Communication method and apparatus, system, electronic device, storage medium, and product

Abstract

The present disclosure relates to the technical field of communications, and particularly provides a communication method and apparatus, a system, an electronic device, a storage medium, and a product. The communication method of the present disclosure comprises: sending first information to a second device, wherein the first information comprises a random seed, and the random seed is used for generating a first bit stream; and receiving a data stream from the second device, wherein the data stream is obtained by processing the first bit stream by means of a transmitter deployed in the second device.

Description

Communication method and device, system, electronic device, storage medium and product

[0001] Cross-reference to Related Applications

[0002] The present disclosure claims priority to Chinese Patent Application No. 202411227085.7 filed on September 3, 2024 in China, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of communication, and in particular to a communication method and device, system, electronic device, storage medium and product. BACKGROUND

[0004] At present, in the training process, the receiver needs to collect the bit stream of the transmitter and the data stream modulated by the transmitter according to the bit stream, that is, the transmitter needs to send both the input data and the output data to the receiver, resulting in excessive overhead for collecting data, and thus resulting in excessive consumption of transmission resources and network resources. SUMMARY

[0005] The present disclosure is proposed in view of the above problems. The present disclosure provides a communication method and device, system, electronic device, storage medium and product.

[0006] According to one aspect of the present disclosure, a communication method is provided, applied to a first device, the first device being deployed with a receiver, the method comprising: sending first information to a second device, the first information comprising a random seed, the random seed being used to generate a first bit stream; receiving a data stream from the second device; the data stream being obtained by processing the first bit stream by a transmitter deployed by the second device.

[0007] According to another aspect of the present disclosure, a communication method is provided, applied to a second device, the second device being deployed with a transmitter, the method comprising: receiving first information from a first device, the first information comprising a random seed; generating a second bit stream based on the random seed; processing the second bit stream into a data stream by using the transmitter; and sending the data stream to the first device.

[0008] According to another aspect of the present disclosure, a communication device is provided, the device comprising: a sending module configured to send first information to a second device, the first information comprising a random seed, the random seed being used to generate a first bit stream; and a receiving module configured to receive a data stream from the second device; the data stream being obtained by processing the first bit stream by a transmitter deployed by the second device.

[0009] According to another aspect of the present disclosure, a communication apparatus is provided, the apparatus comprising: a receiving module configured to receive first information from a first device, the first information comprising a random seed; a generating module configured to generate a second bit stream based on the random seed; a processing module configured to process the second bit stream into a data stream using a transmitter; and a transmitting module configured to transmit the data stream to the first device.

[0010] According to another aspect of the present disclosure, a communication system is provided, the system comprising: a first device configured to implement the method as described above; and a second device configured to implement the method as described above.

[0011] According to another aspect of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory, the processor being configured to execute the computer program to implement the method of any of the embodiments described above.

[0012] According to another aspect of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program / instructions, the computer program / instructions being executable by a processor to implement the method of any of the embodiments described above.

[0013] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program / instructions, the computer program / instructions being executable by a processor to implement the method of any of the embodiments described above.

[0014] As will be described in detail below, according to embodiments of the present disclosure, a communication method and apparatus, system, electronic device, storage medium and product are provided. The present disclosure utilizes a first device to transmit first information to a second device, the first information can comprise a random seed. After the second device obtains a second bit stream using the random seed, the second device can modulate the second bit stream to obtain a data stream, and only transmit the data stream to the first device. Since the first bit stream and the second bit stream are both calculated based on the same random seed, the second bit stream obtained by the second device is the same as the first bit stream. The first device can compare the first bit stream obtained based on the random seed with the bit stream recovered from the data stream, to obtain the demodulation quality of the first device, thereby supervising and training the first device. Compared with related technologies, the present disclosure does not need to transmit both the data stream and the second bit stream when training the first device, only needs to transmit the data stream, thereby reducing the overhead of data transmission, and to some extent, reducing the consumption of resources.

[0015] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the subject technology. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which:

[0017] FIG. 1 is a schematic diagram illustrating a communication system of a related art.

[0018] FIG. 2 is a schematic diagram illustrating another communication system of a related art.

[0019] FIG. 3 is a schematic diagram illustrating time-frequency resource allocation of a related art.

[0020] FIG. 4 is an interaction schematic diagram illustrating a communication method according to an embodiment of the present disclosure.

[0021] FIG. 5 is an interaction schematic diagram illustrating another communication method according to an embodiment of the present disclosure.

[0022] FIG. 6 is a schematic diagram illustrating a receiver model according to an embodiment of the present disclosure.

[0023] FIG. 7 is a block diagram illustrating a communication apparatus according to an embodiment of the present disclosure.

