High-altitude platform equipment collaborative management method, system and electronic equipment

Abstract

The present application relates to the field of high-altitude platform equipment, and specifically discloses a method, system and electronic equipment for collaborative management of high-altitude platform equipment. While extracting the topological features of the drone group, it uses a convolutional neural network model to extract the high-dimensional correlation features of the received signals of each drone. In this way, the drones corresponding to the signal feature vectors can be regarded as signal sources and sensors respectively, and the received signal strength values ​​can be calculated to obtain correction values ​​for representing communication interference between the drones. Further, by correcting the first topological matrix, it is possible to accurately judge whether the deployment pattern of each drone in the drone group meets the preset requirements.

Description

Technical Field

[0001] The present invention relates to the field of high-altitude platform equipment, and more specifically, to a method, system and electronic equipment for collaborative management of high-altitude platform equipment. Background Art

[0002] In recent years, drone swarm technology has received widespread attention in the industry. Compared with a single drone, a drone swarm can complete more complex and diverse tasks through information interaction and mutual collaboration between drones. It has the advantages of distributed functions, high system survival rate, and high efficiency, and has great potential application value.

[0003] During drone swarm flight, high-precision location information and a well-defined topology are crucial for efficient and reliable execution of various missions. For densely packed drone swarm systems, the drones used are typically rotary-wing aircraft. Due to cost and payload constraints, equipping all drones with high-precision navigation equipment is extremely difficult. Therefore, a collaborative management method for high-altitude platform equipment is desired to accurately determine whether the deployment pattern of each drone in a swarm meets preset requirements and improve the positioning accuracy of each drone in the swarm. Summary of the Invention

[0004] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a method, system and electronic device for collaborative management of high-altitude platform equipment, which extracts the topological features of the drone group while using a convolutional neural network model to extract the high-dimensional correlation features of the received signals of each drone. In this way, the drones corresponding to the signal feature vectors can be regarded as signal sources and sensors respectively, and the received signal strength values ​​can be calculated to obtain correction values ​​for representing the communication interference between the drones. Further, by correcting the first topological matrix, it is possible to accurately judge whether the deployment pattern of each drone in the drone group meets the preset requirements.

[0005] According to one aspect of the present application, a method for collaborative management of high-altitude platform equipment is provided, comprising:

[0006] Obtaining an initial distance matrix of the drone swarm through the communication modules of each drone in the drone swarm, wherein the value of each non-diagonal position in the initial distance matrix is ​​a distance value between two drones obtained through communication between the communication modules between the two drones, and the eigenvalue of each diagonal position in the initial distance matrix is ​​zero;

[0007] Passing the initial distance matrix through a first convolutional neural network to obtain a first topological feature matrix;

[0008] Obtaining a received signal from a communication module of each drone in the drone swarm;

[0009] Passing the received signal of the communication module of each of the drones through a second convolutional neural network to obtain a signal feature vector corresponding to the received signal of the communication module of each of the drones;

[0010] For the i-th signal feature vector v of the i-th drone in the drone group i And the j-th signal feature vector v for the j-th UAV in the UAV group j , consider the i-th UAV and the j-th UAV as the signal source and receiving source respectively, calculate the received signal strength value of the j-th UAV relative to the i-th UAV, the received signal strength value is proportional to the transmit power of the i-th UAV and the i-th signal feature vector v i With the j-th signal feature vector v j It is related to the second norm of the difference vector, the path loss index and the shielding attenuation value;

[0011] Arranging the received signal strength values ​​between every two drones in the drone group in two dimensions into a second characteristic matrix;

[0012] Using the second characteristic matrix as a correction factor, correcting the eigenvalues ​​of each position in the first topological characteristic matrix to obtain a second topological characteristic matrix; and

[0013] The second topological feature matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the deployment pattern of each drone in the drone group meets the preset requirements.

[0014] According to another aspect of the present application, a high-altitude platform equipment collaborative management system is provided, comprising:

[0015] an initial distance matrix acquisition unit, configured to acquire an initial distance matrix of the drone swarm through the communication modules of the respective drones in the drone swarm, wherein the value of each non-diagonal position in the initial distance matrix is ​​a distance value between two drones obtained through communication between the communication modules thereof, and the eigenvalue of each diagonal position in the initial distance matrix is ​​zero;

[0016] a first convolution unit, configured to pass the initial distance matrix obtained by the initial distance matrix obtaining unit through a first convolutional neural network to obtain a first topological feature matrix;

[0017] A received signal acquisition unit, configured to acquire a received signal from a communication module of each drone in the drone group;

[0018] A second convolution unit is configured to pass the received signals of the communication modules of the drones obtained by the received signal acquisition units through a second convolutional neural network to obtain signal feature vectors corresponding to the received signals of the communication modules of the drones;

