Training method of communication system, communication method, device, system and storage medium

Abstract

The invention provides a training method of a communication system, a communication method, electronic equipment, the communication system and a storage medium. The method comprises the following steps: processing target data through a power distribution matrix generation network corresponding to a target flow number to obtain a power distribution matrix and a pilot frequency position selection matrix corresponding to each flow; according to the power distribution matrix corresponding to each stream, first original data and first pilot frequency data of each stream to be sent by the transmitter are superposed on a time-frequency resource indicated by the pilot frequency position selection matrix corresponding to each stream to obtain first aliasing data of each stream; acquiring received data of the receiver for each stream, wherein the received data of each stream is obtained after the first aliasing data of each stream passes through a wireless channel; decoding the received data of each stream through a receiver to obtain first decoded data of each stream; and training parameters of the power distribution matrix generation network and the receiver according to the first original data and the first decoded data of each stream. The method can improve the communication performance of the communication system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, in particular to a training method of a communication system, a communication method, an electronic device, a communication system and a storage medium. BACKGROUND

[0002] At present, a communication system generally adopts a pilot sequence of time division multiplexing or frequency division multiplexing to obtain channel state information, but the pilot sequence occupies a time slot or bandwidth that can originally transmit data, loses information rate, and reduces bandwidth utilization. Therefore, a superimposed pilot technology emerges as the times require, which embeds a low-power pilot symbol into a transmitted signal, and a receiver estimates a channel by using a known pilot sequence and statistical characteristics of a received signal. Since the pilot no longer occupies an independent time slot or subcarrier, the superimposed pilot technology can effectively save spectrum resources and improve spectrum efficiency.

[0003] However, superimposed signals interfere with each other, and in particular, in a multi-input multi-output (MIMO) system, mutual interference of superimposed signals of multiple antennas can cause a large error in a channel estimation result, resulting in low communication performance. SUMMARY

[0004] Embodiments of the present application provide a training method of a communication system, a communication method, an electronic device, a communication system and a storage medium.

[0005] In a first aspect, embodiments of the present application provide a training method of a communication system, the communication system comprising a power allocation matrix generation network, a transmitter and a receiver, and the method comprising:

[0006] processing target data by the power allocation matrix generation network corresponding to the target stream number to obtain a power allocation matrix corresponding to each stream and a pilot position selection matrix;

[0007] superimposing first original data and first pilot data of each stream to be sent by the transmitter on time-frequency resources indicated by the pilot position selection matrix corresponding to each stream according to the power allocation matrix corresponding to each stream to obtain first superimposed data of each stream;

[0008] obtaining received data of each stream of the receiver, the received data of each stream being obtained after the first superimposed data of each stream passes through a wireless channel;

[0009] decoding the received data of each stream by the receiver to obtain first decoded data of each stream;

[0010] training parameters of the power allocation matrix generation network and the receiver according to the first original data of each stream and the first decoded data.

[0011] In a second aspect, an embodiment of the present application provides a communication method, comprising:

[0012] The transmitter determines target power allocation matrices and target pilot position selection matrices corresponding to each stream under a current number of streams from a first preset mapping relationship;

[0013] The transmitter superimposes second original data and second pilot data of each stream on time-frequency resources indicated by the target pilot position selection matrices corresponding to each stream according to the target power allocation matrices corresponding to each stream, to obtain second aliasing data of each stream;

[0014] The transmitter transmits target signaling and the second aliasing data of each stream, and the current number of streams is included in the target signaling;

[0015] The receiver receives the target signaling and the second aliasing data of each stream;

[0016] The receiver determines target receiver parameters corresponding to the current number of streams from a second preset mapping relationship;

[0017] The receiver decodes the second aliasing data of each stream based on the target receiver parameters;

[0018] In the first preset mapping relationship, power allocation matrices and pilot position selection matrices corresponding to each stream under different numbers of streams are included, information in the first preset mapping relationship is obtained by inputting target data into a pre-trained power allocation matrix generation network corresponding to each number of streams, and in the second preset mapping relationship, receiver parameters corresponding to each number of streams are included, and the power allocation matrix generation network and the receiver parameters corresponding to each number of streams are trained by using the method provided in the first aspect of the present application.

[0019] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method provided in the first aspect of the present application when executing the computer program.

[0020] In a fourth aspect, an embodiment of the present application provides a communication system, comprising a power allocation matrix generation network, a transmitter and a receiver;

[0021] The transmitter is configured to determine target power allocation matrices and target pilot position selection matrices corresponding to each stream under a current number of streams from a first preset mapping relationship, superimpose second original data and second pilot data of each stream on time-frequency resources indicated by the target pilot position selection matrices corresponding to each stream according to the target power allocation matrices corresponding to each stream, to obtain second aliasing data of each stream, and transmit target signaling and the second aliasing data of each stream, and the current number of streams is included in the target signaling;

[0022] The receiver is configured to receive the target signaling and the second mixed data of the streams, determine target receiver parameters corresponding to the current number of streams from a second preset mapping relationship, and decode the second mixed data of the streams based on the target receiver parameters.

[0023] The first preset mapping relationship includes power allocation matrices and pilot position selection matrices corresponding to different numbers of streams, and information in the first preset mapping relationship is obtained by inputting target data into a power allocation matrix generation network corresponding to each number of streams.

[0024] In a fifth aspect, an embodiment of the present application provides a storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps of the method provided in the first aspect or the second aspect of the present application.

[0025] The technical solution provided in the embodiments of the present application generates the power allocation matrix and the pilot position selection matrix corresponding to each stream through the power allocation matrix generation network, superimposes the first original data and the first pilot data of each stream using the obtained power allocation matrix and pilot position selection matrix to obtain the first mixed data, decodes the received data of each stream through the receiver to obtain the first decoded data of each stream, and trains the parameters of the power allocation matrix generation network and the receiver using the first original data and the first decoded data of each stream. As a result, the obtained parameters are more optimal. In the communication process based on superimposed pilots, the power allocation matrix generation network can generate more optimal power allocation matrices and pilot position selection matrices, and the received signals are decoded through more optimal receiver parameters, which reduces the pilot interference between the superimposed signals of each stream, improves the channel estimation result, and thus improves the decoding effect. BRIEF DESCRIPTION OF DRAWINGS

[0026] Figure 1 FIG. 1 is a structural schematic diagram of a communication system provided in an embodiment of the present application;

[0027] Figure 2 FIG. 2 is a schematic diagram of the working principle of a communication system provided in an embodiment of the present application;

[0028] Figure 3 FIG. 3 is a flowchart of a training method of a communication system provided in an embodiment of the present application;

[0029] Figure 4 FIG. 4 is a structural schematic diagram of a power allocation matrix generation network provided in an embodiment of the present application;

