to the cross-sectional side length of the sample resonance layer. Then, the position correspondence between the sample dielectric layer and the sample resonance layer is determined according to the relative position information of the lower left corner of the cross section of the sample dielectric layer and the sample resonance layer. Thereafter, the target position of the sample resonance layer is determined according to the position correspondence between the sample dielectric layer and the sample resonance layer and the target position of the sample dielectric layer, and then it is determined whether the coordinates of the target position of the sample resonance layer exceed the aforementioned range of values ​​of the coordinates determined. If exceeded, the target position of the sample resonance layer is updated to (-1, -1). Otherwise, the target position of the sample resonance layer is not updated.

[0076] In this embodiment, by determining the target position of the sample resonance layer, a data basis is provided for subsequently determining the value of the current element.

[0077] Step 215 : Calculate the sum of the height of the sample dielectric layer corresponding to the target position of the sample dielectric layer and the height of the sample resonant layer corresponding to the target position of the sample resonant layer to obtain the value of the current element.

[0078] In the specific implementation, in actual application, it can be determined that the value of the current element = the height of the sample dielectric layer corresponding to the target position of the sample dielectric layer + the height of the sample resonant layer corresponding to the target position of the sample resonant layer. In addition, in this embodiment, the base layer, dielectric layer and resonant layer of the all-dielectric broadband absorber are made of the same dielectric material and the cross-sections of the three layers along the height direction are all squares with fixed side lengths. Therefore, the height of each position in the sample dielectric layer is a fixed value, that is, the height of the sample dielectric layer; the height of each position in the sample resonant layer except for the position (-1, -1) is also a fixed value, that is, the height of the sample resonant layer. It should be noted that if the target position of the sample resonant layer is (-1, -1), the height of the sample resonant layer corresponding to the target position of the sample resonant layer is zero.

[0079] In this embodiment, by obtaining the value of the current element, a data basis is provided for obtaining the sample meso-harmonic mapping matrix later.

[0080] Step 216: Obtain a sample median harmonic mapping matrix.

[0081] In a specific implementation, after obtaining the size of the sample median harmonic mapping matrix and the value of each element in the sample median harmonic mapping matrix, the sample median harmonic mapping matrix can be completely constructed, that is, the sample median harmonic mapping matrix is ​​obtained.

[0082] Step 217: Determine the mean and variance of the values ​​corresponding to each element in the sample harmonic mapping matrix.

[0083] In the specific implementation, the values ​​corresponding to each element can be added up first to obtain the sum of the values ​​corresponding to each element, and then the ratio of the sum to the total number of elements can be calculated to obtain the mean of the values ​​corresponding to each element. After that, for each element in the sample harmonic mapping matrix, the difference between its value and the mean is calculated, and then these differences are squared to obtain the square of the difference between each element and the mean. Then the squares of the differences between all elements and the mean are added to obtain the sum of squares. Finally, the ratio of the sum of squares to the total number of elements is calculated to obtain the variance of the values ​​corresponding to each element.

[0084] Step 218: normalize the sample median harmonic mapping matrix according to the variance and the mean to obtain an updated sample median harmonic mapping matrix.

[0085] In the specific implementation, for each element in the sample harmonic mapping matrix, the mean is first subtracted from its value, and then divided by the variance. The above operations can complete the normalization of the sample harmonic mapping matrix, and then obtain the updated sample harmonic mapping matrix.

[0086] In this embodiment, the sample median harmonic mapping matrix is ​​normalized according to the variance and the mean to obtain an updated sample median harmonic mapping matrix, thereby improving data quality.

[0087] Step 219: determine the updated sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample dielectric layer as target sample input data.

[0088] Step 220: Determine the target sample output data and the target sample input data as the target sample data.

[0089] Furthermore, after the target sample output data and the target sample input data are determined as the target sample data, it also includes: inputting the target sample data as training data into the back propagation model, training the back propagation model, and calculating the loss function; optimizing the back propagation model according to the loss function until the preset optimization conditions are met, thereby obtaining an absorption spectrum prediction model.

[0090] Specifically, the preset optimization condition refers to the loss function value reaching a certain threshold or the number of training iterations reaching a certain number. The loss function refers to a function that measures the difference between the model prediction result and the actual result.