[0024] FIG. 8 is a block diagram illustrating another communication apparatus according to an embodiment of the present disclosure.

[0025] FIG. 9 is a schematic diagram illustrating a communication system according to an embodiment of the present disclosure.

[0026] FIG. 10 is a hardware block diagram of an electronic device according to an embodiment of the present disclosure.

[0027] FIG. 11 is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] In order to make the objectives, technical solutions and advantages of the present disclosure more apparent, the following will describe example embodiments according to the present disclosure in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, and are not all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited by the example embodiments described herein.

[0029] Transmitters and transceivers have a wide range of applications in wireless communication, broadcasting, television, radar, navigation, electronic countermeasures, remote sensing, radio astronomy, etc.

[0030] The transmitter can be used for bitstream encoding and modulation. For example, it can perform I / Q modulation on a bitstream encoded with low-density parity-check codes to obtain a constellation diagram. Then, the encoded and modulated bitstream undergoes demodulation reference signal (DMRS) insertion and time-frequency resource mapping to obtain the specific location of the modulated information in the time domain. For instance, the transmitter inserts the constellation diagram into DMRS pilots and performs time-frequency mapping. Next, the modulated signal can be transformed into an orthogonal frequency division multiplexing (OFDM) waveform in the time domain using an inverse fast fourier transform (IFFT). Finally, a cyclic prefix (CP) can be inserted into the OFDM waveform to obtain a data stream, which the transmitter then transmits to the receiver using the channel.

[0031] After sequentially performing CP removal and Fast Fourier Transform (FFT) on the data stream, the receiver extracts the DMRS pilot and estimates and interpolates it to obtain the channel matrix in the entire time-frequency domain. Then, based on the estimated channel matrix, the data is equalized to remove the channel's influence, yielding the modulated signal. Finally, the modulated information is demodulated and the channel is decoded to recover the original bit stream. The specific steps are illustrated in Figure 1, which is a schematic diagram of a communication system using related technologies.

[0032] However, due to the nonlinearity of transmitter components (e.g., power amplifiers, digital-to-analog converters, and peak-to-average power ratio) and the effects of non-stationary time-frequency fading channels, the transmitted signal is distorted. To improve performance, related technologies often incorporate nonlinear compensation in the receiver model.

[0033] A typical approach is to use an Artificial Intelligence (AI) receiver model to replace at least one of the channel estimation, interpolation, equalization, and demodulation in DMRS. Specific implementation details can be seen in Figure 2, which is a schematic diagram of another communication system illustrating the related technology.

[0034] However, training the receiving model requires a large amount of data. During training, the receiving model needs to acquire not only the data stream transmitted by the transmitter through the channel, but also the raw bit stream used to generate the data stream.

[0035] For example, please refer to FIG. 3, which is a schematic diagram illustrating time-frequency resource allocation of the related art. As shown in FIG. 3, for one resource block of one time slot, at least 336 bits of resources are needed in the case of digital modulation using Quadrature Phase Shift Keying (QPSK). If the original bit stream and data stream are transmitted, at least 672 bits of resources are needed.

[0036] As can be seen, the overhead of the acquisition data of the receiving model is too large, resulting in excessive consumption of resources and network resources for transmitting data.

[0037] Moreover, in the case of large differences in channel scenarios or large differences in nonlinearity of transmitter or receiver devices, the performance of the receiver can be significantly reduced, and the receiver cannot quickly make nonlinearity compensation according to different channels, and there is a problem of poor generalization. For example, the transmitter and the receiver use A channel for transmission, and the receiver needs to make B compensation for the received signal for the A channel; after switching to C channel, the signal needs to be compensated for D; if the difference between B and D is large, the receiver cannot respond in time, which can cause the performance of the receiver to decline.

[0038] To solve the above problems, the present disclosure provides a communication method, and the present disclosure generates a bit stream for training using a random seed, thereby saving transmission resources for transmitting the bit stream. FIG. 4 is an interaction schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in FIG. 4, the method specifically comprises:

[0039] S401, the first device sends first information to the second device, the first information comprising a random seed, the random seed being used to generate a first bit stream.

[0040] In the present embodiment, the first device can include but is not limited to at least one of the following: a mobile communication base station, a satellite communication ground station, a television, a radio, a wireless router, a Bluetooth device.

[0041] The second device can include but is not limited to at least one of the following: a mobile communication base station, a satellite communication ground station, a television station, a radio station, a mobile phone, a walkie-talkie, a wireless remote control.

[0042] Specifically, in different scenarios, the first device can send first information to the second device, and the specific scenarios are not specifically limited by the present disclosure, and the details will be described later.