[0030] Figure 5 A schematic structural diagram of a receiver provided in an embodiment of the present application;

[0031] Figure 6 A flow chart of a communication method provided in an embodiment of the present application;

[0032] Figure 7 A schematic diagram of the structure of a training device for a communication system provided in an embodiment of the present application;

[0033] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0035] Figure 1 A schematic diagram of the structure of the communication system provided in the embodiment of the present application. Figure 1 As shown, the communication system may include a power allocation matrix generation network, a transmitter and a receiver, wherein the power allocation matrix generation network is used to generate a power allocation matrix (such as Figure 1 The power allocation matrices A1, A2, A M etc.) and the pilot position selection matrix, the transmitter uses the generated power allocation matrix and pilot position selection matrix to perform superposition processing on the original data to be sent and the pilot data, and sends the superimposed processed data, and the receiver decodes the received data. By superimposing the pilot data and the original data for transmission, the pilot data does not occupy time-frequency resources alone, thereby improving the spectrum utilization efficiency of the communication system. The above-mentioned power allocation matrix generation network and receiver can be constructed using a neural network. Therefore, the above-mentioned communication system can be trained in an end-to-end manner, so that the power allocation matrix generation network in the communication system can output a better power allocation matrix and pilot position selection matrix, reduce the pilot interference between the superimposed signals of each stream, and the receiver can use more optimized parameters to decode the received data, thereby improving the communication performance of the communication system.

[0036] The communication system provided in the embodiment of the present application mainly includes a model training module and a model application module, such as Figure 2 As shown, the model training module adopts an end-to-end architecture joint training optimization. After the training is completed, the power allocation matrix and pilot position selection matrix output by the module can be stored according to the number of streams as the index (such as Figure 2The first preset mapping relationship in the , or the matrix after the power allocation matrix and the pilot position selection matrix are multiplied by the number of streams is stored as the index, and the receiver parameters can also be stored as the index according to the number of streams (such as Figure 2 In this way, the model application module can select the corresponding power allocation matrix and pilot position selection matrix based on the actual number of streams for pilot superposition processing, and simultaneously use the actual number of streams to select the corresponding receiver parameters for decoding the received data. Here, the communication system can be viewed as a single model for overall training.

[0037] Next, let’s introduce the model training process. Figure 3 A flow chart of a training method for a communication system provided in an embodiment of the present application. Figure 3 As shown, the method may include:

[0038] S301. Process target data through a power allocation matrix generation network corresponding to the target number of streams to obtain a power allocation matrix and a pilot position selection matrix corresponding to each stream.

[0039] The target data serves as the input data for the power allocation matrix generation network and can be any set of vectors with no length or amplitude constraints. The target number of streams is related to the number of streams supported by the communication system. For example, if the communication system is a single-input single-output (SISO) system, the target number of streams is 1. If the communication system is a MIMO system, the target number of streams is related to the number of multiple streams supported by the MIMO system.

[0040] A fixed set of vectors is selected as target data and input into the power allocation matrix generation network corresponding to the target number of streams to obtain the power allocation matrix and pilot position selection matrix corresponding to each stream. For example, assuming that the communication system contains L streams, the target data is input into the power allocation matrix generation network corresponding to the L streams to obtain the power allocation matrices A1…A corresponding to each of the L streams. L And the pilot position selection matrix B1…B L , where A1 and B1 correspond to the first stream, A2 and B2 correspond to the second stream, and so on. L , B L Corresponding to the Lth stream.

[0041] S302: Superimpose first original data and first pilot data of each stream to be sent by the transmitter on the time-frequency resources indicated by the pilot position selection matrix corresponding to each stream according to the power allocation matrix corresponding to each stream to obtain first aliased data of each stream.

[0042] The power allocation matrix is used to indicate the power allocated by each time-frequency resource of the scheduling, and the pilot position selection matrix is used to indicate the time-frequency resource of the pilot superposition, so that after obtaining the power allocation matrix and the pilot position selection matrix corresponding to each stream, the first original data and the first pilot data of each stream to be transmitted by the transmitter can be superimposed on the time-frequency resource indicated by the pilot position selection matrix corresponding to each stream according to the power allocation matrix corresponding to each stream, to obtain the first mixed data of each stream, that is, the first original data and the first pilot data are superimposed on the same time-frequency resource, and the specific superposition process can be shown in the following formula 1:

[0043]

[0044] Wherein, C L is the matrix after the point multiplication of the power allocation matrix and the pilot position selection matrix of the Lth stream, is the first pilot data of the Lth stream, is the first original data of the Lth stream, is the first mixed data of the Lth stream, the first pilot data and the first original data are superimposed on the same time-frequency resource indicated by the pilot position selection matrix, and the above L is a positive integer.

[0045] After obtaining the first mixed data, the first mixed data is transmitted through a wireless channel, and the receiver receives the first mixed data after the wireless channel transmission.

[0046] S303, obtaining the received data of the receiver for each stream.

[0047] Wherein, the received data of each stream is the first mixed data of each stream after the wireless channel, which can be a channel simulated by a target channel data set. The target channel data set can include a real channel data set or a channel data set generated by simulation software.

[0048] As an optional implementation, the process of S303 can be: obtaining a target channel data set, processing the mixed data of each stream through a channel simulated by the target channel data set to obtain the received data of the receiver for each stream.

[0049] By collecting real channel data sets or channel data sets generated by simulation software, various wireless channel environments can be simulated through these channel data sets, and the first mixed data generated by the transmitter is transmitted by using the simulated wireless channel environment, and the first mixed data after the wireless channel environment transmission is determined as the data received by the receiver.

[0050] Optionally, after obtaining the received data of the receiver for each stream, the received data of each stream can also be subjected to energy normalization processing to reduce abnormal data, so that the processed received data meets the input requirements of the receiver, facilitating the processing of the receiver.

[0051] S304, decoding the received data of each stream by the receiver to obtain first decoded data of each stream.

[0052] The received data of each stream received by the receiver is obtained as input data of the receiver, and the received data of each stream is decoded by the receiver to obtain first decoded data of each stream.

[0053] Optionally, the above S304 can include: fusing the received data of each stream, the first pilot data, the power allocation matrix and the pilot position selection matrix to obtain first fused data of each stream; and decoding the first fused data of each stream by the receiver to obtain first decoded data of each stream.

[0054] Specifically, the power allocation matrix and the pilot position selection matrix corresponding to each stream are multiplied to obtain a target matrix corresponding to each stream, and the real and imaginary parts of the received data of each stream, the real and imaginary parts of the first pilot data and the real and imaginary parts of the target matrix are superimposed in the third dimension of the three-dimensional matrix to obtain first fused data, and the first fused data is input to the receiver for decoding processing to obtain first decoded data of each stream.