[0091] In a specific implementation, after determining the target sample data, the target sample data can be cleaned and preprocessed to ensure that they meet the input requirements of the back propagation model, and then the target sample output data is used as training data to train the back propagation model. Specifically, the target sample input data in the target sample data is used as the input of the model, and the target sample output data is used as the expected output of the model to start training the back propagation model. During the training process, the model will calculate the output result according to the current parameters, and then calculate the loss function according to the output result and the actual target sample output data. Then determine whether the preset optimization conditions are met (such as the loss function is less than the preset threshold). If not, the back propagation model is optimized according to the loss function until the preset optimization conditions are met to obtain an absorption spectrum prediction model. In addition, the processor used in the training process can be a central processing unit (CPU) and / or a graphics processing unit (GPU).

[0092] In this embodiment, through the above steps, the training time is reduced and the speed of obtaining the absorption spectrum prediction model is increased.

[0093] In one embodiment, the structure of the back propagation model includes an input layer, an output layer and two hidden layers.

[0094] In addition, in order to improve the quality of the back-propagation model, the relationship between the number of nodes in the input layer, output layer, and hidden layer of the back-propagation model can satisfy the following formula:

[0095]

[0096] Among them, s represents the number of nodes in the hidden layer, n represents the number of nodes in the output layer, and m represents the number of nodes in the input layer.

[0097] Furthermore, after obtaining the absorption spectrum prediction model, it also includes: obtaining target geometric parameters of the target all-dielectric broadband absorber, and determining a target dielectric-harmonic mapping matrix of the target all-dielectric broadband absorber according to a preset grid density and the height and cross-sectional side length of the target dielectric layer and the height and cross-sectional side length of the target resonant layer; inputting the target dielectric-harmonic mapping matrix, the height and cross-sectional side length of the target substrate layer and the cross-sectional side length of the target dielectric layer into the absorption spectrum prediction model to obtain a target absorption spectrum of the target all-dielectric broadband absorber.

[0098] Specifically, the target all-dielectric broadband absorber refers to the all-dielectric broadband absorber whose absorption spectrum needs to be predicted in practical applications. The target geometric parameters include the height and cross-sectional side length of the target substrate layer, target dielectric layer and target resonant layer of the target all-dielectric broadband absorber.

[0099] In a specific implementation, the target geometric parameters of the target all-dielectric broadband absorber can be obtained from a database storing the all-dielectric broadband absorbers whose absorption spectra are to be predicted, and then the target dielectric-harmonic mapping matrix of the target all-dielectric broadband absorber is determined according to the preset grid density and the height and cross-sectional side length of the target dielectric layer and the height and cross-sectional side length of the target resonant layer. Thereafter, the target dielectric-harmonic mapping matrix, the height and cross-sectional side length of the target substrate layer, and the cross-sectional side length of the target dielectric layer are input into the absorption spectrum prediction model to obtain the target absorption spectrum of the target all-dielectric broadband absorber.

[0100] In this embodiment, through the above steps, the target absorption spectrum of the target all-dielectric broadband absorber is predicted.

[0101] The data acquisition method provided by the embodiment of the present invention first obtains the sample absorption spectrum corresponding to the sample all-dielectric broadband absorber, and obtains the sample design parameters of the sample all-dielectric broadband absorber, which provides a data basis for determining the target sample output data and the target sample input data. Then, the sample absorption spectrum is sampled at equal intervals according to the sample working frequency to obtain the target sample output data, which effectively reduces the data volume of the target sample output data, not only laying a solid foundation for the subsequent generation of the target sample data, but also significantly improving the training speed of the subsequent model. Then, according to the ratio of the cross-sectional side length of the sample dielectric layer to the preset grid density, the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber is determined. For the current element, the position of the current element on the cross-sectional surface of the sample dielectric layer is determined according to the index of the current element, and the target position of the sample dielectric layer is determined. The target position of the sample resonant layer is determined according to the position correspondence between the sample dielectric layer and the sample resonant layer, the cross-sectional side length of the sample resonant layer and the target position of the sample dielectric layer. The height of the sample dielectric layer corresponding to the target position of the sample dielectric layer and the height of the sample resonant layer corresponding to the target position of the sample resonant layer are calculated to obtain the value of the current element. The sample harmonic mapping matrix is ​​obtained, which realizes the dimensionality reduction of the original data and provides a data basis for the subsequent determination of the target sample input data. Then the mean and variance of the values ​​corresponding to each element in the sample harmonic mapping matrix are determined. The sample harmonic mapping matrix is ​​normalized according to the variance and the mean to obtain an updated sample harmonic mapping matrix, thereby improving the data quality. The updated sample harmonic mapping matrix, the height and cross-sectional side length of the sample substrate layer, and the cross-sectional side length of the sample dielectric layer are then determined as the target sample input data, thereby reducing the amount of input data, thereby reducing the computational complexity of subsequent training, thereby shortening the time for subsequent model training, and improving the training efficiency of subsequent models. Finally, the target sample output data and the target sample input data are determined as the target sample data, and the absorption spectrum prediction model is trained with the target sample data, thereby reducing the time for model training and improving the training efficiency of the model. Therefore, the present invention solves the problem that the training time of the existing absorption spectrum prediction model of the all-dielectric broadband absorber is too long, resulting in overall low efficiency.

