Electromagnetic property monitoring method and device, equipment, storage medium and program product

By using feature extraction network and variational inference model in electromagnetic environment monitoring, the electromagnetic relationship characteristics between electromagnetic equipment are extracted and analyzed, the problem of inaccurate electromagnetic environment monitoring in the existing technology is solved, and the accurate monitoring of the electromagnetic environment is achieved and Deep mining of electromagnetic interference.

CN119025914APending Publication Date: 2024-11-26SHENZHEN POWER SUPPLY BUREAU

Patent Information

Application Number
CN202411057051.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing electromagnetic environment monitoring technology relies on simple sensor data and threshold judgment, and lacks in-depth understanding and analysis of the data, resulting in inaccurate electromagnetic environment monitoring results.

Method used

Using a method based on feature extraction network and variational inference model, the electromagnetic relationship characteristics between electromagnetic devices are extracted by obtaining electromagnetic environment data, and in-depth analysis is carried out to accurately monitor the electromagnetic interference situation.

Benefits of technology

Accurate monitoring of the electromagnetic environment is realized, misjudgment or omission of electromagnetic interference is avoided, and the performance and compatibility of electromagnetic equipment in the electromagnetic environment is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119025914A_ABST
    Figure CN119025914A_ABST
Patent Text Reader

Abstract

The invention relates to an electromagnetic property monitoring method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring electromagnetic environment data between different electromagnetic devices in a to-be-monitored area; based on the trained feature extraction network, extracting electromagnetic relation features among different electromagnetic devices in the electromagnetic environment data; wherein the electromagnetic relation characteristics are used for representing dependency relations and electromagnetic interaction among different electromagnetic devices; and based on the trained variational reasoning model, variational reasoning is carried out on the electromagnetic relation characteristics between the different electromagnetic devices, and the electromagnetic interference condition between the different electromagnetic devices in the to-be-monitored area is obtained. By adopting the method, accurate monitoring of the electromagnetic environment can be realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of signal transmission technology, and in particular to an electromagnetic characteristic monitoring method, device, equipment, storage medium and program product. Background Art

[0002] With the widespread application of 5G technology, the deployment of electromagnetic equipment is becoming more and more intensive; at the same time, in order to ensure the efficiency and accuracy of information transmission, the electromagnetic environment in which the electromagnetic equipment is located must be monitored in real time to improve the performance and electromagnetic compatibility of each electromagnetic equipment in the electromagnetic environment.

[0003] Existing electromagnetic environment monitoring technologies usually rely on simple sensor data and threshold judgments, lacking in-depth understanding and analysis of the data, resulting in inaccurate electromagnetic environment monitoring results. Summary of the invention

[0004] Based on this, it is necessary to provide an electromagnetic characteristic monitoring method, device, equipment, storage medium and program product to address the above technical problems, which can achieve accurate monitoring of the electromagnetic environment.

[0005] In a first aspect, the present application provides an electromagnetic property monitoring method, the method comprising:

[0006] Obtain electromagnetic environment data between different electromagnetic devices in the area to be monitored;

[0007] Based on the trained feature extraction network, the electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data are extracted; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices;

[0008] Based on the trained variational inference model, variational inference is performed on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the monitored area.

[0009] In one embodiment, the feature extraction network is a graph convolutional neural network; based on the trained feature extraction network, electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data are extracted, including:

[0010] The electromagnetic environment data is converted into a target graph structure; wherein the nodes in the target graph structure represent electromagnetic devices, and the edges represent the electromagnetic environment data between electromagnetic devices; the target graph structure is input into a feature extraction network to obtain the electromagnetic relationship features between the nodes in the target graph structure.

[0011] In one embodiment, the target graph structure is input into a feature extraction network to obtain electromagnetic relationship features between nodes in the target graph structure, including:

[0012] According to the target graph structure, the target adjacency matrix corresponding to the electromagnetic environment data is determined; according to the target adjacency matrix, the degree matrix corresponding to the electromagnetic environment data is determined; according to the target adjacency matrix, the degree matrix and the feature extraction network, the electromagnetic relationship characteristics between each node in the target graph structure are determined.

[0013] In one of the embodiments, the electromagnetic environment data includes at least one of a device location, an electromagnetic signal strength, and an electromagnetic signal frequency.

[0014] In one embodiment, based on the trained variational inference model, variational inference is performed on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the monitored area, including:

[0015] According to the electromagnetic relationship characteristics between different electromagnetic devices, the target observation data corresponding to the electromagnetic environment data is determined; based on the variational inference model, the latent variable characteristics used to generate each target observation data are determined; according to the latent variable characteristics, the electromagnetic interference situation between different electromagnetic devices in the monitored area is determined.