[0055] S305, training the parameters of the power allocation matrix generation network and the receiver according to the first original data and the first decoded data of each stream.

[0056] The first original data of each stream is taken as the expected output of the communication system, the first decoded data of each stream is taken as the actual output of the communication system, and the parameters of the power allocation matrix generation network and the receiver in the communication system are trained based on a preset loss function. The loss function can be binary cross entropy or other types of loss function, and the embodiments of the present application are not limited thereto.

[0057] Optionally, the above S305 can be: determining a loss value of the preset loss function according to the first original data and the first decoded data of each stream; updating the parameters of the power allocation matrix generation network and the receiver according to the loss value, and continuing to execute the step of processing the target data by the power allocation matrix generation network corresponding to the target stream number to obtain the power allocation matrix and the pilot position selection matrix corresponding to each stream until the loss value of the preset loss function meets the preset requirement or the model convergence condition is reached.

[0058] For a communication system with different target stream numbers, the processes of S301-S305 can be performed for training, so as to obtain the power allocation matrix generation network and the receiver corresponding to each stream under different stream numbers, and the power allocation matrix and the pilot position selection matrix output by the power allocation matrix generation network are correspondingly stored with different stream numbers as indexes, and the receiver parameters are correspondingly stored with different stream numbers as indexes, thereby saving the time and computing resources of model inference in the model application stage, and improving the real-time performance of the communication system.

[0059] Optionally, as shown in Figure 4 The power allocation matrix generation network can include an input layer, a first feature extraction layer, an activation layer, and a classification decision layer, and the input layer is used to receive target data. Correspondingly, S301 can include: performing feature extraction on the target data through the first feature extraction layer to obtain feature data; performing activation processing on the feature data through the activation layer to obtain the power allocation matrix corresponding to each stream; and performing processing on the target data through the classification decision layer to obtain the pilot position selection matrix corresponding to each stream, and the pilot position selection matrix corresponding to each stream is different.

[0060] Specifically, the first feature extraction layer and the activation layer are used to generate the power allocation matrix. Since the target data is fixed, the power allocation matrix output by the power allocation matrix generation network is composed of the parameters of the power allocation matrix generation network. By optimizing the parameters of the power allocation matrix generation network, the optimal power allocation matrix can be obtained. The activation layer can include multiple fully connected layers and an activation function, which can be a sigmoid function or other types of activation functions. The classification decision layer performs L+1 types of multi-classification on L streams on each scheduled time-frequency resource, which is used to determine on which stream the time-frequency resource at this time is used to superimpose the first pilot data and the first original data. For example, assuming that there are L+1 labels in the classification result, L labels correspond to L streams one by one. If the decision result is that the time-frequency resource belongs to the first label, the time-frequency resource is used to superimpose the first pilot data and the first original data of the first stream. If the decision result is that the time-frequency resource belongs to the second label, the time-frequency resource is used to superimpose the first pilot data and the first original data of the second stream. Similarly, if the decision result is that the time-frequency resource belongs to the Lth label, the time-frequency resource is used to superimpose the first pilot data and the first original data of the Lth stream. If the decision result is that the time-frequency resource belongs to the L+1th label, the time-frequency resource is only used to transmit the first original data of each stream without superimposing the first pilot data of any stream.

[0061] The first feature extraction layer and the activation layer can allocate more optimal power allocation matrices for each stream, and the classification decision layer can stagger the pilots superimposed between different streams to reduce the pilot interference between streams, thereby improving the performance of the communication system.

[0062] Optionally, as Figure 5 The receiver can include an input layer, a dimensionality increasing layer, a second feature extraction layer, and a decision layer, as shown in the figure. Specifically, the data input to the receiver is first processed by the dimensionality increasing layer, then the data after dimensionality increasing is extracted by the second feature extraction layer, and then the extracted feature data is input to the decision layer for processing, so as to obtain the corresponding first decoding data.

[0063] The dimensionality increasing layer is used to aggregate feature information from different channels, so that the information of different channels can be better fused together to generate more rich and diverse feature representations. The second feature extraction layer can include at least one local feature extraction layer and at least one global feature extraction layer, which are arranged alternately. The local feature extraction layer adopts a multi-layer convolutional neural network (CNN) architecture, which automatically learns spatial hierarchical features through multiple layers of convolution, and can effectively extract local features of data. The global feature extraction layer adopts a Transformer architecture, which globally models through a self-attention mechanism, and can effectively handle long-distance dependencies. By alternately arranging the local feature extraction layer and the global feature extraction layer, the overall performance of the receiver is improved. The decision layer can include multiple convolutional layers and an activation function, which can be a sigmoid function or other types of activation functions, which are not limited in the embodiment.

[0064] The training method of the communication system provided by the embodiment of the present application generates the power allocation matrix and the pilot position selection matrix corresponding to each stream through the power allocation matrix generation network, superimposes the first original data and the first pilot data of each stream by using the obtained power allocation matrix and pilot position selection matrix, obtains the first superimposed data, decodes the received data of each stream through the receiver to obtain the first decoding data of each stream, and trains the parameters of the power allocation matrix generation network and the receiver by using the first original data and the first decoding data of each stream. The obtained parameters are more optimal, so that in the communication process based on superimposed pilots, the power allocation matrix generation network can generate more optimal power allocation matrix and pilot position selection matrix, and the received signal is decoded by using more optimal receiver parameters, which reduces the pilot interference between superimposed signals of each stream, improves the channel estimation result, and thus improves the decoding effect.

[0065] Next, the model application process is specifically introduced, Figure 6 A flowchart of the communication method provided by the embodiment of the present application is shown in the figure. Figure 6 As shown in the figure, the method includes:

[0066] S601, the transmitter determines the target power allocation matrix and the target pilot position selection matrix corresponding to each stream under the current stream number from the first preset mapping relationship.

[0067] wherein the first preset mapping relationship includes the power allocation matrix and the pilot position selection matrix corresponding to each stream under different stream numbers, the information in the first preset mapping relationship is obtained by inputting the target data into the power allocation matrix generation network corresponding to each stream number which is pre-trained, and the second preset mapping relationship includes the receiver parameters corresponding to each stream number, the power allocation matrix generation network and the receiver parameters corresponding to each stream number are trained by using the training method of the communication system provided in any one of the above embodiments.

[0068] That is, after the communication system under different stream numbers is trained, the power allocation matrix and the pilot position selection matrix output by the power allocation matrix generation network in the communication system are indexed by the stream number to construct the first preset mapping relationship, and the receiver parameters are indexed by the stream number to construct the second preset mapping relationship.

[0069] In this way, in the model application stage, the transmitter can query the first preset mapping relationship based on the current stream number, so as to obtain the target power allocation matrix and the target pilot position selection matrix corresponding to each stream under the current stream number.