[0019] A received signal strength value calculation unit is used to calculate the i-th signal feature vector v of the i-th drone in the drone group obtained by the second convolution unit. i And the j-th signal feature vector v for the j-th UAV in the UAV group j , consider the i-th UAV and the j-th UAV as the signal source and receiving source respectively, calculate the received signal strength value of the j-th UAV relative to the i-th UAV, the received signal strength value is proportional to the transmit power of the i-th UAV and the i-th signal feature vector v i With the j-th signal feature vector v j It is related to the second norm of the difference vector, the path loss index and the shielding attenuation value;

[0020] a two-dimensional arrangement unit, configured to two-dimensionally arrange the received signal strength values ​​between every two drones in the drone group obtained by the received signal strength value calculation unit into a second characteristic matrix;

[0021] a correction unit, configured to correct the eigenvalues ​​of each position in the first topological feature matrix obtained by the first convolution unit by using the second feature matrix obtained by the two-dimensional arrangement unit as a correction factor to obtain a second topological feature matrix; and

[0022] A classification unit is used to pass the second topological feature matrix obtained by the correction unit through a classifier to obtain a classification result, and the classification result is used to indicate whether the deployment pattern of each drone in the drone group meets the preset requirements.

[0023] According to another aspect of the present application, an electronic device is provided, comprising: a processor; and a memory, wherein computer program instructions are stored in the memory, and when the computer program instructions are executed by the processor, the processor executes the high-altitude platform equipment collaborative management method as described above.

[0024] According to yet another aspect of the present application, a computer-readable medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the high-altitude platform equipment collaborative management method as described above.

[0025] Compared with the existing technology, the high-altitude platform equipment collaborative management method, system and electronic equipment provided by the present application, while extracting the topological features of the drone group, use a convolutional neural network model to extract the high-dimensional correlation features of the received signals of each drone. In this way, the drones corresponding to the signal feature vectors can be regarded as signal sources and sensors respectively, and the received signal strength values ​​can be calculated to obtain correction values ​​for representing the communication interference between the drones. Further, by correcting the first topology matrix, it is possible to accurately judge whether the deployment pattern of each drone in the drone group meets the preset requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0027] Figure 1 This is a diagram of an application scenario of the high-altitude platform equipment collaborative management method according to an embodiment of the present application;

[0028] Figure 2 Flowchart of a method for collaborative management of high-altitude platform equipment according to an embodiment of the present application;

[0029] Figure 3 Schematic diagram of the system architecture of the high-altitude platform equipment collaborative management method according to an embodiment of the present application;

[0030] Figure 4 1 is a block diagram of a collaborative management system for high-altitude platform equipment according to an embodiment of the present application;

[0031] Figure 5 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described herein.

[0033] Scenario Overview

[0034] As mentioned earlier, in recent years, drone swarm technology has received widespread attention in the industry. Compared with a single drone, a drone swarm can complete more complex and diverse tasks through information interaction and mutual collaboration between drones. It has the advantages of distributed functions, high system survival rate, and high efficiency, and has great potential application value.

[0035] During drone swarm flight, high-precision location information and a well-defined topology are crucial for efficient and reliable execution of various missions. For densely packed drone swarm systems, the drones used are typically rotary-wing aircraft. Due to cost and payload constraints, equipping all drones with high-precision navigation equipment is extremely difficult. Therefore, a collaborative management method for high-altitude platform equipment is desired to accurately determine whether the deployment pattern of each drone in a swarm meets preset requirements and improve the positioning accuracy of each drone in the swarm.

[0036] Specifically, in the technical solution of the present application, the initial distance matrix of the drone swarm is first obtained and input into a convolutional neural network to obtain a first topological feature matrix.

[0037] The received signal of each drone is obtained and input into the convolutional neural network to obtain the signal feature vector.

[0038] For the i-th signal feature vector v i and the jth signal eigenvector v j , regard the corresponding drone as the signal source and sensor respectively, and calculate the received signal strength value:

[0039]

[0040] Where P0 is the transmit power measured at the initial distance d0 for the i-th UAV, γ is the path loss exponent, ||·|| represents the vector norm, i.e., the Euclidean distance, and n p is the occlusion attenuation of a zero-mean Gaussian random variable.

[0041] In this way, a correction value for representing the communication interference between drones can be obtained to form a second characteristic matrix, and the first topological characteristic matrix can be corrected to obtain the second topological characteristic matrix.

