Data processing method and related apparatus

Abstract

The present application provides a data processing method and a related apparatus, which are used for enabling a first apparatus to perform data enhancement on first training data, thereby increasing the quantity and diversity of training data, facilitating the training of a transceiver model (such as a transceiver neural network), and improving the training speed and training performance of the transceiver model. The method in the embodiments of the present application comprises: a first apparatus receiving first training data from a second apparatus; and the first apparatus performing data enhancement on the first training data to obtain enhanced training data.

Description

Data processing method and related device Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a data processing method and related devices. Background Art

[0002] The transmitter and receiver can communicate over the air interface. These can be implemented using neural networks. Currently, training the transmitter's neural network with data can achieve better transmission performance, while training the receiver's neural network with data can achieve better reception performance.

[0003] The transmitter and receiver are trained for the wireless environment. Specifically, the transmitter and receiver collect training data related to the wireless environment through the transmission of air interface data, and train the transceiver neural network based on this training data. However, the channel parameters (e.g., channel distribution) in a wireless environment typically change slowly. Therefore, the training data collected by the transmitter and receiver in a short period of time is often highly correlated, which is not conducive to the training of the transceiver neural network. This results in a decrease in the training speed and training performance of the transceiver neural network.

[0004] Summary of the Invention

[0005] The present application provides a data processing method and related apparatus, which can be used by a first device to perform data enhancement on first training data, thereby increasing the quantity and diversity of the training data. This is beneficial for training a transceiver model (e.g., a transceiver neural network), and improving the training speed and training performance of the transceiver model.

[0006] In a first aspect, the present application provides a data processing method, which can be performed by a first device. The first device can be a terminal device or a network device, or a component in the terminal device or network device (for example, a processor, a chip, or a chip system, etc.), or a logic module or software that can implement all or part of the functions of the terminal device, or a logic module or software that can implement all or part of the functions of the network device. The method includes:

[0007] The first device receives first training data from the second device; then, the first device performs data enhancement on the first training data to obtain enhanced training data. Thus, it can be seen that the first device can perform data enhancement on the first training data, thereby increasing the quantity and diversity of the training data. This is beneficial for training a transceiver model (e.g., a transceiver neural network), and improving the training speed and training performance of the transceiver model. For example, the first device can train the receiving model of the first device based on the enhanced training data, thereby improving the training speed and training performance of the receiving model.

[0008] Based on the first aspect, in one possible implementation, a first device performs data augmentation on first training data to obtain enhanced training data, including: the first device obtains a data augmentation configuration; and the first device performs data augmentation on the first training data according to the data augmentation configuration to obtain enhanced training data. Thus, it can be seen that the first device can perform data augmentation on the first training data based on the data augmentation configuration. This increases the amount of training data and makes the training data more diverse, which is beneficial for improving the training speed and training performance of the model.

[0009] Based on the first aspect, in one possible implementation, a first device performs data enhancement on first training data to obtain enhanced training data, including: the first device determines a data enhancement method to be used for the first training data; and the first device uses the data enhancement method to enhance the first training data based on a data enhancement parameter and a number of enhanced samples to obtain enhanced training data. Optionally, the enhanced training data includes multiple enhanced sample data. The number of enhanced sample data can be the aforementioned number of enhanced samples.

[0010] Based on the first aspect, in one possible implementation, a first device obtains a data augmentation configuration, including: the first device receiving first indication information from a second device, where the first indication information is used to indicate the data augmentation configuration. In this implementation, the second device can indicate the data augmentation configuration to the first device. This facilitates the first device to perform reasonable data augmentation on the first training data according to the data augmentation configuration. This facilitates the reasonable implementation of the solution and ensures the legitimacy of the enhanced training data. This helps improve the training speed and training performance of the model.

[0011] Based on the first aspect, in one possible implementation, the method further includes: the first device receives second indication information from the second device, the second indication information being used to indicate a data augmentation configuration available to the first device; and the first device obtains the data augmentation configuration, including: the first device obtains the data augmentation configuration based on the data augmentation configuration available to the first device indicated by the second indication information. This facilitates the first device to select a suitable data augmentation configuration from the data augmentation configurations available to the first device, or the first device can determine a suitable data augmentation configuration with reference to the data augmentation configurations available to the first device. This ensures the legitimacy of the enhanced training data, thereby facilitating improved model training speed and performance.

[0012] Based on the first aspect, in one possible implementation, the second indication information further indicates the priority of the data augmentation configurations available to the first device. This facilitates the first device selecting a data augmentation configuration with a corresponding priority based on actual needs to perform data augmentation on the first training data. This facilitates improving the training speed and training performance of the model.

[0013] Based on the first aspect, in one possible implementation, the data enhancement configuration includes at least one of the following: a data enhancement method, a data enhancement parameter, or the number of enhanced samples. Some possible contents of the data enhancement configuration are shown to make the solution more comprehensive.

[0014] Based on the first aspect, in one possible implementation, the data augmentation method includes at least one of the following: noise addition, signal phase rotation, signal random phase processing, channel simulation processing, or signal rearrangement. This facilitates the implementation of the solution, facilitates obtaining more and more diverse training data, and improves model training speed and performance.

[0015] Based on the first aspect, in one possible implementation, the data enhancement parameter includes at least one of the following: noise power, signal phase rotation angle, the distribution or range of random phases used in signal random phase processing, the ratio of the amplitudes of elements in a diagonal matrix used in channel simulation processing, or the unit of signal rearrangement in the time domain and / or frequency domain. In this implementation, specific forms of the data enhancement parameters are shown for various data enhancement methods, thereby facilitating the implementation of the solution.

[0016] Based on the first aspect, in one possible implementation, the method further includes: the first device training a reception model of the first device based on the enhanced training data, where the reception model is used by the first device to receive data and / or information. This enables the first device to quickly train the reception model based on the enhanced training data, thereby improving the training speed and performance of the reception model. It should be noted that this implementation can be considered an independent aspect and is independent of the first aspect and other implementations of the first aspect.

[0017] Based on the first aspect, in one possible implementation, the receiving model is configured to implement at least one of the following: channel estimation, equalization, channel decoding, symbol demodulation, waveform demodulation, or source decoding. This implementation illustrates some possible functions that the receiving model can implement. It should be noted that different functions can be implemented using different models or the same model. This allows the receiving model to replace the traditional air interface processing module, achieving intelligent air interface transmission.

[0018] Based on the first aspect, in one possible implementation, the method further includes: the first device generating intermediate training parameters and / or loss values ​​based on the enhanced training data; and the first device sending at least one of the following to the second device: an intermediate training parameter, a loss value, or a weighted value, where the weighted value is determined based on the intermediate training parameter or the loss value. This facilitates the second device to train the sending model of the second device based on the intermediate training parameter, the loss value, or the weighted value. Because the enhanced training data includes a larger amount of training data and the training data is more diverse, the first device can feedback more intermediate training parameters and loss values, which is beneficial to improving the training speed and training performance of the sending model of the second device.

[0019] Based on the first aspect, in one possible implementation, the first training data includes channel data between the first device and the second device. Before the first device receives the first training data from the second device, the method further includes: the first device sending a reference signal to the second device. The reference signal is used to determine the channel data, thereby enabling the second device to obtain the first training data.

[0020] The second aspect of the present application is a data processing method, which can be performed by a second device, which can be a terminal device or a network device, or a component in the terminal device or network device (for example, a processor, a chip, or a chip system, etc.), or a logic module or software that can implement all or part of the functions of the terminal device, or a logic module or software that can implement all or part of the functions of the network device. The method includes:

[0021] The second device sends first training data to the first device, and the first training data is used to perform data enhancement on the first training data to obtain enhanced training data. Because the enhanced training data includes a larger amount of training data and a greater diversity of training data, it is beneficial to improve the training speed and training performance of the first device's receiving model. Moreover, the first device can provide feedback of more intermediate training parameters and loss values ​​to the second device, thereby improving the training speed and training performance of the second device's sending model.

[0022] Based on the second aspect, in one possible implementation, the method further includes: the second device sending first indication information to the first device, where the first indication information is used to indicate a data augmentation configuration, and the data augmentation configuration is used to perform data augmentation on the first training data. In this implementation, the second device can indicate the data augmentation configuration to the first device. This facilitates the first device to perform reasonable data augmentation on the first training data according to the data augmentation configuration. This facilitates the reasonable implementation of the solution and ensures the legitimacy of the augmented training data. This helps improve the training speed and training performance of the model.

[0023] Based on the second aspect, in one possible implementation, the method further includes: the second device sending second indication information to the first device, where the second indication information is used to indicate a data augmentation configuration available to the first device. This facilitates the first device in selecting an appropriate data augmentation configuration, thereby ensuring the legitimacy of the augmented training data. This facilitates improving the training speed and performance of the model.

[0024] Based on the second aspect, in one possible implementation, the second indication information further indicates the priority of the data augmentation configurations available to the first device. This facilitates the first device selecting a data augmentation configuration with a corresponding priority based on actual needs to perform data augmentation on the first training data. This facilitates improving the training speed and performance of the model.

[0025] Based on the second aspect, in one possible implementation, the data enhancement configuration includes at least one of the following: a data enhancement method, a data enhancement parameter, or the number of enhanced samples. Some possible contents of the data enhancement configuration are shown to make the solution more comprehensive.

[0026] Based on the second aspect, in one possible implementation, the data augmentation method includes any of the following: noise addition, signal phase rotation, signal random phase processing, channel simulation processing, or signal rearrangement. This allows for implementation of the solution, facilitates obtaining more and more diverse training data, and improves model training speed and performance.

[0027] Based on the second aspect, in one possible implementation, the data enhancement parameter includes at least one of the following: noise power, signal phase rotation angle, the distribution or range of random phases used in signal random phase processing, the ratio of the amplitudes of elements in the diagonal matrix used in channel simulation processing, or the unit of signal rearrangement in the time domain and / or frequency domain. In this implementation, the specific form of the data enhancement parameter is shown for various data enhancement methods, thereby facilitating the implementation of the solution.

[0028] Based on the second aspect, in one possible implementation, the data augmentation configuration is determined based on the configuration of the first device's receiving model, the configuration of the second device's transmitting model, and / or the speed of channel changes between the first and second devices. The receiving model is used by the first device to receive data and / or information, and the transmitting model is used by the second device to send data and / or information. This allows the second device to configure the appropriate data augmentation configuration for the first device, ensuring the legitimacy of the augmented training data. This helps improve model training speed and performance.

[0029] Based on the second aspect, in a possible implementation, the method further includes: the second device receives at least one of the following from the first device: an intermediate training parameter, a loss value, or a weighted value, the intermediate training parameter or loss value is determined based on the enhanced training data, and the weighted value is determined based on the intermediate training parameter or loss value; the second device trains the sending model based on at least one of the intermediate training parameter, loss value and weighted value, and the sending model is used for the second device to send data and / or information. Since the enhanced training data includes a larger amount of training data and the training data is more diverse, the first device can feed back more intermediate training parameters and loss values, which is beneficial to improving the training speed and training performance of the sending model of the second device. It should be noted that this implementation can be used as an independent aspect and does not depend on the second aspect or any implementation of the second aspect.

[0030] Based on the second aspect, in one possible implementation, the transmission model is configured to implement at least one of the following: channel coding, symbol modulation, waveform modulation, or source coding. This implementation illustrates some possible functions that the transmission model can implement. It should be noted that different functions can be implemented using different models or the same model. This allows the transmission model to replace traditional air interface processing modules, achieving intelligent air interface transmission.

[0031] Based on the second aspect, in one possible implementation, the first training data includes channel data between the first device and the second device; the method further includes: the second device receiving a reference signal from the first device; and the second device measuring the reference signal to obtain the channel data. In this implementation, the second device obtains the channel data by measuring the reference signal. This enables the second device and the first device to perform model training based on the channel data.

