Electromagnetic map reconstruction method and device, equipment, storage medium and program product

Abstract

The invention relates to an electromagnetic map reconstruction method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring a sparse electromagnetic map of a target area in a current sensing period through a sensing satellite; determining ephemeris information corresponding to the sparse electromagnetic map; and according to the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map and an electromagnetic map reconstruction model, determining a target electromagnetic map at the last sensing moment in the current sensing period, so that the target electromagnetic map at the last sensing moment in the current sensing period can be obtained under the condition of limited communication satellite sensing resources. The time correlation of the historical electromagnetic situation is learned based on the electromagnetic map reconstruction model, so that the electromagnetic map reconstruction model can realize electromagnetic map reconstruction, and the precision and reliability of electromagnetic map reconstruction are improved.

Description

Technical Field

[0001] This application relates to the field of satellite communication technology, and in particular to an electromagnetic map reconstruction method, apparatus, device, storage medium, and program product. Background Technology

[0002] Electromagnetic maps, as a technological means of presenting electromagnetic situation in geospatial form, can intuitively reflect the spectrum usage in a certain area, becoming an important foundation for supporting frequency sharing and collaborative communication within a satellite constellation. However, limited by resource constraints within a single sensing cycle, communication satellites can typically only perform sparse sensing of the target area, making it difficult to directly acquire a complete electromagnetic map. Therefore, how to reconstruct electromagnetic maps based on sparsely sampled data has become a key issue in satellite spectrum situational awareness.

[0003] Currently, electromagnetic maps are typically reconstructed based on interpolation algorithms, but this method suffers from low reconstruction accuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide an electromagnetic map reconstruction method, apparatus, device, storage medium, and program product to address the aforementioned technical problems.

[0005] Firstly, this application provides an electromagnetic map reconstruction method. The method includes:

[0006] Acquire sparse electromagnetic maps of the target area within the current sensing period using sensing satellites;

[0007] Determine the ephemeris information corresponding to the sparse electromagnetic map;

[0008] Based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model, the target electromagnetic map for the last sensing moment within the current sensing cycle is determined.

[0009] In one embodiment, the method further includes:

[0010] Obtain electromagnetic map samples for each historical sensing moment and ephemeris information samples corresponding to the electromagnetic map samples;

[0011] Based on the electromagnetic map samples and ephemeris information samples of each of the historical sensing moments, the neural network is trained to obtain the electromagnetic map reconstruction model.

[0012] In one embodiment, acquiring electromagnetic map samples at each historical sensing moment and ephemeris information samples corresponding to the electromagnetic map samples includes:

[0013] A simulation scenario is constructed based on preset simulation parameters;

[0014] Based on a preset data format, electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment in the simulation scenario are obtained.

[0015] In one embodiment, the preset simulation parameters include at least one of the following: target area range, sensing frequency, communication constellation parameters, interference constellation parameters, sensing bandwidth, sensing antenna type, and electromagnetic map resolution.

[0016] In one embodiment, the step of training the neural network based on electromagnetic map samples and ephemeris information samples at each of the historical sensing times to obtain the electromagnetic map reconstruction model includes:

[0017] Select a predetermined number of consecutive historical perception moments from each of the aforementioned historical perception moments;

[0018] The electromagnetic map samples and ephemeris information samples corresponding to the preset number of historical sensing moments are used as input features, and the complete electromagnetic map of the last historical sensing moment in the preset number of historical sensing moments is used as a label to train the neural network to obtain the electromagnetic map reconstruction model; the complete electromagnetic map is obtained by reconstructing the sparse electromagnetic map corresponding to the last historical sensing moment.

[0019] In one embodiment, the method further includes:

[0020] The target electromagnetic map is denormalized to obtain a visual electromagnetic map, which is then displayed.

[0021] Secondly, this application also provides an electromagnetic map reconstruction apparatus. The apparatus includes:

[0022] The first acquisition module is used to acquire a sparse electromagnetic map of the target area within the current sensing period via sensing satellites.

[0023] The first determining module is used to determine the ephemeris information corresponding to the sparse electromagnetic map;

[0024] The reconstruction module is used to determine the target electromagnetic map at the last sensing moment in the current sensing cycle based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model.