[0042] Based on this, the present application proposes a method for collaborative management of high-altitude platform equipment, which includes: obtaining an initial distance matrix of the drone group through the communication module of each drone in the drone group, wherein the value of each position on the non-diagonal position in the initial distance matrix is ​​the distance value between the two drones obtained through communication between the communication modules between the two drones, and the eigenvalue of each position on the diagonal position in the initial distance matrix is ​​zero; passing the initial distance matrix through a first convolutional neural network to obtain a first topological feature matrix; obtaining the received signal of the communication module of each drone in the drone group; passing the received signal of the communication module of each drone through a second convolutional neural network to obtain a signal feature vector corresponding to the received signal of the communication module of each drone; for the i-th signal feature vector v of the i-th drone in the drone group i And the j-th signal feature vector v for the j-th UAV in the UAV group j , consider the i-th UAV and the j-th UAV as the signal source and receiving source respectively, calculate the received signal strength value of the j-th UAV relative to the i-th UAV, the received signal strength value is proportional to the transmit power of the i-th UAV and the i-th signal feature vector v i With the j-th signal feature vector v j The method is related to the second norm of the difference vector between them, the path loss index and the occlusion attenuation value; the received signal strength values ​​between every two drones in the drone group are arranged in two dimensions into a second feature matrix; the eigenvalues ​​of each position in the first topological feature matrix are corrected using the second feature matrix as a correction factor to obtain a second topological feature matrix; and the second topological feature matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the deployment pattern of each drone in the drone group meets the preset requirements.

[0043] Figure 1 The diagram shows an application scenario diagram of the high altitude platform equipment collaborative management method according to an embodiment of the present application. Figure 1 As shown, in this application scenario, first, a drone swarm (e.g., Figure 1 Each UAV (e.g., Figure 1 The communication module (eg, U1-Un) shown in FIG. Figure 1 The initial distance matrix of the drone group is obtained by M) and the received signal of the communication module of each drone in the drone group is obtained. Then, the obtained initial distance matrix of the drone group and the received signal of the communication module of each drone in the drone group are input into a server deployed with a high-altitude platform equipment collaborative management algorithm (for example, Figure 1S) as shown in , wherein the server is capable of processing the initial distance matrix of the drone swarm and the received signals of the communication modules of each drone in the drone swarm using a high-altitude platform equipment collaborative management algorithm to generate a classification result indicating whether the deployment pattern of each drone in the drone swarm meets the preset requirements.

[0044] After introducing the basic principles of the present application, various non-limiting embodiments of the present application will be described in detail with reference to the accompanying drawings.

[0045] Exemplary Methods

[0046] Figure 2 The figure shows a flow chart of the collaborative management method of high-altitude platform equipment. Figure 2 As shown, according to the embodiment of the present application, the collaborative management method of high-altitude platform equipment includes: S110, obtaining the initial distance matrix of the drone group through the communication module of each drone in the drone group, wherein the value of each position on the non-diagonal position in the initial distance matrix is ​​the distance value between the two drones obtained through the communication between the communication modules between the two drones, and the eigenvalue of each position on the diagonal position in the initial distance matrix is ​​zero; S120, passing the initial distance matrix through a first convolutional neural network to obtain a first topological feature matrix; S130, obtaining the received signal of the communication module of each drone in the drone group; S140, passing the received signal of the communication module of each drone through a second convolutional neural network to obtain a signal feature vector corresponding to the received signal of the communication module of each drone; S150, for the i-th signal feature vector v of the i-th drone in the drone group i And the j-th signal feature vector v for the j-th UAV in the UAV group j , consider the i-th UAV and the j-th UAV as the signal source and receiving source respectively, calculate the received signal strength value of the j-th UAV relative to the i-th UAV, the received signal strength value is proportional to the transmit power of the i-th UAV and the i-th signal feature vector v i With the j-th signal feature vector v j The second norm of the difference vector between them, the path loss index and the occlusion attenuation value are related; S160, the received signal strength values ​​between each two drones in the drone group are arranged in two dimensions into a second feature matrix; S170, the eigenvalues ​​of each position in the first topological feature matrix are corrected using the second feature matrix as a correction factor to obtain a second topological feature matrix; and, S180, the second topological feature matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the deployment pattern of each drone in the drone group meets the preset requirements.