[0032] A third aspect of the present application provides a data processing method, which can be performed by a first device, which can be a terminal device or a network device, or a component in the terminal device or network device (for example, a processor, a chip, or a chip system, etc.), or a logic module or software that can implement all or part of the functions of the terminal device, or a logic module or software that can implement all or part of the functions of the network device. The method includes:

[0033] The first device receives enhanced training data from the second device, where the enhanced training data is obtained by performing data enhancement on the first training data. Thus, the first device can obtain a larger amount of training data and a wider variety of training data. This is beneficial for training a transceiver model (e.g., a transceiver neural network), and improves the training speed and training performance of the transceiver model. For example, the first device can train the receiving model of the first device based on the enhanced training data, thereby improving the training speed and training performance of the receiving model.

[0034] Based on the third aspect, in one possible implementation, the method further includes: the first device sending first indication information to the second device, where the first indication information is used to indicate a data augmentation configuration, and the data augmentation configuration is used to perform data augmentation on the first training data. In this implementation, the first device can indicate the data augmentation configuration to the second device. This facilitates the second device to perform data augmentation on the first training data according to the data augmentation configuration. This facilitates the rational implementation of the solution and ensures the legitimacy of the augmented training data. This helps improve the training speed and training performance of the model.

[0035] Based on the third aspect, in one possible implementation, the method further includes: the first device sending second indication information to the second device, where the second indication information is used to indicate a data augmentation configuration available to the second device. This facilitates the second device in selecting an appropriate data augmentation configuration, thereby ensuring the legitimacy of the augmented training data. This facilitates improving the training speed and performance of the model.

[0036] Based on the third aspect, in one possible implementation, the second indication information further indicates the priority of the data augmentation configurations available to the second device. This facilitates the second device selecting a data augmentation configuration with a corresponding priority based on actual needs to perform data augmentation on the first training data. This helps improve the training speed and performance of the model.

[0037] Based on the third aspect, in one possible implementation, the data enhancement configuration includes at least one of the following: a data enhancement method, data enhancement parameters, or the number of enhanced samples. Some possible contents of the data enhancement configuration are shown to make the solution more comprehensive.

[0038] Based on the third aspect, in one possible implementation, the data augmentation method includes any of the following: noise addition, signal phase rotation, signal random phase processing, channel simulation processing, or signal rearrangement. This allows for implementation of the solution, facilitates obtaining more and more diverse training data, and improves model training speed and performance.

[0039] Based on the third aspect, in one possible implementation, the data enhancement parameter includes at least one of the following: noise power, signal phase rotation angle, the distribution or range of random phases used in signal random phase processing, the ratio of the amplitudes of elements in the diagonal matrix used in channel simulation processing, or the unit of signal rearrangement in the time domain and / or frequency domain. This implementation shows the specific form of the data enhancement parameter for various data enhancement methods, thereby facilitating the implementation of the solution.

[0040] Based on the third aspect, in a possible implementation, the method further includes: the first device determines intermediate training parameters and / or loss values ​​based on the enhanced training data; the first device sends at least one of the following to the second device: an intermediate training parameter, a loss value, or a weighted value, wherein the intermediate training parameter or loss value is determined based on the enhanced training data, and the weighted value is determined based on the intermediate training parameter or loss value. This facilitates the second device to train the sending model of the second device based on the intermediate training parameter, loss value, or weighted value. Since the enhanced training data includes a larger amount of training data and the training data is more diverse, the first device can feed back more intermediate training parameters and loss values, which is beneficial to improving the training speed and training performance of the sending model of the second device.

[0041] Based on the third aspect, in one possible implementation, the method further includes: the first device training a reception model of the first device based on the enhanced training data, where the reception model is used by the first device to receive data and / or information. This enables the first device to quickly train the reception model based on the enhanced training data, thereby improving the training speed and performance of the reception model.

[0042] Based on the third aspect, in one possible implementation, the receiving model is configured to implement at least one of the following: channel estimation, equalization, channel decoding, symbol demodulation, waveform demodulation, or source decoding. This implementation illustrates some possible functions that the receiving model can implement. It should be noted that different functions can be implemented using different models or the same model. This allows the receiving model to replace the traditional air interface processing module, achieving intelligent air interface transmission.

[0043] Based on the third aspect, in one possible implementation, the first training data includes channel data between the first device and the second device; before the first device receives the enhanced training data from the second device, the method further includes: the first device sending a reference signal to the second device, where the reference signal is used to determine the channel data, thereby facilitating the second device to obtain the first training data.

[0044] A fourth aspect of the present application provides a data processing method, which can be performed by a second device, which can be a terminal device or a network device, or a component in the terminal device or network device (for example, a processor, a chip, or a chip system, etc.), or a logic module or software that can implement all or part of the functions of the terminal device, or a logic module or software that can implement all or part of the functions of the network device. The method includes:

[0045] The second device performs data enhancement on the first training data to obtain enhanced training data; the second device sends the enhanced training data to the first device. It can be seen from this that the second device can perform data enhancement on the first training data and send the enhanced training data to the first device. This is conducive to improving the quantity and diversity of training data. It is conducive to the training of transceiver models (for example, transceiver neural networks) and improving the training speed and training performance of transceiver models. For example, the first device can train the receiving model of the first device based on the enhanced training data, thereby improving the training speed and training performance of the receiving model. The second device can train the sending model of the second device based on the enhanced training data, thereby improving the training speed and training performance of the sending model.

[0046] Based on the fourth aspect, in one possible implementation, the method further includes: a second device acquiring a data augmentation configuration; and the second device performing data augmentation on the first training data to obtain enhanced training data, including: the second device performing data augmentation on the first training data according to the data augmentation configuration to obtain enhanced training data. Thus, it can be seen that the second device can perform data augmentation on the first training data based on the data augmentation configuration. This increases the amount of training data and makes the training data more diverse, which is beneficial for improving the training speed and training performance of the model.

[0047] Based on the fourth aspect, in one possible implementation, the second device obtains a data augmentation configuration, including: the second device receiving first indication information from the first device, where the first indication information is used to indicate the data augmentation configuration. In this implementation, the first device can indicate the data augmentation configuration to the second device. This facilitates the second device to perform data augmentation on the first training data according to the data augmentation configuration. This facilitates the rational implementation of the solution and ensures the legitimacy of the enhanced training data. This helps improve the training speed and training performance of the model.

[0048] Based on the fourth aspect, in one possible implementation, the method further includes: the second device receiving second indication information from the first device, the second indication information being used to indicate a data augmentation configuration available to the second device; the second device obtaining the data augmentation configuration, including: the second device obtaining the data augmentation configuration according to the data augmentation configuration available to the second device indicated by the second indication information. This facilitates the second device to select a suitable data augmentation configuration from the data augmentation configurations available to the second device; alternatively, the second device may determine a suitable data augmentation configuration with reference to the data augmentation configurations available to the second device. This ensures the legitimacy of the enhanced training data, thereby facilitating improved model training speed and performance.

[0049] Based on the fourth aspect, in one possible implementation, the data enhancement configuration includes at least one of the following: a data enhancement method, data enhancement parameters, or the number of enhanced samples. Some possible contents of the data enhancement configuration are shown to make the solution more comprehensive.

[0050] Based on the fourth aspect, in one possible implementation, the data augmentation method includes any of the following: noise addition, signal phase rotation, signal random phase processing, channel simulation processing, or signal rearrangement. This allows for implementation of the solution, facilitates obtaining more and more diverse training data, and improves model training speed and performance.

[0051] Based on the fourth aspect, in one possible implementation, the data enhancement parameter includes at least one of the following: noise power, signal phase rotation angle, the distribution or range of random phases used in signal random phase processing, the ratio of the amplitudes of elements in a diagonal matrix used in channel simulation processing, or the unit of signal rearrangement in the time domain and / or frequency domain. This implementation shows the specific forms of the data enhancement parameters for various data enhancement methods, thereby facilitating the implementation of the solution.

[0052] Based on the fourth aspect, in one possible implementation, the method further includes: the second device receiving at least one of the following from the first device: an intermediate training parameter, a loss value, or a weighted value, wherein the intermediate training parameter or loss value is determined based on the enhanced training data, and the weighted value is determined based on the intermediate training parameter or loss value; the second device trains a sending model of the second device based on at least one of the intermediate training parameter, the loss value, and the weighted value, wherein the sending model is used for the second device to send data and / or information. Because the enhanced training data includes a larger amount of training data and the training data is more diverse, the first device can feedback more intermediate training parameters and loss values, thereby facilitating improving the training speed and training performance of the sending model of the second device.

[0053] Based on the fourth aspect, in one possible implementation, the transmission model is configured to implement at least one of the following: channel coding, symbol modulation, waveform modulation, or source coding. This implementation illustrates some possible functions that the transmission model can implement. It should be noted that different functions can be implemented using different models or the same model. This allows the transmission model to replace traditional air interface processing modules, achieving intelligent air interface transmission.

[0054] Based on the fourth aspect, in one possible implementation, the first training data includes channel data between the first device and the second device; the method further includes: the second device receiving a reference signal from the first device; and the second device measuring the reference signal to obtain the channel data. In this implementation, the second device obtains the channel data by measuring the reference signal. This enables the second device and the first device to perform model training based on the channel data.

[0055] A fifth aspect of the present application provides a first device, including:

[0056] a transceiver module, configured to receive first training data from a second device;

[0057] The processing module is used to perform data enhancement on the first training data to obtain enhanced training data.

[0058] Based on the fifth aspect, in one possible implementation, the processing module is further configured to: obtain a data enhancement configuration;

[0059] The processing module is specifically used to:

[0060] Data enhancement is performed on the first training data according to the data enhancement configuration to obtain enhanced training data.

[0061] Based on the fifth aspect, in one possible implementation, the processing module is specifically configured to:

[0062] First indication information is received from a second device, where the first indication information is used to indicate a data enhancement configuration.

[0063] Based on the fifth aspect, in one possible implementation, the processing module is specifically configured to:

[0064] receiving second indication information from the second device, where the second indication information is used to indicate a data enhancement configuration available to the first device;

[0065] The data enhancement configuration is obtained according to the data enhancement configuration available to the first device indicated by the second indication information.

[0066] Based on the fifth aspect, in a possible implementation, the second indication information further indicates the priority of the data enhancement configuration available to the first device.

[0067] Based on the fifth aspect, in a possible implementation, the data enhancement configuration includes at least one of the following: a data enhancement method, a data enhancement parameter, or the number of enhanced samples.

[0068] Based on the fifth aspect, in a possible implementation, the data enhancement method includes at least one of the following: adding noise, signal phase rotation, signal random phase processing, channel simulation processing, or signal rearrangement.

[0069] Based on the fifth aspect, in one possible implementation method, the data enhancement parameters include at least one of the following: noise power, signal phase rotation angle, distribution or range of random phase adopted by signal random phase processing, ratio of amplitudes of elements of diagonal matrix adopted by channel simulation processing, or rearrangement unit of signal in time domain and / or frequency domain.

[0070] Based on the fifth aspect, in one possible implementation, the processing module is further configured to:

[0071] A receiving model of the first device is trained according to the enhanced training data, and the receiving model is used for the first device to receive data.

[0072] Based on the fifth aspect, in one possible implementation, the receiving model is used to implement at least one of the following: channel estimation, equalization, channel decoding, symbol demodulation, waveform demodulation, or source decoding.

[0073] Based on the fifth aspect, in one possible implementation, the processing module is further configured to:

[0074] generating intermediate training parameters and / or loss values ​​based on the augmented training data;

[0075] The transceiver module is further configured to transmit at least one of the following to the second device: an intermediate training parameter, a loss value, or a weighted value, where the weighted value is determined based on the intermediate training parameter or the loss value. Optionally, the intermediate training parameter, the loss value, and / or the weighted value are used to train a transmission model of the second device.

[0076] A sixth aspect of the present application provides a second device, including:

[0077] The transceiver module is used to send first training data to the first device, where the first training data is used to perform data enhancement on the first training data to obtain enhanced training data.

[0078] Based on the sixth aspect, in one possible implementation, the transceiver module is further configured to:

[0079] First indication information is sent to the first device, where the first indication information is used to indicate a data enhancement configuration, and the data enhancement configuration is used to perform data enhancement on the first training data.

[0080] Based on the sixth aspect, in one possible implementation, the transceiver module is further configured to:

[0081] Second indication information is sent to the first device, where the second indication information is used to indicate a data enhancement configuration available to the first device.