[0070] S602, the transmitter superimposes the second original data and the second pilot data of each stream on the time-frequency resources indicated by the target pilot position selection matrix corresponding to each stream according to the target power allocation matrix corresponding to each stream, to obtain the second superposition data of each stream.

[0071] The target power allocation matrix is used to indicate the power allocated by each time-frequency resource of the scheduling, and the target pilot position selection matrix is used to indicate the time-frequency resources of the pilot superposition, therefore, after the target power allocation matrix and the target pilot position selection matrix corresponding to each stream are obtained, the second original data and the second pilot data of each stream to be sent by the transmitter can be superimposed on the time-frequency resources indicated by the target pilot position selection matrix corresponding to each stream according to the target power allocation matrix corresponding to each stream, to obtain the second superposition data of each stream, that is, the second original data and the second pilot data are superimposed on the same time-frequency resource, and the specific superposition process can be shown in the following formula 2:

[0072]

[0073] wherein C L ′ is the matrix after the point multiplication of the target power allocation matrix and the target pilot position selection matrix of the Lth stream, is the second pilot data of the Lth stream, is the second original data of the Lth stream, The second mixed data, the second pilot data and the second original data of the Lth stream are superimposed on the same time-frequency resource indicated by the target pilot position selection matrix.

[0074] It should be noted that, before the pilot superposition, the second original data and the second pilot data need to be channel encoded and modulated, and the specific encoding mode and modulation mode are not limited.

[0075] S603, the transmitter sends the target signaling and the second mixed data of each stream.

[0076] The transmitter performs Orthogonal Frequency Division Multiplexing (OFDM) symbol shaping processing on the second mixed data after pilot superposition and loads a Cyclic Prefix (CP) to obtain an OFDM signal to be transmitted, and sends the target signaling and the OFDM signal. The current stream number is included in the target signaling, so that the receiver can determine the receiver parameters used for decoding based on the current stream number.

[0077] S604, the receiver receives the target signaling and the second mixed data of each stream.

[0078] The receiver performs CP removal and FFT related processing on the received OFDM signal to obtain the second mixed data. Optionally, the receiver can also perform energy normalization processing on the second mixed data.

[0079] S605, the receiver determines the target receiver parameters corresponding to the current stream number from the second preset mapping relationship.

[0080] The second preset mapping relationship includes the mapping relationship between different stream numbers and receiver parameters, so that after receiving the target signaling, the receiver can query the second preset mapping relationship based on the current stream number carried in the target signaling to obtain the target receiver parameters required for decoding.

[0081] S606, the receiver decodes the second mixed data of each stream based on the target receiver parameters.

[0082] After obtaining the target receiver parameters, the receiver directly decodes the second mixed data based on the target receiver parameters. In order to obtain better decoding effect, optionally, the receiver can also fuse the second mixed data, the second pilot data, the target power allocation matrix and the target pilot position selection matrix of each stream to obtain the second fusion data of each stream; the receiver decodes the second fusion data of each stream based on the target receiver parameters.

[0083] Specifically, the receiver side stores the first preset mapping relationship in addition to the second preset mapping relationship, and the receiver can query the first preset mapping relationship based on the current stream number carried in the target signaling to obtain the target power allocation matrix and the target pilot position selection matrix corresponding to each stream under the current stream number, and multiply the target power allocation matrix and the target pilot position selection matrix corresponding to each stream to obtain an independent comprehensive power allocation matrix between the streams. The real part and the imaginary part of the second aliasing data of each stream, the real part and the imaginary part of the second pilot data, and the real part and the imaginary part of the comprehensive power allocation matrix are superimposed in the third dimension of the three-dimensional matrix to obtain second fusion data, and the second fusion data is decoded and processed based on the target receiver parameter.

[0084] The communication method provided by the embodiment of the application can obtain a more optimal target power allocation matrix, a target pilot position selection matrix, and a target receiver parameter by querying the first preset mapping relationship and the second preset mapping relationship based on the current stream number. The target pilot position selection matrix causes the pilot positions of the superimposed streams to be staggered with each other, reduces the interference between the superimposed pilots of the streams, and the target receiver parameter can better decode the received data, thereby improving the communication performance in the superimposed pilot transmission process.

[0085] The training process and the application process of the communication system are further introduced below by taking specific examples as examples:

[0086] Example one: assuming that the data in an OFDM SISO communication system is single stream, the number of scheduled RBs is 24, the number of REs is 288, the number of symbols is 14, the data signal can be modulated by Quadrature Amplitude Modulation (QAM), such as 16QAM, the pilot signal can be modulated by Binary Phase Shift Keying (BPSK), and the channel data set can be obtained by field collection. Specifically, the model training process is as follows:

[0087] 1. Channel data set collection and arrangement

[0088] The frequency domain channel data is obtained by field collection to construct a data set, and the channel data is normalized. The data set is used to simulate a wireless channel.

[0089] 2. Generating transmitter data

[0090] In this scenario, the communication system is a single stream signal, and the bit data X bit ′ is randomly generated, and the modulated data symbol X symThen, a set of randomly generated vectors with no limit on length and amplitude are selected as the input of the power allocation matrix generation network to obtain a power allocation matrix A1 and a pilot position selection matrix B1, the power allocation matrix A1 and the pilot position selection matrix B1 are point multiplied to obtain a matrix C1. At the same time, the pilot data is modulated using BPSK to obtain modulated pilot data X p ′, and the modulated data symbol and the pilot symbol are layer mapped, and the superposition process is shown in the following formula 3:

[0091]

[0092] 3. Generating and processing the receiver data

[0093] The frequency domain signal X mix ′ after the transmitter data and pilot superposition is obtained mix ′, and the energy normalization process of the signal Y mix ′ is carried out using the following formula 4 to obtain the processed signal Y nor ′.

[0094] Y nor ′=Normal max (Y mix ′) Formula 4

[0095] After that, the data is integrated, and the integration method is to superimpose the real part and the imaginary part of the signal Y nor ′, the real part and the imaginary part of the pilot signal X p ′, and the real part and the imaginary part of the matrix C1 after the point multiplication of the power allocation matrix and the pilot position selection matrix in the third dimension of the three-dimensional matrix to obtain the integrated signal Y in ′.

[0096] 4. LOSS calculation and parameter update

[0097] The integrated signal Y in ′ in step 3 is used as the input data of the receiver, and the integrated output bit value Y bit ′ is obtained after the receiver decoding, and the binary cross entropy is calculated according to the receiver output bit value Y bit ′ and the original bit value X bit ′ using the following formula 5 to obtain the Loss value of the model.

