Communication method and device based on network communication model, medium and storage medium

Abstract

The network communication model of the application comprises a channel layer and a plurality of signal transmission modules, each signal transmission module comprises a signal transmitting module and a signal output module, each signal transmitting module comprises an encoder network, a power distribution network and a coding modulation layer, and the communication method comprises: respectively using each encoder network to encode based on a received to-be-transmitted signal and a preset interference coefficient to obtain a plurality of first encoded signals, respectively using each power distribution network to encode based on the preset interference coefficient to obtain a plurality of second encoded signals, respectively using the coding modulation layer to obtain a transmitting signal transmitted by each signal transmitting module based on each first encoded signal and second encoded signal, using the channel layer to calculate an input signal of each signal output module based on a preset noise, a preset interference coefficient and each transmitting signal, and respectively using each signal output module to decode based on each input signal to obtain a plurality of output signals, thereby reducing the parameter quantity of the encoder network and improving the coding modulation efficiency.

Description

Technical Field

[0001] This application relates to the field of communication technology, specifically to a communication method, apparatus, medium, and storage medium based on a network communication model. Background Technology

[0002] In existing technologies, among the main physical layer coding and modulation methods in the field of communication, in addition to some traditional methods such as Hamming codes and QPSK (Quadrature Phase Shift Keying), some artificial intelligence methods are also used, such as linear neural network layers, such as multilayer perceptrons (MLPs), to fit the features of the sequence data to be transmitted. This method performs well in traditional deep learning tasks, but it has a series of drawbacks in communication scenarios: First, due to insufficient datasets, linear neural networks often exhibit low fitting efficiency when dealing with complex nonlinear features, leading to decreased model accuracy; second, the redundancy of network parameters requires more computational resources during inference, further affecting real-time performance; finally, although models such as recurrent neural networks (RNNs), long short-term memory networks (LSTMs), and attention mechanisms can significantly improve the accuracy of sequence tasks, their inference speed is slow, and the network parameters are often large, reducing their practical value in real-time communication scenarios. Summary of the Invention

[0003] This application addresses the shortcomings of the prior art by proposing a communication method, apparatus, medium, and storage medium based on a network communication model.

[0004] In a first aspect, embodiments of this application provide a communication method based on a network communication model, the network communication model including a channel layer and multiple signal transmission modules, each of the signal transmission modules including a signal transmission module and a signal output module; each of the signal transmission modules including an encoder network, a power distribution network, and a coding modulation layer, the communication method comprising: using each encoder network to encode a received signal to be transmitted and a preset interference coefficient to obtain multiple first coded signals; using each power distribution network to encode a signal based on the preset interference coefficient to obtain multiple second coded signals; using the coding modulation layer to obtain a transmitted signal transmitted by the signal transmission module corresponding to each signal transmission module based on the first coded signals encoded by the encoder network in the signal transmission module corresponding to each signal transmission module and the second coded signals encoded by the power distribution network; using the channel layer to calculate the input signal of the signal output module corresponding to each signal transmission module based on preset noise, the preset interference coefficient, and each transmitted signal; and using each signal output module corresponding to each signal module to decode a signal based on each input signal to obtain multiple output signals.

[0005] Secondly, embodiments of this application provide a communication device for a network communication model, comprising: the network communication model including a channel layer and multiple signal transmission modules, each signal transmission module including a signal transmitting module and a signal output module; each signal transmitting module including an encoder network, a power distribution network, and a coding modulation layer; the communication device comprising: a first encoding module, configured to encode based on a received signal to be transmitted and a preset interference coefficient using each encoder network to obtain multiple first encoded signals; a second encoding module, configured to encode based on the preset interference coefficient using each power distribution network to obtain multiple second encoded signals; and a coding modulation module, configured to divide... The system utilizes the coding and modulation layer to obtain the transmitted signals transmitted by the signal transmission modules corresponding to each signal transmission module, based on the first coded signal encoded by the encoder network in the signal transmission module corresponding to each signal transmission module and the second coded signal encoded by the power allocation network. A calculation module is used to calculate the input signals of the signal output modules corresponding to each signal transmission module using the channel layer, based on preset noise, the preset interference coefficient, and each transmitted signal. A decoding module is used to decode each input signal using the signal output modules corresponding to each signal transmission module to obtain multiple output signals.