[0082] Based on the sixth aspect, in a possible implementation, the second indication information further indicates the priority of the data enhancement configuration available to the first device.

[0083] Based on the sixth aspect, in a possible implementation, the data enhancement configuration includes at least one of the following: a data enhancement method, a data enhancement parameter, or the number of enhanced samples.

[0084] Based on the sixth aspect, in a possible implementation, the data enhancement method includes any one of the following: adding noise, signal phase rotation, signal random phase processing, channel simulation processing, or signal rearrangement.

[0085] Based on the sixth aspect, in one possible implementation, the data enhancement parameters include at least one of the following: noise power, signal phase rotation angle, distribution or range of random phase adopted by signal random phase processing, ratio of amplitudes of elements of diagonal matrix adopted by channel simulation processing, or rearrangement unit of signal in time domain and / or frequency domain.

[0086] Based on the sixth aspect, in one possible implementation method, the data enhancement configuration is determined according to the configuration of the receiving model of the first device, the configuration of the sending model of the second device and / or the speed of channel change between the first device and the second device. The receiving model is used by the first device to receive data and / or information, and the sending model is used by the second device to send data and / or information.

[0087] Based on the sixth aspect, in a possible implementation method, the transceiver module is also used to: receive at least one of the following from the first device: an intermediate training parameter, a loss value, or a weighted value, the intermediate training parameter or loss value is determined based on the enhanced training data, and the weighted value is determined based on the intermediate training parameter or loss value; the processing module is also used to: train the sending model based on at least one of the intermediate training parameters, the loss value and the weighted value, and the sending model is used for the second device to send data and / or information.

[0088] Based on the sixth aspect, in one possible implementation, the transmission model is used to implement at least one of the following: channel coding, symbol modulation, waveform modulation, or source coding.

[0089] Based on the sixth aspect, in a possible implementation, the first training data includes channel data between the first device and the second device; the transceiver module is further used to: receive a reference signal from the first device; and the processing module is further used to: measure the reference signal to obtain the channel data.

[0090] A seventh aspect of the present application provides a first device, including:

[0091] The transceiver module is used to receive enhanced training data from the second device, where the enhanced training data is obtained by performing data enhancement on the first training data.

[0092] Based on the seventh aspect, in a possible implementation method, the transceiver module is further used to: send first indication information to the second device, the first indication information is used to indicate a data enhancement configuration, and the data enhancement configuration is used to perform data enhancement on the first training data.

[0093] Based on the seventh aspect, in a possible implementation, the transceiver module is further used to: send second indication information to the second device, where the second indication information is used to indicate a data enhancement configuration available to the second device.

[0094] Based on the seventh aspect, in a possible implementation, the second indication information further indicates the priority of the data enhancement configuration available to the second device.

[0095] Based on the seventh aspect, in a possible implementation, the data enhancement configuration includes at least one of the following: a data enhancement method, a data enhancement parameter, or the number of enhanced samples.

[0096] Based on the seventh aspect, in a possible implementation, the data enhancement method includes any one of the following: adding noise, signal phase rotation, signal random phase processing, channel simulation processing, or signal rearrangement.

[0097] Based on the seventh aspect, in one possible implementation method, the data enhancement parameters include at least one of the following: noise power, signal phase rotation angle, distribution or range of random phase adopted by signal random phase processing, ratio of amplitudes of elements of diagonal matrix adopted by channel simulation processing, or rearrangement unit of signal in time domain and / or frequency domain.

[0098] Based on the seventh aspect, in a possible implementation, the first device further includes a processing module;

[0099] a processing module for determining intermediate training parameters and / or loss values ​​based on the enhanced training data;

[0100] The transceiver module is used to send at least one of the following items to the second device: an intermediate training parameter, a loss value, or a weighted value, where the intermediate training parameter or the loss value is determined based on the enhanced training data, and the weighted value is determined based on the intermediate training parameter or the loss value.

[0101] Based on the seventh aspect, in a possible implementation, the first device further includes a processing module;

[0102] The processing module is used to train a receiving model of the first device according to the enhanced training data, where the receiving model is used by the first device to receive data and / or information.

[0103] Based on the seventh aspect, in one possible implementation, the receiving model is used to implement at least one of the following: channel estimation, equalization, channel decoding, symbol demodulation, waveform demodulation, or source decoding.

[0104] Based on the seventh aspect, in a possible implementation, the first training data includes channel data between the first device and the second device; the transceiver module is further used to: send a reference signal to the second device, where the reference signal is used to determine the channel data.

[0105] An eighth aspect of the present application provides a second device, including:

[0106] A processing module, configured to perform data enhancement on the first training data to obtain enhanced training data;

[0107] The transceiver module is used to send enhanced training data to the first device.

[0108] Based on the eighth aspect, in one possible implementation, the processing module is specifically configured to:

[0109] Obtain a data enhancement configuration; perform data enhancement on the first training data according to the data enhancement configuration to obtain enhanced training data.

[0110] Based on the eighth aspect, in one possible implementation, the processing module is specifically configured to:

[0111] First indication information is received from a first device, where the first indication information is used to indicate a data enhancement configuration.

[0112] Based on the eighth aspect, in one possible implementation, the processing module is specifically configured to:

[0113] receiving second indication information from the first device, where the second indication information is used to indicate a data enhancement configuration available to the first device;

[0114] The data enhancement configuration is obtained according to the data enhancement configuration available to the first device indicated by the second indication information.

[0115] Based on the eighth aspect, in a possible implementation, the data enhancement configuration includes at least one of the following: a data enhancement method, a data enhancement parameter, or the number of enhanced samples.

[0116] Based on the eighth aspect, in a possible implementation, the data enhancement method includes any one of the following: adding noise, signal phase rotation, signal random phase processing, channel simulation processing, or signal rearrangement.

[0117] Based on the eighth aspect, in one possible implementation method, the data enhancement parameters include at least one of the following: noise power, signal phase rotation angle, distribution or range of random phase adopted by signal random phase processing, ratio of amplitudes of elements of diagonal matrix adopted by channel simulation processing, or rearrangement unit of signal in time domain and / or frequency domain.

[0118] Based on the eighth aspect, in a possible implementation method, the transceiver module is also used to: receive at least one of the following from the first device: an intermediate training parameter, a loss value, or a weighted value, the intermediate training parameter or loss value is determined based on the enhanced training data, and the weighted value is determined based on the intermediate training parameter or loss value.

[0119] Based on the eighth aspect, in a possible implementation method, the processing module is also used to: train a sending model of the second device based on at least one of the intermediate training parameters, loss value and weighted value, and the sending model is used by the second device to send data and / or information.

[0120] Based on the eighth aspect, in one possible implementation, the transmission model is used to implement at least one of the following: channel coding, symbol modulation, waveform modulation, or source coding.

[0121] Based on the eighth aspect, in one possible implementation, the first training data includes channel data between the first device and the second device; the transceiver module is further used to: receive a reference signal from the first device; and the processing module is further used to: measure the reference signal to obtain the channel data.

[0122] In a ninth aspect, the present application provides a first apparatus, comprising: a processor and a memory. The memory stores a computer program or computer instructions, and the processor is configured to call and execute the computer program or computer instructions stored in the memory, so that the processor implements any one of the implementations of the first or third aspects.

[0123] Optionally, the first device further includes a transceiver, and the processor is used to control the transceiver to transmit and receive signals.

[0124] In a tenth aspect, the present application provides a second apparatus, comprising: a processor and a memory. The memory stores a computer program or computer instructions, and the processor is configured to call and execute the computer program or computer instructions stored in the memory, so that the processor implements any one of the implementations of the second aspect or the fourth aspect.

[0125] Optionally, the second device further includes a transceiver, and the processor is used to control the transceiver to transmit and receive signals.

[0126] In an eleventh aspect, the present application provides a first device, comprising a processor and an interface circuit, wherein the processor is configured to communicate with other devices via the interface circuit and execute the method described in the first or third aspect. The processor comprises one or more processors.

[0127] In a twelfth aspect, the present application provides a second device, comprising a processor and an interface circuit, wherein the processor is configured to communicate with other devices via the interface circuit and execute the method described in the second or fourth aspect. The processor may comprise one or more processors.

[0128] In a thirteenth aspect, the present application provides a first device, comprising a processor, configured to be connected to a memory and configured to call a program stored in the memory to execute the method described in the first or third aspect. The memory may be located within or outside the first device. The processor may include one or more processors.

[0129] In a fourteenth aspect, the present application provides a second device, comprising a processor, connected to a memory, configured to invoke a program stored in the memory to execute the method described in the second or fourth aspect. The memory may be located within or outside the second device. The processor may include one or more processors.

[0130] In one implementation, the first device of the fifth, seventh, and ninth aspects may be a chip or a chip system.

[0131] In one implementation, the second device of the sixth, eighth, and tenth aspects may be a chip or a chip system.

[0132] In a fifteenth aspect, the present application provides a computer program product comprising computer instructions, characterized in that when the computer program product is run on a computer, the computer is enabled to execute any one of the implementation methods of any one of the first to fourth aspects.

[0133] In a sixteenth aspect, the present application provides a computer-readable storage medium comprising computer instructions, which, when executed on a computer, enables the computer to execute any one of the implementation methods in any one of the first to fourth aspects.

[0134] In the seventeenth aspect, the present application provides a chip device, comprising a processor for calling a computer program or computer instruction in a memory so that the processor executes any one of the implementation methods of any one of the first to fourth aspects above.

[0135] Optionally, the processor is coupled to the memory via an interface.

[0136] In the eighteenth aspect of the present application, a communication system is provided, which includes a first device and a second device; the first device is used to execute the method shown in the first aspect, and the second device is used to execute the method shown in the second aspect; or, the first device is used to execute the method shown in the third aspect, and the second device is used to execute the method shown in the fourth aspect.

[0137] Through the above technical solution, it can be seen that the first device receives the first training data from the second device. Then, the first device performs data enhancement on the first training data to obtain enhanced training data. It can be seen that the first device can perform data enhancement on the first training data, thereby increasing the quantity and diversity of the training data. It is beneficial to the training of the transceiver model (for example, the transceiver neural network) and improving the training speed and training performance of the transceiver model. For example, the first device can train the receiving model of the first device based on the enhanced training data, thereby improving the training speed and training performance of the receiving model. BRIEF DESCRIPTION OF THE DRAWINGS

[0138] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application;

[0139] FIG2A is a schematic diagram of some functions implemented by a sending model according to an embodiment of the present application;

[0140] FIG2B is a schematic diagram of some functions implemented by a receiving model according to an embodiment of the present application;

[0141] FIG3A is another schematic diagram of a communication system according to an embodiment of the present application;

[0142] FIG3B is another schematic diagram of the communication system according to an embodiment of the present application;

[0143] FIG3C is another schematic diagram of a communication system according to an embodiment of the present application;

[0144] FIG4 is a schematic diagram of an embodiment of a data processing method according to an embodiment of the present application;

[0145] FIG5 is a flow chart of a data processing method according to an embodiment of the present application;

[0146] FIG6 is a schematic diagram of another embodiment of the data processing method according to an embodiment of the present application;

[0147] FIG7 is a schematic structural diagram of the first device according to an embodiment of the present application;

[0148] FIG8 is another structural diagram of the first device according to an embodiment of the present application;

[0149] FIG9 is a schematic structural diagram of a second device according to an embodiment of the present application;

[0150] FIG10 is another schematic structural diagram of the second device according to an embodiment of the present application;

[0151] FIG11 is a schematic structural diagram of a device according to an embodiment of the present application;

[0152] FIG12 is another schematic structural diagram of the device according to an embodiment of the present application;

[0153] FIG13 is another structural diagram of the device according to an embodiment of the present application. DETAILED DESCRIPTION

[0154] The present application provides a data processing method and related apparatus, which can be used by a first device to perform data enhancement on first training data, thereby increasing the quantity and diversity of the training data. This is beneficial for training a transceiver model (e.g., a transceiver neural network), and improving the training speed and training performance of the transceiver model.

[0155] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0156] References to "one embodiment" or "some embodiments" in this application mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0157] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "plurality" means two or more. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c; a and b; a and c; b and c; or a, b, and c. Among them, a, b, and c can be single or multiple.