[0016] In one embodiment, determining the electromagnetic interference between different electromagnetic devices in the area to be monitored based on the potential variable characteristics includes:

[0017] According to the latent variable characteristics, the latent variable value between any two electromagnetic devices is determined; if the latent variable value between the two electromagnetic devices is greater than a first preset threshold, it is determined that electromagnetic interference exists between the two electromagnetic devices; if the latent variable value between the two electromagnetic devices is less than a second preset threshold, it is determined that no electromagnetic interference exists between the two electromagnetic devices; wherein the second preset threshold is not greater than the first preset threshold.

[0018] In a second aspect, the present application also provides an electromagnetic characteristic monitoring device, the device comprising:

[0019] An acquisition module, used to acquire electromagnetic environment data between different electromagnetic devices in the area to be monitored;

[0020] An extraction module is used to extract electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data based on a trained feature extraction network; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices;

[0021] The inference module is used to perform variational inference on the electromagnetic relationship characteristics between different electromagnetic devices based on the trained variational inference model to obtain the electromagnetic interference between different electromagnetic devices in the monitored area.

[0022] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0023] Obtain electromagnetic environment data between different electromagnetic devices in the area to be monitored;

[0024] Based on the trained feature extraction network, the electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data are extracted; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices;

[0025] Based on the trained variational inference model, variational inference is performed on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the monitored area.

[0026] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0027] Obtain electromagnetic environment data between different electromagnetic devices in the area to be monitored;

[0028] Based on the trained feature extraction network, the electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data are extracted; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices;

[0029] Based on the trained variational inference model, variational inference is performed on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the monitored area.

[0030] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0031] Obtain electromagnetic environment data between different electromagnetic devices in the area to be monitored;

[0032] Based on the trained feature extraction network, the electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data are extracted; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices;

[0033] Based on the trained variational inference model, variational inference is performed on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the monitored area.

[0034] The above-mentioned electromagnetic characteristic monitoring method, device, equipment, storage medium and program product can obtain the electromagnetic relationship characteristics between different electromagnetic devices in each electromagnetic environment data by combining the electromagnetic environment data between different electromagnetic devices in the monitored area with the trained feature extraction network, so that the dependency and electromagnetic interaction between different electromagnetic devices can be analyzed; further, the electromagnetic relationship characteristics between different electromagnetic devices are combined with the trained variational inference model, that is, the trained variational inference model is used to further infer and analyze the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the monitored area. This solution introduces a trained feature extraction network so that the acquired electromagnetic environment data can better reflect the dependency and electromagnetic interaction between different electromagnetic devices; further, by introducing a trained variational inference model, the electromagnetic interference between different electromagnetic devices can be deeply explored to avoid the misjudgment or omission of electromagnetic interference, thereby realizing accurate monitoring of the electromagnetic environment of the monitored area. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 An application environment diagram of an electromagnetic characteristic monitoring method provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of a flow chart of an electromagnetic characteristic monitoring method provided in an embodiment of the present application;

[0038] Figure 3 A schematic diagram of a process for extracting electromagnetic relationship features provided in an embodiment of the present application;

[0039] Figure 4 A schematic diagram of a process for obtaining electromagnetic interference conditions provided in an embodiment of the present application;

[0040] Figure 5 A schematic diagram of a flow chart of another electromagnetic characteristic monitoring method provided in an embodiment of the present application;

[0041] Figure 6 A structural block diagram of an electromagnetic characteristic monitoring device provided in an embodiment of the present application;

[0042] Figure 7 This is a structural block diagram of another electromagnetic characteristic monitoring device provided in an embodiment of the present application;

[0043] Figure 8 This is a structural block diagram of another electromagnetic characteristic monitoring device provided in an embodiment of the present application;

[0044] Fig. 9 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] The electromagnetic characteristic monitoring method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The terminal 102 can be installed at each electromagnetic device in the monitored area to collect electromagnetic environment data around each electromagnetic device in the monitored area; further, after the terminal 102 collects the electromagnetic environment data, the collected electromagnetic environment data is transmitted to the server 104, and the server 104 analyzes the collected electromagnetic environment data and obtains the electromagnetic interference between different electromagnetic devices in the monitored area. Among them, the terminal 102 can be but not limited to various sensors, detectors, electromagnetic sensors, computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0047] In an exemplary embodiment, Figure 2 As shown, a method for monitoring electromagnetic characteristics is provided, and the method is applied to Figure 1 Taking the server 104 in the example as an example, the following steps may be included:

[0048] S201, obtaining electromagnetic environment data between different electromagnetic devices in the area to be monitored.

[0049] Among them, the area to be monitored can represent the area where electromagnetic characteristics monitoring is required; the electromagnetic equipment can represent the equipment that generates electromagnetic radiation in the area to be monitored; the electromagnetic environment data can include but are not limited to data such as equipment location, electromagnetic signal strength, electromagnetic signal frequency, current and power.

