WO2023004563A1

WO2023004563A1 - Method for obtaining reference signal and communication devices

Info

Publication number: WO2023004563A1
Application number: PCT/CN2021/108570
Authority: WO
Inventors: 肖寒; 田文强; 刘文东
Original assignee: Oppo广东移动通信有限公司
Priority date: 2021-07-27
Filing date: 2021-07-27
Publication date: 2023-02-02
Also published as: CN117044145A

Abstract

Embodiments of the present invention are applied to the technical field of communications, and provide a method for obtaining a reference signal, a terminal device, and a network device. The embodiments of the present invention comprise: after sending a first reference signal to a second communication device, receiving a compressed reference signal sent by the second communication device, the compressed reference signal being obtained by compressing and encoding a second reference signal, the second reference signal being a reference signal corresponding to the first reference signal received by the second communication device; and decoding and reconstructing the compressed reference signal to obtain a third reference signal.

Description

Method and communication device for obtaining reference signal

technical field

The present invention relates to the field of communication technology, in particular to a method for acquiring a reference signal and a communication device.

Background technique

At present, during the transmission process of sending the pilot signal symbol sequence from the sending end to the receiving end, due to the influence of channel information and noise, the actual pilot signal received by the receiving end is not consistent with the pilot signal symbol sequence sent by the sending end, so the sending end The end needs the receiver to feed back channel information so that the sender can combine the actual channel information for subsequent precoding, so the sender knows the actual pilot signal of the receiver, or the sender knows that the feedback from the receiver matches the actual pilot signal better channel information is an urgent problem to be solved.

Contents of the invention

Embodiments of the present invention provide a method for obtaining a reference signal and a communication device. 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.

In the first aspect, a method for obtaining a reference signal is provided, including:

After sending the first reference signal to the second communication device, receiving the compressed reference signal sent by 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 corresponding to the first reference signal received by the second communication device;

The compressed reference signal is decoded and reconstructed to obtain a third reference signal.

In the second aspect, a method for obtaining a reference signal is provided, including:

The receiver is configured to receive the compressed reference signal sent by the second communication device after sending the first reference signal to the second communication device, where the compressed reference signal is obtained by compressing and encoding the second reference signal, the The second reference signal is a reference signal received by the second communication device and corresponding to the first reference signal;

A processor, configured to decode and reconstruct the compressed reference signal to obtain a third reference signal.

In a third aspect, a first communication device is provided, including:

In a fourth aspect, a second communication device is provided, including:

a receiver, configured to receive a second reference signal corresponding to the first reference signal sent by the first communication device;

a processor, configured to perform compression coding processing on the second reference signal to obtain a compressed reference signal;

A transmitter, configured to send the compressed reference signal to the first communication device. In a fifth aspect, a first communication device is provided, including:

The receiving module is configured to receive the compressed reference signal sent by the second communication device after sending the first reference signal to the second communication device, the compressed reference signal is obtained by compressing and encoding the second reference signal, the The second reference signal is a reference signal received by the second communication device and corresponding to the first reference signal;

A processing module, configured to decode and reconstruct the compressed reference signal to obtain a third reference signal.

In a sixth aspect, a second communication device is provided, including:

A receiving module, configured to receive a second reference signal, where the second reference signal corresponds to the first reference signal sent by the first communication device;

A processing module, configured to compress and encode the second reference signal to obtain a compressed reference signal;

A sending module, configured to send the compressed reference signal to the first communication device.

In a seventh aspect, there is provided a computer-readable storage medium, comprising: computer instructions, when the computer instructions are run on a computer, the computer is made to execute the method of the first aspect above.

In an eighth aspect, there is provided a computer-readable storage medium, including: computer instructions, which, when run on a computer, cause the computer to execute the method of the second aspect above.

In a ninth aspect, a computer program product is provided, including computer instructions. When the computer program product runs on a computer, the computer executes the computer instructions, so that the computer executes the method in the first aspect above.

In a tenth aspect, a computer program product is provided, including computer instructions. When the computer program product runs on a computer, the computer executes the computer instructions, so that the computer executes the method of the second aspect above.

An embodiment of the present invention provides a method for obtaining a reference signal. After the first communication device sends the first reference signal to the second communication device, it receives the compressed reference signal sent by the second communication device, and the compressed reference signal is a reference signal for the second reference signal. The second reference signal obtained after compression and encoding is a reference signal corresponding to the first reference signal received by the second communication device; the compressed reference signal is 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 the compressed reference signal to the first communication device, so that the sending end can obtain the actual pilot signal received by the receiving end, In this way, channel information more matching with the actual pilot signal is obtained.

Description of drawings

FIG. 1 is a schematic diagram of a basic workflow of a wireless communication system provided by an embodiment of the present invention;

FIG. 2 is a schematic diagram of a channel estimation and restoration process provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of the basic structure of a neural network provided by an embodiment of the present invention;

FIG. 4A is a schematic diagram of a convolutional neural network provided by an embodiment of the present invention;

FIG. 4B is a schematic diagram of an LSTM model provided by an embodiment of the present invention;

FIG. 5 is a schematic diagram of a channel estimation process of a neural network provided by an embodiment of the present invention;

FIG. 6 is a schematic diagram of a channel feedback process of a neural network provided by an embodiment of the present invention;

FIG. 7 is a schematic diagram of a channel information feedback system provided by an embodiment of the present invention;

FIG. 8 is a schematic diagram of a method for acquiring a reference signal provided by an embodiment of the present invention;

FIG. 9 is a schematic diagram of an overall signal flow of a CSI feedback scheme for compressed pilot signals provided by an embodiment of the present invention;

FIG. 10 is a schematic diagram of a training phase of a pilot design module provided by an embodiment of the present invention;

FIG. 11 is a schematic diagram of an application phase of a pilot design model provided by an embodiment of the present invention;

FIG. 12 is a schematic structural diagram of a first communication device provided by an embodiment of the present invention;

FIG. 13 is a schematic structural diagram of a second communication device provided by an embodiment of the present invention;

Fig. 14 is a schematic structural diagram of a communication device provided by an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

In the embodiments of the present invention, words such as "exemplary" or "for example" are used as examples, illustrations or illustrations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present invention shall not be construed as being more preferred or more advantageous than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete manner.