[0158] It is understood that in this application, "indication" can include direct indication, indirect indication, explicit indication, and implicit indication. When describing that a certain indication information is used to indicate A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A.

[0159] In this application, the information indicated by the indication information is referred to as the information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated, etc., or the information to be indicated can be indirectly indicated by indicating other information, wherein there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can also be achieved with the help of the arrangement order of each information agreed in advance (such as specified in the protocol), thereby reducing the indication overhead to a certain extent.

[0160] The information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately. The transmission period and / or transmission timing of these sub-information can be the same or different. The specific transmission method is not limited in this application. The transmission period and / or transmission timing of these sub-information can be predefined, for example, according to a protocol, or can be configured by the transmitting device through sending configuration information to the receiving device.

[0161] It can be understood that "sending" and "receiving" in this application indicate the direction of signal transmission. For example, "sending information to XX" can be understood as the destination of the information is XX, which can include direct sending through the air interface, and also include indirect sending through the air interface by other units or modules. "Receiving information from YY" can be understood as the source of the information is YY, which can include direct receiving from YY through the air interface, and also include indirect receiving from YY through the air interface from other units or modules. "Sending" can also be understood as the "output" of the chip interface, and "receiving" can also be understood as the "input" of the chip interface.

[0162] In other words, sending and receiving can be performed between devices, for example, between a network device and a terminal device, or can be performed within a device, for example, sending or receiving between components, modules, chips, software modules or hardware modules within the device through a bus, wiring or interface.

[0163] It is understandable that information may be processed between the source and destination of information transmission, such as coding, modulation, etc., but the destination can understand the valid information from the source. Similar expressions in this application can be understood similarly and will not be repeated.

[0164] The technical solution of the present application can be applied to cellular communication systems related to the 3rd Generation Partnership Project (3GPP). For example, the fourth generation (4G) communication system, the fifth generation (5G) communication system, and the communication system after the fifth generation communication system. For example, the sixth generation communication system. For example, the fourth generation communication system may include a long term evolution (LTE) communication system. The fifth generation communication system may include a new radio (NR) communication system. The technical solution of the present application can also be applied to wireless fidelity (WiFi) systems, communication systems that support the integration of multiple wireless technologies, device-to-device (D2D) systems, vehicle to everything (V2X) communication systems, or satellite communication systems, etc. The wireless communication systems involved in this application also include but are not limited to: narrowband Internet of Things (NB-IoT) system, global system for mobile communications (GSM), enhanced data rate for GSM evolution (EDGE), wideband code division multiple access (WCDMA), code division multiple access 2000 (CDMA2000), or time division-synchronization code division multiple access (TD-SCDMA).

[0165] The communication system to which the technical solution of the present application is applicable includes a first device and a second device. The first device has a receiver, and the receiver is used to receive data and / or information, etc. Optionally, the receiver can be implemented by a receiving model, and the receiving model is used to receive data and / or information. The receiving model can be a receiving neural network, or other artificial intelligence (AI) model, which is not specifically limited in this application. The second device has a transmitter, and the transmitter is used to send data and / or information, etc. Optionally, the transmitter is implemented by a sending model, and the sending model is used to send data and / or information. The sending model can be a sending neural network, or other AI model, which is not specifically limited in this application. Optionally, from the perspective of sending and receiving training data, the first device can also be called a receiving end device, and the second device can also be called a sending end device.

[0166] Optionally, the first device is a network device or a terminal device; or the first device is a chip, a chip system, or a processor in the network device or the terminal device; or the first device is a logic module or software that implements part or all of the functions of the network device; or the first device is a logic module or software that implements part or all of the functions of the terminal device.

[0167] Optionally, the second device is a network device or a terminal device; or the first device is a chip, chip system, or processor in the network device or the terminal device; or the first device is a logic module or software that implements part or all of the functions of the network device; or the second device is a logic module or software that implements part or all of the functions of the terminal device.

[0168] Optionally, the first device is a terminal device and the second device is a network device; or the first device is a network device and the second device is a terminal device. Optionally, the network device is an access network device or a core network device. The following mainly uses the network device as an access network device as an example to introduce the technical solution of this application.

[0169] Optionally, the first device is a first terminal device, and the second device is a second terminal device.

[0170] Optionally, the first device is a first network device, and the second device is a second network device. For example, the first network device is a first access network device, and the second network device is a second access network device. Alternatively, the first network device is a first core network device, and the second network device is a second core network device. Alternatively, the first network device is an access network device, and the second network device is a core network device. Alternatively, the first network device is a core network device, and the second network device is an access network device. This application does not limit this.

[0171] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application. Referring to FIG1 , the first device includes a receiver, which is used to receive data and / or information, etc. The receiver can be implemented by a receiving model. The second device includes a transmitter, which is used to send data and / or information, etc. The transmitter can be implemented by a sending model. The transmitter and the receiver communicate through a channel. Optionally, the sending model can be a sending neural network, or other AI models, which is not limited in this application. Optionally, the receiving model can be a receiving neural network, or other AI models, which is not limited in this application. The transmitter transmits the data x through the sending model. k Processing to obtain data z k Data z k After transmission through the channel, the data y received by the receiver k The receiver receives the data y through the receiving model k Processing to obtain data

[0172] Optionally, the transmission model can replace one or more functional modules used in the transmission process. For example, as shown in FIG2A , the transmission model can implement at least one of the following: source coding, channel coding, symbol modulation, or waveform modulation. That is, the transmission model can replace the source coding module, channel coding module, symbol modulation module, and / or waveform modulation module in a traditional transmitter.

[0173] It should be noted that, in the present application, optionally, the sending model includes the processing of the data and / or information to be sent by the second device at the physical (PHY) layer, the media access control (MAC) layer, the radio resource control (RRC) layer, the packet data convergence protocol (PDCP) layer, and / or the application layer. Here, only an example is given of the sending model including the processing of the data and / or information to be sent by the second device at some possible protocol layers. The sending model may also include the processing of the data and / or information to be sent by the second device at other protocol layers, which is not specifically limited in this application.

[0174] Optionally, the receiving model can replace one or more functional modules used in the receiving process. For example, as shown in FIG2B , the receiving model can implement at least one of the following: waveform demodulation, channel estimation, channel equalization, symbol demodulation, channel decoding, or source decoding. That is, the receiving model can replace the waveform demodulation module, channel estimation module, channel equalization, symbol demodulation module, channel decoding module, and / or source decoding module in a traditional receiver.

[0175] It should be noted that, in the present application, the reception model includes the processing of received data and / or information by the first device at the PHY layer, MAC layer, RRC layer, PDCP layer, and / or application layer. Here, only an example is given of the reception model including the processing of received data and / or information by the first device at some possible protocol layers. The reception model may also include the processing of received data and / or information by the first device at other protocol layers, which is not specifically limited in the present application.

[0176] The following introduces the terminal equipment and network equipment involved in this application.

[0177] Terminal equipment, also known as user equipment (UE), mobile station (MS), mobile terminal (MT), or customer premise equipment (CPE), is a device that includes wireless communication capabilities (providing voice and data connectivity to users). Examples include handheld devices, in-vehicle devices, and machine-type communication (MTC) terminals with wireless connectivity. Currently, terminal equipment can include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals used in industrial control, self-driving vehicles, remote medical surgery, smart grids, transportation safety, smart cities, and smart homes. For example, wireless terminals in unmanned driving can be drones, helicopters, or airplanes. For example, wireless terminals in the Internet of Vehicles can be onboard equipment, complete vehicle equipment, onboard modules, vehicles, or ships. Wireless terminals in industrial control can be cameras, robots, or robotic arms. Wireless terminals in smart homes can be televisions, air conditioners, vacuum cleaners, speakers, or set-top boxes.

[0178] It should be noted that the terminal device can be a device or apparatus with a chip, or a device or apparatus with integrated circuits, or a chip, module or control unit in the device or apparatus shown above, and this application does not limit this specifically.

[0179] A network device is a device deployed in a radio access network (RAN) to provide wireless communication capabilities for terminal devices. A network device can also be called an access network (RAN) entity, access node, network node, or communication device.

[0180] Specifically, the network device may be an access network device of a cellular system related to the 3rd Generation Partnership Project (3GPP). For example, a fourth-generation (4G) mobile communication system or a 5G mobile communication system. The network device may also be an access network device in an open access network (O-RAN or ORAN) or a cloud radio access network (CRAN). Alternatively, the network device may be an access network device in a communication system obtained by integrating two or more of the above communication systems.

[0181] The network equipment includes, but is not limited to, evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved NodeB, or home Node B, HNB), baseband unit (BBU), access point (AP) in wireless fidelity (WIFI) system, macro base station, micro base station, wireless relay node, donor node, wireless controller in CRAN scenario, wireless backhaul node, transmission point (TP) or transmission and receiving point (TRP). The network equipment can also be an access network equipment in a 5G mobile communication system. For example, a next generation NodeB (gNB) in a new radio (NR) system, a TRP, a TP, or one or a group of antenna panels (including multiple antenna panels) of a base station in a 5G mobile communication system. Alternatively, the network device may also be a network node constituting a gNB or a transmission point. For example, a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). The CU and DU may be configured separately or included in the same network element. For example, a BBU. The RU may be included in a radio frequency device or radio frequency unit. For example, in a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH). Alternatively, the network device may also be a server, a wearable device, a vehicle, or an on-board device. For example, in V2X technology, the network device may be a road side unit (RSU).

[0182] It should be noted that in different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (ORAN) system, CU may also be called an open centralized unit (O-CU) or an open CU, DU may also be called an open distributed unit (O-DU), a centralized unit control plane (CU-CP) may also be called an open centralized unit control plane (O-CU-CP) or an open CU-CP, a centralized unit user plane (CU-UP) may also be called an open centralized unit user plane (O-CU-UP) or an open CU-UP, and RU may also be called an open radio unit (O-RU). This application does not limit this. Any of the CU, CU-CP, CU-UP, DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0183] Optionally, for network elements in the ORAN system, each network element may implement the protocol layer functions shown in Table 1 below.

[0184] Table 1

[0185] It should be noted that the network device can be one or more network elements shown in Table 1 above, and this application does not make any specific limitations.

[0186] It should be noted that Table 1 above is merely an example. In actual applications, the protocol layer functions supported by each network element are not limited. For example, each network element may support more protocol layer functions, or the protocol layer functions supported by each network element may be specifically configured based on actual conditions. This application does not impose any specific restrictions.

[0187] The following describes the architecture of the CU and DU of an access network device. The access network device includes at least one CU and at least one DU. Optionally, the access network device also includes at least one RU.

[0188] The following is an introduction using the example of an access network device including a CU and a DU. The CU has some functions of the core network, and the CU may include a CU-CP and a CU-UP. The CU and the DU may be configured according to the protocol layer functions of the wireless network they implement. For example, the CU is configured to implement the functions of the PDCP layer and the protocol layers above it (for example, the RRC layer and / or the SDAP layer). The DU is configured to implement the functions of the protocol layers below the PDCP layer (for example, the RLC layer, the MAC layer, and / or the PHY layer). For another example, the CU is configured to implement the functions of the protocol layers above the PDCP layer (such as the RRC layer and / or the SDAP layer), and the DU is configured to implement the functions of the PDCP layer and the protocol layers below it (for example, the RLC layer, the MAC layer, and / or the PHY layer, etc.).

[0189] When a CU includes a CU-CP and a CU-UP, the CU-CP is used to implement the control plane functions of the CU, and the CU-UP is used to implement the user plane functions of the CU. For example, when the CU is configured to implement the functions of the PDCP layer, RRC layer, and SDAP layer, the CU-CP is used to implement the RRC layer functions and the control plane functions of the PDCP layer, and the CU-UP is used to implement the SDAP layer functions and the user plane functions of the PDCP layer.

[0190] The CU-CP can interact with the network elements in the core network for implementing control plane functions. The network elements in the core network for implementing control plane functions may be access and mobility function network elements, such as the access and mobility management function (AMF) in the 5G mobile communication system. The access and mobility function network element is responsible for mobility management in the mobile network, such as location update of the terminal device, registration network of the terminal device, switching of the terminal device, etc. The CU-UP can interact with the network elements in the core network for implementing user plane functions. The network elements in the core network for implementing user plane functions, such as the user plane function (UPF) in the 5G mobile communication system, are responsible for forwarding and receiving data in the terminal device.

