UAV semantic communication method, device, electronic device, storage medium and program product

Abstract

The present disclosure provides a method, apparatus, electronic device, storage medium, and program product for semantic communication between unmanned aerial vehicles (UAVs), including: determining user location information, and obtaining channel gain data based on the user location information; determining an original transmit signal, and inputting it and the channel gain data into a pre-trained data transmission optimization model; optimizing the original transmit signal based on the channel gain data by the data transmission optimization model, and outputting an optimized transmit signal; determining noise information of the communication channel, and combining it with the channel gain data and the optimized transmit signal to obtain an original receive signal; inputting the original receive signal and the channel gain data into the data transmission optimization model; optimizing the original receive signal based on the channel gain data by the transmission data optimization model, and outputting an optimized receive signal. The present disclosure can improve the ability to collect mobile user data in UAV applications and significantly enhance the quality of data information restoration.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wireless communication networks, and in particular to a method, device, electronic device, storage medium, and program product for semantic communication between unmanned aerial vehicles (UAVs). Background Art

[0002] This section is intended to provide a background or context to the embodiments of the present disclosure that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] Drone communication is a technology that uses drones as aerial platforms to enhance or restore the connectivity of ground communication networks. Drones can carry communication equipment to provide wireless signal coverage for ground users. Signal processing refers to the general term for the extraction, transformation, analysis, and synthesis of signals. Its basic contents include transformation, filtering, modulation, demodulation, detection, spectrum analysis, and estimation.

[0004] However, in related technologies, mobile user information cannot be collected efficiently in drone scenarios, and the reconstruction quality of the data information is not high. Summary of the Invention

[0005] In view of this, the purpose of the present disclosure is to propose a drone semantic communication method, device, electronic device, storage medium and program product, which can at least to some extent solve one of the technical problems in the related art.

[0006] Based on the above objectives, the first aspect of the exemplary embodiments of the present disclosure provides a drone semantic communication method, which is applied to a server. The method includes:

[0007] Determining user location information, and obtaining channel gain data based on the user location information;

[0008] Determining an original transmit signal, inputting the original transmit signal and the channel gain data into a pre-trained data transmission optimization model, optimizing the original transmit signal based on the channel gain data using the data transmission optimization model, and outputting an optimized transmit signal;

[0009] Determining noise information of a communication channel, and obtaining an original received signal based on the noise information, the channel gain data, and the optimized transmitted signal;

[0010] The original received signal and the channel gain data are input into the data transmission optimization model, and the original received signal is optimized based on the channel gain data by the transmission data optimization model to output an optimized received signal.

[0011] Based on the same inventive concept, a second aspect of the exemplary embodiment of the present disclosure provides a drone semantic communication device, comprising:

[0012] a gain data determination module, configured to determine user location information, and obtain channel gain data based on the user location information;

[0013] a transmission signal determination module configured to determine an original transmission signal, input the original transmission signal and the channel gain data into a pre-trained data transmission optimization model, optimize the original transmission signal based on the channel gain data using the data transmission optimization model, and output an optimized transmission signal;

[0014] an original received signal determination module, configured to determine noise information of a communication channel, and obtain an original received signal based on the noise information, the channel gain data, and the optimized transmit signal;

[0015] The optimized received signal determination module is configured to input the original received signal and the channel gain data into the data transmission optimization model, optimize the original received signal based on the channel gain data through the transmission data optimization model, and output an optimized received signal.

[0016] Based on the same inventive concept, the third aspect of the exemplary embodiment of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the first aspect is implemented.

[0017] Based on the same inventive concept, a fourth aspect of the exemplary embodiment of the present disclosure provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method described in the first aspect.

[0018] Based on the same inventive concept, a fifth aspect of the exemplary embodiments of the present disclosure provides a computer program product, including computer program instructions. When the computer program instructions are executed on a computer, the computer is caused to execute the method described in the first aspect.