[0025] Thirdly, this application also provides a computer device, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of any of the above methods.

[0026] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above methods.

[0027] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above methods.

[0028] The aforementioned electromagnetic map reconstruction method, apparatus, equipment, storage medium, and program product acquire a sparse electromagnetic map of a target area within the current sensing period via a sensing satellite; determine the ephemeris information corresponding to the sparse electromagnetic map; and, based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model, determine the target electromagnetic map at the last sensing moment within the current sensing period. This allows for learning the temporal correlation of historical electromagnetic situations based on the electromagnetic map reconstruction model, even with limited communication satellite sensing resources, thus enabling the electromagnetic map reconstruction model to achieve electromagnetic map reconstruction and improving the accuracy and reliability of electromagnetic map reconstruction. Attached Figure Description

[0029] Figure 1 This is an application environment diagram of the electromagnetic map reconstruction method in one embodiment;

[0030] Figure 2 This is a flowchart illustrating an electromagnetic map reconstruction method provided in an embodiment of this application;

[0031] Figure 3 This is a flowchart illustrating a method for determining an electromagnetic map reconstruction model provided in an embodiment of this application;

[0032] Figure 4 This is a flowchart illustrating a training sample acquisition method provided in an embodiment of this application;

[0033] Figure 5 This is a flowchart illustrating another method for determining an electromagnetic map reconstruction model provided in an embodiment of this application;

[0034] Figure 6 This is a flowchart illustrating an electromagnetic map sparse reconstruction method provided in an embodiment of this application;

[0035] Figure 7 This is a schematic diagram of an electromagnetic map reconstruction result provided in an embodiment of this application;

[0036] Figure 8 This is a structural block diagram of an electromagnetic map reconstruction device provided in an embodiment of this application;

[0037] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0039] The electromagnetic map reconstruction method provided in this application can be applied to, for example... Figure 1 The application environment is shown. In this environment, the operations control center communicates with the sensing satellite via a gateway station. The sensing satellite acquires sparse electromagnetic maps using sparse sensing beams. The operations control center can be, but is not limited to, various computer devices, including servers. These servers can be standalone servers or a server cluster.

[0040] In one embodiment, such as Figure 2 As shown, Figure 2 This is a flowchart illustrating an electromagnetic map reconstruction method provided in an embodiment of this application. This method can be applied to... Figure 1 The operation control center in the system, the method includes the following steps:

[0041] S201 acquires a sparse electromagnetic map of the target area within the current sensing period using sensing satellites.

[0042] For example, a target area can be sensed by a sensing satellite, and the sparse electromagnetic map of each sensing moment in the current sensing period can be transmitted to the operation and control center through a gateway station, so that the operation and control center can obtain the sparse electromagnetic maps of the current sensing period.

[0043] Optionally, if the sensing satellite is a communication satellite that has been interfered with, its sensing resources are limited, so it cannot obtain a sparse electromagnetic map of every sensing moment in the current sensing period, but can only obtain a sparse electromagnetic map of some sensing moments in the current sensing period.

[0044] For example, if a perception cycle includes T perception moments, then the current perception cycle includes the current perception moment and the T-1 perception moments preceding the current perception moment.

[0045] S202, determine the ephemeris information corresponding to the sparse electromagnetic map.

[0046] Optionally, the operations control center can determine the location information of the interference constellation and the sensing satellite corresponding to each sparse electromagnetic map, and use the location information of the interference constellation and the sensing satellite corresponding to each sparse electromagnetic map as the ephemeris information corresponding to each sparse electromagnetic map.

[0047] S203, based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model, determine the target electromagnetic map for the last sensing moment within the current sensing cycle.

[0048] Optionally, the sparse electromagnetic maps and their corresponding ephemeris information can be preprocessed to ensure that the data format of each sparse electromagnetic map and its ephemeris information conforms to the input format requirements of the electromagnetic map reconstruction model. Then, the preprocessed sparse electromagnetic maps and their ephemeris information are used as input to the electromagnetic map reconstruction model to reconstruct the electromagnetic map based on the electromagnetic map reconstruction model, thereby obtaining the target electromagnetic map at the last sensing moment in the current sensing period, which is also the target electromagnetic map corresponding to the current sensing moment.

[0049] Alternatively, the above preprocessing can be, for example, normalization processing.