[0047] Figure 3 The figure shows a schematic diagram of the architecture of the high-altitude platform equipment collaborative management method according to an embodiment of the present application. Figure 3 As shown, in the network architecture of the high-altitude platform equipment collaborative management method, first, the obtained initial distance matrix (for example, Figure 3 M1) is passed through a first convolutional neural network (e.g., Figure 3 CNN1 as shown in FIG) to obtain a first topological feature matrix (for example, as Figure 3 Then, the received signals of the communication modules of the obtained drones (for example, Figure 3 P1) is passed through a second convolutional neural network (e.g., Figure 3 CNN2 shown in FIG) to obtain the signal feature vectors of the received signals corresponding to the communication modules of each of the drones (for example, Figure 3 Then, for the i-th signal feature vector v of the i-th drone in the drone group, i And the j-th signal feature vector v for the j-th UAV in the UAV group j , consider the i-th UAV and the j-th UAV as the signal source and the receiving source respectively, and calculate the received signal strength value of the j-th UAV relative to the i-th UAV (for example, Figure 3 Then, the received signal strength values ​​between every two drones in the drone group are arranged in two dimensions into a second feature matrix (for example, Figure 3 MF2 shown in FIG); then, the eigenvalues ​​of each position in the first topological characteristic matrix are corrected using the second characteristic matrix as a correction factor to obtain a second topological characteristic matrix (for example, Figure 3 MF shown in FIG); and finally, the second topological feature matrix is ​​passed through a classifier (for example, Figure 3 The classification result is used to indicate whether the deployment pattern of each drone in the drone group meets the preset requirements.

[0048] In steps S110 and S120, an initial distance matrix for the drone swarm is obtained through the communication modules of each drone in the drone swarm, wherein the values ​​for each off-diagonal position in the initial distance matrix are the distance values ​​between two drones obtained through communication between the communication modules, and the eigenvalues ​​for each diagonal position in the initial distance matrix are zero. The initial distance matrix is ​​then passed through a first convolutional neural network to obtain a first topological feature matrix. As previously mentioned, in order to accurately determine whether the deployment pattern of each drone in the drone swarm meets preset requirements and thereby improve the positioning accuracy of each drone in the drone swarm, it is desirable to utilize communication between the drones to obtain the distance between the corresponding two drones. However, considering that two drones may be interfered with by other drones during communication, it is necessary to use communication interference information to correct the topological data for a more accurate determination.

[0049] That is, specifically, in the technical solution of the present application, first, it is necessary to obtain the initial distance matrix of the drone swarm through the communication modules of each drone in the drone swarm. Here, the values ​​of each position on the non-diagonal position in the initial distance matrix are the distance values ​​between the two drones obtained through the communication between the communication modules between the two drones, and the eigenvalues ​​of each position on the diagonal position in the initial distance matrix are zero. Then, the initial distance matrix is ​​processed through the first convolutional neural network to extract the topological features of each drone in the drone swarm, thereby obtaining a first topological feature matrix. Accordingly, in a specific example, each layer of the first convolutional neural network is used to perform convolution processing, pooling processing along the channel dimension and activation processing on the input data during the forward pass of the layer so that the first topological feature matrix is ​​output by the last layer of the first convolutional neural network, wherein the input of the first layer of the first convolutional neural network is the initial distance matrix.

[0050] In step S130 and step S140, the received signal of the communication module of each drone in the drone group is obtained, and the received signal of the communication module of each drone is passed through a second convolutional neural network to obtain a signal feature vector corresponding to the received signal of the communication module of each drone. It should be understood that in the technical solution of the present application, considering that the drone may be interfered with by other drones during communication, it is expected to take the communication interference into account to correct the topology data. That is, specifically, first, the received signal of the communication module of each drone in the drone group is obtained. Then, the received signal of the communication module of each drone is processed through a second convolutional neural network to extract the high-dimensional implicit correlation features of the received signal of the communication module of each drone, thereby obtaining the signal feature vector corresponding to the received signal of the communication module of each drone. Accordingly, in a specific example, each layer of the second convolutional neural network performs convolution processing, feature matrix-based pooling processing and activation processing on the input data during the forward transfer process of the layer to output the signal feature vector by the last layer of the second convolutional neural network, wherein the input of the first layer of the second convolutional neural network is the waveform diagram of the received signal of the communication module of each of the drones.

[0051] In step S150 and step S160, for the i-th signal feature vector v of the i-th drone in the drone group, i And the j-th signal feature vector v for the j-th UAV in the UAV group j , consider the i-th UAV and the j-th UAV as the signal source and receiving source respectively, calculate the received signal strength value of the j-th UAV relative to the i-th UAV, the received signal strength value is proportional to the transmit power of the i-th UAV and the i-th signal feature vector v i With the j-th signal feature vector v j The second norm of the difference vector between them, the path loss index and the occlusion attenuation value are related, and the received signal strength values ​​between each two drones in the drone group are arranged in two dimensions into a second characteristic matrix. It should be understood that in order to use the communication between drones to obtain the distance between the corresponding two drones, so as to obtain a more accurate judgment result on whether the deployment pattern of each drone in the drone group meets the preset requirements, it is necessary to correct the interference information of the drone during communication. That is, in the technical solution of the present application, for the i-th signal characteristic vector v in the drone group i and the jth signal feature vector v in the UAV swarm j, treating the corresponding drones as signal sources and sensors respectively, and calculating the received signal strength value of the j-th drone relative to the i-th drone. This way, a correction value representing the communication interference between the drones can be obtained. Then, the obtained received signal strength values ​​between every two drones in the drone group are two-dimensionally arranged into a second characteristic matrix to facilitate subsequent correction of the first topology matrix.