[0019] As can be seen from the above, the embodiments of the present disclosure provide a method, device, electronic device, storage medium, and program product for drone semantic communication. The method includes:

[0020] Determine user location information, and obtain channel gain data based on the user location information; determine the original transmission signal, input the original transmission signal and the channel gain data into a pre-trained data transmission optimization model, optimize the original transmission signal based on the channel gain data through the data transmission optimization model, and output an optimized transmission signal; determine the noise information of the communication channel, and obtain the original reception signal based on the noise information, the channel gain data, and the optimized transmission signal; input the original reception signal and the channel gain data into the data transmission optimization model, optimize the original reception signal based on the channel gain data through the transmission data optimization model, and output an optimized reception signal. The present disclosure can improve the ability to collect mobile user data in a drone application environment and significantly enhance the restoration quality of data information. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A schematic diagram of an application scenario of the UAV semantic communication method provided by an exemplary embodiment of the present disclosure;

[0023] Figure 2 A flowchart of a UAV semantic communication method provided by an exemplary embodiment of the present disclosure;

[0024] Figure 3 A schematic structural diagram of a UAV semantic communication device provided by an exemplary embodiment of the present disclosure;

[0025] Figure 4 A schematic diagram of the hardware structure of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] It is understandable that before using the technical solutions disclosed in the embodiments of this application, the type, scope of use, usage scenarios, etc. of the personal information involved in this application should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0027] For example, in response to receiving a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. Thus, based on the prompt message, the user can independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operation of the technical solution of this application.

[0028] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0029] It is understandable that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this application. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this application.

[0030] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0031] To make the objectives, technical solutions, and advantages of the present disclosure more clearly understood, the principles and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0032] It should be understood herein that any number of elements in the drawings is for illustration only and not for limitation, and any naming is only for distinction and does not have any limiting meaning.

[0033] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should have the usual meanings understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. The article "one" or "an" before an element does not exclude the presence of multiple such elements.

[0034] The principles and spirit of the present disclosure are explained in detail below with reference to several representative embodiments of the present disclosure.

[0035] As described in the background technology, in the related art, mobile user information cannot be collected efficiently in drone scenarios, and the reconstruction quality of data information is not high. Specifically, in the related art, drones are used to collect visual information in the real world, and then deep learning technology is used to analyze the collected data, extract core semantic information, and construct a scene graph; in order to efficiently distribute these semantically rich data to virtual service providers (VSPs) in need, this technical solution adopts a combinatorial auction method, allowing VSPs to bid based on the importance and value of the data to their own services; once the bid is successful, the drone will send the corresponding semantic information to the winning VSP, and the VSP will then use this information to update the various services it provides in the metaverse, such as virtual tourism, online meetings and other services; the entire process includes automated data collection, extraction of semantic information, auction process and update of metaverse services, ensuring the synchronization and consistency of virtual environment and real-world data.

[0036] However, although this technical solution collects data through drones and uses deep learning models to extract semantic information to support metaverse services, it focuses on the semantic processing of data and the design of auction mechanisms; the comparative document only treats drones as fixed edge devices in the scenario and trains them under an additive white Gaussian noise (AWGN) channel with a specific signal-to-noise ratio (SNR), lacking the use of its dynamics and optimization research on corresponding problems.

[0037] Among the related technologies, the importance of personalization for specific tasks was explored in depth, and an innovative semantic communication architecture was developed. This architecture can customize the weight distribution of image data based on the user's personal preferences and specific task requirements, thereby improving the level of personalization and efficiency in the communication process. In a drone network environment, this technical solution has been verified through simulation experiments. By changing the distance between the drone and the user, the experiment demonstrated how the relative position between the drone and the user significantly affects the performance of semantic communication.

[0038] However, this technical solution only demonstrates the effect of the relative position between the drone and the user on the image transmission quality through a trial-by-trial approach. This solution does not take into account the dynamic adjustment of the drone's position. When the user's geographical location changes, this technical solution cannot effectively adapt to these changes, and thus cannot guarantee the stability and reliability of communication quality. Therefore, this technical solution fails to achieve flexible optimization of the drone's position to meet the communication challenges brought about by user movement.

[0039] Among the related technologies, the focus is on the transmission of image data when drones perform classification tasks. By installing a lightweight model on the drone and applying deep reinforcement learning technology, this solution can select the semantic information blocks that contribute most to the classification task for transmission, and send the collected image information to the back-end mobile edge computing platform for in-depth analysis. Considering the limitations of drones in storage and processing capabilities, how to efficiently transmit data that is critical to artificial intelligence algorithms has become a key issue. Therefore, deep reinforcement learning technology is used to accurately identify and transmit the semantic information blocks that are most critical to the classification algorithm, and at the same time, optimize the balance between transmission delay and classification accuracy under different channel conditions.

[0040] However, this technical solution mainly focuses on selecting important semantic information blocks and improving transmission efficiency, but when dealing with changes in the positions of drones and users, it only optimizes the channel gain by simplifying it to a few fixed discrete values. This solution does not deeply consider the specific impact of the dynamically changing positions between drones and users on communication quality, and lacks research on the comprehensive optimization of semantic signal power allocation and drone positions. This may lead to the inability to achieve optimal signal coverage and transmission efficiency in certain dynamic environments, thereby affecting the flexibility of communication strategies and overall communication performance. Therefore, this technical solution has limitations in adapting to user mobility and optimizing communication quality.