[0191] The above configuration of CU and DU is only an example, and the functions of CU and DU can also be configured as needed. For example, the CU or DU can be configured to have the functions of more protocol layers, or the CU or DU can be configured to have partial processing functions of the protocol layer. For example, some functions of the RLC layer and the functions of the protocol layers above the RLC layer are set in the CU, and the remaining functions of the RLC layer and the functions of the protocol layers below the RLC layer are set in the DU. For another example, the functions of the CU or DU can be divided according to the service type or other system requirements. For example, according to the delay, the functions whose processing time needs to meet the smaller delay requirement are set in the DU, and the functions that do not need to meet the delay requirement are set in the CU.

[0192] The DU and RU can work together to implement the functions of the PHY layer. A DU can be connected to one or more RUs. The functions of the DU and RU can be configured in various ways according to the design. For example, the DU is configured to implement the baseband function, and the RU is configured to implement the mid-RF function. For another example, the DU is configured to implement the high-layer functions in the PHY layer, and the RU is configured to implement the low-layer functions in the PHY layer or to implement the low-layer functions and the RF functions. The high-layer functions in the physical layer may include a part of the functions of the physical layer, which is closer to the MAC layer, and the low-layer functions in the physical layer may include another part of the functions of the physical layer, which is closer to the mid-RF side.

[0193] Optionally, the network device may also be a core network device. The core network device is responsible for access control, registration management, service management, mobility management, etc. for terminal devices accessing the network. For example, the core network device is an AMF.

[0194] It should be noted that the network device can be the device or apparatus shown above, or it can be a component (for example, a chip), module, or unit in the device or apparatus shown above, and this application does not limit it specifically.

[0195] The communication system provided in the present application can introduce AI network elements to implement some or all AI-related operations. The AI ​​network element can also be called an AI node, AI device, AI entity, AI module, AI model, or AI unit, etc. The AI ​​network element can be a network element built into the communication system. For example, the AI ​​network element can be an AI module built into: an access network device, a core network device, a cloud server, or a network management (operation, administration and maintenance, OAM) to implement AI-related functions. The OAM can be a network management device as a core network device and / or a network management device as an access network device. Alternatively, the AI ​​network element can also be a network element independently set up in the communication system. Optionally, the terminal device or the chip built into the terminal device can also include an AI entity to implement AI-related functions. The following describes another communication system provided in an embodiment of the present application in conjunction with Figure 3A.

[0196] Figure 3A is another schematic diagram of a communication system according to an embodiment of the present application. As shown in Figure 3A, network elements in the communication system are connected through interfaces (for example, NG interfaces, or Xn interfaces) or air interfaces. One or more AI modules are provided in these network element nodes (for example, core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in OAM) (for the sake of clarity, only one is shown in Figure 3A). The access network node can be a separate RAN node, or it can include multiple RAN nodes, for example, including CU and DU. One or more AI modules can also be provided in the CU and / or DU. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are provided in the CU-CP and / or CU-UP.

[0197] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements can be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of the input parameters), or output parameters (such as the type of output parameters and / or the dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0198] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or on the same node or device.

[0199] It should be noted that the access network node shown in Figure 3A can be used as a whole, or the access network node shown in Figure 3A can adopt a CU and DU separated architecture. Figure 3B shows a schematic diagram of a communication system in which the access network node is used as a whole and the access network node is connected to a terminal device. Figure 3C shows a schematic diagram of a communication system in which the access network node adopts a CU and DU separated architecture.

[0200] As shown in Figure 1, a transmitter and receiver can communicate over the air interface. These transmitters and receivers can be implemented using neural networks. Currently, training the transmitter's neural network with data can achieve better transmission performance, while training the receiver's neural network with data can achieve better reception performance.

[0201] The transmitter and receiver are trained for the wireless environment. Specifically, the transmitter and receiver collect training data related to the wireless environment through over-the-air data transmission, and train the transceiver neural network based on this training data. However, channel parameters in a wireless environment (e.g., channel distribution) typically change slowly. Therefore, the training data collected by the transmitter and receiver in a short period of time is often highly correlated, which is not conducive to the training of the transceiver neural network. This results in a decrease in the training speed and performance of the transceiver neural network.

[0202] This application provides a data processing method and related apparatus that facilitates the training of a transceiver model (e.g., a transceiver neural network), improving the training speed and performance of the transceiver model. For details, please refer to the relevant descriptions of the embodiments shown in Figures 4 and 6 below.

[0203] The technical solution of this application is introduced below in conjunction with specific embodiments.

[0204] In the following embodiments, the first device has a receiver and the second device has a transmitter. Optionally, the receiver is implemented by a receiving model, and the receiving model is used to receive data and / or information, etc. The receiving model can be a receiving neural network, or other AI models, which is not specifically limited in this application. Optionally, the transmitter is implemented by a sending model, and the sending model is used to send data and / or information, etc. The sending model can be a sending neural network, or other AI models, which is not specifically limited in this application. In the embodiment shown in Figure 4, the second device sends the first training data, and the first device performs data enhancement on the received first training data. In the embodiment shown in Figure 6, the second device performs data enhancement on the first training data to obtain enhanced training data, and then sends the enhanced training data to the first device.

[0205] FIG4 is a schematic diagram of an embodiment of a data processing method according to an embodiment of the present application. Referring to FIG4 , the method includes:

[0206] 401. A second device sends first training data to a first device. Correspondingly, the first device receives the first training data from the second device.

[0207] For example, as shown in FIG5 , the second device processes the first training data x0 through the sending model to obtain the data to be sent z0. The data to be sent z0=f(x0;ω tx ). Among them, ω tx is the weight parameter of the sending model. tx ) refers to the use of ω tx The signal obtained by the neural network processing x0 is the signal output by the second device through the sending model.

[0208] Optionally, the first training data may be preset bits or sample data from a training set. Alternatively, the first training data may be channel data between the first device and the second device. Optionally, the embodiment shown in FIG4 further includes steps 401a and 401b. Steps 401a and 401b may be performed before step 401.

[0209] 401a: The first device sends a reference signal to the second device. Correspondingly, the second device receives the reference signal from the first device.

[0210] For example, the first device is a network device, and the second device is a terminal device. The reference signal is a channel state information reference signal (CSI-RS) or a demodulation reference signal (DMRS).

[0211] For another example, the first device is a terminal device, the second device is a network device, and the reference signal is a sounding reference signal (SRS).

[0212] For another example, the first device is a first terminal device, the second device is a second terminal device, and the reference signal is a reference signal on a sidelink.

[0213] 401b. The second device measures the reference signal to obtain first training data.

[0214] Specifically, the second device measures the reference signal to obtain channel data between the first device and the second device. The channel data can be used as the first training data.

[0215] 402. The first device performs data enhancement on the first training data to obtain enhanced training data.

[0216] For example, as shown in Figure 5, the second device processes the first training data x0 through the transmission model to obtain the data to be transmitted z0. The data to be transmitted z0 is transmitted to the first device through the channel h, and the data received by the first device is y0. For example, y0 = h(z0) + n0, where n0 is the channel noise. The first device performs data enhancement on the data y0 to obtain the enhanced training data y k Specifically, k =h A (y0;∈ k ), k = 1, 2..., K, K is the number of enhanced samples, that is, the number of data enhancements. ∈ k represents the data augmentation configuration for the augmented sample data k.

[0217] It should be noted that, optionally, the enhanced training data includes the enhanced training data and the first training data. That is, the first device performs data enhancement on the first training data to obtain more training data and more diverse training data.

[0218] Optionally, the first device performs data enhancement on the first training data through a data enhancement configuration to obtain enhanced training data.

[0219] Optionally, the data enhancement configuration includes at least one of the following: a data enhancement method, a data enhancement parameter, or the number of enhanced samples.

[0220] The data enhancement method includes at least one of the following: adding noise, signal phase rotation, signal random phase processing, channel simulation processing, or signal rearrangement. The above is only an example, and this application is still applicable to other data enhancement methods, and this application does not limit them specifically.

[0221] The data enhancement parameters include at least one of the following: noise power, signal phase rotation angle, distribution or range of random phase used in signal random phase processing, ratio of amplitude of elements of diagonal matrix used in channel simulation processing, or rearrangement unit of signal in time domain and / or frequency domain.

[0222] Optionally, the noise power may belong to an interval, that is, the first device may select the size of the noise power within the interval. The signal phase rotation angle may include one or more angles, that is, a discrete interval. For example, φ k ∈{π*i / 4}, i=1, 2, ..., K. K is the number of enhanced samples, that is, the number of data enhancements. That is, the signal phase rotation angle can be taken from this discrete interval. The distribution or range of the random phase used in the signal random phase processing can be represented by an interval. For example, That is, the random phase can take values ​​from this interval, specifically It is obtained by sampling from a uniform distribution in [0,2π]. Optionally, the diagonal matrix used in the channel simulation process can be a multiple-input multiple-output (MIMO) diagonal matrix, without changing the channel correlation matrix.

[0223] The unit of signal reordering in the time domain may be a time domain symbol, a time slot, a subframe, or a frame, etc., which is not specifically limited in this application. The unit of signal reordering in the frequency domain may be a resource element (RE) or a resource block (RB), etc., which is not specifically limited in this application.

[0224] The number of enhanced samples refers to the number of enhanced samples obtained by performing data augmentation on the first training data.

[0225] It should be noted that if the data enhancement method is noise addition, the data enhancement parameters may include noise power. If the data enhancement method is signal random phase processing, the data enhancement parameters may include the signal phase rotation angle. If the data enhancement method is signal random phase processing, the data enhancement parameters may include the distribution or range of the random phase used in the signal random phase processing. If the data enhancement method is channel simulation processing, the data enhancement parameters may include the ratio of the amplitudes of the elements of the diagonal matrix used in the channel simulation processing. If the data enhancement method is signal rearrangement, the data enhancement parameters may include the rearrangement units of the signal in the time domain and / or frequency domain.

[0226] The following introduces various data enhancement methods.

[0227] 1. Add noise.

[0228] The first device determines the data enhancement method of adding noise according to the data enhancement configuration. Then, the first device performs noise processing on the first training data received by the first device according to the data enhancement parameters and the enhanced sample data to obtain enhanced training data. For example, as shown in FIG5 , the first device performs noise processing on the first training data y0 received by the first device to obtain enhanced training data y k =y0+n k Among them, n k is the noise power, i.e. the data enhancement parameter. k The value of can be derived from the noise power interval indicated in the data enhancement configuration. k can be 1, 2, 3, ..., K. K is the number of enhanced samples. Therefore, the first apparatus can obtain K enhanced sample data by adding noise to the first training data received by the first apparatus.

[0229] 2. Signal phase rotation.

[0230] The first device determines a data enhancement method using signal phase rotation according to the data enhancement configuration. Then, the first device performs signal phase rotation on the first training data received by the first device according to the data enhancement parameters and the enhanced sample data to obtain enhanced training data. For example, the first training data received by the first device is represented by y a , the first device receives the first training data y a Perform channel equalization and get y b Therefore, the enhanced training data y k =y b *φ k ,φ k is the signal phase rotation angle, i.e., the data enhancement parameter. k ∈{π*i / 4}, where i can be 1, 2, 3, ..., K. K is the number of enhanced samples. Therefore, the first device can obtain K enhanced sample data by performing signal phase rotation on the first training data received by the first device.

[0231] 3. Signal random phase processing.

[0232] The first device determines a data enhancement method using signal random phase processing according to the data enhancement configuration. Then, the first device performs signal random phase processing on the first training data received by the first device according to the data enhancement parameters and the enhanced sample data to obtain enhanced training data. For example, as shown in FIG5 , the first device performs signal random phase processing on the first training data y0 received by the first device to obtain enhanced training data. For example, That is, the random phase can take values ​​from this interval, specifically It is obtained by sampling from the uniform distribution of [0,2π], that is, is a data enhancement parameter. k can be 1, 2, 3, ..., K. K is the number of enhanced samples. Therefore, the first device can obtain K enhanced sample data by performing signal random phase processing on the first training data received by the first device.