[0102] Figure 3 A structural schematic diagram of a data acquisition device provided in an embodiment of the present invention. The device and the data acquisition methods of the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiments of the data acquisition device, reference can be made to the embodiments of the above-mentioned data acquisition methods.

[0103] like Figure 3 As shown, the device comprises:

[0104] An acquisition module 310 is used to acquire a sample absorption spectrum corresponding to a sample all-dielectric broadband absorber, and acquire sample design parameters of the sample all-dielectric broadband absorber, wherein the sample design parameters include a sample operating frequency and sample geometric parameters of the sample all-dielectric broadband absorber; the sample geometric parameters include a height and a cross-sectional side length of a sample base layer, a sample dielectric layer, and a sample resonant layer of the sample all-dielectric broadband absorber;

[0105] An output data determination module 320 is used to perform equal-interval sampling on the sample absorption spectrum according to the sample operating frequency to obtain target sample output data;

[0106] A matrix determination module 330 is used to determine the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to a preset grid density and the cross-sectional side length of the sample dielectric layer, and to determine the value of each element in the sample dielectric harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer, so as to obtain the sample dielectric harmonic mapping matrix;

[0107] An input data determination module 340 is used to determine the sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample dielectric layer as target sample input data;

[0108] The target data determination module 350 is used to determine the target sample output data and the target sample input data as target sample data, wherein the target sample data is used to train an absorption spectrum prediction model, and the absorption spectrum prediction model is used to predict the absorption spectrum of a target all-dielectric broadband absorber.

[0109] Based on the above embodiment, the matrix determination module 330 determines the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to the preset grid density and the cross-sectional side length of the sample dielectric layer, including:

[0110] The size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber is determined according to the ratio of the cross-sectional side length of the sample dielectric layer to the preset grid density.

[0111] Based on the above embodiment, the matrix determination module 330 determines the value of each element in the sample dielectric-harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer, including:

[0112] For a current element, determining a position of the current element on a cross section of the sample medium layer according to an index of the current element, and determining a target position of the sample medium layer;

[0113] Determine a target position of the sample resonance layer according to a position correspondence between the sample dielectric layer and the sample resonance layer, a side length of a cross section of the sample resonance layer, and a target position of the sample dielectric layer;

[0114] The sum of the height of the sample dielectric layer corresponding to the target position of the sample dielectric layer and the height of the sample resonant layer corresponding to the target position of the sample resonant layer is calculated to obtain the value of the current element.

[0115] Based on the above embodiment, the device further includes:

[0116] A normalization module is used to determine the mean and variance of the values ​​corresponding to each element in the sample harmonic mapping matrix after obtaining the sample harmonic mapping matrix; and normalize the sample harmonic mapping matrix according to the variance and the mean to obtain an updated sample harmonic mapping matrix.

[0117] Based on the above embodiment, the device further includes:

[0118] A training module is used to input the target sample output data and the target sample input data as training data into a back propagation model after determining the target sample output data and the target sample input data as target sample data, perform model training on the back propagation model, and calculate a loss function; perform model optimization on the back propagation model according to the loss function until a preset optimization condition is met, thereby obtaining the absorption spectrum prediction model.

[0119] Based on the above embodiment, the device further includes:

[0120] A module is used to obtain target geometric parameters of a target all-dielectric broadband absorber after obtaining the absorption spectrum prediction model, wherein the target geometric parameters include the height and cross-sectional side length of a target substrate layer, a target dielectric layer and a target resonant layer of the target all-dielectric broadband absorber; and determine a target dielectric-harmonic mapping matrix of the target all-dielectric broadband absorber according to the preset grid density and the height and cross-sectional side length of the target dielectric layer and the height and cross-sectional side length of the target resonant layer; and input the target dielectric-harmonic mapping matrix, the height and cross-sectional side length of the target substrate layer and the cross-sectional side length of the target dielectric layer into the absorption spectrum prediction model to obtain a target absorption spectrum of the target all-dielectric broadband absorber.