[0043] The first information carries at least the random seed, and can also carry other types of information, which are not specifically limited herein. The first device can generate a unique and deterministic first bit stream by combining the random seed with a pseudo-random algorithm. The type of the pseudo-random algorithm is not specifically limited herein and will be described in detail later, and thus is not described in detail herein.

[0044] S402, the second device receives the first information from the first device.

[0045] After receiving the first information, the second device can read the first information to obtain the random seed.

[0046] S403, the second device generates a second bit stream based on the random seed.

[0047] The second device can generate the second bit stream by using the random seed and a locally deployed pseudo-random algorithm. When the random seed and the pseudo-random algorithm are consistent, the same bit stream can be obtained. In actual situations, the second device often deploys the same pseudo-random algorithm as the first device, that is, the first bit stream obtained by the first device by using the same random seed and pseudo-random algorithm is the same as the second bit stream. This means that the first device only needs to calculate according to the pseudo-random algorithm and the random seed to obtain the second bit stream before modulation of the second device, and does not need to transmit the second bit stream.

[0048] S404, the second device processes the second bit stream into a data stream by using the transmitter.

[0049] This step is mainly used for modulating the second bit stream, that is, sequentially performing the above steps of encoding, modulation, time-frequency mapping, inverse fast Fourier transform conversion, and inserting a cyclic prefix on the second bit stream to obtain a data stream, so as to be applied to the first device for recovery processing, thereby training the first device. Briefly, the second bit stream is the input (i.e., the original bit stream) of the second device, and the data stream is the output of the second device, which can be referred to FIG. 1 and FIG. 2.

[0050] S405, the second device sends the data stream to the first device.

[0051] The second device can send the data stream to the first device through a channel. The type of the channel is not specifically limited herein, which means that when the type of the channel changes, the first device needs to make different compensations on the signal in the recovery process.

[0052] The channel can include, but is not limited to, at least one of the following: a wired channel, a wireless channel, a non-stationary time fading channel, a stationary fading channel, a frequency selective fading channel, a Rayleigh channel, a constant parameter channel, and a random parameter channel.

[0053] S406, the first device receives the data stream from the second device.

[0054] After receiving the data stream, the first device can process the data stream in different scenarios.

[0055] For the training scenario of the first device, after receiving the data stream from the second device, the first device can demodulate the data stream to obtain a third bit stream.

[0056] For the performance evaluation scenario of the first device, after obtaining the third bit stream, the first device needs to compare the third bit stream with the first bit stream of the second device to obtain the recovery of the data stream by the first device. In actual application, since the first bit stream and the second bit stream are the same, the first device can compare the first bit stream and the third bit stream generated independently using the random seed to obtain the recovery of the data stream by the first device.

[0057] It should be understood that the above two processing methods can also be combined, that is, while training the first device, the performance of the first device can also be evaluated.

[0058] In summary, the present disclosure uses the first device to send first information to the second device, and the first information can include a random seed. After obtaining the second bit stream using the random seed, the second device can modulate the second bit stream to obtain the data stream, and only send the data stream to the first device. Since the first bit stream and the second bit stream are both calculated based on the same random seed, the second bit stream obtained by the second device is the same as the first bit stream. The first device can compare the first bit stream obtained based on the random seed with the bit stream recovered from the data stream to obtain the demodulation quality of the first device, thereby supervising and training the first device. Compared with related technologies, the present disclosure does not need to transmit two kinds of data, data stream and second bit stream, when training the first device, only needs to transmit the data stream, thereby reducing the overhead of data transmission, and also reducing the consumption of resources to a certain extent.

[0059] In addition, the present disclosure also specifically considers the triggering scenario of the first device sending the first information. It can be divided into the following types: 1. Triggered in the scenario after training; 2. Triggered in the scenario without training.

[0060] Specifically, for scenario 1, the first device can trigger the sending of the first information based on the occurrence of a specific event, and the present disclosure does not specifically limit the state of the first device. That is, even if the first device has been trained and put into normal use, if a specific event is triggered, the first device can be trained again. Thus, it can quickly respond to changes in the environment, thereby flexibly coping with different channel transmission scenarios and improving the generalization ability.

[0061] The specific event can be an internal event of the first device or an external event of another device.

[0062] In an illustrative embodiment, the first device can send the first information to the second device when the receiver is abnormal, and the second device can read the random seed after receiving the first information, and then perform the training process.

[0063] The receiver abnormality can include, but is not limited to, at least one of the following: output result abnormality, intermediate result abnormality. The output result abnormality includes, but is not limited to, at least one of the following: bit error rate higher than a preset first threshold, cyclic redundancy check abnormality, timing detection abnormality; the intermediate result abnormality includes: cyclic prefix removal result abnormality, fast Fourier transform result abnormality.

