Method for acquiring reference signal and communication device

Abstract

The embodiment of the present application provides a kind of method for obtaining reference signal, terminal equipment and network equipment, applied to communication technical field, the embodiment of the present application includes: after sending first reference signal to second communication device, receiving the compressed reference signal sent by second communication device, compressed reference signal is obtained after the second reference signal is compressed encoding, and the second reference signal is the reference signal corresponding to first reference signal received by second communication device;Third reference signal is obtained by decoding and reconstructing compressed reference signal.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a method and communication device for acquiring a reference signal. Background Technology

[0002] Currently, during the transmission process where the transmitter sends the pilot signal symbol sequence to the receiver, the actual pilot signal received by the receiver is not consistent with the pilot signal symbol sequence sent by the transmitter due to the influence of channel information and noise. Therefore, the transmitter needs the receiver to feed back channel information so that the transmitter can combine the actual channel information for subsequent precoding. Thus, it is an urgent problem to solve that the transmitter needs to know the actual pilot signal of the receiver, or the transmitter needs to know the channel information fed back by the receiver that is more consistent with the actual pilot signal. Summary of the Invention

[0003] This invention provides a method and communication device for obtaining a reference signal. The transmitting end can obtain the actual pilot signal received by the receiving end and thereby obtain channel information that better matches the actual pilot signal.

[0004] Firstly, a method for obtaining a reference signal is provided, including:

[0005] After sending a first reference signal to the second communication device, a compressed reference signal sent by the second communication device is received. The compressed reference signal is obtained by compressing and encoding the second reference signal. The second reference signal is a reference signal received by the second communication device that corresponds to the first reference signal.

[0006] The compressed reference signal is decoded and reconstructed to obtain the third reference signal.

[0007] Secondly, a method for obtaining a reference signal is provided, including:

[0008] The receiver is configured to receive a compressed reference signal sent by the second communication device after sending a first reference signal to the second communication device. The compressed reference signal is obtained by compressing and encoding the second reference signal, and the second reference signal is a reference signal received by the second communication device that corresponds to the first reference signal.

[0009] The processor is used to decode and reconstruct the compressed reference signal to obtain a third reference signal.

[0010] Thirdly, a first communication device is provided, comprising:

[0011] The receiver is configured to receive a compressed reference signal sent by the second communication device after sending a first reference signal to the second communication device. The compressed reference signal is obtained by compressing and encoding the second reference signal, and the second reference signal is a reference signal received by the second communication device that corresponds to the first reference signal.

[0012] The processor is used to decode and reconstruct the compressed reference signal to obtain a third reference signal.

[0013] Fourthly, a second communication device is provided, comprising:

[0014] A receiver is configured to receive a second reference signal, the second reference signal corresponding to the first reference signal sent by the first communication device;

[0015] The processor is used to perform compression encoding processing on the second reference signal to obtain a compressed reference signal;

[0016] A transmitter is provided for transmitting the compressed reference signal to the first communication device. In a fifth aspect, a first communication device is provided, comprising:

[0017] The receiving module is configured to receive a compressed reference signal sent by the second communication device after sending a first reference signal to the second communication device. The compressed reference signal is obtained by compressing and encoding the second reference signal, and the second reference signal is a reference signal received by the second communication device that corresponds to the first reference signal.

[0018] The processing module is used to decode and reconstruct the compressed reference signal to obtain a third reference signal.

[0019] Sixthly, a second communication device is provided, comprising:

[0020] A receiving module is configured to receive a second reference signal, the second reference signal corresponding to the first reference signal sent by the first communication device;

[0021] The processing module is used to perform compression encoding processing on the second reference signal to obtain a compressed reference signal;

[0022] The transmitting module is used to transmit the compressed reference signal to the first communication device.

[0023] A seventh aspect provides a computer-readable storage medium comprising: computer instructions that, when executed on a computer, cause the computer to perform the method described in the first aspect.

[0024] Eighthly, a computer-readable storage medium is provided, comprising: computer instructions that, when executed on a computer, cause the computer to perform the method as described in the second aspect above.

[0025] Ninth aspect, a computer program product is provided, including computer instructions, which, when the computer program product is run on a computer, cause the computer to execute the method as described in the first aspect above.

[0026] In a tenth aspect, a computer program product is provided, comprising computer instructions that, when the computer program product is run on a computer, cause the computer to execute the computer instructions, thereby performing the method as described in the second aspect above.

[0027] This invention provides a method for obtaining a reference signal. After a first communication device sends a first reference signal to a second communication device, it receives a compressed reference signal sent by the second communication device. The compressed reference signal is obtained by compressing and encoding the second reference signal, which is the reference signal received by the second communication device corresponding to the first reference signal. The compressed reference signal is then decoded and reconstructed to obtain a third reference signal. Through this scheme, after the first communication device sends the first reference signal to the second communication device, the second communication device can send a compressed reference signal back to the first communication device. This allows the transmitting end to obtain the actual pilot signal received by the receiving end and thus obtain channel information that more closely matches the actual pilot signal. Attached Figure Description

[0028] Figure 1 A schematic diagram illustrating the basic workflow of a wireless communication system provided in an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram of a channel estimation and recovery process provided in an embodiment of the present invention;

[0030] Figure 3 A schematic diagram of the basic structure of a neural network provided in an embodiment of the present invention;

[0031] Figure 4A A schematic diagram of a convolutional neural network provided in an embodiment of the present invention;

[0032] Figure 4B A schematic diagram of an LSTM model provided in an embodiment of the present invention;

[0033] Figure 5 This is a schematic diagram of a channel estimation process for a neural network provided in an embodiment of the present invention;

[0034] Figure 6 A schematic diagram of a channel feedback process of a neural network provided in an embodiment of the present invention;

[0035] Figure 7 A schematic diagram of a channel information feedback system provided in an embodiment of the present invention;

[0036] Figure 8 This is a schematic diagram of a method for acquiring a reference signal according to an embodiment of the present invention;

[0037] Figure 9 This is a schematic diagram of the overall signal flow of a CSI feedback scheme for compressed pilot signals provided in an embodiment of the present invention;

[0038] Figure 10 A schematic diagram of the training phase of a pilot design module provided in an embodiment of the present invention;

[0039] Figure 11 A schematic diagram illustrating the application stage of a pilot design model provided in an embodiment of the present invention;

[0040] Figure 12 This is a schematic diagram of the structure of a first communication device provided in an embodiment of the present invention;

[0041] Figure 13 This is a schematic diagram of the structure of a second communication device provided in an embodiment of the present invention;

[0042] Figure 14 This is a schematic diagram of the structure of a communication device provided in an embodiment of the present invention. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0044] In embodiments of the present invention, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0045] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0046] The following is a brief description of the relevant technologies and terms involved in the embodiments of the present invention:

[0047] 1. Overall Description of the Wireless Communication System

[0048] like Figure 1 The diagram shows the basic workflow of a wireless communication system, including the following main processes:

[0049] The transmitter (i.e., the transmitting equipment) performs channel coding and modulation on the source bit stream to obtain modulation symbols; then pilot symbols can be inserted into the obtained modulation symbols for channel estimation and symbol detection at the receiving end; finally, the transmitted signal is formed and reaches the receiving end through the channel.