[0050] Exemplarily, a sensor, that is, a terminal 102, is installed at each electromagnetic device and around each electromagnetic device in the area to be monitored. For example, an electromagnetic inductor is installed. Further, the initial electromagnetic environment data X between different electromagnetic devices in the area to be monitored is obtained through the terminal 102. raw , which can be specifically expressed as:

[0051] (1)

[0052] Among them, s i It can represent the initial electromagnetic environment data collected by the i-th sensor, and can include at least one of the device location, electromagnetic signal strength, electromagnetic signal frequency, current and power.

[0053] Furthermore, in order to eliminate the dimension effect and reduce the deviation between different sensors, the initial electromagnetic environment data X raw Perform data standardization to obtain electromagnetic environment data X norm . It can be specifically expressed as:

[0054] (2)

[0055] in, can be the mean value of the initial electromagnetic environment data, It can be the standard deviation of the initial electromagnetic environment data.

[0056] S202, extracting electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data based on the trained feature extraction network.

[0057] Among them, the feature extraction network can be a graph convolutional neural network, which is used to extract the electromagnetic relationship features between different electromagnetic devices; the electromagnetic relationship features can be used to characterize the dependency and electromagnetic interaction between different electromagnetic devices.

[0058] As in the above example, the electromagnetic environment data X norm Transform the electromagnetic environment data X norm After analysis and processing, the electromagnetic relationship characteristics between different electromagnetic devices in each electromagnetic environment data are finally obtained.

[0059] It should be noted that the feature extraction network is trained based on a large number of training samples so that it can better learn the electromagnetic relationship characteristics between different electromagnetic devices in various electromagnetic environment data; after reaching the preset accuracy of the training, a trained feature extraction network can be obtained.

[0060] S203, based on the trained variational inference model, variational inference is performed on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference conditions between different electromagnetic devices in the area to be monitored.

[0061] Among them, the variational reasoning model can be a model for in-depth analysis of the electromagnetic relationship characteristics between different electromagnetic devices in each electromagnetic environment data; the electromagnetic interference situation can be divided into a situation where electromagnetic interference exists and a situation where there is no electromagnetic interference; the electromagnetic interference situation can also be specifically divided into a strong electromagnetic interference situation, a medium electromagnetic interference situation, a weak electromagnetic interference situation and a situation where there is no electromagnetic interference according to the numerical value of the variational reasoning.

[0062] As shown in the above example, the electromagnetic relationship features are input into the variational reasoning model, which performs a deeper analysis and reasoning on the electromagnetic relationship features, explores more potential relationships between electromagnetic devices, and based on the results of the deep mining, conducts a more comprehensive analysis of the electromagnetic interference between different electromagnetic devices in the monitoring area.

[0063] The above-mentioned electromagnetic characteristic monitoring method can obtain the electromagnetic relationship characteristics between different electromagnetic devices in each electromagnetic environment data by combining the electromagnetic environment data between different electromagnetic devices in the monitored area with the trained feature extraction network, so that the dependency and electromagnetic interaction between different electromagnetic devices can be analyzed; further, the electromagnetic relationship characteristics between different electromagnetic devices are combined with the trained variational inference model, that is, the trained variational inference model is used to further infer and analyze the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the monitored area. This scheme introduces a trained feature extraction network so that the acquired electromagnetic environment data can better reflect the dependency and electromagnetic interaction between different electromagnetic devices; further, by introducing a trained variational inference model, it is possible to deeply explore the electromagnetic interference between different electromagnetic devices, avoid misjudgment or omission of electromagnetic interference, and thus achieve accurate monitoring of the electromagnetic environment of the monitored area.

[0064] Based on the above embodiment, the present embodiment of the application explains the above embodiment S202 in detail. Specifically, the present embodiment of the application involves the process of extracting electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data, such as Figure 3 As shown, the specific steps include:

[0065] S301, converting electromagnetic environment data into a target graph structure.

[0066] Among them, the nodes in the target graph structure can represent electromagnetic devices, and the edges can represent electromagnetic environment data between electromagnetic devices; the electromagnetic environment data between electromagnetic devices can include at least one of data such as device distance, electromagnetic signal strength difference, and electromagnetic signal frequency difference.

[0067] Exemplarily, the electromagnetic devices in the monitored area are electromagnetic device 1, electromagnetic device 2 and electromagnetic device 3, and the electromagnetic environment data include three types of data: device location d, electromagnetic signal strength s and electromagnetic signal frequency f; by collecting data from electromagnetic sensors installed at electromagnetic device 1, electromagnetic device 2 and electromagnetic device 3, respectively, the electromagnetic environment data corresponding to electromagnetic device 1, electromagnetic device 2 and electromagnetic device 3 are determined, such as the electromagnetic environment data corresponding to electromagnetic device 1 are device location d1, electromagnetic signal strength s1 and electromagnetic signal frequency f1; the electromagnetic environment data corresponding to electromagnetic device 2 are device location d2, electromagnetic signal strength s2 and electromagnetic signal frequency f2; the electromagnetic environment data corresponding to electromagnetic device 3 are device location d3, electromagnetic signal strength s3 and electromagnetic signal frequency f3.

