CN-119174124-B - Method, device, storage medium and chip for obtaining channel quality

Abstract

The present disclosure relates to a method, apparatus, storage medium and chip for acquiring channel quality. The method comprises the steps of enabling terminal equipment to receive pilot signals sent by network equipment through a downlink channel, obtaining a first channel matrix according to the pilot signals, compressing the first channel matrix according to a Channel State Information (CSI) compression model and Channel State Information (CSI) compression parameters to obtain a compressed target channel matrix, and sending the target channel matrix to the network equipment so that the network equipment can determine the channel quality of the downlink channel according to the target channel matrix. The system comprises a first channel matrix, a Channel State Information (CSI) compression model and target channel matrix, wherein the first channel matrix is used for representing the channel quality of a downlink channel, the CSI compression model comprises a channel encoder which comprises a plurality of sub-encoders, different sub-encoders correspond to different CSI compression parameters, and the target channel matrix is used for indicating network equipment to determine the channel quality of the downlink channel.

Inventors

• CHI LIANGANG
• CHEN DONG

Assignees

• 北京小米移动软件有限公司

Dates

Publication Date

20260508

Application Date

20220519

Claims (20)

1. 1. A method for acquiring channel quality, applied to a terminal device, the method comprising: receiving a pilot signal sent by network equipment through a downlink channel; acquiring a first channel matrix according to the pilot signal, wherein the first channel matrix is used for representing the channel quality of the downlink channel; Compressing the first channel matrix according to a Channel State Information (CSI) compression model and Channel State Information (CSI) compression parameters to obtain a compressed target channel matrix, wherein the CSI compression model comprises a channel encoder which comprises a plurality of sub-encoders; Transmitting the target channel matrix to the network equipment so that the network equipment can determine the channel quality of the downlink channel according to the target channel matrix; the obtaining the first channel matrix according to the pilot signal comprises: According to the received pilot signals, channel State Information (CSI) estimation is carried out to obtain a CSI estimation matrix; Determining the first channel matrix according to the CSI estimation matrix; The compressing the first channel matrix according to the channel state information CSI compression model and the channel state information CSI compression parameters to obtain a compressed target channel matrix includes: taking a sub-encoder corresponding to the CSI compression parameter as a first target sub-encoder; and compressing the first channel matrix through the first target sub-encoder to obtain a target channel matrix.
2. 2. The method of claim 1, wherein the CSI compression model further comprises a feature converter, wherein compressing the first channel matrix according to the channel state information CSI compression model and the channel state information CSI compression parameters to obtain a compressed target channel matrix comprises: inputting the first channel matrix into the feature converter, and extracting key features of the first channel matrix to obtain a second channel matrix representing the key features of the CSI; and compressing the second channel matrix according to the CSI compression parameters and the channel encoder to obtain the target channel matrix.
3. 3. The method of claim 2, wherein compressing the second channel matrix according to the CSI compression parameter and the channel encoder to obtain the target channel matrix comprises: taking a sub-encoder corresponding to the CSI compression parameter as a second target sub-encoder; And compressing the second channel matrix through the second target sub-encoder to obtain a target channel matrix.
4. 4. The method of claim 2, wherein the feature transformer comprises a feature extraction network, an attention mechanism network, and a feature restoration network, wherein inputting the first channel matrix into the feature transformer, performing key feature extraction on the first channel matrix, and obtaining a second channel matrix characterizing CSI key features comprises: Inputting the first channel matrix into the feature extraction network to obtain a plurality of first feature graphs; inputting the plurality of first feature maps into the attention mechanism network to obtain a second feature map, wherein the second feature map comprises key feature information in the first feature map; And inputting the second feature map into the feature reduction network to obtain a second channel matrix.
5. 5. The method of claim 4, wherein said inputting a plurality of said first feature maps into said attention mechanism network to obtain a second feature map comprises: Performing maximum pooling operation on the plurality of first feature images through the attention mechanism network to obtain a maximum pooling feature image; carrying out average pooling operation on a plurality of first feature graphs through the attention mechanism network to obtain average pooling feature graphs; and determining a second characteristic diagram according to the maximum pooling characteristic diagram and the average pooling characteristic diagram.
6. 6. The method of claim 5, wherein the attention mechanism network comprises a converged subnetwork, wherein the determining a second feature map from the maximum pooling feature map and the average pooling feature map comprises: Inputting the maximum pooling feature map and the average pooling feature map into the fusion sub-network to obtain a fused feature map; and determining a second feature map according to the fusion feature map and the first feature map.
7. 7. The method of claim 1, wherein said obtaining a first channel matrix from said pilot signals comprises: According to the pilot signal, measuring to obtain a space domain channel matrix; Transforming the airspace channel matrix into an angle time delay domain channel matrix through discrete Fourier transform; And determining the first channel matrix according to the angle time delay domain channel matrix.
8. 8. The method according to any of claims 1 to 7, wherein the CSI compression model is trained by: Acquiring a first sample channel matrix for training, wherein the first sample channel matrix is a matrix for representing the quality of the downlink channel, which is acquired by terminal equipment according to a received pilot signal; training a first target network model according to the first sample channel matrix to obtain the CSI compression model; The first target network model comprises a first target compression model and a first target decompression model, the network structure of the first target compression model is the same as that of the CSI compression model, the first target decompression model comprises a channel decoder, the channel decoder comprises a plurality of sub-decoders, and different sub-decoders correspond to different CSI compression parameters.