[0050] The receiver (i.e., the receiving end device) receives the signal and uses pilots to perform channel estimation; then, it feeds the channel information back to the transmitter through a feedback link, allowing the transmitter to adjust the channel coding method, modulation method, and precoding method, etc.; finally, the receiver obtains the final recovered bit stream through symbol detection, demodulation, and channel decoding reconstruction steps. In this embodiment of the invention, the channel information involved can be Channel-State Information (CSI).

[0051] Figure 1 This is a simplified illustration of the basic workflow in a wireless communication system. Traditional communication systems may also include other modules and workflows not listed here. For example, they may also include functional modules such as resource mapping, precoding, interference cancellation, and CSI measurement. These modules can be designed and implemented independently, and their integration can form a complete wireless communication system.

[0052] 2. Channel estimation

[0053] Due to the complexity and time-varying nature of wireless channel environments, in situations such as Figure 1 In the wireless communication system described above, the receiver's estimation and recovery of the wireless channel directly affects the data recovery performance of the final recovered bitstream.

[0054] The current channel estimation and recovery process in communication systems is as follows: Figure 2 As shown:

[0055] Regarding the channel transmission phase: In terms of time and frequency resources, the transmitter, in addition to information data symbols (i.e.... Figure 2 In addition to the data symbols shown, a series of specific pilot symbols known to the receiver (i.e., Figure 2Reference signal symbols shown in the figure, such as Channel-State Information Reference Signal (CSI-RS) signal, Demodulation Reference Signal (DMRS) signal, etc.

[0056] For the channel estimation stage: the receiver can estimate the channel information at the reference signal location using the least squares method (also known as the LS method) based on the actual pilot and the received pilot;

[0057] For the channel recovery phase: The receiver uses an interpolation algorithm based on the channel information estimated at the pilot position to recover the channel information on the full time-frequency resources, which is used for subsequent channel information feedback or data recovery, etc.

[0058] 3. Channel feedback

[0059] For 5G New Radio (NR) systems, current CSI feedback designs primarily utilize codebook-based schemes to extract and feedback channel features. Specifically, after channel estimation at the transmitting end, a precoding matrix matching the current channel is selected from a pre-defined precoding codebook based on the estimation results and certain optimization criteria. The matrix index information, the Precoding Matrix Indicator (PMI), is then fed back to the receiving end via the air interface feedback link for precoding. Simultaneously, the Channel Quality Indication (CQI), obtained from measurements, is also fed back to the receiving end for adaptive modulation and coding.

[0060] 4. Neural Networks

[0061] In recent years, artificial intelligence research, represented by Neural Networks (NN), has achieved remarkable results in many fields, and it will play an important role in people's production and life for a long time to come.

[0062] like Figure 3 As shown, the basic structure of a neural network includes an input layer, hidden layers, and an output layer. The input layer is responsible for receiving data, the hidden layers are responsible for processing the data, and the final result is generated in the output layer. Each node represents a processing unit, which can be considered as simulating a neuron. Multiple neurons form a layer of the neural network, and the information transmission and processing across multiple layers construct a complete neural network.

[0063] With the continuous development of neural network research, deep learning algorithms for neural networks have been proposed in recent years. More hidden layers have been introduced, and feature learning is carried out by training the neural network layer by layer through multiple hidden layers. This has greatly improved the learning and processing capabilities of the neural network and has been widely used in pattern recognition, signal processing, optimization and combination, anomaly detection and other fields.

[0064] Similarly, with the development of deep learning, Convolutional Neural Networks (CNNs) have been proposed in recent years. For example... Figure 4A The diagram shows a convolutional neural network. The basic structure of this network includes an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer. In convolutional neural networks, the introduction of convolutional and pooling layers effectively controls the rapid increase in network parameters, limits the number of parameters, and leverages the characteristics of local structures, thus improving the robustness of the algorithm.

[0065] like Figure 4B As shown, a Recurrent Neural Network (RNN) is a type of recurrent neural network that takes sequential data as input, recursively processes the data in the direction of the sequence, and connects all nodes (recurrent units) in a chain-like manner. As the most commonly used and traditional deep learning model in natural language processing (NLP), RNN networks process sequential data step by step, similar to how humans understand text, comprehending it word by word or sentence by sentence. Long Short-Term Memory (LSTM) networks are a variant of RNNs, such as... Figure 4B The diagram illustrates an LSTM model. The essence of this model lies in introducing the concept of cell states. Unlike RNNs, which only consider the most recent state, LSTM's cell states determine which states are retained and which can be ignored, thus overcoming the shortcomings of traditional RNNs in long-term memory. Here, Xt-1, Xt, and Xt+1 represent three consecutive inputs, ht-1, ht, and ht+1 represent three consecutive outputs, tanh represents a neural network layer with tanh as the activation function, and σ represents a neural network layer with sigmoid as the activation function.

[0066] 5. Channel estimation based on neural networks

[0067] Current neural network-based channel estimation methods consider utilizing artificial intelligence (AI) to achieve channel estimation and recovery. For example... Figure 5The diagram illustrates a channel estimation process using a neural network. The reference signal is input to an AI-based channel estimation and recovery module, which then outputs the channel estimation and recovery result (i.e., the result of the channel estimation and recovery). Figure 5 (The channel recovery results are shown in the image). It's important to note that the input information for the AI-based channel estimation and recovery module can include not only the reference signal but also other auxiliary information to improve its performance. For example, this auxiliary information could include feature extraction information from the reference signal, energy level information, time delay characteristics, noise characteristics, etc.