[0098] Loss=BCE(X bit ′,Y bit ′) Formula 5

[0099] The parameters of the power allocation matrix generation network and the receiver are updated based on the calculated loss value, and steps 2 through 4 are repeated until the model converges. After the model is trained, the power allocation matrix and pilot position selection matrix (or the matrix resulting from the dot product of the power allocation matrix and the pilot position selection matrix) output by the power allocation matrix generation network are stored indexed by the number of streams, and the receiver parameters are stored indexed by the number of streams.

[0100] Next, the model application process is as follows:

[0101] 1. Generate transmitter data

[0102] In this scenario, the communication system is a single-stream signal, which sends the bit data X bit After channel coding and 16QAM modulation, the modulated data symbol X is obtained. sym Then, the power allocation matrix A1 and the pilot position selection matrix B1 are obtained by looking up the table according to the current number of streams. At the same time, the pilot data is modulated using BPSK to obtain the modulated pilot data X p ″, and perform layer mapping on the data symbols and pilot symbols, and superimpose the data symbols and pilot symbols on the same time-frequency resources according to the power allocation matrix and the pilot position selection matrix. The superposition process is shown in the following formula 6:

[0103]

[0104] 2. Aliasing data X after pilot superposition mix Perform OFDM symbol shaping and add CP to obtain the OFDM signal to be transmitted, send target signaling for indicating the current number of streams, and send the above-mentioned OFDM signal after sending the target signaling.

[0105] 3. The receiver performs related processing such as CP removal and FFT on the received OFDM signal.

[0106] 4. Processing receiving end data

[0107] After processing in step 3, the receiving end frequency domain signal Y is obtained mix ″, select the corresponding receiver parameters and the corresponding power allocation matrix A1 and pilot position selection matrix B1 according to the number of streams 1 indicated by the target signaling. Then, according to the following formula 7, the signal Y mix Perform energy normalization processing to obtain the processed signal Y nor ″.

[0108] Y nor ″=Normal max (Y mix ″) Formula 7

[0109] After the integration of data, the integration method is to superimpose the real part and the imaginary part of the signal Y nor v, the real part and the imaginary part of the pilot signal X p , and the real part and the imaginary part of the matrix C1 after the point multiplication of the power distribution matrix and the pilot position selection matrix selected based on the current stream number, and the real part and the imaginary part of the matrix C1 in the third dimension of the three-dimensional matrix are superimposed to obtain the integrated signal Y in . The integrated signal Y in is used as the input data of the receiver, and the receiver parameters obtained by the above table lookup are used to decode Y in , to obtain the integrated output bit value Y bit .

[0110] Example two: Assuming that the data in an OFDM MIMO communication system is two streams, the number of scheduled RBs is 6, the number of REs is 72, the number of symbols is 14, the data signal uses 64QAM modulation, the pilot signal uses Quadrature Phase Shift Keying (QPSK) modulation, and the channel data set is generated by simulation software. Specifically, the model training process is as follows:

[0111] 1. Collect and organize the channel data set

[0112] Similar simulation frequency domain channel data is used to construct the data set, and the channel data is normalized.

[0113] 2. Generate the transmitting end data

[0114] In this scenario, the communication system is a two-stream signal, and the bit data X bit1 is randomly generated, and after 64QAM modulation, the modulated data symbol X sym1 is obtained. Next, a set of randomly generated vectors with no length and amplitude are selected as the input data of the power distribution matrix generation network to obtain the power distribution matrices A1 and A2, and the pilot position selection matrices B1 and B2, A1 and B1 correspond to the first stream, and A2 and B2 correspond to the second stream. At the same time, the pilot data is modulated using QPSK to obtain the modulated pilot data X p1 , and the modulated data symbol and the pilot symbol are layer mapped, and the superposition process is shown in the following formula 8:

[0115]

[0116] Where C L is the matrix obtained by point multiplication of the power distribution matrix and the pilot position selection matrix corresponding to the Lth stream, and L is 1 or 2.

[0117] 3. Generate and process the receiving end data

[0118] Obtain the frequency domain signal X after superimposing the transmit end data and pilot mix1 After that, generate the receive end frequency domain signal Y by using the channel data set in step 1 to simulate the channel process mix1 , and perform energy normalization processing on the signal Y mix1 by using the following formula 9 to obtain the processed signal Y nor1 .

[0119] Y nor1 = Normal max (Y mix1 ) Formula 9

[0120] After that, integrate the data, and the integration method is to superimpose the real part and the imaginary part of the signal Y nor1 , the real part and the imaginary part of the pilot signal X p1 , and the real part and the imaginary part of the matrix C L obtained by multiplying the power allocation matrix and the pilot position selection matrix in the third dimension of the three-dimensional matrix to obtain the integrated signal Y in1 .

[0121] 4、LOSS calculation and parameter update

[0122] Use the integrated signal Y in1 in step 3 as the input data of the receiver to obtain the integrated output bit value Y bit1 , and according to the bit value Y bit1 output by the receiver and the original bit value X bit1 , calculate the binary cross entropy by using the following formula 10 to obtain the Loss value of the model.

[0123] Loss = BCE (X bit1 , Y bit1 ) Formula 10

[0124] According to the calculated Loss value, update the parameters of the power allocation matrix generation network and the receiver, and repeat steps 2 to 4 until the model converges. After that, store the power allocation matrix output by the power allocation matrix generation network and the pilot position selection matrix (or the matrix obtained by multiplying the power allocation matrix and the pilot position selection matrix) according to the flow number as the index, and store the receiver parameters according to the flow number as the index.

[0125] Next, the model application process is as follows:

[0126] 1、Generate transmit end data

[0127] In this scenario, the communication system is a two-flow signal, and after the bit data X bit2 at the transmit end is encoded and modulated by 64QAM, the modulated data symbol X sym2Then, according to the current stream number, the power allocation matrix A1, A2 and pilot position selection matrix B1, B2 are obtained by looking up the table. Meanwhile, the pilot data is modulated by QPSK to obtain the modulated pilot data X p2 , and the data symbol and the pilot symbol are layer mapped, and the data symbol and the pilot symbol are superimposed on the same time-frequency resource according to the power allocation matrix and the pilot position selection matrix, and the superimposing process is shown in the following formula 11:

[0128]

[0129] , wherein C L is the matrix obtained by multiplying the power allocation matrix and the pilot position selection matrix corresponding to the Lth stream, and the value of L is 1 or 2.

[0130] 2. The superimposed data after the pilot is subjected to OFDM symbol forming processing and CP loading to obtain the OFDM signal to be transmitted, and the target signaling indicating the current stream number is sent, and the above OFDM signal is sent after the target signaling is sent.

[0131] 3. The receiver performs related processing such as CP removal and FFT on the received OFDM signal.