[0068] Further, based on the electromagnetic environment data corresponding to the electromagnetic device 1, the electromagnetic device 2 and the electromagnetic device 3 respectively, the electromagnetic environment data between the electromagnetic devices is determined; for example, the device distance in the electromagnetic environment data between the electromagnetic device 1 and the electromagnetic device 2 can be expressed as d 12 = d1-d2, the difference in electromagnetic signal strength in the electromagnetic environment data between electromagnetic device 1 and electromagnetic device 2 can be expressed as s 12 =s1-s2, the difference in the electromagnetic signal frequency in the electromagnetic environment data between electromagnetic device 1 and electromagnetic device 2 can be expressed as f 12 =f1-f2. Similarly, determine the electromagnetic environment data between electromagnetic equipment 1 and electromagnetic equipment 3 (d 13 、s 13 and f 13 ), and the electromagnetic environment data between electromagnetic equipment 2 and electromagnetic equipment 3 (d 23 、s 23 and f 23 ).

[0069] Furthermore, based on the electromagnetic environment data between electromagnetic equipment 1, electromagnetic equipment 2 and electromagnetic equipment 3, a target graph structure G is constructed; wherein the target graph structure G includes two parts, namely, a node set V and an edge set E; the node set V includes three nodes, representing v1 (electromagnetic equipment 1), v2 (electromagnetic equipment 2) and v3 (electromagnetic equipment 3); the edge set E can be expressed as {(v1, v2,), (v1, v3), (v2, v3)}, and the electromagnetic environment data between the three nodes can be represented by the edge weight w, such as w 12 =[d 12 ,s12 , f 12 ],w 13 =[d 13 , s 13 , f 13 ],w 23 =[d 23 , s 23 , f 23 ].

[0070] S302, inputting the target graph structure into a feature extraction network to obtain electromagnetic relationship features between nodes in the target graph structure.

[0071] An implementable method is to determine the target adjacency matrix corresponding to the electromagnetic environment data according to the target graph structure; determine the degree matrix corresponding to the electromagnetic environment data according to the target adjacency matrix; and determine the electromagnetic relationship characteristics between each node in the target graph structure according to the target adjacency matrix, the degree matrix and the feature extraction network.

[0072] As shown in the above example, based on the node set V, edge set E and edge weight w in the target graph structure G, the target adjacency matrix A corresponding to the electromagnetic environment data can be determined. For example, it can be determined that A[v1, v2]=[d 12 , s 12 , f 12 ],A[v1, v3]=[d 13 , s 13 ,f 13 ],A[v2, v3]=[d 23 , s 23 , f 23 ]; further, based on the target adjacency matrix A and the identity matrix I N , the degree matrix corresponding to the electromagnetic environment data can be determined, such as the target adjacency matrix A and the unit matrix I N Add together to get a new matrix , to achieve node self-connection, and then, the new matrix Add the values ​​of each row in to get the degree matrix ; Thus, based on the new matrix , degree matrix and parameters in the feature extraction network, the feature extraction network is analyzed, and the electromagnetic relationship characteristics between nodes in the target graph structure are determined based on the analysis results.

[0073] In another implementation, the feature extraction network directly extracts electromagnetic relationship features from the target graph structure A, and compares the extracted electromagnetic relationship features of the target graph structure A with the historical electromagnetic relationship features, and determines the historical electromagnetic relationship features M that have the highest matching degree with the electromagnetic relationship features of the target graph structure A; further, the historical electromagnetic relationship features M are determined as the electromagnetic relationship features between nodes in the target graph structure A. The feature extraction network is trained based on the training samples (graph structure); the historical electromagnetic relationship features are electromagnetic relationship features learned based on the training samples.

[0074] In an embodiment of the present application, the electromagnetic relationship between each electromagnetic device is structured by converting the electromagnetic environment data into a target graph structure; further, by introducing a feature extraction network, the target graph structure is analyzed, so that the electromagnetic relationship between each electromagnetic device is clearer and it is easier to analyze the electromagnetic interference between each electromagnetic device.

[0075] Based on the above embodiment, the present application embodiment explains the above embodiment S203 in detail. Specifically, the present application embodiment involves a process of obtaining the electromagnetic interference conditions between different electromagnetic devices in the area to be monitored, such as Figure 4 As shown, the specific steps include:

[0076] S401, determining target observation data corresponding to the electromagnetic environment data according to electromagnetic relationship characteristics between different electromagnetic devices.