[0050] In one embodiment, the preprocessed electromagnetic map samples at each historical sensing moment and the corresponding ephemeris information samples of the electromagnetic map samples can be used as a training dataset. The neural network is trained based on this training dataset to obtain the aforementioned electromagnetic map reconstruction model.

[0051] In this embodiment, a sparse electromagnetic map of the target area within the current sensing period is acquired by a sensing satellite; ephemeris information corresponding to the sparse electromagnetic map is determined; and the target electromagnetic map at the last sensing moment within the current sensing period is determined based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model. This allows the electromagnetic map reconstruction model to learn the temporal correlation of historical electromagnetic situations based on the electromagnetic map reconstruction model, even with limited communication satellite sensing resources, thereby improving the accuracy and reliability of electromagnetic map reconstruction.

[0052] Reference Figure 3 , Figure 3 This is a flowchart illustrating a method for determining an electromagnetic map reconstruction model according to an embodiment of this application. Based on the above embodiment, the method further includes the following steps:

[0053] S301, acquire electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment.

[0054] Optionally, the actual electromagnetic maps acquired by the sensing satellite at each historical sensing moment, as well as the actual ephemeris information corresponding to each actual electromagnetic map, can be directly obtained, so that each actual electromagnetic map can be used as an electromagnetic map sample at each historical sensing moment, and each actual ephemeris information can be used as an ephemeris information sample at each historical sensing moment.

[0055] Alternatively, a simulation scenario can be constructed based on preset simulation parameters to obtain the simulated electromagnetic map at each historical sensing moment and the simulated ephemeris information corresponding to each simulated electromagnetic map under the simulation scenario, so that each simulated electromagnetic map can be used as an electromagnetic map sample at each historical sensing moment, and each simulated ephemeris information can be used as an ephemeris information sample at each historical sensing moment.

[0056] Alternatively, the actual electromagnetic map and the simulated electromagnetic map can be used together as the electromagnetic map sample, and the actual ephemeris information and the simulated ephemeris information can be used together as the ephemeris information sample.

[0057] S302, based on electromagnetic map samples and ephemeris information samples at each historical sensing moment, the neural network is trained to obtain an electromagnetic map reconstruction model.

[0058] Optionally, the electromagnetic map samples and ephemeris information samples at each historical sensing moment can be preprocessed, such as by normalization, and the preprocessed electromagnetic map samples and ephemeris information samples can be divided to obtain training sets and validation sets. The neural network can then be trained based on the training sets and validation sets to obtain an electromagnetic map reconstruction model.

[0059] For example, the neural network can be any network structure capable of learning the temporal correlations of sparse electromagnetic maps and ephemeris information at different times. For instance, it may include at least one of fully connected neural networks, convolutional neural networks, spatial attention networks, channel attention networks, temporal attention networks, residual networks, and long short-term memory networks.

[0060] Optionally, the training method used to train the neural network may include at least one of SGD (Stochastic Gradient Descent), Adam (Adaptive Moment Estimation), and RMSProp (Root Mean Square Propagation). The loss function may include at least one of MSE (Mean Squared Error) and MAE (Mean Absolute Error).

[0061] In this embodiment, electromagnetic map samples and corresponding ephemeris information samples at each historical sensing moment are obtained. Based on the electromagnetic map samples and ephemeris information samples at each historical sensing moment, the neural network is trained to obtain an electromagnetic map reconstruction model. This allows the model to learn the temporal correlation of historical electromagnetic situations when communication satellite sensing resources are limited, thereby enabling the electromagnetic map reconstruction model to achieve electromagnetic map reconstruction and improving the accuracy and reliability of electromagnetic map reconstruction.

[0062] Reference Figure 4, Figure 4 This is a flowchart illustrating a training sample acquisition method provided in an embodiment of this application. This embodiment relates to a possible implementation of how to acquire electromagnetic map samples at each historical sensing moment and the corresponding ephemeris information samples. Based on the above embodiment, S301 includes the following steps:

[0063] S401, construct a simulation scenario based on preset simulation parameters.

[0064] For example, preset simulation parameters such as target area range, sensing frequency, communication constellation parameters, interference constellation parameters, sensing bandwidth, sensing antenna type, and electromagnetic map resolution can be obtained. Based on these preset simulation parameters, a simulation scenario can be constructed to simulate a real sparse electromagnetic map acquisition scenario.