The term "and/or" in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and/or B can mean: A exists alone, A and B exist simultaneously, and there exists alone B these three situations. The symbol "/" in this document indicates that the associated object is an or relationship, for example, A/B indicates A or B.

The relevant technologies and terms involved in the embodiments of the present invention are briefly described below:

1. Overall description of the wireless communication system

As shown in Figure 1, it is the basic work flow in the wireless communication system, and the main flow includes:

The transmitter (that is, the transmitting end device) 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 transmission The signal passes through the channel to the receiver.

The receiver (that is, the receiving end device) receives the signal and uses the pilot frequency to perform channel estimation; then the channel information is fed back to the transmitter through the feedback link, so that the transmitter can adjust the channel coding method, modulation method, and precoding method, etc.; finally The receiver obtains the final restored bit stream through the steps of symbol detection, demodulation and channel decoding and reconstruction. Wherein, the channel information involved in the embodiment of the present invention may be channel state information (Channel-State Information, CSI).

Fig. 1 is a simple illustration of the basic work flow in the wireless communication system, and there may be other unlisted modules and work flow in the traditional communication system. For example, it may also include functional modules such as resource mapping, precoding, interference cancellation, and CSI measurement. These modules may be designed and implemented separately, and these independent modules may be integrated to form a complete wireless communication system.

2. Channel estimation

Due to the complexity and time-varying nature of the wireless channel environment, in the above wireless communication system as shown in FIG. 1 , the receiver's estimation and recovery of the wireless channel directly affects the data recovery performance of the final recovered bit stream.

The channel estimation and recovery process in the current communication system is shown in Figure 2:

For the channel transmission stage: In addition to the information data symbols (that is, the data symbols shown in Figure 2), the transmitter will also send a series of specific pilot symbols known to the receiver (that is, the data symbols shown in Figure 2) on the time-frequency resources Reference signal symbol), such as channel information reference signal (Channel-State Information Reference Signal, CSI-RS) signal, demodulation reference signal (Demodulation Reference Signal, DMRS) signal, etc.

For the channel estimation stage: the receiver can use the least square method (also called LS method) to estimate the channel information at the position of the reference signal according to the real pilot and the received pilot;

For the channel recovery stage: the receiver uses the interpolation algorithm to recover the channel information on the full time-frequency resource according to the channel information estimated at the pilot position, which is used for subsequent channel information feedback or data recovery.

3. Channel feedback

For the 5G New Radio (NR) system, in the current CSI feedback design, the codebook-based scheme is mainly used to realize the extraction and feedback of channel features. That is, after the channel estimation is performed at the transmitting end, according to the result of the channel estimation, a precoding matrix matching the current channel is selected from the pre-set precoding codebook according to a certain optimization criterion, and the index of the matrix is passed through the feedback link of the air interface The information precoding matrix indicator (Precoding Matrix Indicator, PMI) is fed back to the receiving end for the receiving end to implement precoding, and the channel quality indication (Channel Quality Indication, CQI) obtained according to the measurement is also fed back to the receiving end for the receiving end Realize adaptive modulation and coding, etc.

4. Neural network

In recent years, artificial intelligence research represented by neural networks (Neural Networks, NN) has achieved great results in many fields, and it will also play an important role in people's production and life for a long time in the future.

As shown in Figure 3, the basic structure of a neural network includes: input layer, hidden layer and output layer. The input layer is responsible for receiving data, the hidden layer is responsible for processing the data, and the final result is generated in the output layer. Among them, each node represents a processing unit, which can be regarded as simulating a neuron. Multiple neurons form a layer of neural network, and multi-layer information transmission and processing construct an overall neural network.

With the continuous development of neural network research, neural network deep learning algorithms have been proposed in recent years, more hidden layers have been introduced, and feature learning is performed through layer-by-layer training of neural networks with multiple hidden layers, which greatly improves the learning of neural networks. And processing capabilities, and are widely used in pattern recognition, signal processing, optimization combination, anomaly detection, etc.

Similarly, with the development of deep learning, Convolutional Neural Networks (CNN) have also been proposed in recent years. As shown in FIG. 4A , it is a schematic diagram of a convolutional neural network. The basic structure of the convolutional neural network includes: an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer. In the convolutional neural network, the introduction of the convolutional layer and the pooling layer effectively controls the sharp increase of network parameters, limits the number of parameters and taps the characteristics of the local structure, which improves the robustness of the algorithm.

As shown in Figure 4B, a recurrent neural network (Recurrent Neural Network, RNN) is a type of recurrent neural network that takes sequence data as input, recurses in the evolution direction of the sequence, and connects all nodes (recurrent units) in a chain. As the most commonly used and traditional deep learning model in natural language processing (NLP), the RNN network reads sequence data in order and processes them step by step. Similar to human understanding of text, it is a word, a sentence to understand of. Long Short-Term Memory (LSTM) is a kind of variant model of RNN. As shown in Figure 4B, it is a schematic diagram of an LSTM model. The essence of this model is that it introduces the concept of cell state, which is different from RNN Only considering the recent state, the cell state of LSTM will determine which states are kept and which states can be ignored, which solves the defects of traditional RNN in long-term memory. Among them, Xt-1, Xt and Xt+1 are three consecutive inputs, ht-1, ht and ht+1 are three consecutive outputs, tanh represents the neural network layer with tanh as the activation function, and σ represents sigmoid as the activation function neural network layers.

5. Channel estimation based on neural network

The existing neural network-based channel estimation considers the use of artificial intelligence (AI) to realize channel estimation and recovery. As shown in Figure 5, it is a schematic diagram of the channel estimation process of a neural network, wherein the reference signal is input into the AI-based channel estimation and recovery module and then outputs information, and the output information is the result of channel estimation and recovery (that is, in Figure 5 channel recovery results). It should be noted here that for the input information of the AI-based channel estimation and recovery module here, in addition to the reference signal, other auxiliary information can also be added to improve the performance of the AI-based channel estimation and recovery module. For example, these other auxiliary information may be feature extraction information, energy level information, delay feature information, noise feature information, etc. for the reference signal.