9. 9. The method of claim 8, wherein training the first target network model based on the first sample channel matrix comprises: Circularly executing a first model training step until a trained first target network model meets a first preset iteration stopping condition according to the first sample channel matrix and a first prediction channel matrix, and taking a first target compression model in the trained first target network model as the CSI compression model; The first model training step includes: Inputting the first sample channel matrix into the first target compression model, and compressing the first sample channel matrix through a plurality of sub-encoders to obtain a first target sample channel matrix; inputting the first target sample channel matrix into the first target decompression model, and decompressing the first target sample channel matrix through a plurality of sub-decoders to obtain a first prediction channel matrix; And under the condition that the first target network model does not meet the first preset iteration stopping condition according to the first sample channel matrix and the first prediction channel matrix, determining a first loss value according to the first sample channel matrix and the first prediction channel matrix, updating parameters of the first target network model according to the first loss value to obtain a trained first target network model, and taking the trained first target network model as a new first target network model.
10. 10. The method of claim 8, wherein the method further comprises: Acquiring first decompression model parameters corresponding to a first target decompression model in the trained first target network model; And sending the first decompression model parameters to the network equipment so as to instruct the network equipment to determine a Channel State Information (CSI) decompression model according to the first decompression model parameters, wherein the CSI decompression model is used for determining the channel quality of the downlink channel according to the target channel matrix by the network equipment.
11. 11. The method according to any one of claims 1 to 7, further comprising: Receiving a second compression model parameter sent by the network equipment; And determining a CSI compression model according to the second compression model parameters.
12. 12. The method according to any one of claims 1 to 7, further comprising: receiving a first compression parameter sent by network equipment; And determining the CSI compression parameter according to the first compression parameter.
13. 13. A method of acquiring channel quality, for use with a network device, the method comprising: Receiving a target channel matrix sent by terminal equipment, wherein the target channel matrix is obtained by compressing a first channel matrix obtained by the terminal equipment according to a Channel State Information (CSI) compression model and Channel State Information (CSI) compression parameters, and the first channel matrix is a matrix which is obtained by the terminal equipment according to pilot signals and is used for representing the channel quality of a downlink channel; Decompressing the target channel matrix according to a Channel State Information (CSI) decompression model and the CSI compression parameters to obtain a third channel matrix, wherein the CSI decompression model comprises a channel decoder, the channel decoder comprises a plurality of sub-decoders, and different sub-decoders correspond to different CSI compression parameters; And determining the channel quality of the downlink channel according to the third channel matrix.
14. 14. The method of claim 13, wherein decompressing the target channel matrix according to the channel state information CSI decompression model and the CSI compression parameters to obtain a third channel matrix comprises: Taking a sub-decoder corresponding to the CSI compression parameter as a target sub-decoder; Decompressing the target channel matrix through the target sub-decoder to obtain a fourth channel matrix; and determining the third channel matrix according to the fourth channel matrix.
15. 15. The method of claim 14, wherein the CSI decompression model further comprises a CSI reconstruction module, and wherein said determining the third channel matrix from the fourth channel matrix comprises: and inputting the fourth channel matrix into the CSI reconstruction module to obtain the third channel matrix.
16. 16. The method according to any of claims 13 to 15, wherein the CSI decompression model is trained by: acquiring a second sample channel matrix for training, wherein the second sample channel matrix is a matrix for representing the quality of the downlink channel, which is acquired by the terminal equipment according to the received pilot signal; Training a second target network model according to the second sample channel matrix to obtain the CSI decompression model; The second target network model comprises a second target compression model and a second target decompression model, the network structure of the second target decompression model is the same as that of the CSI decompression model, the second target compression model comprises a channel encoder, the channel encoder comprises a plurality of sub-encoders, and different sub-encoders correspond to different CSI compression parameters.
17. 17. The method of claim 16, wherein training a second target network model based on the second sample channel matrix comprises: Circularly executing a second model training step until a trained second target network model meets a second preset iteration stopping condition according to the second sample channel matrix and a second prediction channel matrix, and taking a second target decompression model in the trained second target network model as the CSI decompression model; The second model training step includes: inputting the second sample channel matrix into the second target compression model, and compressing the second sample channel matrix through a plurality of sub-encoders to obtain a second target sample channel matrix; Inputting the second target sample channel matrix into the second target decompression model, and decompressing the second target sample channel matrix through a plurality of sub-decoders to obtain a second prediction channel matrix; And under the condition that the second target network model does not meet the second preset iteration stopping condition according to the second sample channel matrix and the second prediction channel matrix, determining a second loss value according to the second sample channel matrix and the second prediction channel matrix, updating parameters of the second target network model according to the second loss value to obtain a trained second target network model, and taking the trained second target network model as a new second target network model.
18. 18. The method of claim 16, wherein the method further comprises: Acquiring second compression model parameters corresponding to a second target compression model in the trained second target network model; And sending the second compression model parameters to the terminal equipment so as to instruct the terminal equipment to determine a CSI compression model according to the second compression model parameters, wherein the CSI compression model is used for the terminal equipment to acquire a target channel matrix according to the first channel matrix.
19. 19. The method according to any one of claims 13 to 15, further comprising: receiving a first decompression model parameter sent by the terminal equipment; And determining a CSI decompression model according to the first decompression model parameters.
20. 20. The method according to any one of claims 13 to 15, further comprising: Determining a first compression parameter according to the CSI compression parameter; and sending the first compression parameter to the terminal equipment.