[0068] 6. Channel feedback based on neural networks

[0069] Given the tremendous success of AI technology in areas such as computer vision and natural language processing, the communications field has begun to explore new technological approaches to address technical challenges that are limited by traditional methods, such as deep learning. The neural network architecture commonly used in deep learning is non-linear and data-driven, capable of extracting features from actual channel matrix data and reconstructing the compressed channel matrix information from the user equipment (UE) at the base station side as accurately as possible. This not only ensures the reconstruction of channel information but also provides the possibility of reducing CSI feedback overhead at the UE side.

[0070] like Figure 6 The diagram shows a channel feedback process of a neural network. The channel information can be regarded as a channel image to be compressed. Assuming that the channel image is a 28×28=784 image, the channel information is compressed using a deep learning autoencoder and fed back to the peer device of the current device. Then, the peer device reconstructs the compressed channel image, which can preserve the channel information to a greater extent and obtain the reconstructed channel image.

[0071] like Figure 7 The diagram shown illustrates a channel information feedback system. This system consists of an encoder and a decoder, with the encoder deployed at the transmitting end (e.g., [example of encoder deployment]). Figure 1 The receiver shown in the image), the decoder is deployed at the receiving end (e.g., the receiver shown in the image). Figure 1(The transmitter shown is an example). After obtaining channel information through channel estimation, the transmitting end convolves the channel information matrix through the convolutional layer of the encoder's neural network to obtain a 32×32 encoding matrix. Then, through dimensionality transformation, an N×1 encoding matrix is ​​obtained. Further, the N×1 encoding matrix is ​​compressed through a fully connected layer and converted into an M×1 encoding matrix, where M is less than N, completing the compression encoding. The compressed bitstream is fed back to the receiving end through the air interface feedback link. The receiving end uses a decoder to recover the channel information based on the feedback bitstream to obtain complete feedback channel information. Specifically, the received M×1 encoding matrix can first be recovered into an N×1 feature map, then the N×1 feature map can be converted into a 32×32 feature map encoding matrix. After convolution and summation, the convolution and summation operations are repeated to obtain the recovered channel information and output it. Figure 7 As shown, the encoder can use several fully connected layers for encoding, while the decoder uses a residual network structure for decoding. This allows for flexible design of the network model structures within the encoder and decoder while maintaining the original encoding / decoding framework.

[0072] Currently, the channel information feedback in the 5G NR standard uses a codebook-based feedback scheme. However, the codebook-based feedback scheme selects the optimal channel information feature vector from the codebook based on the estimated channel. Since the codebook itself is finite, the mapping process from the estimated channel information to the channel information in the codebook is lossy in terms of quantization. This reduces the accuracy of the final feedback channel information, thereby reducing the performance of precoding.

[0073] In one optional embodiment, a neural network-based channel information feedback scheme is introduced. This scheme directly encodes and compresses the channel information obtained after channel estimation, thus feeding back the full channel information and alleviating the accuracy problem of codebook-based schemes. However, since the full channel information is still recovered and received at the transmitting end, eigenvalue decomposition of the full channel information matrix is ​​still required to obtain eigenvectors for beamforming. Therefore, compared to directly compressing the eigenvectors, excessive redundant information in the full channel information is compressed, reducing compression efficiency.

[0074] In another alternative embodiment, a scheme is introduced that directly compresses and feeds back the feature vectors using a neural network. This scheme divides the subcarriers of the scheduling bandwidth into multiple groups, each corresponding to a sub-band channel. After obtaining the full channel information at the receiving end by performing channel estimation based on the received pilot signals, eigenvalue decomposition can be performed to obtain feature vectors, and the feature vectors of each sub-band channel can be fed back separately. However, as the precoding accuracy requirements increase, the granularity of sub-band channel division becomes finer, and the number of sub-band channels also increases, resulting in a still significant feedback overhead.

[0075] In practical applications, the receiving end is often a mobile phone or other terminal device, which has less computing power compared to the transmitting end, the base station. After receiving the pilot signal, a series of operations such as channel estimation and eigenvalue decomposition are required, which places high demands on the computing power of the terminal device. This is especially true when considering AI-based channel estimation, which places even higher demands on the computing power of the terminal device. The hardware implementation of the terminal device is quite difficult, and practical terminal devices are unlikely to support the above-mentioned scheme.

[0076] To address the aforementioned problems, this invention provides a method for obtaining a reference signal. After sending a first reference signal to a second communication device, a first communication device receives a compressed reference signal sent by the second communication device. The compressed reference signal is obtained by compressing and encoding the second reference signal, which is the reference signal received by the second communication device corresponding to the first reference signal. The compressed reference signal is then decoded and reconstructed to obtain a third reference signal. With this method, after the first communication device sends the first reference signal to the second communication device, the second communication device can send a compressed reference signal back to the first communication device. This allows the transmitting end to obtain the actual pilot signal received by the receiving end and thus obtain channel information that more closely matches the actual pilot signal.

[0077] Furthermore, since the second communication device is a receiving device, it does not need to perform channel estimation in this embodiment of the invention, and its computing power requirements are low. Therefore, when the receiving device is a mobile phone, the computing power requirements can be fully met. Thus, this solution does not have high hardware requirements and can be applied to more communication scenarios.

[0078] In this embodiment of the invention, the communication device (first communication device or second communication device) involved can be either a receiver or a transmitter. Optionally, the receiver can be a terminal device or a network device; the transmitter can also be a terminal device or a network device.

[0079] Terminal devices can be stations (STAION, ST) in WLANs, cellular phones, cordless phones, Session Initiation Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistant (PDA) devices, handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, in-vehicle devices, wearable devices, terminal devices in next-generation communication systems such as NR networks, or terminal devices in future evolved Public Land Mobile Network (PLMN) networks, etc.

[0080] In this embodiment of the invention, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships); and it can also be deployed in the air (e.g., on airplanes, balloons and satellites).

[0081] In embodiments of the present invention, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical care, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0082] By way of example and not limitation, in this embodiment of the invention, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on only one type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0083] In this embodiment of the invention, the network device can be a device for communicating with mobile devices. The network device can be an access point (AP) in WLAN, a base station (BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved Node B (eNB or eNodeB) in LTE, a relay station or access point, or a vehicle-mounted device, wearable device, or a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or an NTN network, etc.