[0121] Based on the above embodiment, the structure of the back propagation model includes an input layer, an output layer and two hidden layers.

[0122] The data acquisition device provided in the embodiment of the present invention can execute the data acquisition method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0123] It is worth noting that in the embodiment of the above-mentioned data acquisition device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0124] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4 A block diagram of an exemplary electronic device 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The electronic device 4 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0125] like Figure 4 As shown, the electronic device 4 is in the form of a general purpose computing electronic device. The components of the electronic device 4 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0126] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0127] The electronic device 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 4, including volatile and non-volatile media, removable and non-removable media.

[0128] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0129] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0130] The electronic device 4 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the electronic device 4, and / or any device that enables the electronic device 4 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 4 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. Figure 4 As shown, the network adapter 20 communicates with other modules of the electronic device 4 via the bus 18. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 4, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0131] The processing unit 16 executes various functional applications and page displays by running the programs stored in the system memory 28, for example, implementing the data acquisition method provided in the embodiment of the present invention, which includes:

[0132] Obtaining a sample absorption spectrum corresponding to a sample all-dielectric broadband absorber, and obtaining sample design parameters of the sample all-dielectric broadband absorber, wherein the sample design parameters include a sample operating frequency and sample geometric parameters of the sample all-dielectric broadband absorber; the sample geometric parameters include the height and cross-sectional side length of a sample base layer, a sample dielectric layer, and a sample resonant layer of the sample all-dielectric broadband absorber;

[0133] Sampling the sample absorption spectrum at equal intervals according to the sample operating frequency to obtain target sample output data;

[0134] Determine the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to the preset grid density and the cross-sectional side length of the sample dielectric layer, and determine the value of each element in the sample dielectric harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer, to obtain the sample dielectric harmonic mapping matrix;

[0135] Determine the sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample medium layer as target sample input data;

[0136] The target sample output data and the target sample input data are determined as target sample data, wherein the target sample data is used for training an absorption spectrum prediction model, and the absorption spectrum prediction model is used to predict the absorption spectrum of a target all-dielectric broadband absorber.

[0137] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the data acquisition method provided by any embodiment of the present invention.

[0138] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, for example, a data acquisition method provided by an embodiment of the present invention is implemented. The method includes:

[0139] Obtaining a sample absorption spectrum corresponding to a sample all-dielectric broadband absorber, and obtaining sample design parameters of the sample all-dielectric broadband absorber, wherein the sample design parameters include a sample operating frequency and sample geometric parameters of the sample all-dielectric broadband absorber; the sample geometric parameters include the height and cross-sectional side length of a sample base layer, a sample dielectric layer, and a sample resonant layer of the sample all-dielectric broadband absorber;

[0140] Sampling the sample absorption spectrum at equal intervals according to the sample operating frequency to obtain target sample output data;

[0141] Determine the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to the preset grid density and the cross-sectional side length of the sample dielectric layer, and determine the value of each element in the sample dielectric harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer, to obtain the sample dielectric harmonic mapping matrix;

[0142] Determine the sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample medium layer as target sample input data;

[0143] The target sample output data and the target sample input data are determined as target sample data, wherein the target sample data is used for training an absorption spectrum prediction model, and the absorption spectrum prediction model is used to predict the absorption spectrum of a target all-dielectric broadband absorber.

[0144] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0145] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0146] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0147] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0148] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0149] In addition, the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of national laws and regulations.

[0150] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A data acquisition method, characterized in that: include: Obtaining a sample absorption spectrum corresponding to a sample all-dielectric broadband absorber, and obtaining sample design parameters of the sample all-dielectric broadband absorber, wherein the sample design parameters include a sample operating frequency and sample geometric parameters of the sample all-dielectric broadband absorber; the sample geometric parameters include the height and cross-sectional side length of a sample base layer, a sample dielectric layer, and a sample resonant layer of the sample all-dielectric broadband absorber; Performing equal-interval sampling on the sample absorption spectrum according to the sample operating frequency to obtain target sample output data; Determine the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to the preset grid density and the cross-sectional side length of the sample dielectric layer, and determine the value of each element in the sample dielectric harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer, to obtain the sample dielectric harmonic mapping matrix; Determine the sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample medium layer as target sample input data; The target sample output data and the target sample input data are determined as target sample data, wherein the target sample data is used for training an absorption spectrum prediction model, and the absorption spectrum prediction model is used to predict the absorption spectrum of a target all-dielectric broadband absorber.