[0064] The bit error rate can be understood as the probability of data stream being transmitted incorrectly in the transmission process. The bit error rate here is not limited to the bit error rate of the training data (for example, the data stream obtained from the second bit stream), but also can be the bit error rate of the production data (that is, the data received when the first device is put into use).

[0065] That is, the first device can be retrained regardless of the output result abnormality of which data.

[0066] Referring to FIG. 5, FIG. 5 is an interaction diagram illustrating another communication method of an embodiment of the present disclosure. In FIG. 5, a next generation node B (gNB) is a first device, and a user equipment (UE) is a second device.

[0067] In step 1, a receiver or an AI receiver (that is, a receiver with a receiving model) needs to be deployed in the gNB, and the AI receiver can also be used for data demodulation.

[0068] In step 2, the gNB can send a frequency domain data collection random sequence generation algorithm (that is, a pseudo-random algorithm) for generating a first bit stream to the UE in advance, and when the gNB is triggered by a special event, the gNB can directly send first information to the UE to perform training.

[0069] In step 3, the UE can send a data stream to the gNB. The data stream here can be a data stream for generating data or a data stream for training data.

[0070] In step 4, the gNB can demodulate the data stream by using the receiver or the AI receiver after receiving the data stream.

[0071] In step 5, when the gNB sends the demodulation data error rate is too high, the training data collection can be started, that is, the gNB can send the first information to the UE, so as to perform the above training process, which will not be repeated here.

[0072] For scenario 2, the first device can send the first information to the second device before being put into use. For example, after the first device is turned on, the first device can directly enter the training state: sending the first information to the second device.

[0073] It should be understood that scheme 1 and scheme 2 can also be combined, that is, the first device can trigger the sending of the first information after being turned on, so as to train the first device. In the use process after the training is completed, the first device can retrain under the condition that a specific event is triggered.

[0074] For the above scenarios, the same pseudo-random algorithm needs to be deployed on both the first device and the second device to generate the same bit stream. The pseudo-random algorithm can be generated by the first device itself, or generated by other devices (such as the second device) and then sent to the first device. The specific scheme can be determined according to the actual situation, which is not limited here.

[0075] Specifically, the pseudo-random algorithm can be deployed before training. For example, in scheme 1, before the specific event is triggered, the first device and the second device can deploy the pseudo-random algorithm in advance (for example, step 2 of FIG. 5). When the specific event is triggered, the first device can directly send the first information to the second device without other preparations. In this scenario, the first device can send the second information to the second device, and the second device can generate the second bit stream using the second information and the first information. The second information is used to indicate the second bit stream generation method, and the second information includes but is not limited to at least one of the following: pseudo-random algorithm, constant to be configured for the pseudo-random algorithm.

[0076] The pseudo-random algorithm can also be deployed when training is needed, thereby reducing the number of interactions and saving communication resources. For example, in scheme 2, after the first device is turned on, the first device can directly send the first information to the second device. At this time, the first information can carry the second information. The second device can directly obtain the random seed and the pseudo-random algorithm by reading the first information.

[0077] The first information and the second information can be transmitted through a message or signaling.

[0078] For example, the second information can be transmitted through Radio Resource Control (RRC) signaling. Since RRC signaling has high security, the pseudo-random algorithm can be prevented from leaking during transmission to some extent, thereby improving the security of the system.

[0079] For another example, the first information can be transmitted through Downlink Control Information (DCI). Since DCI is transmitted frequently, DCI can quickly deliver the first information to the second device. At this time, the first information can also carry time-frequency resource information used for transmission of the data stream between the first device and the second device.

[0080] The pseudo-random algorithms deployed on the first device and the second device are the same, but the types are not limited and can include but are not limited to at least one of the following: linear congruential method, mixed congruential method, and Mason rotation algorithm, without being exhaustive.

[0081] For example, when the pseudo-random algorithm is the linear congruential method, it is applied to Scheme 1, and the second information includes at least the number of random bits to be generated. After receiving the second information and the first information from the first device, the second device can read the number of random bits and generate a 0 / 1 random sequence of the corresponding length according to the locally deployed linear congruential algorithm and the random seed. The relationship between the random seed and the sequence can satisfy:

[0082] A N+1 =(A N C+B)%M;

[0083] Wherein, A0 is the random seed; C is the multiplier; B is the increment; M is the modulus, wherein B and M are prime numbers; N is an integer greater than or equal to 0; wherein B, M, C and A0 can be determined according to actual conditions, and are not specifically limited here.