[0084] By way of example and not limitation, in this embodiment of the invention, the network device may have mobility characteristics; for example, the network device may be a mobile device. Optionally, the network device may be a satellite or a balloon station. For example, the satellite may be a low Earth orbit (LEO) satellite, a medium Earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station located on land, water, or other similar locations.

[0085] In this embodiment of the invention, a network device can provide services to a cell. A terminal device communicates with the network device through the transmission resources (e.g., frequency domain resources, or spectrum resources) used by the cell. The cell can be the cell corresponding to the network device (e.g., a base station). The cell can belong to a macro base station or to a base station corresponding to a small cell. The small cell can include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0086] The technical solutions of this invention can be applied to various communication systems, such as: Global System for Mobile Communication (GSM), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), General Packet Radio Service (GPRS), Long Term Evolution (LTE), Advanced Long Term Evolution (LTE-A), New Radio (NR), evolution systems of NR, LTE-based access to unlicensed spectrum (LTE-U), NR-based access to unlicensed spectrum (NR-U), Non-Terrestrial Networks (NTN), Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), and Wireless Fidelity. Fidelity (WiFi), 5th-Generation (5G) communication systems, or other communication systems.

[0087] Traditional communication systems typically support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication but also, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication. The embodiments of this invention can also be applied to these communication systems.

[0088] The communication system in this embodiment of the invention can be applied to carrier aggregation (CA) scenarios, dual connectivity (DC) scenarios, and standalone (SA) network deployment scenarios.

[0089] Optionally, the communication system in the embodiments of the present invention can be applied to unlicensed spectrum, wherein unlicensed spectrum can also be considered as shared spectrum; or, the communication system in the embodiments of the present invention can also be applied to licensed spectrum, wherein licensed spectrum can also be considered as non-shared spectrum.

[0090] Optionally, embodiments of the present invention can be applied to non-terrestrial network (NTN) systems or terrestrial network (TN) systems.

[0091] It should be understood that the terms "system" and "network" are often used interchangeably in this document. The term "and / or" in this document merely describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0092] It should be understood that the term "instruction" mentioned in the embodiments of the present invention can be a direct instruction, an indirect instruction, or an indication of an association. For example, A instructing B can mean that A directly instructs B, for example, B can be obtained through A; it can also mean that A indirectly instructs B, for example, A instructs C, B can be obtained through C; or it can mean that there is an association between A and B.

[0093] In the description of the embodiments of the present invention, the term "correspondence" may indicate that there is a direct or indirect correspondence between the two, or that there is an association between the two, or that there is a relationship of instruction and being instructed, configuration and being configured, etc.

[0094] Optionally, the indication information in the embodiments of the present invention includes at least one of physical layer signaling, such as Downlink Control Information (DCI), Radio Resource Control (RRC) signaling, and Media Access Control Element (MAC CE).

[0095] Optionally, the higher-layer parameters or higher-layer signaling in the embodiments of the present invention include at least one of Radio Resource Control (RRC) signaling and Media Access Control Control Element (MAC CE).

[0096] like Figure 8 As shown, an embodiment of the present invention provides a method for obtaining a reference signal, the method comprising:

[0097] 801. The first communication device sends a first reference signal to the second communication device.

[0098] 802. The second communication device receives the second reference signal.

[0099] The second reference signal is the reference signal received by the second communication device that corresponds to the first reference signal.

[0100] During the process of the first communication device sending the first reference signal to the second communication device, due to the influence of channel information and noise, the actual signal received by the second communication device is not consistent with the first reference signal sent by the transmitting end, and there will be a certain loss. In this embodiment of the invention, the signal actually received by the second communication device is referred to as the second reference signal.

[0101] The first reference signal is a sequence of reference signal symbols. Optionally, the first reference signal includes pilot symbols and data symbols, and can be a sequence of pilot symbols and data symbols (also known as a pilot symbol sequence), or the first reference signal includes data symbols, and can be a sequence of data symbols (also known as a data symbol sequence).

[0102] Optionally, the first reference signal is a sequence of data symbols, that is, the first reference signal may only include data symbols.

[0103] Optionally, the first reference signal is a sequence of data symbols, and at least one data symbol in the first reference signal is a pilot signal. That is, a portion of the data symbols (i.e., at least one data symbol) in the first reference signal is used as pilot symbols.

[0104] Optionally, the first communication device may also send a pilot signal indication to the second communication device, the pilot signal indication being used to indicate that the at least one data symbol is a pilot symbol.

[0105] Optionally, the pilot signal indicator can be an index of at least one data symbol.

[0106] Optionally, if the first communication device is a network device and the second communication device is a terminal device, then when the network device sends the aforementioned pilot signal indication to the terminal device, the pilot signal indication can be carried in at least one of the following messages:

[0107] Radio Resource Control (RRC) signaling, Media Access Control Unit (MAC) CE, and Downlink Control Information (DCI).

[0108] 803. The second communication device performs compression encoding on the second reference signal to obtain a compressed reference signal.

[0109] In one optional implementation: the second communication device can use a traditional compression method to compress the second reference signal to obtain a compressed reference signal.

[0110] In another optional implementation: the first communication device can input the compressed reference signal into the reference signal compression model; and acquire the compressed reference signal output by the reference signal compression model.

[0111] The reference signal compression model can be a model that has been pre-trained.

[0112] Optionally, during the training process, reference signals can be pre-collected as a training set. The sample reference signals in the training set are input into the reference signal compression model to be trained to obtain the compressed reference signal corresponding to the sample channel information. The compressed reference signal is then decoded and reconstructed to obtain the target reference signal. Based on the target reference signal and the sample reference signal, the loss function is determined. The initial reference signal compression model is then updated based on the loss function to obtain the trained reference signal compression model.

[0113] 804. The second communication device sends a compressed reference signal to the first communication device.

[0114] 805. The first communication device decodes and reconstructs the compressed reference signal to obtain the third reference signal.

[0115] Decoding and reconstruction is often referred to as decompression.

[0116] In one optional implementation: the first communication device decodes and reconstructs the compressed reference signal by using a traditional decompression method to obtain the third reference signal.

[0117] In another optional implementation: the first communication device inputs the compressed reference signal into the reference signal decompression model; and obtains the third reference signal output by the pilot signal decompression model.

[0118] 806. The first communication device performs channel estimation on the third reference signal to obtain the first channel information.

[0119] Optionally, channel estimation of the third reference signal to obtain the first channel information includes: inputting the third reference signal into the channel estimation model; and obtaining the first channel information output by the channel estimation model.