[0041] To solve the above problems, the present disclosure provides a method, device, electronic device, storage medium, and program product solution for drone semantic communication, specifically including:

[0042] Determine user location information, and obtain channel gain data based on the user location information; determine the original transmission signal, input the original transmission signal and the channel gain data into a pre-trained data transmission optimization model, optimize the original transmission signal based on the channel gain data through the data transmission optimization model, and output an optimized transmission signal; determine the noise information of the communication channel, and obtain the original reception signal based on the noise information, the channel gain data, and the optimized transmission signal; input the original reception signal and the channel gain data into the data transmission optimization model, optimize the original reception signal based on the channel gain data through the transmission data optimization model, and output an optimized reception signal. The present disclosure obtains user location information, calculates channel gain data, and optimizes the original transmission signal and reception signal using a pre-trained data transmission optimization model, ultimately obtaining an optimized transmission signal and an optimized reception signal, thereby improving the efficiency of mobile user information collection and the quality of data reconstruction in drone scenarios.

[0043] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.

[0044] refer to Figure 1 , which is a schematic diagram of an application scenario of the drone semantic communication method provided by the exemplary embodiment of the present disclosure.

[0045] This application scenario includes a terminal device 101 and a server 102. The terminal device 101 and the server 102 may be connected via a wired or wireless communication network to achieve data interaction.

[0046] The terminal device 101 can be an electronic device close to the user with data transmission and multimedia input / output functions, including but not limited to a desktop computer, a mobile phone, a mobile computer, a tablet computer, a media player, a smart wearable device, a personal digital assistant (PDA), or other electronic devices capable of implementing the above functions. The electronic device may include a processor and a display screen with touch input function, the display screen is used to present a graphical user interface, and the graphical user interface can display an application interface. The processor is used to process application data, generate the graphical user interface, and control the display of the graphical user interface on the display screen.

[0047] Server 102 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0048] In some exemplary embodiments, the drone semantic communication method can be run on the terminal device 101 or the server 102.

[0049] When the drone semantic communication method is run on the server 102 , the server 102 is used to provide drone semantic communication services to the user of the terminal device 101 .

[0050] The server 102 determines user location information, and the server 102 obtains channel gain data based on the user location information;

[0051] The server 102 determines an original transmission signal, and inputs the original transmission signal and the channel gain data into a pre-trained data transmission optimization model. The server 102 optimizes the original transmission signal based on the channel gain data using the data transmission optimization model, and outputs an optimized transmission signal.

[0052] The server 102 determines noise information of the communication channel, and the server 102 obtains an original received signal based on the noise information, the channel gain data, and the optimized transmitted signal;

[0053] The server 102 inputs the original received signal and the channel gain data into the data transmission optimization model. The server 102 optimizes the original received signal based on the channel gain data through the transmission data optimization model and outputs an optimized received signal.

[0054] It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principles of the present disclosure, and the embodiments of the present disclosure are not limited in this respect. On the contrary, the embodiments of the present disclosure can be applied to any applicable scenario.

[0055] refer to Figure 2 ,UAV semantic communication method, applied to a server, the method comprises the following steps:

[0056] Step S210: Determine user location information, and obtain channel gain data based on the user location information.

[0057] In specific implementations, the method for determining user location information includes, but is not limited to, at least one of the following:

[0058] Obtain user location information through positioning technology, specifically, use the Global Positioning System (GPS) or other positioning technologies (such as cellular network triangulation, Wi-Fi positioning, Bluetooth positioning, etc.) to determine the user's geographic location, obtain user location information through drone sensor data, specifically, use sensors on drones or user devices (such as accelerometers, gyroscopes, magnetometers, etc.) to track user movements and location changes, and use signal characteristics of user devices to obtain user location information, specifically, analyze signal characteristics sent from user devices, such as signal arrival time (TOA), signal arrival angle (AOA) or signal strength (RSSI) to estimate the user's location, or obtain user location information through a communication network, specifically, through interaction with the communication network, such as feedback information from base stations, to determine the user's location relative to the network infrastructure.