[0065] S402, based on a preset data format, acquires electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment in the simulation scenario.

[0066] Optionally, the data format of the sparse electromagnetic map and the data format of the ephemeris information can be determined according to the simulation scenario, that is, the aforementioned preset data format. Then, electromagnetic map samples and ephemeris information samples corresponding to the electromagnetic map samples at each historical sensing time in the preset data format under the simulation scenario can be obtained.

[0067] It should be noted that the above-mentioned preset data format is the data format of the sparse electromagnetic map and the corresponding ephemeris information acquired at each sensing moment that can be provided in the actual scenario.

[0068] In this embodiment, a simulation scenario is constructed based on preset simulation parameters; based on a preset data format, electromagnetic map samples and corresponding ephemeris information samples at each historical sensing moment in the simulation scenario are obtained. This enables the acquisition of data samples required for training through simulation, reducing the cost of acquiring training samples. Furthermore, the preset parameters can also simulate extreme scenarios that are difficult to reproduce, thereby improving the comprehensiveness and accuracy of training samples.

[0069] Reference Figure 5 , Figure 5 This is a flowchart illustrating another method for determining an electromagnetic map reconstruction model provided in this application. This embodiment relates to a possible implementation of training a neural network based on electromagnetic map samples and ephemeris information samples from various historical sensing moments to obtain an electromagnetic map reconstruction model. Based on the above embodiment, step S302 includes the following steps:

[0070] S501, Select a preset number of consecutive historical sensing moments from each historical sensing moment.

[0071] Optionally, the preset number is equal to the number of sensing moments contained in the current sensing cycle.

[0072] For example, if a sensing cycle includes T sensing moments, then T consecutive historical sensing moments can be randomly selected from each historical sensing moment as the time unit for one round of training. The neural network is trained using electromagnetic map samples and ephemeris information samples corresponding to the selected T consecutive historical sensing moments to obtain an electromagnetic map reconstruction model.

[0073] S502, the electromagnetic map samples and ephemeris information samples corresponding to a preset number of historical sensing moments are used as input features, and the complete electromagnetic map of the last historical sensing moment in the preset number of historical sensing moments is used as a label to train the neural network and obtain the electromagnetic map reconstruction model.

[0074] The complete electromagnetic map is obtained by reconstructing the sparse electromagnetic map corresponding to the last historical sensing moment.

[0075] Optionally, the electromagnetic map samples include complete electromagnetic maps for each historical sensing moment. Sparse sampling can be performed on these electromagnetic map samples to obtain sparse electromagnetic map samples. Each sparse electromagnetic map sample and its corresponding ephemeris information sample are used as input features to the neural network. Then, the complete electromagnetic map of the last historical sensing moment out of the selected T historical sensing moments can be obtained and used as a label. The input features and labels are divided into training and validation sets to train the neural network, resulting in an electromagnetic map reconstruction model.

[0076] In this embodiment, a predetermined number of consecutive historical sensing moments are selected from each historical sensing moment. The electromagnetic map samples and ephemeris information samples corresponding to the predetermined number of historical sensing moments are used as input features, and the complete electromagnetic map of the last historical sensing moment in the predetermined number of historical sensing moments is used as a label to train the neural network, thereby obtaining an electromagnetic map reconstruction model. This allows the model to learn the temporal correlation of historical electromagnetic situations based on the electromagnetic map reconstruction model when communication satellite sensing resources are limited, so that the electromagnetic map reconstruction model can realize electromagnetic map reconstruction and improve the accuracy and reliability of electromagnetic map reconstruction.

[0077] Based on the above embodiments, after obtaining the target electromagnetic map, the target electromagnetic map can be denormalized to convert its format into a visual format to obtain a visual electromagnetic map. This visual electromagnetic map can then be displayed, making it easier for users to intuitively view the reconstructed electromagnetic map and improving the practicality of the electromagnetic map reconstruction method.

[0078] Reference Figure 6 , Figure 6 This is a flowchart illustrating a sparse reconstruction method for electromagnetic maps provided in an embodiment of this application. The method includes the following steps:

[0079] S601 determines the preset simulation parameters based on the actual scenario and perception requirements.