[0084] The A N+1 generated in this way is a random number less than M. If M = 2 16 , a 16-bit 0 / 1 sequence can be generated at a time. If a 128-bit long random sequence is needed, only 128 ÷ 16 = 8 cycles are needed.

[0085] It should be understood that the information carried by the second information above is only the information required by the present embodiment, and the second information can be different in actual application, which can be determined according to actual conditions.

[0086] The random sequence generated according to the above steps can be used as the second bit stream of the second device, and the first device can also obtain the first bit stream according to the same steps, and the first bit stream and the second bit stream are the same in principle. In this way, the resources consumed by the first device for collecting data can be saved. For example, in the case of transmitting a resource block of one time slot and using QPSK for digital modulation, the first device only needs to consume 336 resources for collecting the data stream, and does not need to collect the second bit stream. Compared with 672 bits consumed by related technologies, at least 336 bits of resources can be saved.

[0087] It should be noted that DMRS pilots or physical uplink control channels (PUCCH) can not be inserted in the resource blocks of the above data. If DMRS pilots or PUCCH need to be inserted, the corresponding number of bits needs to be subtracted.

[0088] Further, since the data stream is generated by a pseudo-random algorithm and a random seed, and is not actually required to be transmitted, the first device does not need to pass the data stream to the upper layer, thereby saving transmission resources.

[0089] In a possible embodiment, the first device can be provided with a receiving model, wherein the receiving model is deployed in the receiver, and the receiving model can implement at least one of channel estimation, interpolation, equalization, and arbitration.

[0090] The structure of the receiving model can include but is not limited to at least one of the following: a convolutional neural network, a deep residual network, and a self-attention neural network.

[0091] The first bit stream and the data stream described above can also be used to train the receiving model. That is, the data stream is used as an input sample of the receiving model, the time-frequency domain symbol level data after the removal of the cyclic prefix processing and the fast Fourier transform processing is used as the input data, the first bit stream is used as the output sample, and the probability of each bit being 0 or 1 obtained by evaluation is the output data. The output data can be compared with the output sample, so as to supervise the training of the receiving model.

[0092] Further, the receiving model can also be provided with a loss function, wherein the loss function is used to evaluate the difference between the output data of the input sample and the output sample.

[0093] Exemplarily, referring to FIG. 6, which is a schematic diagram illustrating a receiver model of an embodiment of the present disclosure, as shown in FIG. 6, after the data passes through a cyclic prefix removal module and a fast Fourier transform module, time-frequency domain symbol data can be obtained, which is input into the receiver AI model (i.e., the above-mentioned receiving model), and the log likelihood ratio (LLR) of the time-frequency domain symbol data can be obtained. The forward-propagated LLR is first subjected to sigmoid transformation to become a floating-point number between 0 and 1, and the greater the value, the greater the probability that the bit is 1.

[0094] The specific relationship can satisfy:

[0095] wherein b LLR is the probability that the bit is 1; and LLR is the log likelihood ratio.

[0096] The present disclosure does not specifically limit the type of loss function, and the loss function can include but is not limited to at least one of the following: mean squared error loss (MSE), mean absolute error loss (MAE), and binary sigmoid cross-entropy loss function.

[0097] For ease of understanding, taking the binary sigmoid cross-entropy loss function as an example, the loss value and b LLR The relationship can satisfy:

[0098] wherein N is the number of resource blocks; B is the number of bits transmitted in the resource blocks; b label is the first bit stream; and Loss is the loss value.

[0099] In this way, the first device can obtain the difference between the third bit stream and the first bit stream according to the loss value, and when the difference is large (e.g., greater than a preset first threshold), the loss value can be used as a basis for updating the channel compensation of the first device.

[0100] The above method can also be applied to a receiver without a receiving model. The receiver includes at least one of the following: a cyclic prefix removal module, a fast Fourier transform module, a receiving model, and a decoding module.

[0101] The above-mentioned transmitter includes but is not limited to at least one of the following modules: an encoding module, a modulation module, a mapping module, an inverse fast Fourier transform module, and a cyclic prefix module.

[0102] The present disclosure also provides a communication device. FIG. 7 is a structural block diagram of a communication device according to an embodiment of the present disclosure. As shown in FIG. 7, the communication device 700 includes:

[0103] The sending module 701 is configured to send first information to a second device, wherein the first information includes a random seed, and the random seed is used to generate a first bit stream.

[0104] The receiving module 702 is configured to receive a data stream from the second device, wherein the data stream is processed from the first bit stream by a transmitter deployed in the second device.

[0105] In an exemplary embodiment, the communication device 700 is further configured to generate the first bit stream based on the random seed, and train a receiving model based on the first bit stream and the data stream, wherein the receiving model is deployed in the receiver to implement at least one of reference signal estimation, interpolation, equalization, and arbitration, and the first bit stream is generated by using a pseudo-random algorithm.