[0120] Furthermore, the first communication device can perform eigenvalue decomposition on the first channel information to obtain eigenvectors. These eigenvectors can be used for subsequent precoding of the modulation symbols.

[0121] Based on the above Figure 8 The scheme shown provides a CSI feedback scheme for compressed pilot signals, in which the first communication device can be regarded as the transmitter and the second communication device as the receiver.

[0122] like Figure 9 The diagram illustrates the overall signal flow of a CSI feedback scheme for compressed pilot signals. The flow includes: the transmitter first inserts a pilot symbol P into the allocated physical resource block and transmits it downlink to the receiver. After receiving the pilot signal Y_p, the receiver uses a neural network to compress and encode Y_p, generating a bit stream b, which is then fed back uplink to the transmitter via the feedback link. The transmitter uses the received feedback bit stream to decode and reconstruct the pilot signal using the neural network, generating the recovered pilot signal Y`_p. Further, the transmitter estimates the downlink channel through channel estimation to obtain the estimated channel H`. Finally, the estimated channel H` is processed through signal processing steps such as eigenvalue decomposition to obtain a precoding matrix, which is used for precoding operations in subsequent downlink transmissions.

[0123] In the above scheme, both pilot signal compression and pilot signal decompression can be achieved using existing AI-based pilot signal compression and decompression models.

[0124] In the above schemes, channel estimation can be implemented directly using traditional channel estimation schemes, or channel estimation can be implemented using AI-based channel estimation models.

[0125] The method for obtaining a reference signal provided in this embodiment of the invention involves a first communication device sending a first reference signal to a second communication device, followed by receiving a compressed reference signal sent by the second communication device. The compressed reference signal is obtained by compressing the second reference signal, which is the reference signal received by the second communication device corresponding to the first reference signal. The compressed reference signal is then decoded and reconstructed to obtain a third reference signal. Through this scheme, after the first communication device sends the first reference signal to the second communication device, the second communication device can send a compressed reference signal back to the first communication device. This allows the transmitting end to obtain the actual pilot signal received by the receiving end and thereby obtain channel information that more closely matches the actual pilot signal.

[0126] Furthermore, since the second communication device is a receiving device, it does not need to perform channel estimation in this embodiment of the invention, and its computing power requirements are low. Therefore, when the second communication device is a mobile phone, it can fully meet the computing power requirements. Thus, this solution does not have high hardware requirements and can be applied to more communication scenarios.

[0127] This invention mainly addresses the functional requirement of CSI feedback in communication systems. It considers directly compressing and feeding back the pilot signal after receiving it at the receiving end, and then performing channel estimation at the transmitting end to obtain channel information.

[0128] Compared to the traditional codebook CSI feedback scheme, it improves the accuracy of obtaining channel information;

[0129] Compared to existing neural network-based full-channel information feedback schemes, this solves the problem of redundant feedback;

[0130] Furthermore, it also alleviates the requirements for algorithm complexity and computing power for terminal devices in existing solutions.

[0131] Since the method for obtaining the reference signal provided in this embodiment of the invention considers compressing and feeding back the received pilot signal at the receiving end and performing channel estimation at the transmitting end, the receiving end does not need to know the pilot sequence. However, since the transmitting end knows both the pilot and the data, more flexible pilot design and insertion can be considered. Because this scheme considers performing channel estimation at the transmitting end, i.e., the pilot sequence information does not need to be known at the receiving end, the following design points for inserting the pilot module can be considered, including: a pilot design scheme based on neural networks and a pilotless scheme based on data.

[0132] (1) Pilot design scheme based on neural network

[0133] Optionally, after step 806 above, the method provided in this embodiment of the invention further includes: the first communication device can input the first channel information into the first pilot design model; and obtain the first pilot signal output by the first pilot design model; and the first communication device sends the first pilot signal to the second communication device.

[0134] Optionally, for the aforementioned first pilot design model, the first communication device may use the sample channel information in the training set to train an initial pilot design model to obtain the first pilot design model.

[0135] The training set includes information from multiple sample channels.

[0136] Optionally, the training process of training the initial pilot design model using sample channel information from the training set includes:

[0137] After repeating steps 1 to 5 one or more times, the updated initial pilot reference model is used as the first pilot device model:

[0138] Step 1: Input the sample channel information from the training set into the initial pilot design model to obtain the second pilot signal corresponding to the sample channel information. The second pilot signal is a sequence including pilot symbols and data symbols.

[0139] Step 2: Process the second pilot signal based on the sample channel information and noise to obtain the third pilot signal;

[0140] Step 3: Perform channel estimation on the third pilot signal to obtain the target channel information;

[0141] Step 4: Determine the loss function based on the target channel information and the sample channel information;

[0142] Step 5: Update the initial pilot design model based on the loss function.

[0143] Optionally, the noise can be noise that simulates the actual channel between the transmitter and receiver.

[0144] Multiple sample channel information from the training set can be input into the initial pilot design model one by one, and the training process of training the initial pilot design model using the sample channel information from the training set can be repeated to complete the training of the initial pilot design model and obtain the first pilot design model.

[0145] Optionally, the sample channel information in the above sample set can be historical channel information.

[0146] like Figure 10 The diagram illustrates the training phase of a pilot design model. The pilot design model is an AI-based pilot design module. The input to the pilot design module is the previously estimated channel information, and the output is a pilot sequence. During the training phase, the channel H from the pre-collected training set is first fed into the pilot design module. The output pilot sequence P, after passing through the channel and random noise, is input into the AI-based channel estimation module (i.e., the channel estimation model). Finally, the estimated channel information H' is obtained. H' is compared with H to obtain a loss function, which is then used to update the AI-based pilot design model. After end-to-end training using this framework, a trained AI-based pilot design module is obtained.

[0147] Furthermore, such as Figure 11 The diagram shown illustrates the application stage of a pilot design model. The input to the AI-based pilot design module is the channel H' previously estimated by the transmitter. After pilot design using this module, the pilot sequence P is obtained.

[0148] (2) Pilot-free scheme

[0149] Since the channel estimation process in this invention is performed at the transmitting end, and the transmitted data symbols are known at the transmitting end, the transmitted data symbols can be used as pilot sequences for corresponding channel estimation, so there is no need to insert pilot symbols on the time-frequency resource block.