[0132] 4. Process the data at the receiving end

[0133] The receiving end frequency domain signal Y mix2 is obtained after step 3 processing, and the stream number 2 indicated by the target signaling is selected to select the corresponding receiver parameters, the corresponding power allocation matrix A1 and A2, and the corresponding pilot position selection matrix B1 and B2. Then, the signal Y mix2 is subjected to energy normalization processing according to the following formula 12 to normalize the maximum value of the signal energy to 1 to obtain Y nor2 .

[0134] Y nor2 = Normal max (Y mix2 ) Formula 12

[0135] Then, the data is integrated, and the integration method is to superimpose the real part and the imaginary part of the signal Y nor2 , the real part and the imaginary part of the pilot signal X p2 , and the real part and the imaginary part of the matrix C L obtained by multiplying the power allocation matrix and the pilot position selection matrix based on the current stream number in the third dimension of the three-dimensional matrix to obtain the integrated signal Y in2 . The integrated signal Y in2 is used as the input data of the receiver, and the receiver parameters obtained by looking up the table are used to decode Y in2 to obtain the integrated output bit value Y bit2 .

[0136] Example Three: Assuming that the data in an OFDM MIMO communication system is four streams, the number of scheduled RBs is 12, the number of REs is 144, and the number of symbols is 14. The data signal is modulated by QPSK, the pilot signal is modulated by BPSK, and the channel data set is obtained by real field collection. Specifically, the model training process is as follows:

[0137] 1. Channel data set collection and arrangement

[0138] The frequency domain channel data is obtained by real field collection to construct the data set, and the channel data is normalized.

[0139] 2. Generating the transmitting end data

[0140] In this scenario, the communication system is a four-stream signal, and the transmitting end bit data X is randomly generated bit3 After QPSK modulation, the modulated data symbol X is obtained sym3 .Next, a set of randomly generated vectors with unlimited length and amplitude are selected as the input data of the power allocation matrix generation network to obtain the power allocation matrices A1, A2, A3, A4, the pilot position selection matrices B1, B2, B3, B4, A1 and B1 correspond to the first stream, A2 and B2 correspond to the second stream, A3 and B3 correspond to the third stream, and A4 and B4 correspond to the fourth stream. At the same time, the pilot data is modulated by BPSK to obtain the modulated pilot data X p3 , and the data symbol and the pilot symbol are layer mapped and superimposed, and the superposition process is shown in the following formula 13:

[0141]

[0142] Wherein, C L is the matrix obtained by multiplying the power allocation matrix and the pilot position selection matrix corresponding to the Lth stream, and the value of L is 1, 2, 3, or 4.

[0143] 3. Generating and processing the receiving end data

[0144] After obtaining the frequency domain signal X mix3 obtained by superimposing the transmitting end data and the pilot, the receiving end frequency domain signal Y mix3 is generated by simulating the channel process using the frequency domain channel data set in step 1, and the energy normalization processing is performed on the signal Y mix3 using the following formula 14 to obtain Y nor3 .

[0145] Y nor3 = Normal max (Y mix3 ) Formula 14

[0146] After that, the data is integrated. The integration method is to superimpose the real part and the imaginary part of the signal Y nor3 , the real part and the imaginary part of the pilot signal X p3 , and the real part and the imaginary part of the matrix C L obtained by multiplying the power allocation matrix and the pilot position selection matrix in the third dimension of the three-dimensional matrix to obtain the integrated signal Y in3 .

[0147] 4. LOSS calculation and parameter update

[0148] The integrated signal Y in3 in step 3 is used as the input data of the receiver to obtain the integrated output bit value Y bit3 . According to the bit value Y bit3 output by the receiver and the original bit value X bit3 , the binary cross entropy is calculated using the following formula 15 to obtain the loss value of the model.

[0149] Loss = BCE (X bit3 , Y bit3 ) Formula 15

[0150] According to the calculated loss value, the parameters of the power allocation matrix generation network and the receiver are updated, and steps 2 to 4 are repeated until the model converges. After that, the power allocation matrix and the pilot position selection matrix (or the matrix obtained by multiplying the power allocation matrix and the pilot position selection matrix) output by the power allocation matrix generation network are stored according to the flow number as the index, and the receiver parameters are stored according to the flow number as the index.

[0151] Next, the model application process is as follows:

[0152] 1. Generate transmitter data

[0153] In this scenario, the communication system is a four-flow signal, and the bit data X bit4 of the transmitting end is encoded and modulated by QPSK to obtain the modulated data symbol X sym4 . Then, according to the current flow number, the power allocation matrix A1, A2, A3, A4, and the pilot position selection matrix B1, B2, B3, B4 of each flow are obtained. At the same time, the pilot data is modulated by BPSK to obtain the modulated pilot data X p4 , and the data symbol and the pilot symbol are layer mapped, and the data symbol and the pilot symbol are superimposed on the same time-frequency resource according to the power allocation matrix and the pilot position selection matrix. The superposition process is shown in the following formula 16:

[0154]

[0155] Where C LThe matrix obtained by multiplying the power allocation matrix corresponding to the Lth stream and the pilot position selection matrix is ​​L, and the value of L is 1, 2, 3, or 4.

[0156] 2. Perform OFDM symbol shaping on the aliased data after pilot superposition and add a CP to obtain the OFDM signal to be transmitted. Send target signaling for indicating the current number of streams. After sending the target signaling, send the above-mentioned OFDM signal.

[0157] 3. The receiver performs related processing such as CP removal and FFT on the received OFDM signal.

[0158] 4. Processing receiving end data

[0159] After step 3, the frequency domain signal Y at the receiving end is obtained mix4 , select the corresponding receiver parameters and the corresponding power allocation matrix A1, A2, A3, A4, and the corresponding pilot position selection matrix B1, B2, B3, B4 according to the target signaling indication of stream number 4. Then, according to the following formula 17, the signal Y mix4 Perform energy normalization to obtain Y nor4 .

[0160] Y nor4 =Normal max (Y mix4 ) Formula 17

[0161] Then the data is integrated by converting the signal Y nor4 The real and imaginary parts of the pilot signal X p4 The real and imaginary parts of the matrix C are multiplied by the power allocation matrix and the pilot position selection matrix selected based on the current number of streams. L The real and imaginary parts of the three-dimensional matrix are superimposed on the third dimension to obtain the integrated signal Y in4 The integrated signal Y in4 As the input data of the receiver, the receiver parameters obtained by the above table are used to calculate Y in4 Decode and get the integrated output bit value Y bit4 .

[0162] Figure 7 A structural diagram of a training device for a communication system provided in an embodiment of the present application. Figure 7 As shown, the apparatus may include: a first processing module 701 , an acquisition module 702 , a second processing module 703 and a training module 704 .