[0006] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the method described in the first aspect above.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0008] The technical solutions provided in this application embodiment have at least the following technical effects or advantages:

[0009] The network communication model of this application embodiment includes a channel layer and multiple signal transmission modules. Each signal transmission module includes a signal transmission module and a signal output module. Each signal transmission module includes an encoder network, a power distribution network, and a coding modulation layer. Each encoder network encodes the received signal to be transmitted and a preset interference coefficient to obtain multiple first coded signals. Each power distribution network encodes the signal based on the preset interference coefficient to obtain multiple second coded signals. Then, each coding modulation layer uses the first coded signals encoded by the encoder network in the corresponding signal transmission module and the second coded signals encoded by the power distribution network to obtain the transmitted signals transmitted by the corresponding signal transmission module. Using the channel layer, the input signals of the corresponding signal output modules are calculated based on preset noise, preset interference coefficients, and the transmitted signals. Finally, each signal output module decodes the input signals to obtain multiple output signals. This significantly reduces the number of parameters required by the network communication model, achieves a lower bit error rate, reduces computing power requirements, and improves the practicality of deep learning networks in physical layer communication.

[0010] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0011] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0012] Figure 1 A schematic diagram of the network communication model provided in an embodiment of this application is shown;

[0013] Figure 2 A flowchart illustrating a communication method based on a network communication model provided in an embodiment of this application is shown;

[0014] Figure 3 A schematic diagram of the structure of a communication device based on a network communication model provided in an embodiment of this application is shown;

[0015] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0016] Exemplary embodiments of this application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0017] In existing technologies, among the main physical layer coding and modulation methods in the field of communication, in addition to some traditional methods such as Hamming codes and QPSK (Quadrature Phase Shift Keying), some artificial intelligence methods are also used, such as linear neural network layers, such as multilayer perceptrons (MLPs), to fit the features of the sequence data to be transmitted. This method performs well in traditional deep learning tasks, but it has a series of drawbacks in communication scenarios: First, due to insufficient datasets, linear neural networks often exhibit low fitting efficiency when dealing with complex nonlinear features, leading to decreased model accuracy; second, the redundancy of network parameters requires more computational resources during inference, further affecting real-time performance; finally, although models such as recurrent neural networks (RNNs), long short-term memory networks (LSTMs), and attention mechanisms can significantly improve the accuracy of sequence tasks, their inference speed is slow, and the network parameters are often large, reducing their practical value in real-time communication scenarios.

[0018] Figure 1 This is a schematic diagram of the network communication model on which the communication method provided in this application is based. The network communication model includes a channel layer and multiple signal transmission modules. Each signal transmission module includes a signal transmitting module and a signal output module. The signal transmitting module is connected to the channel layer and the signal output module in sequence. Each signal transmitting module includes an encoder network, a power distribution network and a coding modulation layer. The encoder network and the power distribution network are respectively connected to the coding modulation layer.

[0019] The first encoder network includes a first input layer, a first encoding layer, a connection layer, a second encoding layer, and a normalization layer. The first input layer, the first encoding layer, the first connection layer, the second encoding layer, and the normalization layer are connected sequentially. The first input layer includes multiple input nodes, and the first encoding layer includes multiple activation functions. Each input node is connected to each activation function. The second encoding layer has the same structure as the first encoding layer. The first connection layer includes multiple addition nodes. Each activation function of the first encoding layer is connected to each of the multiple addition nodes in a one-to-one correspondence. Then, the multiple addition nodes are also connected to each activation function of the second encoding layer in a one-to-one correspondence. The first encoder network is any one of multiple encoder networks.

[0020] The structures of each power distribution network are similar to those of each encoder network. The difference is that the activation function of the coding layer in each power distribution network is smaller than that of the coding layer in the encoder network. The specific structure is shown in the figure, and will not be repeated here.

[0021] The channel layer includes multiple noise addition layers and multiple noise layers. Each signal transmission module is connected to each noise layer in a one-to-one correspondence, and a noise addition layer connects two adjacent noise layers.