[0052] Specifically, in the embodiment of the present application, for the i-th signal feature vector v of the i-th drone in the drone group, i And the j-th signal feature vector v for the j-th UAV in the UAV group j , regarding the i-th UAV and the j-th UAV as a signal source and a receiving source, respectively, and calculating the received signal strength value of the j-th UAV relative to the i-th UAV, comprising: calculating the received signal strength value of the j-th UAV relative to the i-th UAV using the following formula, wherein the formula is:

[0053]

[0054] Where P0 is the transmit power of the i-th UAV, measured at the initial distance d0, γ is the path loss exponent, ||·|| represents the vector norm, i.e., the Euclidean distance, and n p is the occlusion attenuation of a zero-mean Gaussian random variable.

[0055] In step S170 and step S180, the second feature matrix is ​​used as a correction factor to correct the eigenvalues ​​of each position in the first topological feature matrix to obtain a second topological feature matrix, and the second topological feature matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the deployment pattern of each drone in the drone swarm meets the preset requirements. That is, in the technical solution of the present application, after obtaining the second feature matrix, the second feature matrix is ​​used as a correction factor to correct the eigenvalues ​​of each position in the first topological feature matrix to obtain a second topological feature matrix. Accordingly, in a specific example, the first topological feature matrix and the second feature matrix are matrix multiplied to map the distance correction information contained in the second feature matrix to the feature space of the first topological feature matrix to obtain the second topological feature matrix. Then, the second topological feature matrix is ​​passed through a classifier to obtain a classification result indicating whether the deployment pattern of each drone in the drone swarm meets the preset requirements.

[0056] Specifically, in an embodiment of the present application, the process of passing the second topological feature matrix through a classifier to obtain a classification result includes: using the classifier to process the second topological feature matrix using the following formula to generate the classification result, wherein the formula is:

[0057] softmax{(W n , B n ):...:(W1,B1)|Project(F)}, where Project(F) represents the projection of the second topological feature matrix into a vector, W1 to W n is the weight matrix of each fully connected layer, B1 to B n Represents the bias matrix of each fully connected layer.

[0058] In summary, the high-altitude platform equipment collaborative management method of the embodiment of the present application is explained. It extracts the topological features of the drone group while using a convolutional neural network model to extract the high-dimensional correlation features of the received signals of each drone. In this way, the drones corresponding to the signal feature vectors can be regarded as signal sources and sensors respectively, and the received signal strength values ​​can be calculated to obtain correction values ​​for representing the communication interference between the drones. Further, by correcting the first topology matrix, it is possible to accurately judge whether the deployment patterns of each drone in the drone group meet the preset requirements.

[0059] Exemplary Systems

[0060] Figure 4 FIG is a block diagram of a high altitude platform equipment collaborative management system according to an embodiment of the present application. Figure 4As shown, according to the embodiment of the present application, the high-altitude platform equipment collaborative management system 400 includes: an initial distance matrix acquisition unit 410, which is used to obtain the initial distance matrix of the drone group through the communication module of each drone in the drone group, wherein the value of each position on the non-diagonal position in the initial distance matrix is ​​the distance value between the two drones obtained through communication between the communication modules between the two drones, and the eigenvalue of each position on the diagonal position in the initial distance matrix is ​​zero; a first convolution unit 420, which is used to pass the initial distance matrix obtained by the initial distance matrix acquisition unit 410 through a first convolutional neural network to obtain a first topological feature matrix; a received signal acquisition unit 430, which is used to obtain the received signal of the communication module of each drone in the drone group; a second convolution unit 440, which is used to pass the received signal of the communication module of each drone obtained by the received signal acquisition unit 430 through a second convolutional neural network to obtain a signal feature vector corresponding to the received signal of the communication module of each drone; a received signal strength value calculation unit 450, which is used to calculate the i-th signal feature vector v of the i-th drone in the drone group obtained by the second convolution unit 440. i And the j-th signal feature vector v for the j-th UAV in the UAV group j , consider the i-th UAV and the j-th UAV as the signal source and receiving source respectively, calculate the received signal strength value of the j-th UAV relative to the i-th UAV, the received signal strength value is proportional to the transmit power of the i-th UAV and the i-th signal feature vector v i With the j-th signal feature vector v j The second norm of the difference vector between them, the path loss index and the occlusion attenuation value are related; a two-dimensional arrangement unit 460 is used to two-dimensionally arrange the received signal strength values ​​between each two drones in the drone group obtained by the received signal strength value calculation unit 450 into a second feature matrix; a correction unit 470 is used to correct the eigenvalues ​​of each position in the first topological feature matrix obtained by the first convolution unit using the second feature matrix obtained by the two-dimensional arrangement unit 460 as a correction factor to obtain a second topological feature matrix; and a classification unit 480 is used to pass the second topological feature matrix obtained by the correction unit 470 through a classifier to obtain a classification result, and the classification result is used to indicate whether the deployment pattern of each drone in the drone group meets the preset requirements.