[0163] Specifically, the first processing module 701 is configured to generate the network to process the target data through a power allocation matrix corresponding to the target streams, to obtain a power allocation matrix corresponding to each stream and a pilot position selection matrix; and superimpose first original data and first pilot data of each stream to be sent by the transmitter on time-frequency resources indicated by the pilot position selection matrix corresponding to each stream according to the power allocation matrix corresponding to each stream, to obtain first superimposed data of each stream.

[0164] The acquisition module 702 is configured to acquire received data of each stream of the receiver, the received data of each stream being obtained after the first superimposed data of each stream passes through a wireless channel.

[0165] The second processing module 703 is configured to decode the received data of each stream by the receiver, to obtain first decoded data of each stream.

[0166] The training module 704 is configured to train parameters of the power allocation matrix generation network and the receiver according to the first original data of each stream and the first decoded data.

[0167] On the basis of the above embodiment, optionally, the power allocation matrix generation network comprises a first feature extraction layer, an activation layer and a classification decision layer.

[0168] The first processing module 701 is specifically configured to extract features of the target data through the first feature extraction layer, to obtain feature data; perform activation processing on the feature data through the activation layer, to obtain a power allocation matrix corresponding to each stream; and process the target data through the classification decision layer, to obtain a pilot position selection matrix corresponding to each stream, the pilot position selection matrices corresponding to each stream being different.

[0169] On the basis of the above embodiment, optionally, the receiver comprises an elevation layer, a second feature extraction layer and a decision layer.

[0170] On the basis of the above embodiment, optionally, the second feature extraction layer comprises at least one local feature extraction layer and at least one global feature extraction layer, the at least one local feature extraction layer and the at least one global feature extraction layer being arranged alternately.

[0171] On the basis of the above embodiment, optionally, the local feature extraction layer adopts a multi-layer convolutional neural network (CNN) architecture, and the global feature extraction layer adopts a Transformer architecture.

[0172] Based on the above embodiment, optionally, the acquisition module 702 is specifically used to obtain a target channel data set, where the target channel data set includes a real channel data set or a channel data set generated by simulation software; the aliasing data of each stream is processed through the channel simulated by the target channel data set to obtain the reception data of the receiver for each stream.

[0173] Based on the above embodiment, optionally, the second processing module 703 is specifically used to fuse the received data, first pilot data, power allocation matrix and pilot position selection matrix of each stream to obtain first fused data of each stream; and decode the first fused data of each stream through the receiver to obtain first decoded data of each stream.

[0174] Based on the above embodiment, optionally, the training module 704 is specifically used to determine the loss value of the preset loss function based on the first original data and the first decoded data of each stream; update the parameters of the power allocation matrix generation network and the receiver according to the loss value, and continue to execute the step of processing the target data through the power allocation matrix generation network corresponding to the target number of streams to obtain the power allocation matrix and pilot position selection matrix corresponding to each stream, until the loss value meets the preset requirements.

[0175] In one embodiment, an electronic device is provided, wherein the internal structure of the electronic device can be as follows: Figure 8 As shown. The electronic device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data generated during the training process of the communication system. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a training method for a communication system is implemented.

[0176] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0177] The present application also provides a communication system. Figure 1 As shown, the communication system may include a power allocation matrix generation network, a transmitter, and a receiver;

[0178] Specifically, the power allocation matrix generation network is configured to generate the power allocation matrix and the pilot position selection matrix corresponding to each stream.

[0179] The transmitter is configured to determine the target power allocation matrix and the target pilot position selection matrix corresponding to each stream under the current number of streams from the first preset mapping relationship; superimpose the second original data and the second pilot data of each stream on the time-frequency resources indicated by the target pilot position selection matrix corresponding to each stream according to the target power allocation matrix corresponding to each stream, to obtain the second superimposed data of each stream; and transmit the target signaling and the second superimposed data of each stream, the target signaling including the current number of streams.

[0180] The receiver is configured to receive the target signaling and the second superimposed data of each stream; determine the target receiver parameter corresponding to the current number of streams from the second preset mapping relationship; and decode the second superimposed data of each stream based on the target receiver parameter.

[0181] The first preset mapping relationship includes the power allocation matrix and the pilot position selection matrix corresponding to each stream under different numbers of streams, the information in the first preset mapping relationship is obtained by inputting the target data into the power allocation matrix generation network corresponding to each number of streams which is pre-trained, and the second preset mapping relationship includes the receiver parameter corresponding to each number of streams, the power allocation matrix generation network corresponding to each number of streams and the receiver parameter are trained by using the training method of the communication system provided in any one of the above embodiments.

[0182] Optionally, the receiver is further configured to fuse the second superimposed data of each stream, the second pilot data, the target power allocation matrix and the target pilot position selection matrix to obtain the second fused data of each stream; and decode the second fused data of each stream based on the target receiver parameter.

[0183] Optionally, the power allocation matrix generation network includes a first feature extraction layer, an activation layer and a classification decision layer.

[0184] Optionally, the receiver includes a dimension increasing layer, a second feature extraction layer and a decision layer.

[0185] Optionally, the second feature extraction layer includes at least one local feature extraction layer and at least one global feature extraction layer, and the at least one local feature extraction layer and the at least one global feature extraction layer are arranged alternately.

[0186] Optionally, the local feature extraction layer adopts a multi-layer convolutional neural network (CNN) architecture, and the global feature extraction layer adopts a Transformer architecture.

[0187] The embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the training method or the communication method of the communication system provided by any of the above embodiments.

[0188] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. The computer readable storage medium includes (but is not exhaustive) an electrical connection having one or more conductive wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an electrically erasable, programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus.

[0189] The computer readable signal medium can include a data signal propagating in a baseband or as part of a carrier wave propagating through a transmission medium, and the data signal bears computer readable program code. Such a propagated data signal can take on many forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can be used to carry or store the program for use by or in connection with an instruction execution system, apparatus or device.

[0190] The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, radio frequency (Radio Frequency, RF), etc., or any suitable combination thereof.

[0191] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++, Ruby, Go, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0192] Those skilled in the art will appreciate that the term user terminal encompasses any appropriate type of wireless user equipment, such as a mobile phone, a portable data processing apparatus, a portable web browser, or a vehicle mounted mobile station.

[0193] In general, the various embodiments of the application can be implemented in hardware or special purpose circuits, software, logic or any combination thereof. For example, some aspects can be implemented in hardware, while other aspects can be implemented in

[0194] Embodiments of the application can be implemented by the data processor of a mobile device executing computer program instructions, for example in a processor entity, or by hardware, or by a combination of software and hardware. Computer program instructions can be in assemblies, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or in any combination of one or more programming languages, executed on one or more computing devices.