[0022] Each signal output module includes a decoder network. The decoder network has a structure including a second normalization layer, a first decoding layer, a second connection layer, a second decoding layer, and an output layer. The second normalization layer has the same structure as the normalization layer in the first encoder network. The first decoding layer has a similar structure to the first encoding layer in the first encoder network. The first decoding layer includes multiple sigmoid activation functions. Similarly, the second decoding layer has the same structure as the first decoding layer. The output layer has the same structure as the first input layer in the first encoder network. The connections between the second normalization layer, the third encoding layer, the second connection layer, the fourth encoding layer, and the output layer in this decoder network are reversed compared to the connections in the first encoder network. This will not be repeated here.

[0023] The network communication model of this application embodiment can support communication scenarios of resource-constrained physical layer transceivers, reducing the dependence on large amounts of data and computing resources. By integrating knowledge from the field of communication into network design, the model-driven approach can better solve problems related to communication signal processing, thereby improving communication performance. Moreover, the network communication model of this application embodiment can also support coding and modulation designs with low bit error rate requirements. By adjusting the communication scheme according to changes in channel conditions, the bit error rate performance of communication can be improved, ensuring high-speed transmission and reliability under various channel conditions.

[0024] Figure 2 This application provides a communication method based on a network communication model. The following detailed description of the embodiment of this application is provided in conjunction with the accompanying drawings.

[0025] See Figure 2 The flowchart illustrates a communication method based on a network communication model, which is the network communication model described in the above embodiments. The method specifically includes the following steps:

[0026] Step 101: Using each encoder network, encode the received signal to be transmitted and the preset interference coefficient to obtain multiple first encoded signals.

[0027] In one embodiment, the first encoder network includes a first input layer, a first coding layer, a first connection layer, a second coding layer, and a normalization layer. The first encoder network can be any one of multiple encoder networks. Then, the first input layer can be used to align the received signal to be transmitted with a preset interference coefficient. The first coding layer can be used to encode the aligned signal to be transmitted to obtain a first intermediate coded signal. The first intermediate coded signal includes multiple first activation values. The first connection layer can be used to connect the first activation values ​​to obtain a second intermediate transmission signal. The second coding layer can be used to encode the second intermediate transmission signal to obtain a third intermediate transmission signal. The normalization layer can be used to normalize the third intermediate transmission signal to obtain a first coded signal. Finally, based on the preset interference coefficient, the target signal output by the target input layer is channel equalized and then input to the next target input layer adjacent to the target input layer. The target input layer includes any one of the input layer, the first coding layer, the first connection layer, the second coding layer, and the normalization layer.

[0028] Based on the above implementation method, in some modified implementation methods, the first input layer includes multiple input nodes, the first encoding layer includes multiple activation functions, and the first encoding layer is used to encode the aligned signal to be transmitted to obtain a first intermediate encoded signal. Specifically, it may include: using the first activation function to calculate the first activation value based on the aligned signal to be transmitted transmitted by each input node, wherein the first activation function is any one of the multiple activation functions, and the activation function is as shown in the following formula (1):

[0029]

[0030] Wherein, φ(x) j ) represents the first activation value, w b w represents the first learned parameter. s Denotes the second learning parameter, b(x) j ) represents the basic activation function, B i (x j ) represents a spline function, c i Let x represent the coefficients of the spline function, i represent the number of spline functions, and x represent the number of spline functions. jThis represents the aligned signal to be transmitted from the j-th input node.

[0031] Based on the above implementation method, in some modified implementation methods, the first connection layer includes multiple addition nodes, each addition node adds the activation values ​​calculated by each activation function to obtain each second intermediate transmission signal.

[0032] Furthermore, the second coding layer also includes multiple activation functions, which are the same as those in the first coding layer. Each activation function is used to calculate a second activation value based on each second intermediate transmission signal. At this point, φ(x) in formula (1)... j ) represents the second activation value, w b w represents the first learned parameter. s Denotes the second learning parameter, b(x) j ) represents the basic activation function, B i (x j ) represents a spline function, c i Let x represent the coefficients of the spline function, i represent the number of spline functions, and x represent the number of spline functions. j This represents the j-th second intermediate transmission signal, and the second activation value is used as the third intermediate transmission signal.

[0033] Furthermore, the normalization layer performs normalization processing based on each third intermediate transmission signal to obtain the first coded signal.