6. Channel feedback based on neural network

In view of the great success of AI technology in computer vision, natural language processing, etc., the communication field has begun to try to use AI technology to find new technical ideas to solve technical problems that are limited by traditional methods, such as deep learning. The neural network architecture commonly used in deep learning is nonlinear and data-driven. It can extract features from the actual channel matrix data and restore the channel matrix information compressed and fed back from the user equipment (UE) side as much as possible on the base station side. It also provides the possibility to reduce the CSI feedback overhead on the UE side while ensuring the restoration of channel information.

As shown in Figure 6, it is a schematic diagram of the channel feedback process of a neural network. The channel information can be regarded as the channel image to be compressed, assuming that the channel image is a 28×28=784 image, and the deep learning autoencoder is used to analyze the channel The information is compressed and fed back to the peer device of the current device, and then the compressed channel image is reconstructed in the peer device, which can retain the channel information to a greater extent and obtain the reconstructed channel image.

As shown in FIG. 7 , it is a schematic diagram of a channel information feedback system. The channel information feedback system is divided into an encoder and a decoder, wherein the encoder is deployed at the sending end (the receiver shown in Figure 1), and the decoder is deployed at the receiving end (the transmitter shown in Figure 1 ). After the sender obtains the channel information through channel estimation, the channel information matrix is convoluted through the convolutional layer in the neural network of the encoder to obtain a 32×32 encoding matrix, and then the N×1 encoding matrix is obtained through dimension conversion, and then further The N×1 encoding matrix is compressed and converted into an M×1 encoding matrix through the fully connected layer, where M is less than N, and the compressed encoding is completed, and the compressed encoded bit stream is fed back to the receiving end through the air interface feedback link, and the receiving end The decoder restores the channel information according to the feedback bit stream to obtain complete feedback channel information. Specifically, the received M×1 encoding matrix can be restored to an N×1 feature map first, and then the N×1 feature map can be converted into a 32×32 feature map encoding matrix, and the convolution and addition After summing, the convolution and summation operations are repeated to obtain the restored channel information and output it. As shown in Figure 7, several fully connected layers can be used in the encoder for encoding, and the residual network structure can be used for decoding in the decoder. Among them, the network model structure inside the encoder and decoder can be flexibly designed under the condition that the encoding and decoding framework remains unchanged.

The channel information feedback in the current 5G NR standard is a codebook-based feedback scheme. However, the codebook-based feedback scheme is to select the optimal channel information eigenvalue vector from the codebook according to the estimated channel. Due to the limitation of the codebook itself, the channel information from the estimated channel information to the channel information in the codebook The mapping process is quantized and lossy, which reduces the accuracy of the final feedback channel information, thereby reducing the performance of precoding.

In an optional embodiment, a neural network-based channel information feedback scheme is introduced, which can directly encode and compress the channel information obtained after channel estimation, that is, the feedback is full channel information, which can alleviate the codebook-based The accuracy of the program. However, since the full channel information is recovered and received at the sending end, it is still necessary to perform eigenvalue decomposition on the full channel information matrix to obtain eigenvectors and use them for beamforming. Therefore, compared with directly compressing the eigenvectors, the compression of the full channel Too much redundant information in the information reduces the compression efficiency.

In another optional embodiment, a scheme of using a neural network to directly compress and feed back feature vectors is introduced. This scheme can divide the sub-carriers of the scheduling bandwidth into multiple groups, which correspond to multiple sub-band channels. After the channel estimation at the receiving end according to the received pilot signal to obtain the full channel information, the eigenvalue decomposition can be performed to obtain the eigenvector. And feed back the eigenvectors of each sub-band channel separately. However, with the improvement of precoding precision requirements, the granularity of sub-band channel division is finer, and the number of sub-band channels is also increased, and the overhead of feedback is still very large.

Since the receiving end is often a terminal device such as a mobile phone in practical applications, it has less computing power than the base station side of the sending end. After receiving the pilot signal, a series of operations such as channel estimation and eigenvalue decomposition are required, which requires high computing power for terminal equipment, especially when considering AI-based channel estimation, the computing power of terminal equipment is even more demanding. High, the hardware implementation of the terminal equipment is quite difficult, and the actual terminal equipment is difficult to support the above solution.

In order to solve the above problems, an embodiment of the present invention provides a method for obtaining a reference signal. After the first communication device sends the first reference signal to the second communication device, it receives the compressed reference signal sent by the second communication device, and the compressed reference signal It is obtained by compressing and encoding the second reference signal, which is a reference signal received by the second communication device and corresponding to the first reference signal; the compressed reference signal is decoded and reconstructed to obtain the 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 the compressed reference signal to the first communication device, so that the sending end can obtain the actual pilot signal received by the receiving end, In this way, channel information more matching with the actual pilot signal is obtained.

Furthermore, since the second communication device is used as the receiving end device, in the embodiment of the present invention, it does not need to perform channel estimation, and has relatively low requirements for computing power. Therefore, when the receiving end device is a mobile phone, the computing power can be fully satisfied. Therefore, the implementation of this solution does not require high hardware requirements, and can be applied to more communication scenarios.

In the embodiment of the present invention, the involved communication device (the first communication device or the second communication device) may be a receiver or a transmitter. Optionally, the receiver may be a terminal device or a network device; the sender may also be a terminal device or a network device.

The terminal device can be a station (STAION, ST) in the WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (Session Initiation Protocol, SIP) phone, a wireless local loop (Wireless Local Loop, WLL) station, a personal digital processing (Personal Digital Assistant, PDA) devices, handheld devices with wireless communication functions, computing devices or other processing devices connected to wireless modems, vehicle-mounted devices, wearable devices, next-generation communication systems such as terminal devices in NR networks, or future Terminal equipment in the evolved public land mobile network (Public Land Mobile Network, PLMN) network, etc.