Description

Method, device, storage medium and chip for obtaining channel quality Technical Field The present disclosure relates to the field of communications technologies, and in particular, to a method, an apparatus, a storage medium, and a chip for obtaining channel quality. Background As a key technology of 5G (the 5th GenerationMobile Communication Technology, fifth generation mobile communication system), mMIMO (massive Multiple-Input Multiple-Output) technology has been widely studied and used in the communication field in recent years. By adopting a centralized or distributed method to deploy a large number of antennas at the transmitting end, the mMIMO system has good performance in the aspects of system stability, energy utilization rate and anti-interference capability. In order to fully exploit the advantages of mMIMO systems, accurate CSI (ChannelStateInformation ) needs to be obtained at the transmitting end. For example, the terminal device may report CSI information to the network device, so that the network device obtains channel quality of the downlink channel, and selects an appropriate modulation and coding scheme for downlink transmission according to the channel quality, thereby improving performance of data transmission. However, in mMIMO, the number of antennas is continuously increased, and the information contained in the CSI is more and more abundant, so that the resource overhead for reporting the CSI is more and more large. In the related art, in order to reduce the CSI reporting overhead, a CSI compression technique based on discrete fourier transform (DiscreteFouriertransform, DFT) may be used, and the terminal device performs CSI compression and then reports the CSI to the network device. However, the accuracy of channel quality acquired by the network device is reduced by the CSI compression reporting, and particularly, the accuracy difference of the CSI compressed under different scenes is large, which affects the data transmission efficiency. Disclosure of Invention To overcome the above-described problems in the related art, the present disclosure provides a method, apparatus, storage medium, and chip for acquiring channel quality. According to a first aspect of embodiments of the present disclosure, there is provided a method for obtaining channel quality, applied to a terminal device, the method including: receiving a pilot signal sent by network equipment through a downlink channel; acquiring a first channel matrix according to the pilot signal, wherein the first channel matrix is used for representing the channel quality of the downlink channel; Compressing the first channel matrix according to a Channel State Information (CSI) compression model and Channel State Information (CSI) compression parameters to obtain a compressed target channel matrix, wherein the CSI compression model comprises a channel encoder which comprises a plurality of sub-encoders; And sending the target channel matrix to the network equipment so that the network equipment can acquire the channel quality of the downlink channel according to the target channel matrix. According to a second aspect of embodiments of the present disclosure, there is provided a method of acquiring channel quality, applied to a network device, the method comprising: receiving a target channel matrix sent by terminal equipment, wherein the target channel matrix is obtained by compressing a first channel matrix according to a Channel State Information (CSI) compression model and Channel State Information (CSI) compression parameters by the terminal equipment, and the first channel matrix is a matrix which is obtained by the terminal equipment according to a pilot signal and is used for representing the channel quality of a downlink channel; Decompressing the target channel matrix according to a Channel State Information (CSI) decompression model and the CSI compression parameters to obtain a third channel matrix, wherein the CSI decompression model comprises a channel decoder, the channel decoder comprises a plurality of sub-decoders, and different sub-decoders correspond to different CSI compression parameters; And determining the channel quality of the downlink channel according to the third channel matrix. According to a third aspect of embodiments of the present disclosure, there is provided an apparatus for acquiring channel quality, applied to a terminal device, the apparatus including: The first receiving module is configured to receive a pilot signal sent by the network equipment through a downlink channel; the first matrix acquisition module is configured to acquire a first channel matrix according to the pilot signals, wherein the first channel matrix is used for representing the channel quality of the downlink channel; The system comprises a target matrix acquisition module, a first channel matrix acquisition module and a second channel matrix acquisition module, wherein the target matrix acquisition module is configured