[0034] Step 102: Encode each signal using a power distribution network based on a preset interference coefficient to obtain multiple second encoded signals.

[0035] In this embodiment, the encoding methods of each power distribution network and the encoder network are the same, and will not be repeated here.

[0036] Step 103: Using the coding modulation layer, based on the first coded signal obtained by the encoder network encoding in the signal transmission module corresponding to each signal transmission module, and the second coded signal obtained by the power distribution network encoding, the transmitted signal transmitted by the signal transmission module corresponding to each signal transmission module is obtained.

[0037] In one embodiment, a first encoding modulation layer is used to multiply the first encoded signal obtained by the encoder network in the signal transmission module corresponding to the first signal transmission module with the second encoded signal obtained by the power distribution network in the signal transmission module corresponding to the first signal transmission module to obtain the transmitted signal transmitted by the signal transmission module corresponding to the first signal transmission module. The first encoding modulation layer is the encoding modulation layer in the signal transmission module corresponding to the first signal transmission module, and the first signal transmission module is any one of a plurality of signal transmission modules.

[0038] Step 104: Using the channel layer, based on preset noise, preset interference coefficient and each transmitted signal, calculate the input signal of the signal output module corresponding to each signal transmission module.

[0039] In one implementation, the channel layer uses the preset noise, preset interference coefficient, and each transmitted signal to calculate the input signal of the signal output module corresponding to each signal transmission module using the following formula (2):

[0040]

[0041] in, This represents the input signal of the output module corresponding to the m-th signal transmission module. This represents the transmitted signal transmitted by the signal transmitting module corresponding to the m-th signal transmission module, where α represents the preset interference coefficient. This represents the transmitted signal emitted by the signal transmitting module corresponding to the nth signal transmission module that interferes with the mth signal transmission module, where N represents the number of signal transmission modules that interfere with the mth signal transmission module. This represents the preset noise of the m-th signal transmission module.

[0042] Step 105: Decode each input signal using the corresponding signal output module of each signal transmission module to obtain multiple output signals.

[0043] In one implementation, the input signal can be normalized using a normalization layer in the first signal output module to eliminate the influence of the channel layer on the amplitude range of the received and transmitted signals, resulting in multiple first intermediate decoded signals. Then, multiple Sigmond activation functions in the first decoding layer of the first signal output module are used to decode each of the first intermediate decoded signals, resulting in multiple second intermediate decoded signals. Similarly, multiple Sigmond activation functions in the second decoding layer of the first signal output module are used to decode each of the second intermediate decoded signals, resulting in multiple third intermediate decoded signals. These third intermediate decoded signals are then output by the output nodes of the output layer in the first signal output module, resulting in multiple output signals. The first signal output module can be any one of the multiple signal output modules.

[0044] Based on the above implementation, in some modified implementations, the first encoder network includes a first encoding layer. The first encoder network is any one of multiple encoder networks. Before encoding based on the received signal to be transmitted and preset interference coefficients using each encoder network, the method further includes: initializing the network communication model to be trained based on preset parameters. These parameters include: a first number of the training transmission signal dataset, a second number of the training transmission signals processed by the network communication model to be trained, a third number of channels, the number of times the network communication model is updated, the number of activation functions in the first encoding layer, the order and grid precision of the spline functions in the activation functions, and the learning rate of the network communication model to be trained. Based on the third number, the network communication model to be trained is trained cyclically. If the network communication model reaches the convergence condition, the network communication model is obtained.

[0045] Based on the above implementation, in some modified implementations, the convergence condition can be the number of training iterations of the network communication model to be trained, i.e., the third number. When the number of training iterations reaches the third number, it is determined that the network communication model has reached the convergence condition, and the network communication model is obtained.

[0046] Based on the above implementation methods, in some modified implementation methods, training the network communication model to be trained includes: randomly generating interference coefficients to be trained and a transmission signal dataset to be trained; then, generating noise to be trained based on a predefined search space; freezing the channel gradient; training the network communication model to be trained based on the interference coefficients to be trained, the transmission signal dataset to be trained, and the noise to be trained to obtain a transmission signal dataset to be trained; calculating the loss value based on the transmission signal dataset to be trained and the output signal dataset to be trained; and finally, updating the weights of the network communication model to be trained using backpropagation based on the loss value.