[0106] In an exemplary embodiment, the communication device 700 is further configured to the pseudo-random algorithm includes at least one of a linear congruential method, a mixed congruential method, and a Mersenne Twister algorithm.

[0107] In an exemplary embodiment, the communication device 700 is further configured to supervise the training of the receiving model by taking the data stream as an input sample of the receiving model and taking the first bit stream as an output sample of the receiving model.

[0108] In an exemplary embodiment, the communication device 700 is further configured to a loss function of the receiving model is used to evaluate a difference between output data of the input sample and the output sample, wherein the output data is obtained by processing the data stream by the receiving model in the training, and the output data is used to represent a probability of the first bit stream being 0 or 1.

[0109] In an exemplary embodiment, the communication device 700 is further configured to send second information to the first device, or the first information carries the second information, wherein the second information is used to indicate a generation manner of a second bit stream.

[0110] In an exemplary embodiment, the communication device 700 is further configured to send the second information to the first device by using radio resource control (RRC) signaling.

[0111] In an exemplary embodiment, the communication device 700 is further configured to send the first information to the second device by using downlink control information (DCI).

[0112] In an example embodiment, the communication apparatus 700 is further configured to have the first information further carrying time-frequency resource information, the time-frequency resource information being used for transmission of the data stream between the first device and the second device.

[0113] In an example embodiment, the communication apparatus 700 is further configured to have the data stream not used for passing to a higher layer.

[0114] In an example embodiment, the communication apparatus 700 is further configured to send the first information to the second device when the receiver is abnormal; wherein the receiver being abnormal includes at least one of the following: output result abnormality, intermediate result abnormality; wherein the output result abnormality includes at least one of the following: bit error rate being higher than a preset first threshold, cyclic redundancy check abnormality, timing detection abnormality; the intermediate result abnormality includes cyclic prefix removal result abnormality.

[0115] In an example embodiment, the communication apparatus 700 is further configured to have the receiver including at least one of the following: cyclic prefix removal module, fast Fourier transform module, receiving model, decoding module.

[0116] The present disclosure also provides a communication apparatus. FIG. 8 is a structural block diagram of another communication apparatus provided by an embodiment of the present disclosure, as shown in FIG. 8, the communication apparatus 800 includes:

[0117] A receiving module 801 is configured to receive first information from a first device, the first information including a random seed.

[0118] A generating module 802 is configured to generate a second bit stream based on the random seed.

[0119] A processing module 803 is configured to process the second bit stream into a data stream by using a transmitter.

[0120] A sending module 804 is configured to send the data stream to the first device.

[0121] In an example embodiment, the communication apparatus 800 is further configured to have the data stream and a first bit stream used for training a receiving model; the first bit stream is generated by the first device based on the random seed; the receiving model is deployed in the first device, and the receiving model is used to implement at least one of the following: reference signal estimation, interpolation, equalization, mediation.

[0122] In an example embodiment, the communication apparatus 800 is further configured to receive second information from the first device; or,

[0123] The first information carries the second information; wherein the second information is used to indicate a first bit stream generation manner.

[0124] In an example embodiment, the communication apparatus 800 is further configured to generate the second bit stream based on the second bit stream generation manner indicated by the second information, using the random seed; wherein the second bit stream is a random sequence generated based on the random seed; and the second bit stream is generated using a pseudo-random algorithm.

[0125] In an example embodiment, the communication apparatus 800 is further configured to the pseudo-random algorithm comprises at least one of: a linear congruential method, a mixed congruential method, and a Mersenne Twister algorithm.

[0126] In an example embodiment, the communication apparatus 800 is further configured to receive the second information from the first device through RRC signaling.

[0127] In an example embodiment, the communication apparatus 800 is further configured to receive the first information from the second device through DCI.

[0128] In an example embodiment, the communication apparatus 800 is further configured to the first information further carries time-frequency resource information, the time-frequency resource information being used for transmission of the data stream between the first device and the second device; and the sending the data stream to the first device comprises sending the DCI to the first device based on time-frequency resources indicated by the time-frequency resource information.

[0129] In an example embodiment, the communication apparatus 800 is further configured to receive first information from the first device; the first information is sent in response to a receiver exception; wherein the receiver exception comprises at least one of: an output result exception and an intermediate result exception; wherein the output result exception comprises at least one of: a bit error rate higher than a preset first threshold, a cyclic redundancy check exception, and a timing detection exception; and the intermediate result exception comprises a cyclic prefix removal result exception.