[0059] In the above exemplary embodiment, a method for obtaining user location information is introduced. The following describes a method for obtaining channel gain data:

[0060] In this exemplary embodiment, obtaining channel gain data based on the user location information includes:

[0061] Determine the rated transmit power of user information communication, and obtain the drone base station location based on the user location information and the rated transmit power; perform path loss calculation based on the user location information and the drone base station location to obtain the channel gain data.

[0062] In specific implementations, the methods for determining the rated transmit power of user information communication include, but are not limited to, at least one of the following:

[0063] The rated transmit power of user information communication is obtained by evaluating the capabilities of user devices. Specifically, the hardware capabilities of the user devices are evaluated, including battery life, transmit power limit, and device performance, to determine the maximum transmit power that each user device can support. The rated transmit power of user information communication is obtained through communication protocol standards. Specifically, the rated transmit power of the user device is determined based on the power level specified by wireless communication protocols and standards (such as 3GPP, Wi-Fi Alliance, etc.), or the power category and allowed power range of the user device are understood through network configuration information provided by the wireless network operator.

[0064] In a specific implementation, obtaining the drone base station location based on the user location information and the rated transmit power means:

[0065] As a specific example, assume that a UAV base station collects information about N users on the ground. The user set is represented as N={1,2,…,n,…,N}, and the position of user n is represented as ; Among them, the maximum transmission power of each user As weight, the updated position of the drone base station is set to the weighted centroid of the user's position, and the position of the drone Expressed as:

[0066] .

[0067] In a specific implementation, performing path loss calculation based on the user location information and the drone base station location to obtain the channel gain data means:

[0068] Following the above exemplary embodiment, the position information of the user and the drone base station is used to calculate the straight-line distance between the two, and the calculated distance is substituted into the free space path loss model. The path loss Expressed as:

[0069] ;

[0070] in It's distance, is the frequency, is the speed of light, and the constant term includes antenna gain and polarization loss, etc.; considering the impact of environmental factors on signal propagation, such as buildings, terrain, weather conditions, etc., these factors may increase additional path loss, channel gain It can be expressed as the inverse of the path loss, that is, , channel gain , channel gain It will be fed back to both the sending user and the receiving drone base station at the same time.

[0071] Step S220: determine the original transmission signal, input the original transmission signal and the channel gain data into a pre-trained data transmission optimization model, optimize the original transmission signal based on the channel gain data through the data transmission optimization model, and output an optimized transmission signal.

[0072] In this exemplary embodiment, determining the original transmitted signal includes:

[0073] Determine the data to be transmitted, perform semantic extraction on the data to be transmitted to obtain semantic feature information; normalize the semantic feature information to obtain the original transmission signal.

[0074] During specific implementation, the data to be transmitted includes but is not limited to at least one of the following:

[0075] Text data, audio data, image data or video data.

[0076] In a specific implementation, performing semantic extraction on the data to be transmitted to obtain semantic feature information means:

[0077] Following the above exemplary embodiment, it is assumed that the information transmitted by the user is an image, and the image data they transmit is recorded as , under the AWGN channel condition with fixed user position, the Joint Source-Channel (JSC) codec is and The purpose of training is to obtain a set of high-performance codecs under simple channels. , which focuses on semantic feature extraction of the source and provides a foundation for the next layer of semantic signal processing. The process is described in detail as follows:

[0078] JSC Encoder Image to be transmitted from user n The semantic features extracted from Expressed as:

[0079] ;

[0080] Among them, C represents the complex field, that is, a set of real and imaginary numbers, K represents the number of subcarriers, and I is the number of OFDM-NOMA symbols (referring to the number of independent symbols that the system can transmit within one OFDM symbol period. Each OFDM symbol is composed of modulation symbols on multiple subcarriers. These subcarriers are orthogonal in frequency and can transmit data simultaneously without interfering with each other. In the NOMA system, these OFDM symbols can be used to serve multiple users at the same time, and the user data is superimposed together through different power levels). Each symbol carries K semantic features that need to be transmitted.

[0081] In a specific implementation, normalizing the semantic feature information to obtain the original transmitted signal means:

[0082] Following the above exemplary embodiment, since the transmission power of each user is constrained by their own hardware equipment, it is necessary to convert the semantic features of each OFDM-NOMA symbol of the user on all subcarriers into Normalize to get the transmission signal ;

[0083] ;

[0084] in represents the maximum average transmit power of user n on all subcarriers in each OFDM-NOMA symbol.

