Semantic communication method, device and system for large-scale access

Abstract

The invention discloses a large-scale access-oriented semantic communication method, device and system. The method comprises the following steps of: acquiring user information at an information source end and extracting semantic information by using a semantic encoder; the high-dimensional features of the semantic information are converted into binary code streams transmitted in a physical channel; the converted semantic features are sent to a wireless channel after channel coding; aggregating local features on the same subcarrier of the semantic features; the aggregated semantic features are directly used for intelligent tasks; solving a weight parameter of an air calculation encoder through end-to-end joint training; and carrying out joint optimization solution on the semantic codec and the air computing encoder. According to the technical scheme, connection and information processing of a large number of devices in the Internet of Things can be effectively processed, and more efficient interconnection is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of wireless communications, and in particular relates to a semantic communication method, device and system for large-scale access. Background Art

[0002] With the rapid development of IoT and AI technologies, the number of IoT terminal devices has grown rapidly, and IoT applications are also developing in a more intelligent, efficient, and personalized direction. Taking urban flood warning as an example, various densely deployed sensors obtain environmental information such as precipitation and water level in the form of images, radar point clouds, satellite signals, etc. Then, these massive multimodal data are sent to the monitoring center to train AI-based flood warning prediction models. With the increase of such AI-based, task-oriented applications, wireless communications will face huge transmission pressure, and the computing workload of the receiver will also increase significantly.

[0003] In order to alleviate the transmission pressure, semantic communication has attracted widespread attention as a novel communication paradigm. In semantic communication, the sender only needs to send semantic information related to the task or source to the receiver, rather than all the information. Unlike traditional bit-based communication methods that focus on how to accurately transmit symbols, semantic communication solves the problem of how to accurately convey the meaning of the content and ignore irrelevant information. Therefore, semantic communication can significantly improve communication efficiency.

[0004] Semantic communication can be divided into unimodal multi-user semantic communication and multimodal multi-user semantic communication. In the case of unimodal multi-user semantic communication, a multi-user semantic communication system for collaborative object recognition fuses single semantic features into global features by dynamically adjusting weights, and multiple semantic features are used together for recognition, thereby reducing system latency. In the case of multimodal multi-user semantic communication, a multi-user semantic communication method that supports multimodal data transmission proposes a Transformer-based semantic communication framework for image retrieval, machine translation, and visual question-answering tasks. Although these studies have made some progress, they have a common disadvantage: the multi-user data fusion performed at the receiver follows the paradigm of communication first and then calculation. In order to facilitate signal fusion processing, algorithms such as zero forcing (ZF), successive interference cancellation (SIC), and parallel interference cancellation (PIC) are needed to separate and recover the signals from each user individually. However, as the number of access nodes increases, the computational complexity of these algorithms grows exponentially, which brings huge processing and computational pressure to the receiver and brings high energy consumption and communication delay to the system. Moreover, when the channel conditions are poor, the accuracy of signal detection cannot be guaranteed, which affects the reliability and performance of the communication system. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a semantic communication method, device and system for large-scale access; it can not only effectively handle the connection and information processing of a large number of devices in the Internet of Things, and achieve more efficient interconnection; it can also process information from different users in different modes, and achieve multi-source perception and processing; in addition, by combining deep air computing with semantic communication, the orthogonality of the semantic domain is fully exploited, and the fusion of multi-modal and multi-user signals can be achieved during the transmission process. The fused information can be directly used for subsequent intelligent tasks at the receiving end without the need for multi-user detection.

[0006] To achieve the above object, the present invention adopts the following technical solution:

[0007] A semantic communication method for large-scale access, comprising:

[0008] Step S1, obtaining user information at the source end and extracting semantic information using a semantic encoder;

[0009] Step S2: converting the high-dimensional features of the semantic information into a binary code stream transmitted in a physical channel;

[0010] Step S3, sending the converted semantic features to the wireless channel after channel coding;

[0011] Step S4, aggregating local features on the same subcarrier of the semantic features;

[0012] Step S5: directly use the aggregated semantic features for intelligent tasks; wherein the intelligent tasks include semantic segmentation, classification, and object detection;

[0013] Step S6, solving the weight parameters of the air calculation encoder through end-to-end joint training;

[0014] Step S7: jointly optimize and solve the semantic codec and the air computing encoder.