2. The data acquisition method according to claim 1, characterized in that: Determining the size of the sample dielectric-harmonic mapping matrix of the sample all-dielectric broadband absorber according to the preset grid density and the cross-sectional side length of the sample dielectric layer includes: The size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber is determined according to the ratio of the cross-sectional side length of the sample dielectric layer to the preset grid density.

3. The data acquisition method according to claim 1, characterized in that: Determining the value of each element in the sample dielectric-harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer includes: For a current element, determining a position of the current element on a cross section of the sample medium layer according to an index of the current element, and determining a target position of the sample medium layer; Determine a target position of the sample resonance layer according to a position correspondence between the sample dielectric layer and the sample resonance layer, a side length of a cross section of the sample resonance layer, and a target position of the sample dielectric layer; The sum of the height of the sample dielectric layer corresponding to the target position of the sample dielectric layer and the height of the sample resonant layer corresponding to the target position of the sample resonant layer is calculated to obtain the value of the current element.

4. The data acquisition method according to claim 1, characterized in that: After obtaining the sample media harmonic mapping matrix, it also includes: Determine the mean and variance of the values ​​corresponding to each element in the sample harmonic mapping matrix; The sample meso-harmonic mapping matrix is ​​normalized according to the variance and the mean to obtain an updated sample meso-harmonic mapping matrix.

5. The data acquisition method according to claim 1, characterized in that: After determining the target sample output data and the target sample input data as target sample data, the method further includes: Input the target sample data as training data into a back propagation model, perform model training on the back propagation model, and calculate a loss function; The back propagation model is optimized according to the loss function until a preset optimization condition is met to obtain the absorption spectrum prediction model.

6. The data acquisition method according to claim 5, characterized in that: After obtaining the absorption spectrum prediction model, the method further includes: Obtaining target geometric parameters of a target all-dielectric broadband absorber, wherein the target geometric parameters include the height and cross-sectional side length of a target substrate layer, a target dielectric layer, and a target resonant layer of the target all-dielectric broadband absorber; and determining a target dielectric-harmonic mapping matrix of the target all-dielectric broadband absorber according to the preset grid density and the height and cross-sectional side length of the target dielectric layer and the height and cross-sectional side length of the target resonant layer; The target dielectric harmonic mapping matrix, the height and cross-sectional side length of the target substrate layer, and the cross-sectional side length of the target dielectric layer are input into the absorption spectrum prediction model to obtain the target absorption spectrum of the target all-dielectric broadband absorber.

7. The data acquisition method according to claim 5, characterized in that: The structure of the back propagation model includes an input layer, an output layer and two hidden layers.

8. A data acquisition device, characterized in that: include: An acquisition module, used to acquire a sample absorption spectrum corresponding to a sample all-dielectric broadband absorber, and acquire sample design parameters of the sample all-dielectric broadband absorber, wherein the sample design parameters include a sample operating frequency and sample geometric parameters of the sample all-dielectric broadband absorber; the sample geometric parameters include a height and a cross-sectional side length of a sample base layer, a sample dielectric layer, and a sample resonant layer of the sample all-dielectric broadband absorber; An output data determination module, used for sampling the sample absorption spectrum at equal intervals according to the sample operating frequency to obtain target sample output data; a matrix determination module, used to determine the size of the sample dielectric harmonic mapping matrix of the sample all-dielectric broadband absorber according to a preset grid density and the cross-sectional side length of the sample dielectric layer, and to determine the value of each element in the sample dielectric harmonic mapping matrix according to the height of the sample dielectric layer, the height of the sample resonant layer, and the cross-sectional side length of the sample resonant layer, so as to obtain the sample dielectric harmonic mapping matrix; An input data determination module, used to determine the sample dielectric harmonic mapping matrix, the height and cross-sectional side length of the sample base layer, and the cross-sectional side length of the sample dielectric layer as target sample input data; The target data determination module is used to determine the target sample output data and the target sample input data as target sample data, wherein the target sample data is used to train an absorption spectrum prediction model, and the absorption spectrum prediction model is used to predict the absorption spectrum of a target all-dielectric broadband absorber.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the data acquisition method described in any one of claims 1 to 7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the data acquisition method described in any one of claims 1 to 7 when executed by a computer processor.

Images