In the embodiment of the present invention, the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships, etc.); it can also be deployed in the air (such as aircraft, balloons and satellites) superior).

In the embodiment of the present invention, the terminal device may be a mobile phone (Mobile Phone), a tablet computer (Pad), a computer with a wireless transceiver function, a virtual reality (Virtual Reality, VR) terminal device, an augmented reality (Augmented Reality, AR) terminal Equipment, wireless terminal equipment in industrial control, wireless terminal equipment in self driving, wireless terminal equipment in remote medical, wireless terminal equipment in smart grid , wireless terminal equipment in transportation safety, wireless terminal equipment in smart city, or wireless terminal equipment in smart home.

As an example but not a limitation, in this embodiment of the present invention, the terminal device may also be a wearable device. Wearable devices can also be called wearable smart devices, which is a general term for the application of wearable technology to intelligently design daily wear and develop wearable devices, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not only a hardware device, but also achieve powerful functions through software support, data interaction, and cloud interaction. Generalized wearable smart devices include full-featured, large-sized, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, etc., and only focus on a certain type of application functions, and need to cooperate with other devices such as smart phones Use, such as various smart bracelets and smart jewelry for physical sign monitoring.

In the embodiment of the present invention, the network device can be a device for communicating with the mobile device, and the network device can be an access point (Access Point, AP) in WLAN, a base station (Base Transceiver Station, BTS) in GSM or CDMA , or a base station (NodeB, NB) in WCDMA, or an evolved base station (Evolutional Node B, eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and an NR network The network equipment (gNB) in the network or the network equipment in the future evolved PLMN network or the network equipment in the NTN network, etc.

As an example but not a limitation, in this embodiment of the present invention, the network device may have a mobile feature, for example, the network device may be a mobile device. Optionally, the network equipment may be a satellite or a balloon station. For example, the satellite can be a low earth orbit (low earth orbit, LEO) satellite, a medium earth orbit (medium earth orbit, MEO) satellite, a geosynchronous earth orbit (geosynchronous earth orbit, GEO) satellite, a high elliptical orbit (High Elliptical Orbit, HEO) satellite. ) Satellite etc. Optionally, the network device may also be a base station installed on land, water, and other locations.

In this embodiment of the present invention, the network device may provide services for a cell, and the terminal device communicates with the network device through the transmission resources (for example, frequency domain resources, or spectrum resources) used by the cell, and the cell may be a network device ( For example, a cell corresponding to a base station), the cell may belong to a macro base station, or may belong to a base station corresponding to a small cell (Small cell), and the small cell here may include: a metro cell (Metro cell), a micro cell (Micro cell), a pico cell ( Pico cell), Femto cell, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.

The technical solution of the embodiment of the present invention can be applied to various communication systems, such as: Global System of Mobile communication (Global System of Mobile communication, GSM) system, code division multiple access (Code Division Multiple Access, CDMA) system, broadband code division multiple access (Wideband Code Division Multiple Access, WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced long term evolution (LTE-A) system , New Radio (NR) system, evolution system of NR system, LTE (LTE-based access to unlicensed spectrum, LTE-U) system on unlicensed spectrum, NR (NR-based access to unlicensed spectrum) on unlicensed spectrum unlicensed spectrum (NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunications System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (Wireless Fidelity, WiFi), fifth-generation communication (5th-Generation, 5G) system or other communication systems, etc.

Generally speaking, the number of connections supported by traditional communication systems is limited and easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication, but also support, for example, Device to Device (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, etc. , the embodiments of the present invention may also be applied to these communication systems.

The communication system in the embodiment of the present invention may be applied to a carrier aggregation (Carrier Aggregation, CA) scenario, may also be applied to a dual connectivity (Dual Connectivity, DC) scenario, and may also be applied to an independent (Standalone, SA) network deployment scenario.

Optionally, the communication system in this embodiment of the present invention may be applied to an unlicensed spectrum, where the unlicensed spectrum may also be considered a shared spectrum; or, the communication system in this embodiment of the present invention may also be applied to a licensed spectrum, where, Licensed spectrum can also be considered as non-shared spectrum.

Optionally, the embodiments of the present invention may be applied to a non-terrestrial communication network (Non-Terrestrial Networks, NTN) system, and may also be applied to a terrestrial communication network (Terrestrial Networks, TN) system.

It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and/or" in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and/or B can mean: A exists alone, A and B exist simultaneously, and there exists alone B these three situations. In addition, the character "/" in this article generally indicates that the contextual objects are an "or" relationship.

It should be understood that the "indication" mentioned in the embodiments of the present invention may be a direct indication, may also be an indirect indication, and may also mean that there is an association relationship. For example, A indicates B, which can mean that A directly indicates B, for example, B can be obtained through A; it can also indicate that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also indicate that there is an association between A and B relation.

In the description of the embodiments of the present invention, the term "corresponding" may indicate that there is a direct correspondence or an indirect correspondence between the two, or that there is an association between the two, or that it indicates and is indicated, or configures and is indicated. configuration etc.

Optionally, the indication information in this embodiment of the present invention includes physical layer signaling such as downlink control information (Downlink Control Information, DCI), radio resource control (Radio Resource Control, RRC) signaling, and media access control unit (Media At least one of Access Control Control Element, MAC CE).

Optionally, the high-level parameters or high-level signaling in the embodiment of the present invention include at least one of radio resource control (Radio Resource Control, RRC) signaling and media access control element (Media Access Control Control Element, MAC CE) kind.

As shown in FIG. 8, an embodiment of the present invention provides a method for obtaining a reference signal, the method including:

801. The first communications device sends a first reference signal to a second communications device.

802. The second communications device receives a second reference signal.

Wherein, the second reference signal is a reference signal received by the second communication device and corresponding to the first reference signal.

During the process of sending the first reference signal from the first communication device 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 sending end. Certain loss, in the embodiment of the present invention, the signal actually received by the second communication device is called the second reference signal.