[0015] Preferably, in step S4, OFDM modulation is used to transmit M-dimensional semantic features on M subcarriers, and the signal transmitted through the channel is:

[0016]

[0017] Among them, h k is the channel coefficient of the channel between each user node and the receiver, is the identity matrix, is additive white Gaussian noise, and the channel signal-to-noise ratio is p k is the transmission power of the kth transmitter;

[0018] The fusion feature y[m] on the mth subcarrier is:

[0019]

[0020] Where N = Σ k,s n is Gaussian additive white noise.

[0021] Preferably, in step S6, the weight parameters of the aerial computation encoder are solved through end-to-end joint training based on the video data and the skeleton point data; wherein the video data is used to provide appearance information of human body movements, and the skeleton point data is used to provide spatial information of human body posture and movements.

[0022] The present invention also provides a semantic communication device for large-scale access, comprising:

[0023] The first processing module is used to obtain user information at the source end and extract semantic information using a semantic encoder;

[0024] A second processing module, used for converting high-dimensional features of semantic information into a binary code stream transmitted in a physical channel;

[0025] The third processing module is used to send the converted semantic features to the wireless channel after channel coding;

[0026] A fourth processing module, used for aggregating local features on the same subcarrier of the semantic features;

[0027] A fifth processing module is used to directly use the aggregated semantic features for intelligent tasks; wherein the intelligent tasks include semantic segmentation, classification, and object detection;

[0028] A sixth processing module, configured to solve weight parameters of an air-computing encoder through end-to-end joint training;

[0029] The seventh processing module is used to jointly optimize and solve the semantic codec and the air computing encoder.

[0030] Preferably, in step S4, OFDM modulation is used to transmit M-dimensional semantic features on M subcarriers, and the signal transmitted through the channel is:

[0031]

[0032] Among them, h k is the channel coefficient of the channel between each user node and the receiver, is the identity matrix, is additive white Gaussian noise, and the channel signal-to-noise ratio is p k is the transmission power of the kth transmitter;

[0033] The fusion feature y[m] on the mth subcarrier is:

[0034]

[0035] Where N = Σ k,s n is Gaussian additive white noise.

[0036] Preferably, the sixth processing module solves the weight parameters of the aerial computation encoder through end-to-end joint training based on the video data and the skeleton point data; wherein the video data is used to provide appearance information of human body movements, and the skeleton point data is used to provide spatial information of human body posture and movements.

[0037] The present invention also provides a semantic communication system for large-scale access, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a semantic communication method for large-scale access when executed by the processor.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention can effectively handle the connection and information processing of a large number of devices in the Internet of Things, and realize more efficient interconnection; it can process information of different modes from different users, and realize multi-source perception and processing; it realizes "comprehensive calculation combination", fully explores the orthogonality of semantic domains, realizes efficient information fusion, and reduces the complexity of communication systems; by designing appropriate semantic codecs, it can be flexibly applied to various intelligent tasks; under different channel conditions, its performance is better than that of traditional multi-user communication methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0041] Figure 1 It is a block diagram of the task-oriented multi-user semantic communication system based on air computing of the present invention;

[0042] Figure 2 It is a joint optimization framework of the semantic codec and the air computing encoder of the present invention;

[0043] Figure 3 It is a flow chart of the semantic communication method for large-scale access of the present invention;

[0044] Figure 4 It is a convergence trend diagram of the reward function of the DDQN algorithm of the present invention and the loss function of the semantic decoder training;

[0045] Figure 5 is a comparison chart of the motion recognition accuracy results of the present invention and other methods under different signal-to-noise ratio conditions;

[0046] Figure 6 It is a transmission energy consumption variation diagram under different access quantity scenarios of the present invention;

[0047] Figure 7 is a result graph of the semantic segmentation task performed by the present invention;

[0048] Figure 8 This is a comparison chart of semantic segmentation mean intersection over union (mIoU) between the present invention and other methods under different signal-to-noise ratio conditions;

[0049] Fig. 9 This is a comparison chart of the average accuracy of semantic segmentation of the present invention and other methods under different signal-to-noise ratio conditions. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0052] Embodiment 1:

[0053] The embodiment of the present invention provides a semantic communication method for large-scale access, such as Figure 1 , 2 As shown in FIG. 1 , the multi-user semantic communication framework designed by the present invention consists of K single-antenna transmitters and a receiver equipped with M antennas, and all transmitters share the same channel. The local device collects data Extracting semantic features Then, the feature vector encoded by the encoder is calculated over the air through the SIMO-OFDM channel Transmit to the receiver. Use different subcarriers to transmit semantic features of different dimensions. For the same dimension of all local features, use the same subcarrier for transmission. The method of the embodiment of the present invention supports multiple local devices in the same channel to simultaneously transmit feature vectors at the same frequency. By using air computing technology, the feature vectors are naturally superimposed in multiple access channels. Finally, the global semantic feature Y is obtained at the receiving end, and the global features of different intelligent tasks are directly subjected to task-oriented semantic decoding to obtain the task result z.

[0054] like Figure 3 As shown, the semantic communication method for large-scale access according to an embodiment of the present invention includes:

[0055] Step S1: Build a semantic transmitter. The multi-user semantic communication framework in the embodiment of the present invention is equipped with K single-antenna transmitters, collects user information at the source end, and uses a semantic encoder to extract semantic information. The specific steps are as follows:

[0056] Step 101: The source collects user data c s Indicates the data modality type. During the communication process, a total of S types of modal data need to be transmitted. Each type of modal data can be provided by one or more users. The obtained semantic feature vector is Where M is the feature dimension. Here, a deep neural network is used as a semantic encoder to extract semantic features:

[0057]

[0058] in, is the semantic encoder, is the encoding parameter.

[0059] In the specific implementation process of the present invention, the human action recognition task is taken as an example, and the task contains two types of modal data: appearance and posture. For appearance data, ResNet is used as the backbone network for feature extraction, and the output of ResNet is globally averaged and pooled to obtain the global features of the image. For posture data, the same ResNet model is used to extract posture features, and a front-end convolution block is added. The module consists of a convolution with a kernel size of 3, batch normalization, and a rectified linear unit (ReLU) activation function. This module is added to adapt to the input channel dimension of the first block of ResNet.

[0060] Step 102: Use an air-computation encoder to calculate local semantic features Encode and get The expression is as follows:

[0061]

[0062] Among them, ψ k is the kth element of Ψ, Ψ=[ψ1,ψ2,...,ψ k ,...,ψ K ] T is the encoder weight parameter calculated over the air. Ψ includes the modality alignment parameter and the weights between different modalities.

[0063] Step S2: convert the high-dimensional features of the semantic information into a binary code stream transmitted in a physical channel.

[0064] For categorical features (discrete features), you can use one of the following methods to encode:

[0065] One-Hot Encoding: Each category is assigned a binary vector whose length is equal to the number of categories and has 1 in the position corresponding to the category and 0 in the rest of the positions.

[0066] Binary Encoding: Map each category directly to a binary number.

[0067] For continuous features, one of the following methods can be used for encoding:

[0068] Linear quantization: Mapping the value of a feature to a finite range of binary numbers.

[0069] Nonlinear quantization: Use piecewise functions to map feature values ​​to binary codes.

[0070] Step S3: Wireless channel modeling. The processed semantic features are sent to the wireless channel after channel coding. Using OFDM modulation, M-dimensional semantic features are transmitted on M subcarriers. The signal transmitted through the channel can be expressed as:

[0071]

[0072] Among them, h k is the channel coefficient of the channel between each user node and the receiver. For Rayleigh fading channel, Among them I Nr is the identity matrix, is additive white Gaussian noise, and the channel signal-to-noise ratio is p k is the transmission power of the kth transmitter.

[0073] Step S4: The transmitter sends the semantic information of multiple users to the wireless channel. At the receiving end, the local features on the same subcarrier are aggregated. The fused feature y[m] on the mth subcarrier can be expressed as:

[0074]

[0075] Where N = Σ k,s n is Gaussian additive white noise.

[0076] Step S5: Aggregate the local feature vectors across all dimensions of M subcarriers, and obtain the global semantic feature Y=[y[1], y[2], ..., y[M]] at the receiving end. T The fused semantic features are then directly used for intelligent tasks:

[0077] z=F se (Y;ω),

[0078] Among them, z is the execution result of the intelligent task, F se (·; ω) is a task-oriented semantic decoder and ω is a learnable parameter.