[0077] Among them, the target observation data can represent the variables that can be observed in the variational inference model, and is the input data of the variational inference model.

[0078] Optionally, the electromagnetic relationship characteristic data between different electromagnetic devices may be directly determined as the target observation data x corresponding to the electromagnetic environment data.

[0079] S402: Based on the variational inference model, determine the latent variable features used to generate each target observation data.

[0080] The variational inference model may be a model that generates latent variable features of each target observation data through a variational inference method; the latent variable features may represent the predicted value corresponding to each target observation data.

[0081] Exemplarily, based on the target observation data x and the hypothesized latent variable features z corresponding to the target observation data x, construct the posterior distribution , but in solving the posterior distribution Some integrals in the process are difficult to solve. Therefore, we introduce the approximate posterior distribution of , through the order and The difference is the smallest to obtain the optimal latent variable feature z. Among them, and The difference can be measured by the reverse KL (Kullback-Leibler) divergence. and The reverse KL (Kullback-Leibler) divergence of It can be specifically expressed as:

[0082]

[0083]

[0084] (3)

[0085] make , then formula (3) can be written as:

[0086] (4)

[0087] Right now , in the order and The process with the smallest difference is The smallest and also the The process of maximization.

[0088] It can be understood that the variational inference model generates the latent variable features z of each target observation data based on each target observation data x, that is, based on the standard observation data x, determine The latent variable feature z corresponding to the maximum value.

[0089] It should be noted that and are all parameters in the variational inference model; the parameters in the variational inference model are determined during the process of variational inference model training and self-supervised learning model learning. Optionally, the process of self-supervised model learning can be expressed as ; where x t represents the target observation data at time t, represents the predicted observation data at time t+1, f represents the prediction function of the self-supervised learning model, and W represents the weight of the self-supervised learning model.

[0090] S403: Determine the electromagnetic interference between different electromagnetic devices in the area to be monitored based on the potential variable characteristics.

[0091] In one implementation, the potential variable value between any two electromagnetic devices is determined based on the potential variable characteristics; if the potential variable value between the two electromagnetic devices is greater than a first preset threshold, it is determined that there is electromagnetic interference between the two electromagnetic devices; if the potential variable value between the two electromagnetic devices is less than a second preset threshold, it is determined that there is no electromagnetic interference between the two electromagnetic devices. The second preset threshold is not greater than the first preset threshold; the first preset threshold and the second preset threshold can be preset by experts based on experience.

[0092] For example, based on the latent variable feature z, the latent variable value between any two electromagnetic devices can be determined, such as the latent variable value z between electromagnetic device 1 and electromagnetic device 2. 12 ; Further, the potential variable value between the two electromagnetic devices is compared with the preset threshold, and a judgment is made on whether there is electromagnetic interference between the two electromagnetic devices based on the comparison result. If the potential variable value z between electromagnetic device 1 and electromagnetic device 2 is 12 is greater than a first preset threshold, it is determined that there is electromagnetic interference between electromagnetic device 1 and electromagnetic device 2; if the potential variable value z between electromagnetic device 1 and electromagnetic device 2 12 If it is less than the second preset threshold, it is determined that there is no electromagnetic interference between electromagnetic device 1 and electromagnetic device 2; wherein, in order to ensure the accuracy of the judgment result, the first preset threshold may not be equal to the second preset threshold, and a questionable value between the first preset threshold and the second preset threshold is allowed.

[0093] Another possible implementation method is to determine the potential variable value between any two electromagnetic devices based on the potential variable characteristics; if the potential variable value between the two electromagnetic devices is compared with the intervals corresponding to each electromagnetic interference situation. For example, the electromagnetic interference situation is divided into four types, namely no electromagnetic interference, weak electromagnetic interference, medium electromagnetic interference and strong electromagnetic interference, and the corresponding intervals are no electromagnetic interference [0, 1], weak electromagnetic interference (1, 2], medium electromagnetic interference (2, 3] and strong electromagnetic interference (3, +∞), the potential variable value z between electromagnetic device 1 and electromagnetic device 2 is compared with the intervals corresponding to each electromagnetic interference situation. 12 =1.8 compared with each interval, due to 1 <z 12 (1.8)<2, therefore, the electromagnetic interference between electromagnetic device 1 and electromagnetic device 2 is weak electromagnetic interference.

[0094] In the embodiments of the present application, by introducing a variational reasoning model, in-depth analysis and reasoning of the electromagnetic relationship characteristics between different electromagnetic devices are achieved, and the electromagnetic relationship between different electromagnetic devices is deeply explored, laying the foundation for accurately determining the electromagnetic interference between different electromagnetic devices.