Wherein, the first reference signal is a reference signal symbol sequence. Optionally, the first reference signal includes pilot symbols and data symbols, and may be a sequence composed of pilot symbols and data symbols (also called a pilot symbol sequence), or the first reference signal includes data symbols, and may be composed of A sequence of data symbols (also known as a sequence of data symbols).

Optionally, the first reference signal is a sequence including data symbols, that is, the first reference signal may only include data symbols.

Optionally, the first reference signal is a sequence including data symbols, and at least one data symbol in the first reference signal is a pilot signal. That is, part of the data symbols (that is, at least one data symbol) in the first reference signal is used as the pilot symbol.

Optionally, the first communication device may further send a pilot signal indication to the second communication device, where the pilot signal indication is used to indicate that the at least one data symbol is used as a pilot symbol.

Optionally, the pilot signal indication may be an index of at least one data symbol.

Optionally, the first communication device is a network device, and the second communication device is a terminal device, then when the network device sends the above pilot signal indication to the terminal device, the pilot signal indication may be carried in at least one of the following messages middle:

Radio resource control RRC signaling, medium access control element MAC CE, downlink control information DCI.

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

In an optional implementation manner: the second communication device may use a traditional compression method to perform compression processing on the second reference signal to obtain a compressed reference signal.

In another optional implementation manner: the first communication device may input the compressed reference signal into the reference signal compression model; and acquire the compressed reference signal output by the reference signal compression model.

Wherein, the reference signal compression model may be a model obtained through pre-training.

Optionally, during the training process, the reference signals can be collected in advance as a training set, and the sample reference signals in the training set are input to the reference signal compression model to be trained to obtain the compressed reference signal corresponding to the sample channel information, and the decoded and repeated The compressed reference signal is constructed to obtain the target reference signal, the loss function is determined according to the target reference signal and the sample reference signal, and the initial reference signal compression model is updated according to the loss function to obtain the trained reference signal compression model.

804. The second communications device sends the compressed reference signal to the first communications device.

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

Among them, decoding reconstruction is also generally referred to as decompression.

In an optional implementation manner: the decoding and reconstruction of the compressed reference signal by the first communication device may be decompressed in a traditional decompression manner to obtain the third reference signal.

In another optional implementation manner: the first communication device inputs the compressed reference signal into the reference signal decompression model; and acquires a third reference signal output by the pilot signal decompression model.

806. The first communications device performs channel estimation on the third reference signal to obtain first channel information.

Optionally, performing channel estimation on the third reference signal to obtain the first channel information includes: inputting the third reference signal into a channel estimation model; and acquiring first channel information output by the channel estimation model.

Further, the first communication device may perform eigenvalue decomposition on the first channel information to obtain an eigenvector. These eigenvectors can be used for subsequent precoding of modulation symbols.

Based on the solution shown in FIG. 8 above, a CSI feedback solution for compressed pilot signals is provided. In this solution, the first communication device may be regarded as a sending end, and the second communication device may be regarded as a receiving end.

As shown in FIG. 9 , it is an overall signal process of a CSI feedback scheme for compressing pilot signals. The process includes: the transmitting end first inserts a pilot symbol P on the allocated physical resource block, and downlinks the pilot symbol P to the receiving end. After receiving the pilot signal Y_p, the receiving end uses the neural network to compress and encode Y_p to generate a bit stream b, and feeds back to the sending end through the feedback link. The sending end uses the neural network to decode and reconstruct the pilot signal by using the received feedback bit stream to generate the restored pilot signal Y`_p. Further, the transmitting end estimates the downlink channel through channel estimation, and obtains the estimated channel H'. Finally, for the estimated channel H`, a precoding matrix is obtained through a signal processing process such as eigenvalue decomposition, which is used for a precoding operation for subsequent downlink transmission.

The pilot signal compression and pilot signal decompression compression in the above solution can be realized through the existing AI-based pilot signal compression model and AI-based pilot signal decompression model.

In the above solutions, the channel estimation can be realized directly by using a traditional channel estimation solution, or the channel estimation can be realized by using an AI-based channel estimation model.

In the method for obtaining a reference signal provided by an embodiment of the present invention, the first communication device receives the compressed reference signal sent by the second communication device after sending the first reference signal to the second communication device, and compressing the reference signal is to compress the second reference signal The second reference signal obtained later is a reference signal received by the second communication device and corresponding to the first reference signal; the compressed reference signal is 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 the compressed reference signal to the first communication device, so that the sending end can obtain the actual pilot signal received by the receiving end, In this way, channel information more matching with the actual pilot signal is obtained.

Further, since the second communication device is used as the receiving end device, in the embodiment of the present invention, it does not need to perform channel estimation and has relatively low requirements for computing power. Therefore, when the second communication device is a mobile phone, it can fully satisfy the calculation Therefore, the implementation of this solution does not require high hardware requirements, and can be applied to more communication scenarios.

The present invention mainly aims at CSI feedback, which is the functional requirement of the communication system, and considers that after the pilot signal is received at the receiving end, the pilot signal is directly compressed and fed back, and channel estimation is performed at the sending end to obtain channel information.

Compared with the traditional codebook CSI feedback scheme, the accuracy of obtaining channel information is improved;

Compared with the existing full-channel information feedback scheme based on neural network, it solves the problem of redundant feedback;

Furthermore, the algorithm complexity requirements and computing power requirements for the terminal equipment in the current existing solutions are also alleviated.

In the method for obtaining reference signals provided by the embodiments of the present invention, it is considered that the received pilot signal is compressed and fed back at the receiving end, and the channel estimation is performed at the sending end, so the receiving end does not need to know the pilot sequence. Since both the pilot and the data are known at the transmitting end, it may be considered to design and insert the pilot more flexibly. Since this scheme considers channel estimation at the sending end, that is, 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: neural network-based pilot design scheme and data-based wireless pilot scheme.

(1) Pilot design scheme based on neural network

Optionally, after the above step 806, the method provided by the embodiment of the present invention further includes: the first communication device may input the first channel information into the first pilot design model; and obtain the first pilot output from the first pilot design model. frequency signal; the first communication device sends the first pilot signal to the second communication device.