[0061] In one example, in the above-mentioned high-altitude platform equipment collaborative management system 400, the first convolution unit 420 is further used to: use each layer of the first convolutional neural network to perform convolution processing, pooling processing along the channel dimension and activation processing on the input data during the forward transmission process of the layer to output the first topological feature matrix by the last layer of the first convolutional neural network, wherein the input of the first layer of the first convolutional neural network is the initial distance matrix.

[0062] In one example, in the above-mentioned high-altitude platform equipment collaborative management system 400, the second convolution unit 440 is further used to: each layer of the second convolutional neural network performs convolution processing, feature matrix-based pooling processing and activation processing on the input data during the forward transmission process of the layer to output the signal feature vector by the last layer of the second convolutional neural network, wherein the input of the first layer of the second convolutional neural network is the waveform diagram of the receiving signal of the communication module of each of the drones.

[0063] In one example, in the high-altitude platform equipment collaborative management system 400, the received signal strength value calculation unit 450 is further configured to calculate the received signal strength value of the j-th UAV relative to the i-th UAV using the following formula, wherein the formula is:

[0064]

[0065] Where P0 is the transmit power for the i-th UAV, γ is the path loss exponent, ||·|| represents the vector norm, and n p is the occlusion attenuation of a zero-mean Gaussian random variable.

[0066] In one example, in the above-mentioned high-altitude platform equipment collaborative management system 400, the correction unit 470 is further used to: perform matrix multiplication on the first topological feature matrix and the second feature matrix to map the distance correction information contained in the second feature matrix to the feature space of the first topological feature matrix to obtain the second topological feature matrix.

[0067] In one example, in the above-mentioned high-altitude platform equipment collaborative management system 400, the classification unit 480 is further used to: use the classifier to process the second topological feature matrix using the following formula to generate the classification result, wherein the formula is: softmax{(W n , B n ):...:(W1,B1)|Project(F)}, where Project(F) represents the projection of the second topological feature matrix into a vector, W1 to W n is the weight matrix of each fully connected layer, B1 to Bn Represents the bias matrix of each fully connected layer.

[0068] Here, those skilled in the art will appreciate that the specific functions and operations of the various units and modules in the aerial platform equipment collaborative management system 400 have been described in detail above. Figures 1 to 3 The method has been introduced in detail in the description of the collaborative management method of high-altitude platform equipment, and therefore, its repeated description will be omitted.

[0069] As described above, the high-altitude platform equipment collaborative management system 400 according to the embodiment of the present application can be implemented in various terminal devices, such as a server of the high-altitude platform equipment collaborative management algorithm. In one example, the high-altitude platform equipment collaborative management system 400 according to the embodiment of the present application can be integrated into the terminal device as a software module and / or hardware module. For example, the high-altitude platform equipment collaborative management system 400 can be a software module in the operating system of the terminal device, or it can be an application developed for the terminal device; of course, the high-altitude platform equipment collaborative management system 400 can also be one of the many hardware modules of the terminal device.

[0070] Alternatively, in another example, the high-altitude platform equipment collaborative management system 400 and the terminal device may also be separate devices, and the high-altitude platform equipment collaborative management system 400 may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0071] Exemplary electronic devices

[0072] Below, reference Figure 5 To describe the electronic device according to the embodiment of the present application. Figure 5 As shown, the electronic device 10 includes one or more processors 11 and a memory 12. The processor 11 may be a central processing unit (CPU) or other processing unit having data processing capability and / or instruction execution capability, and may control other components in the electronic device 10 to perform desired functions.

[0073] The memory 12 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the functions of the high-altitude platform equipment collaborative management method of each embodiment of the present application described above and / or other desired functions. Various contents such as received signal strength, signal characteristic vector, etc. may also be stored in the computer-readable storage medium.

[0074] In one example, the electronic device 10 may further include an input system 13 and an output system 14 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0075] The input system 13 may include, for example, a keyboard, a mouse, and the like.

[0076] The output system 14 can output various information to the outside, including classification results, etc. The output system 14 can include, for example, a display, a speaker, a printer, a communication network and its connected remote output devices, etc.

[0077] Of course, to simplify, Figure 5 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device 10 may further include any other appropriate components according to specific application scenarios.