[0095] Based on the above embodiment, this embodiment provides an optional example of an electromagnetic characteristic monitoring method. Figure 5 As shown, the specific implementation process is as follows:

[0096] S501, obtaining electromagnetic environment data between different electromagnetic devices in the area to be monitored.

[0097] The electromagnetic environment data may include but is not limited to at least one of the device location, electromagnetic signal strength and electromagnetic signal frequency.

[0098] S502, converting the electromagnetic environment data into a target graph structure.

[0099] The nodes in the target graph structure represent electromagnetic devices, and the edges represent electromagnetic environment data between electromagnetic devices.

[0100] S503: Determine a target adjacency matrix corresponding to the electromagnetic environment data according to the target graph structure.

[0101] S504: Determine the degree matrix corresponding to the electromagnetic environment data according to the target adjacency matrix.

[0102] S505, determining the electromagnetic relationship features between nodes in the target graph structure according to the target adjacency matrix, the degree matrix and the feature extraction network.

[0103] S506, determining target observation data corresponding to the electromagnetic environment data according to the electromagnetic relationship characteristics between different electromagnetic devices.

[0104] S507, based on the variational inference model, determine the latent variable features used to generate each target observation data.

[0105] S508, determining the potential variable value between any two electromagnetic devices according to the potential variable characteristics.

[0106] S509, judging the potential variable value between any two electromagnetic devices; if the potential variable value between the two electromagnetic devices is greater than the first preset threshold, executing S510; if the potential variable value between the two electromagnetic devices is less than the second preset threshold, executing S511.

[0107] The second preset threshold is not greater than the first preset threshold.

[0108] S510: Determine whether electromagnetic interference exists between two electromagnetic devices.

[0109] S511, determining that there is no electromagnetic interference between two electromagnetic devices.

[0110] The specific process of S501-S511 above can refer to the description of the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0111] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0112] Based on the same inventive concept, the embodiment of the present application also provides an electromagnetic characteristic monitoring device for implementing the electromagnetic characteristic monitoring method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more electromagnetic characteristic monitoring device embodiments provided below can refer to the limitations of the electromagnetic characteristic monitoring method above, and will not be repeated here.

[0113] In an exemplary embodiment, Figure 6 As shown, an electromagnetic characteristic monitoring device 1 is provided, comprising: an acquisition module 10, an extraction module 20 and an inference module 30, wherein:

[0114] The acquisition module 10 is used to acquire electromagnetic environment data between different electromagnetic devices in the area to be monitored.

[0115] The extraction module 20 is used to extract the electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data based on the trained feature extraction network; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices.

[0116] The reasoning module 30 is used to perform variational reasoning on the electromagnetic relationship characteristics between different electromagnetic devices based on the trained variational reasoning model to obtain the electromagnetic interference conditions between different electromagnetic devices in the area to be monitored.

[0117] In one embodiment, Figure 7 As shown, the extraction module 20 specifically further includes:

[0118] The conversion unit 21 is used to convert the electromagnetic environment data into a target graph structure; wherein the nodes in the target graph structure represent electromagnetic devices, and the edges represent the electromagnetic environment data between the electromagnetic devices.

[0119] The input unit 22 is used to input the target graph structure into the feature extraction network to obtain the electromagnetic relationship features between the nodes in the target graph structure.

[0120] In one embodiment, the input unit 22 is further used for:

[0121] According to the target graph structure, the target adjacency matrix corresponding to the electromagnetic environment data is determined; according to the target adjacency matrix, the degree matrix corresponding to the electromagnetic environment data is determined; according to the target adjacency matrix, the degree matrix and the feature extraction network, the electromagnetic relationship characteristics between each node in the target graph structure are determined.

[0122] In one embodiment, the electromagnetic environment data includes at least one of a device location, an electromagnetic signal strength, and an electromagnetic signal frequency.

[0123] In one embodiment, Figure 8 As shown, the reasoning module 30 specifically includes:

[0124] The first determining unit 31 is used to determine target observation data corresponding to the electromagnetic environment data according to the electromagnetic relationship characteristics between different electromagnetic devices.

[0125] The second determination unit 32 is used to determine the potential variable features used to generate each target observation data based on the variational inference model.

[0126] The third determining unit 33 is used to determine the electromagnetic interference between different electromagnetic devices in the area to be monitored according to the potential variable characteristics.

[0127] In one embodiment, the third determining unit 33 is further configured to:

[0128] According to the latent variable characteristics, the latent variable value between any two electromagnetic devices is determined; if the latent variable value between the two electromagnetic devices is greater than a first preset threshold, it is determined that electromagnetic interference exists between the two electromagnetic devices; if the latent variable value between the two electromagnetic devices is less than a second preset threshold, it is determined that no electromagnetic interference exists between the two electromagnetic devices; wherein the second preset threshold is not greater than the first preset threshold.