[0233] 4. Channel simulation processing.

[0234] The first device determines the data enhancement method using channel simulation processing according to the data enhancement configuration. Then, the first device performs channel simulation processing on the first training data according to the data enhancement parameters and the enhanced sample data to obtain enhanced training data. For example, as shown in FIG5 , the first device performs channel simulation processing on the first training data y0 received by the first device to obtain enhanced training data y k =y0*h k .h k is the data enhancement parameter, h krepresents a diagonal matrix. k can be 1, 2, 3, ..., K. K is the number of enhanced samples. Therefore, the first device can obtain K enhanced sample data by performing channel simulation processing on the first training data received by the first device.

[0235] 5. Signal rearrangement.

[0236] The first device reorders the first training data received by the first device according to the signal reordering unit in the time domain and / or frequency domain to obtain enhanced training data. That is, the minimum unit used by the first device to reorder the first training data received by the first device should be greater than or equal to the minimum unit used by the second device to send the first training data. After reordering, the training data within different reordering units can be processed independently. For example, the second device sends the first training data in the frequency domain using RB as the granularity. Therefore, the first device should reorder the first training data received by the first device using RB as the reordering unit to obtain enhanced training data.

[0237] It should be noted that the three data enhancement methods of signal phase rotation, signal rearrangement and channel simulation processing are related to the signal characteristics and / or transmission mode of the signal sent by the second device. Therefore, the second device needs to indicate the corresponding data enhancement method and / or data enhancement parameters of the first device. For example, for signal phase rotation, the signal sent by the second device is required to have a phase rotation characteristic, and the other signal obtained after the signal rotation is still a legal signal. The legal signal can be understood as a signal that the second device can send. For example, the second device sends a signal based on binary phase shift keying (BPSK) modulation, and the first device obtains another signal after performing phase rotation on the signal. The other signal should be a signal that the second device can generate and send based on the BPSK modulation mode. For another example, for channel simulation processing, it is related to the transmission mode of the signal sent by the second device, and the transmission mode is related to the training task. For example, the second device jointly sends the first training data through multiple antennas. The first device can perform channel simulation processing on the first training data received by the first device through a MIMO diagonal array.

[0238] It should be noted that, for the first training data, the first device may use one or more data enhancement methods to perform data enhancement on the first training data, which is not specifically limited in this application.

[0239] Optionally, the data enhancement configuration is determined based on the configuration of the receiving model of the first device, the configuration of the sending model of the second device, and / or the speed of channel change between the first device and the second device.

[0240] Optionally, the configuration of the reception model of the first device includes at least one of the following: a model structure, a model size, or a number of model parameters of the reception model. Optionally, the configuration of the reception model of the first device may be determined in combination with a task to be performed by the first device and / or a capability of the first device.

[0241] Optionally, the configuration of the transmission model of the second device includes at least one of the following: a model structure, a model size, or a number of model parameters of the transmission model. Optionally, the configuration of the transmission model of the second device can be determined in combination with the task to be performed by the second device and / or the capabilities of the second device.

[0242] For example, the receiving model has a larger model size than the sending model. The number of update rounds required for the receiving model is greater than that required for the sending model. The number of enhanced samples can be N times the number of data samples included in the first training data. N is equal to the ratio of the number of update rounds required for the receiving model to the number of update rounds required for the sending model.

[0243] For another example, if the channel between the first device and the second device changes slowly, the number of enhanced samples can be larger, thereby facilitating the first device to obtain more training data and improving the speed and performance of model training.

[0244] Optionally, the data enhancement configuration is pre-agreed between the first device and the second device, or is specified in the communication protocol, or is selected by the first device itself, which is not specifically limited in this application. Two possible implementations are described below. This application is still applicable to other implementations, which are not specifically limited in this application.

[0245] Implementation 1 is described below in conjunction with step 402a. Optionally, the embodiment shown in FIG4 further includes step 402a. Step 402a can be performed before step 402.

[0246] 402a: The second device sends first indication information to the first device. Correspondingly, the first device receives the first indication information from the second device.

[0247] Among them, the first indication information is used to indicate the data enhancement configuration. The data enhancement configuration is used to perform data enhancement on the first training data. For the data enhancement configuration, please refer to the aforementioned related introduction. Optionally, the first device obtains the data enhancement configuration including: the first device receives the first indication information from the second device. It should be noted that there is no fixed execution order between step 402a and step 401. Step 402a can be executed first, and then step 401; or, step 401 can be executed first, and then step 402a; or, step 401 and step 402a can be executed simultaneously according to the situation, and this application does not limit it specifically.

[0248] Implementation 2 is described below in conjunction with step 402b. Optionally, the embodiment shown in FIG4 further includes step 402b. Step 402b can be performed before step 402.

[0249] 402b: The second device sends second indication information to the first device. Correspondingly, the first device receives the second indication information from the second device.

[0250] The second indication information is used to indicate a data enhancement configuration available to the first device. Optionally, the second indication information further indicates a priority of the available data enhancement configuration. Optionally, the first device obtaining the data enhancement configuration includes: the first device receiving the second indication information from the second device; and the first device determining the data enhancement configuration based on the data enhancement configuration available to the first device indicated by the second indication information.

[0251] In this implementation, the second device provides an available data enhancement configuration to the first device. The first device can select a data enhancement configuration for data enhancement of the first training data from the available data enhancement configurations. For example, the first device can select a data enhancement configuration with a higher or highest priority as the data enhancement configuration for data enhancement of the first training data received by the first device. Then, the first device performs data enhancement on the first training data received by the first device through the selected data enhancement configuration to obtain enhanced training data. Alternatively, the first device can determine the data enhancement configuration with reference to the data enhancement configuration available to the first device indicated by the second indication information. Then, the first device performs data enhancement on the first training data received by the first device based on the determined data enhancement configuration to obtain enhanced training data.

[0252] Optionally, the embodiment shown in FIG4 further includes step 403. Step 403 may be performed after step 402.

[0253] 403. The first device trains a receiving model of the first device according to the enhanced training data.

[0254] For example, as shown in Figure 5, the enhanced training data is represented as y k , the receiving model is a receiving neural network. The first device processes the enhanced training data through the receiving neural network to obtain f(y k ;ω rx ) refers to the use of ω rx The neural network for y k The signal obtained by processing is the signal output by the receiving model of the first device. The first device calculates the loss value through the loss function The first device knows in advance that the first training data sent by the second device is x0. The first device can calculate the weight gradient of the receiving neural network. Wherein, K is the number of enhanced samples. The first device can update the receiving neural network through the weight gradient.

[0255] Optionally, in step 403, the enhanced training data includes multiple enhanced sample data. The first device trains the receiving model based on some or all of the multiple enhanced sample data. For example, the first device performs data enhancement on the first training data to obtain enhanced sample data with different signal-to-noise ratios. The first device selects, from the enhanced sample data with different signal-to-noise ratios, a portion of enhanced sample data whose signal-to-noise ratio falls within the signal-to-noise ratio range of the training data for the receiving model, and trains the receiving model based on the portion of enhanced sample data.

[0256] Optionally, the embodiment shown in FIG4 further includes steps 404 and 405. Steps 404 and 405 may be performed after step 402.

[0257] 404. The first device generates intermediate training parameters and / or loss values ​​according to the enhanced training data.

[0258] Optionally, the intermediate training parameters are intermediate gradients.

[0259] For example, as shown in FIG5 , the first device processes the enhanced training data by receiving the neural network to obtain For the kth enhanced sample data, the first device calculates the loss value through the loss function The enhanced training data includes K enhanced sample data. For the kth enhanced sample data, the intermediate gradient is Merging intermediate gradients can be expressed as

[0260] It should be noted that the first device can generate at least one intermediate training parameter and / or at least one loss value based on the enhanced training data. For example, the enhanced training data includes K enhanced sample data, each enhanced sample data corresponds to an intermediate training parameter and / or a loss value. Therefore, the first device can generate K intermediate training parameters and / or K loss values ​​based on the K enhanced sample data.

[0261] 405. The first device sends at least one of the following to the second device: an intermediate training parameter, a loss value, or a weighted value.

[0262] The weighted value is determined based on the intermediate training parameters or loss values. For example, the enhanced training data includes K enhanced sample data, and the first device can generate K intermediate training parameters and / or K loss values. The weighted value can be obtained by weighting some or all of the K intermediate training parameters. For example, the K intermediate training parameters include K intermediate gradients. The weighted value is the average value of the K intermediate gradients. Alternatively, the weighted value can be obtained by weighting some or all of the K loss values. For example, the weighted value is the average value of the K loss values.

[0263] Optionally, the first device generates K intermediate training parameters and / or K loss values. In step 405, the first device sends some or all of the K intermediate training parameters and / or some or all of the K loss values ​​to the second device.

[0264] Optionally, the second device sends third indication information to the first device. The third indication information is used to indicate conditions that the part of the intermediate training parameters, the part of the loss values, or the weighted values ​​need to meet.

[0265] The enhanced training data includes a plurality of enhanced sample data. The part of the intermediate training parameters, the part of the loss value and the weighted value are all determined based on the part of the enhanced sample data in the plurality of enhanced sample data. In a possible implementation, the second device sends the first training data. The first device receives the first training data and performs data enhancement on the first training data to obtain enhanced sample data with different signal-to-noise ratios. The first device selects part of the enhanced sample data whose signal-to-noise ratio is within the signal-to-noise ratio range of the training data of the sent model from the enhanced sample data with different signal-to-noise ratios. Then, the first device generates the part of the intermediate training parameters, the part of the loss value, and / or the weighted value based on the part of the enhanced sample data. The first device feeds back the part of the intermediate training parameters, the part of the loss value, and / or the weighted value to the second device.

[0266] Optionally, the third indication information is carried in the data enhancement configuration.

[0267] It should be noted that there is no fixed order for executing step 403 and steps 404 to 405. Step 403 may be executed first, followed by steps 404 to 405; or steps 404 to 405 may be executed first, followed by step 403; or, depending on the circumstances, steps 403 and 404 to 405 may be executed simultaneously, which is not limited in this application.

[0268] Optionally, the embodiment shown in FIG4 further includes step 406. Step 406 may be performed after step 405.

[0269] 406. The second device trains the sending model of the second device according to at least one of the intermediate training parameters, the loss value, and the weighted value.

[0270] For more information about the sending model, please refer to the above introduction, which will not be repeated here.

[0271] For example, as shown in Figure 5, for the k-th enhanced sample data, the intermediate gradient is The sending model is the sending neural network, and the weight parameter of the sending neural network is ω tx The gradient of Then, the second device updates the weight parameters of the sending neural network using the gradient.

[0272] In an embodiment of the present application, a first device receives first training data from a second device. Then, the first device performs data enhancement on the first training data to obtain enhanced training data. It can be seen that the first device can perform data enhancement on the first training data to increase the quantity and diversity of the training data. This is beneficial to the training of the transceiver model (e.g., the transceiver neural network) and improves the training speed and training performance of the transceiver model. For example, the first device can train the receiving model of the first device based on the enhanced training data, thereby improving the training speed and training performance of the receiving model.

[0273] FIG6 is a schematic diagram of another embodiment of the data processing method of the present application. Referring to FIG6 , the method includes:

[0274] 601. The second device performs data enhancement on the first training data to obtain enhanced training data.

[0275] Step 601 is similar to step 402 in the embodiment shown in Figure 4 , and for details, please refer to the relevant introduction of step 402 in the embodiment shown in Figure 4 , which will not be repeated here. It should be noted that, optionally, the enhanced training data includes the enhanced training data and the first training data.

[0276] Optionally, the second device performs data enhancement on the first training data through a data enhancement configuration to obtain enhanced training data. For details about the data enhancement configuration, please refer to the relevant introduction in step 402 of the embodiment shown in FIG4 , which will not be repeated here.

[0277] Optionally, the data enhancement configuration is pre-agreed between the first device and the second device, or is specified in the communication protocol, or is selected by the second device itself, which is not specifically limited in this application. Two possible implementations are described below. This application is still applicable to other implementations, which are not specifically limited in this application.