[0078] Exemplary computer program products and computer-readable storage media

[0079] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps in the functions of the high-altitude platform equipment collaborative management method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0080] The computer program product may be written in any combination of one or more programming languages ​​to implement the program code for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0081] In addition, an embodiment of the present application may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the high-altitude platform equipment collaborative management method described in the above-mentioned "Exemplary Method" section of this specification.

[0082] The computer-readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can, for example, include but is not limited to a system, system or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0083] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this application are merely illustrative and not restrictive, and it should not be assumed that these advantages, strengths, and effects are required of each embodiment of this application. In addition, the specific details disclosed above are merely illustrative and facilitating understanding, and are not restrictive. The above details do not limit this application to necessarily being implemented using the above specific details.

[0084] The block diagrams of the devices, devices, equipment, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0085] It should also be noted that in the apparatus, device, and method of the present application, each component or each step can be decomposed and / or recombined, and such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0086] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0087] The above description has been provided for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for collaborative management of high-altitude platform equipment, characterized in that: During the flight of the drone swarm, the method includes the following steps: First, an initial distance matrix of the drone swarm is obtained through the communication modules of each drone in the drone swarm, and a received signal of the communication module of each drone in the drone swarm is obtained; wherein the value of each non-diagonal position in the initial distance matrix is ​​a distance value between two drones obtained through communication between the communication modules of the two drones, and the eigenvalue of each diagonal position in the initial distance matrix is ​​zero; Then, the obtained initial distance matrix of the drone swarm and the received signals of the communication modules of each drone in the drone swarm are input into a server deployed with a high-altitude platform equipment collaborative management algorithm; the server processes the initial distance matrix of the drone swarm and the received signals of the communication modules of each drone in the drone swarm using the high-altitude platform equipment collaborative management algorithm to generate a classification result indicating whether the deployment pattern of each drone in the drone swarm meets preset requirements, including the following steps: Passing the initial distance matrix through a first convolutional neural network to obtain a first topological feature matrix; Passing the received signal of the communication module of each of the drones through a second convolutional neural network to obtain a signal feature vector corresponding to the received signal of the communication module of each of the drones; For the i-th signal feature vector v of the i-th drone in the drone group i And the j-th signal feature vector v for the j-th UAV in the UAV group j , consider the i-th UAV and the j-th UAV as the signal source and receiving source respectively, calculate the received signal strength value of the j-th UAV relative to the i-th UAV; the received signal strength value is proportional to the transmit power of the i-th UAV and the i-th signal feature vector v i With the j-th signal feature vector v j It is related to the second norm of the difference vector, the path loss index and the shielding attenuation value; Arranging the received signal strength values ​​between every two drones in the drone group in two dimensions into a second characteristic matrix; The second feature matrix is ​​used as a correction factor to correct the eigenvalues ​​of each position in the first topological feature matrix to obtain a second topological feature matrix; and the second topological feature matrix is ​​passed through a classifier to obtain a classification result, which is used to indicate whether the deployment pattern of each drone in the drone group meets the preset requirements.

2. The collaborative management method for high-altitude platform equipment according to claim 1, wherein: Passing the initial distance matrix through a first convolutional neural network to obtain a first topological feature matrix includes: Use each layer of the first convolutional neural network to perform convolution processing, pooling processing along the channel dimension and activation processing on the input data during the forward pass of the layer to output the first topological feature matrix by the last layer of the first convolutional neural network, wherein the input of the first layer of the first convolutional neural network is the initial distance matrix.

3. The collaborative management method for high-altitude platform equipment according to claim 2, wherein: Passing the received signal of the communication module of each of the drones through a second convolutional neural network to obtain a signal feature vector corresponding to the received signal of the communication module of each of the drones, comprising: Each layer of the second convolutional neural network performs convolution processing, feature matrix-based pooling processing and activation processing on the input data during the forward transmission process of the layer so that the signal feature vector is output by the last layer of the second convolutional neural network, wherein the input of the first layer of the second convolutional neural network is the waveform diagram of the received signal of the communication module of each of the drones.

4. The method for collaborative management of high-altitude platform equipment according to claim 3, wherein: For the i-th signal feature vector v of the i-th drone in the drone group i And the j-th signal feature vector v for the j-th UAV in the UAV group j , regarding the i-th UAV and the j-th UAV as a signal source and a receiving source, respectively, and calculating the received signal strength value of the j-th UAV relative to the i-th UAV, including: The received signal strength value of the j-th UAV relative to the i-th UAV is calculated using the following formula, where the formula is: Where P0 is the transmit power measured for the i-th UAV at the initial distance d0; γ is the path loss exponent; ||·|| represents the vector norm, i.e., the Euclidean distance; and n p is the occlusion attenuation of a zero-mean Gaussian random variable.