[0047] Based on the above implementation method, in some modified implementation methods, the loss value is calculated based on the training transmission signal dataset and the training output signal dataset, including: calculating the loss value based on the training transmission signal dataset and the training output signal dataset using a loss function, which is as follows: Formula (3):

[0048]

[0049]

[0050] in, L represents the loss value. i This represents the first temporary training value, and G represents the number of training transmission signal datasets or training output signal datasets. This represents the i-th transmission signal to be trained. This represents the i-th output signal to be trained.

[0051] This application embodiment utilizes each encoder network to encode the received signal to be transmitted and a preset interference coefficient to obtain multiple first coded signals. Then, each power allocation network encodes the signal based on the preset interference coefficient to obtain multiple second coded signals. Next, each signal transmission module's corresponding signal transmission module transmits its own transmitted signal using the first coded signals encoded by the encoder network and the second coded signals encoded by the power allocation network. Finally, the channel layer calculates the input signals of each signal transmission module's corresponding signal output module based on preset noise, preset interference coefficients, and the transmitted signals. Finally, each signal transmission module's corresponding signal output module decodes the input signals to obtain multiple output signals. This significantly reduces the number of parameters required for the network communication model, achieves a lower bit error rate, reduces computational requirements, and improves the practicality of deep learning networks in physical layer communication.

[0052] See Figure 3 This application also provides a communication device for a network communication model, which is used to execute the communication method of the network communication model described in the above embodiments. The network communication model includes a channel layer and multiple signal transmission modules. Each signal transmission module includes a signal transmitting module and a signal output module. Each signal transmitting module includes an encoder network, a power distribution network, and a coding modulation layer. The communication device includes:

[0053] The first encoding module 201 is used to encode the received signal to be transmitted and a preset interference coefficient using each of the encoder networks to obtain a plurality of first encoded signals.

[0054] The second encoding module 202 is used to encode each of the power distribution networks based on the preset interference coefficient to obtain multiple second encoded signals.

[0055] The encoding and modulation module 203 is used to obtain the transmitted signal transmitted by the signal transmission module corresponding to each signal transmission module by using the first encoded signal encoded by the encoder network in the signal transmission module corresponding to each signal transmission module and the second encoded signal encoded by the power distribution network.

[0056] The calculation module 204 is used to calculate the input signal of the signal output module corresponding to each signal transmission module using the channel layer, based on the preset noise, the preset interference coefficient and each of the transmitted signals;

[0057] The decoding module 205 is used to decode each of the input signals using the signal output modules corresponding to each of the signal transmission modules, thereby obtaining multiple output signals.

[0058] The communication device of the network communication model provided in this application embodiment and the communication method of the network communication model provided in the above embodiment are based on the same inventive concept and have the same beneficial effects as the methods they adopt, operate or implement.

[0059] This application also provides an electronic device corresponding to the communication method of the network communication model provided in the foregoing embodiments. Please refer to... Figure 4 This illustrates a schematic diagram of an electronic device provided by some embodiments of this application. For example... Figure 4 As shown, the electronic device 30 may include: a processor 300, a memory 301, a bus 302, and a communication interface 303. The processor 300, the communication interface 303, and the memory 301 are connected via the bus 302. The memory 301 stores a computer program that can run on the processor 300. When the processor 300 runs the computer program, it executes the communication method of the network communication model provided in any of the foregoing embodiments of this application.

[0060] The memory 301 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one physical port 303 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.

[0061] Bus 302 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store programs. After receiving an execution instruction, the processor 300 executes the program. The communication method of the network communication model disclosed in any of the foregoing embodiments of this application can be applied to the processor 300, or implemented by the processor 300.

[0062] The processor 300 may be an integrated circuit with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 300 or by instructions in software form. The processor 300 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 301. The processor 300 reads the information in memory 301 and, in conjunction with its hardware, completes the steps of the above method.

[0063] The electronic device and the network communication model provided in this application are based on the same inventive concept and have the same beneficial effects as the methods they adopt, operate or implement.

[0064] This application also provides a computer-readable storage medium corresponding to the communication method of the network communication model provided in the foregoing embodiments, wherein a computer program (i.e., a program product) is stored thereon, and the computer program, when run by a processor, executes the communication method of the network communication model provided in any of the foregoing embodiments.