[0085] In the above exemplary embodiment, a method for obtaining the original transmission signal is introduced. Now, a method for training the data transmission optimization model is introduced:

[0086] In this exemplary embodiment, the method of training the data transmission optimization model includes:

[0087] Construct a sample set including several samples; wherein the samples include: sample data and label data; the sample data includes an original transmission signal for training and an original reception signal for training; the label data includes an optimized transmission signal for training corresponding to the original transmission signal for training and an optimized reception signal for training corresponding to the original reception signal for training; input the sample data into the data transmission optimization model to obtain predicted data output by the model, wherein the predicted data includes a reconstructed transmission signal and a reconstructed reception signal output by the model; determine a first difference between the predicted data and the label data; based on the first difference, update the model parameters through a loss function until the difference between the predicted data and the label data is minimized, thereby obtaining the pre-trained data transmission optimization model.

[0088] In a specific implementation, a sample set including several samples is constructed; wherein the samples include: sample data and label data; the sample data includes the original transmitted signal for training and the original received signal for training, which means:

[0089] Following the above exemplary embodiments, the encoder and decoder are used to When providing communication services to users, users are divided into Group, represented by After the channel transmission, the UAV base station will receive the superimposed power signal, of which the superimposed signal received by the qth group of users is Expressed as

[0090] ;

[0091] in is the path loss between the UAV base station and user n at a fixed location, represents the noise matrix, It not only represents the transmission signal, but also the original transmission signal used for data transmission optimization model training. It not only represents the received signal, but also the original received signal used for data transmission optimization model training.

[0092] In a specific implementation, the sample data is input into the data transmission optimization model to obtain the predicted data output by the model, wherein the predicted data includes the reconstructed transmission signal and the reconstructed reception signal output by the model, which means:

[0093] Following the above exemplary embodiment, the JSC decoder deployed at the drone base station The received superimposed signal Y Decode and get the reconstructed image , expressed as:

[0094] .

[0095] In a specific implementation, determining a first difference between the predicted data and the labeled data; and updating model parameters based on the first difference using a loss function until the difference between the predicted data and the labeled data is minimized, thereby obtaining the pre-trained data transmission optimization model.

[0096] in , during the training process of the semantic feature extraction layer, the loss function of minimizing the error between the reconstructed image and the original image is:

[0097] ;

[0098] Obtaining a data transmission optimization model include encoders and a single decoder.

[0099] In the above exemplary embodiment, a method of training a data transmission optimization model is introduced. Now, a method of obtaining an optimized transmission signal is introduced:

[0100] In a specific implementation, the original transmission signal and the channel gain data are input into a pre-trained data transmission optimization model, and the original transmission signal is optimized based on the channel gain data by the data transmission optimization model, and the optimized transmission signal is outputted.

[0101] Following the above exemplary embodiment, the original transmission signal passes through the transmitting end semantic signal processor in the data transmission optimization model Get the optimized sending signal , the process is expressed as:

[0102] ;

[0103] in, Represents the originating semantic signal processor of the data transmission optimization model in the case where a drone follows a user.

[0104] Step S230: Determine noise information of the communication channel, and obtain an original received signal based on the noise information, the channel gain data, and the optimized transmitted signal.

[0105] In a specific implementation, determining the noise information of the communication channel means:

[0106] In a simulation environment, noise information is usually randomly generated based on the statistical characteristics of the channel, such as noise power spectral density and noise distribution (usually Gaussian distribution), to simulate the interference in the actual communication process. In an actual communication system, noise information can be measured by the signal processing hardware at the receiving end.

[0107] In the above exemplary embodiment, a method for obtaining noise information of a communication channel is introduced. Now, a method for obtaining an original received signal is introduced:

[0108] In this exemplary embodiment, obtaining an original received signal based on the noise information, the channel gain data, and the optimized transmit signal includes:

[0109] The noise information, the channel gain data, and the optimized transmit signal of at least one user are determined, and the noise information of the at least one user is added to the sum of the products of the channel gain data and the optimized transmit signal to obtain the original received signal.

[0110] In a specific implementation, determining the noise information, the channel gain data, and the optimized transmit signal of at least one user, and adding the noise information of the at least one user to the sum of the products of the channel gain data and the optimized transmit signal to obtain the original received signal means:

[0111] Following the above exemplary embodiment, under the changing drone-user position and channel conditions, the received signal of the qth group of non-orthogonal users at the base station is Expressed as:

[0112] ;

[0113] in and Consistently represent the noise matrix, and Both represent noise matrices, But they represent the noise characteristics under different processing stages; It is usually the additive noise matrix under the initial assumption that the channel gain is fixed and the transmitted signal is not optimized. It reflects the random noise inherent in the received signal, which may come from thermal noise, intermodulation interference or other interference factors in the process of wireless signal propagation. It is the new noise matrix after optimization at the receiving end. It may take into account the changes in the noise model during the optimization process, such as the impact of the signal processing algorithm on the noise, the introduction of channel estimation errors, or the changes in noise characteristics due to changes in the transmitted signal and channel conditions.