5. The method for collaborative management of high-altitude platform equipment according to claim 4, wherein: Using the second characteristic matrix as a correction factor to correct the eigenvalues ​​of each position in the first topological characteristic matrix to obtain a second topological characteristic matrix, comprising: The first topological feature matrix and the second feature matrix are matrix-multiplied to map the distance correction information contained in the second feature matrix into the feature space of the first topological feature matrix to obtain the second topological feature matrix.

6. The method for collaborative management of high-altitude platform equipment according to claim 5, wherein: Passing the second topological feature matrix through a classifier to obtain a classification result includes: The second topological feature matrix is ​​processed using the classifier according to the following formula to generate the classification result, wherein the formula is: softmax{(W n ,B n ):…:(W1,B1)|Project(F)}, where Project(F) represents the projection of the second topological feature matrix into a vector, W1 to W n is the weight matrix of each fully connected layer, B1 to B n Represents the bias matrix of each fully connected layer.

7. A high-altitude platform equipment collaborative management system is a server deployed with a high-altitude platform equipment collaborative management algorithm, characterized in that: Inputting an initial distance matrix of the drone swarm obtained through the communication modules of each drone in the drone swarm and a received signal of the communication module of each drone in the drone swarm into a server; the server processes the initial distance matrix of the drone swarm and the received signal of the communication module of each drone in the drone swarm using a high-altitude platform equipment collaborative management algorithm to generate a classification result indicating whether the deployment pattern of each drone in the drone swarm meets preset requirements; The high-altitude platform equipment collaborative management system includes: an initial distance matrix acquisition unit, configured to acquire an initial distance matrix of the drone swarm through the communication modules of the respective drones in the drone swarm, wherein the values ​​of each non-diagonal position in the initial distance matrix are distance values ​​between two drones obtained through communication between the communication modules thereof, and the eigenvalues ​​of each diagonal position in the initial distance matrix are zero; a first convolution unit, configured to pass the initial distance matrix obtained by the initial distance matrix obtaining unit through a first convolutional neural network to obtain a first topological feature matrix; a received signal acquisition unit, configured to acquire a received signal from a communication module of each drone in the drone group; A second convolution unit is configured to pass the received signals of the communication modules of the drones obtained by the received signal acquisition units through a second convolutional neural network to obtain signal feature vectors corresponding to the received signals of the communication modules of the drones; A received signal strength value calculation unit is used to calculate the i-th signal feature vector v of the i-th drone in the drone group obtained by the second convolution unit. i And the j-th signal feature vector v for the j-th UAV in the UAV group j , consider the i-th UAV and the j-th UAV as the signal source and receiving source respectively, calculate the received signal strength value of the j-th UAV relative to the i-th UAV, the received signal strength value is proportional to the transmit power of the i-th UAV and the i-th signal feature vector v i With the j-th signal feature vector v j It is related to the second norm of the difference vector, the path loss index and the shielding attenuation value; a two-dimensional arrangement unit, configured to two-dimensionally arrange the received signal strength values ​​between every two drones in the drone group obtained by the received signal strength value calculation unit into a second characteristic matrix; a correction unit, used to correct the eigenvalues ​​of each position in the first topological feature matrix obtained by the first convolution unit using the second feature matrix obtained by the two-dimensional arrangement unit as a correction factor to obtain a second topological feature matrix; and a classification unit, used to pass the second topological feature matrix obtained by the correction unit through a classifier to obtain a classification result, wherein the classification result is used to indicate whether the deployment pattern of each drone in the drone swarm meets the preset requirements.

8. The high-altitude platform equipment collaborative management system according to claim 7, wherein: The first convolution unit is further configured to: Use each layer of the first convolutional neural network to perform convolution processing, pooling processing along the channel dimension and activation processing on the input data during the forward pass of the layer to output the first topological feature matrix by the last layer of the first convolutional neural network, wherein the input of the first layer of the first convolutional neural network is the initial distance matrix.

9. The high-altitude platform equipment collaborative management system according to claim 7, wherein: The received signal strength value calculation unit is further configured to calculate the received signal strength value of the j-th UAV relative to the i-th UAV using the following formula, wherein the formula is: Where P0 is the transmit power measured for the i-th UAV at the initial distance d0, γ is the path loss exponent, ||·|| represents the vector two norm, i.e., the Euclidean distance; and n p is the occlusion attenuation of a zero-mean Gaussian random variable.

10. An electronic device comprising: processor; and a memory, wherein computer program instructions are stored in the memory, and when the computer program instructions are executed by the processor, the processor executes the high-altitude platform equipment collaborative management method according to any one of claims 1 to 6.

Images