[0150] Optionally, the first reference signal is a sequence of data symbols, and at least one data symbol in the first reference signal is a pilot signal.

[0151] Optionally, in the above pilotless scheme, the transmitting end can send a pilot signal indication to the receiving end. The pilot signal indication is used to indicate that at least one data symbol is a pilot signal. Specifically, the index of at least one data symbol can be indicated so that the receiving end can know that at least one data symbol is a pilot signal.

[0152] The above-mentioned pilot-free scheme can reduce pilot overhead because it does not require the insertion of pilot symbols on the time-frequency resource block.

[0153] like Figure 12 As shown, an embodiment of the present invention provides a first communication device, the first communication device comprising:

[0154] The receiving module 1201 is used to receive a compressed reference signal sent by the second communication device after sending a first reference signal to the second communication device. The compressed reference signal is obtained by compressing and encoding the second reference signal. The second reference signal is a reference signal received by the second communication device that corresponds to the first reference signal.

[0155] The processing module 1202 is used to decode and reconstruct the compressed reference signal to obtain the third reference signal.

[0156] Optionally, processing module 1202 is specifically used for:

[0157] The compressed reference signal is input into the reference signal decompression model;

[0158] Obtain the third reference signal output from the pilot signal decompression model.

[0159] Optionally, the processing module 1202 is also used for:

[0160] Channel estimation is performed on the third reference signal to obtain the first channel information.

[0161] Optionally, the processing module 1202 is specifically used for:

[0162] Input the third reference signal into the channel estimation model;

[0163] Obtain the first channel information output by the channel estimation model.

[0164] Optionally, the processing module 1202 is also used for:

[0165] The first channel information is decomposed into eigenvalues ​​to obtain eigenvectors, which are used for precoding the modulation symbols.

[0166] Optionally, the processing module 1202 is also used for:

[0167] Input the first channel information into the first pilot design model;

[0168] Obtain the first pilot signal output from the first pilot design model;

[0169] Optional, also includes:

[0170] The transmitting module 1203 is used to transmit a first pilot signal to the second communication device.

[0171] Optionally, the processing module 1202 is also used for:

[0172] The initial pilot design model is trained using the sample channel information in the training set to obtain the first pilot design model.

[0173] Optionally, the processing module 1202 is specifically used for:

[0174] The sample channel information from the training set is input into the initial pilot design model to obtain the second pilot signal corresponding to the sample channel information;

[0175] Based on the sample channel information and noise, the second pilot signal is processed to obtain the third pilot signal;

[0176] Channel estimation is performed on the third pilot signal to obtain the target channel information;

[0177] The loss function is determined based on the target channel information and the sample channel information;

[0178] Update the initial pilot design model based on the loss function;

[0179] The first pilot design model is obtained based on the updated initial pilot design model.

[0180] Optionally, the first reference signal includes pilot symbols and data symbols, or the first reference signal includes data symbols.

[0181] Optionally, the first reference signal includes data symbols, and at least one data symbol in the first reference signal serves as a pilot symbol.

[0182] Optional, also includes:

[0183] The transmitting module 1203 is used to transmit a pilot signal indication to the second communication device, wherein the pilot signal indication is used to indicate at least one data symbol as a pilot symbol.

[0184] Optionally, the first communication device is a network device, and the pilot signal indication is carried in at least one of the following messages:

[0185] Radio Resource Control (RRC) signaling, Media Access Control Unit (MAC) CE, and Downlink Control Information (DCI).

[0186] like Figure 13 As shown, embodiments of the present invention also provide a second communication device, the second communication device comprising:

[0187] The receiving module 1301 is used to receive a second reference signal, which corresponds to a first reference signal sent by the first communication device.

[0188] Processing module 1302 is used to perform compression encoding processing on the second reference signal to obtain a compressed reference signal;

[0189] The transmitting module 1303 is used to transmit a compressed reference signal to the first communication device.

[0190] Optionally, the first reference signal includes data symbols, and at least one data symbol in the first reference signal serves as a pilot signal.

[0191] Optionally, the receiving module 1301 is further configured to receive a pilot signal indication sent by the first communication device, the pilot signal indication being used to indicate at least one data symbol as a pilot symbol.

[0192] Optionally, the first communication device is a network device, and the pilot signal indication is carried in at least one of the following messages:

[0193] Radio Resource Control (RRC) signaling, Media Access Control Unit (MAC) CE, and Downlink Control Information (DCI).

[0194] like Figure 14 As shown in the diagram, this embodiment of the invention also provides a hardware structure diagram of a communication device. The communication device may include components such as a radio frequency (RF) circuit 1410, a memory 1420, and a processor 1430. The RF circuit 1410 includes a receiver 1411 and a transmitter 1412. Those skilled in the art will understand that... Figure 14 The structure of the communication device shown does not constitute a limitation on the communication device. It may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0195] RF circuit 1410 can be used for receiving and transmitting signals during information transmission or calls. Specifically, it receives downlink information from the base station and processes it with processor 1430; additionally, it transmits uplink data to the base station. Typically, RF circuit 1410 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier (LNA), a duplexer, etc. Furthermore, RF circuit 1410 can also communicate wirelessly with networks and other devices. The aforementioned wireless communication can use any communication standard or protocol, including but not limited to Global System for Mobile Communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Message Service (SMS), etc.

[0196] The memory 1420 can be used to store software programs and modules. The processor 1430 executes various functional applications and data processing of the communication device by running the software programs and modules stored in the memory 1420. The memory 1420 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the communication device (such as audio data, telephone directory, etc.). In addition, the memory 1420 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0197] The processor 1430 is the control center, connecting various parts of the communication device through various interfaces and lines. It performs various functions and processes data by running or executing software programs and / or modules stored in the memory 1420 and calling data stored in the memory 1420, thereby providing overall monitoring of the communication device. Optionally, the processor 1430 may include one or more processing units; preferably, the processor 1430 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1430.

[0198] Optional, if Figure 14 The communication device shown is the first communication device. In this embodiment of the invention, the receiver 1411 in the radio frequency circuit 1410 is used to receive the compressed reference signal sent by the second communication device after the transmitter 1412 sends the first reference signal to the second communication device. The compressed reference signal is obtained by compressing and encoding the second reference signal. The second reference signal is the reference signal received by the second communication device that corresponds to the first reference signal.

[0199] Processor 1430 is used to decode and reconstruct the compressed reference signal to obtain a third reference signal.