[0129] Each module in the above electromagnetic characteristic monitoring device can be implemented in whole or in part by software, hardware and a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0130] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig. 9As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store electromagnetic environment data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an electromagnetic characteristic monitoring method is implemented.

[0131] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0132] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0133] Obtain electromagnetic environment data between different electromagnetic devices in the area to be monitored;

[0134] Based on the trained feature extraction network, the electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data are extracted; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices;

[0135] Based on the trained variational inference model, variational inference is performed on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the monitored area.

[0136] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0137] The electromagnetic environment data is converted into a target graph structure; wherein the nodes in the target graph structure represent electromagnetic devices, and the edges represent the electromagnetic environment data between electromagnetic devices; the target graph structure is input into a feature extraction network to obtain the electromagnetic relationship features between the nodes in the target graph structure.

[0138] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0139] According to the target graph structure, the target adjacency matrix corresponding to the electromagnetic environment data is determined; according to the target adjacency matrix, the degree matrix corresponding to the electromagnetic environment data is determined; according to the target adjacency matrix, the degree matrix and the feature extraction network, the electromagnetic relationship characteristics between each node in the target graph structure are determined.

[0140] In one embodiment, the electromagnetic environment data includes at least one of a device location, an electromagnetic signal strength, and an electromagnetic signal frequency.

[0141] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0142] According to the electromagnetic relationship characteristics between different electromagnetic devices, the target observation data corresponding to the electromagnetic environment data is determined; based on the variational inference model, the latent variable characteristics used to generate each target observation data are determined; according to the latent variable characteristics, the electromagnetic interference situation between different electromagnetic devices in the monitored area is determined.

[0143] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0144] According to the latent variable characteristics, the latent variable value between any two electromagnetic devices is determined; if the latent variable value between the two electromagnetic devices is greater than a first preset threshold, it is determined that electromagnetic interference exists between the two electromagnetic devices; if the latent variable value between the two electromagnetic devices is less than a second preset threshold, it is determined that no electromagnetic interference exists between the two electromagnetic devices; wherein the second preset threshold is not greater than the first preset threshold.

[0145] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0146] Obtain electromagnetic environment data between different electromagnetic devices in the area to be monitored;

[0147] Based on the trained feature extraction network, the electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data are extracted; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices;

[0148] Based on the trained variational inference model, variational inference is performed on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the monitored area.

[0149] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0150] The electromagnetic environment data is converted into a target graph structure; wherein the nodes in the target graph structure represent electromagnetic devices, and the edges represent the electromagnetic environment data between electromagnetic devices; the target graph structure is input into a feature extraction network to obtain the electromagnetic relationship features between the nodes in the target graph structure.

[0151] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0152] According to the target graph structure, the target adjacency matrix corresponding to the electromagnetic environment data is determined; according to the target adjacency matrix, the degree matrix corresponding to the electromagnetic environment data is determined; according to the target adjacency matrix, the degree matrix and the feature extraction network, the electromagnetic relationship characteristics between each node in the target graph structure are determined.

[0153] In one embodiment, the electromagnetic environment data includes at least one of a device location, an electromagnetic signal strength, and an electromagnetic signal frequency.

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

[0155] According to the electromagnetic relationship characteristics between different electromagnetic devices, the target observation data corresponding to the electromagnetic environment data is determined; based on the variational inference model, the latent variable characteristics used to generate each target observation data are determined; according to the latent variable characteristics, the electromagnetic interference situation between different electromagnetic devices in the monitored area is determined.

[0156] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0157] According to the latent variable characteristics, the latent variable value between any two electromagnetic devices is determined; if the latent variable value between the two electromagnetic devices is greater than a first preset threshold, it is determined that electromagnetic interference exists between the two electromagnetic devices; if the latent variable value between the two electromagnetic devices is less than a second preset threshold, it is determined that no electromagnetic interference exists between the two electromagnetic devices; wherein the second preset threshold is not greater than the first preset threshold.

[0158] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0159] Obtain electromagnetic environment data between different electromagnetic devices in the area to be monitored;

[0160] Based on the trained feature extraction network, the electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data are extracted; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices;

[0161] Based on the trained variational inference model, variational inference is performed on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the monitored area.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0163] The electromagnetic environment data is converted into a target graph structure; wherein the nodes in the target graph structure represent electromagnetic devices, and the edges represent the electromagnetic environment data between electromagnetic devices; the target graph structure is input into a feature extraction network to obtain the electromagnetic relationship features between the nodes in the target graph structure.

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

[0165] According to the target graph structure, the target adjacency matrix corresponding to the electromagnetic environment data is determined; according to the target adjacency matrix, the degree matrix corresponding to the electromagnetic environment data is determined; according to the target adjacency matrix, the degree matrix and the feature extraction network, the electromagnetic relationship characteristics between each node in the target graph structure are determined.