[0080] S602, construct a simulation scenario and obtain electromagnetic map samples and ephemeris information samples at each historical sensing moment.

[0081] S603 determines the structure of the neural network to be trained based on the actual scenario and perception requirements.

[0082] S604. Determine the loss function and training method based on the structure and reconstruction requirements of the neural network to be trained.

[0083] S605, based on electromagnetic map samples and ephemeris information samples at each historical sensing moment, trains the neural network until convergence.

[0084] S606, acquire the sparse electromagnetic map of the target area within the current sensing period and the ephemeris information corresponding to the sparse electromagnetic map.

[0085] S607: Input the preprocessed sparse electromagnetic maps and ephemeris information into the electromagnetic map reconstruction model to obtain the target electromagnetic map.

[0086] S608 performs inverse normalization on the target electromagnetic map to obtain a visual electromagnetic map.

[0087] S609 formulates communication strategies based on a visual electromagnetic map to reduce the impact of interference.

[0088] To more clearly illustrate the beneficial effects of the embodiments of this application, the following is combined with... Figure 7 An example is provided. Figure 7 This is a schematic diagram of an electromagnetic map reconstruction result provided in an embodiment of this application.

[0089] For example, suppose there exists a low-Earth orbit (LEO) constellation B, consisting of 3600 satellites, coexisting with communication satellite A (i.e., a sensing satellite) at the same frequency. Communication satellite A is a medium-Earth orbit (MEO) satellite with a wide field of view. It utilizes communication gaps to perform electromagnetic situational awareness of the target area. A certain number of LEO constellation earth stations are randomly distributed within the area, communicating with LEO constellation B. The ground stations select the LEO satellites at their highest elevation angle for uplink transmission and, where possible, avoid switching satellites. The sensing area is divided into a grid. When communication satellite A has a view of the entire region of interest, sparse sensing and electromagnetic map reconstruction are performed. The preset simulation parameters are shown in Table 1 below.

[0090]

[0091] Table 1

[0092] First, based on preset simulation parameters, the sensing frequency was determined to be 29 GHz, the sensing period to be 1 second, and parameters such as sensing range, antenna type, and satellite orbit were confirmed. A simulation scenario was built according to these preset parameters, and multiple simulations were performed to obtain complete electromagnetic maps under different times, numbers of earth stations, and distributions of earth stations, thus constructing electromagnetic map samples. Based on scenario requirements, the neural network structure was determined to be a hybrid 2D and 3D convolutional network, and temporal attention, Convolutional Block Attention Module (CBAM), and residuals were added to improve learning efficiency. The neural network loss function was MSE (Mean Squared Error), and the training method was Adam (Adaptive Moment Estimation).

[0093] The electromagnetic map samples are normalized and sparsely sampled to obtain sparse electromagnetic map samples. The T sparse electromagnetic map samples are used as input features, and the Tth complete electromagnetic map is used as the label. The neural network is trained until convergence.

[0094] Reselect the number and location distribution of Earth stations for constellation B, repeat the process of obtaining the training set to obtain the test set, and determine the test results based on the test set. These test results can be used as follows: Figure 7 As shown in Table 2:

[0095]

[0096] Table 2

[0097] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0098] Based on the same inventive concept, this application also provides an electromagnetic map reconstruction apparatus for implementing the electromagnetic map reconstruction method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more electromagnetic map reconstruction apparatus embodiments provided below can be found in the limitations of the electromagnetic map reconstruction method described above, and will not be repeated here.

[0099] In one embodiment, such as Figure 8 As shown, Figure 8 This is a structural block diagram of an electromagnetic map reconstruction device provided in an embodiment of this application. The device 800 includes:

[0100] The first acquisition module 801 is used to acquire a sparse electromagnetic map of the target area within the current sensing period via a sensing satellite.

[0101] The first determining module 802 is used to determine the ephemeris information corresponding to the sparse electromagnetic map.

[0102] The reconstruction module 803 is used to determine the target electromagnetic map at the last sensing moment in the current sensing cycle based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model.

[0103] In one embodiment, the device 800 further includes:

[0104] The second acquisition module is used to acquire electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment.