[0200] Optionally, the processor 1430 is specifically used for:

[0201] The compressed reference signal is input into the reference signal decompression model;

[0202] Obtain the third reference signal output from the pilot signal decompression model.

[0203] Optionally, the processor 1430 is also used for:

[0204] Channel estimation is performed on the third reference signal to obtain the first channel information.

[0205] Optionally, the processor 1430 is specifically used to: input the third reference signal into the channel estimation model;

[0206] Obtain the first channel information output by the channel estimation model.

[0207] Optionally, the processor 1430 is also used for:

[0208] The first channel information is decomposed into eigenvalues ​​to obtain eigenvectors, which are used for precoding the modulation symbols.

[0209] Optionally, the processor 1430 is also used for:

[0210] Input the first channel information into the first pilot design model;

[0211] Obtain the first pilot signal output from the first pilot design model;

[0212] Transmitter 1412 is also used to transmit a first pilot signal to a second communication device.

[0213] Optionally, the processor 1430 is also used for:

[0214] The initial pilot design model is trained using the sample channel information in the training set to obtain the first pilot design model.

[0215] Optionally, the processor 1430 is specifically used to: input the sample channel information from the training set into the initial pilot design model to obtain the pilot symbol sequence corresponding to the sample channel information;

[0216] Based on the sample channel information and noise, the pilot symbol sequence is processed to obtain the pilot signal;

[0217] Channel estimation is performed on the pilot signal to obtain the target channel information;

[0218] The loss function is determined based on the target channel information and the sample channel information;

[0219] Update the initial pilot design model based on the loss function;

[0220] The first pilot design model is obtained based on the updated initial pilot design model.

[0221] Optionally, the first reference signal includes pilot symbols and data symbols, or the first reference signal includes data symbols.

[0222] Optionally, the first reference signal includes data symbols, and at least one data symbol in the first reference signal is a pilot signal.

[0223] Optional, also includes:

[0224] Transmitter 1412 is used to transmit a pilot signal indication to a second communication device, the pilot signal indication being used to indicate at least one data symbol.

[0225] Optionally, the first communication device is a network device, and the pilot signal indication is carried in at least one of the following messages:

[0226] Radio Resource Control (RRC) signaling, Media Access Control Unit (MAC) CE, and Downlink Control Information (DCI).

[0227] Optional, such as Figure 14If the communication device shown is the second communication device, then in this embodiment of the invention, the receiver 1411 in the radio frequency circuit 1410 is used to receive the second reference signal, which corresponds to the first reference signal sent by the first communication device.

[0228] Processor 1430 is used to perform compression encoding processing on the second reference signal to obtain a compressed reference signal;

[0229] Transmitter 1412 is used to send a compressed reference signal to the first communication device.

[0230] Optionally, the first reference signal includes data symbols, and at least one data symbol in the first reference signal is a pilot signal.

[0231] Optionally, receiver 1411 is also configured to receive a pilot signal indication sent by the first communication device, the pilot signal indication being used to indicate at least one data symbol.

[0232] Optionally, the first communication device is a network device, and the pilot signal indication is carried in at least one of the following messages:

[0233] Radio Resource Control (RRC) signaling, Media Access Control Unit (MAC) CE, and Downlink Control Information (DCI).

[0234] This invention also provides a computer-readable storage medium, including: computer instructions that, when executed on a processor, cause the processor to perform various processes of the communication device as described in the above method embodiments.

[0235] This invention also provides a computer program product, including computer instructions. When the computer program product is run on a processor, the computer instructions are executed to implement the various processes of the communication device described in the above method embodiments.

[0236] This invention also provides a chip coupled to a memory in a communication device, such that the chip, during operation, calls program instructions stored in the memory, causing the communication device to execute various processes of the communication device as described in the above method embodiments.

[0237] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state disk (SSD)).

[0238] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

Claims

1. A method for acquiring a reference signal, characterized in that, Applied to a first communication device, including: After sending a first reference signal to the second communication device, a compressed reference signal sent by the second communication device is received. The compressed reference signal is obtained by compressing and encoding the second reference signal. The second reference signal is a reference signal received by the second communication device that corresponds to the first reference signal. The second reference signal is the signal actually received by the second communication device after the first reference signal is affected by channel information and noise during transmission. The compressed reference signal is decoded and reconstructed to obtain the third reference signal; Wherein, the first reference signal includes data symbols, and at least one data symbol in the first reference signal serves as a pilot symbol; The method further includes: Send a pilot signal indication to the second communication device, the pilot signal indication being used to indicate that the at least one data symbol is a pilot symbol; The pilot signal indicates an index of at least one data symbol.

2. The method according to claim 1, characterized in that, The step of decoding and reconstructing the compressed reference signal to obtain the third reference signal includes: The compressed reference signal is input into the reference signal decompression model; Obtain the third reference signal output by the pilot signal decompression model.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Channel estimation is performed on the third reference signal to obtain the first channel information.

4. The method according to claim 3, characterized in that, The process of performing channel estimation on the third reference signal to obtain first channel information includes: The third reference signal is input into the channel estimation model; Obtain the first channel information output by the channel estimation model.

5. The method according to claim 3, characterized in that, The method further includes: The first channel information is decomposed into eigenvalues ​​to obtain a feature vector, which is used to precode the modulation symbols.

6. The method according to claim 3, characterized in that, The method further includes: Input the first channel information into the first pilot design model; Obtain the first pilot signal output by the first pilot design model; The first pilot signal is sent to the second communication device.

7. The method according to claim 6, characterized in that, The method further includes: Using the sample channel information in the training set, an initial pilot design model is trained to obtain the first pilot design model.

8. The method according to claim 7, characterized in that, The step of training the initial pilot design model using sample channel information from the training set to obtain the first pilot design model includes: The sample channel information in the training set is input into the initial pilot design model to obtain the second pilot signal corresponding to the sample channel information; Based on the sample channel information and noise, the second pilot signal is processed to obtain the third pilot signal; Channel estimation is performed on the third pilot signal to obtain the target channel information; The loss function is determined based on the target channel information and the sample channel information; The initial pilot design model is updated based on the loss function; The first pilot design model is obtained based on the updated initial pilot design model.

9. The method according to claim 1, characterized in that, The first communication device is a network device, and the pilot signal indicates that it is carried in at least one of the following messages: Radio Resource Control (RRC) signaling, Media Access Control Unit (MAC) CE, and Downlink Control Information (DCI).