Optionally, for the above-mentioned first pilot related 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.

Wherein, the training set includes a plurality of sample channel information.

Optionally, the above-mentioned training process of using the sample channel information in the training set to train the initial pilot design model includes:

After cyclically performing the following steps 1 to 5 one or more times, use the updated initial pilot reference model as the first pilot device model:

Step 1: Input the sample channel information in 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;

Step 2: Process the second pilot signal according to the sample channel information and noise to obtain the third pilot signal;

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

Step 4: Determine the loss function according to the target channel information and the sample channel information;

Step 5: Update the initial pilot design model according to the loss function.

Optionally, the noise may be to simulate noise in a channel between the actual sending end and the receiving end.

A plurality of sample channel information in the training set can be input to the initial pilot design model one by one, and the above-mentioned training process of using the sample channel information in the training set to train the initial pilot design model is repeated to complete the initial pilot design model. training to obtain the above-mentioned first pilot design model.

Optionally, the sample channel information in the above sample set may be historical channel information.

As shown in FIG. 10 , it is a schematic diagram of a training phase of a pilot design model. The pilot design model is an AI-based pilot design module. The input of the pilot design module is the channel information estimated last time, and the output is the pilot sequence. In the training phase, the channel H in the pre-collected training set is first sent to the pilot design module, and the output pilot sequence P is input into the AI-based channel estimation module (that is, the channel estimation model) after passing through the channel and random noise, and finally the estimated The final channel information H`, and according to the comparison between H` and H, the loss function is obtained, and the loss function is used to update the AI-based pilot reference model. After using the framework for end-to-end training, the trained based AI's pilot design module.

Further, as shown in FIG. 11 , it is a schematic diagram of an application phase of a pilot design model. The input of the AI-based pilot design module is the channel H` estimated last time by the sending end, and the pilot sequence P is obtained after using this module for pilot reference.

(2) No pilot scheme

Since the channel estimation process in the present 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 that the time-frequency resource blocks can be There is no need to insert pilot symbols.

Optionally, the first reference signal is a data symbol sequence, and at least one data symbol in the first reference signal is a pilot signal.

Optionally, in the foregoing no-pilot solution, the sending end may send a pilot signal indication to the receiving end, where the pilot signal indication is used to indicate that at least one data symbol is a pilot signal. Specifically, an index of at least one data symbol may be indicated, so that the receiving end may know that at least one data symbol is used as a pilot signal.

In the above-mentioned no-pilot solution, since there is no need to insert pilot symbols on the time-frequency resource blocks, pilot overhead can be reduced.

As shown in FIG. 12, an embodiment of the present invention provides a first communication device, and the first communication device includes:

The receiving module 1201 is configured to receive the compressed reference signal sent by the second communication device after sending the 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 corresponding to the first reference signal received by the second communication device;

The processing module 1202 is configured to decode and reconstruct the compressed reference signal to obtain a third reference signal.

Optionally, the processing module 1202 is specifically used for:

inputting the compressed reference signal into the reference signal decompression model;

A third reference signal output by the pilot signal decompression model is acquired.

Optionally, the processing module 1202 is also used for:

Perform channel estimation on the third reference signal to obtain first channel information.

Optionally, the processing module 1202 is specifically used for:

inputting the third reference signal into the channel estimation model;

Acquire first channel information output by the channel estimation model.

Optionally, the processing module 1202 is also used for:

Perform eigenvalue decomposition on the first channel information to obtain an eigenvector, and the eigenvector is used to precode the modulation symbols.

Optionally, the processing module 1202 is also used for:

inputting first channel information into a first pilot design model;

Obtaining a first pilot signal output by the first pilot design model;

Optionally, also include:

A sending module 1203, configured to send the first pilot signal to the second communication device.

Optionally, the processing module 1202 is also used for:

The initial pilot design model is trained by using the sample channel information in the training set to obtain a first pilot design model.

Optionally, the processing module 1202 is specifically used for:

Inputting the sample channel information in the training set to the initial pilot design model to obtain a second pilot signal corresponding to the sample channel information;

processing the second pilot signal according to the sample channel information and noise to obtain a third pilot signal;

performing channel estimation on the third pilot signal to obtain target channel information;

Determine the loss function according to the target channel information and the sample channel information;

Update the initial pilot design model according to the loss function;

The first pilot design model is obtained according to the updated initial pilot design model.

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

Optionally, the first reference signal includes data symbols, and at least one data symbol in the first reference signal is used as a pilot symbol.

Optionally, also include:

The sending module 1203 is configured to send a pilot signal indication to the second communication device, where the pilot signal indication is used to indicate at least one data symbol as a pilot symbol.

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

As shown in Figure 13, the embodiment of the present invention also provides a second communication device, the second communication device includes:

A receiving module 1301, configured to receive a second reference signal, where the second reference signal corresponds to the first reference signal sent by the first communication device;

A processing module 1302, configured to perform compression coding processing on the second reference signal to obtain a compressed reference signal;

A sending module 1303, configured to send the compressed reference signal to the first communication device.

Optionally, the first reference signal includes data symbols, and at least one data symbol in the first reference signal is used as a pilot signal.

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

As shown in FIG. 14 , an embodiment of the present invention also provides a schematic diagram of a hardware structure of a communication device. The communication device may include: a radio frequency (radio frequency, RF) circuit 1410, a memory 1420, a processor 1430 and other components. Wherein, the radio frequency circuit 1410 includes a receiver 1411 and a transmitter 1412 . Those skilled in the art can understand that the structure of the communication device shown in FIG. 14 does not constitute a limitation to the communication device, and may include more or less components than those shown in the illustration, or combine certain components, or arrange different components .