[0079] These intelligent tasks may include semantic segmentation, classification, object detection, etc. The specific learnable parameters depend on the type of task.

[0080] Step S6: construct an optimization problem and solve the weight parameters of the air-computing encoder through end-to-end joint training. The specific steps are as follows:

[0081] Step 601: Construct an optimization problem:

[0082] To explain this process more clearly, we use the action recognition task as an illustrative example. The action recognition task contains two data modes: video and skeleton points: the video provides the appearance information of human actions, while the skeleton points provide the spatial information of human posture and action. The fusion of these two types of information helps to improve the accuracy and robustness of action recognition.

[0083] Assume that there are k1 users providing video data and k2 users providing skeleton point data in the system, where k1+k2=K. Before fusion, feature alignment is first performed to ensure that their dimensions are consistent. Then they are used to construct the m-th dimension fusion feature y[m] as:

[0084]

[0085] Next, a softmax function with a fully connected layer is used as a semantic decoder at the receiving end to obtain the decoding result:

[0086]

[0087] Among them, ω and b are the weight and bias parameters of the fully connected layer, respectively, and M′ is the dimension of the output of the fully connected layer.

[0088] The next step is to use cross entropy loss to train the semantic decoder and construct the cross entropy loss function:

[0089]

[0090] in is the true value, and T is the number of samples.

[0091] The loss function is determined by the semantic encoder parameter α, the air-computation encoder parameter ψ, and the semantic encoder parameters ω and b. In order to obtain the minimum loss, the stochastic gradient descent (SGD) algorithm is used to optimize α, ω, and b. For the aggregate weight ψ, when α, ω, and b are determined, the optimization is performed by constructing the following optimization problem P.

[0092]

[0093] in is the semantic feature of the video data, is the semantic feature of the skeleton point data. Ψ1 and Ψ2 are the sum of the weights of the video data and the skeleton point data, respectively. min and max are their minimum and maximum values ​​respectively.

[0094] Step 602: Given the air computation encoder and the semantic decoder, use the stochastic gradient descent algorithm to solve the semantic encoder parameter α so as to minimize the cross entropy function.

[0095] Step 603: Given the semantic encoder and semantic decoder, solve the encoder parameters in the air. Due to the non-convexity of the target loss function and the existence of the ResNet neural network, the problem P cannot be solved using traditional methods, so the deep reinforcement learning algorithm DDQN is used to solve it, and the key elements are defined as follows:

[0096] Agent: Set the edge server as the agent, responsible for calculating the fusion weight;

[0097] State space: The fusion weights assigned by the encoder to each user are calculated on the fly:

[0098]

[0099] Action space: The change of each user's fusion weight. Assuming that the minimum step size of the change is Δψ and the number of connected users is K=3, the action space can be expressed as:

[0100] A={a|a∈{(1,2),(1,3),(2,1),(2,3),(3,1),(3,2)}}

[0101] Among them, (i, j) represents (ψ i +Δψ,ψ j -Δψ),i,j∈{1,2,3},

[0102] Environmental feedback: Environmental feedback is set to the difference between the reward function R of the next state and the current state, where ΔR = RR′.

[0103] The negative value of the optimization target given by P is used as the reward function R. The greater the accuracy of the task during training, the higher the value of R.

[0104] Therefore, it is hoped that R will be optimized in the direction of increase. When R increases, the feedback function ΔR is positive, generating rewards; when R decreases, ΔR is negative, resulting in penalties. When the number of training rounds reaches the predetermined maximum value or the model converges, the training ends.

[0105] Build the main Q network to select actions based on the maximum Q value;

[0106] a=argmaxQ(s,a;θ),

[0107] Build a target Q network to generate Q values ​​for calculating the loss function of each action during training;

[0108] Q t (s,a;θ t )=ΔR+λmaxQ(s′,a′;θ t ),

[0109] Among them, θ t is the target Q network parameter, s, a is the current state and action, s′, a′ is the next state and action, λ is the reward decay factor;

[0110] Calculate the loss function of the double Q network:

[0111] L q =(Q t (s,a;θ t )-Q(s,a;θ)) 2 .

[0112] Step 604: Given the parameters of the semantic encoder and the air computation encoder, the semantic decoder is trained by minimizing the loss function using the SGD algorithm.

[0113] Step S7: jointly optimize and solve the semantic codec and the air computing encoder.