[0105] The training module is used to train the neural network based on electromagnetic map samples and ephemeris information samples at each historical sensing time to obtain an electromagnetic map reconstruction model.

[0106] In one embodiment, the second acquisition module includes:

[0107] The building unit is used to construct a simulation scenario based on preset simulation parameters.

[0108] The acquisition unit is used to acquire electromagnetic map samples and corresponding ephemeris information samples at each historical sensing moment in the simulation scenario based on a preset data format.

[0109] In one embodiment, the preset simulation parameters include at least one of the following: target area range, sensing frequency, communication constellation parameters, interference constellation parameters, sensing bandwidth, sensing antenna type, and electromagnetic map resolution.

[0110] In one embodiment, the training module includes:

[0111] The selection unit is used to select a preset number of consecutive historical sensing moments from each historical sensing moment.

[0112] The training unit is used to train the neural network with electromagnetic map samples and ephemeris information samples corresponding to a preset number of historical sensing moments as input features, and the complete electromagnetic map of the last historical sensing moment in the preset number of historical sensing moments as a label, to obtain an electromagnetic map reconstruction model; the complete electromagnetic map is obtained by reconstructing the sparse electromagnetic map corresponding to the last historical sensing moment.

[0113] In one embodiment, the device 800 further includes:

[0114] The display module is used to perform inverse normalization processing on the target electromagnetic map to obtain a visual electromagnetic map, and then display the visual electromagnetic map.

[0115] Each module in the aforementioned electromagnetic map reconstruction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0116] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. When executed by the processor, the computer program implements an electromagnetic map reconstruction method.

[0117] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0118] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0119] Acquire sparse electromagnetic maps of the target area within the current sensing period using sensing satellites;

[0120] Determine the ephemeris information corresponding to the sparse electromagnetic map;

[0121] Based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model, the target electromagnetic map for the last sensing moment within the current sensing cycle is determined.

[0122] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0123] Obtain electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment;

[0124] Based on electromagnetic map samples and ephemeris information samples from various historical sensing moments, a neural network is trained to obtain an electromagnetic map reconstruction model.

[0125] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0126] A simulation scenario is constructed based on preset simulation parameters;

[0127] Based on a preset data format, electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment in the simulation scenario are obtained.

[0128] In one embodiment, the preset simulation parameters include at least one of the following: target area range, sensing frequency, communication constellation parameters, interference constellation parameters, sensing bandwidth, sensing antenna type, and electromagnetic map resolution.

[0129] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0130] Select a preset number of consecutive historical perception moments from each historical perception moment;

[0131] The electromagnetic map samples and ephemeris information samples corresponding to a preset number of historical sensing moments are used as input features, and the complete electromagnetic map of the last historical sensing moment in the preset number of historical sensing moments is used as a label to train the neural network to obtain an electromagnetic map reconstruction model; the complete electromagnetic map is obtained by reconstructing the sparse electromagnetic map corresponding to the last historical sensing moment.

[0132] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0133] The target electromagnetic map is denormalized to obtain a visual electromagnetic map, which is then displayed.

[0134] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0135] Acquire sparse electromagnetic maps of the target area within the current sensing period using sensing satellites;

[0136] Determine the ephemeris information corresponding to the sparse electromagnetic map;

[0137] Based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model, the target electromagnetic map for the last sensing moment within the current sensing cycle is determined.

[0138] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0139] Obtain electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment;

[0140] Based on electromagnetic map samples and ephemeris information samples from various historical sensing moments, a neural network is trained to obtain an electromagnetic map reconstruction model.

[0141] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0142] A simulation scenario is constructed based on preset simulation parameters;

[0143] Based on a preset data format, electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment in the simulation scenario are obtained.

[0144] In one embodiment, the preset simulation parameters include at least one of the following: target area range, sensing frequency, communication constellation parameters, interference constellation parameters, sensing bandwidth, sensing antenna type, and electromagnetic map resolution.

[0145] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0146] Select a preset number of consecutive historical perception moments from each historical perception moment;

[0147] The electromagnetic map samples and ephemeris information samples corresponding to a preset number of historical sensing moments are used as input features, and the complete electromagnetic map of the last historical sensing moment in the preset number of historical sensing moments is used as a label to train the neural network to obtain an electromagnetic map reconstruction model; the complete electromagnetic map is obtained by reconstructing the sparse electromagnetic map corresponding to the last historical sensing moment.