[0278] The following describes the method 1 in conjunction with step 601a. ​​Optionally, the embodiment shown in FIG6 further includes step 601a, which can be performed before step 601.

[0279] 601a. ​​A first device sends first indication information to a second device. The first indication information is used to indicate a data enhancement configuration. Correspondingly, the second device receives the first indication information from the first device.

[0280] The data enhancement configuration is used to perform data enhancement on the first training data. Optionally, the second device acquiring the data enhancement configuration includes: the second device receiving first indication information from the first device.

[0281] The following describes the method 2 in conjunction with step 601b. Optionally, the embodiment shown in FIG6 further includes step 601b, which can be performed before step 601.

[0282] 601b. The first device sends second indication information to the second device. The second indication information is used to indicate a data enhancement configuration available to the second device. Correspondingly, the second device receives the second indication information from the first device.

[0283] Optionally, the second indication information also indicates the priority of the available data enhancement configuration.

[0284] Optionally, the second device obtains the data enhancement configuration including: the second device receives second indication information from the first device; and the second device determines the data enhancement configuration based on the data enhancement configuration available to the second device indicated by the second indication information.

[0285] In this implementation, the first device provides the second device with an available data enhancement configuration. The second device can select a data enhancement configuration from the available data enhancement configurations for performing data enhancement on the first training data. For example, the second device can select a data enhancement configuration with a higher or highest priority. Then, the second device performs data enhancement on the first training data using the selected data enhancement configuration to obtain enhanced training data. Alternatively, the second device can determine the data enhancement configuration with reference to the data enhancement configuration available to the second device indicated by the second indication information; then, the second device performs data enhancement on the first training data received by the second device based on the determined data enhancement configuration to obtain enhanced training data.

[0286] Optionally, the first training data is channel data between the first device and the second device. Optionally, the embodiment shown in FIG6 further includes steps 601c to 601d. Steps 601c to 601d may be performed before step 601.

[0287] 601c: The first device sends a reference signal to the second device. Correspondingly, the second device receives the reference signal from the first device.

[0288] 601d. The second device measures the reference signal to obtain first training data.

[0289] Steps 601c to 601d are similar to steps 401a to 401b in the embodiment shown in FIG. 4 . For details, please refer to the relevant introduction of steps 401a to 401b in the embodiment shown in FIG. 4 , which will not be repeated here.

[0290] It should be noted that there is no fixed order for executing steps 601c to 601d and step 601a or step 601b. Steps 601c to 601d may be executed first, followed by step 601a or step 601b; or, step 601a or step 601b may be executed first, followed by steps 601c to 601d; or, depending on the circumstances, steps 601c to 601d and step 601a, or steps 601c to 601d and step 601, may be executed simultaneously. This application does not impose any specific restrictions.

[0291] 602. The second device sends enhanced training data to the first device. Correspondingly, the first device receives the enhanced training data from the second device.

[0292] Optionally, the embodiment shown in FIG6 further includes step 603 , which may be performed after step 602 .

[0293] 603. The first device trains a receiving model of the first device according to the enhanced training data.

[0294] Step 603 is similar to step 403 in the embodiment shown in FIG. 4 . For details, please refer to the relevant introduction of step 403 in the embodiment shown in FIG. 4 , which will not be repeated here.

[0295] Optionally, the embodiment shown in FIG6 further includes steps 604 and 605. Steps 604 and 605 may be performed after step 602.

[0296] 604. The first device determines intermediate training parameters and / or loss values ​​based on the enhanced training data.

[0297] 605. The first device sends at least one of the following to the second device: an intermediate training parameter, a loss value, or a weighted value. Correspondingly, the second device receives at least one of the following from the first device: an intermediate training parameter, a loss value, or a weighted value.

[0298] Steps 604 to 605 are similar to steps 404 to 405 in the embodiment shown in FIG. 4 . For details, please refer to the relevant introduction of steps 404 to 405 in the embodiment shown in FIG. 4 , which will not be repeated here.

[0299] It should be noted that there is no fixed order for executing steps 604 to 605 and step 603. Step 603 may be executed first, followed by steps 604 to 605; or steps 604 to 605 may be executed first, followed by step 603; or, depending on the circumstances, steps 604 to 605 and step 603 may be executed simultaneously, and this application does not impose any specific restrictions.

[0300] Optionally, the first device generates K intermediate training parameters and / or K loss values. In step 605, the first device sends some or all of the K intermediate training parameters and / or some or all of the K loss values ​​to the second device.

[0301] Optionally, the second device sends third indication information to the first device. The third indication information is used to indicate conditions that the part of the intermediate training parameters, the part of the loss values, or the weighted values ​​need to meet.

[0302] Specifically, the enhanced training data includes a plurality of enhanced sample data. The second device sends the plurality of enhanced sample data using a signal-to-noise ratio range that covers the signal-to-noise ratio range of the training data of the receiving model. The first device selects, from the plurality of enhanced sample data, a portion of enhanced sample data whose signal-to-noise ratio is within the signal-to-noise ratio range of the training data of the sending model, and generates a portion of intermediate training parameters, a portion of loss values, and / or weighted values ​​based on the portion of sample data. The first device feeds back the portion of intermediate training parameters, the portion of loss values, and / or weighted values ​​to the second device.

[0303] Optionally, the embodiment shown in FIG6 further includes step 606. Step 606 may be performed after step 605.

[0304] 606. The second device trains the sending model of the second device according to at least one of the intermediate training parameters, the loss value, and the weighted value.

[0305] Step 606 is similar to step 406 in the embodiment shown in FIG. 4 . For details, please refer to the relevant introduction of step 406 in the embodiment shown in FIG. 4 , which will not be repeated here.

[0306] In an embodiment of the present application, the first device receives enhanced training data from the second device. The enhanced training data is obtained by performing data enhancement on the first training data. As can be seen, the first device can obtain a larger amount of training data and a more diverse training data. This is beneficial for training the transceiver model (e.g., the transceiver neural network) and improving the training speed and training performance of the transceiver model. For example, the first device can train the receiving model of the first device based on the enhanced training data, thereby improving the training speed and training performance of the receiving model.

[0307] The first device and the second device provided in the embodiments of the present application are described below.

[0308] FIG7 is a schematic diagram of the structure of the first device according to an embodiment of the present application. Referring to FIG7 , the first device can be used to execute the process executed by the first device in the embodiment shown in FIG4 . For details, please refer to the relevant description in the above method embodiment.

[0309] The first device 700 includes a transceiver module 701 and a processing module 702 .

[0310] The processing module 702 is used to process data. The transceiver module 701 can implement corresponding communication functions. The transceiver module 701 can also be called a communication interface or a communication module.

[0311] Optionally, the first device 700 may further include a storage module, which may be used to store instructions and / or data. The processing module 702 may read the instructions and / or data in the storage module so that the first device implements the aforementioned method embodiment.

[0312] The first device 700 can be configured to perform the actions performed by the first device in the above method embodiments. The first device 700 can be a first device or a component configurable in the first device. The processing module 702 is configured to perform the processing-related operations on the first device side in the above method embodiments. The transceiver module 701 is configured to perform the reception-related operations on the first device side in the above method embodiments.

[0313] Optionally, the transceiver module 701 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiment. The receiving module is used to perform the receiving operation in the above method embodiment.

[0314] It should be noted that the first device 700 may include a sending module but not a receiving module. Alternatively, the first device 700 may include a receiving module but not a sending module. The specific details may depend on whether the above solution executed by the first device 700 includes a sending action and a receiving action.

[0315] Optionally, the first device 700 is used to perform the actions performed by the first device in the embodiment shown in FIG4 above. For details, please refer to the relevant introduction of the embodiment shown in FIG4 above, which will not be expanded in detail here. For example, the first device 700 is used to perform the following scheme:

[0316] The transceiver module 701 is configured to receive first training data from a second device;

[0317] The processing module 702 is configured to perform data enhancement on the first training data to obtain enhanced training data.

[0318] For other implementations, please refer to the detailed description of the embodiment shown in FIG4 , which will not be described in detail here.

[0319] It should be understood that the specific process of each module executing the above corresponding process has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0320] The processing module 702 in the above embodiment can be implemented by at least one processor or processor-related circuits. The transceiver module 701 can be implemented by a transceiver or transceiver-related circuits. The transceiver module 701 can also be called a communication module or communication interface. The storage module can be implemented by at least one memory.

[0321] FIG8 is another structural diagram of the first device according to an embodiment of the present application. Referring to FIG8 , the first device can be used to execute the process executed by the first device in the embodiment shown in FIG6 . For details, please refer to the relevant description in the above method embodiment.

[0322] The first device 800 includes a transceiver module 801. Optionally, the first device 800 further includes a processing module 802.

[0323] The processing module 802 is used to perform data processing. The transceiver module 801 can implement corresponding communication functions. The transceiver module 801 can also be called a communication interface or a communication module.

[0324] Optionally, the first device 800 may further include a storage module, which may be used to store instructions and / or data. The processing module 802 may read the instructions and / or data in the storage module so that the first device implements the aforementioned method embodiment.

[0325] The first device 800 can be used to perform the actions performed by the first device in the above method embodiments. The first device 800 can be a first device or a component configurable in the first device. The processing module 802 is used to perform the processing-related operations on the first device side in the above method embodiments. The transceiver module 801 is used to perform the reception-related operations on the first device side in the above method embodiments.

[0326] Optionally, the transceiver module 801 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiment. The receiving module is used to perform the receiving operation in the above method embodiment.

[0327] It should be noted that the first device 800 may include a sending module but not a receiving module. Alternatively, the first device 800 may include a receiving module but not a sending module. The specific implementation depends on whether the above solution executed by the first device 800 includes a sending action and a receiving action.

[0328] Optionally, the first device 800 is used to perform the actions performed by the first device in the embodiment shown in FIG6 above. For details, please refer to the relevant introduction of the embodiment shown in FIG6 above, which will not be expanded in detail here. For example, the first device 800 is used to perform the following scheme:

[0329] The transceiver module 801 is configured to receive enhanced training data from a second device, where the enhanced training data is obtained by performing data enhancement on the first training data.

[0330] For other implementations, please refer to the detailed description of the embodiment shown in FIG6 , which will not be described in detail here.

[0331] It should be understood that the specific process of each module executing the above corresponding process has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0332] The processing module 802 in the above embodiment can be implemented by at least one processor or processor-related circuits. The transceiver module 801 can be implemented by a transceiver or transceiver-related circuits. The transceiver module 801 can also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0333] FIG9 is a schematic diagram of the structure of the second device according to an embodiment of the present application. Referring to FIG9 , the second device can be used to execute the process executed by the second device in the embodiment shown in FIG4 . For details, please refer to the relevant description of the above method embodiment.

[0334] The second device 900 includes a transceiver module 901. Optionally, the second device 900 further includes a processing module 902.

[0335] The processing module 902 is used to perform data processing. The transceiver module 901 can implement corresponding communication functions. The transceiver module 901 can also be called a communication interface or a communication module.

[0336] Optionally, the second device 900 may further include a storage module, which may be used to store instructions and / or data. The processing module 902 may read the instructions and / or data in the storage module so that the second device implements the aforementioned method embodiment.

[0337] The second device 900 can be used to perform the actions performed by the second device in the above method embodiments. The second device 900 can be a second device or a component that can be configured in the second device. The processing module 902 is used to perform the processing-related operations on the second device side in the above method embodiments. The transceiver module 901 is used to perform the reception-related operations on the second device side in the above method embodiments.

[0338] Optionally, the transceiver module 901 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiment. The receiving module is used to perform the receiving operation in the above method embodiment.

[0339] It should be noted that the second device 900 may include a sending module but not a receiving module. Alternatively, the second device 900 may include a receiving module but not a sending module. The specific implementation depends on whether the above solution executed by the second device 900 includes a sending action and a receiving action.