[0065] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0066] This application also provides a computer program product corresponding to the communication method of the network communication model provided in the foregoing embodiments, including a computer program that is executed by a processor to implement the communication method of the network communication model provided in the above embodiments.

[0067] The computer-readable storage medium and computer program product provided in the above embodiments of this application are based on the same inventive concept as the communication method of the network communication model provided in the embodiments of this application, and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0068] It should be noted that:

[0069] The algorithms and displays provided herein are not inherently related to any particular computer, virtual device, or other equipment. Various general-purpose devices can also be used in conjunction with the teachings herein. The required structure for constructing such devices is apparent from the above description. Furthermore, this application is not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of this application.

[0070] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0071] Similarly, it should be understood that, in order to simplify this application and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of this application, various features of this application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.

[0072] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0073] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0074] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the virtual machine creation apparatus according to embodiments of this application. This application can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0075] It should be noted that the above embodiments are illustrative of this application and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0076] The above description is merely a preferred embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method based on a network communication model, characterized in that, The network communication model includes a channel layer and multiple signal transmission modules, each signal transmission module including a signal transmitting module and a signal output module; each signal transmitting module includes an encoder network, a power distribution network, and a coding modulation layer; the communication method includes: Each encoder network is used to encode the received signal to be transmitted and a preset interference coefficient to obtain multiple first encoded signals. Each of the aforementioned power distribution networks is used to encode signals based on the preset interference coefficient, resulting in multiple second coded signals. Using the coding and modulation layer, the first coded signal obtained by the encoder network in the signal transmission module corresponding to each signal transmission module and the second coded signal obtained by the power distribution network are respectively used to obtain the transmission signal transmitted by the signal transmission module corresponding to each signal transmission module; Using the channel layer, based on the preset noise, the preset interference coefficient, and each of the transmitted signals, the input signal of the signal output module corresponding to each of the signal transmission modules is calculated; Each signal transmission module is used to decode the input signal to obtain multiple output signals.

2. The communication method based on a network communication model according to claim 1, characterized in that, The first encoder network includes a first input layer, a first encoding layer, a first connection layer, a second encoding layer, and a normalization layer. The first encoder network is any one of the plurality of encoder networks. The encoding is performed using each of the encoder networks based on the received signal to be transmitted and a preset interference coefficient to obtain a plurality of first encoded signals, including: The first input layer is used to align the received signal to be transmitted with the preset interference coefficient. The first coding layer is used to encode the aligned signal to be transmitted to obtain a first intermediate coded signal, which includes a plurality of first activation values: The first connection layer is used to connect each of the first activation values ​​to obtain a second intermediate transmission signal; The second intermediate transmission signal is encoded using the second coding layer to obtain the third intermediate transmission signal; The first coded signal is obtained by performing normalization processing based on the third intermediate transmission signal using the normalization layer. Based on the preset interference coefficient, after channel equalization is performed on the target signal output by the target input layer, the target signal is input to the next target input layer adjacent to the target input layer. The target input layer includes any one of the input layer, the first coding layer, the first connection layer, the second coding layer, and the normalization layer.

3. The communication method based on the network communication model according to claim 2, characterized in that, The first input layer includes multiple input nodes, and the first encoding layer includes multiple activation functions. The step of encoding the aligned signal to be transmitted using the first encoding layer to obtain a first intermediate encoded signal includes: The first activation value is calculated based on the aligned signal to be transmitted transmitted at each input node using the first activation function, wherein the first activation function is any one of the plurality of activation functions; The activation function includes: in, This represents the first activation value. Indicates the first learning parameter. Indicates the second learning parameter. Represents the basic activation function. Represents a spline function. Let represent the coefficients of the spline function, and i represent the number of spline functions. This represents the aligned signal to be transmitted transmitted by the j-th input node.