[0114] Step S240: Input the original received signal and the channel gain data into the data transmission optimization model, optimize the original received signal based on the channel gain data through the transmission data optimization model, and output an optimized received signal.

[0115] In a specific implementation, inputting the original received signal and the channel gain data into the data transmission optimization model, optimizing the original received signal based on the channel gain data by the transmission data optimization model, and outputting the optimized received signal means:

[0116] At the drone base station, the receiving semantic signal processor in the data transmission optimization model The original received signal Processing to obtain the optimized received signal Expressed as:

[0117] .

[0118] Based on the above exemplary embodiments, an optimized received signal can be obtained. , below, we introduce the received signal based on the optimization How to update the loss function in the data transfer optimization model:

[0119] Determine a second difference between the optimized received signal and the original received signal for training; and update the loss function of the data transmission optimization model based on the first difference and the second difference.

[0120] In a specific implementation, determining the second difference between the optimized received signal and the original received signal for training refers to:

[0121] Following the above exemplary embodiment, in the end-to-end training process, due to the data transmission optimization model The parameters are frozen, and the training set can be the original transmission signal in addition to the image dataset M. ; In order to achieve the optimized received signal Adaptive decoder In the present exemplary embodiment, the semantic signal error function is defined as:

[0122] .

[0123] In a specific implementation, updating the loss function of the data transmission optimization model based on the first difference and the second difference means:

[0124] Combining image distortion and semantic signal error, a hybrid loss function is proposed to train the semantic signal processor at the transceiver end, which is expressed as

[0125] ;

[0126] in and are the weights of the two parts of distortion to balance the numerical differences caused by different data meanings; due to the semantic signal error of the second part The gradient of the network parameters does not pass through the JSC encoder, so the gradient disappearance phenomenon will not occur, which can better guide the training process and enable the network to converge gradually; while the first part is distorted After the second part of the distortion guidance converges, it can also assist in enhancing image reconstruction quality. In summary, end-to-end training of the semantic signal processors at the transceiver and receiver enables the transmitted signal to adapt to changes in user location, improving the image reconstruction quality at the receiver and meeting the high concurrency requirements of mobile users.

[0127] It should be noted that the method of the embodiments of the present disclosure can be performed by a single device, such as a computer or server. The method of the embodiments of the present disclosure can also be applied in a distributed scenario, where multiple devices cooperate to perform the method. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiments of the present disclosure, and the multiple devices will interact with each other to complete the method.

[0128] It should be noted that the above description is limited to some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0129] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a drone semantic communication device.

[0130] refer to Figure 3 , the UAV semantic communication device comprises:

[0131] The gain data determination module 310 is configured to determine user location information and obtain channel gain data based on the user location information;

[0132] a transmission signal determination module 320 configured to determine an original transmission signal, input the original transmission signal and the channel gain data into a pre-trained data transmission optimization model, optimize the original transmission signal based on the channel gain data using the data transmission optimization model, and output an optimized transmission signal;

[0133] The original received signal determination module 330 is configured to determine noise information of the communication channel, and obtain an original received signal based on the noise information, the channel gain data and the optimized transmitted signal;

[0134] The optimized received signal determination module 340 is configured to input the original received signal and the channel gain data into the data transmission optimization model, optimize the original received signal based on the channel gain data through the transmission data optimization model, and output an optimized received signal.

[0135] In this exemplary embodiment, the gain data determination module 310 is specifically configured to:

[0136] Determine the user location information and the rated power of the user information communication, and obtain the drone base station location based on the user location information and the rated power; perform path loss calculation based on the user location information and the drone base station location to obtain the channel gain data; obtain the channel gain data based on the user location information.