[0114] First, the semantic encoder is optimized using the stochastic gradient descent algorithm while freezing ψ, w, and b. Subsequently, the air computation encoder is optimized using the DDQN algorithm while freezing other models. Finally, we use the SGD algorithm to update the parameters w and b of the semantic decoder, keeping α and ψ fixed and minimizing the loss value. The semantic decoder processes the fused features and obtains the results. Based on these results, we calculate the reward function ΔR and provide feedback results of the parameter update to the air computation encoder and the semantic encoder. This iterative process continues until the loss function converges, at which point the joint optimization is completed. The convergence results are shown in Figure 2. Figure 4 shown.

[0115] The comparison results of the motion recognition accuracy of the present invention with other methods under different signal-to-noise ratio conditions are as follows: Figure 5 shown. Figure 5 SC-DAC is the method proposed by the present invention; BPG+LDPC represents the traditional communication method based on BPG image compression and LDPC channel coding; Error-free Transmission represents error-free transmission; SC-FR represents the feature reconstruction method, the semantic encoder extracts the global semantic information of the data, and reconstructs the features according to the received semantic information; CIF represents the channel-level information fusion method, the multimodal data from multiple users are fused through the wireless channel during the transmission stage, and weightedly aggregated according to the channel gain. Under the framework proposed by the present invention, the accuracy of task recognition is much higher than that of other communication methods, especially when the signal-to-noise ratio is lower than 30dB, its advantage is more obvious. Under low signal-to-noise ratio conditions, the accuracy of action recognition is improved by about 20% compared with traditional methods and by 50% compared with other multi-user semantic communication methods. At the same time, it can be seen from the result curve that the present invention shows stronger stability to changes in channel conditions.

[0116] The transmission energy consumption changes under different numbers of access users in the present invention are as follows: Figure 6 As shown in the figure, there is a small increase in transmission energy consumption as the number of access users increases. Assuming that the data provided by each user is consistent, the exponential growth in the number of users will lead to a proportional increase in the amount of data. It is worth noting that when the number of users increases from 10 to 20, the increase in transmission energy consumption is negligible. This shows the nonlinear response of the system to the exponential growth of users.

[0117] The results of applying the present invention to semantic segmentation tasks are as follows: Figure 7 As shown in the figure, MFnet is a CNN architecture for real-time semantic segmentation of autonomous vehicles. Compared with MFnet, the mIoU of the present invention is reduced by 0.06, and the class average accuracy is improved by 0.04. The segmentation accuracy of the "Car Stop" and "Bump" categories is much higher than that of MFnet.

[0118] Comparison of semantic segmentation mean intersection over union (mIoU) and class average accuracy between the proposed method and other methods under different signal-to-noise ratio conditions Figure 8 and Fig. 9 As shown in the figure, the semantic segmentation mIoU and class average precision that can be achieved by the present invention are much higher than those of other methods, and the accuracy of semantic segmentation is improved by 0.2 to 0.34.

[0119] In summary, it is possible to effectively handle the connection and information processing of a large number of devices in the IoT scenario, realize multi-source perception, and reduce the complexity of the communication system through "comprehensive calculation combination". In addition, by designing appropriate semantic codecs, this method can be flexibly applied to various intelligent tasks and show better performance than traditional multi-user communication methods under different channel conditions, thus helping to achieve more efficient and intelligent IoT interconnection.

[0120] Embodiment 2:

[0121] The embodiment of the present invention further provides a semantic communication device for large-scale access, including:

[0122] The first processing module is used to obtain user information at the source end and extract semantic information using a semantic encoder;

[0123] A second processing module, used for converting high-dimensional features of semantic information into a binary code stream transmitted in a physical channel;

[0124] The third processing module is used to send the converted semantic features to the wireless channel after channel coding;

[0125] A fourth processing module, used for aggregating local features on the same subcarrier of the semantic features;

[0126] A fifth processing module is used to directly use the aggregated semantic features for intelligent tasks; wherein the intelligent tasks include semantic segmentation, classification, and object detection;

[0127] A sixth processing module, configured to solve weight parameters of an air-computing encoder through end-to-end joint training;

[0128] The seventh processing module is used to jointly optimize and solve the semantic codec and the air computing encoder.