10. A method for acquiring a reference signal, characterized in that, Applied to a second communication device, including: Receive a second reference signal, which corresponds to a first reference signal sent by the first communication device. The second reference signal is the signal actually received by the second communication device after the first reference signal is affected by channel information and noise during transmission. The second reference signal is compressed and encoded to obtain a compressed reference signal. Send the compressed reference signal to the first communication device; Wherein, the first reference signal includes data symbols, and at least one data symbol in the first reference signal serves as a pilot symbol; The method further includes: Receive pilot signal indication sent by the first communication device, the pilot signal indication being used to indicate that the at least one data symbol is a pilot signal; The pilot signal indicates an index of at least one data symbol.

11. The method according to claim 10, characterized in that, The first communication device is a network device, and the pilot signal indicates that it is carried in at least one of the following messages: Radio Resource Control (RRC) signaling, Media Access Control Unit (MAC) CE, and Downlink Control Information (DCI).

12. A first communication device, characterized in that, include: A receiver is configured to receive a compressed reference signal sent by the second communication device after sending a first reference signal to the second communication device. The compressed reference signal is obtained by compressing and encoding the second reference signal. The second reference signal is a reference signal received by the second communication device that corresponds to the first reference signal. The second reference signal is the signal actually received by the second communication device after the first reference signal is affected by channel information and noise during transmission. A processor is configured to decode and reconstruct the compressed reference signal to obtain a third reference signal; Wherein, the first reference signal includes data symbols, and at least one data symbol in the first reference signal serves as a pilot symbol; The first communication device further includes a transmitter for sending a pilot signal indication to the second communication device. The pilot signal indication is used to instruct the at least one data symbol to send a pilot signal indication to the second communication device, and the pilot signal indication is used to instruct the at least one data symbol to act as a pilot symbol. The pilot signal indicates an index of at least one data symbol.

13. The first communication device according to claim 12, characterized in that, The processor is specifically used for: The compressed reference signal is input into the reference signal decompression model; Obtain the third reference signal output by the pilot signal decompression model.

14. The first communication device according to claim 12 or 13, characterized in that, The processor is also used for: Channel estimation is performed on the third reference signal to obtain the first channel information.

15. The first communication device according to claim 14, characterized in that, The processor is specifically used to: input the third reference signal into the channel estimation model; Obtain the first channel information output by the channel estimation model.

16. The first communication device according to claim 14, characterized in that, The processor is also used for: The first channel information is decomposed into eigenvalues ​​to obtain a feature vector, which is used to precode the modulation symbols.

17. The first communication device according to claim 14, characterized in that, The processor is also configured to: input the first channel information into the first pilot design model; Obtain the first pilot signal output by the first pilot design model; Also includes: A transmitter is used to send the first pilot signal to the second communication device.

18. The first communication device according to claim 17, characterized in that, The processor is also used for: The initial pilot design model is trained using sample channel information from the training set to obtain the first pilot design model.

19. The first communication device according to claim 18, characterized in that, The processor is specifically used for: The sample channel information in the training set is input into the initial pilot design model to obtain the second pilot signal corresponding to the sample channel information; Based on the sample channel information and noise, the second pilot signal is processed to obtain the third pilot signal; Channel estimation is performed on the third pilot signal to obtain the target channel information; The loss function is determined based on the target channel information and the sample channel information; The initial pilot design model is updated based on the loss function; The first pilot design model is obtained based on the updated initial pilot design model.

20. The first communication device according to claim 12, characterized in that, The first communication device is a network device, and the pilot signal indicates that it is carried in at least one of the following messages: Radio Resource Control (RRC) signaling, Media Access Control Unit (MAC) CE, and Downlink Control Information (DCI).

21. A second communication device, characterized in that, include: A receiver is used to receive a second reference signal, which corresponds to a first reference signal sent by a first communication device. The second reference signal is the signal actually received by the second communication device after the first reference signal is affected by channel information and noise during transmission. The processor is used to perform compression encoding processing on the second reference signal to obtain a compressed reference signal; A transmitter is used to send the compressed reference signal to the first communication device; Wherein, the first reference signal includes data symbols, and at least one data symbol in the first reference signal serves as a pilot symbol; The receiver is further configured to receive a pilot signal indication sent by the first communication device, the pilot signal indication being used to indicate the at least one data symbol; The pilot signal indicates an index of at least one data symbol.

22. The second communication device according to claim 21, characterized in that, The first communication device is a network device, and the pilot signal indicates that it is carried in at least one of the following messages: Radio Resource Control (RRC) signaling, Media Access Control Unit (MAC) CE, and Downlink Control Information (DCI).

23. A first communication device, characterized in that, include: The receiving module is configured to receive a compressed reference signal sent by the second communication device after sending a first reference signal to the second communication device. The compressed reference signal is obtained by compressing and encoding the second reference signal. The second reference signal is a reference signal received by the second communication device that corresponds to the first reference signal. The second reference signal is the signal actually received by the second communication device after the first reference signal is affected by channel information and noise during transmission. The processing module is used to decode and reconstruct the compressed reference signal to obtain a third reference signal; Wherein, the first reference signal includes data symbols, and at least one data symbol in the first reference signal serves as a pilot symbol; The first communication device further includes: The transmitting module is configured to transmit a pilot signal indication to the second communication device, the pilot signal indication being used to indicate that the at least one data symbol is a pilot symbol; The pilot signal indicates an index of at least one data symbol.

24. A second communication device, characterized in that, include: A receiving module is used to receive a second reference signal, which corresponds to a first reference signal sent by a first communication device. The second reference signal is the signal actually received by the second communication device after the first reference signal is affected by channel information and noise during transmission. The processing module is used to perform compression encoding processing on the second reference signal to obtain a compressed reference signal; The transmitting module is used to transmit the compressed reference signal to the first communication device; Wherein, the first reference signal includes data symbols, and at least one data symbol in the first reference signal serves as a pilot symbol; The receiving module is further configured to receive a pilot signal indication sent by the first communication device, wherein the pilot signal indication is used to indicate that the at least one data symbol is a pilot symbol; The pilot signal indicates an index of at least one data symbol.

25. A computer-readable storage medium, characterized in that, Includes computer instructions that, when executed on a processor, cause the processor to perform the method of acquiring a reference signal as described in any one of claims 1 to 11.

Images