The RF circuit 1410 can be used for sending and receiving information or receiving and sending signals during a call. In particular, after receiving the downlink information from the base station, it is processed by the processor 1430; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit 1410 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (low noise amplifier, LNA), a duplexer, and the like. In addition, RF circuitry 1410 may also communicate with networks and other devices via wireless communications. The above wireless communication can use any communication standard or protocol, including but not limited to global system of mobile communication (global system of mobile communication, GSM), general packet radio service (general packet radio service, GPRS), code division multiple access (code division multiple access) multiple access (CDMA), wideband code division multiple access (WCDMA), long term evolution (LTE), e-mail, short message service (short messaging service, SMS), etc.

The memory 1420 can be used to store software programs and modules, and 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 . Memory 1420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, at least one application program required by a function (such as a sound playback function, an image playback function, etc.); Data created by the use of communication devices (such as audio data, phonebook, etc.), etc. In addition, the memory 1420 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

The processor 1430 is the control center, and uses various interfaces and lines to connect various parts of the entire communication device. By running or executing software programs and/or modules stored in the memory 1420, and calling data stored in the memory 1420, execution Various functions and processing data of communication equipment, so as to monitor the communication equipment as a whole. 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 processes operating systems, user interfaces, and application programs, etc. , the modem processor mainly handles wireless communications. It can be understood that, the foregoing modem processor may not be integrated into the processor 1430 .

Optionally, if the communication device shown in FIG. 14 is the first communication device, in the embodiment of the present invention, the receiver 1411 in the radio frequency circuit 1410 is used to send the first reference to the second communication device at the transmitter 1412 After receiving the compressed reference signal sent by 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 corresponding to the first reference signal received by the second communication device ;

The processor 1430 is configured to decode and reconstruct the compressed reference signal to obtain a third reference signal.

Optionally, the processor 1430 is specifically used for:

Optionally, the processor 1430 is also used for:

Optionally, the processor 1430 is specifically configured to: input the third reference signal into the channel estimation model;

Acquire first channel information output by the channel estimation model.

Optionally, the processor 1430 is also used for:

inputting first channel information into a first pilot design model;

Obtaining a first pilot signal output by the first pilot design model;

The transmitter 1412 is further configured to send the first pilot signal to the second communication device.

Optionally, the processor 1430 is also used for:

Optionally, the processor 1430 is specifically configured to: input the sample channel information in the training set to the initial pilot design model, so as to obtain the pilot symbol sequence corresponding to the sample channel information;

According to the sample channel information and noise, process the pilot symbol sequence to obtain the pilot signal;

Perform channel estimation on the pilot signal to obtain target channel information;

Update the initial pilot design model according to the loss function;

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

Optionally, also include:

The transmitter 1412 is configured to send a pilot signal indication to the second communication device, where the pilot signal indication is used to indicate at least one data symbol.

Optionally, the communication device shown in FIG. 14 is the second communication device, then in the embodiment of the present invention, the receiver 1411 in the radio frequency circuit 1410 is used to receive the second reference signal, and the second reference signal is the same as the first Corresponding to the first reference signal sent by the communication device;

The processor 1430 is configured to perform compression coding processing on the second reference signal to obtain a compressed reference signal;

The transmitter 1412 is configured to send the compressed reference signal to the first communication device.

Optionally, the receiver 1411 is further configured to receive a pilot signal indication sent by the first communication device, where the pilot signal indication is used to indicate at least one data symbol.

An embodiment of the present invention also provides a computer-readable storage medium, including: computer instructions, which, when run on a processor, cause the processor to execute various processes of the communication device in the foregoing method embodiments.

An embodiment of the present invention also provides a computer program product, including computer instructions. When the computer program product runs on a processor, the computer instructions are run to implement various processes of the communication device in the above method embodiments.

The embodiment of the present invention also provides a chip, the chip is coupled with the memory in the communication device, so that the chip calls the program instructions stored in the memory during operation, so that the communication device executes various processes of the communication device in the above method embodiments.

In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present invention are produced in whole or in part. A computer can be a general purpose computer, special purpose computer, computer network, or other programmable device. Computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, e.g. Coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that can be stored by a computer, or a data storage device such as a server, a data center, etc. integrated with one or more available media. Available media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, DVD), or semiconductor media (eg, Solid State Disk (SSD)).

The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and not necessarily Used to describe a specific sequence or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device comprising a sequence of steps or elements is not necessarily limited to the expressly listed instead, may include other steps or elements not explicitly listed or inherent to the process, method, product or apparatus.

Claims

A method for obtaining a reference signal, characterized in that it is applied to a first communication device, comprising:

After sending the first reference signal to the second communication device, receiving the compressed reference signal sent by 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 corresponding to the first reference signal received by the second communication device;

The compressed reference signal is decoded and reconstructed to obtain a third reference signal.
The method according to claim 1, wherein said decoding and reconstructing said compressed reference signal to obtain a third reference signal comprises:

inputting the compressed reference signal into a reference signal decompression model;

Acquire the third reference signal output by the pilot signal decompression model.
The method according to claim 1 or 2, characterized in that the method further comprises:

Perform channel estimation on the third reference signal to obtain first channel information.
The method according to claim 3, wherein said performing channel estimation on said third reference signal to obtain first channel information comprises:

inputting the third reference signal into a channel estimation model;

Acquiring the first channel information output by the channel estimation model.
The method according to claim 3 or 4, wherein the method further comprises:

Performing eigenvalue decomposition on the first channel information to obtain an eigenvector, where the eigenvector is used to precode modulation symbols.
The method according to claim 3, further comprising:

inputting the first channel information into a first pilot design model;

Acquiring a first pilot signal output by the first pilot design model;

sending the first pilot signal to the second communications device.
The method according to claim 6, further comprising:

Using the sample channel information in the training set, train the initial pilot design model to obtain the first pilot design model.
The method according to claim 7, wherein the training the initial pilot design model using sample channel information in the training set to obtain the first pilot design model comprises:

inputting sample channel information in the training set to the initial pilot design model to obtain a second pilot signal corresponding to the sample channel information;

processing the second pilot signal according to the sample channel information and noise to obtain a third pilot signal;

performing channel estimation on the third pilot signal to obtain target channel information;

determining a loss function according to the target channel information and the sample channel information;

updating the initial pilot design model according to the loss function;