[0340] Optionally, the second device 900 is used to perform the actions performed by the second device in the embodiment shown in FIG4 above. For details, please refer to the relevant introduction of the embodiment shown in FIG4 above, which will not be expanded in detail here. For example, the second device 900 is used to perform the following scheme:

[0341] The transceiver module 901 is used to send first training data to the first device; and receive at least one of the following items from the first device: an intermediate training parameter, a loss value, or a weighted value, where the intermediate training parameter or the loss value is determined based on the enhanced training data, the enhanced training data is obtained by data enhancement of the first training data, and the weighted value is determined based on the intermediate training parameter or the loss value.

[0342] For other implementations, please refer to the detailed description of the embodiment shown in FIG4 , which will not be described in detail here.

[0343] It should be understood that the specific process of each module executing the above corresponding process has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0344] The processing module 902 in the above embodiment can be implemented by at least one processor or processor-related circuits. The transceiver module 901 can be implemented by a transceiver or transceiver-related circuits. The transceiver module 901 can also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0345] FIG10 is another schematic diagram of the structure of the second device according to an embodiment of the present application. Referring to FIG10 , the second device can be used to execute the process executed by the second device in the embodiment shown in FIG6 . For details, please refer to the relevant description of the above method embodiment.

[0346] The second device 1000 includes a transceiver module 1001 and a processing module 1002 .

[0347] The processing module 1002 is used to process data. The transceiver module 1001 can implement corresponding communication functions. The transceiver module 1001 can also be called a communication interface or a communication module.

[0348] Optionally, the second device 1000 may further include a storage module, which may be used to store instructions and / or data. The processing module 1002 may read the instructions and / or data in the storage module so that the second device implements the aforementioned method embodiment.

[0349] The second device 1000 can be used to perform the actions performed by the second device in the above method embodiments. The second device 1000 can be a second device or a component configurable in the second device. The processing module 1002 is used to perform the processing-related operations on the second device side in the above method embodiments. The transceiver module 1001 is used to perform the reception-related operations on the second device side in the above method embodiments.

[0350] Optionally, the transceiver module 1001 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiment. The receiving module is used to perform the receiving operation in the above method embodiment.

[0351] It should be noted that the second device 1000 may include a sending module but not a receiving module. Alternatively, the second device 1000 may include a receiving module but not a sending module. The specific implementation depends on whether the above solution executed by the second device 1000 includes a sending action and a receiving action.

[0352] Optionally, the second device 1000 is used to perform the actions performed by the second device in the embodiment shown in FIG6 above. For details, please refer to the relevant introduction of the embodiment shown in FIG6 above, which will not be expanded in detail here. For example, the second device 1000 is used to perform the following scheme:

[0353] A processing module 1002 is configured to perform data enhancement on the first training data to obtain enhanced training data;

[0354] The transceiver module 1001 is configured to send enhanced training data to the first device.

[0355] For other implementations, please refer to the detailed description of the embodiment shown in FIG6 , which will not be described in detail here.

[0356] It should be understood that the specific process of each module executing the above corresponding process has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0357] The processing module 1002 in the above embodiment can be implemented by at least one processor or processor-related circuits. The transceiver module 1001 can be implemented by a transceiver or transceiver-related circuits. The transceiver module 1001 can also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0358] The present application also provides an apparatus 1100. Referring to Figure 11 , apparatus 1100 includes a processor 1110 coupled to a memory 1120. Memory 1120 is configured to store computer programs, instructions, and / or data. Processor 1110 is configured to execute the computer programs, instructions, and / or data stored in memory 1120, thereby implementing the method described in the method embodiments described above. Apparatus 1100 is configured to implement the operations performed by the first apparatus or the second apparatus described in the method embodiments described above.

[0359] Optionally, the device 1100 includes one or more processors 1110.

[0360] Optionally, as shown in FIG11 , the apparatus 1100 may further include a memory 1120 .

[0361] Optionally, the memory 1120 included in the device 1100 may be one or more.

[0362] Optionally, the memory 1120 may be integrated with the processor 1110 or provided separately.

[0363] Optionally, as shown in Figure 11 , the apparatus 1100 may further include a transceiver 1130, which is configured to receive and / or transmit signals. For example, the processor 1110 is configured to control the transceiver 1130 to receive and / or transmit signals.

[0364] The present application further provides an apparatus 1200, which may be a terminal device, a processor in the terminal device, or a chip. The apparatus 1200 may be used to execute the operations performed by the first apparatus or the second apparatus in the above method embodiment.

[0365] When apparatus 1200 is a terminal device, FIG12 shows a simplified schematic diagram of the terminal device structure. As shown in FIG12, the terminal device includes a processor, a memory, and a transceiver. The memory can store computer program code, and the transceiver includes a transmitter 1231, a receiver 1232, a radio frequency circuit (not shown), an antenna 1233, and input / output devices (not shown).

[0366] The processor is mainly used to process communication protocols and communication data; control terminal devices, execute software programs and process software program data, etc.

[0367] Memory is mainly used to store software programs and data.

[0368] Radio frequency circuits are mainly used for conversion between baseband signals and radio frequency signals and for processing radio frequency signals.

[0369] Antennas are mainly used to send and receive radio frequency signals in the form of electromagnetic waves.

[0370] The input and output device may include a touch screen, a display screen, or a keyboard. The input and output device is mainly used to receive data input by the user and output data to the user. It should be noted that some types of terminal devices may not have input and output devices.

[0371] When data needs to be sent, the processor performs baseband processing on the data to be sent and outputs the baseband signal to the RF circuit. The RF circuit then performs RF processing on the baseband signal and transmits the RF signal to the outside in the form of electromagnetic waves through the antenna. When data is sent to the terminal device, the RF circuit receives the RF signal through the antenna. The RF circuit converts the RF signal into a baseband signal and outputs the baseband signal to the processor. The processor converts the baseband signal into data and processes the data. For ease of explanation, Figure 12 only shows one memory, processor, and transceiver. In actual terminal device products, there may be one or more processors and one or more memories. The memory may also be referred to as a storage medium or storage device, etc. The memory may be set independently of the processor or integrated with the processor, and this embodiment of the application does not limit this.

[0372] In the embodiment of the present application, the antenna and radio frequency circuit with transceiver functions can be regarded as the transceiver module of the terminal device, and the processor with processing function can be regarded as the processing module of the terminal device.

[0373] As shown in FIG12 , the terminal device includes a processor 1210, a memory 1220, and a transceiver 1230. The processor 1210 may also be referred to as a processing unit, a processing board, a processing module, or a processing device. The transceiver 1230 may also be referred to as a transceiver unit, a transceiver, or a transceiver device.

[0374] Optionally, the device used to implement the receiving function in transceiver 1230 is considered a receiving module, and the device used to implement the transmitting function in transceiver 1230 is considered a transmitting module. That is, transceiver 1230 includes a receiver and a transmitter. A transceiver may also be sometimes referred to as a transceiver, a transceiver module, or a transceiver circuit. A receiver may also be sometimes referred to as a receiver, a receiving module, or a receiving circuit. A transmitter may also be sometimes referred to as a transmitter, a transmitting module, or a transmitting circuit.

[0375] The processor 1210 is configured to execute the processing actions of the first device or the second device in the embodiments shown in Figures 4 and 6. The transceiver 1230 is configured to execute the transceiver actions of the first device or the second device in the embodiments shown in Figures 4 and 6.

[0376] It should be understood that Figure 12 is only an example and not a limitation. The above-mentioned terminal device including the transceiver module and the processing module may not rely on the structure shown in Figures 7, 8, 9, 10, 11 or 12.

[0377] When the device 1200 is a chip, the chip includes a processor, a memory, and a transceiver. The transceiver may be an input / output circuit or a communication interface. The processor may be a processing module, a microprocessor, or an integrated circuit integrated on the chip. The sending operation of the first or second device in the above method embodiments may be understood as an output of the chip, and the receiving operation of the first or second device in the above method embodiments may be understood as an input of the chip.

[0378] The present application further provides an apparatus 1300, which can be a network device or a chip. The apparatus 1300 can be used to perform the operations performed by the first apparatus or the second apparatus in the embodiments shown in FIG. 4 and FIG. 6 .

[0379] When the apparatus 1300 is a network device, for example, a base station, FIG13 shows a simplified schematic diagram of a base station structure. The base station includes a portion 1310, a portion 1320, and a portion 1330.

[0380] Part 1310 is mainly used for baseband processing, base station control, etc.; Part 1310 is usually the control center of the base station, which can usually be called a processor, used to control the base station to execute the processing operations on the first device or second device side in the above method embodiment.

[0381] Part 1320 is mainly used to store computer program code and data.

[0382] Section 1330 is primarily used for receiving and transmitting RF signals and converting RF signals to baseband signals. Section 1330 can generally be referred to as a transceiver module, transceiver, transceiver circuit, or transceiver. The transceiver module in section 1330, which can also be referred to as a transceiver or transceiver, includes an antenna 1333 and a RF circuit (not shown in the figure), where the RF circuit is primarily used for RF processing. Optionally, the device used to implement the receiving function in section 1330 can be considered a receiver, and the device used to implement the transmitting function can be considered a transmitter. That is, section 1330 includes receiver 1332 and transmitter 1331. A receiver can also be referred to as a receiving module, receiver, or receiving circuit, and a transmitter can be referred to as a transmitting module, transmitter, or transmitting circuit.

[0383] Sections 1310 and 1320 may include one or more boards, each of which may include one or more processors and one or more memories. The processor is used to read and execute programs in the memory to implement baseband processing functions and control the base station. If multiple boards are present, the boards may be interconnected to enhance processing capabilities. As an optional implementation, multiple boards may share one or more processors, multiple boards may share one or more memories, or multiple boards may simultaneously share one or more processors.

[0384] For example, in one implementation, the transceiver module in section 1330 is used to perform the transceiver-related processes performed by the first device or the second device in the embodiments shown in Figures 4 and 6. The processor in section 1310 is used to perform the processing-related processes performed by the first device or the second device in the embodiments shown in Figures 4 and 6.

[0385] It should be understood that FIG13 is merely an example and not a limitation, and the network device including the processor, memory, and transceiver may not rely on the structures shown in FIG7, FIG8, FIG9, FIG10, FIG11 or FIG13.

[0386] When device 1300 is a chip, the chip includes a transceiver, a memory, and a processor. The transceiver may be an input / output circuit or a communication interface; the processor may be a processor, microprocessor, or integrated circuit integrated on the chip. In the above method embodiments, the sending operation of the first or second device can be understood as an output of the chip, and the receiving operation of the first or second device in the above method embodiments can be understood as an input of the chip.

[0387] An embodiment of the present application further provides a computer-readable storage medium storing computer instructions for implementing the method executed by the first device or the second device in the above method embodiment.

[0388] For example, when the computer program is executed by a computer, the computer can implement the method performed by the first device or the second device in the above method embodiment.

[0389] An embodiment of the present application further provides a computer program product comprising instructions, which, when executed by a computer, enables the computer to implement the method performed by the first device or the second device in the above method embodiment.

[0390] The present application also provides a communication system including the first device described in the above embodiment and the second device described in the above embodiment. The first device is configured to perform some or all of the operations performed by the first device described in the above method embodiment, and the second device is configured to perform some or all of the operations performed by the second device described in the above method embodiment.

[0391] An embodiment of the present application further provides a chip device, including a processor, configured to call a computer program or computer instruction stored in the memory so that the processor executes the method provided in the embodiments shown in FIG. 4 and FIG. 6 .

[0392] In one possible implementation, the input of the chip device corresponds to the receiving operation in any one of the embodiments shown in FIG. 4 and FIG. 6 , and the output of the chip device corresponds to the sending operation in any one of the embodiments shown in FIG. 4 and FIG. 6 .

[0393] Optionally, the processor is coupled to the memory via an interface.

[0394] Optionally, the chip device further includes a memory, in which computer programs or computer instructions are stored.

[0395] The processor mentioned in any of the above may be a general-purpose central processing unit, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the method provided in any of the embodiments shown in Figures 4 and 6. The memory mentioned in any of the above may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM), etc.

[0396] Those skilled in the art can clearly understand that, for the sake of convenience and brevity of description, the explanation of the relevant contents and beneficial effects of any of the above-mentioned devices can refer to the corresponding method embodiments provided above, and will not be repeated here.

[0397] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0398] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0399] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0400] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the part that essentially contributes to the technical solution of the present application or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0401] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Images