[0148] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0149] The target electromagnetic map is denormalized to obtain a visual electromagnetic map, which is then displayed.

[0150] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0151] Acquire sparse electromagnetic maps of the target area within the current sensing period using sensing satellites;

[0152] Determine the ephemeris information corresponding to the sparse electromagnetic map;

[0153] Based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model, the target electromagnetic map for the last sensing moment within the current sensing cycle is determined.

[0154] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0155] Obtain electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment;

[0156] Based on electromagnetic map samples and ephemeris information samples from various historical sensing moments, a neural network is trained to obtain an electromagnetic map reconstruction model.

[0157] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0158] A simulation scenario is constructed based on preset simulation parameters;

[0159] Based on a preset data format, electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment in the simulation scenario are obtained.

[0160] In one embodiment, the preset simulation parameters include at least one of the following: target area range, sensing frequency, communication constellation parameters, interference constellation parameters, sensing bandwidth, sensing antenna type, and electromagnetic map resolution.

[0161] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0162] Select a preset number of consecutive historical perception moments from each historical perception moment;

[0163] The electromagnetic map samples and ephemeris information samples corresponding to a preset number of historical sensing moments are used as input features, and the complete electromagnetic map of the last historical sensing moment in the preset number of historical sensing moments is used as a label to train the neural network to obtain an electromagnetic map reconstruction model; the complete electromagnetic map is obtained by reconstructing the sparse electromagnetic map corresponding to the last historical sensing moment.

[0164] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0165] The target electromagnetic map is denormalized to obtain a visual electromagnetic map, which is then displayed.

[0166] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0167] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0168] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An electromagnetic map reconstruction method, characterized in that, The method includes: Acquire sparse electromagnetic maps of the target area within the current sensing period using sensing satellites; Determine the ephemeris information corresponding to the sparse electromagnetic map; Based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model, the target electromagnetic map for the last sensing moment within the current sensing cycle is determined.

2. The method according to claim 1, characterized in that, The method further includes: Obtain electromagnetic map samples for each historical sensing moment and ephemeris information samples corresponding to the electromagnetic map samples; Based on the electromagnetic map samples and ephemeris information samples of each of the historical sensing moments, the neural network is trained to obtain the electromagnetic map reconstruction model.

3. The method according to claim 2, characterized in that, The acquisition of electromagnetic map samples at each historical sensing moment and the corresponding ephemeris information samples of the electromagnetic map samples includes: A simulation scenario is constructed based on preset simulation parameters; Based on a preset data format, electromagnetic map samples and corresponding ephemeris information samples for each historical sensing moment in the simulation scenario are obtained.

4. The method according to claim 3, characterized in that, The preset simulation parameters include at least one of the following: target area range, sensing frequency, communication constellation parameters, interference constellation parameters, sensing bandwidth, sensing antenna type, and electromagnetic map resolution.

5. The method according to claim 2, characterized in that, The electromagnetic map reconstruction model is obtained by training the neural network based on electromagnetic map samples and ephemeris information samples from each of the historical sensing times, including: Select a predetermined number of consecutive historical perception moments from each of the aforementioned historical perception moments; The electromagnetic map samples and ephemeris information samples corresponding to the preset number of historical sensing moments are used as input features, and the complete electromagnetic map of the last historical sensing moment in the preset number of historical sensing moments is used as a label to train the neural network to obtain the electromagnetic map reconstruction model; the complete electromagnetic map is obtained by reconstructing the sparse electromagnetic map corresponding to the last historical sensing moment.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: The target electromagnetic map is denormalized to obtain a visual electromagnetic map, which is then displayed.

7. An electromagnetic map reconstruction device, characterized in that, The device includes: The first acquisition module is used to acquire a sparse electromagnetic map of the target area within the current sensing period via sensing satellites. The first determining module is used to determine the ephemeris information corresponding to the sparse electromagnetic map; The reconstruction module is used to determine the target electromagnetic map at the last sensing moment in the current sensing cycle based on the sparse electromagnetic map, the ephemeris information corresponding to the sparse electromagnetic map, and the electromagnetic map reconstruction model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images