[0130] In an example embodiment, the communication apparatus 800 is further configured to the transmitter comprises at least one of: an encoding module, a modulation module, a mapping module, an inverse fast Fourier transform module, and a cyclic prefix module.

[0131] The present disclosure also provides a communication apparatus. FIG. 9 is a schematic diagram of a communication system according to an example embodiment of the present disclosure. As shown in FIG. 9, the communication system comprises: a first device configured to implement the method described above.

[0132] a second device configured to implement the method described above.

[0133] FIG. 10 is a hardware block diagram of an electronic device according to an embodiment of the disclosure. The electronic device 1000 according to an embodiment of the disclosure includes at least a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the signal transmission method according to any of the above-described embodiments.

[0134] The electronic device 1000 shown in FIG. 10 specifically includes a central processing unit (CPU) 1001, a graphics processing unit (GPU) 1002, and a memory 1003. These units are connected to each other through a bus 1004. The central processing unit (CPU) 1001 and / or the graphics processing unit (GPU) 1002 can be used as the processor described above, and the memory 1003 can be used as the memory storing the computer readable instructions described above. In addition, the electronic device 1000 can further include a communication unit 1005, a storage unit 1006, an output unit 1007, an input unit 1008, and an external device 1009, and these units are also connected to the bus 1004.

[0135] FIG. 11 is a schematic diagram of a computer readable storage medium according to an embodiment of the disclosure. As shown in FIG. 11, the computer readable storage medium 1100 according to an embodiment of the disclosure has computer readable instructions 1101 stored thereon. The computer readable instructions 1101 are executed by a processor to implement the signal transmission method according to any of the above-described embodiments of the disclosure. The computer readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.

[0136] The disclosure further provides a computer program product including computer programs / instructions, which, when executed by a processor, implement the communication method according to any of the above-described embodiments of the disclosure.

[0137] The above describes the basic principles of the disclosure in conjunction with specific embodiments, but it should be noted that the advantages, benefits, effects, etc. mentioned in the disclosure are only examples and are not limiting, and these advantages, benefits, effects, etc. cannot be considered as the various embodiments of the disclosure must have. In addition, the above-described specific details are only for the purpose of example and for the purpose of understanding, and are not limiting, and the above-described details do not limit the disclosure to the above-described specific details.

[0138] The block diagrams of devices, apparatuses, equipment, systems referred to in the present disclosure are merely illustrative examples and are not intended to require or imply that the connection, arrangement, configuration must be as shown in the block diagrams. These devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner as will be appreciated by those skilled in the art. Words such as "include," "contain," "have," etc. are open-ended words that are to be interpreted to mean "including but not limited to," and are to be interpreted not to exclude other items. The words "or" and "and" as used herein are to be interpreted as the word "and / or," and are to be interpreted not to exclude other items. The word "such as" as used herein is to be interpreted as the phrase "such as but not limited to," and is to be interpreted not to exclude other items.

[0139] Also, as used herein, the "or" as used in the context of "at least one of A, B or C" is to be interpreted as "at least one of A, at least one of B, or at least one of C." Further, the phrase "example of" is not meant to be limiting in any way.

[0140] It is also to be noted that in the systems and methods of the present disclosure, the various components or steps can be divided and / or recombined. These divisions and / or re-combinations are to be considered as equivalent to the systems and methods of the present disclosure.

[0141] Various changes, modifications and alterations in the teachings and techniques described herein can be made without departing from the teachings and techniques defined by the appended claims. Moreover, the scope of the claims of the present disclosure is not limited to the specific aspects described above. Processes, machines, manufacture, compositions of matter, means, methods, or steps, presently existing or later to be developed that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Accordingly, the appended claims include within their scope such processes, machines, manufacture, compositions of matter, means, methods, or steps.

[0142] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0143] The foregoing description has been presented for the purposes of illustration and description. Furthermore, the description is not intended to limit the embodiments of the disclosure to the forms disclosed herein. Although the various example aspects and embodiments have been described herein with regard to particular aspects and embodiments, those skilled in the art will recognize that certain modifications, changes, substitutions, additions and sub-combinations can be made without departing from the spirit of the disclosure.