The first pilot design model is obtained according to the updated initial pilot design model.
The method according to any one of claims 1 to 8, characterized in that,

The first reference signal includes pilot symbols and data symbols, or, the first reference signal includes data symbols.
The method according to claim 9, wherein the first reference signal includes data symbols, and at least one data symbol in the first reference signal is used as a pilot symbol.
The method according to claim 10, characterized in that the method further comprises:

sending a pilot signal indication to the second communications device, the pilot signal indication being used to indicate the at least one data symbol as a pilot symbol.
The method according to claim 11, wherein the first communication device is a network device, and the pilot signal indication is carried in at least one of the following messages:

Radio resource control RRC signaling, medium access control element MAC CE, downlink control information DCI.
A method for obtaining a reference signal, characterized in that it is applied to a second communication device, comprising:

receiving a second reference signal, the second reference signal corresponding to the first reference signal sent by the first communication device;

performing compression coding processing on the second reference signal to obtain a compressed reference signal;

The compressed reference signal is sent to the first communications device.
The method according to claim 13, wherein the first reference signal includes data symbols, and at least one data symbol in the first reference signal is used as a pilot signal.
The method according to claim 14, characterized in that the method further comprises:

receiving a pilot signal indication sent by the first communication device, where the pilot signal indication is used to indicate that the at least one data symbol is used as a pilot signal.
The method according to claim 15, wherein the first communication device is a network device, and the pilot signal indication is carried in at least one of the following messages:

Radio resource control RRC signaling, medium access control element MAC CE, downlink control information DCI.
A first communication device, characterized by comprising:

The receiver is configured to receive the compressed reference signal sent by the second communication device after sending the first reference signal to the second communication device, where the compressed reference signal is obtained by compressing and encoding the second reference signal, the The second reference signal is a reference signal received by the second communication device and corresponding to the first reference signal;

A processor, configured to decode and reconstruct the compressed reference signal to obtain a third reference signal.
The first communication device according to claim 17, wherein the processor is specifically configured to:

inputting the compressed reference signal into a reference signal decompression model;

Acquire the third reference signal output by the pilot signal decompression model.
The first communication device according to claim 17 or 18, wherein the processor is further configured to:

Perform channel estimation on the third reference signal to obtain first channel information.
The first communication device according to claim 19, wherein the processor is specifically configured to: input the third reference signal into a channel estimation model;

Acquiring the first channel information output by the channel estimation model.
The first communication device according to claim 19 or 20, wherein the processor is further configured to:

Performing eigenvalue decomposition on the first channel information to obtain an eigenvector, where the eigenvector is used to precode modulation symbols.
The first communication device according to claim 19, wherein the processor is further configured to: input the first channel information into a first pilot design model;

Acquiring a first pilot signal output by the first pilot design model;

Also includes:

A transmitter, configured to send the first pilot signal to the second communication device.
The first communication device according to claim 22, wherein the processor is further configured to:

The initial pilot design model is trained by using sample channel information in the training set to obtain the first pilot design model.
The first communication device according to claim 23, wherein the processor is specifically configured to:

inputting sample channel information in the training set to the initial pilot design model to obtain a second pilot signal corresponding to the sample channel information;

processing the second pilot signal according to the sample channel information and noise to obtain a third pilot signal;

performing channel estimation on the third pilot signal to obtain target channel information;

determining a loss function according to the target channel information and the sample channel information;

updating the initial pilot design model according to the loss function;

The first pilot design model is obtained according to the updated initial pilot design model.
The first communication device according to any one of claims 17 to 24, characterized in that,

The first reference signal includes pilot symbols and data symbols, or, the first reference signal includes data symbols.
The first communication device according to claim 25, wherein the first reference signal includes data symbols, and at least one data symbol in the first reference signal is used as a pilot symbol.
The first communication device according to claim 26, further comprising:

A transmitter, configured to send a pilot signal indication to the second communication device, where the pilot signal indication is used to indicate the at least one data symbol.
The first communication device according to claim 27, wherein the first communication device is a network device, and the pilot signal indication is carried in at least one of the following messages:

Radio resource control RRC signaling, medium access control element MAC CE, downlink control information DCI.
A second communication device, characterized by comprising:

a receiver, configured to receive a second reference signal corresponding to the first reference signal sent by the first communication device;

a processor, configured to perform compression coding processing on the second reference signal to obtain a compressed reference signal;

A transmitter, configured to send the compressed reference signal to the first communication device.
The second communication device according to claim 29, wherein the first reference signal includes data symbols, and at least one data symbol in the first reference signal is a pilot signal.
The second communication device according to claim 30, wherein the receiver is further configured to receive a pilot signal indication sent by the first communication device, and the pilot signal indication is used to indicate the at least A data symbol.
The second communication device according to claim 31, wherein the first communication device is a network device, and the pilot signal indication is carried in at least one of the following messages:

Radio resource control RRC signaling, medium access control element MAC CE, downlink control information DCI.
A first communication device, characterized by comprising:

The receiving module is configured to receive the compressed reference signal sent by the second communication device after sending the first reference signal to the second communication device, the compressed reference signal is obtained by compressing and encoding the second reference signal, the The second reference signal is a reference signal received by the second communication device and corresponding to the first reference signal;

A processing module, configured to decode and reconstruct the compressed reference signal to obtain a third reference signal.
A second communication device, characterized by comprising:

A receiving module, configured to receive a second reference signal, where the second reference signal corresponds to the first reference signal sent by the first communication device;

A processing module, configured to compress and encode the second reference signal to obtain a compressed reference signal;

A sending module, configured to send the compressed reference signal to the first communication device.
A computer-readable storage medium, characterized by comprising computer instructions, and when the computer instructions are run on a processor, the processor is made to execute the method for acquiring a reference signal according to any one of claims 1 to 16.
A computer-readable storage medium, characterized by comprising computer instructions, and when the computer instructions are run on a processor, the processor is made to execute the method for acquiring a reference signal according to any one of claims 17 to 28.