[0137] In this exemplary embodiment, the signal transmission determination module 320 is specifically configured to:

[0138] Determine the data to be transmitted, perform semantic extraction on the data to be transmitted, and obtain semantic feature information; normalize the semantic feature information to obtain the original transmission signal; input the original transmission signal and the channel gain data into a pre-trained data transmission optimization model, optimize the original transmission signal based on the channel gain data through the data transmission optimization model, and output an optimized transmission signal; a method of training the data transmission optimization model: construct a sample set including a plurality of samples; wherein the samples include: sample data and label data; the sample data include the original transmission signal for training and the original reception signal for training; the label data include the optimized transmission signal for training corresponding to the original transmission signal for training and the optimized reception signal for training corresponding to the original reception signal for training; input the sample data into the data transmission optimization model to obtain predicted data output by the model, wherein the predicted data include the reconstructed transmission signal and the reconstructed reception signal output by the model; determine a first difference between the predicted data and the label data; based on the first difference, update the model parameters through the loss function until the difference between the predicted data and the label data is minimized, thereby obtaining the pre-trained data transmission optimization model.

[0139] In this exemplary embodiment, the original received signal determination module 330 is specifically configured to:

[0140] Determine noise information of a communication channel, the noise information of at least one user, the channel gain data, and the optimized transmit signal, and add the noise information of the at least one user to the sum of the products of the channel gain data and the optimized transmit signal to obtain the original received signal.

[0141] In this exemplary embodiment, the optimized received signal determination module 340 is specifically configured to:

[0142] The original received signal and the channel gain data are input into the data transmission optimization model, and the original received signal is optimized based on the channel gain data by the transmission data optimization model to output an optimized received signal; after outputting the optimized received signal, the method further includes: determining a second difference between the optimized received signal and the original received signal for training; and updating the loss function of the data transmission optimization model based on the first difference and the second difference.

[0143] For the convenience of description, the above devices are described as being functionally divided into various modules. Of course, when implementing the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0144] The device of the above embodiment is used to implement the corresponding drone semantic communication method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0145] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the program, the drone semantic communication method described in any of the above embodiments is implemented.

[0146] Figure 4 10 is a schematic diagram showing a more specific hardware structure of an electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other within the device via the bus 1050.

[0147] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0148] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 1020 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0149] The input / output interface 1030 is used to connect to an input / output module to enable information input and output. The input / output module can be configured as a component within the device (not shown) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc. Output devices may include a display, speaker, vibrator, indicator light, etc.

[0150] The communication interface 1040 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, Wi-Fi, Bluetooth, etc.).

[0151] The bus 1050 comprises a pathway for transmitting information between various components of the device, such as the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 .

[0152] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, it will be understood by those skilled in the art that the above device may only include the components necessary to implement the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0153] The electronic device of the above embodiment is used to implement the corresponding drone semantic communication method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0154] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the drone semantic communication method described in any of the above embodiments.

[0155] The computer-readable media of this embodiment includes permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0156] The above-mentioned non-transitory computer-readable storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO)), optical storage (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (such as ROMs, EPROMs, EEPROMs, non-volatile memories (NAND FLASH), solid-state drives (SSDs)), etc.

[0157] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the drone semantic communication method described in any embodiment in the above exemplary method section, and have the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0158] Based on the same inventive concept, corresponding to the drone semantic communication method described in any of the above embodiments, the present disclosure also provides a computer program product comprising computer program instructions. In some embodiments, the computer program instructions can be executed by one or more processors of a computer to cause the computer and / or the processor to perform the drone semantic communication method. For the execution entities corresponding to the steps in each embodiment of the drone semantic communication method, the processors executing the corresponding steps can belong to the corresponding execution entities.

[0159] The computer program product of the above embodiment is used to enable the computer and / or the processor to execute the drone semantic communication method as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0160] Those skilled in the art will appreciate that embodiments of the present disclosure may be implemented as a system, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the present disclosure may be implemented in the form of a computer program product embodied in one or more computer-readable media containing computer-readable program code.

[0161] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (non-exhaustive) of computer-readable storage media may include, for example, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0162] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0163] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0164] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0165] It should be understood that each block in the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine. These computer program instructions are executed by the computer or other programmable data processing device to produce a device that implements the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0166] These computer program instructions can also be stored in a computer-readable medium that enables a computer or other programmable data processing device to operate in a specific manner. In this way, the instructions stored in the computer-readable medium produce a product that includes an instruction device that implements the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0167] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, such that the instructions executed on the computer or other programmable apparatus provide a process that implements the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0168] Furthermore, although the operations of the disclosed method are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in that particular order, or that all of the operations shown must be performed to achieve the desired results. Rather, the steps depicted in the flowcharts may be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into a single step, and / or a single step may be broken down into multiple steps.