4. The communication method based on a network communication model according to claim 1, characterized in that, The step of calculating the input signal of the signal output module corresponding to each signal transmission module using the channel layer based on preset noise, preset interference coefficient, and each of the transmitted signals includes: The input signal of the signal output module corresponding to each signal transmission module is calculated using the following formula, based on the preset noise, the preset interference coefficient, and each of the transmitted signals, at the channel layer: in, This represents the input signal of the output module corresponding to the m-th signal transmission module. Let represent the real part of the input signal of the output module corresponding to the m-th signal transmission module. Let represent the imaginary part of the input signal of the output module corresponding to the m-th signal transmission module. This refers to the transmitted signal emitted by the signal transmitting module corresponding to the m-th signal transmission module. Let represent the real part of the transmitted signal transmitted by the signal transmitting module corresponding to the m-th signal transmission module. This represents the imaginary part of the transmitted signal transmitted by the signal transmitting module corresponding to the m-th signal transmission module. This represents the preset interference coefficient. This refers to the transmitted signal emitted by the signal transmitting module corresponding to the nth signal transmission module that interferes with the mth signal transmission module. Let represent the real part of the transmitted signal transmitted by the signal transmitting module corresponding to the nth signal transmission module that interferes with the mth signal transmission module. The imaginary part of the transmitted signal emitted by the signal transmitting module corresponding to the nth signal transmission module that interferes with the mth signal transmission module is denoted by N, where N represents the number of signal transmission modules that interfere with the mth signal transmission module. This represents the preset noise of the m-th signal transmission module. The real part of the preset noise of the m-th signal transmission module is represented. This represents the imaginary part of the preset noise of the m-th signal transmission module.

5. The communication method based on a network communication model according to claim 1, characterized in that, The first encoder network includes a first encoding layer, wherein the first encoder network is any one of the plurality of encoder networks, and before encoding based on the received signal to be transmitted and a preset interference coefficient using each of the encoder networks, the method further includes: Based on preset parameters, the network communication model to be trained is initialized. The parameters include: a first number of training transmission signal datasets, a second number of training transmission signals processed by the network communication model to be trained, a third number of channels, the number of times the network communication model is updated, the number of activation functions in the first coding layer, the order and grid precision of the spline functions in the activation functions, and the learning rate of the network communication model to be trained. Based on the third quantity, the network communication model to be trained is trained cyclically; If the network communication model reaches the convergence condition, the network communication model is obtained.

6. The communication method based on a network communication model according to claim 5, characterized in that, Training the network communication model to be trained includes: Randomly generate the interference coefficients and transmission signal dataset to be trained; Based on a predefined search space, generate noise to be trained; Freeze the channel gradient; Based on the interference coefficients to be trained, the transmission signal dataset to be trained, and the noise to be trained, the network communication model to be trained is trained to obtain the output signal dataset to be trained. Calculate the loss value based on the training transmission signal dataset and the training output signal dataset; Based on the loss value, the weights of the network communication model to be trained are updated using backpropagation.

7. The communication method based on a network communication model according to claim 6, characterized in that, The step of calculating the loss value based on the training transmission signal dataset and the training output signal dataset includes: Based on the training transmission signal dataset and the training output signal dataset, the loss value is calculated using the following loss function: in, This represents the loss value. This represents the first training temporary value of the k-th signal transmission module. This represents the preset loss weight of the k-th signal transmission module, where K represents the total number of signal transmission modules, and G represents the size of the training transmission signal dataset or the training output signal dataset. This represents the i-th transmission signal to be trained. This represents the i-th output signal to be trained.

8. A communication device based on a network communication model, characterized in that, The network communication model includes a channel layer and multiple signal transmission modules, each signal transmission module including a signal transmitting module and a signal output module; each signal transmitting module includes an encoder network, a power distribution network, and a coding and modulation layer; the communication device includes: The first encoding module is used to encode the received signal to be transmitted and a preset interference coefficient using each of the encoder networks to obtain multiple first encoded signals. The second encoding module is used to encode each of the power distribution networks based on the preset interference coefficient to obtain multiple second encoded signals. The coding and modulation module is used to obtain the transmitted signal transmitted by the signal transmission module corresponding to each signal transmission module by using the first coded signal encoded by the encoder network in the signal transmission module corresponding to each signal transmission module and the second coded signal encoded by the power distribution network, respectively. The calculation module is used to calculate the input signal of the signal output module corresponding to each signal transmission module using the channel layer, based on the preset noise, the preset interference coefficient and each of the transmitted signals; The decoding module is used to decode each input signal based on the corresponding signal output module of each signal transmission module to obtain multiple output signals.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1-7.

Images