[0129] As an implementation method of the embodiment of the present invention, in step S4, OFDM modulation is used to transmit M-dimensional semantic features on M subcarriers, and the signal transmitted through the channel is:

[0130]

[0131] Among them, h k is the channel coefficient of the channel between each user node and the receiver, is the identity matrix, is additive white Gaussian noise, and the channel signal-to-noise ratio is p k is the transmission power of the kth transmitter;

[0132] The fusion feature y[m] on the mth subcarrier is:

[0133]

[0134] Where N = ∑ k,s n is Gaussian additive white noise.

[0135] As an implementation mode of an embodiment of the present invention, the sixth processing module solves the weight parameters of the aerial calculation encoder through end-to-end joint training based on the video data and the skeleton point data; wherein the video data is used to provide the appearance information of the human body movement, and the skeleton point data is used to provide the spatial information of the human body posture and movement.

[0136] Embodiment 3:

[0137] An embodiment of the present invention also provides a semantic communication system for large-scale access, including: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a semantic communication method for large-scale access when executed by the processor.

[0138] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should fall within the protection scope determined by the claims of the present invention.

Claims

1. A semantic communication method for large-scale access, characterized in that: include: Step S1, obtaining user information at the source end and extracting semantic information using a semantic encoder; Step S2: converting the high-dimensional features of the semantic information into a binary code stream transmitted in a physical channel; Step S3, sending the converted semantic features to the wireless channel after channel coding; Step S4, aggregating local features on the same subcarrier of the semantic features; Step S5: directly use the aggregated semantic features for intelligent tasks; wherein the intelligent tasks include semantic segmentation, classification, and object detection; Step S6, solving the weight parameters of the air calculation encoder through end-to-end joint training; Step S7: jointly optimize and solve the semantic codec and the air computing encoder.

2. The semantic communication method for large-scale access according to claim 1, characterized in that: In step S4, OFDM modulation is used to transmit M-dimensional semantic features on M subcarriers, and the signal transmitted through the channel is: Among them, h k is the channel coefficient of the channel between each user node and the receiver, is the identity matrix, is additive white Gaussian noise, and the channel signal-to-noise ratio is p k is the transmission power of the kth transmitter; The fusion feature y[m] on the mth subcarrier is: Where N = ∑ k,s n is Gaussian additive white noise.

3. The semantic communication method for large-scale access as claimed in claim 2, characterized in that: In step S6, the weight parameters of the aerial computation encoder are solved through end-to-end joint training based on the video data and the skeleton point data; wherein the video data is used to provide appearance information of human body movements, and the skeleton point data is used to provide spatial information of human body posture and movement.

4. A semantic communication device for large-scale access, characterized in that: include: The first processing module is used to obtain user information at the source end and extract semantic information using a semantic encoder; A second processing module, used for converting high-dimensional features of semantic information into a binary code stream transmitted in a physical channel; The third processing module is used to send the converted semantic features to the wireless channel after channel coding; A fourth processing module, used for aggregating local features on the same subcarrier of the semantic features; A fifth processing module is used to directly use the aggregated semantic features for intelligent tasks; wherein the intelligent tasks include semantic segmentation, classification, and object detection; A sixth processing module, configured to solve weight parameters of an air-computing encoder through end-to-end joint training; The seventh processing module is used to jointly optimize and solve the semantic codec and the air computing encoder.

5. The semantic communication device for large-scale access as claimed in claim 4, characterized in that: In step S4, OFDM modulation is used to transmit M-dimensional semantic features on M subcarriers, and the signal transmitted through the channel is: Among them, h k is the channel coefficient of the channel between each user node and the receiver, is the identity matrix, is additive white Gaussian noise, and the channel signal-to-noise ratio is p k is the transmission power of the kth transmitter; The fusion feature y[m] on the mth subcarrier is: Where N = ∑ k,s n is Gaussian additive white noise.

6. The semantic communication device for large-scale access as claimed in claim 5, characterized in that: The sixth processing module solves the weight parameters of the aerial computing encoder through end-to-end joint training based on the video data and the skeleton point data; wherein the video data is used to provide the appearance information of the human body movement, and the skeleton point data is used to provide the spatial information of the human body posture and movement.

7. A semantic communication system for large-scale access, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the semantic communication method for large-scale access according to any one of claims 1 to 3 is executed.

Images