[0166] In one embodiment, the electromagnetic environment data includes at least one of a device location, an electromagnetic signal strength, and an electromagnetic signal frequency.

[0167] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0168] According to the electromagnetic relationship characteristics between different electromagnetic devices, the target observation data corresponding to the electromagnetic environment data is determined; based on the variational inference model, the latent variable characteristics used to generate each target observation data are determined; according to the latent variable characteristics, the electromagnetic interference situation between different electromagnetic devices in the monitored area is determined.

[0169] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0170] According to the latent variable characteristics, the latent variable value between any two electromagnetic devices is determined; if the latent variable value between the two electromagnetic devices is greater than a first preset threshold, it is determined that electromagnetic interference exists between the two electromagnetic devices; if the latent variable value between the two electromagnetic devices is less than a second preset threshold, it is determined that no electromagnetic interference exists between the two electromagnetic devices; wherein the second preset threshold is not greater than the first preset threshold.

[0171] It should be noted that the electromagnetic equipment information and data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0172] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0173] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0174] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring electromagnetic characteristics, characterized in that: The method comprises: Obtain electromagnetic environment data between different electromagnetic devices in the area to be monitored; Based on the trained feature extraction network, extract the electromagnetic relationship features between different electromagnetic devices in each of the electromagnetic environment data; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices; Based on the trained variational inference model, variational inference is performed on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference conditions between different electromagnetic devices in the area to be monitored.

2. The method according to claim 1, characterized in that: The feature extraction network is a graph convolutional neural network; the feature extraction network based on the training extracts the electromagnetic relationship features between different electromagnetic devices in each electromagnetic environment data, including: Converting the electromagnetic environment data into a target graph structure; wherein the nodes in the target graph structure represent electromagnetic devices, and the edges represent the electromagnetic environment data between electromagnetic devices; The target graph structure is input into the feature extraction network to obtain the electromagnetic relationship features between the nodes in the target graph structure.

3. The method according to claim 2, characterized in that The step of inputting the target graph structure into the feature extraction network to obtain electromagnetic relationship features between nodes in the target graph structure includes: Determining a target adjacency matrix corresponding to the electromagnetic environment data according to the target graph structure; Determining a degree matrix corresponding to the electromagnetic environment data according to the target adjacency matrix; The electromagnetic relationship features between nodes in the target graph structure are determined according to the target adjacency matrix, the degree matrix and the feature extraction network.

4. The method according to claim 2, characterized in that: The electromagnetic environment data includes at least one of a device location, an electromagnetic signal strength, and an electromagnetic signal frequency.

5. According to right The method according to any one of claims 1 to 3, characterized in that The variational inference model based on the training is used to perform variational inference on the electromagnetic relationship characteristics between different electromagnetic devices to obtain the electromagnetic interference between different electromagnetic devices in the area to be monitored, including: Determining target observation data corresponding to the electromagnetic environment data according to electromagnetic relationship characteristics between different electromagnetic devices; Based on the variational inference model, determining the latent variable features used to generate each of the target observation data; According to the potential variable characteristics, the electromagnetic interference conditions between different electromagnetic devices in the area to be monitored are determined.

6. The method according to claim 5, characterized in that Determining the electromagnetic interference between different electromagnetic devices in the area to be monitored according to the potential variable characteristics includes: Determining a potential variable value between any two electromagnetic devices according to the potential variable characteristics; If the potential variable value between the two electromagnetic devices is greater than a first preset threshold, it is determined that electromagnetic interference exists between the two electromagnetic devices; If the potential variable value between the two electromagnetic devices is less than a second preset threshold, it is determined that there is no electromagnetic interference between the two electromagnetic devices; wherein the second preset threshold is not greater than the first preset threshold.

7. An electromagnetic characteristic monitoring device, characterized in that: The device comprises: An acquisition module, used to acquire electromagnetic environment data between different electromagnetic devices in the area to be monitored; An extraction module, used for extracting electromagnetic relationship features between different electromagnetic devices in each of the electromagnetic environment data based on a trained feature extraction network; wherein the electromagnetic relationship features are used to characterize the dependency relationship and electromagnetic interaction between different electromagnetic devices; The inference module is used to perform variational inference on the electromagnetic relationship characteristics between different electromagnetic devices based on the trained variational inference model to obtain the electromagnetic interference conditions between different electromagnetic devices in the area to be monitored.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

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

Citation Information

Patent Citations

  • Electromagnetic signal identification method and device for constructing graph convolutional network based on implicit knowledge

    CN110210330A

  • Electromagnetic spectrum map construction method and system based on variational graph structure

    CN117609770A

Cited By

  • Electromagnetic environment monitoring system and method based on deep learning

    CN119246971A