[0195] The block diagrams of any logical flow of the present application in the drawings can represent program steps or can represent interconnected logic circuits, modules, and functions, or can represent a combination of program steps and logic circuits, modules, and functions. The computer program can be stored on a memory. The memory can be of any type suitable to the local technical environment and can be realized using any suitable data storage technology, such as, but not limited to, read only memory (ROM), random access memory (RAM), optical storage devices, and systems, such as digital versatile disc (DVD) or CD, and the like. The computer readable medium can include non-transitory storage media. The data processor can be of any type suitable to the local technical environment, and can include, but is not limited to, a general purpose computer, a special purpose computer, a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), and a processor based on multi-core processor architecture.

Claims

1. A training method for a communication system, characterized in that: The communication system includes a power allocation matrix generation network, a transmitter, and a receiver, and the method includes: The target data is processed through the power allocation matrix generation network corresponding to the target number of streams to obtain the power allocation matrix and pilot position selection matrix corresponding to each stream; Superimposing, according to the power allocation matrix corresponding to each stream, the first original data and the first pilot data of each stream to be sent by the transmitter on the time-frequency resources indicated by the pilot position selection matrix corresponding to each stream to obtain first aliased data of each stream; Acquire received data for each stream from a receiver, where the received data for each stream is obtained after first aliased data of the stream passes through a wireless channel; Decoding the received data of each stream by the receiver to obtain first decoded data of each stream; Parameters of the power allocation matrix generation network and the receiver are trained according to the first original data and the first decoded data of each stream.

2. The method according to claim 1, characterized in that The power allocation matrix generation network includes a first feature extraction layer, an activation layer and a classification decision layer; The target data is processed by a power allocation matrix generation network corresponding to the target number of streams to obtain a power allocation matrix and a pilot position selection matrix corresponding to each stream, including: Performing feature extraction on the target data through the first feature extraction layer to obtain feature data; Activate the characteristic data through the activation layer to obtain a power allocation matrix corresponding to each flow; The target data is processed through a classification decision layer to obtain a pilot position selection matrix corresponding to each stream, and the pilot position selection matrix corresponding to each stream is different.

3. The method according to claim 1, characterized in that The receiver includes a dimensionality increase layer, a second feature extraction layer and a decision layer.

4. The method according to claim 3, characterized in that The second feature extraction layer includes at least one local feature extraction layer and at least one global feature extraction layer, and the at least one local feature extraction layer and the at least one global feature extraction layer are arranged alternately.

5. The method according to claim 4, characterized in that The local feature extraction layer adopts a multi-layer convolutional neural network (CNN) architecture, and the global feature extraction layer adopts a Transformer architecture.

6. The method according to claim 1, characterized in that The obtaining of the reception data of the receiver for each stream includes: Acquire a target channel data set, where the target channel data set includes a real channel data set or a channel data set generated by simulation software; The aliased data of each stream is processed through a channel simulated by the target channel data set to obtain received data for each stream at a receiver.

7. The method according to claim 1, characterized in that Decoding the received data of each stream by the receiver to obtain first decoded data of each stream includes: Fusing the received data of each stream, the first pilot data, the power allocation matrix, and the pilot position selection matrix to obtain first fused data of each stream; The first fused data of each stream is decoded by the receiver to obtain first decoded data of each stream.

8. The method according to claim 1, characterized in that The training of the parameters of the power allocation matrix generation network and the receiver according to the first original data and the first decoded data of each stream includes: Determine a loss value of a preset loss function according to the first original data and the first decoded data of each stream; The parameters of the power allocation matrix generation network and the receiver are updated according to the loss value, and the step of processing the target data through the power allocation matrix generation network corresponding to the target number of streams to obtain the power allocation matrix and pilot position selection matrix corresponding to each stream is continued until the loss value meets the preset requirements.

9. A communication method, characterized in that: include: The transmitter determines, from the first preset mapping relationship, a target power allocation matrix and a target pilot position selection matrix corresponding to each stream under the current number of streams; The transmitter superimposes the second original data and the second pilot data of each stream on the time-frequency resources indicated by the target pilot position selection matrix corresponding to each stream according to the target power allocation matrix corresponding to each stream to obtain second aliased data of each stream; The transmitter sends target signaling and second aliased data of each stream, where the target signaling includes the current number of streams; A receiver receives the target signaling and the second aliased data of each stream; The receiver determines the target receiver parameters corresponding to the current number of streams from the second preset mapping relationship; The receiver decodes the second aliased data of each stream based on the target receiver parameter; In which, the first preset mapping relationship includes a power allocation matrix and a pilot position selection matrix corresponding to each stream under different numbers of streams. The information in the first preset mapping relationship is obtained by inputting the target data into a pre-trained power allocation matrix generation network corresponding to each number of streams. The second preset mapping relationship includes receiver parameters corresponding to different numbers of streams. The power allocation matrix generation network and receiver parameters corresponding to each number of streams are trained using the method described in any one of claims 1 to 8.

10. The method according to claim 9, characterized in that The receiver decodes the second aliased data of each stream based on the target receiver parameter, comprising: The receiver fuses the second aliased data of each stream, the second pilot data, the target power allocation matrix, and the target pilot position selection matrix to obtain second fused data of each stream; The receiver decodes the second fused data of the streams based on the target receiver parameters.

11. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 8 when executing the computer program.

12. A communication system, characterized in that: include: Power allocation matrix generation network, transmitters, and receivers; The transmitter is configured to determine, from a first preset mapping relationship, a target power allocation matrix and a target pilot position selection matrix corresponding to each stream under the current number of streams; and superimpose, based on the target power allocation matrix corresponding to each stream, the second original data and the second pilot data of each stream on the time-frequency resources indicated by the target pilot position selection matrix corresponding to each stream to obtain second aliased data of each stream; Sending target signaling and second aliased data of each stream, wherein the target signaling includes the current number of streams; The receiver is configured to receive the target signaling and the second aliased data of each stream; Determining a target receiver parameter corresponding to the current number of streams from a second preset mapping relationship; decoding the second aliased data of the respective streams based on the target receiver parameters; In which, the first preset mapping relationship includes a power allocation matrix and a pilot position selection matrix corresponding to each stream under different numbers of streams. The information in the first preset mapping relationship is obtained by inputting the target data into a pre-trained power allocation matrix generation network corresponding to each number of streams. The second preset mapping relationship includes receiver parameters corresponding to different numbers of streams. The power allocation matrix generation network and receiver parameters corresponding to each number of streams are trained using the method described in any one of claims 1 to 8.

13. The communication system according to claim 12, wherein: The receiver is further configured to fuse the second aliased data of each stream, the second pilot data, the target power allocation matrix, and the target pilot position selection matrix to obtain second fused data of each stream; The second fused data of the streams is decoded based on the target receiver parameters.

14. A storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images