[0169] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0170] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0171] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. Within the scope of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0172] In addition, to simplify the description and discussion, and to avoid obscuring the embodiments of the present application, well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures. Furthermore, devices may be shown in block diagram form to avoid obscuring the embodiments of the present application, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present application will be implemented (i.e., these details should be fully understood by those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present application, it will be apparent to those skilled in the art that the embodiments of the present application can be implemented without these specific details or with variations therefrom. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0173] Although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art based on the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may utilize the discussed embodiments.

[0174] The embodiments of the present application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of this application.

[0175] Although the spirit and principles of the present disclosure have been described with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the specific embodiments disclosed, and the division into various aspects does not mean that the features of these aspects cannot be combined to benefit. Such division is merely for the convenience of expression. The present disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. The scope of the appended claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.

Claims

1. A UAV semantic communication method, characterized in that: include: Determining user location information, and obtaining channel gain data based on the user location information; Determining an original transmit signal, inputting the original transmit signal and the channel gain data into a pre-trained data transmission optimization model, optimizing the original transmit signal based on the channel gain data using the data transmission optimization model, and outputting an optimized transmit signal; Determining noise information of a communication channel, and obtaining an original received signal based on the noise information, the channel gain data, and the optimized transmitted signal; The original received signal and the channel gain data are input into the data transmission optimization model, and the original received signal is optimized based on the channel gain data by the data transmission optimization model to output an optimized received signal, wherein the data transmission optimization model is trained by the following method: Constructing a sample set including a plurality of samples; wherein the samples include: sample data and label data; the sample data includes an original training transmitted signal and an original training received signal; the label data includes an optimized training transmitted signal corresponding to the original training transmitted signal and an optimized training received signal corresponding to the original training received signal; Inputting the sample data into the data transmission optimization model to obtain prediction data output by the model, wherein the prediction data includes a reconstructed transmission signal and a reconstructed reception signal output by the model; determining a first difference between the predicted data and the label data; Based on the first difference, updating the model parameters by using a loss function until the difference between the predicted data and the label data is minimized, thereby obtaining the pre-trained data transmission optimization model; Determine a second difference between the optimized received signal and the original received signal for training; and update the loss function of the data transmission optimization model based on the first difference and the second difference.

2. The method according to claim 1, characterized in that The obtaining channel gain data based on the user location information includes: Determine a rated transmit power for user information communication, and obtain a location of a drone base station based on the user location information and the rated transmit power; Path loss is calculated based on the user location information and the location of the drone base station to obtain the channel gain data.

3. The method according to claim 1, characterized in that The determining of the original transmitted signal includes: Determining data to be transmitted, performing semantic extraction on the data to be transmitted, and obtaining semantic feature information; The semantic feature information is normalized to obtain the original transmission signal.

4. The method according to claim 1, wherein The obtaining of an original received signal based on the noise information, the channel gain data, and the optimized transmitted signal comprises: The noise information, the channel gain data, and the optimized transmit signal of at least one user are determined, and the noise information of the at least one user is added to the sum of the products of the channel gain data and the optimized transmit signal to obtain the original received signal.

5. A UAV semantic communication device, characterized in that: include: a gain data determination module, configured to determine user location information, and obtain channel gain data based on the user location information; a transmission signal determination module configured to determine an original transmission signal, input the original transmission signal and the channel gain data into a pre-trained data transmission optimization model, optimize the original transmission signal based on the channel gain data using the data transmission optimization model, and output an optimized transmission signal; an original received signal determination module, configured to determine noise information of a communication channel, and obtain an original received signal based on the noise information, the channel gain data, and the optimized transmit signal; The optimized received signal determination module is configured to input the original received signal and the channel gain data into the data transmission optimization model, optimize the original received signal based on the channel gain data through the data transmission optimization model, and output an optimized received signal, wherein the data transmission optimization model is trained by the following method: Constructing a sample set including a plurality of samples; wherein the samples include: sample data and label data; the sample data includes an original training transmitted signal and an original training received signal; the label data includes an optimized training transmitted signal corresponding to the original training transmitted signal and an optimized training received signal corresponding to the original training received signal; Inputting the sample data into the data transmission optimization model to obtain prediction data output by the model, wherein the prediction data includes a reconstructed transmission signal and a reconstructed reception signal output by the model; determining a first difference between the predicted data and the label data; Based on the first difference, updating the model parameters by using a loss function until the difference between the predicted data and the label data is minimized, thereby obtaining the pre-trained data transmission optimization model; Determine a second difference between the optimized received signal and the original received signal for training; and update the loss function of the data transmission optimization model based on the first difference and the second difference.

6. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium, characterized in that The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 4.

8. A computer program product, characterized in that The method comprises computer program instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 4.

Images