Claims

A communication method applied to a first device, the first device being deployed with a receiver, the method comprising: sending first information to a second device, the first information comprising a random seed, the random seed being used to generate a first bit stream; receiving a data stream from the second device; the data stream being processed to the first bit stream by a transmitter deployed in the second device. The method according to claim 1, further comprising: generating the first bit stream based on the random seed; training a receiving model based on the first bit stream and the data stream; wherein the receiving model is deployed in the receiver to implement at least one of reference signal estimation, interpolation, equalization, arbitration; the first bit stream is generated by a pseudo-random algorithm. The method of claim 2, wherein, The pseudo-random algorithm comprises at least one of linear congruential method, mixed congruential method, and mersenne twister algorithm. The method of claim 2, wherein, The training of the receiving model based on the first bit stream and the data stream comprises: supervised training of the receiving model by taking the data stream as input samples and the first bit stream as output samples. The method of claim 2, wherein, The loss function of the receiving model is used to evaluate the difference between the output data of the input samples and the output samples; wherein the output data is obtained by processing the data stream by the receiving model in training; the output data is used to represent the probability of the first bit stream being 0 or 1. The method according to claim 1, further comprising: sending second information to the first device; or, the first information carries the second information; wherein the second information is used to indicate the generation mode of the second bit stream. The method of claim 6, wherein, The sending of the second information to the first device comprises: sending the second information to the first device by radio resource control (RRC) signaling. The method of claim 1, wherein, The sending of the first information to the second device comprises: sending the first information to the second device by downlink control information (DCI). The method of claim 8, wherein, The first information further carries time-frequency resource information, which is used for the transmission of the data stream between the first device and the second device. The method of claim 1, wherein, The data stream is not used to pass to a higher layer. The method of claim 1, wherein, The sending of the first information to the second device comprises: when the receiver is abnormal, sending the first information to the second device; wherein the receiver abnormality comprises at least one of output result abnormality and intermediate result abnormality; wherein the output result abnormality comprises at least one of bit error rate being higher than a preset first threshold, cyclic redundancy check abnormality, and timing detection abnormality; the intermediate result abnormality comprises cyclic prefix removal result abnormality. The method of claim 1, wherein, The receiver comprises at least one of a cyclic prefix removal module, a fast Fourier transform module, a receiving model, and a decoding module. A communication method applied to a second device, the second device being deployed with a transmitter, the method comprising: receiving first information from a first device, the first information comprising a random seed; generating a second bit stream based on the random seed; processing the second bit stream to a data stream by the transmitter; sending the data stream to the first device. The method of claim 13, wherein, The data stream is used for training a receiving model; The first bit stream is generated by the first device based on the random seed; The receiving model is deployed on the first device, and the receiving model is used to implement at least one of reference signal estimation, interpolation, equalization, and arbitration. The method of claim 13, further comprising: Receiving second information from the first device; Or, The first information carries the second information; The second information is used to indicate a first bit stream generation manner. The method of claim 15, wherein, The second bit stream is generated based on the random seed, including: The second bit stream is generated based on the second bit stream generation manner indicated by the second information and the random seed; The second bit stream is a random sequence generated based on the random seed; The second bit stream is generated by using a pseudo-random algorithm. The method of claim 16, wherein, The pseudo-random algorithm includes at least one of a linear congruential method, a mixed congruential method, and a Mersenne Twister algorithm. The method of claim 16, wherein, Receiving second information from the first device through RRC signaling. The method of claim 13, wherein, Receiving the first information from the second device through DCI. The method of claim 19, wherein, The first information also carries time-frequency resource information, which is used for transmission of the data stream between the first device and the second device; The data stream is transmitted to the first device, including: The DCI is transmitted to the first device based on the time-frequency resource indicated by the time-frequency resource information. The method of claim 13, wherein, Receiving first information from the first device; the first information is sent in response to a receiver exception; The receiver exception includes at least one of an output result exception and an intermediate result exception; The output result exception includes at least one of a bit error rate higher than a preset first threshold, a cyclic redundancy check exception, and a timing detection exception; The intermediate result exception includes a cyclic prefix removal result exception. The method of claim 13, wherein, The transmitter includes at least one of an encoding module, a modulation module, a mapping module, an inverse fast Fourier transform module, and a cyclic prefix module. A communication device, the device comprising: A sending module configured to send first information to a second device, the first information including a random seed used to generate a first bit stream; A receiving module configured to receive a data stream from the second device; The data stream is processed by a transmitter deployed on the second device. A communication device, the device comprising: A receiving module configured to receive first information from a first device, the first information including a random seed; A generating module configured to generate a second bit stream based on the random seed; A processing module configured to process the second bit stream into a data stream by using a transmitter; A sending module configured to send the data stream to the first device. A communication system, the system comprising: A first device configured to implement the method of any one of claims 1-12; A second device configured to implement the method of any one of claims 13-22. An electronic device comprising a memory, a processor, and a computer program stored on the memory, the processor executing the computer program to implement the method of any one of claims 1-22. A computer readable storage medium having stored thereon computer programs / instructions which, when executed by a processor, implement the method of any one of claims 1-22. A computer program product comprising computer programs / instructions which, when executed by a processor, implement the method of any one of claims 1-22.

Images